From 0b7c01533aa9f4a228d07d2768d084acb3a387bc Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:39 -0400 Subject: NFS: add a struct nfs_commit_data to replace nfs_write_data in commits Commits don't need the vectors of pages, etc. that writes do. Split out a separate structure for the commit operation. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 4 ++-- include/linux/nfs_xdr.h | 45 ++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 44 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 52a1bdb4ee2b..d5d68f322bf0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -552,8 +552,8 @@ extern int nfs_wb_page(struct inode *inode, struct page* page); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_write_data *nfs_commitdata_alloc(void); -extern void nfs_commit_free(struct nfs_write_data *wdata); +extern struct nfs_commit_data *nfs_commitdata_alloc(void); +extern void nfs_commit_free(struct nfs_commit_data *data); #else static inline int nfs_commit_inode(struct inode *inode, int how) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7ba3551a0414..8fb036a0d489 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -518,6 +518,24 @@ struct nfs_writeres { struct nfs4_sequence_res seq_res; }; +/* + * Arguments to the commit call. + */ +struct nfs_commitargs { + struct nfs_fh *fh; + __u64 offset; + __u32 count; + const u32 *bitmask; + struct nfs4_sequence_args seq_args; +}; + +struct nfs_commitres { + struct nfs_fattr *fattr; + struct nfs_writeverf *verf; + const struct nfs_server *server; + struct nfs4_sequence_res seq_res; +}; + /* * Common arguments to the unlink call */ @@ -1171,6 +1189,8 @@ struct nfs_read_data { struct page *page_array[NFS_PAGEVEC_SIZE]; }; +struct nfs_direct_req; + struct nfs_write_data { struct rpc_task task; struct inode *inode; @@ -1186,7 +1206,6 @@ struct nfs_write_data { struct nfs_writeres res; /* result struct */ struct pnfs_layout_segment *lseg; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_commit_index; const struct rpc_call_ops *mds_ops; int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); #ifdef CONFIG_NFS_V4 @@ -1197,6 +1216,25 @@ struct nfs_write_data { struct page *page_array[NFS_PAGEVEC_SIZE]; }; +struct nfs_commit_data { + struct rpc_task task; + struct inode *inode; + struct rpc_cred *cred; + struct nfs_fattr fattr; + struct nfs_writeverf verf; + struct list_head pages; /* Coalesced requests we wish to flush */ + struct list_head list; /* lists of struct nfs_write_data */ + struct nfs_direct_req *dreq; /* O_DIRECT request */ + struct nfs_commitargs args; /* argument struct */ + struct nfs_commitres res; /* result struct */ + struct nfs_open_context *context; + struct pnfs_layout_segment *lseg; + struct nfs_client *ds_clp; /* pNFS data server */ + int ds_commit_index; + const struct rpc_call_ops *mds_ops; + int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); +}; + struct nfs_unlinkdata { struct hlist_node list; struct nfs_removeargs args; @@ -1277,8 +1315,9 @@ struct nfs_rpc_ops { void (*write_setup) (struct nfs_write_data *, struct rpc_message *); void (*write_rpc_prepare)(struct rpc_task *, struct nfs_write_data *); int (*write_done) (struct rpc_task *, struct nfs_write_data *); - void (*commit_setup) (struct nfs_write_data *, struct rpc_message *); - int (*commit_done) (struct rpc_task *, struct nfs_write_data *); + void (*commit_setup) (struct nfs_commit_data *, struct rpc_message *); + void (*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *); + int (*commit_done) (struct rpc_task *, struct nfs_commit_data *); int (*lock)(struct file *, int, struct file_lock *); int (*lock_check_bounds)(const struct file_lock *); void (*clear_acl_cache)(struct inode *); -- cgit v1.2.3 From cd841605f7a721878d8a2d1362484723d8abf569 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:44 -0400 Subject: NFS: create common nfs_pgio_header for both read and write In order to avoid duplicating all the data in nfs_read_data whenever we split it up into multiple RPC calls (either due to a short read result or due to rsize < PAGE_SIZE), we split out the bits that are the same per RPC call into a separate "header" structure. The goal this patch moves towards is to have a single header refcounted by several rpc_data structures. Thus, want to always refer from rpc_data to the header, and not the other way. This patch comes close to that ideal, but the directio code currently needs some special casing, isolated in the nfs_direct_[read_write]hdr_release() functions. This will be dealt with in a future patch. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.c | 79 +++++++++++++++-------------- fs/nfs/direct.c | 73 ++++++++++++++++++--------- fs/nfs/internal.h | 4 ++ fs/nfs/nfs3proc.c | 14 ++++-- fs/nfs/nfs4filelayout.c | 40 ++++++++------- fs/nfs/nfs4proc.c | 44 ++++++++++------- fs/nfs/objlayout/objio_osd.c | 16 +++--- fs/nfs/objlayout/objlayout.c | 19 ++++--- fs/nfs/pnfs.c | 102 ++++++++++++++++++++++---------------- fs/nfs/proc.c | 10 ++-- fs/nfs/read.c | 89 +++++++++++++++++++-------------- fs/nfs/write.c | 104 ++++++++++++++++++++++----------------- include/linux/nfs_fs.h | 12 ----- include/linux/nfs_xdr.h | 48 ++++++++++-------- 14 files changed, 376 insertions(+), 278 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 7f6a23f0244e..7a482517f4c6 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -187,7 +187,6 @@ static void bl_end_io_read(struct bio *bio, int err) struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct nfs_read_data *rdata = (struct nfs_read_data *)par->data; do { struct page *page = bvec->bv_page; @@ -198,9 +197,12 @@ static void bl_end_io_read(struct bio *bio, int err) SetPageUptodate(page); } while (bvec >= bio->bi_io_vec); if (!uptodate) { - if (!rdata->pnfs_error) - rdata->pnfs_error = -EIO; - pnfs_set_lo_fail(rdata->lseg); + struct nfs_read_data *rdata = par->data; + struct nfs_pgio_header *header = rdata->header; + + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -221,7 +223,7 @@ bl_end_par_io_read(void *data, int unused) { struct nfs_read_data *rdata = data; - rdata->task.tk_status = rdata->pnfs_error; + rdata->task.tk_status = rdata->header->pnfs_error; INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup); schedule_work(&rdata->task.u.tk_work); } @@ -229,6 +231,7 @@ bl_end_par_io_read(void *data, int unused) static enum pnfs_try_status bl_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *header = rdata->header; int i, hole; struct bio *bio = NULL; struct pnfs_block_extent *be = NULL, *cow_read = NULL; @@ -256,10 +259,10 @@ bl_read_pagelist(struct nfs_read_data *rdata) bl_put_extent(cow_read); bio = bl_submit_bio(READ, bio); /* Get the next one */ - be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg), + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read); if (!be) { - rdata->pnfs_error = -EIO; + header->pnfs_error = -EIO; goto out; } extent_length = be->be_length - @@ -286,7 +289,7 @@ bl_read_pagelist(struct nfs_read_data *rdata) isect, pages[i], be_read, bl_end_io_read, par); if (IS_ERR(bio)) { - rdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } @@ -294,9 +297,9 @@ bl_read_pagelist(struct nfs_read_data *rdata) isect += PAGE_CACHE_SECTORS; extent_length -= PAGE_CACHE_SECTORS; } - if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) { + if ((isect << SECTOR_SHIFT) >= header->inode->i_size) { rdata->res.eof = 1; - rdata->res.count = rdata->inode->i_size - f_offset; + rdata->res.count = header->inode->i_size - f_offset; } else { rdata->res.count = (isect << SECTOR_SHIFT) - f_offset; } @@ -345,7 +348,6 @@ static void bl_end_io_write_zero(struct bio *bio, int err) struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; do { struct page *page = bvec->bv_page; @@ -358,9 +360,12 @@ static void bl_end_io_write_zero(struct bio *bio, int err) } while (bvec >= bio->bi_io_vec); if (unlikely(!uptodate)) { - if (!wdata->pnfs_error) - wdata->pnfs_error = -EIO; - pnfs_set_lo_fail(wdata->lseg); + struct nfs_write_data *data = par->data; + struct nfs_pgio_header *header = data->header; + + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -370,12 +375,13 @@ static void bl_end_io_write(struct bio *bio, int err) { struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; + struct nfs_write_data *data = par->data; + struct nfs_pgio_header *header = data->header; if (!uptodate) { - if (!wdata->pnfs_error) - wdata->pnfs_error = -EIO; - pnfs_set_lo_fail(wdata->lseg); + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -391,9 +397,9 @@ static void bl_write_cleanup(struct work_struct *work) dprintk("%s enter\n", __func__); task = container_of(work, struct rpc_task, u.tk_work); wdata = container_of(task, struct nfs_write_data, task); - if (likely(!wdata->pnfs_error)) { + if (likely(!wdata->header->pnfs_error)) { /* Marks for LAYOUTCOMMIT */ - mark_extents_written(BLK_LSEG2EXT(wdata->lseg), + mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg), wdata->args.offset, wdata->args.count); } pnfs_ld_write_done(wdata); @@ -404,12 +410,12 @@ static void bl_end_par_io_write(void *data, int num_se) { struct nfs_write_data *wdata = data; - if (unlikely(wdata->pnfs_error)) { - bl_free_short_extents(&BLK_LSEG2EXT(wdata->lseg)->bl_inval, + if (unlikely(wdata->header->pnfs_error)) { + bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval, num_se); } - wdata->task.tk_status = wdata->pnfs_error; + wdata->task.tk_status = wdata->header->pnfs_error; wdata->verf.committed = NFS_FILE_SYNC; INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup); schedule_work(&wdata->task.u.tk_work); @@ -540,6 +546,7 @@ check_page: static enum pnfs_try_status bl_write_pagelist(struct nfs_write_data *wdata, int sync) { + struct nfs_pgio_header *header = wdata->header; int i, ret, npg_zero, pg_index, last = 0; struct bio *bio = NULL; struct pnfs_block_extent *be = NULL, *cow_read = NULL; @@ -552,7 +559,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) pgoff_t index; u64 temp; int npg_per_block = - NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; + NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; dprintk("%s enter, %Zu@%lld\n", __func__, count, offset); /* At this point, wdata->pages is a (sequential) list of nfs_pages. @@ -566,7 +573,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) /* At this point, have to be more careful with error handling */ isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT); - be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read); + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read); if (!be || !is_writable(be, isect)) { dprintk("%s no matching extents!\n", __func__); goto out_mds; @@ -597,10 +604,10 @@ fill_invalid_ext: dprintk("%s zero %dth page: index %lu isect %llu\n", __func__, npg_zero, index, (unsigned long long)isect); - page = bl_find_get_zeroing_page(wdata->inode, index, + page = bl_find_get_zeroing_page(header->inode, index, cow_read); if (unlikely(IS_ERR(page))) { - wdata->pnfs_error = PTR_ERR(page); + header->pnfs_error = PTR_ERR(page); goto out; } else if (page == NULL) goto next_page; @@ -612,7 +619,7 @@ fill_invalid_ext: __func__, ret); end_page_writeback(page); page_cache_release(page); - wdata->pnfs_error = ret; + header->pnfs_error = ret; goto out; } if (likely(!bl_push_one_short_extent(be->be_inval))) @@ -620,11 +627,11 @@ fill_invalid_ext: else { end_page_writeback(page); page_cache_release(page); - wdata->pnfs_error = -ENOMEM; + header->pnfs_error = -ENOMEM; goto out; } /* FIXME: This should be done in bi_end_io */ - mark_extents_written(BLK_LSEG2EXT(wdata->lseg), + mark_extents_written(BLK_LSEG2EXT(header->lseg), page->index << PAGE_CACHE_SHIFT, PAGE_CACHE_SIZE); @@ -632,7 +639,7 @@ fill_invalid_ext: isect, page, be, bl_end_io_write_zero, par); if (IS_ERR(bio)) { - wdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } @@ -653,10 +660,10 @@ next_page: bl_put_extent(be); bio = bl_submit_bio(WRITE, bio); /* Get the next one */ - be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, NULL); if (!be || !is_writable(be, isect)) { - wdata->pnfs_error = -EINVAL; + header->pnfs_error = -EINVAL; goto out; } if (be->be_state == PNFS_BLOCK_INVALID_DATA) { @@ -664,7 +671,7 @@ next_page: be->be_inval))) par->bse_count++; else { - wdata->pnfs_error = -ENOMEM; + header->pnfs_error = -ENOMEM; goto out; } } @@ -677,7 +684,7 @@ next_page: if (unlikely(ret)) { dprintk("%s bl_mark_sectors_init fail %d\n", __func__, ret); - wdata->pnfs_error = ret; + header->pnfs_error = ret; goto out; } } @@ -685,7 +692,7 @@ next_page: isect, pages[i], be, bl_end_io_write, par); if (IS_ERR(bio)) { - wdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index fb7fbaa79c20..56176af1436f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -242,7 +242,7 @@ static void nfs_direct_read_release(void *calldata) { struct nfs_read_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req; + struct nfs_direct_req *dreq = (struct nfs_direct_req *)data->header->req; int status = data->task.tk_status; spin_lock(&dreq->lock); @@ -269,6 +269,15 @@ static const struct rpc_call_ops nfs_read_direct_ops = { .rpc_release = nfs_direct_read_release, }; +static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr) +{ + struct nfs_read_data *data = &rhdr->rpc_data; + + if (data->pagevec != data->page_array) + kfree(data->pagevec); + nfs_readhdr_free(&rhdr->header); +} + /* * For each rsize'd chunk of the user's buffer, dispatch an NFS READ * operation. If nfs_readdata_alloc() or get_user_pages() fails, @@ -301,6 +310,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, ssize_t started = 0; do { + struct nfs_read_header *rhdr; struct nfs_read_data *data; size_t bytes; @@ -308,23 +318,24 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, bytes = min(rsize,count); result = -ENOMEM; - data = nfs_readdata_alloc(nfs_page_array_len(pgbase, bytes)); - if (unlikely(!data)) + rhdr = nfs_readhdr_alloc(nfs_page_array_len(pgbase, bytes)); + if (unlikely(!rhdr)) break; + data = &rhdr->rpc_data; down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, data->npages, 1, 0, data->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { - nfs_readdata_free(data); + nfs_direct_readhdr_release(rhdr); break; } if ((unsigned)result < data->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { nfs_direct_release_pages(data->pagevec, result); - nfs_readdata_free(data); + nfs_direct_readhdr_release(rhdr); break; } bytes -= pgbase; @@ -333,9 +344,9 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, get_dreq(dreq); - data->req = (struct nfs_page *) dreq; - data->inode = inode; - data->cred = msg.rpc_cred; + rhdr->header.req = (struct nfs_page *) dreq; + rhdr->header.inode = inode; + rhdr->header.cred = msg.rpc_cred; data->args.fh = NFS_FH(inode); data->args.context = get_nfs_open_context(ctx); data->args.lock_context = dreq->l_ctx; @@ -447,13 +458,23 @@ out: return result; } +static void nfs_direct_writehdr_release(struct nfs_write_header *whdr) +{ + struct nfs_write_data *data = &whdr->rpc_data; + + if (data->pagevec != data->page_array) + kfree(data->pagevec); + nfs_writehdr_free(&whdr->header); +} + static void nfs_direct_free_writedata(struct nfs_direct_req *dreq) { while (!list_empty(&dreq->rewrite_list)) { - struct nfs_write_data *data = list_entry(dreq->rewrite_list.next, struct nfs_write_data, pages); - list_del(&data->pages); - nfs_direct_release_pages(data->pagevec, data->npages); - nfs_writedata_free(data); + struct nfs_pgio_header *hdr = list_entry(dreq->rewrite_list.next, struct nfs_pgio_header, pages); + struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); + list_del(&hdr->pages); + nfs_direct_release_pages(whdr->rpc_data.pagevec, whdr->rpc_data.npages); + nfs_direct_writehdr_release(whdr); } } @@ -463,6 +484,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) struct inode *inode = dreq->inode; struct list_head *p; struct nfs_write_data *data; + struct nfs_pgio_header *hdr; struct rpc_task *task; struct rpc_message msg = { .rpc_cred = dreq->ctx->cred, @@ -479,7 +501,8 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) get_dreq(dreq); list_for_each(p, &dreq->rewrite_list) { - data = list_entry(p, struct nfs_write_data, pages); + hdr = list_entry(p, struct nfs_pgio_header, pages); + data = &(container_of(hdr, struct nfs_write_header, header))->rpc_data; get_dreq(dreq); @@ -652,7 +675,8 @@ static void nfs_direct_write_result(struct rpc_task *task, void *calldata) static void nfs_direct_write_release(void *calldata) { struct nfs_write_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req; + struct nfs_pgio_header *hdr = data->header; + struct nfs_direct_req *dreq = (struct nfs_direct_req *) hdr->req; int status = data->task.tk_status; spin_lock(&dreq->lock); @@ -684,7 +708,7 @@ out_unlock: spin_unlock(&dreq->lock); if (put_dreq(dreq)) - nfs_direct_write_complete(dreq, data->inode); + nfs_direct_write_complete(dreq, hdr->inode); } static const struct rpc_call_ops nfs_write_direct_ops = { @@ -725,6 +749,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, ssize_t started = 0; do { + struct nfs_write_header *whdr; struct nfs_write_data *data; size_t bytes; @@ -732,23 +757,25 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, bytes = min(wsize,count); result = -ENOMEM; - data = nfs_writedata_alloc(nfs_page_array_len(pgbase, bytes)); - if (unlikely(!data)) + whdr = nfs_writehdr_alloc(nfs_page_array_len(pgbase, bytes)); + if (unlikely(!whdr)) break; + data = &whdr->rpc_data; + down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, data->npages, 0, 0, data->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { - nfs_writedata_free(data); + nfs_direct_writehdr_release(whdr); break; } if ((unsigned)result < data->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { nfs_direct_release_pages(data->pagevec, result); - nfs_writedata_free(data); + nfs_direct_writehdr_release(whdr); break; } bytes -= pgbase; @@ -757,11 +784,11 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, get_dreq(dreq); - list_move_tail(&data->pages, &dreq->rewrite_list); + list_move_tail(&whdr->header.pages, &dreq->rewrite_list); - data->req = (struct nfs_page *) dreq; - data->inode = inode; - data->cred = msg.rpc_cred; + whdr->header.req = (struct nfs_page *) dreq; + whdr->header.inode = inode; + whdr->header.cred = msg.rpc_cred; data->args.fh = NFS_FH(inode); data->args.context = ctx; data->args.lock_context = dreq->l_ctx; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 650127fd24bb..7dc9be1a6e1a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -296,6 +296,8 @@ extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh); struct nfs_pageio_descriptor; /* read.c */ +extern struct nfs_read_header *nfs_readhdr_alloc(unsigned int npages); +extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); extern int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops); @@ -309,6 +311,8 @@ extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); /* write.c */ +extern struct nfs_write_header *nfs_writehdr_alloc(unsigned int npages); +extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct list_head *head); extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index b1daca7f0f7b..56dcefc2f3f7 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -811,11 +811,13 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data) { - if (nfs3_async_handle_jukebox(task, data->inode)) + struct inode *inode = data->header->inode; + + if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; - nfs_invalidate_atime(data->inode); - nfs_refresh_inode(data->inode, &data->fattr); + nfs_invalidate_atime(inode); + nfs_refresh_inode(inode, &data->fattr); return 0; } @@ -831,10 +833,12 @@ static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data) { - if (nfs3_async_handle_jukebox(task, data->inode)) + struct inode *inode = data->header->inode; + + if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; if (task->tk_status >= 0) - nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr); + nfs_post_op_update_inode_force_wcc(inode, data->res.fattr); return 0; } diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index c536328557cb..ad1d68013a5b 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -148,6 +148,7 @@ wait_on_recovery: static int filelayout_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) { + struct nfs_pgio_header *hdr = data->header; int reset = 0; dprintk("%s DS read\n", __func__); @@ -157,7 +158,7 @@ static int filelayout_read_done_cb(struct rpc_task *task, dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", __func__, data->ds_clp, data->ds_clp->cl_session); if (reset) { - pnfs_set_lo_fail(data->lseg); + pnfs_set_lo_fail(hdr->lseg); nfs4_reset_read(task, data); } rpc_restart_call_prepare(task); @@ -175,13 +176,15 @@ static int filelayout_read_done_cb(struct rpc_task *task, static void filelayout_set_layoutcommit(struct nfs_write_data *wdata) { - if (FILELAYOUT_LSEG(wdata->lseg)->commit_through_mds || + struct nfs_pgio_header *hdr = wdata->header; + + if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds || wdata->res.verf->committed == NFS_FILE_SYNC) return; pnfs_set_layoutcommit(wdata); - dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino, - (unsigned long) NFS_I(wdata->inode)->layout->plh_lwb); + dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, + (unsigned long) NFS_I(hdr->inode)->layout->plh_lwb); } /* @@ -210,27 +213,28 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data) dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); /* Note this may cause RPC to be resent */ - rdata->mds_ops->rpc_call_done(task, data); + rdata->header->mds_ops->rpc_call_done(task, data); } static void filelayout_read_count_stats(struct rpc_task *task, void *data) { struct nfs_read_data *rdata = data; - rpc_count_iostats(task, NFS_SERVER(rdata->inode)->client->cl_metrics); + rpc_count_iostats(task, NFS_SERVER(rdata->header->inode)->client->cl_metrics); } static void filelayout_read_release(void *data) { struct nfs_read_data *rdata = data; - put_lseg(rdata->lseg); - rdata->mds_ops->rpc_release(data); + put_lseg(rdata->header->lseg); + rdata->header->mds_ops->rpc_release(data); } static int filelayout_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) { + struct nfs_pgio_header *hdr = data->header; int reset = 0; if (filelayout_async_handle_error(task, data->args.context->state, @@ -238,7 +242,7 @@ static int filelayout_write_done_cb(struct rpc_task *task, dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", __func__, data->ds_clp, data->ds_clp->cl_session); if (reset) { - pnfs_set_lo_fail(data->lseg); + pnfs_set_lo_fail(hdr->lseg); nfs4_reset_write(task, data); } rpc_restart_call_prepare(task); @@ -297,22 +301,22 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data) struct nfs_write_data *wdata = data; /* Note this may cause RPC to be resent */ - wdata->mds_ops->rpc_call_done(task, data); + wdata->header->mds_ops->rpc_call_done(task, data); } static void filelayout_write_count_stats(struct rpc_task *task, void *data) { struct nfs_write_data *wdata = data; - rpc_count_iostats(task, NFS_SERVER(wdata->inode)->client->cl_metrics); + rpc_count_iostats(task, NFS_SERVER(wdata->header->inode)->client->cl_metrics); } static void filelayout_write_release(void *data) { struct nfs_write_data *wdata = data; - put_lseg(wdata->lseg); - wdata->mds_ops->rpc_release(data); + put_lseg(wdata->header->lseg); + wdata->header->mds_ops->rpc_release(data); } static void filelayout_commit_prepare(struct rpc_task *task, void *data) @@ -377,7 +381,8 @@ static const struct rpc_call_ops filelayout_commit_call_ops = { static enum pnfs_try_status filelayout_read_pagelist(struct nfs_read_data *data) { - struct pnfs_layout_segment *lseg = data->lseg; + struct nfs_pgio_header *hdr = data->header; + struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; loff_t offset = data->args.offset; u32 j, idx; @@ -385,7 +390,7 @@ filelayout_read_pagelist(struct nfs_read_data *data) int status; dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", - __func__, data->inode->i_ino, + __func__, hdr->inode->i_ino, data->args.pgbase, (size_t)data->args.count, offset); if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags)) @@ -423,7 +428,8 @@ filelayout_read_pagelist(struct nfs_read_data *data) static enum pnfs_try_status filelayout_write_pagelist(struct nfs_write_data *data, int sync) { - struct pnfs_layout_segment *lseg = data->lseg; + struct nfs_pgio_header *hdr = data->header; + struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; loff_t offset = data->args.offset; u32 j, idx; @@ -445,7 +451,7 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) return PNFS_NOT_ATTEMPTED; } dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s\n", __func__, - data->inode->i_ino, sync, (size_t) data->args.count, offset, + hdr->inode->i_ino, sync, (size_t) data->args.count, offset, ds->ds_remotestr); data->write_done_cb = filelayout_write_done_cb; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index cc04b6e409ed..5375862075de 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3336,12 +3336,12 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, void __nfs4_read_done_cb(struct nfs_read_data *data) { - nfs_invalidate_atime(data->inode); + nfs_invalidate_atime(data->header->inode); } static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) { - struct nfs_server *server = NFS_SERVER(data->inode); + struct nfs_server *server = NFS_SERVER(data->header->inode); if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) { rpc_restart_call_prepare(task); @@ -3376,7 +3376,7 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) { - if (nfs4_setup_sequence(NFS_SERVER(data->inode), + if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, task)) @@ -3387,22 +3387,25 @@ static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da /* Reset the the nfs_read_data to send the read to the MDS. */ void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data) { + struct nfs_pgio_header *hdr = data->header; + struct inode *inode = hdr->inode; + dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(data->lseg); - data->lseg = NULL; + put_lseg(hdr->lseg); + hdr->lseg = NULL; + data->ds_clp = NULL; /* offsets will differ in the dense stripe case */ data->args.offset = data->mds_offset; - data->ds_clp = NULL; - data->args.fh = NFS_FH(data->inode); + data->args.fh = NFS_FH(inode); data->read_done_cb = nfs4_read_done_cb; - task->tk_ops = data->mds_ops; - rpc_task_reset_client(task, NFS_CLIENT(data->inode)); + task->tk_ops = hdr->mds_ops; + rpc_task_reset_client(task, NFS_CLIENT(inode)); } EXPORT_SYMBOL_GPL(nfs4_reset_read); static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) { - struct inode *inode = data->inode; + struct inode *inode = data->header->inode; if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) { rpc_restart_call_prepare(task); @@ -3426,25 +3429,28 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data) /* Reset the the nfs_write_data to send the write to the MDS. */ void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data) { + struct nfs_pgio_header *hdr = data->header; + struct inode *inode = hdr->inode; + dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(data->lseg); - data->lseg = NULL; - data->ds_clp = NULL; + put_lseg(hdr->lseg); + hdr->lseg = NULL; + data->ds_clp = NULL; data->write_done_cb = nfs4_write_done_cb; - data->args.fh = NFS_FH(data->inode); + data->args.fh = NFS_FH(inode); data->args.bitmask = data->res.server->cache_consistency_bitmask; data->args.offset = data->mds_offset; data->res.fattr = &data->fattr; - task->tk_ops = data->mds_ops; - rpc_task_reset_client(task, NFS_CLIENT(data->inode)); + task->tk_ops = hdr->mds_ops; + rpc_task_reset_client(task, NFS_CLIENT(inode)); } EXPORT_SYMBOL_GPL(nfs4_reset_write); static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg) { - struct nfs_server *server = NFS_SERVER(data->inode); + struct nfs_server *server = NFS_SERVER(data->header->inode); - if (data->lseg) { + if (data->header->lseg) { data->args.bitmask = NULL; data->res.fattr = NULL; } else @@ -3460,7 +3466,7 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) { - if (nfs4_setup_sequence(NFS_SERVER(data->inode), + if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, task)) diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 4bff4a3dab46..fbf4874ec252 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -440,11 +440,12 @@ static void _read_done(struct ore_io_state *ios, void *private) int objio_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *hdr = rdata->header; struct objio_state *objios; int ret; - ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout, true, - rdata->lseg, rdata->args.pages, rdata->args.pgbase, + ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true, + hdr->lseg, rdata->args.pages, rdata->args.pgbase, rdata->args.offset, rdata->args.count, rdata, GFP_KERNEL, &objios); if (unlikely(ret)) @@ -483,12 +484,12 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) { struct objio_state *objios = priv; struct nfs_write_data *wdata = objios->oir.rpcdata; + struct address_space *mapping = wdata->header->inode->i_mapping; pgoff_t index = offset / PAGE_SIZE; - struct page *page = find_get_page(wdata->inode->i_mapping, index); + struct page *page = find_get_page(mapping, index); if (!page) { - page = find_or_create_page(wdata->inode->i_mapping, - index, GFP_NOFS); + page = find_or_create_page(mapping, index, GFP_NOFS); if (unlikely(!page)) { dprintk("%s: grab_cache_page Failed index=0x%lx\n", __func__, index); @@ -518,11 +519,12 @@ static const struct _ore_r4w_op _r4w_op = { int objio_write_pagelist(struct nfs_write_data *wdata, int how) { + struct nfs_pgio_header *hdr = wdata->header; struct objio_state *objios; int ret; - ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout, false, - wdata->lseg, wdata->args.pages, wdata->args.pgbase, + ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false, + hdr->lseg, wdata->args.pages, wdata->args.pgbase, wdata->args.offset, wdata->args.count, wdata, GFP_NOFS, &objios); if (unlikely(ret)) diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index 595c5fc21a19..874613545301 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -258,7 +258,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) if (status >= 0) rdata->res.count = status; else - rdata->pnfs_error = status; + rdata->header->pnfs_error = status; objlayout_iodone(oir); /* must not use oir after this point */ @@ -279,12 +279,14 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) enum pnfs_try_status objlayout_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *hdr = rdata->header; + struct inode *inode = hdr->inode; loff_t offset = rdata->args.offset; size_t count = rdata->args.count; int err; loff_t eof; - eof = i_size_read(rdata->inode); + eof = i_size_read(inode); if (unlikely(offset + count > eof)) { if (offset >= eof) { err = 0; @@ -297,17 +299,17 @@ objlayout_read_pagelist(struct nfs_read_data *rdata) } rdata->res.eof = (offset + count) >= eof; - _fix_verify_io_params(rdata->lseg, &rdata->args.pages, + _fix_verify_io_params(hdr->lseg, &rdata->args.pages, &rdata->args.pgbase, rdata->args.offset, rdata->args.count); dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n", - __func__, rdata->inode->i_ino, offset, count, rdata->res.eof); + __func__, inode->i_ino, offset, count, rdata->res.eof); err = objio_read_pagelist(rdata); out: if (unlikely(err)) { - rdata->pnfs_error = err; + hdr->pnfs_error = err; dprintk("%s: Returned Error %d\n", __func__, err); return PNFS_NOT_ATTEMPTED; } @@ -340,7 +342,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync) wdata->res.count = status; wdata->verf.committed = oir->committed; } else { - wdata->pnfs_error = status; + wdata->header->pnfs_error = status; } objlayout_iodone(oir); /* must not use oir after this point */ @@ -363,15 +365,16 @@ enum pnfs_try_status objlayout_write_pagelist(struct nfs_write_data *wdata, int how) { + struct nfs_pgio_header *hdr = wdata->header; int err; - _fix_verify_io_params(wdata->lseg, &wdata->args.pages, + _fix_verify_io_params(hdr->lseg, &wdata->args.pages, &wdata->args.pgbase, wdata->args.offset, wdata->args.count); err = objio_write_pagelist(wdata, how); if (unlikely(err)) { - wdata->pnfs_error = err; + hdr->pnfs_error = err; dprintk("%s: Returned Error %d\n", __func__, err); return PNFS_NOT_ATTEMPTED; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 9c4d14a17d49..d705da427e6d 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1191,13 +1191,15 @@ static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head * static void pnfs_ld_handle_write_error(struct nfs_write_data *data) { - dprintk("pnfs write error = %d\n", data->pnfs_error); - if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags & + struct nfs_pgio_header *hdr = data->header; + + dprintk("pnfs write error = %d\n", hdr->pnfs_error); + if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags & PNFS_LAYOUTRET_ON_ERROR) { - clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(data->inode)->flags); - pnfs_return_layout(data->inode); + clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); + pnfs_return_layout(hdr->inode); } - data->task.tk_status = pnfs_write_done_resend_to_mds(data->inode, &data->pages); + data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, &hdr->pages); } /* @@ -1205,13 +1207,15 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data) */ void pnfs_ld_write_done(struct nfs_write_data *data) { - if (likely(!data->pnfs_error)) { + struct nfs_pgio_header *hdr = data->header; + + if (!hdr->pnfs_error) { pnfs_set_layoutcommit(data); - data->mds_ops->rpc_call_done(&data->task, data); + hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_write_error(data); - put_lseg(data->lseg); - data->mds_ops->rpc_release(data); + put_lseg(hdr->lseg); + hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_write_done); @@ -1219,12 +1223,14 @@ static void pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_write_data *data) { - list_splice_tail_init(&data->pages, &desc->pg_list); - if (data->req && list_empty(&data->req->wb_list)) - nfs_list_add_request(data->req, &desc->pg_list); + struct nfs_pgio_header *hdr = data->header; + + list_splice_tail_init(&hdr->pages, &desc->pg_list); + if (hdr->req && list_empty(&hdr->req->wb_list)) + nfs_list_add_request(hdr->req, &desc->pg_list); nfs_pageio_reset_write_mds(desc); desc->pg_recoalesce = 1; - put_lseg(data->lseg); + put_lseg(hdr->lseg); nfs_writedata_release(data); } @@ -1234,20 +1240,21 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata, struct pnfs_layout_segment *lseg, int how) { - struct inode *inode = wdata->inode; + struct nfs_pgio_header *hdr = wdata->header; + struct inode *inode = hdr->inode; enum pnfs_try_status trypnfs; struct nfs_server *nfss = NFS_SERVER(inode); - wdata->mds_ops = call_ops; - wdata->lseg = get_lseg(lseg); + hdr->mds_ops = call_ops; + hdr->lseg = get_lseg(lseg); dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__, inode->i_ino, wdata->args.count, wdata->args.offset, how); trypnfs = nfss->pnfs_curr_ld->write_pagelist(wdata, how); if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(wdata->lseg); - wdata->lseg = NULL; + put_lseg(hdr->lseg); + hdr->lseg = NULL; } else nfs_inc_stats(inode, NFSIOS_PNFS_WRITE); @@ -1318,13 +1325,15 @@ static int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *h static void pnfs_ld_handle_read_error(struct nfs_read_data *data) { - dprintk("pnfs read error = %d\n", data->pnfs_error); - if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags & + struct nfs_pgio_header *hdr = data->header; + + dprintk("pnfs read error = %d\n", hdr->pnfs_error); + if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags & PNFS_LAYOUTRET_ON_ERROR) { - clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(data->inode)->flags); - pnfs_return_layout(data->inode); + clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); + pnfs_return_layout(hdr->inode); } - data->task.tk_status = pnfs_read_done_resend_to_mds(data->inode, &data->pages); + data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, &hdr->pages); } /* @@ -1332,13 +1341,15 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data) */ void pnfs_ld_read_done(struct nfs_read_data *data) { - if (likely(!data->pnfs_error)) { + struct nfs_pgio_header *hdr = data->header; + + if (likely(!hdr->pnfs_error)) { __nfs4_read_done_cb(data); - data->mds_ops->rpc_call_done(&data->task, data); + hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_read_error(data); - put_lseg(data->lseg); - data->mds_ops->rpc_release(data); + put_lseg(hdr->lseg); + hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_read_done); @@ -1346,9 +1357,11 @@ static void pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_read_data *data) { - list_splice_tail_init(&data->pages, &desc->pg_list); - if (data->req && list_empty(&data->req->wb_list)) - nfs_list_add_request(data->req, &desc->pg_list); + struct nfs_pgio_header *hdr = data->header; + + list_splice_tail_init(&hdr->pages, &desc->pg_list); + if (hdr->req && list_empty(&hdr->req->wb_list)) + nfs_list_add_request(hdr->req, &desc->pg_list); nfs_pageio_reset_read_mds(desc); desc->pg_recoalesce = 1; nfs_readdata_release(data); @@ -1362,20 +1375,21 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata, const struct rpc_call_ops *call_ops, struct pnfs_layout_segment *lseg) { - struct inode *inode = rdata->inode; + struct nfs_pgio_header *hdr = rdata->header; + struct inode *inode = hdr->inode; struct nfs_server *nfss = NFS_SERVER(inode); enum pnfs_try_status trypnfs; - rdata->mds_ops = call_ops; - rdata->lseg = get_lseg(lseg); + hdr->mds_ops = call_ops; + hdr->lseg = get_lseg(lseg); dprintk("%s: Reading ino:%lu %u@%llu\n", __func__, inode->i_ino, rdata->args.count, rdata->args.offset); trypnfs = nfss->pnfs_curr_ld->read_pagelist(rdata); if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(rdata->lseg); - rdata->lseg = NULL; + put_lseg(hdr->lseg); + hdr->lseg = NULL; } else { nfs_inc_stats(inode, NFSIOS_PNFS_READ); } @@ -1450,30 +1464,32 @@ EXPORT_SYMBOL_GPL(pnfs_set_lo_fail); void pnfs_set_layoutcommit(struct nfs_write_data *wdata) { - struct nfs_inode *nfsi = NFS_I(wdata->inode); + struct nfs_pgio_header *hdr = wdata->header; + struct inode *inode = hdr->inode; + struct nfs_inode *nfsi = NFS_I(inode); loff_t end_pos = wdata->mds_offset + wdata->res.count; bool mark_as_dirty = false; - spin_lock(&nfsi->vfs_inode.i_lock); + spin_lock(&inode->i_lock); if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { mark_as_dirty = true; dprintk("%s: Set layoutcommit for inode %lu ", - __func__, wdata->inode->i_ino); + __func__, inode->i_ino); } - if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) { + if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) { /* references matched in nfs4_layoutcommit_release */ - get_lseg(wdata->lseg); + get_lseg(hdr->lseg); } if (end_pos > nfsi->layout->plh_lwb) nfsi->layout->plh_lwb = end_pos; - spin_unlock(&nfsi->vfs_inode.i_lock); + spin_unlock(&inode->i_lock); dprintk("%s: lseg %p end_pos %llu\n", - __func__, wdata->lseg, nfsi->layout->plh_lwb); + __func__, hdr->lseg, nfsi->layout->plh_lwb); /* if pnfs_layoutcommit_inode() runs between inode locks, the next one * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */ if (mark_as_dirty) - mark_inode_dirty_sync(wdata->inode); + mark_inode_dirty_sync(inode); } EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index bf80503200f5..22ee70586875 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -641,12 +641,14 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data) { + struct inode *inode = data->header->inode; + if (nfs_async_handle_expired_key(task)) return -EAGAIN; - nfs_invalidate_atime(data->inode); + nfs_invalidate_atime(inode); if (task->tk_status >= 0) { - nfs_refresh_inode(data->inode, data->res.fattr); + nfs_refresh_inode(inode, data->res.fattr); /* Emulate the eof flag, which isn't normally needed in NFSv2 * as it is guaranteed to always return the file attributes */ @@ -668,11 +670,13 @@ static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_dat static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data) { + struct inode *inode = data->header->inode; + if (nfs_async_handle_expired_key(task)) return -EAGAIN; if (task->tk_status >= 0) - nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr); + nfs_post_op_update_inode_force_wcc(inode, data->res.fattr); return 0; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 4ddba6706347..d6d46823d9e4 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -35,19 +35,24 @@ static const struct rpc_call_ops nfs_read_full_ops; static struct kmem_cache *nfs_rdata_cachep; -struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) +struct nfs_read_header *nfs_readhdr_alloc(unsigned int pagecount) { - struct nfs_read_data *p; + struct nfs_read_header *p; p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); if (p) { - INIT_LIST_HEAD(&p->pages); - p->npages = pagecount; - if (pagecount <= ARRAY_SIZE(p->page_array)) - p->pagevec = p->page_array; + struct nfs_pgio_header *hdr = &p->header; + struct nfs_read_data *data = &p->rpc_data; + + INIT_LIST_HEAD(&hdr->pages); + INIT_LIST_HEAD(&data->list); + data->npages = pagecount; + data->header = hdr; + if (pagecount <= ARRAY_SIZE(data->page_array)) + data->pagevec = data->page_array; else { - p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); - if (!p->pagevec) { + data->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + if (!data->pagevec) { kmem_cache_free(nfs_rdata_cachep, p); p = NULL; } @@ -56,17 +61,19 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) return p; } -void nfs_readdata_free(struct nfs_read_data *p) +void nfs_readhdr_free(struct nfs_pgio_header *hdr) { - if (p && (p->pagevec != &p->page_array[0])) - kfree(p->pagevec); - kmem_cache_free(nfs_rdata_cachep, p); + struct nfs_read_header *rhdr = container_of(hdr, struct nfs_read_header, header); + + kmem_cache_free(nfs_rdata_cachep, rhdr); } void nfs_readdata_release(struct nfs_read_data *rdata) { put_nfs_open_context(rdata->args.context); - nfs_readdata_free(rdata); + if (rdata->pagevec != rdata->page_array) + kfree(rdata->pagevec); + nfs_readhdr_free(rdata->header); } static @@ -173,13 +180,13 @@ int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops) { - struct inode *inode = data->inode; + struct inode *inode = data->header->inode; int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0; struct rpc_task *task; struct rpc_message msg = { .rpc_argp = &data->args, .rpc_resp = &data->res, - .rpc_cred = data->cred, + .rpc_cred = data->header->cred, }; struct rpc_task_setup task_setup_data = { .task = &data->task, @@ -216,11 +223,11 @@ EXPORT_SYMBOL_GPL(nfs_initiate_read); static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, unsigned int count, unsigned int offset) { - struct inode *inode = req->wb_context->dentry->d_inode; + struct inode *inode = data->header->inode; - data->req = req; - data->inode = inode; - data->cred = req->wb_context->cred; + data->header->req = req; + data->header->inode = inode; + data->header->cred = req->wb_context->cred; data->args.fh = NFS_FH(inode); data->args.offset = req_offset(req) + offset; @@ -239,7 +246,7 @@ static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, static int nfs_do_read(struct nfs_read_data *data, const struct rpc_call_ops *call_ops) { - struct inode *inode = data->args.context->dentry->d_inode; + struct inode *inode = data->header->inode; return nfs_initiate_read(NFS_CLIENT(inode), data, call_ops); } @@ -293,6 +300,7 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head { struct nfs_page *req = nfs_list_entry(desc->pg_list.next); struct page *page = req->wb_page; + struct nfs_read_header *rhdr; struct nfs_read_data *data; size_t rsize = desc->pg_bsize, nbytes; unsigned int offset; @@ -306,9 +314,10 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head do { size_t len = min(nbytes,rsize); - data = nfs_readdata_alloc(1); - if (!data) + rhdr = nfs_readhdr_alloc(1); + if (!rhdr) goto out_bad; + data = &rhdr->rpc_data; data->pagevec[0] = page; nfs_read_rpcsetup(req, data, len, offset); list_add(&data->list, res); @@ -333,26 +342,28 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head * { struct nfs_page *req; struct page **pages; + struct nfs_read_header *rhdr; struct nfs_read_data *data; struct list_head *head = &desc->pg_list; int ret = 0; - data = nfs_readdata_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!data) { + rhdr = nfs_readhdr_alloc(nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!rhdr) { nfs_async_read_error(head); ret = -ENOMEM; goto out; } + data = &rhdr->rpc_data; pages = data->pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &data->pages); + nfs_list_add_request(req, &rhdr->header.pages); *pages++ = req->wb_page; } - req = nfs_list_entry(data->pages.next); + req = nfs_list_entry(rhdr->header.pages.next); nfs_read_rpcsetup(req, data, desc->pg_count, 0); list_add(&data->list, res); @@ -390,20 +401,21 @@ static const struct nfs_pageio_ops nfs_pageio_read_ops = { */ int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data) { + struct inode *inode = data->header->inode; int status; dprintk("NFS: %s: %5u, (status %d)\n", __func__, task->tk_pid, task->tk_status); - status = NFS_PROTO(data->inode)->read_done(task, data); + status = NFS_PROTO(inode)->read_done(task, data); if (status != 0) return status; - nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, data->res.count); + nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, data->res.count); if (task->tk_status == -ESTALE) { - set_bit(NFS_INO_STALE, &NFS_I(data->inode)->flags); - nfs_mark_for_revalidate(data->inode); + set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); + nfs_mark_for_revalidate(inode); } return 0; } @@ -417,7 +429,7 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data return; /* This is a short read! */ - nfs_inc_stats(data->inode, NFSIOS_SHORTREAD); + nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD); /* Has the server at least made some progress? */ if (resp->count == 0) return; @@ -449,7 +461,7 @@ static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata) static void nfs_readpage_release_partial(void *calldata) { struct nfs_read_data *data = calldata; - struct nfs_page *req = data->req; + struct nfs_page *req = data->header->req; struct page *page = req->wb_page; int status = data->task.tk_status; @@ -461,13 +473,13 @@ static void nfs_readpage_release_partial(void *calldata) SetPageUptodate(page); nfs_readpage_release(req); } - nfs_readdata_release(calldata); + nfs_readdata_release(data); } void nfs_read_prepare(struct rpc_task *task, void *calldata) { struct nfs_read_data *data = calldata; - NFS_PROTO(data->inode)->read_rpc_prepare(task, data); + NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data); } static const struct rpc_call_ops nfs_read_partial_ops = { @@ -524,9 +536,10 @@ static void nfs_readpage_result_full(struct rpc_task *task, void *calldata) static void nfs_readpage_release_full(void *calldata) { struct nfs_read_data *data = calldata; + struct nfs_pgio_header *hdr = data->header; - while (!list_empty(&data->pages)) { - struct nfs_page *req = nfs_list_entry(data->pages.next); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); nfs_list_remove_request(req); nfs_readpage_release(req); @@ -685,7 +698,7 @@ out: int __init nfs_init_readpagecache(void) { nfs_rdata_cachep = kmem_cache_create("nfs_read_data", - sizeof(struct nfs_read_data), + sizeof(struct nfs_read_header), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_rdata_cachep == NULL) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 76735dd8c9a7..dbb5c0a613b8 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -69,19 +69,24 @@ void nfs_commit_free(struct nfs_commit_data *p) } EXPORT_SYMBOL_GPL(nfs_commit_free); -struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) +struct nfs_write_header *nfs_writehdr_alloc(unsigned int pagecount) { - struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); + struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); if (p) { + struct nfs_pgio_header *hdr = &p->header; + struct nfs_write_data *data = &p->rpc_data; + memset(p, 0, sizeof(*p)); - INIT_LIST_HEAD(&p->pages); - p->npages = pagecount; - if (pagecount <= ARRAY_SIZE(p->page_array)) - p->pagevec = p->page_array; + INIT_LIST_HEAD(&hdr->pages); + INIT_LIST_HEAD(&data->list); + data->npages = pagecount; + data->header = hdr; + if (pagecount <= ARRAY_SIZE(data->page_array)) + data->pagevec = data->page_array; else { - p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); - if (!p->pagevec) { + data->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); + if (!data->pagevec) { mempool_free(p, nfs_wdata_mempool); p = NULL; } @@ -90,17 +95,18 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) return p; } -void nfs_writedata_free(struct nfs_write_data *p) +void nfs_writehdr_free(struct nfs_pgio_header *hdr) { - if (p && (p->pagevec != &p->page_array[0])) - kfree(p->pagevec); - mempool_free(p, nfs_wdata_mempool); + struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); + mempool_free(whdr, nfs_wdata_mempool); } void nfs_writedata_release(struct nfs_write_data *wdata) { put_nfs_open_context(wdata->args.context); - nfs_writedata_free(wdata); + if (wdata->pagevec != wdata->page_array) + kfree(wdata->pagevec); + nfs_writehdr_free(wdata->header); } static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) @@ -507,9 +513,8 @@ static inline int nfs_write_need_commit(struct nfs_write_data *data) { if (data->verf.committed == NFS_DATA_SYNC) - return data->lseg == NULL; - else - return data->verf.committed != NFS_FILE_SYNC; + return data->header->lseg == NULL; + return data->verf.committed != NFS_FILE_SYNC; } static inline @@ -517,7 +522,7 @@ int nfs_reschedule_unstable_write(struct nfs_page *req, struct nfs_write_data *data) { if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) { - nfs_mark_request_commit(req, data->lseg); + nfs_mark_request_commit(req, data->header->lseg); return 1; } if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) { @@ -841,13 +846,13 @@ int nfs_initiate_write(struct rpc_clnt *clnt, const struct rpc_call_ops *call_ops, int how) { - struct inode *inode = data->inode; + struct inode *inode = data->header->inode; int priority = flush_task_priority(how); struct rpc_task *task; struct rpc_message msg = { .rpc_argp = &data->args, .rpc_resp = &data->res, - .rpc_cred = data->cred, + .rpc_cred = data->header->cred, }; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, @@ -896,14 +901,15 @@ static void nfs_write_rpcsetup(struct nfs_page *req, unsigned int count, unsigned int offset, int how) { + struct nfs_pgio_header *hdr = data->header; struct inode *inode = req->wb_context->dentry->d_inode; /* Set up the RPC argument and reply structs * NB: take care not to mess about with data->commit et al. */ - data->req = req; - data->inode = inode = req->wb_context->dentry->d_inode; - data->cred = req->wb_context->cred; + hdr->req = req; + hdr->inode = inode = req->wb_context->dentry->d_inode; + hdr->cred = req->wb_context->cred; data->args.fh = NFS_FH(inode); data->args.offset = req_offset(req) + offset; @@ -935,7 +941,7 @@ static int nfs_do_write(struct nfs_write_data *data, const struct rpc_call_ops *call_ops, int how) { - struct inode *inode = data->args.context->dentry->d_inode; + struct inode *inode = data->header->inode; return nfs_initiate_write(NFS_CLIENT(inode), data, call_ops, how); } @@ -981,6 +987,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head { struct nfs_page *req = nfs_list_entry(desc->pg_list.next); struct page *page = req->wb_page; + struct nfs_write_header *whdr; struct nfs_write_data *data; size_t wsize = desc->pg_bsize, nbytes; unsigned int offset; @@ -1000,9 +1007,10 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head do { size_t len = min(nbytes, wsize); - data = nfs_writedata_alloc(1); - if (!data) + whdr = nfs_writehdr_alloc(1); + if (!whdr) goto out_bad; + data = &whdr->rpc_data; data->pagevec[0] = page; nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags); list_add(&data->list, res); @@ -1036,13 +1044,14 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *r { struct nfs_page *req; struct page **pages; + struct nfs_write_header *whdr; struct nfs_write_data *data; struct list_head *head = &desc->pg_list; int ret = 0; - data = nfs_writedata_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!data) { + whdr = nfs_writehdr_alloc(nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!whdr) { while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); @@ -1051,14 +1060,15 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *r ret = -ENOMEM; goto out; } + data = &whdr->rpc_data; pages = data->pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &data->pages); + nfs_list_add_request(req, &whdr->header.pages); *pages++ = req->wb_page; } - req = nfs_list_entry(data->pages.next); + req = nfs_list_entry(whdr->header.pages.next); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) @@ -1126,10 +1136,11 @@ static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata) dprintk("NFS: %5u write(%s/%lld %d@%lld)", task->tk_pid, - data->req->wb_context->dentry->d_inode->i_sb->s_id, + data->header->inode->i_sb->s_id, (long long) - NFS_FILEID(data->req->wb_context->dentry->d_inode), - data->req->wb_bytes, (long long)req_offset(data->req)); + NFS_FILEID(data->header->inode), + data->header->req->wb_bytes, + (long long)req_offset(data->header->req)); nfs_writeback_done(task, data); } @@ -1137,7 +1148,7 @@ static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata) static void nfs_writeback_release_partial(void *calldata) { struct nfs_write_data *data = calldata; - struct nfs_page *req = data->req; + struct nfs_page *req = data->header->req; struct page *page = req->wb_page; int status = data->task.tk_status; @@ -1169,13 +1180,13 @@ static void nfs_writeback_release_partial(void *calldata) out: if (atomic_dec_and_test(&req->wb_complete)) nfs_writepage_release(req, data); - nfs_writedata_release(calldata); + nfs_writedata_release(data); } void nfs_write_prepare(struct rpc_task *task, void *calldata) { struct nfs_write_data *data = calldata; - NFS_PROTO(data->inode)->write_rpc_prepare(task, data); + NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data); } void nfs_commit_prepare(struct rpc_task *task, void *calldata) @@ -1208,11 +1219,12 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata) static void nfs_writeback_release_full(void *calldata) { struct nfs_write_data *data = calldata; + struct nfs_pgio_header *hdr = data->header; int status = data->task.tk_status; /* Update attributes as result of writeback. */ - while (!list_empty(&data->pages)) { - struct nfs_page *req = nfs_list_entry(data->pages.next); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct page *page = req->wb_page; nfs_list_remove_request(req); @@ -1233,7 +1245,7 @@ static void nfs_writeback_release_full(void *calldata) if (nfs_write_need_commit(data)) { memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - nfs_mark_request_commit(req, data->lseg); + nfs_mark_request_commit(req, hdr->lseg); dprintk(" marked for commit\n"); goto next; } @@ -1244,7 +1256,7 @@ remove_request: nfs_unlock_request(req); nfs_end_page_writeback(page); } - nfs_writedata_release(calldata); + nfs_writedata_release(data); } static const struct rpc_call_ops nfs_write_full_ops = { @@ -1261,6 +1273,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) { struct nfs_writeargs *argp = &data->args; struct nfs_writeres *resp = &data->res; + struct inode *inode = data->header->inode; int status; dprintk("NFS: %5u nfs_writeback_done (status %d)\n", @@ -1273,10 +1286,10 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) * another writer had changed the file, but some applications * depend on tighter cache coherency when writing. */ - status = NFS_PROTO(data->inode)->write_done(task, data); + status = NFS_PROTO(inode)->write_done(task, data); if (status != 0) return; - nfs_add_stats(data->inode, NFSIOS_SERVERWRITTENBYTES, resp->count); + nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) if (resp->verf->committed < argp->stable && task->tk_status >= 0) { @@ -1294,7 +1307,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) if (time_before(complain, jiffies)) { dprintk("NFS: faulty NFS server %s:" " (committed = %d) != (stable = %d)\n", - NFS_SERVER(data->inode)->nfs_client->cl_hostname, + NFS_SERVER(inode)->nfs_client->cl_hostname, resp->verf->committed, argp->stable); complain = jiffies + 300 * HZ; } @@ -1304,7 +1317,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) if (task->tk_status >= 0 && resp->count < argp->count) { static unsigned long complain; - nfs_inc_stats(data->inode, NFSIOS_SHORTWRITE); + nfs_inc_stats(inode, NFSIOS_SHORTWRITE); /* Has the server at least made some progress? */ if (resp->count != 0) { @@ -1333,7 +1346,6 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) /* Can't do anything about it except throw an error. */ task->tk_status = -EIO; } - return; } @@ -1745,7 +1757,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, int __init nfs_init_writepagecache(void) { nfs_wdata_cachep = kmem_cache_create("nfs_write_data", - sizeof(struct nfs_write_data), + sizeof(struct nfs_write_header), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_wdata_cachep == NULL) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d5d68f322bf0..8d3a2b804201 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -568,12 +568,6 @@ nfs_have_writebacks(struct inode *inode) return NFS_I(inode)->npages != 0; } -/* - * Allocate nfs_write_data structures - */ -extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages); -extern void nfs_writedata_free(struct nfs_write_data *); - /* * linux/fs/nfs/read.c */ @@ -584,12 +578,6 @@ extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *); extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, struct page *); -/* - * Allocate nfs_read_data structures - */ -extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages); -extern void nfs_readdata_free(struct nfs_read_data *); - /* * linux/fs/nfs3proc.c */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 8fb036a0d489..fee324175391 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1168,52 +1168,58 @@ struct nfs_page; #define NFS_PAGEVEC_SIZE (8U) struct nfs_read_data { + struct nfs_pgio_header *header; + struct list_head list; struct rpc_task task; - struct inode *inode; - struct rpc_cred *cred; struct nfs_fattr fattr; /* fattr storage */ - struct list_head pages; /* Coalesced read requests */ - struct list_head list; /* lists of struct nfs_read_data */ - struct nfs_page *req; /* multi ops per nfs_page */ struct page **pagevec; unsigned int npages; /* Max length of pagevec */ struct nfs_readargs args; struct nfs_readres res; unsigned long timestamp; /* For lease renewal */ - struct pnfs_layout_segment *lseg; - struct nfs_client *ds_clp; /* pNFS data server */ - const struct rpc_call_ops *mds_ops; int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data); __u64 mds_offset; - int pnfs_error; struct page *page_array[NFS_PAGEVEC_SIZE]; + struct nfs_client *ds_clp; /* pNFS data server */ +}; + +struct nfs_pgio_header { + struct inode *inode; + struct rpc_cred *cred; + struct list_head pages; + struct nfs_page *req; + struct pnfs_layout_segment *lseg; + const struct rpc_call_ops *mds_ops; + int pnfs_error; +}; + +struct nfs_read_header { + struct nfs_pgio_header header; + struct nfs_read_data rpc_data; }; struct nfs_direct_req; struct nfs_write_data { + struct nfs_pgio_header *header; + struct list_head list; struct rpc_task task; - struct inode *inode; - struct rpc_cred *cred; struct nfs_fattr fattr; struct nfs_writeverf verf; - struct list_head pages; /* Coalesced requests we wish to flush */ - struct list_head list; /* lists of struct nfs_write_data */ - struct nfs_page *req; /* multi ops per nfs_page */ struct page **pagevec; unsigned int npages; /* Max length of pagevec */ struct nfs_writeargs args; /* argument struct */ struct nfs_writeres res; /* result struct */ - struct pnfs_layout_segment *lseg; - struct nfs_client *ds_clp; /* pNFS data server */ - const struct rpc_call_ops *mds_ops; - int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); -#ifdef CONFIG_NFS_V4 unsigned long timestamp; /* For lease renewal */ -#endif + int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); __u64 mds_offset; /* Filelayout dense stripe */ - int pnfs_error; struct page *page_array[NFS_PAGEVEC_SIZE]; + struct nfs_client *ds_clp; /* pNFS data server */ +}; + +struct nfs_write_header { + struct nfs_pgio_header header; + struct nfs_write_data rpc_data; }; struct nfs_commit_data { -- cgit v1.2.3 From 30dd374f6fc1b202db3a1b57b61afff1326bad92 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:45 -0400 Subject: NFS: create struct nfs_page_array Both nfs_read_data and nfs_write_data devote several fields which can be combined into a single shared struct. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.c | 11 ++++++----- fs/nfs/direct.c | 40 +++++++++++++++++++++++----------------- fs/nfs/internal.h | 1 + fs/nfs/pagelist.c | 13 +++++++++++++ fs/nfs/read.c | 22 ++++++++-------------- fs/nfs/write.c | 22 ++++++++-------------- include/linux/nfs_xdr.h | 14 ++++++++------ 7 files changed, 67 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 7a482517f4c6..7ae8a608956f 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -242,7 +242,7 @@ bl_read_pagelist(struct nfs_read_data *rdata) int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT; dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__, - rdata->npages, f_offset, (unsigned int)rdata->args.count); + rdata->pages.npages, f_offset, (unsigned int)rdata->args.count); par = alloc_parallel(rdata); if (!par) @@ -252,7 +252,7 @@ bl_read_pagelist(struct nfs_read_data *rdata) isect = (sector_t) (f_offset >> SECTOR_SHIFT); /* Code assumes extents are page-aligned */ - for (i = pg_index; i < rdata->npages; i++) { + for (i = pg_index; i < rdata->pages.npages; i++) { if (!extent_length) { /* We've used up the previous extent */ bl_put_extent(be); @@ -285,7 +285,8 @@ bl_read_pagelist(struct nfs_read_data *rdata) struct pnfs_block_extent *be_read; be_read = (hole && cow_read) ? cow_read : be; - bio = bl_add_page_to_bio(bio, rdata->npages - i, READ, + bio = bl_add_page_to_bio(bio, rdata->pages.npages - i, + READ, isect, pages[i], be_read, bl_end_io_read, par); if (IS_ERR(bio)) { @@ -654,7 +655,7 @@ next_page: /* Middle pages */ pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT; - for (i = pg_index; i < wdata->npages; i++) { + for (i = pg_index; i < wdata->pages.npages; i++) { if (!extent_length) { /* We've used up the previous extent */ bl_put_extent(be); @@ -688,7 +689,7 @@ next_page: goto out; } } - bio = bl_add_page_to_bio(bio, wdata->npages - i, WRITE, + bio = bl_add_page_to_bio(bio, wdata->pages.npages - i, WRITE, isect, pages[i], be, bl_end_io_write, par); if (IS_ERR(bio)) { diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 56176af1436f..0faba4cb531d 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -252,11 +252,11 @@ static void nfs_direct_read_release(void *calldata) } else { dreq->count += data->res.count; spin_unlock(&dreq->lock); - nfs_direct_dirty_pages(data->pagevec, + nfs_direct_dirty_pages(data->pages.pagevec, data->args.pgbase, data->res.count); } - nfs_direct_release_pages(data->pagevec, data->npages); + nfs_direct_release_pages(data->pages.pagevec, data->pages.npages); if (put_dreq(dreq)) nfs_direct_complete(dreq); @@ -273,8 +273,8 @@ static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr) { struct nfs_read_data *data = &rhdr->rpc_data; - if (data->pagevec != data->page_array) - kfree(data->pagevec); + if (data->pages.pagevec != data->pages.page_array) + kfree(data->pages.pagevec); nfs_readhdr_free(&rhdr->header); } @@ -312,6 +312,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, do { struct nfs_read_header *rhdr; struct nfs_read_data *data; + struct nfs_page_array *pages; size_t bytes; pgbase = user_addr & ~PAGE_MASK; @@ -322,24 +323,25 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, if (unlikely(!rhdr)) break; data = &rhdr->rpc_data; + pages = &data->pages; down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, - data->npages, 1, 0, data->pagevec, NULL); + pages->npages, 1, 0, pages->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { nfs_direct_readhdr_release(rhdr); break; } - if ((unsigned)result < data->npages) { + if ((unsigned)result < pages->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { - nfs_direct_release_pages(data->pagevec, result); + nfs_direct_release_pages(pages->pagevec, result); nfs_direct_readhdr_release(rhdr); break; } bytes -= pgbase; - data->npages = result; + pages->npages = result; } get_dreq(dreq); @@ -352,7 +354,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, data->args.lock_context = dreq->l_ctx; data->args.offset = pos; data->args.pgbase = pgbase; - data->args.pages = data->pagevec; + data->args.pages = pages->pagevec; data->args.count = bytes; data->res.fattr = &data->fattr; data->res.eof = 0; @@ -462,8 +464,8 @@ static void nfs_direct_writehdr_release(struct nfs_write_header *whdr) { struct nfs_write_data *data = &whdr->rpc_data; - if (data->pagevec != data->page_array) - kfree(data->pagevec); + if (data->pages.pagevec != data->pages.page_array) + kfree(data->pages.pagevec); nfs_writehdr_free(&whdr->header); } @@ -472,8 +474,10 @@ static void nfs_direct_free_writedata(struct nfs_direct_req *dreq) while (!list_empty(&dreq->rewrite_list)) { struct nfs_pgio_header *hdr = list_entry(dreq->rewrite_list.next, struct nfs_pgio_header, pages); struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); + struct nfs_page_array *p = &whdr->rpc_data.pages; + list_del(&hdr->pages); - nfs_direct_release_pages(whdr->rpc_data.pagevec, whdr->rpc_data.npages); + nfs_direct_release_pages(p->pagevec, p->npages); nfs_direct_writehdr_release(whdr); } } @@ -751,6 +755,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, do { struct nfs_write_header *whdr; struct nfs_write_data *data; + struct nfs_page_array *pages; size_t bytes; pgbase = user_addr & ~PAGE_MASK; @@ -762,24 +767,25 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, break; data = &whdr->rpc_data; + pages = &data->pages; down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, - data->npages, 0, 0, data->pagevec, NULL); + pages->npages, 0, 0, pages->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { nfs_direct_writehdr_release(whdr); break; } - if ((unsigned)result < data->npages) { + if ((unsigned)result < pages->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { - nfs_direct_release_pages(data->pagevec, result); + nfs_direct_release_pages(pages->pagevec, result); nfs_direct_writehdr_release(whdr); break; } bytes -= pgbase; - data->npages = result; + pages->npages = result; } get_dreq(dreq); @@ -794,7 +800,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, data->args.lock_context = dreq->l_ctx; data->args.offset = pos; data->args.pgbase = pgbase; - data->args.pages = data->pagevec; + data->args.pages = pages->pagevec; data->args.count = bytes; data->args.stable = sync; data->res.fattr = &data->fattr; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7dc9be1a6e1a..5c3d77fda560 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -210,6 +210,7 @@ extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); +extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount); /* nfs2xdr.c */ extern int nfs_stat_to_errno(enum nfs_stat); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index d21fceaa9f62..d349bd4c48db 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -26,6 +26,19 @@ static struct kmem_cache *nfs_page_cachep; +bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) +{ + p->npages = pagecount; + if (pagecount <= ARRAY_SIZE(p->page_array)) + p->pagevec = p->page_array; + else { + p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + if (!p->pagevec) + p->npages = 0; + } + return p->pagevec != NULL; +} + static inline struct nfs_page * nfs_page_alloc(void) { diff --git a/fs/nfs/read.c b/fs/nfs/read.c index d6d46823d9e4..f6ab30b5a462 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -46,16 +46,10 @@ struct nfs_read_header *nfs_readhdr_alloc(unsigned int pagecount) INIT_LIST_HEAD(&hdr->pages); INIT_LIST_HEAD(&data->list); - data->npages = pagecount; data->header = hdr; - if (pagecount <= ARRAY_SIZE(data->page_array)) - data->pagevec = data->page_array; - else { - data->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); - if (!data->pagevec) { - kmem_cache_free(nfs_rdata_cachep, p); - p = NULL; - } + if (!nfs_pgarray_set(&data->pages, pagecount)) { + kmem_cache_free(nfs_rdata_cachep, p); + p = NULL; } } return p; @@ -71,8 +65,8 @@ void nfs_readhdr_free(struct nfs_pgio_header *hdr) void nfs_readdata_release(struct nfs_read_data *rdata) { put_nfs_open_context(rdata->args.context); - if (rdata->pagevec != rdata->page_array) - kfree(rdata->pagevec); + if (rdata->pages.pagevec != rdata->pages.page_array) + kfree(rdata->pages.pagevec); nfs_readhdr_free(rdata->header); } @@ -232,7 +226,7 @@ static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, data->args.fh = NFS_FH(inode); data->args.offset = req_offset(req) + offset; data->args.pgbase = req->wb_pgbase + offset; - data->args.pages = data->pagevec; + data->args.pages = data->pages.pagevec; data->args.count = count; data->args.context = get_nfs_open_context(req->wb_context); data->args.lock_context = req->wb_lock_context; @@ -318,7 +312,7 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head if (!rhdr) goto out_bad; data = &rhdr->rpc_data; - data->pagevec[0] = page; + data->pages.pagevec[0] = page; nfs_read_rpcsetup(req, data, len, offset); list_add(&data->list, res); requests++; @@ -356,7 +350,7 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head * } data = &rhdr->rpc_data; - pages = data->pagevec; + pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index dbb5c0a613b8..2efae049b4f0 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -80,16 +80,10 @@ struct nfs_write_header *nfs_writehdr_alloc(unsigned int pagecount) memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&hdr->pages); INIT_LIST_HEAD(&data->list); - data->npages = pagecount; data->header = hdr; - if (pagecount <= ARRAY_SIZE(data->page_array)) - data->pagevec = data->page_array; - else { - data->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); - if (!data->pagevec) { - mempool_free(p, nfs_wdata_mempool); - p = NULL; - } + if (!nfs_pgarray_set(&data->pages, pagecount)) { + mempool_free(p, nfs_wdata_mempool); + p = NULL; } } return p; @@ -104,8 +98,8 @@ void nfs_writehdr_free(struct nfs_pgio_header *hdr) void nfs_writedata_release(struct nfs_write_data *wdata) { put_nfs_open_context(wdata->args.context); - if (wdata->pagevec != wdata->page_array) - kfree(wdata->pagevec); + if (wdata->pages.pagevec != wdata->pages.page_array) + kfree(wdata->pages.pagevec); nfs_writehdr_free(wdata->header); } @@ -916,7 +910,7 @@ static void nfs_write_rpcsetup(struct nfs_page *req, /* pnfs_set_layoutcommit needs this */ data->mds_offset = data->args.offset; data->args.pgbase = req->wb_pgbase + offset; - data->args.pages = data->pagevec; + data->args.pages = data->pages.pagevec; data->args.count = count; data->args.context = get_nfs_open_context(req->wb_context); data->args.lock_context = req->wb_lock_context; @@ -1011,7 +1005,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head if (!whdr) goto out_bad; data = &whdr->rpc_data; - data->pagevec[0] = page; + data->pages.pagevec[0] = page; nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags); list_add(&data->list, res); requests++; @@ -1061,7 +1055,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *r goto out; } data = &whdr->rpc_data; - pages = data->pagevec; + pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index fee324175391..e34beaf86e9c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1167,19 +1167,23 @@ struct nfs_page; #define NFS_PAGEVEC_SIZE (8U) +struct nfs_page_array { + struct page **pagevec; + unsigned int npages; /* Max length of pagevec */ + struct page *page_array[NFS_PAGEVEC_SIZE]; +}; + struct nfs_read_data { struct nfs_pgio_header *header; struct list_head list; struct rpc_task task; struct nfs_fattr fattr; /* fattr storage */ - struct page **pagevec; - unsigned int npages; /* Max length of pagevec */ struct nfs_readargs args; struct nfs_readres res; unsigned long timestamp; /* For lease renewal */ int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data); __u64 mds_offset; - struct page *page_array[NFS_PAGEVEC_SIZE]; + struct nfs_page_array pages; struct nfs_client *ds_clp; /* pNFS data server */ }; @@ -1206,14 +1210,12 @@ struct nfs_write_data { struct rpc_task task; struct nfs_fattr fattr; struct nfs_writeverf verf; - struct page **pagevec; - unsigned int npages; /* Max length of pagevec */ struct nfs_writeargs args; /* argument struct */ struct nfs_writeres res; /* result struct */ unsigned long timestamp; /* For lease renewal */ int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); __u64 mds_offset; /* Filelayout dense stripe */ - struct page *page_array[NFS_PAGEVEC_SIZE]; + struct nfs_page_array pages; struct nfs_client *ds_clp; /* pNFS data server */ }; -- cgit v1.2.3 From 4db6e0b74c0f6dfc2f9c0690e8df512e3b635983 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:46 -0400 Subject: NFS: merge _full and _partial read rpc_ops Decouple nfs_pgio_header and nfs_read_data, and have (possibly multiple) nfs_read_datas each take a refcount on nfs_pgio_header. For the moment keeps nfs_read_header as a way to preallocate a single nfs_read_data with the nfs_pgio_header. The code doesn't need this, and would be prettier without, but given the amount of churn I am already introducing I didn't want to play with tuning new mempools. This also fixes bug in pnfs_ld_handle_read_error. In the case of desc->pg_bsize < PAGE_CACHE_SIZE, the pages list was empty, causing replay attempt to do nothing. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 10 +- fs/nfs/internal.h | 15 ++- fs/nfs/nfs4filelayout.c | 1 - fs/nfs/nfs4proc.c | 2 - fs/nfs/pagelist.c | 24 ++++ fs/nfs/pnfs.c | 55 +++++--- fs/nfs/read.c | 338 ++++++++++++++++++++++------------------------- include/linux/nfs_page.h | 1 - include/linux/nfs_xdr.h | 16 +++ 9 files changed, 252 insertions(+), 210 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 0faba4cb531d..90b00ce42cbe 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -319,10 +319,16 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, bytes = min(rsize,count); result = -ENOMEM; - rhdr = nfs_readhdr_alloc(nfs_page_array_len(pgbase, bytes)); + rhdr = nfs_readhdr_alloc(); if (unlikely(!rhdr)) break; - data = &rhdr->rpc_data; + data = nfs_readdata_alloc(&rhdr->header, nfs_page_array_len(pgbase, bytes)); + if (!data) { + nfs_readhdr_free(&rhdr->header); + break; + } + data->header = &rhdr->header; + atomic_inc(&data->header->refcnt); pages = &data->pages; down_read(¤t->mm->mmap_sem); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5c3d77fda560..33af5e51c0bb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -200,6 +200,7 @@ struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) extern struct svc_version nfs4_callback_version1; extern struct svc_version nfs4_callback_version4; +struct nfs_pageio_descriptor; /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); @@ -211,6 +212,10 @@ extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount); +extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, + void (*release)(struct nfs_pgio_header *hdr)); +void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); /* nfs2xdr.c */ extern int nfs_stat_to_errno(enum nfs_stat); @@ -295,17 +300,19 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh); #endif -struct nfs_pageio_descriptor; /* read.c */ -extern struct nfs_read_header *nfs_readhdr_alloc(unsigned int npages); +extern void nfs_async_read_error(struct list_head *head); +extern struct nfs_read_header *nfs_readhdr_alloc(void); extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); +extern void nfs_read_completion(struct nfs_pgio_header *hdr); +extern struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount); extern int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, - struct list_head *head); - + struct nfs_pgio_header *hdr); extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, struct inode *inode); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index ad1d68013a5b..333e765f3ac2 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -227,7 +227,6 @@ static void filelayout_read_release(void *data) { struct nfs_read_data *rdata = data; - put_lseg(rdata->header->lseg); rdata->header->mds_ops->rpc_release(data); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 5375862075de..ce31ab22bc55 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3391,8 +3391,6 @@ void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data) struct inode *inode = hdr->inode; dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(hdr->lseg); - hdr->lseg = NULL; data->ds_clp = NULL; /* offsets will differ in the dense stripe case */ data->args.offset = data->mds_offset; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index d349bd4c48db..cd4c038135a7 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -39,6 +39,30 @@ bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) return p->pagevec != NULL; } +void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, + void (*release)(struct nfs_pgio_header *hdr)) +{ + hdr->req = nfs_list_entry(desc->pg_list.next); + hdr->inode = desc->pg_inode; + hdr->cred = hdr->req->wb_context->cred; + hdr->io_start = req_offset(hdr->req); + hdr->good_bytes = desc->pg_count; + hdr->release = release; +} + +void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) +{ + spin_lock(&hdr->lock); + if (pos < hdr->io_start + hdr->good_bytes) { + set_bit(NFS_IOHDR_ERROR, &hdr->flags); + clear_bit(NFS_IOHDR_EOF, &hdr->flags); + hdr->good_bytes = pos - hdr->io_start; + hdr->error = error; + } + spin_unlock(&hdr->lock); +} + static inline struct nfs_page * nfs_page_alloc(void) { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d705da427e6d..d1a91dbe7654 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1333,7 +1333,9 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data) clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); pnfs_return_layout(hdr->inode); } - data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, &hdr->pages); + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) + data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, + &hdr->pages); } /* @@ -1348,7 +1350,6 @@ void pnfs_ld_read_done(struct nfs_read_data *data) hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_read_error(data); - put_lseg(hdr->lseg); hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_read_done); @@ -1359,11 +1360,11 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, { struct nfs_pgio_header *hdr = data->header; - list_splice_tail_init(&hdr->pages, &desc->pg_list); - if (hdr->req && list_empty(&hdr->req->wb_list)) - nfs_list_add_request(hdr->req, &desc->pg_list); - nfs_pageio_reset_read_mds(desc); - desc->pg_recoalesce = 1; + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + list_splice_tail_init(&hdr->pages, &desc->pg_list); + nfs_pageio_reset_read_mds(desc); + desc->pg_recoalesce = 1; + } nfs_readdata_release(data); } @@ -1381,18 +1382,13 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata, enum pnfs_try_status trypnfs; hdr->mds_ops = call_ops; - hdr->lseg = get_lseg(lseg); dprintk("%s: Reading ino:%lu %u@%llu\n", __func__, inode->i_ino, rdata->args.count, rdata->args.offset); trypnfs = nfss->pnfs_curr_ld->read_pagelist(rdata); - if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(hdr->lseg); - hdr->lseg = NULL; - } else { + if (trypnfs != PNFS_NOT_ATTEMPTED) nfs_inc_stats(inode, NFSIOS_PNFS_READ); - } dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); return trypnfs; } @@ -1408,7 +1404,7 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea while (!list_empty(head)) { enum pnfs_try_status trypnfs; - data = list_entry(head->next, struct nfs_read_data, list); + data = list_first_entry(head, struct nfs_read_data, list); list_del_init(&data->list); trypnfs = pnfs_try_to_read_data(data, call_ops, lseg); @@ -1418,20 +1414,41 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea put_lseg(lseg); } +static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) +{ + put_lseg(hdr->lseg); + nfs_readhdr_free(hdr); +} + int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_read_header *rhdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_pagein(desc, &head); - if (ret != 0) { + rhdr = nfs_readhdr_alloc(); + if (!rhdr) { + nfs_async_read_error(&desc->pg_list); + ret = -ENOMEM; put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; return ret; } - pnfs_do_multiple_reads(desc, &head); - return 0; + hdr = &rhdr->header; + nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); + hdr->lseg = get_lseg(desc->pg_lseg); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_pagein(desc, hdr); + if (ret != 0) { + put_lseg(desc->pg_lseg); + desc->pg_lseg = NULL; + set_bit(NFS_IOHDR_REDO, &hdr->flags); + } else + pnfs_do_multiple_reads(desc, &hdr->rpc_list); + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_read_completion(hdr); + return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index f6ab30b5a462..c9633b2501bd 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -30,29 +30,49 @@ #define NFSDBG_FACILITY NFSDBG_PAGECACHE static const struct nfs_pageio_ops nfs_pageio_read_ops; -static const struct rpc_call_ops nfs_read_partial_ops; -static const struct rpc_call_ops nfs_read_full_ops; +static const struct rpc_call_ops nfs_read_common_ops; static struct kmem_cache *nfs_rdata_cachep; -struct nfs_read_header *nfs_readhdr_alloc(unsigned int pagecount) +struct nfs_read_header *nfs_readhdr_alloc() { - struct nfs_read_header *p; + struct nfs_read_header *rhdr; - p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); - if (p) { - struct nfs_pgio_header *hdr = &p->header; - struct nfs_read_data *data = &p->rpc_data; + rhdr = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); + if (rhdr) { + struct nfs_pgio_header *hdr = &rhdr->header; INIT_LIST_HEAD(&hdr->pages); - INIT_LIST_HEAD(&data->list); + INIT_LIST_HEAD(&hdr->rpc_list); + spin_lock_init(&hdr->lock); + atomic_set(&hdr->refcnt, 0); + } + return rhdr; +} + +struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount) +{ + struct nfs_read_data *data, *prealloc; + + prealloc = &container_of(hdr, struct nfs_read_header, header)->rpc_data; + if (prealloc->header == NULL) + data = prealloc; + else + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out; + + if (nfs_pgarray_set(&data->pages, pagecount)) { data->header = hdr; - if (!nfs_pgarray_set(&data->pages, pagecount)) { - kmem_cache_free(nfs_rdata_cachep, p); - p = NULL; - } + atomic_inc(&hdr->refcnt); + } else { + if (data != prealloc) + kfree(data); + data = NULL; } - return p; +out: + return data; } void nfs_readhdr_free(struct nfs_pgio_header *hdr) @@ -64,10 +84,18 @@ void nfs_readhdr_free(struct nfs_pgio_header *hdr) void nfs_readdata_release(struct nfs_read_data *rdata) { + struct nfs_pgio_header *hdr = rdata->header; + struct nfs_read_header *read_header = container_of(hdr, struct nfs_read_header, header); + put_nfs_open_context(rdata->args.context); if (rdata->pages.pagevec != rdata->pages.page_array) kfree(rdata->pages.pagevec); - nfs_readhdr_free(rdata->header); + if (rdata != &read_header->rpc_data) + kfree(rdata); + else + rdata->header = NULL; + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_read_completion(hdr); } static @@ -79,35 +107,6 @@ int nfs_return_empty_page(struct page *page) return 0; } -static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data) -{ - unsigned int remainder = data->args.count - data->res.count; - unsigned int base = data->args.pgbase + data->res.count; - unsigned int pglen; - struct page **pages; - - if (data->res.eof == 0 || remainder == 0) - return; - /* - * Note: "remainder" can never be negative, since we check for - * this in the XDR code. - */ - pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; - base &= ~PAGE_CACHE_MASK; - pglen = PAGE_CACHE_SIZE - base; - for (;;) { - if (remainder <= pglen) { - zero_user(*pages, base, remainder); - break; - } - zero_user(*pages, base, pglen); - pages++; - remainder -= pglen; - pglen = PAGE_CACHE_SIZE; - base = 0; - } -} - void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, struct inode *inode) { @@ -170,6 +169,46 @@ static void nfs_readpage_release(struct nfs_page *req) nfs_release_request(req); } +/* Note io was page aligned */ +void nfs_read_completion(struct nfs_pgio_header *hdr) +{ + unsigned long bytes = 0; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out; + if (!test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { + if (bytes > hdr->good_bytes) + zero_user(page, 0, PAGE_SIZE); + else if (hdr->good_bytes - bytes < PAGE_SIZE) + zero_user_segment(page, + hdr->good_bytes & ~PAGE_MASK, + PAGE_SIZE); + } + SetPageUptodate(page); + nfs_list_remove_request(req); + nfs_readpage_release(req); + bytes += PAGE_SIZE; + } + } else { + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + bytes += req->wb_bytes; + if (bytes <= hdr->good_bytes) + SetPageUptodate(req->wb_page); + nfs_list_remove_request(req); + nfs_readpage_release(req); + } + } +out: + hdr->release(hdr); +} + int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops) @@ -214,16 +253,12 @@ EXPORT_SYMBOL_GPL(nfs_initiate_read); /* * Set up the NFS read request struct */ -static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, +static void nfs_read_rpcsetup(struct nfs_read_data *data, unsigned int count, unsigned int offset) { - struct inode *inode = data->header->inode; - - data->header->req = req; - data->header->inode = inode; - data->header->cred = req->wb_context->cred; + struct nfs_page *req = data->header->req; - data->args.fh = NFS_FH(inode); + data->args.fh = NFS_FH(data->header->inode); data->args.offset = req_offset(req) + offset; data->args.pgbase = req->wb_pgbase + offset; data->args.pages = data->pages.pagevec; @@ -255,7 +290,7 @@ nfs_do_multiple_reads(struct list_head *head, while (!list_empty(head)) { int ret2; - data = list_entry(head->next, struct nfs_read_data, list); + data = list_first_entry(head, struct nfs_read_data, list); list_del_init(&data->list); ret2 = nfs_do_read(data, call_ops); @@ -265,7 +300,7 @@ nfs_do_multiple_reads(struct list_head *head, return ret; } -static void +void nfs_async_read_error(struct list_head *head) { struct nfs_page *req; @@ -290,11 +325,11 @@ nfs_async_read_error(struct list_head *head) * won't see the new data until our attribute cache is updated. This is more * or less conventional NFS client behavior. */ -static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head *res) +static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { - struct nfs_page *req = nfs_list_entry(desc->pg_list.next); + struct nfs_page *req = hdr->req; struct page *page = req->wb_page; - struct nfs_read_header *rhdr; struct nfs_read_data *data; size_t rsize = desc->pg_bsize, nbytes; unsigned int offset; @@ -302,85 +337,97 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head int ret = 0; nfs_list_remove_request(req); + nfs_list_add_request(req, &hdr->pages); offset = 0; nbytes = desc->pg_count; do { size_t len = min(nbytes,rsize); - rhdr = nfs_readhdr_alloc(1); - if (!rhdr) + data = nfs_readdata_alloc(hdr, 1); + if (!data) goto out_bad; - data = &rhdr->rpc_data; data->pages.pagevec[0] = page; - nfs_read_rpcsetup(req, data, len, offset); - list_add(&data->list, res); + nfs_read_rpcsetup(data, len, offset); + list_add(&data->list, &hdr->rpc_list); requests++; nbytes -= len; offset += len; } while(nbytes != 0); - atomic_set(&req->wb_complete, requests); - desc->pg_rpc_callops = &nfs_read_partial_ops; + desc->pg_rpc_callops = &nfs_read_common_ops; return ret; out_bad: - while (!list_empty(res)) { - data = list_entry(res->next, struct nfs_read_data, list); + while (!list_empty(&hdr->rpc_list)) { + data = list_first_entry(&hdr->rpc_list, struct nfs_read_data, list); list_del(&data->list); nfs_readdata_release(data); } - nfs_readpage_release(req); + nfs_async_read_error(&hdr->pages); return -ENOMEM; } -static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head *res) +static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { struct nfs_page *req; struct page **pages; - struct nfs_read_header *rhdr; - struct nfs_read_data *data; + struct nfs_read_data *data; struct list_head *head = &desc->pg_list; int ret = 0; - rhdr = nfs_readhdr_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!rhdr) { + data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!data) { nfs_async_read_error(head); ret = -ENOMEM; goto out; } - data = &rhdr->rpc_data; pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &rhdr->header.pages); + nfs_list_add_request(req, &hdr->pages); *pages++ = req->wb_page; } - req = nfs_list_entry(rhdr->header.pages.next); - nfs_read_rpcsetup(req, data, desc->pg_count, 0); - list_add(&data->list, res); - desc->pg_rpc_callops = &nfs_read_full_ops; + nfs_read_rpcsetup(data, desc->pg_count, 0); + list_add(&data->list, &hdr->rpc_list); + desc->pg_rpc_callops = &nfs_read_common_ops; out: return ret; } -int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct list_head *head) +int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { if (desc->pg_bsize < PAGE_CACHE_SIZE) - return nfs_pagein_multi(desc, head); - return nfs_pagein_one(desc, head); + return nfs_pagein_multi(desc, hdr); + return nfs_pagein_one(desc, hdr); } static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_read_header *rhdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_pagein(desc, &head); + rhdr = nfs_readhdr_alloc(); + if (!rhdr) { + nfs_async_read_error(&desc->pg_list); + return -ENOMEM; + } + hdr = &rhdr->header; + nfs_pgheader_init(desc, hdr, nfs_readhdr_free); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_pagein(desc, hdr); if (ret == 0) - ret = nfs_do_multiple_reads(&head, desc->pg_rpc_callops); + ret = nfs_do_multiple_reads(&hdr->rpc_list, + desc->pg_rpc_callops); + else + set_bit(NFS_IOHDR_REDO, &hdr->flags); + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_read_completion(hdr); return ret; } @@ -419,15 +466,13 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data struct nfs_readargs *argp = &data->args; struct nfs_readres *resp = &data->res; - if (resp->eof || resp->count == argp->count) - return; - /* This is a short read! */ nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD); /* Has the server at least made some progress? */ - if (resp->count == 0) + if (resp->count == 0) { + nfs_set_pgio_error(data->header, -EIO, argp->offset); return; - + } /* Yes, so retry the read at the end of the data */ data->mds_offset += resp->count; argp->offset += resp->count; @@ -436,38 +481,34 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data rpc_restart_call_prepare(task); } -/* - * Handle a read reply that fills part of a page. - */ -static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata) +static void nfs_readpage_result_common(struct rpc_task *task, void *calldata) { struct nfs_read_data *data = calldata; - + struct nfs_pgio_header *hdr = data->header; + + /* Note the only returns of nfs_readpage_result are 0 and -EAGAIN */ if (nfs_readpage_result(task, data) != 0) return; if (task->tk_status < 0) - return; - - nfs_readpage_truncate_uninitialised_page(data); - nfs_readpage_retry(task, data); + nfs_set_pgio_error(hdr, task->tk_status, data->args.offset); + else if (data->res.eof) { + loff_t bound; + + bound = data->args.offset + data->res.count; + spin_lock(&hdr->lock); + if (bound < hdr->io_start + hdr->good_bytes) { + set_bit(NFS_IOHDR_EOF, &hdr->flags); + clear_bit(NFS_IOHDR_ERROR, &hdr->flags); + hdr->good_bytes = bound - hdr->io_start; + } + spin_unlock(&hdr->lock); + } else if (data->res.count != data->args.count) + nfs_readpage_retry(task, data); } -static void nfs_readpage_release_partial(void *calldata) +static void nfs_readpage_release_common(void *calldata) { - struct nfs_read_data *data = calldata; - struct nfs_page *req = data->header->req; - struct page *page = req->wb_page; - int status = data->task.tk_status; - - if (status < 0) - set_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags); - - if (atomic_dec_and_test(&req->wb_complete)) { - if (!test_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags)) - SetPageUptodate(page); - nfs_readpage_release(req); - } - nfs_readdata_release(data); + nfs_readdata_release(calldata); } void nfs_read_prepare(struct rpc_task *task, void *calldata) @@ -476,75 +517,10 @@ void nfs_read_prepare(struct rpc_task *task, void *calldata) NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data); } -static const struct rpc_call_ops nfs_read_partial_ops = { - .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_readpage_result_partial, - .rpc_release = nfs_readpage_release_partial, -}; - -static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data) -{ - unsigned int count = data->res.count; - unsigned int base = data->args.pgbase; - struct page **pages; - - if (data->res.eof) - count = data->args.count; - if (unlikely(count == 0)) - return; - pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; - base &= ~PAGE_CACHE_MASK; - count += base; - for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++) - SetPageUptodate(*pages); - if (count == 0) - return; - /* Was this a short read? */ - if (data->res.eof || data->res.count == data->args.count) - SetPageUptodate(*pages); -} - -/* - * This is the callback from RPC telling us whether a reply was - * received or some error occurred (timeout or socket shutdown). - */ -static void nfs_readpage_result_full(struct rpc_task *task, void *calldata) -{ - struct nfs_read_data *data = calldata; - - if (nfs_readpage_result(task, data) != 0) - return; - if (task->tk_status < 0) - return; - /* - * Note: nfs_readpage_retry may change the values of - * data->args. In the multi-page case, we therefore need - * to ensure that we call nfs_readpage_set_pages_uptodate() - * first. - */ - nfs_readpage_truncate_uninitialised_page(data); - nfs_readpage_set_pages_uptodate(data); - nfs_readpage_retry(task, data); -} - -static void nfs_readpage_release_full(void *calldata) -{ - struct nfs_read_data *data = calldata; - struct nfs_pgio_header *hdr = data->header; - - while (!list_empty(&hdr->pages)) { - struct nfs_page *req = nfs_list_entry(hdr->pages.next); - - nfs_list_remove_request(req); - nfs_readpage_release(req); - } - nfs_readdata_release(calldata); -} - -static const struct rpc_call_ops nfs_read_full_ops = { +static const struct rpc_call_ops nfs_read_common_ops = { .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_readpage_result_full, - .rpc_release = nfs_readpage_release_full, + .rpc_call_done = nfs_readpage_result_common, + .rpc_release = nfs_readpage_release_common, }; /* diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index eac30d6bec17..5c520344d8ad 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -27,7 +27,6 @@ enum { PG_CLEAN, PG_NEED_COMMIT, PG_NEED_RESCHED, - PG_PARTIAL_READ_FAILED, PG_COMMIT_TO_DS, }; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e34beaf86e9c..164862148ba0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1187,14 +1187,30 @@ struct nfs_read_data { struct nfs_client *ds_clp; /* pNFS data server */ }; +/* used as flag bits in nfs_pgio_header */ +enum { + NFS_IOHDR_ERROR = 0, + NFS_IOHDR_EOF, + NFS_IOHDR_REDO, +}; + struct nfs_pgio_header { struct inode *inode; struct rpc_cred *cred; struct list_head pages; + struct list_head rpc_list; + atomic_t refcnt; struct nfs_page *req; struct pnfs_layout_segment *lseg; + loff_t io_start; const struct rpc_call_ops *mds_ops; + void (*release) (struct nfs_pgio_header *hdr); + spinlock_t lock; + /* fields protected by lock */ int pnfs_error; + int error; /* merge with pnfs_error */ + unsigned long good_bytes; /* boundary of good data */ + unsigned long flags; }; struct nfs_read_header { -- cgit v1.2.3 From 6c75dc0d498caa402fb17b1bf769835a9db875c8 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:47 -0400 Subject: NFS: merge _full and _partial write rpc_ops Decouple nfs_pgio_header and nfs_write_data, and have (possibly multiple) nfs_write_datas each take a refcount on nfs_pgio_header. For the moment keeps nfs_write_header as a way to preallocate a single nfs_write_data with the nfs_pgio_header. The code doesn't need this, and would be prettier without, but given the amount of churn I am already introducing I didn't want to play with tuning new mempools. This also fixes bug in pnfs_ld_handle_write_error. In the case of desc->pg_bsize < PAGE_CACHE_SIZE, the pages list was empty, causing replay attempt to do nothing. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 10 +- fs/nfs/internal.h | 8 +- fs/nfs/nfs4filelayout.c | 1 - fs/nfs/nfs4proc.c | 4 +- fs/nfs/pnfs.c | 58 +++++--- fs/nfs/write.c | 383 ++++++++++++++++++++++-------------------------- include/linux/nfs_xdr.h | 2 + 7 files changed, 227 insertions(+), 239 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 90b00ce42cbe..22a40c408449 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -768,11 +768,17 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, bytes = min(wsize,count); result = -ENOMEM; - whdr = nfs_writehdr_alloc(nfs_page_array_len(pgbase, bytes)); + whdr = nfs_writehdr_alloc(); if (unlikely(!whdr)) break; - data = &whdr->rpc_data; + data = nfs_writedata_alloc(&whdr->header, nfs_page_array_len(pgbase, bytes)); + if (!data) { + nfs_writehdr_free(&whdr->header); + break; + } + data->header = &whdr->header; + atomic_inc(&data->header->refcnt); pages = &data->pages; down_read(¤t->mm->mmap_sem); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 33af5e51c0bb..16bc9c47c83e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -319,10 +319,14 @@ extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); /* write.c */ -extern struct nfs_write_header *nfs_writehdr_alloc(unsigned int npages); +extern void nfs_async_write_error(struct list_head *head); +extern struct nfs_write_header *nfs_writehdr_alloc(void); extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); +extern struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount); +extern void nfs_write_completion(struct nfs_pgio_header *hdr); extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, - struct list_head *head); + struct nfs_pgio_header *hdr); extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 333e765f3ac2..02d8170ce0f3 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -314,7 +314,6 @@ static void filelayout_write_release(void *data) { struct nfs_write_data *wdata = data; - put_lseg(wdata->header->lseg); wdata->header->mds_ops->rpc_release(data); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ce31ab22bc55..87af80d28a82 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3431,8 +3431,6 @@ void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data) struct inode *inode = hdr->inode; dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(hdr->lseg); - hdr->lseg = NULL; data->ds_clp = NULL; data->write_done_cb = nfs4_write_done_cb; data->args.fh = NFS_FH(inode); @@ -3448,7 +3446,7 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag { struct nfs_server *server = NFS_SERVER(data->header->inode); - if (data->header->lseg) { + if (data->ds_clp) { data->args.bitmask = NULL; data->res.fattr = NULL; } else diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d1a91dbe7654..d515f00614cd 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1199,7 +1199,9 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data) clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); pnfs_return_layout(hdr->inode); } - data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, &hdr->pages); + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) + data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, + &hdr->pages); } /* @@ -1214,7 +1216,6 @@ void pnfs_ld_write_done(struct nfs_write_data *data) hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_write_error(data); - put_lseg(hdr->lseg); hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_write_done); @@ -1225,12 +1226,11 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, { struct nfs_pgio_header *hdr = data->header; - list_splice_tail_init(&hdr->pages, &desc->pg_list); - if (hdr->req && list_empty(&hdr->req->wb_list)) - nfs_list_add_request(hdr->req, &desc->pg_list); - nfs_pageio_reset_write_mds(desc); - desc->pg_recoalesce = 1; - put_lseg(hdr->lseg); + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + list_splice_tail_init(&hdr->pages, &desc->pg_list); + nfs_pageio_reset_write_mds(desc); + desc->pg_recoalesce = 1; + } nfs_writedata_release(data); } @@ -1246,18 +1246,12 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata, struct nfs_server *nfss = NFS_SERVER(inode); hdr->mds_ops = call_ops; - hdr->lseg = get_lseg(lseg); dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__, inode->i_ino, wdata->args.count, wdata->args.offset, how); - trypnfs = nfss->pnfs_curr_ld->write_pagelist(wdata, how); - if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(hdr->lseg); - hdr->lseg = NULL; - } else + if (trypnfs != PNFS_NOT_ATTEMPTED) nfs_inc_stats(inode, NFSIOS_PNFS_WRITE); - dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); return trypnfs; } @@ -1273,7 +1267,7 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he while (!list_empty(head)) { enum pnfs_try_status trypnfs; - data = list_entry(head->next, struct nfs_write_data, list); + data = list_first_entry(head, struct nfs_write_data, list); list_del_init(&data->list); trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how); @@ -1283,20 +1277,40 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he put_lseg(lseg); } +static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) +{ + put_lseg(hdr->lseg); + nfs_writehdr_free(hdr); +} + int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_write_header *whdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_flush(desc, &head); - if (ret != 0) { + whdr = nfs_writehdr_alloc(); + if (!whdr) { + nfs_async_write_error(&desc->pg_list); put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; - return ret; + return -ENOMEM; } - pnfs_do_multiple_writes(desc, &head, desc->pg_ioflags); - return 0; + hdr = &whdr->header; + nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); + hdr->lseg = get_lseg(desc->pg_lseg); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_flush(desc, hdr); + if (ret != 0) { + put_lseg(desc->pg_lseg); + desc->pg_lseg = NULL; + set_bit(NFS_IOHDR_REDO, &hdr->flags); + } else + pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags); + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_write_completion(hdr); + return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2efae049b4f0..076075eb676c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -42,8 +42,7 @@ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc, struct inode *inode, int ioflags); static void nfs_redirty_request(struct nfs_page *req); -static const struct rpc_call_ops nfs_write_partial_ops; -static const struct rpc_call_ops nfs_write_full_ops; +static const struct rpc_call_ops nfs_write_common_ops; static const struct rpc_call_ops nfs_commit_ops; static struct kmem_cache *nfs_wdata_cachep; @@ -69,26 +68,47 @@ void nfs_commit_free(struct nfs_commit_data *p) } EXPORT_SYMBOL_GPL(nfs_commit_free); -struct nfs_write_header *nfs_writehdr_alloc(unsigned int pagecount) +struct nfs_write_header *nfs_writehdr_alloc(void) { struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); if (p) { struct nfs_pgio_header *hdr = &p->header; - struct nfs_write_data *data = &p->rpc_data; memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&hdr->pages); - INIT_LIST_HEAD(&data->list); - data->header = hdr; - if (!nfs_pgarray_set(&data->pages, pagecount)) { - mempool_free(p, nfs_wdata_mempool); - p = NULL; - } + INIT_LIST_HEAD(&hdr->rpc_list); + spin_lock_init(&hdr->lock); + atomic_set(&hdr->refcnt, 0); } return p; } +struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount) +{ + struct nfs_write_data *data, *prealloc; + + prealloc = &container_of(hdr, struct nfs_write_header, header)->rpc_data; + if (prealloc->header == NULL) + data = prealloc; + else + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out; + + if (nfs_pgarray_set(&data->pages, pagecount)) { + data->header = hdr; + atomic_inc(&hdr->refcnt); + } else { + if (data != prealloc) + kfree(data); + data = NULL; + } +out: + return data; +} + void nfs_writehdr_free(struct nfs_pgio_header *hdr) { struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); @@ -97,10 +117,18 @@ void nfs_writehdr_free(struct nfs_pgio_header *hdr) void nfs_writedata_release(struct nfs_write_data *wdata) { + struct nfs_pgio_header *hdr = wdata->header; + struct nfs_write_header *write_header = container_of(hdr, struct nfs_write_header, header); + put_nfs_open_context(wdata->args.context); if (wdata->pages.pagevec != wdata->pages.page_array) kfree(wdata->pages.pagevec); - nfs_writehdr_free(wdata->header); + if (wdata != &write_header->rpc_data) + kfree(wdata); + else + wdata->header = NULL; + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_write_completion(hdr); } static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) @@ -511,20 +539,6 @@ int nfs_write_need_commit(struct nfs_write_data *data) return data->verf.committed != NFS_FILE_SYNC; } -static inline -int nfs_reschedule_unstable_write(struct nfs_page *req, - struct nfs_write_data *data) -{ - if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) { - nfs_mark_request_commit(req, data->header->lseg); - return 1; - } - if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) { - nfs_mark_request_dirty(req); - return 1; - } - return 0; -} #else static void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) @@ -542,13 +556,43 @@ int nfs_write_need_commit(struct nfs_write_data *data) return 0; } -static inline -int nfs_reschedule_unstable_write(struct nfs_page *req, - struct nfs_write_data *data) +#endif + +void nfs_write_completion(struct nfs_pgio_header *hdr) { - return 0; + unsigned long bytes = 0; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out; + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + bytes += req->wb_bytes; + nfs_list_remove_request(req); + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && + (hdr->good_bytes < bytes)) { + nfs_set_pageerror(page); + nfs_context_set_write_error(req->wb_context, hdr->error); + goto remove_req; + } + if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) { + nfs_mark_request_dirty(req); + goto next; + } + if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { + nfs_mark_request_commit(req, hdr->lseg); + goto next; + } +remove_req: + nfs_inode_remove_request(req); +next: + nfs_unlock_request(req); + nfs_end_page_writeback(page); + } +out: + hdr->release(hdr); } -#endif #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) static int @@ -813,17 +857,6 @@ int nfs_updatepage(struct file *file, struct page *page, return status; } -static void nfs_writepage_release(struct nfs_page *req, - struct nfs_write_data *data) -{ - struct page *page = req->wb_page; - - if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req, data)) - nfs_inode_remove_request(req); - nfs_unlock_request(req); - nfs_end_page_writeback(page); -} - static int flush_task_priority(int how) { switch (how & (FLUSH_HIGHPRI|FLUSH_LOWPRI)) { @@ -890,22 +923,16 @@ EXPORT_SYMBOL_GPL(nfs_initiate_write); /* * Set up the argument/result storage required for the RPC call. */ -static void nfs_write_rpcsetup(struct nfs_page *req, - struct nfs_write_data *data, +static void nfs_write_rpcsetup(struct nfs_write_data *data, unsigned int count, unsigned int offset, int how) { - struct nfs_pgio_header *hdr = data->header; - struct inode *inode = req->wb_context->dentry->d_inode; + struct nfs_page *req = data->header->req; /* Set up the RPC argument and reply structs * NB: take care not to mess about with data->commit et al. */ - hdr->req = req; - hdr->inode = inode = req->wb_context->dentry->d_inode; - hdr->cred = req->wb_context->cred; - - data->args.fh = NFS_FH(inode); + data->args.fh = NFS_FH(data->header->inode); data->args.offset = req_offset(req) + offset; /* pnfs_set_layoutcommit needs this */ data->mds_offset = data->args.offset; @@ -919,7 +946,7 @@ static void nfs_write_rpcsetup(struct nfs_page *req, case 0: break; case FLUSH_COND_STABLE: - if (nfs_need_commit(NFS_I(inode))) + if (nfs_need_commit(NFS_I(data->header->inode))) break; default: data->args.stable = NFS_FILE_SYNC; @@ -950,7 +977,7 @@ static int nfs_do_multiple_writes(struct list_head *head, while (!list_empty(head)) { int ret2; - data = list_entry(head->next, struct nfs_write_data, list); + data = list_first_entry(head, struct nfs_write_data, list); list_del_init(&data->list); ret2 = nfs_do_write(data, call_ops, how); @@ -973,15 +1000,26 @@ static void nfs_redirty_request(struct nfs_page *req) nfs_end_page_writeback(page); } +void nfs_async_write_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_redirty_request(req); + } +} + /* * Generate multiple small requests to write out a single * contiguous dirty area on one page. */ -static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head *res) +static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { - struct nfs_page *req = nfs_list_entry(desc->pg_list.next); + struct nfs_page *req = hdr->req; struct page *page = req->wb_page; - struct nfs_write_header *whdr; struct nfs_write_data *data; size_t wsize = desc->pg_bsize, nbytes; unsigned int offset; @@ -989,6 +1027,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head int ret = 0; nfs_list_remove_request(req); + nfs_list_add_request(req, &hdr->pages); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit || @@ -1001,28 +1040,27 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head do { size_t len = min(nbytes, wsize); - whdr = nfs_writehdr_alloc(1); - if (!whdr) + data = nfs_writedata_alloc(hdr, 1); + if (!data) goto out_bad; - data = &whdr->rpc_data; data->pages.pagevec[0] = page; - nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags); - list_add(&data->list, res); + nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags); + list_add(&data->list, &hdr->rpc_list); requests++; nbytes -= len; offset += len; } while (nbytes != 0); atomic_set(&req->wb_complete, requests); - desc->pg_rpc_callops = &nfs_write_partial_ops; + desc->pg_rpc_callops = &nfs_write_common_ops; return ret; out_bad: - while (!list_empty(res)) { - data = list_entry(res->next, struct nfs_write_data, list); + while (!list_empty(&hdr->rpc_list)) { + data = list_first_entry(&hdr->rpc_list, struct nfs_write_data, list); list_del(&data->list); nfs_writedata_release(data); } - nfs_redirty_request(req); + nfs_async_write_error(&hdr->pages); return -ENOMEM; } @@ -1034,64 +1072,74 @@ out_bad: * This is the case if nfs_updatepage detects a conflicting request * that has been written but not committed. */ -static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *res) +static int nfs_flush_one(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { struct nfs_page *req; struct page **pages; - struct nfs_write_header *whdr; struct nfs_write_data *data; struct list_head *head = &desc->pg_list; int ret = 0; - whdr = nfs_writehdr_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); - if (!whdr) { - while (!list_empty(head)) { - req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_redirty_request(req); - } + data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base, + desc->pg_count)); + if (!data) { + nfs_async_write_error(head); ret = -ENOMEM; goto out; } - data = &whdr->rpc_data; + pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &whdr->header.pages); + nfs_list_add_request(req, &hdr->pages); *pages++ = req->wb_page; } - req = nfs_list_entry(whdr->header.pages.next); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) desc->pg_ioflags &= ~FLUSH_COND_STABLE; /* Set up the argument struct */ - nfs_write_rpcsetup(req, data, desc->pg_count, 0, desc->pg_ioflags); - list_add(&data->list, res); - desc->pg_rpc_callops = &nfs_write_full_ops; + nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags); + list_add(&data->list, &hdr->rpc_list); + desc->pg_rpc_callops = &nfs_write_common_ops; out: return ret; } -int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct list_head *head) +int nfs_generic_flush(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { if (desc->pg_bsize < PAGE_CACHE_SIZE) - return nfs_flush_multi(desc, head); - return nfs_flush_one(desc, head); + return nfs_flush_multi(desc, hdr); + return nfs_flush_one(desc, hdr); } static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_write_header *whdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_flush(desc, &head); + whdr = nfs_writehdr_alloc(); + if (!whdr) { + nfs_async_write_error(&desc->pg_list); + return -ENOMEM; + } + hdr = &whdr->header; + nfs_pgheader_init(desc, hdr, nfs_writehdr_free); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_flush(desc, hdr); if (ret == 0) - ret = nfs_do_multiple_writes(&head, desc->pg_rpc_callops, - desc->pg_ioflags); + ret = nfs_do_multiple_writes(&hdr->rpc_list, + desc->pg_rpc_callops, + desc->pg_ioflags); + else + set_bit(NFS_IOHDR_REDO, &hdr->flags); + if (atomic_dec_and_test(&hdr->refcnt)) + nfs_write_completion(hdr); return ret; } @@ -1121,62 +1169,6 @@ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, nfs_pageio_init_write_mds(pgio, inode, ioflags); } -/* - * Handle a write reply that flushed part of a page. - */ -static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata) -{ - struct nfs_write_data *data = calldata; - - dprintk("NFS: %5u write(%s/%lld %d@%lld)", - task->tk_pid, - data->header->inode->i_sb->s_id, - (long long) - NFS_FILEID(data->header->inode), - data->header->req->wb_bytes, - (long long)req_offset(data->header->req)); - - nfs_writeback_done(task, data); -} - -static void nfs_writeback_release_partial(void *calldata) -{ - struct nfs_write_data *data = calldata; - struct nfs_page *req = data->header->req; - struct page *page = req->wb_page; - int status = data->task.tk_status; - - if (status < 0) { - nfs_set_pageerror(page); - nfs_context_set_write_error(req->wb_context, status); - dprintk(", error = %d\n", status); - goto out; - } - - if (nfs_write_need_commit(data)) { - struct inode *inode = page->mapping->host; - - spin_lock(&inode->i_lock); - if (test_bit(PG_NEED_RESCHED, &req->wb_flags)) { - /* Do nothing we need to resend the writes */ - } else if (!test_and_set_bit(PG_NEED_COMMIT, &req->wb_flags)) { - memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - dprintk(" defer commit\n"); - } else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_verf))) { - set_bit(PG_NEED_RESCHED, &req->wb_flags); - clear_bit(PG_NEED_COMMIT, &req->wb_flags); - dprintk(" server reboot detected\n"); - } - spin_unlock(&inode->i_lock); - } else - dprintk(" OK\n"); - -out: - if (atomic_dec_and_test(&req->wb_complete)) - nfs_writepage_release(req, data); - nfs_writedata_release(data); -} - void nfs_write_prepare(struct rpc_task *task, void *calldata) { struct nfs_write_data *data = calldata; @@ -1190,12 +1182,6 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); } -static const struct rpc_call_ops nfs_write_partial_ops = { - .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_writeback_done_partial, - .rpc_release = nfs_writeback_release_partial, -}; - /* * Handle a write reply that flushes a whole page. * @@ -1203,60 +1189,37 @@ static const struct rpc_call_ops nfs_write_partial_ops = { * writebacks since the page->count is kept > 1 for as long * as the page has a write request pending. */ -static void nfs_writeback_done_full(struct rpc_task *task, void *calldata) +static void nfs_writeback_done_common(struct rpc_task *task, void *calldata) { struct nfs_write_data *data = calldata; nfs_writeback_done(task, data); } -static void nfs_writeback_release_full(void *calldata) +static void nfs_writeback_release_common(void *calldata) { struct nfs_write_data *data = calldata; struct nfs_pgio_header *hdr = data->header; int status = data->task.tk_status; + struct nfs_page *req = hdr->req; - /* Update attributes as result of writeback. */ - while (!list_empty(&hdr->pages)) { - struct nfs_page *req = nfs_list_entry(hdr->pages.next); - struct page *page = req->wb_page; - - nfs_list_remove_request(req); - - dprintk("NFS: %5u write (%s/%lld %d@%lld)", - data->task.tk_pid, - req->wb_context->dentry->d_inode->i_sb->s_id, - (long long)NFS_FILEID(req->wb_context->dentry->d_inode), - req->wb_bytes, - (long long)req_offset(req)); - - if (status < 0) { - nfs_set_pageerror(page); - nfs_context_set_write_error(req->wb_context, status); - dprintk(", error = %d\n", status); - goto remove_request; - } - - if (nfs_write_need_commit(data)) { + if ((status >= 0) && nfs_write_need_commit(data)) { + spin_lock(&hdr->lock); + if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) + ; /* Do nothing */ + else if (!test_and_set_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - nfs_mark_request_commit(req, hdr->lseg); - dprintk(" marked for commit\n"); - goto next; - } - dprintk(" OK\n"); -remove_request: - nfs_inode_remove_request(req); - next: - nfs_unlock_request(req); - nfs_end_page_writeback(page); + else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_verf))) + set_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags); + spin_unlock(&hdr->lock); } nfs_writedata_release(data); } -static const struct rpc_call_ops nfs_write_full_ops = { +static const struct rpc_call_ops nfs_write_common_ops = { .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_writeback_done_full, - .rpc_release = nfs_writeback_release_full, + .rpc_call_done = nfs_writeback_done_common, + .rpc_release = nfs_writeback_release_common, }; @@ -1307,38 +1270,40 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) } } #endif - /* Is this a short write? */ - if (task->tk_status >= 0 && resp->count < argp->count) { + if (task->tk_status < 0) + nfs_set_pgio_error(data->header, task->tk_status, argp->offset); + else if (resp->count < argp->count) { static unsigned long complain; + /* This a short write! */ nfs_inc_stats(inode, NFSIOS_SHORTWRITE); /* Has the server at least made some progress? */ - if (resp->count != 0) { - /* Was this an NFSv2 write or an NFSv3 stable write? */ - if (resp->verf->committed != NFS_UNSTABLE) { - /* Resend from where the server left off */ - data->mds_offset += resp->count; - argp->offset += resp->count; - argp->pgbase += resp->count; - argp->count -= resp->count; - } else { - /* Resend as a stable write in order to avoid - * headaches in the case of a server crash. - */ - argp->stable = NFS_FILE_SYNC; + if (resp->count == 0) { + if (time_before(complain, jiffies)) { + printk(KERN_WARNING + "NFS: Server wrote zero bytes, expected %u.\n", + argp->count); + complain = jiffies + 300 * HZ; } - rpc_restart_call_prepare(task); + nfs_set_pgio_error(data->header, -EIO, argp->offset); + task->tk_status = -EIO; return; } - if (time_before(complain, jiffies)) { - printk(KERN_WARNING - "NFS: Server wrote zero bytes, expected %u.\n", - argp->count); - complain = jiffies + 300 * HZ; + /* Was this an NFSv2 write or an NFSv3 stable write? */ + if (resp->verf->committed != NFS_UNSTABLE) { + /* Resend from where the server left off */ + data->mds_offset += resp->count; + argp->offset += resp->count; + argp->pgbase += resp->count; + argp->count -= resp->count; + } else { + /* Resend as a stable write in order to avoid + * headaches in the case of a server crash. + */ + argp->stable = NFS_FILE_SYNC; } - /* Can't do anything about it except throw an error. */ - task->tk_status = -EIO; + rpc_restart_call_prepare(task); } } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 164862148ba0..0d17db7973de 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1192,6 +1192,8 @@ enum { NFS_IOHDR_ERROR = 0, NFS_IOHDR_EOF, NFS_IOHDR_REDO, + NFS_IOHDR_NEED_COMMIT, + NFS_IOHDR_NEED_RESCHED, }; struct nfs_pgio_header { -- cgit v1.2.3 From 061ae2edb7375ab6776468b075da71008a098b55 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:48 -0400 Subject: NFS: create completion structure to pass into page_init functions Factors out the code that will need to change when directio starts using these code paths. This will allow directio to use the generic pagein and flush routines Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 11 +++++------ fs/nfs/pagelist.c | 3 +++ fs/nfs/pnfs.c | 39 +++++++++++++++++++++++++-------------- fs/nfs/pnfs.h | 6 ++++-- fs/nfs/read.c | 36 ++++++++++++++++++++++-------------- fs/nfs/write.c | 41 ++++++++++++++++++++++++++--------------- include/linux/nfs_page.h | 2 ++ include/linux/nfs_xdr.h | 6 ++++++ 8 files changed, 93 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 16bc9c47c83e..3ef8fcda1a5f 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -300,11 +300,10 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh); #endif +struct nfs_pgio_completion_ops; /* read.c */ -extern void nfs_async_read_error(struct list_head *head); extern struct nfs_read_header *nfs_readhdr_alloc(void); extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); -extern void nfs_read_completion(struct nfs_pgio_header *hdr); extern struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, unsigned int pagecount); extern int nfs_initiate_read(struct rpc_clnt *clnt, @@ -314,21 +313,21 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr); extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode); + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); /* write.c */ -extern void nfs_async_write_error(struct list_head *head); extern struct nfs_write_header *nfs_writehdr_alloc(void); extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); extern struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr, unsigned int pagecount); -extern void nfs_write_completion(struct nfs_pgio_header *hdr); extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr); extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags); + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_writedata_release(struct nfs_write_data *wdata); extern void nfs_commit_free(struct nfs_commit_data *p); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index cd4c038135a7..4cf2a68493e0 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -49,6 +49,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->io_start = req_offset(hdr->req); hdr->good_bytes = desc->pg_count; hdr->release = release; + hdr->completion_ops = desc->pg_completion_ops; } void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) @@ -240,6 +241,7 @@ EXPORT_SYMBOL_GPL(nfs_generic_pg_test); void nfs_pageio_init(struct nfs_pageio_descriptor *desc, struct inode *inode, const struct nfs_pageio_ops *pg_ops, + const struct nfs_pgio_completion_ops *compl_ops, size_t bsize, int io_flags) { @@ -252,6 +254,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_recoalesce = 0; desc->pg_inode = inode; desc->pg_ops = pg_ops; + desc->pg_completion_ops = compl_ops; desc->pg_ioflags = io_flags; desc->pg_error = 0; desc->pg_lseg = NULL; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d515f00614cd..b3a0c01718af 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1113,26 +1113,31 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page * EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write); bool -pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode) +pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_server *server = NFS_SERVER(inode); struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; if (ld == NULL) return false; - nfs_pageio_init(pgio, inode, ld->pg_read_ops, server->rsize, 0); + nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, + server->rsize, 0); return true; } bool -pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags) +pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, + int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_server *server = NFS_SERVER(inode); struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; if (ld == NULL) return false; - nfs_pageio_init(pgio, inode, ld->pg_write_ops, server->wsize, ioflags); + nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, + server->wsize, ioflags); return true; } @@ -1162,13 +1167,15 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, } EXPORT_SYMBOL_GPL(pnfs_generic_pg_test); -static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head) +static int pnfs_write_done_resend_to_mds(struct inode *inode, + struct list_head *head, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_pageio_descriptor pgio; LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE); + nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops); while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1201,7 +1208,8 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data) } if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, - &hdr->pages); + &hdr->pages, + hdr->completion_ops); } /* @@ -1292,7 +1300,7 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) whdr = nfs_writehdr_alloc(); if (!whdr) { - nfs_async_write_error(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&hdr->pages); put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; return -ENOMEM; @@ -1309,18 +1317,20 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) } else pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags); if (atomic_dec_and_test(&hdr->refcnt)) - nfs_write_completion(hdr); + hdr->completion_ops->completion(hdr); return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); -static int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head) +static int pnfs_read_done_resend_to_mds(struct inode *inode, + struct list_head *head, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_pageio_descriptor pgio; LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_read_mds(&pgio, inode); + nfs_pageio_init_read_mds(&pgio, inode, compl_ops); while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1349,7 +1359,8 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data) } if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, - &hdr->pages); + &hdr->pages, + hdr->completion_ops); } /* @@ -1443,7 +1454,7 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) rhdr = nfs_readhdr_alloc(); if (!rhdr) { - nfs_async_read_error(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&desc->pg_list); ret = -ENOMEM; put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; @@ -1461,7 +1472,7 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) } else pnfs_do_multiple_reads(desc, &hdr->rpc_list); if (atomic_dec_and_test(&hdr->refcnt)) - nfs_read_completion(hdr); + hdr->completion_ops->completion(hdr); return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 442ebf68eeec..734e4eff7fb0 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -168,8 +168,10 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); void get_layout_hdr(struct pnfs_layout_hdr *lo); void put_lseg(struct pnfs_layout_segment *lseg); -bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *); -bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int); +bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *, + const struct nfs_pgio_completion_ops *); +bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, + int, const struct nfs_pgio_completion_ops *); void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32); void unset_pnfs_layoutdriver(struct nfs_server *); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index c9633b2501bd..5e78af162039 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -31,6 +31,7 @@ static const struct nfs_pageio_ops nfs_pageio_read_ops; static const struct rpc_call_ops nfs_read_common_ops; +static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; static struct kmem_cache *nfs_rdata_cachep; @@ -95,7 +96,7 @@ void nfs_readdata_release(struct nfs_read_data *rdata) else rdata->header = NULL; if (atomic_dec_and_test(&hdr->refcnt)) - nfs_read_completion(hdr); + hdr->completion_ops->completion(hdr); } static @@ -108,9 +109,10 @@ int nfs_return_empty_page(struct page *page) } void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode) + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { - nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, + nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops, NFS_SERVER(inode)->rsize, 0); } @@ -122,10 +124,11 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); static void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, - struct inode *inode) + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { - if (!pnfs_pageio_init_read(pgio, inode)) - nfs_pageio_init_read_mds(pgio, inode); + if (!pnfs_pageio_init_read(pgio, inode, compl_ops)) + nfs_pageio_init_read_mds(pgio, inode, compl_ops); } int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, @@ -146,7 +149,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, if (len < PAGE_CACHE_SIZE) zero_user_segment(page, len, PAGE_CACHE_SIZE); - nfs_pageio_init_read(&pgio, inode); + nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); return 0; @@ -170,7 +173,7 @@ static void nfs_readpage_release(struct nfs_page *req) } /* Note io was page aligned */ -void nfs_read_completion(struct nfs_pgio_header *hdr) +static void nfs_read_completion(struct nfs_pgio_header *hdr) { unsigned long bytes = 0; @@ -300,7 +303,7 @@ nfs_do_multiple_reads(struct list_head *head, return ret; } -void +static void nfs_async_read_error(struct list_head *head) { struct nfs_page *req; @@ -312,6 +315,11 @@ nfs_async_read_error(struct list_head *head) } } +static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = { + .error_cleanup = nfs_async_read_error, + .completion = nfs_read_completion, +}; + /* * Generate multiple requests to fill a single page. * @@ -362,7 +370,7 @@ out_bad: list_del(&data->list); nfs_readdata_release(data); } - nfs_async_read_error(&hdr->pages); + desc->pg_completion_ops->error_cleanup(&hdr->pages); return -ENOMEM; } @@ -378,7 +386,7 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base, desc->pg_count)); if (!data) { - nfs_async_read_error(head); + desc->pg_completion_ops->error_cleanup(head); ret = -ENOMEM; goto out; } @@ -414,7 +422,7 @@ static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) rhdr = nfs_readhdr_alloc(); if (!rhdr) { - nfs_async_read_error(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&desc->pg_list); return -ENOMEM; } hdr = &rhdr->header; @@ -427,7 +435,7 @@ static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) else set_bit(NFS_IOHDR_REDO, &hdr->flags); if (atomic_dec_and_test(&hdr->refcnt)) - nfs_read_completion(hdr); + hdr->completion_ops->completion(hdr); return ret; } @@ -652,7 +660,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&pgio, inode); + nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 076075eb676c..150397279b8d 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -40,10 +40,12 @@ * Local function declarations */ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc, - struct inode *inode, int ioflags); + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops); static void nfs_redirty_request(struct nfs_page *req); static const struct rpc_call_ops nfs_write_common_ops; static const struct rpc_call_ops nfs_commit_ops; +static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; static struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; @@ -128,7 +130,7 @@ void nfs_writedata_release(struct nfs_write_data *wdata) else wdata->header = NULL; if (atomic_dec_and_test(&hdr->refcnt)) - nfs_write_completion(hdr); + hdr->completion_ops->completion(hdr); } static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) @@ -337,7 +339,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc struct nfs_pageio_descriptor pgio; int err; - nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc)); + nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), + &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); nfs_pageio_complete(&pgio); if (err < 0) @@ -380,7 +383,8 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); - nfs_pageio_init_write(&pgio, inode, wb_priority(wbc)); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), + &nfs_async_write_completion_ops); err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); nfs_pageio_complete(&pgio); @@ -558,7 +562,7 @@ int nfs_write_need_commit(struct nfs_write_data *data) #endif -void nfs_write_completion(struct nfs_pgio_header *hdr) +static void nfs_write_completion(struct nfs_pgio_header *hdr) { unsigned long bytes = 0; @@ -1000,7 +1004,7 @@ static void nfs_redirty_request(struct nfs_page *req) nfs_end_page_writeback(page); } -void nfs_async_write_error(struct list_head *head) +static void nfs_async_write_error(struct list_head *head) { struct nfs_page *req; @@ -1011,6 +1015,11 @@ void nfs_async_write_error(struct list_head *head) } } +static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { + .error_cleanup = nfs_async_write_error, + .completion = nfs_write_completion, +}; + /* * Generate multiple small requests to write out a single * contiguous dirty area on one page. @@ -1060,7 +1069,7 @@ out_bad: list_del(&data->list); nfs_writedata_release(data); } - nfs_async_write_error(&hdr->pages); + desc->pg_completion_ops->error_cleanup(&hdr->pages); return -ENOMEM; } @@ -1084,7 +1093,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base, desc->pg_count)); if (!data) { - nfs_async_write_error(head); + desc->pg_completion_ops->error_cleanup(head); ret = -ENOMEM; goto out; } @@ -1125,7 +1134,7 @@ static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) whdr = nfs_writehdr_alloc(); if (!whdr) { - nfs_async_write_error(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&hdr->pages); return -ENOMEM; } hdr = &whdr->header; @@ -1139,7 +1148,7 @@ static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) else set_bit(NFS_IOHDR_REDO, &hdr->flags); if (atomic_dec_and_test(&hdr->refcnt)) - nfs_write_completion(hdr); + hdr->completion_ops->completion(hdr); return ret; } @@ -1149,9 +1158,10 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = { }; void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags) + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { - nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, + nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops, NFS_SERVER(inode)->wsize, ioflags); } @@ -1163,10 +1173,11 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags) + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { - if (!pnfs_pageio_init_write(pgio, inode, ioflags)) - nfs_pageio_init_write_mds(pgio, inode, ioflags); + if (!pnfs_pageio_init_write(pgio, inode, ioflags, compl_ops)) + nfs_pageio_init_write_mds(pgio, inode, ioflags, compl_ops); } void nfs_write_prepare(struct rpc_task *task, void *calldata) diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 5c520344d8ad..bc5b7a5e787e 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -67,6 +67,7 @@ struct nfs_pageio_descriptor { int pg_ioflags; int pg_error; const struct rpc_call_ops *pg_rpc_callops; + const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; }; @@ -83,6 +84,7 @@ extern void nfs_release_request(struct nfs_page *req); extern void nfs_pageio_init(struct nfs_pageio_descriptor *desc, struct inode *inode, const struct nfs_pageio_ops *pg_ops, + const struct nfs_pgio_completion_ops *compl_ops, size_t bsize, int how); extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0d17db7973de..6fa1d2278c9d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1207,6 +1207,7 @@ struct nfs_pgio_header { loff_t io_start; const struct rpc_call_ops *mds_ops; void (*release) (struct nfs_pgio_header *hdr); + const struct nfs_pgio_completion_ops *completion_ops; spinlock_t lock; /* fields protected by lock */ int pnfs_error; @@ -1261,6 +1262,11 @@ struct nfs_commit_data { int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); }; +struct nfs_pgio_completion_ops { + void (*error_cleanup)(struct list_head *head); + void (*completion)(struct nfs_pgio_header *hdr); +}; + struct nfs_unlinkdata { struct hlist_node list; struct nfs_removeargs args; -- cgit v1.2.3 From 9533da2979757258d3fd5429d830a297013d69ed Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:49 -0400 Subject: NFS: remove unused wb_complete field from struct nfs_page Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 1 - fs/nfs/write.c | 1 - include/linux/nfs_page.h | 1 - 3 files changed, 3 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 4cf2a68493e0..5d01a1651084 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -114,7 +114,6 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, * long write-back delay. This will be adjusted in * update_nfs_request below if the region is not locked. */ req->wb_page = page; - atomic_set(&req->wb_complete, 0); req->wb_index = page->index; page_cache_get(page); BUG_ON(PagePrivate(page)); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 150397279b8d..705bf01cfbba 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1059,7 +1059,6 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, nbytes -= len; offset += len; } while (nbytes != 0); - atomic_set(&req->wb_complete, requests); desc->pg_rpc_callops = &nfs_write_common_ops; return ret; diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index bc5b7a5e787e..0a5b63f16116 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -36,7 +36,6 @@ struct nfs_page { struct page *wb_page; /* page to read in/write out */ struct nfs_open_context *wb_context; /* File state context info */ struct nfs_lock_context *wb_lock_context; /* lock context info */ - atomic_t wb_complete; /* i/os we're waiting for */ pgoff_t wb_index; /* Offset >> PAGE_CACHE_SHIFT */ unsigned int wb_offset, /* Offset & ~PAGE_CACHE_MASK */ wb_pgbase, /* Start of page data */ -- cgit v1.2.3 From 584aa810b6240d88c28113a90c5029449814a3b5 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:51 -0400 Subject: NFS: rewrite directio read to use async coalesce code This also has the advantage that it allows directio to use pnfs. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 255 +++++++++++++++++++++++------------------------ fs/nfs/internal.h | 5 +- fs/nfs/pagelist.c | 7 +- fs/nfs/read.c | 10 +- include/linux/nfs_page.h | 1 + include/linux/nfs_xdr.h | 4 +- 6 files changed, 138 insertions(+), 144 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 22a40c408449..4ba9a2c839bb 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -124,22 +124,6 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_ return -EINVAL; } -static void nfs_direct_dirty_pages(struct page **pages, unsigned int pgbase, size_t count) -{ - unsigned int npages; - unsigned int i; - - if (count == 0) - return; - pages += (pgbase >> PAGE_SHIFT); - npages = (count + (pgbase & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT; - for (i = 0; i < npages; i++) { - struct page *page = pages[i]; - if (!PageCompound(page)) - set_page_dirty(page); - } -} - static void nfs_direct_release_pages(struct page **pages, unsigned int npages) { unsigned int i; @@ -226,58 +210,92 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) nfs_direct_req_release(dreq); } -/* - * We must hold a reference to all the pages in this direct read request - * until the RPCs complete. This could be long *after* we are woken up in - * nfs_direct_wait (for instance, if someone hits ^C on a slow server). - */ -static void nfs_direct_read_result(struct rpc_task *task, void *calldata) +void nfs_direct_readpage_release(struct nfs_page *req) { - struct nfs_read_data *data = calldata; - - nfs_readpage_result(task, data); + dprintk("NFS: direct read done (%s/%lld %d@%lld)\n", + req->wb_context->dentry->d_inode->i_sb->s_id, + (long long)NFS_FILEID(req->wb_context->dentry->d_inode), + req->wb_bytes, + (long long)req_offset(req)); + nfs_release_request(req); } -static void nfs_direct_read_release(void *calldata) +static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) { + unsigned long bytes = 0; + struct nfs_direct_req *dreq = hdr->dreq; - struct nfs_read_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *)data->header->req; - int status = data->task.tk_status; + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out_put; spin_lock(&dreq->lock); - if (unlikely(status < 0)) { - dreq->error = status; - spin_unlock(&dreq->lock); + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0)) + dreq->error = hdr->error; + else + dreq->count += hdr->good_bytes; + spin_unlock(&dreq->lock); + + if (!test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { + if (bytes > hdr->good_bytes) + zero_user(page, 0, PAGE_SIZE); + else if (hdr->good_bytes - bytes < PAGE_SIZE) + zero_user_segment(page, + hdr->good_bytes & ~PAGE_MASK, + PAGE_SIZE); + } + bytes += req->wb_bytes; + nfs_list_remove_request(req); + nfs_direct_readpage_release(req); + if (!PageCompound(page)) + set_page_dirty(page); + page_cache_release(page); + } } else { - dreq->count += data->res.count; - spin_unlock(&dreq->lock); - nfs_direct_dirty_pages(data->pages.pagevec, - data->args.pgbase, - data->res.count); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + if (bytes < hdr->good_bytes) + if (!PageCompound(req->wb_page)) + set_page_dirty(req->wb_page); + bytes += req->wb_bytes; + page_cache_release(req->wb_page); + nfs_list_remove_request(req); + nfs_direct_readpage_release(req); + } } - nfs_direct_release_pages(data->pages.pagevec, data->pages.npages); - +out_put: if (put_dreq(dreq)) nfs_direct_complete(dreq); - nfs_readdata_release(data); + hdr->release(hdr); } -static const struct rpc_call_ops nfs_read_direct_ops = { - .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_direct_read_result, - .rpc_release = nfs_direct_read_release, -}; - -static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr) +static void nfs_sync_pgio_error(struct list_head *head) { - struct nfs_read_data *data = &rhdr->rpc_data; + struct nfs_page *req; - if (data->pages.pagevec != data->pages.page_array) - kfree(data->pages.pagevec); - nfs_readhdr_free(&rhdr->header); + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_release_request(req); + } } +static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr) +{ + get_dreq(hdr->dreq); +} + +static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { + .error_cleanup = nfs_sync_pgio_error, + .init_hdr = nfs_direct_pgio_init, + .completion = nfs_direct_read_completion, +}; + /* * For each rsize'd chunk of the user's buffer, dispatch an NFS READ * operation. If nfs_readdata_alloc() or get_user_pages() fails, @@ -285,118 +303,85 @@ static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr) * handled automatically by nfs_direct_read_result(). Otherwise, if * no requests have been sent, just return an error. */ -static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, +static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc, const struct iovec *iov, loff_t pos) { + struct nfs_direct_req *dreq = desc->pg_dreq; struct nfs_open_context *ctx = dreq->ctx; struct inode *inode = ctx->dentry->d_inode; unsigned long user_addr = (unsigned long)iov->iov_base; size_t count = iov->iov_len; size_t rsize = NFS_SERVER(inode)->rsize; - struct rpc_task *task; - struct rpc_message msg = { - .rpc_cred = ctx->cred, - }; - struct rpc_task_setup task_setup_data = { - .rpc_client = NFS_CLIENT(inode), - .rpc_message = &msg, - .callback_ops = &nfs_read_direct_ops, - .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, - }; unsigned int pgbase; int result; ssize_t started = 0; + struct page **pagevec = NULL; + unsigned int npages; do { - struct nfs_read_header *rhdr; - struct nfs_read_data *data; - struct nfs_page_array *pages; size_t bytes; + int i; pgbase = user_addr & ~PAGE_MASK; - bytes = min(rsize,count); + bytes = min(max(rsize, PAGE_SIZE), count); result = -ENOMEM; - rhdr = nfs_readhdr_alloc(); - if (unlikely(!rhdr)) - break; - data = nfs_readdata_alloc(&rhdr->header, nfs_page_array_len(pgbase, bytes)); - if (!data) { - nfs_readhdr_free(&rhdr->header); + npages = nfs_page_array_len(pgbase, bytes); + if (!pagevec) + pagevec = kmalloc(npages * sizeof(struct page *), + GFP_KERNEL); + if (!pagevec) break; - } - data->header = &rhdr->header; - atomic_inc(&data->header->refcnt); - pages = &data->pages; - down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, - pages->npages, 1, 0, pages->pagevec, NULL); + npages, 1, 0, pagevec, NULL); up_read(¤t->mm->mmap_sem); - if (result < 0) { - nfs_direct_readhdr_release(rhdr); + if (result < 0) break; - } - if ((unsigned)result < pages->npages) { + if ((unsigned)result < npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { - nfs_direct_release_pages(pages->pagevec, result); - nfs_direct_readhdr_release(rhdr); + nfs_direct_release_pages(pagevec, result); break; } bytes -= pgbase; - pages->npages = result; + npages = result; } - get_dreq(dreq); - - rhdr->header.req = (struct nfs_page *) dreq; - rhdr->header.inode = inode; - rhdr->header.cred = msg.rpc_cred; - data->args.fh = NFS_FH(inode); - data->args.context = get_nfs_open_context(ctx); - data->args.lock_context = dreq->l_ctx; - data->args.offset = pos; - data->args.pgbase = pgbase; - data->args.pages = pages->pagevec; - data->args.count = bytes; - data->res.fattr = &data->fattr; - data->res.eof = 0; - data->res.count = bytes; - nfs_fattr_init(&data->fattr); - msg.rpc_argp = &data->args; - msg.rpc_resp = &data->res; - - task_setup_data.task = &data->task; - task_setup_data.callback_data = data; - NFS_PROTO(inode)->read_setup(data, &msg); - - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - break; - - dprintk("NFS: %5u initiated direct read call " - "(req %s/%Ld, %zu bytes @ offset %Lu)\n", - task->tk_pid, - inode->i_sb->s_id, - (long long)NFS_FILEID(inode), - bytes, - (unsigned long long)data->args.offset); - rpc_put_task(task); - - started += bytes; - user_addr += bytes; - pos += bytes; - /* FIXME: Remove this unnecessary math from final patch */ - pgbase += bytes; - pgbase &= ~PAGE_MASK; - BUG_ON(pgbase != (user_addr & ~PAGE_MASK)); - - count -= bytes; + for (i = 0; i < npages; i++) { + struct nfs_page *req; + unsigned int req_len = min(bytes, PAGE_SIZE - pgbase); + /* XXX do we need to do the eof zeroing found in async_filler? */ + req = nfs_create_request(dreq->ctx, dreq->inode, + pagevec[i], + pgbase, req_len); + if (IS_ERR(req)) { + nfs_direct_release_pages(pagevec + i, + npages - i); + result = PTR_ERR(req); + break; + } + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (!nfs_pageio_add_request(desc, req)) { + result = desc->pg_error; + nfs_release_request(req); + nfs_direct_release_pages(pagevec + i, + npages - i); + break; + } + pgbase = 0; + bytes -= req_len; + started += req_len; + user_addr += req_len; + pos += req_len; + count -= req_len; + } } while (count != 0); + kfree(pagevec); + if (started) return started; return result < 0 ? (ssize_t) result : -EFAULT; @@ -407,15 +392,19 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, unsigned long nr_segs, loff_t pos) { + struct nfs_pageio_descriptor desc; ssize_t result = -EINVAL; size_t requested_bytes = 0; unsigned long seg; + nfs_pageio_init_read(&desc, dreq->inode, + &nfs_direct_read_completion_ops); get_dreq(dreq); + desc.pg_dreq = dreq; for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; - result = nfs_direct_read_schedule_segment(dreq, vec, pos); + result = nfs_direct_read_schedule_segment(&desc, vec, pos); if (result < 0) break; requested_bytes += result; @@ -424,6 +413,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } + nfs_pageio_complete(&desc); + /* * If no bytes were started, return the error, and let the * generic layer handle the completion. diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3ef8fcda1a5f..cd5d4a300bc9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -304,8 +304,9 @@ struct nfs_pgio_completion_ops; /* read.c */ extern struct nfs_read_header *nfs_readhdr_alloc(void); extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); -extern struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, - unsigned int pagecount); +extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops); extern int nfs_initiate_read(struct rpc_clnt *clnt, struct nfs_read_data *data, const struct rpc_call_ops *call_ops); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 638ca7f5a1e4..33a21ca9b84b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -48,8 +48,11 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->cred = hdr->req->wb_context->cred; hdr->io_start = req_offset(hdr->req); hdr->good_bytes = desc->pg_count; + hdr->dreq = desc->pg_dreq; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; + if (hdr->completion_ops->init_hdr) + hdr->completion_ops->init_hdr(hdr); } void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) @@ -116,9 +119,6 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, req->wb_page = page; req->wb_index = page->index; page_cache_get(page); - BUG_ON(PagePrivate(page)); - BUG_ON(!PageLocked(page)); - BUG_ON(page->mapping->host != inode); req->wb_offset = offset; req->wb_pgbase = offset; req->wb_bytes = count; @@ -257,6 +257,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_ioflags = io_flags; desc->pg_error = 0; desc->pg_lseg = NULL; + desc->pg_dreq = NULL; } /** diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 5e78af162039..35e2dcebffe6 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -51,8 +51,8 @@ struct nfs_read_header *nfs_readhdr_alloc() return rhdr; } -struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, - unsigned int pagecount) +static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount) { struct nfs_read_data *data, *prealloc; @@ -123,9 +123,9 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); -static void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, - struct inode *inode, - const struct nfs_pgio_completion_ops *compl_ops) +void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { if (!pnfs_pageio_init_read(pgio, inode, compl_ops)) nfs_pageio_init_read_mds(pgio, inode, compl_ops); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 0a5b63f16116..f9ee9eba7f88 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -68,6 +68,7 @@ struct nfs_pageio_descriptor { const struct rpc_call_ops *pg_rpc_callops; const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; + struct nfs_direct_req *pg_dreq; }; #define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags)) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6fa1d2278c9d..38687b87ca9b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1208,6 +1208,7 @@ struct nfs_pgio_header { const struct rpc_call_ops *mds_ops; void (*release) (struct nfs_pgio_header *hdr); const struct nfs_pgio_completion_ops *completion_ops; + struct nfs_direct_req *dreq; spinlock_t lock; /* fields protected by lock */ int pnfs_error; @@ -1221,8 +1222,6 @@ struct nfs_read_header { struct nfs_read_data rpc_data; }; -struct nfs_direct_req; - struct nfs_write_data { struct nfs_pgio_header *header; struct list_head list; @@ -1264,6 +1263,7 @@ struct nfs_commit_data { struct nfs_pgio_completion_ops { void (*error_cleanup)(struct list_head *head); + void (*init_hdr)(struct nfs_pgio_header *hdr); void (*completion)(struct nfs_pgio_header *hdr); }; -- cgit v1.2.3 From ea2cf2282b4278461266013e9c002ee1c66700ff Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:53 -0400 Subject: NFS: create struct nfs_commit_info It is COMMIT that is handled the most differently between the paged and direct paths. Create a structure that encapsulates everything either path needs to know about the commit state. We could use void to hide some of the layout driver stuff, but Trond suggests pulling it out to ensure type checking, given the huge changes being made, and the fact that it doesn't interfere with other drivers. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 6 +- fs/nfs/internal.h | 12 +++- fs/nfs/nfs4filelayout.c | 119 ++++++++++++++++++++---------------- fs/nfs/nfs4filelayout.h | 14 +---- fs/nfs/pnfs.h | 72 ++++++++++++++-------- fs/nfs/write.c | 158 ++++++++++++++++++++++++++++-------------------- include/linux/nfs_fs.h | 5 +- include/linux/nfs_xdr.h | 27 +++++++++ 8 files changed, 248 insertions(+), 165 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e8bbfa5b3500..59a12c6a8df6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1547,7 +1547,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) nfsi->delegation_state = 0; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; - atomic_set(&nfsi->commits_outstanding, 0); + atomic_set(&nfsi->commit_info.rpcs_out, 0); #endif } @@ -1559,9 +1559,9 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); - INIT_LIST_HEAD(&nfsi->commit_list); + INIT_LIST_HEAD(&nfsi->commit_info.list); nfsi->npages = 0; - nfsi->ncommit = 0; + nfsi->commit_info.ncommit = 0; atomic_set(&nfsi->silly_count, 1); INIT_HLIST_HEAD(&nfsi->silly_list); init_waitqueue_head(&nfsi->waitqueue); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index cd5d4a300bc9..145e9e7dc8ce 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -346,12 +346,18 @@ extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg); void nfs_retry_commit(struct list_head *page_list, - struct pnfs_layout_segment *lseg); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); void nfs_commit_clear_lock(struct nfs_inode *nfsi); void nfs_commitdata_release(struct nfs_commit_data *data); void nfs_commit_release_pages(struct nfs_commit_data *data); -void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head); -void nfs_request_remove_commit_list(struct nfs_page *req); +void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, + struct nfs_commit_info *cinfo); +void nfs_request_remove_commit_list(struct nfs_page *req, + struct nfs_commit_info *cinfo); +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index e40523f2fe26..fe2cb55ca6b1 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -347,9 +347,11 @@ static void filelayout_commit_count_stats(struct rpc_task *task, void *data) static void filelayout_commit_release(void *calldata) { struct nfs_commit_data *data = calldata; + struct nfs_commit_info cinfo; nfs_commit_release_pages(data); - if (atomic_dec_and_test(&NFS_I(data->inode)->commits_outstanding)) + nfs_init_cinfo(&cinfo, data->inode, data->dreq); + if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) nfs_commit_clear_lock(NFS_I(data->inode)); put_lseg(data->lseg); nfs_commitdata_release(data); @@ -695,17 +697,16 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg) static int filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, gfp_t gfp_flags) { struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); - struct nfs4_filelayout *flo = FILELAYOUT_FROM_HDR(lseg->pls_layout); - - struct nfs4_fl_commit_bucket *buckets; + struct pnfs_commit_bucket *buckets; int size; if (fl->commit_through_mds) return 0; - if (flo->commit_info.nbuckets != 0) { + if (cinfo->ds->nbuckets != 0) { /* This assumes there is only one IOMODE_RW lseg. What * we really want to do is have a layout_hdr level * dictionary of keys, each @@ -718,25 +719,25 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg, size = (fl->stripe_type == STRIPE_SPARSE) ? fl->dsaddr->ds_num : fl->dsaddr->stripe_count; - buckets = kcalloc(size, sizeof(struct nfs4_fl_commit_bucket), + buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket), gfp_flags); if (!buckets) return -ENOMEM; else { int i; - spin_lock(&lseg->pls_layout->plh_inode->i_lock); - if (flo->commit_info.nbuckets != 0) + spin_lock(cinfo->lock); + if (cinfo->ds->nbuckets != 0) kfree(buckets); else { - flo->commit_info.buckets = buckets; - flo->commit_info.nbuckets = size; + cinfo->ds->buckets = buckets; + cinfo->ds->nbuckets = size; for (i = 0; i < size; i++) { INIT_LIST_HEAD(&buckets[i].written); INIT_LIST_HEAD(&buckets[i].committing); } } - spin_unlock(&lseg->pls_layout->plh_inode->i_lock); + spin_unlock(cinfo->lock); return 0; } } @@ -821,6 +822,7 @@ static void filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { + struct nfs_commit_info cinfo; int status; BUG_ON(pgio->pg_lseg != NULL); @@ -836,7 +838,8 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) goto out_mds; - status = filelayout_alloc_commit_info(pgio->pg_lseg, GFP_NOFS); + nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq); + status = filelayout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS); if (status < 0) { put_lseg(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -871,40 +874,42 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j) * If this will make the bucket empty, it will need to put the lseg reference. */ static void -filelayout_clear_request_commit(struct nfs_page *req) +filelayout_clear_request_commit(struct nfs_page *req, + struct nfs_commit_info *cinfo) { struct pnfs_layout_segment *freeme = NULL; - struct inode *inode = req->wb_context->dentry->d_inode; - spin_lock(&inode->i_lock); + spin_lock(cinfo->lock); if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags)) goto out; + cinfo->ds->nwritten--; if (list_is_singular(&req->wb_list)) { - struct nfs4_fl_commit_bucket *bucket; + struct pnfs_commit_bucket *bucket; bucket = list_first_entry(&req->wb_list, - struct nfs4_fl_commit_bucket, + struct pnfs_commit_bucket, written); freeme = bucket->wlseg; bucket->wlseg = NULL; } out: - nfs_request_remove_commit_list(req); - spin_unlock(&inode->i_lock); + nfs_request_remove_commit_list(req, cinfo); + spin_unlock(cinfo->lock); put_lseg(freeme); } static struct list_head * filelayout_choose_commit_list(struct nfs_page *req, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); u32 i, j; struct list_head *list; - struct nfs4_fl_commit_bucket *buckets; + struct pnfs_commit_bucket *buckets; if (fl->commit_through_mds) - return &NFS_I(req->wb_context->dentry->d_inode)->commit_list; + return &cinfo->mds->list; /* Note that we are calling nfs4_fl_calc_j_index on each page * that ends up being committed to a data server. An attractive @@ -914,7 +919,7 @@ filelayout_choose_commit_list(struct nfs_page *req, */ j = nfs4_fl_calc_j_index(lseg, req_offset(req)); i = select_bucket_index(fl, j); - buckets = FILELAYOUT_FROM_HDR(lseg->pls_layout)->commit_info.buckets; + buckets = cinfo->ds->buckets; list = &buckets[i].written; if (list_empty(list)) { /* Non-empty buckets hold a reference on the lseg. That ref @@ -926,17 +931,19 @@ filelayout_choose_commit_list(struct nfs_page *req, buckets[i].wlseg = get_lseg(lseg); } set_bit(PG_COMMIT_TO_DS, &req->wb_flags); + cinfo->ds->nwritten++; return list; } static void filelayout_mark_request_commit(struct nfs_page *req, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct list_head *list; - list = filelayout_choose_commit_list(req, lseg); - nfs_request_add_commit_list(req, list); + list = filelayout_choose_commit_list(req, lseg, cinfo); + nfs_request_add_commit_list(req, list, cinfo); } static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) @@ -993,8 +1000,9 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) } static int -filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, - spinlock_t *lock) +filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, + struct nfs_commit_info *cinfo, + int max) { struct list_head *src = &bucket->written; struct list_head *dst = &bucket->committing; @@ -1004,9 +1012,9 @@ filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, list_for_each_entry_safe(req, tmp, src, wb_list) { if (!nfs_lock_request(req)) continue; - if (cond_resched_lock(lock)) + if (cond_resched_lock(cinfo->lock)) list_safe_reset_next(req, tmp, wb_list); - nfs_request_remove_commit_list(req); + nfs_request_remove_commit_list(req, cinfo); clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); nfs_list_add_request(req, dst); ret++; @@ -1014,6 +1022,8 @@ filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, break; } if (ret) { + cinfo->ds->nwritten -= ret; + cinfo->ds->ncommitting += ret; bucket->clseg = bucket->wlseg; if (list_empty(src)) bucket->wlseg = NULL; @@ -1024,37 +1034,32 @@ filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, } /* Move reqs from written to committing lists, returning count of number moved. - * Note called with i_lock held. + * Note called with cinfo->lock held. */ -static int filelayout_scan_commit_lists(struct inode *inode, int max, - spinlock_t *lock) +static int filelayout_scan_commit_lists(struct nfs_commit_info *cinfo, + int max) { - struct nfs4_fl_commit_info *fl_cinfo; int i, rv = 0, cnt; - fl_cinfo = &FILELAYOUT_FROM_HDR(NFS_I(inode)->layout)->commit_info; - if (fl_cinfo->nbuckets == 0) - goto out_done; - for (i = 0; i < fl_cinfo->nbuckets && max != 0; i++) { - cnt = filelayout_scan_ds_commit_list(&fl_cinfo->buckets[i], - max, lock); + for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) { + cnt = filelayout_scan_ds_commit_list(&cinfo->ds->buckets[i], + cinfo, max); max -= cnt; rv += cnt; } -out_done: return rv; } static unsigned int -alloc_ds_commits(struct inode *inode, struct list_head *list) +alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list) { - struct nfs4_fl_commit_info *fl_cinfo; - struct nfs4_fl_commit_bucket *bucket; + struct pnfs_ds_commit_info *fl_cinfo; + struct pnfs_commit_bucket *bucket; struct nfs_commit_data *data; int i, j; unsigned int nreq = 0; - fl_cinfo = &FILELAYOUT_FROM_HDR(NFS_I(inode)->layout)->commit_info; + fl_cinfo = cinfo->ds; bucket = fl_cinfo->buckets; for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) { if (list_empty(&bucket->committing)) @@ -1073,7 +1078,7 @@ alloc_ds_commits(struct inode *inode, struct list_head *list) for (j = i; j < fl_cinfo->nbuckets; j++, bucket++) { if (list_empty(&bucket->committing)) continue; - nfs_retry_commit(&bucket->committing, bucket->clseg); + nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo); put_lseg(bucket->clseg); bucket->clseg = NULL; } @@ -1084,7 +1089,7 @@ alloc_ds_commits(struct inode *inode, struct list_head *list) /* This follows nfs_commit_list pretty closely */ static int filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, - int how) + int how, struct nfs_commit_info *cinfo) { struct nfs_commit_data *data, *tmp; LIST_HEAD(list); @@ -1097,17 +1102,17 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, list_add(&data->pages, &list); nreq++; } else - nfs_retry_commit(mds_pages, NULL); + nfs_retry_commit(mds_pages, NULL, cinfo); } - nreq += alloc_ds_commits(inode, &list); + nreq += alloc_ds_commits(cinfo, &list); if (nreq == 0) { nfs_commit_clear_lock(NFS_I(inode)); goto out; } - atomic_add(nreq, &NFS_I(inode)->commits_outstanding); + atomic_add(nreq, &cinfo->mds->rpcs_out); list_for_each_entry_safe(data, tmp, &list, pages) { list_del_init(&data->pages); @@ -1116,14 +1121,15 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, how); } else { - struct nfs4_fl_commit_info *fl_cinfo; + struct pnfs_commit_bucket *buckets; - fl_cinfo = &FILELAYOUT_FROM_HDR(data->lseg->pls_layout)->commit_info; - nfs_init_commit(data, &fl_cinfo->buckets[data->ds_commit_index].committing, data->lseg); + buckets = cinfo->ds->buckets; + nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg); filelayout_initiate_commit(data, how); } } out: + cinfo->ds->ncommitting = 0; return PNFS_ATTEMPTED; } @@ -1148,6 +1154,12 @@ filelayout_free_layout_hdr(struct pnfs_layout_hdr *lo) kfree(FILELAYOUT_FROM_HDR(lo)); } +static struct pnfs_ds_commit_info * +filelayout_get_ds_info(struct inode *inode) +{ + return &FILELAYOUT_FROM_HDR(NFS_I(inode)->layout)->commit_info; +} + static struct pnfs_layoutdriver_type filelayout_type = { .id = LAYOUT_NFSV4_1_FILES, .name = "LAYOUT_NFSV4_1_FILES", @@ -1158,6 +1170,7 @@ static struct pnfs_layoutdriver_type filelayout_type = { .free_lseg = filelayout_free_lseg, .pg_read_ops = &filelayout_pg_read_ops, .pg_write_ops = &filelayout_pg_write_ops, + .get_ds_info = &filelayout_get_ds_info, .mark_request_commit = filelayout_mark_request_commit, .clear_request_commit = filelayout_clear_request_commit, .scan_commit_lists = filelayout_scan_commit_lists, diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h index 333a3ac97606..96b89bbddf4f 100644 --- a/fs/nfs/nfs4filelayout.h +++ b/fs/nfs/nfs4filelayout.h @@ -74,18 +74,6 @@ struct nfs4_file_layout_dsaddr { struct nfs4_pnfs_ds *ds_list[1]; }; -struct nfs4_fl_commit_bucket { - struct list_head written; - struct list_head committing; - struct pnfs_layout_segment *wlseg; - struct pnfs_layout_segment *clseg; -}; - -struct nfs4_fl_commit_info { - int nbuckets; - struct nfs4_fl_commit_bucket *buckets; -}; - struct nfs4_filelayout_segment { struct pnfs_layout_segment generic_hdr; u32 stripe_type; @@ -100,7 +88,7 @@ struct nfs4_filelayout_segment { struct nfs4_filelayout { struct pnfs_layout_hdr generic_hdr; - struct nfs4_fl_commit_info commit_info; + struct pnfs_ds_commit_info commit_info; }; static inline struct nfs4_filelayout * diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 734e4eff7fb0..4cd8760c2f89 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -94,11 +94,18 @@ struct pnfs_layoutdriver_type { const struct nfs_pageio_ops *pg_read_ops; const struct nfs_pageio_ops *pg_write_ops; + struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode); void (*mark_request_commit) (struct nfs_page *req, - struct pnfs_layout_segment *lseg); - void (*clear_request_commit) (struct nfs_page *req); - int (*scan_commit_lists) (struct inode *inode, int max, spinlock_t *lock); - int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); + void (*clear_request_commit) (struct nfs_page *req, + struct nfs_commit_info *cinfo); + int (*scan_commit_lists) (struct nfs_commit_info *cinfo, + int max); + int (*commit_pagelist)(struct inode *inode, + struct list_head *mds_pages, + int how, + struct nfs_commit_info *cinfo); /* * Return PNFS_ATTEMPTED to indicate the layout code has attempted @@ -263,49 +270,57 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss) } static inline int -pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how) +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, + struct nfs_commit_info *cinfo) { - if (!test_and_clear_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags)) + if (cinfo->ds == NULL || cinfo->ds->ncommitting == 0) return PNFS_NOT_ATTEMPTED; - return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how); + return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how, cinfo); +} + +static inline struct pnfs_ds_commit_info * +pnfs_get_ds_info(struct inode *inode) +{ + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; + + if (ld == NULL || ld->get_ds_info == NULL) + return NULL; + return ld->get_ds_info(inode); } static inline bool -pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct inode *inode = req->wb_context->dentry->d_inode; struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (lseg == NULL || ld->mark_request_commit == NULL) return false; - ld->mark_request_commit(req, lseg); + ld->mark_request_commit(req, lseg, cinfo); return true; } static inline bool -pnfs_clear_request_commit(struct nfs_page *req) +pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { struct inode *inode = req->wb_context->dentry->d_inode; struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (ld == NULL || ld->clear_request_commit == NULL) return false; - ld->clear_request_commit(req); + ld->clear_request_commit(req, cinfo); return true; } static inline int -pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock) +pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, + int max) { - struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; - int ret; - - if (ld == NULL || ld->scan_commit_lists == NULL) + if (cinfo->ds == NULL || cinfo->ds->nwritten == 0) return 0; - ret = ld->scan_commit_lists(inode, max, lock); - if (ret != 0) - set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags); - return ret; + else + return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max); } /* Should the pNFS client commit and return the layout upon a setattr */ @@ -409,25 +424,34 @@ static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, st } static inline int -pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how) +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, + struct nfs_commit_info *cinfo) { return PNFS_NOT_ATTEMPTED; } +static inline struct pnfs_ds_commit_info * +pnfs_get_ds_info(struct inode *inode) +{ + return NULL; +} + static inline bool -pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { return false; } static inline bool -pnfs_clear_request_commit(struct nfs_page *req) +pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { return false; } static inline int -pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock) +pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, + int max) { return 0; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2500f1cf1996..18bf70055272 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -452,65 +452,79 @@ nfs_mark_request_dirty(struct nfs_page *req) /** * nfs_request_add_commit_list - add request to a commit list * @req: pointer to a struct nfs_page - * @head: commit list head + * @dst: commit list head + * @cinfo: holds list lock and accounting info * - * This sets the PG_CLEAN bit, updates the inode global count of + * This sets the PG_CLEAN bit, updates the cinfo count of * number of outstanding requests requiring a commit as well as * the MM page stats. * - * The caller must _not_ hold the inode->i_lock, but must be + * The caller must _not_ hold the cinfo->lock, but must be * holding the nfs_page lock. */ void -nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head) +nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - set_bit(PG_CLEAN, &(req)->wb_flags); - spin_lock(&inode->i_lock); - nfs_list_add_request(req, head); - NFS_I(inode)->ncommit++; - spin_unlock(&inode->i_lock); + spin_lock(cinfo->lock); + nfs_list_add_request(req, dst); + cinfo->mds->ncommit++; + spin_unlock(cinfo->lock); inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE); - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + __mark_inode_dirty(req->wb_context->dentry->d_inode, I_DIRTY_DATASYNC); } EXPORT_SYMBOL_GPL(nfs_request_add_commit_list); /** * nfs_request_remove_commit_list - Remove request from a commit list * @req: pointer to a nfs_page + * @cinfo: holds list lock and accounting info * - * This clears the PG_CLEAN bit, and updates the inode global count of + * This clears the PG_CLEAN bit, and updates the cinfo's count of * number of outstanding requests requiring a commit * It does not update the MM page stats. * - * The caller _must_ hold the inode->i_lock and the nfs_page lock. + * The caller _must_ hold the cinfo->lock and the nfs_page lock. */ void -nfs_request_remove_commit_list(struct nfs_page *req) +nfs_request_remove_commit_list(struct nfs_page *req, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) return; nfs_list_remove_request(req); - NFS_I(inode)->ncommit--; + cinfo->mds->ncommit--; } EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list); +static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, + struct inode *inode) +{ + cinfo->lock = &inode->i_lock; + cinfo->mds = &NFS_I(inode)->commit_info; + cinfo->ds = pnfs_get_ds_info(inode); +} + +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq) +{ + nfs_init_cinfo_from_inode(cinfo, inode); +} +EXPORT_SYMBOL_GPL(nfs_init_cinfo); /* * Add a request to the inode's commit list. */ static void -nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - - if (pnfs_mark_request_commit(req, lseg)) + if (pnfs_mark_request_commit(req, lseg, cinfo)) return; - nfs_request_add_commit_list(req, &NFS_I(inode)->commit_list); + nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo); } static void @@ -525,11 +539,13 @@ nfs_clear_request_commit(struct nfs_page *req) { if (test_bit(PG_CLEAN, &req->wb_flags)) { struct inode *inode = req->wb_context->dentry->d_inode; + struct nfs_commit_info cinfo; - if (!pnfs_clear_request_commit(req)) { - spin_lock(&inode->i_lock); - nfs_request_remove_commit_list(req); - spin_unlock(&inode->i_lock); + nfs_init_cinfo_from_inode(&cinfo, inode); + if (!pnfs_clear_request_commit(req, &cinfo)) { + spin_lock(cinfo.lock); + nfs_request_remove_commit_list(req, &cinfo); + spin_unlock(cinfo.lock); } nfs_clear_page_commit(req->wb_page); } @@ -545,7 +561,8 @@ int nfs_write_need_commit(struct nfs_write_data *data) #else static void -nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { } @@ -564,10 +581,12 @@ int nfs_write_need_commit(struct nfs_write_data *data) static void nfs_write_completion(struct nfs_pgio_header *hdr) { + struct nfs_commit_info cinfo; unsigned long bytes = 0; if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) goto out; + nfs_init_cinfo_from_inode(&cinfo, hdr->inode); while (!list_empty(&hdr->pages)) { struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct page *page = req->wb_page; @@ -585,7 +604,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) goto next; } if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { - nfs_mark_request_commit(req, hdr->lseg); + nfs_mark_request_commit(req, hdr->lseg, &cinfo); goto next; } remove_req: @@ -599,16 +618,16 @@ out: } #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) -static int -nfs_need_commit(struct nfs_inode *nfsi) +static unsigned long +nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { - return nfsi->ncommit > 0; + return cinfo->mds->ncommit; } -/* i_lock held by caller */ +/* cinfo->lock held by caller */ static int -nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, - spinlock_t *lock) +nfs_scan_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max) { struct nfs_page *req, *tmp; int ret = 0; @@ -616,9 +635,9 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, list_for_each_entry_safe(req, tmp, src, wb_list) { if (!nfs_lock_request(req)) continue; - if (cond_resched_lock(lock)) + if (cond_resched_lock(cinfo->lock)) list_safe_reset_next(req, tmp, wb_list); - nfs_request_remove_commit_list(req); + nfs_request_remove_commit_list(req, cinfo); nfs_list_add_request(req, dst); ret++; if (ret == max) @@ -630,37 +649,38 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, /* * nfs_scan_commit - Scan an inode for commit requests * @inode: NFS inode to scan - * @dst: destination list + * @dst: mds destination list + * @cinfo: mds and ds lists of reqs ready to commit * * Moves requests from the inode's 'commit' request list. * The requests are *not* checked to ensure that they form a contiguous set. */ static int -nfs_scan_commit(struct inode *inode, struct list_head *dst) +nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo) { - struct nfs_inode *nfsi = NFS_I(inode); int ret = 0; - spin_lock(&inode->i_lock); - if (nfsi->ncommit > 0) { + spin_lock(cinfo->lock); + if (cinfo->mds->ncommit > 0) { const int max = INT_MAX; - ret = nfs_scan_commit_list(&nfsi->commit_list, dst, max, - &inode->i_lock); - ret += pnfs_scan_commit_lists(inode, max - ret, - &inode->i_lock); + ret = nfs_scan_commit_list(&cinfo->mds->list, dst, + cinfo, max); + ret += pnfs_scan_commit_lists(inode, cinfo, max - ret); } - spin_unlock(&inode->i_lock); + spin_unlock(cinfo->lock); return ret; } #else -static inline int nfs_need_commit(struct nfs_inode *nfsi) +static unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { return 0; } -static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst) +static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo) { return 0; } @@ -929,7 +949,7 @@ EXPORT_SYMBOL_GPL(nfs_initiate_write); */ static void nfs_write_rpcsetup(struct nfs_write_data *data, unsigned int count, unsigned int offset, - int how) + int how, struct nfs_commit_info *cinfo) { struct nfs_page *req = data->header->req; @@ -950,7 +970,7 @@ static void nfs_write_rpcsetup(struct nfs_write_data *data, case 0: break; case FLUSH_COND_STABLE: - if (nfs_need_commit(NFS_I(data->header->inode))) + if (nfs_reqs_to_commit(cinfo)) break; default: data->args.stable = NFS_FILE_SYNC; @@ -1034,12 +1054,14 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, unsigned int offset; int requests = 0; int ret = 0; + struct nfs_commit_info cinfo; + nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); nfs_list_remove_request(req); nfs_list_add_request(req, &hdr->pages); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && - (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit || + (desc->pg_moreio || nfs_reqs_to_commit(&cinfo) || desc->pg_count > wsize)) desc->pg_ioflags &= ~FLUSH_COND_STABLE; @@ -1053,7 +1075,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, if (!data) goto out_bad; data->pages.pagevec[0] = page; - nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags); + nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags, &cinfo); list_add(&data->list, &hdr->rpc_list); requests++; nbytes -= len; @@ -1088,6 +1110,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct nfs_write_data *data; struct list_head *head = &desc->pg_list; int ret = 0; + struct nfs_commit_info cinfo; data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base, desc->pg_count)); @@ -1097,6 +1120,7 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, goto out; } + nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); @@ -1106,11 +1130,11 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc, } if ((desc->pg_ioflags & FLUSH_COND_STABLE) && - (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) + (desc->pg_moreio || nfs_reqs_to_commit(&cinfo))) desc->pg_ioflags &= ~FLUSH_COND_STABLE; /* Set up the argument struct */ - nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags); + nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo); list_add(&data->list, &hdr->rpc_list); desc->pg_rpc_callops = &nfs_write_common_ops; out: @@ -1417,14 +1441,15 @@ void nfs_init_commit(struct nfs_commit_data *data, EXPORT_SYMBOL_GPL(nfs_init_commit); void nfs_retry_commit(struct list_head *page_list, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs_page *req; while (!list_empty(page_list)) { req = nfs_list_entry(page_list->next); nfs_list_remove_request(req); - nfs_mark_request_commit(req, lseg); + nfs_mark_request_commit(req, lseg, cinfo); dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); dec_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE); @@ -1437,7 +1462,8 @@ EXPORT_SYMBOL_GPL(nfs_retry_commit); * Commit dirty pages */ static int -nfs_commit_list(struct inode *inode, struct list_head *head, int how) +nfs_commit_list(struct inode *inode, struct list_head *head, int how, + struct nfs_commit_info *cinfo) { struct nfs_commit_data *data; @@ -1450,7 +1476,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how) nfs_init_commit(data, head, NULL); return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, how); out_bad: - nfs_retry_commit(head, NULL); + nfs_retry_commit(head, NULL, cinfo); nfs_commit_clear_lock(NFS_I(inode)); return -ENOMEM; } @@ -1524,30 +1550,32 @@ static const struct rpc_call_ops nfs_commit_ops = { }; static int nfs_generic_commit_list(struct inode *inode, struct list_head *head, - int how) + int how, struct nfs_commit_info *cinfo) { int status; - status = pnfs_commit_list(inode, head, how); + status = pnfs_commit_list(inode, head, how, cinfo); if (status == PNFS_NOT_ATTEMPTED) - status = nfs_commit_list(inode, head, how); + status = nfs_commit_list(inode, head, how, cinfo); return status; } int nfs_commit_inode(struct inode *inode, int how) { LIST_HEAD(head); + struct nfs_commit_info cinfo; int may_wait = how & FLUSH_SYNC; int res; res = nfs_commit_set_lock(NFS_I(inode), may_wait); if (res <= 0) goto out_mark_dirty; - res = nfs_scan_commit(inode, &head); + nfs_init_cinfo_from_inode(&cinfo, inode); + res = nfs_scan_commit(inode, &head, &cinfo); if (res) { int error; - error = nfs_generic_commit_list(inode, &head, how); + error = nfs_generic_commit_list(inode, &head, how, &cinfo); if (error < 0) return error; if (!may_wait) @@ -1578,14 +1606,14 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr int ret = 0; /* no commits means nothing needs to be done */ - if (!nfsi->ncommit) + if (!nfsi->commit_info.ncommit) return ret; if (wbc->sync_mode == WB_SYNC_NONE) { /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ - if (nfsi->ncommit <= (nfsi->npages >> 1)) + if (nfsi->commit_info.ncommit <= (nfsi->npages >> 1)) goto out_mark_dirty; /* don't wait for the COMMIT response */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8d3a2b804201..8a88c16662c5 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -179,8 +179,7 @@ struct nfs_inode { __be32 cookieverf[2]; unsigned long npages; - unsigned long ncommit; - struct list_head commit_list; + struct nfs_mds_commit_info commit_info; /* Open contexts for shared mmap writes */ struct list_head open_files; @@ -201,7 +200,6 @@ struct nfs_inode { /* pNFS layout information */ struct pnfs_layout_hdr *layout; - atomic_t commits_outstanding; #endif /* CONFIG_NFS_V4*/ #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; @@ -230,7 +228,6 @@ struct nfs_inode { #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ #define NFS_INO_COMMIT (7) /* inode is committing unstable writes */ -#define NFS_INO_PNFS_COMMIT (8) /* use pnfs code for commit */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 38687b87ca9b..224e1e82670c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1079,6 +1079,21 @@ struct nfstime4 { }; #ifdef CONFIG_NFS_V4_1 + +struct pnfs_commit_bucket { + struct list_head written; + struct list_head committing; + struct pnfs_layout_segment *wlseg; + struct pnfs_layout_segment *clseg; +}; + +struct pnfs_ds_commit_info { + int nwritten; + int ncommitting; + int nbuckets; + struct pnfs_commit_bucket *buckets; +}; + #define NFS4_EXCHANGE_ID_LEN (48) struct nfs41_exchange_id_args { struct nfs_client *client; @@ -1242,6 +1257,18 @@ struct nfs_write_header { struct nfs_write_data rpc_data; }; +struct nfs_mds_commit_info { + atomic_t rpcs_out; + unsigned long ncommit; + struct list_head list; +}; + +struct nfs_commit_info { + spinlock_t *lock; + struct nfs_mds_commit_info *mds; + struct pnfs_ds_commit_info *ds; +}; + struct nfs_commit_data { struct rpc_task task; struct inode *inode; -- cgit v1.2.3 From f453a54a01c7c0453ad9550906e3d2663dd486ac Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:54 -0400 Subject: NFS: create nfs_commit_completion_ops Factors out the code that needs to change when directio starts using these code paths. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 5 ++--- fs/nfs/nfs4filelayout.c | 12 ++++-------- fs/nfs/write.c | 31 +++++++++++++++++++++---------- include/linux/nfs_xdr.h | 9 +++++++++ 4 files changed, 36 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 145e9e7dc8ce..137f5cd71433 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -344,13 +344,12 @@ extern int nfs_initiate_commit(struct rpc_clnt *clnt, int how); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, - struct pnfs_layout_segment *lseg); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo); -void nfs_commit_clear_lock(struct nfs_inode *nfsi); void nfs_commitdata_release(struct nfs_commit_data *data); -void nfs_commit_release_pages(struct nfs_commit_data *data); void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_request_remove_commit_list(struct nfs_page *req, diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index fe2cb55ca6b1..26d1da486761 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -347,12 +347,8 @@ static void filelayout_commit_count_stats(struct rpc_task *task, void *data) static void filelayout_commit_release(void *calldata) { struct nfs_commit_data *data = calldata; - struct nfs_commit_info cinfo; - nfs_commit_release_pages(data); - nfs_init_cinfo(&cinfo, data->inode, data->dreq); - if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) - nfs_commit_clear_lock(NFS_I(data->inode)); + data->completion_ops->completion(data); put_lseg(data->lseg); nfs_commitdata_release(data); } @@ -1108,7 +1104,7 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, nreq += alloc_ds_commits(cinfo, &list); if (nreq == 0) { - nfs_commit_clear_lock(NFS_I(inode)); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); goto out; } @@ -1117,14 +1113,14 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, list_for_each_entry_safe(data, tmp, &list, pages) { list_del_init(&data->pages); if (!data->lseg) { - nfs_init_commit(data, mds_pages, NULL); + nfs_init_commit(data, mds_pages, NULL, cinfo); nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, how); } else { struct pnfs_commit_bucket *buckets; buckets = cinfo->ds->buckets; - nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg); + nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo); filelayout_initiate_commit(data, how); } } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 18bf70055272..333d01d26292 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -46,6 +46,7 @@ static void nfs_redirty_request(struct nfs_page *req); static const struct rpc_call_ops nfs_write_common_ops; static const struct rpc_call_ops nfs_commit_ops; static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; +static const struct nfs_commit_completion_ops nfs_commit_completion_ops; static struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; @@ -505,6 +506,7 @@ static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, cinfo->lock = &inode->i_lock; cinfo->mds = &NFS_I(inode)->commit_info; cinfo->ds = pnfs_get_ds_info(inode); + cinfo->completion_ops = &nfs_commit_completion_ops; } void nfs_init_cinfo(struct nfs_commit_info *cinfo, @@ -1358,13 +1360,12 @@ static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) return (ret < 0) ? ret : 1; } -void nfs_commit_clear_lock(struct nfs_inode *nfsi) +static void nfs_commit_clear_lock(struct nfs_inode *nfsi) { clear_bit(NFS_INO_COMMIT, &nfsi->flags); smp_mb__after_clear_bit(); wake_up_bit(&nfsi->flags, NFS_INO_COMMIT); } -EXPORT_SYMBOL_GPL(nfs_commit_clear_lock); void nfs_commitdata_release(struct nfs_commit_data *data) { @@ -1413,8 +1414,9 @@ EXPORT_SYMBOL_GPL(nfs_initiate_commit); * Set up the argument/result storage required for the RPC call. */ void nfs_init_commit(struct nfs_commit_data *data, - struct list_head *head, - struct pnfs_layout_segment *lseg) + struct list_head *head, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs_page *first = nfs_list_entry(head->next); struct inode *inode = first->wb_context->dentry->d_inode; @@ -1428,6 +1430,7 @@ void nfs_init_commit(struct nfs_commit_data *data, data->cred = first->wb_context->cred; data->lseg = lseg; /* reference transferred */ data->mds_ops = &nfs_commit_ops; + data->completion_ops = cinfo->completion_ops; data->args.fh = NFS_FH(data->inode); /* Note: we always request a commit of the entire inode */ @@ -1473,11 +1476,12 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, goto out_bad; /* Set up the argument struct */ - nfs_init_commit(data, head, NULL); + nfs_init_commit(data, head, NULL, cinfo); + atomic_inc(&cinfo->mds->rpcs_out); return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, how); out_bad: nfs_retry_commit(head, NULL, cinfo); - nfs_commit_clear_lock(NFS_I(inode)); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } @@ -1495,10 +1499,11 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_done(task, data); } -void nfs_commit_release_pages(struct nfs_commit_data *data) +static void nfs_commit_release_pages(struct nfs_commit_data *data) { struct nfs_page *req; int status = data->task.tk_status; + struct nfs_commit_info cinfo; while (!list_empty(&data->pages)) { req = nfs_list_entry(data->pages.next); @@ -1531,15 +1536,16 @@ void nfs_commit_release_pages(struct nfs_commit_data *data) next: nfs_unlock_request(req); } + nfs_init_cinfo(&cinfo, data->inode, data->dreq); + if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) + nfs_commit_clear_lock(NFS_I(data->inode)); } -EXPORT_SYMBOL_GPL(nfs_commit_release_pages); static void nfs_commit_release(void *calldata) { struct nfs_commit_data *data = calldata; - nfs_commit_release_pages(data); - nfs_commit_clear_lock(NFS_I(data->inode)); + data->completion_ops->completion(data); nfs_commitdata_release(calldata); } @@ -1549,6 +1555,11 @@ static const struct rpc_call_ops nfs_commit_ops = { .rpc_release = nfs_commit_release, }; +static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { + .completion = nfs_commit_release_pages, + .error_cleanup = nfs_commit_clear_lock, +}; + static int nfs_generic_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo) { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 224e1e82670c..0e8b88ad9ae2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1263,10 +1263,18 @@ struct nfs_mds_commit_info { struct list_head list; }; +struct nfs_commit_data; +struct nfs_inode; +struct nfs_commit_completion_ops { + void (*error_cleanup) (struct nfs_inode *nfsi); + void (*completion) (struct nfs_commit_data *data); +}; + struct nfs_commit_info { spinlock_t *lock; struct nfs_mds_commit_info *mds; struct pnfs_ds_commit_info *ds; + const struct nfs_commit_completion_ops *completion_ops; }; struct nfs_commit_data { @@ -1285,6 +1293,7 @@ struct nfs_commit_data { struct nfs_client *ds_clp; /* pNFS data server */ int ds_commit_index; const struct rpc_call_ops *mds_ops; + const struct nfs_commit_completion_ops *completion_ops; int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); }; -- cgit v1.2.3 From b359f9d09bcbaede09243cfe844172ba055d89fd Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Fri, 20 Apr 2012 14:47:55 -0400 Subject: NFS: add dreq to nfs_commit_info Need this to pass into nfs_commitdata_init, in order to keep data->dreq accurate. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 2 ++ include/linux/nfs_xdr.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 333d01d26292..44a93d8c7b52 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -506,6 +506,7 @@ static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, cinfo->lock = &inode->i_lock; cinfo->mds = &NFS_I(inode)->commit_info; cinfo->ds = pnfs_get_ds_info(inode); + cinfo->dreq = NULL; cinfo->completion_ops = &nfs_commit_completion_ops; } @@ -1431,6 +1432,7 @@ void nfs_init_commit(struct nfs_commit_data *data, data->lseg = lseg; /* reference transferred */ data->mds_ops = &nfs_commit_ops; data->completion_ops = cinfo->completion_ops; + data->dreq = cinfo->dreq; data->args.fh = NFS_FH(data->inode); /* Note: we always request a commit of the entire inode */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0e8b88ad9ae2..5f563bd113e8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1274,6 +1274,7 @@ struct nfs_commit_info { spinlock_t *lock; struct nfs_mds_commit_info *mds; struct pnfs_ds_commit_info *ds; + struct nfs_direct_req *dreq; /* O_DIRECT request */ const struct nfs_commit_completion_ops *completion_ops; }; -- cgit v1.2.3 From 2671bfc3beb44e70636bd0208274426db57f73b5 Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Fri, 27 Apr 2012 13:27:44 -0400 Subject: NFS: Remove secinfo knowledge out of the generic client And also remove the unneeded rpc_op. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 3 --- fs/nfs/namespace.c | 29 ----------------------------- fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4namespace.c | 29 +++++++++++++++++++++++++++++ fs/nfs/nfs4proc.c | 1 - include/linux/nfs_xdr.h | 1 - 6 files changed, 30 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index d68810f61869..d6994443f285 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -286,9 +286,6 @@ extern void nfs_sb_deactive(struct super_block *sb); extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen); extern struct vfsmount *nfs_d_automount(struct path *path); -#ifdef CONFIG_NFS_V4 -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); -#endif /* getroot.c */ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index d51868e5683c..2a9591b0b150 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -119,35 +119,6 @@ Elong: } #ifdef CONFIG_NFS_V4 -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) -{ - struct gss_api_mech *mech; - struct xdr_netobj oid; - int i; - rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; - - for (i = 0; i < flavors->num_flavors; i++) { - struct nfs4_secinfo_flavor *flavor; - flavor = &flavors->flavors[i]; - - if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) { - pseudoflavor = flavor->flavor; - break; - } else if (flavor->flavor == RPC_AUTH_GSS) { - oid.len = flavor->gss.sec_oid4.len; - oid.data = flavor->gss.sec_oid4.data; - mech = gss_mech_get_by_OID(&oid); - if (!mech) - continue; - pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service); - gss_mech_put(mech); - break; - } - } - - return pseudoflavor; -} - static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, struct qstr *name, struct nfs_fh *fh, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 8d75021020b3..53a487ee9867 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -206,6 +206,7 @@ extern const struct dentry_operations nfs4_dentry_operations; extern const struct inode_operations nfs4_dir_inode_operations; /* nfs4namespace.c */ +rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); /* nfs4proc.c */ diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index a7f3dedc4ec7..a69ee3952bbe 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -132,6 +132,35 @@ static size_t nfs_parse_server_name(char *string, size_t len, return ret; } +rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) +{ + struct gss_api_mech *mech; + struct xdr_netobj oid; + int i; + rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; + + for (i = 0; i < flavors->num_flavors; i++) { + struct nfs4_secinfo_flavor *flavor; + flavor = &flavors->flavors[i]; + + if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) { + pseudoflavor = flavor->flavor; + break; + } else if (flavor->flavor == RPC_AUTH_GSS) { + oid.len = flavor->gss.sec_oid4.len; + oid.data = flavor->gss.sec_oid4.data; + mech = gss_mech_get_by_OID(&oid); + if (!mech) + continue; + pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service); + gss_mech_put(mech); + break; + } + } + + return pseudoflavor; +} + static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name) { struct page *page; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 87af80d28a82..fa661b91e57c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6610,7 +6610,6 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .close_context = nfs4_close_context, .open_context = nfs4_atomic_open, .init_client = nfs4_init_client, - .secinfo = nfs4_proc_secinfo, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5f563bd113e8..eb1f143042f4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1397,7 +1397,6 @@ struct nfs_rpc_ops { struct iattr *iattr); int (*init_client) (struct nfs_client *, const struct rpc_timeout *, const char *, rpc_authflavor_t, int); - int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); }; /* -- cgit v1.2.3 From 281cad46b34db4dbb1d1e603f7b9cfe25d1ae7c9 Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Fri, 27 Apr 2012 13:27:45 -0400 Subject: NFS: Create a submount rpc_op This simplifies the code for v2 and v3 and gives v4 a chance to decide on referrals without needing to modify the generic client. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 15 +++------- fs/nfs/namespace.c | 75 +++++++++++++------------------------------------ fs/nfs/nfs3proc.c | 1 + fs/nfs/nfs4_fs.h | 2 ++ fs/nfs/nfs4namespace.c | 24 +++++++++++++++- fs/nfs/nfs4proc.c | 1 + fs/nfs/proc.c | 1 + include/linux/nfs_xdr.h | 2 ++ 8 files changed, 54 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index d6994443f285..0fd1efaf1cff 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -185,17 +185,6 @@ static inline void nfs_fs_proc_exit(void) } #endif -/* nfs4namespace.c */ -#ifdef CONFIG_NFS_V4 -extern struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry); -#else -static inline -struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) -{ - return ERR_PTR(-ENOENT); -} -#endif - /* callback_xdr.c */ extern struct svc_version nfs4_callback_version1; extern struct svc_version nfs4_callback_version4; @@ -286,6 +275,10 @@ extern void nfs_sb_deactive(struct super_block *sb); extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen); extern struct vfsmount *nfs_d_automount(struct path *path); +struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); +struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *, + struct nfs_fattr *, rpc_authflavor_t); /* getroot.c */ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 2a9591b0b150..e36fd8a51819 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -26,11 +26,6 @@ static LIST_HEAD(nfs_automount_list); static DECLARE_DELAYED_WORK(nfs_automount_task, nfs_expire_automounts); int nfs_mountpoint_expiry_timeout = 500 * HZ; -static struct vfsmount *nfs_do_submount(struct dentry *dentry, - struct nfs_fh *fh, - struct nfs_fattr *fattr, - rpc_authflavor_t authflavor); - /* * nfs_path - reconstruct the path given an arbitrary dentry * @base - used to return pointer to the end of devname part of path @@ -118,35 +113,6 @@ Elong: return ERR_PTR(-ENAMETOOLONG); } -#ifdef CONFIG_NFS_V4 -static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, - struct qstr *name, - struct nfs_fh *fh, - struct nfs_fattr *fattr) -{ - int err; - - if (NFS_PROTO(dir)->version == 4) - return nfs4_proc_lookup_mountpoint(dir, name, fh, fattr); - - err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr); - if (err) - return ERR_PTR(err); - return rpc_clone_client(NFS_SERVER(dir)->client); -} -#else /* CONFIG_NFS_V4 */ -static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, - struct qstr *name, - struct nfs_fh *fh, - struct nfs_fattr *fattr) -{ - int err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr); - if (err) - return ERR_PTR(err); - return rpc_clone_client(NFS_SERVER(dir)->client); -} -#endif /* CONFIG_NFS_V4 */ - /* * nfs_d_automount - Handle crossing a mountpoint on the server * @path - The mountpoint @@ -162,10 +128,9 @@ static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, struct vfsmount *nfs_d_automount(struct path *path) { struct vfsmount *mnt; - struct dentry *parent; + struct nfs_server *server = NFS_SERVER(path->dentry->d_inode); struct nfs_fh *fh = NULL; struct nfs_fattr *fattr = NULL; - struct rpc_clnt *client; dprintk("--> nfs_d_automount()\n"); @@ -181,21 +146,7 @@ struct vfsmount *nfs_d_automount(struct path *path) dprintk("%s: enter\n", __func__); - /* Look it up again to get its attributes */ - parent = dget_parent(path->dentry); - client = nfs_lookup_mountpoint(parent->d_inode, &path->dentry->d_name, fh, fattr); - dput(parent); - if (IS_ERR(client)) { - mnt = ERR_CAST(client); - goto out; - } - - if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) - mnt = nfs_do_refmount(client, path->dentry); - else - mnt = nfs_do_submount(path->dentry, fh, fattr, client->cl_auth->au_flavor); - rpc_shutdown_client(client); - + mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr); if (IS_ERR(mnt)) goto out; @@ -268,10 +219,8 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, * @authflavor - security flavor to use when performing the mount * */ -static struct vfsmount *nfs_do_submount(struct dentry *dentry, - struct nfs_fh *fh, - struct nfs_fattr *fattr, - rpc_authflavor_t authflavor) +struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, + struct nfs_fattr *fattr, rpc_authflavor_t authflavor) { struct nfs_clone_mount mountdata = { .sb = dentry->d_sb, @@ -304,3 +253,19 @@ out: dprintk("<-- nfs_do_submount() = %p\n", mnt); return mnt; } + +struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + int err; + struct dentry *parent = dget_parent(dentry); + + /* Look it up again to get its attributes */ + err = server->nfs_client->rpc_ops->lookup(server->client, parent->d_inode, + &dentry->d_name, fh, fattr); + dput(parent); + if (err != 0) + return ERR_PTR(err); + + return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor); +} diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 56dcefc2f3f7..c23214d55ecf 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -885,6 +885,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .file_inode_ops = &nfs3_file_inode_operations, .file_ops = &nfs_file_operations, .getroot = nfs3_proc_get_root, + .submount = nfs_submount, .getattr = nfs3_proc_getattr, .setattr = nfs3_proc_setattr, .lookup = nfs3_proc_lookup, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 53a487ee9867..97365b0f9d3f 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -208,6 +208,8 @@ extern const struct inode_operations nfs4_dir_inode_operations; /* nfs4namespace.c */ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); +struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); /* nfs4proc.c */ extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index a69ee3952bbe..80fc0fe7095e 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -329,7 +329,7 @@ out: * @dentry - dentry of referral * */ -struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) +static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) { struct vfsmount *mnt = ERR_PTR(-ENOMEM); struct dentry *parent; @@ -370,3 +370,25 @@ out: dprintk("%s: done\n", __func__); return mnt; } + +struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + struct dentry *parent = dget_parent(dentry); + struct rpc_clnt *client; + struct vfsmount *mnt; + + /* Look it up again to get its attributes and sec flavor */ + client = nfs4_proc_lookup_mountpoint(parent->d_inode, &dentry->d_name, fh, fattr); + dput(parent); + if (IS_ERR(client)) + return ERR_CAST(client); + + if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) + mnt = nfs_do_refmount(client, dentry); + else + mnt = nfs_do_submount(dentry, fh, fattr, client->cl_auth->au_flavor); + + rpc_shutdown_client(client); + return mnt; +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index fa661b91e57c..2091af294c61 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6571,6 +6571,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .file_inode_ops = &nfs4_file_inode_operations, .file_ops = &nfs4_file_operations, .getroot = nfs4_proc_get_root, + .submount = nfs4_submount, .getattr = nfs4_proc_getattr, .setattr = nfs4_proc_setattr, .lookup = nfs4_proc_lookup, diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 22ee70586875..76b3229fc527 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -742,6 +742,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .file_inode_ops = &nfs_file_inode_operations, .file_ops = &nfs_file_operations, .getroot = nfs_proc_get_root, + .submount = nfs_submount, .getattr = nfs_proc_getattr, .setattr = nfs_proc_setattr, .lookup = nfs_proc_lookup, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index eb1f143042f4..4dada94eba7d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1341,6 +1341,8 @@ struct nfs_rpc_ops { int (*getroot) (struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); + struct vfsmount *(*submount) (struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); int (*getattr) (struct nfs_server *, struct nfs_fh *, struct nfs_fattr *); int (*setattr) (struct dentry *, struct nfs_fattr *, -- cgit v1.2.3 From 80a16b21a81eb639f0b726549f4c46c0e9aff92e Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Fri, 27 Apr 2012 13:27:46 -0400 Subject: NFS: Remove extra rpc_clnt argument to proc_lookup Now that I'm doing secinfo automatically in the v4 code this extra argument isn't needed. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 6 +++--- fs/nfs/namespace.c | 3 +-- fs/nfs/nfs3proc.c | 2 +- fs/nfs/nfs4proc.c | 2 +- fs/nfs/proc.c | 2 +- include/linux/nfs_xdr.h | 2 +- 6 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 8789210c6905..82b42e2ea65c 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1143,7 +1143,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) if (fhandle == NULL || fattr == NULL) goto out_error; - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error) goto out_bad; if (nfs_compare_fh(NFS_FH(inode), fhandle)) @@ -1299,7 +1299,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru parent = dentry->d_parent; /* Protect against concurrent sillydeletes */ nfs_block_sillyrename(parent); - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error == -ENOENT) goto no_entry; if (error < 0) { @@ -1646,7 +1646,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, if (dentry->d_inode) goto out; if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error) goto out_error; } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index e36fd8a51819..08b9c93675da 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -261,8 +261,7 @@ struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, struct dentry *parent = dget_parent(dentry); /* Look it up again to get its attributes */ - err = server->nfs_client->rpc_ops->lookup(server->client, parent->d_inode, - &dentry->d_name, fh, fattr); + err = server->nfs_client->rpc_ops->lookup(parent->d_inode, &dentry->d_name, fh, fattr); dput(parent); if (err != 0) return ERR_PTR(err); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index c23214d55ecf..48bcad294161 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -142,7 +142,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs3_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, +nfs3_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs3_diropargs arg = { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2091af294c61..1780391a2c4c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2578,7 +2578,7 @@ out: return err; } -static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, +static int nfs4_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { int status; diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 76b3229fc527..fea9163d6f8e 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -178,7 +178,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, +nfs_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_diropargs arg = { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4dada94eba7d..c940d46eb423 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1347,7 +1347,7 @@ struct nfs_rpc_ops { struct nfs_fattr *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct rpc_clnt *clnt, struct inode *, struct qstr *, + int (*lookup) (struct inode *, struct qstr *, struct nfs_fh *, struct nfs_fattr *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, -- cgit v1.2.3 From 4f97615d19c370d1d907ef37f8bcd9c3672851ca Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 30 Apr 2012 18:39:20 -0400 Subject: NFS: Fix a compile issue when CONFIG_NFS_V4_1 is undefined struct nfs_direct_req can't compile when struct pnfs_ds_commit_info is undefined. Reported-by: Bryan Schumaker Signed-off-by: Trond Myklebust Cc: Fred Isaman --- include/linux/nfs_xdr.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c940d46eb423..6deb8f097c42 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1176,6 +1176,11 @@ struct nfs41_free_stateid_res { struct nfs4_sequence_res seq_res; }; +#else + +struct pnfs_ds_commit_info { +}; + #endif /* CONFIG_NFS_V4_1 */ struct nfs_page; -- cgit v1.2.3 From 4630b130b30be6420394ba31121e111c8771ca08 Mon Sep 17 00:00:00 2001 From: Aaron Sierra Date: Wed, 28 Mar 2012 09:43:10 -0500 Subject: mfd: Add LPC driver for Intel ICH chipsets This driver currently creates resources for use by a forthcoming ICH chipset GPIO driver. It could be expanded to create the resources for converting the esb2rom (mtd) and iTCO_wdt (wdt), and potentially more, drivers to use the mfd model. Signed-off-by: Aaron Sierra Signed-off-by: Guenter Roeck Signed-off-by: Samuel Ortiz --- drivers/mfd/Kconfig | 9 + drivers/mfd/Makefile | 1 + drivers/mfd/lpc_ich.c | 719 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/lpc_ich.h | 41 +++ 4 files changed, 770 insertions(+) create mode 100644 drivers/mfd/lpc_ich.c create mode 100644 include/linux/mfd/lpc_ich.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 11e44386fa9b..c6edba69678a 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -748,6 +748,15 @@ config LPC_SCH LPC bridge function of the Intel SCH provides support for System Management Bus and General Purpose I/O. +config LPC_ICH + tristate "Intel ICH LPC" + depends on PCI + select MFD_CORE + help + The LPC bridge function of the Intel ICH provides support for + many functional units. This driver provides needed support for + other drivers to control these functions, currently GPIO. + config MFD_RDC321X tristate "Support for RDC-R321x southbridge" select MFD_CORE diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 05fa538c5efe..c4500c35d5ba 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -99,6 +99,7 @@ obj-$(CONFIG_MFD_DB5500_PRCMU) += db5500-prcmu.o obj-$(CONFIG_MFD_TIMBERDALE) += timberdale.o obj-$(CONFIG_PMIC_ADP5520) += adp5520.o obj-$(CONFIG_LPC_SCH) += lpc_sch.o +obj-$(CONFIG_LPC_ICH) += lpc_ich.o obj-$(CONFIG_MFD_RDC321X) += rdc321x-southbridge.o obj-$(CONFIG_MFD_JANZ_CMODIO) += janz-cmodio.o obj-$(CONFIG_MFD_JZ4740_ADC) += jz4740-adc.o diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c new file mode 100644 index 000000000000..7e3a7b6ab022 --- /dev/null +++ b/drivers/mfd/lpc_ich.c @@ -0,0 +1,719 @@ +/* + * lpc_ich.c - LPC interface for Intel ICH + * + * LPC bridge function of the Intel ICH contains many other + * functional units, such as Interrupt controllers, Timers, + * Power Management, System Management, GPIO, RTC, and LPC + * Configuration Registers. + * + * This driver is derived from lpc_sch. + + * Copyright (c) 2011 Extreme Engineering Solution, Inc. + * Author: Aaron Sierra + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; see the file COPYING. If not, write to + * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + * + * This driver supports the following I/O Controller hubs: + * (See the intel documentation on http://developer.intel.com.) + * document number 290655-003, 290677-014: 82801AA (ICH), 82801AB (ICHO) + * document number 290687-002, 298242-027: 82801BA (ICH2) + * document number 290733-003, 290739-013: 82801CA (ICH3-S) + * document number 290716-001, 290718-007: 82801CAM (ICH3-M) + * document number 290744-001, 290745-025: 82801DB (ICH4) + * document number 252337-001, 252663-008: 82801DBM (ICH4-M) + * document number 273599-001, 273645-002: 82801E (C-ICH) + * document number 252516-001, 252517-028: 82801EB (ICH5), 82801ER (ICH5R) + * document number 300641-004, 300884-013: 6300ESB + * document number 301473-002, 301474-026: 82801F (ICH6) + * document number 313082-001, 313075-006: 631xESB, 632xESB + * document number 307013-003, 307014-024: 82801G (ICH7) + * document number 322896-001, 322897-001: NM10 + * document number 313056-003, 313057-017: 82801H (ICH8) + * document number 316972-004, 316973-012: 82801I (ICH9) + * document number 319973-002, 319974-002: 82801J (ICH10) + * document number 322169-001, 322170-003: 5 Series, 3400 Series (PCH) + * document number 320066-003, 320257-008: EP80597 (IICH) + * document number 324645-001, 324646-001: Cougar Point (CPT) + * document number TBD : Patsburg (PBG) + * document number TBD : DH89xxCC + * document number TBD : Panther Point + * document number TBD : Lynx Point + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#define ACPIBASE 0x40 +#define ACPIBASE_GPE_OFF 0x28 +#define ACPIBASE_GPE_END 0x2f +#define ACPICTRL 0x44 + +#define GPIOBASE 0x48 +#define GPIOCTRL 0x4C + +static int lpc_ich_acpi_save = -1; +static int lpc_ich_gpio_save = -1; + +static struct resource gpio_ich_res[] = { + /* GPIO */ + { + .flags = IORESOURCE_IO, + }, + /* ACPI - GPE0 */ + { + .flags = IORESOURCE_IO, + }, +}; + +enum lpc_cells { + LPC_GPIO = 0, +}; + +static struct mfd_cell lpc_ich_cells[] = { + [LPC_GPIO] = { + .name = "gpio_ich", + .num_resources = ARRAY_SIZE(gpio_ich_res), + .resources = gpio_ich_res, + .ignore_resource_conflicts = true, + }, +}; + +/* chipset related info */ +enum lpc_chipsets { + LPC_ICH = 0, /* ICH */ + LPC_ICH0, /* ICH0 */ + LPC_ICH2, /* ICH2 */ + LPC_ICH2M, /* ICH2-M */ + LPC_ICH3, /* ICH3-S */ + LPC_ICH3M, /* ICH3-M */ + LPC_ICH4, /* ICH4 */ + LPC_ICH4M, /* ICH4-M */ + LPC_CICH, /* C-ICH */ + LPC_ICH5, /* ICH5 & ICH5R */ + LPC_6300ESB, /* 6300ESB */ + LPC_ICH6, /* ICH6 & ICH6R */ + LPC_ICH6M, /* ICH6-M */ + LPC_ICH6W, /* ICH6W & ICH6RW */ + LPC_631XESB, /* 631xESB/632xESB */ + LPC_ICH7, /* ICH7 & ICH7R */ + LPC_ICH7DH, /* ICH7DH */ + LPC_ICH7M, /* ICH7-M & ICH7-U */ + LPC_ICH7MDH, /* ICH7-M DH */ + LPC_NM10, /* NM10 */ + LPC_ICH8, /* ICH8 & ICH8R */ + LPC_ICH8DH, /* ICH8DH */ + LPC_ICH8DO, /* ICH8DO */ + LPC_ICH8M, /* ICH8M */ + LPC_ICH8ME, /* ICH8M-E */ + LPC_ICH9, /* ICH9 */ + LPC_ICH9R, /* ICH9R */ + LPC_ICH9DH, /* ICH9DH */ + LPC_ICH9DO, /* ICH9DO */ + LPC_ICH9M, /* ICH9M */ + LPC_ICH9ME, /* ICH9M-E */ + LPC_ICH10, /* ICH10 */ + LPC_ICH10R, /* ICH10R */ + LPC_ICH10D, /* ICH10D */ + LPC_ICH10DO, /* ICH10DO */ + LPC_PCH, /* PCH Desktop Full Featured */ + LPC_PCHM, /* PCH Mobile Full Featured */ + LPC_P55, /* P55 */ + LPC_PM55, /* PM55 */ + LPC_H55, /* H55 */ + LPC_QM57, /* QM57 */ + LPC_H57, /* H57 */ + LPC_HM55, /* HM55 */ + LPC_Q57, /* Q57 */ + LPC_HM57, /* HM57 */ + LPC_PCHMSFF, /* PCH Mobile SFF Full Featured */ + LPC_QS57, /* QS57 */ + LPC_3400, /* 3400 */ + LPC_3420, /* 3420 */ + LPC_3450, /* 3450 */ + LPC_EP80579, /* EP80579 */ + LPC_CPT, /* Cougar Point */ + LPC_CPTD, /* Cougar Point Desktop */ + LPC_CPTM, /* Cougar Point Mobile */ + LPC_PBG, /* Patsburg */ + LPC_DH89XXCC, /* DH89xxCC */ + LPC_PPT, /* Panther Point */ + LPC_LPT, /* Lynx Point */ +}; + +struct lpc_ich_info lpc_chipset_info[] __devinitdata = { + [LPC_ICH] = { + .name = "ICH", + }, + [LPC_ICH0] = { + .name = "ICH0", + }, + [LPC_ICH2] = { + .name = "ICH2", + }, + [LPC_ICH2M] = { + .name = "ICH2-M", + }, + [LPC_ICH3] = { + .name = "ICH3-S", + }, + [LPC_ICH3M] = { + .name = "ICH3-M", + }, + [LPC_ICH4] = { + .name = "ICH4", + }, + [LPC_ICH4M] = { + .name = "ICH4-M", + }, + [LPC_CICH] = { + .name = "C-ICH", + }, + [LPC_ICH5] = { + .name = "ICH5 or ICH5R", + }, + [LPC_6300ESB] = { + .name = "6300ESB", + }, + [LPC_ICH6] = { + .name = "ICH6 or ICH6R", + .gpio_version = ICH_V6_GPIO, + }, + [LPC_ICH6M] = { + .name = "ICH6-M", + .gpio_version = ICH_V6_GPIO, + }, + [LPC_ICH6W] = { + .name = "ICH6W or ICH6RW", + .gpio_version = ICH_V6_GPIO, + }, + [LPC_631XESB] = { + .name = "631xESB/632xESB", + .gpio_version = ICH_V6_GPIO, + }, + [LPC_ICH7] = { + .name = "ICH7 or ICH7R", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_ICH7DH] = { + .name = "ICH7DH", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_ICH7M] = { + .name = "ICH7-M or ICH7-U", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_ICH7MDH] = { + .name = "ICH7-M DH", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_NM10] = { + .name = "NM10", + }, + [LPC_ICH8] = { + .name = "ICH8 or ICH8R", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_ICH8DH] = { + .name = "ICH8DH", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_ICH8DO] = { + .name = "ICH8DO", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_ICH8M] = { + .name = "ICH8M", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_ICH8ME] = { + .name = "ICH8M-E", + .gpio_version = ICH_V7_GPIO, + }, + [LPC_ICH9] = { + .name = "ICH9", + .gpio_version = ICH_V9_GPIO, + }, + [LPC_ICH9R] = { + .name = "ICH9R", + .gpio_version = ICH_V9_GPIO, + }, + [LPC_ICH9DH] = { + .name = "ICH9DH", + .gpio_version = ICH_V9_GPIO, + }, + [LPC_ICH9DO] = { + .name = "ICH9DO", + .gpio_version = ICH_V9_GPIO, + }, + [LPC_ICH9M] = { + .name = "ICH9M", + .gpio_version = ICH_V9_GPIO, + }, + [LPC_ICH9ME] = { + .name = "ICH9M-E", + .gpio_version = ICH_V9_GPIO, + }, + [LPC_ICH10] = { + .name = "ICH10", + .gpio_version = ICH_V10CONS_GPIO, + }, + [LPC_ICH10R] = { + .name = "ICH10R", + .gpio_version = ICH_V10CONS_GPIO, + }, + [LPC_ICH10D] = { + .name = "ICH10D", + .gpio_version = ICH_V10CORP_GPIO, + }, + [LPC_ICH10DO] = { + .name = "ICH10DO", + .gpio_version = ICH_V10CORP_GPIO, + }, + [LPC_PCH] = { + .name = "PCH Desktop Full Featured", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_PCHM] = { + .name = "PCH Mobile Full Featured", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_P55] = { + .name = "P55", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_PM55] = { + .name = "PM55", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_H55] = { + .name = "H55", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_QM57] = { + .name = "QM57", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_H57] = { + .name = "H57", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_HM55] = { + .name = "HM55", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_Q57] = { + .name = "Q57", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_HM57] = { + .name = "HM57", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_PCHMSFF] = { + .name = "PCH Mobile SFF Full Featured", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_QS57] = { + .name = "QS57", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_3400] = { + .name = "3400", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_3420] = { + .name = "3420", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_3450] = { + .name = "3450", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_EP80579] = { + .name = "EP80579", + }, + [LPC_CPT] = { + .name = "Cougar Point", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_CPTD] = { + .name = "Cougar Point Desktop", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_CPTM] = { + .name = "Cougar Point Mobile", + .gpio_version = ICH_V5_GPIO, + }, + [LPC_PBG] = { + .name = "Patsburg", + }, + [LPC_DH89XXCC] = { + .name = "DH89xxCC", + }, + [LPC_PPT] = { + .name = "Panther Point", + }, + [LPC_LPT] = { + .name = "Lynx Point", + }, +}; + +/* + * This data only exists for exporting the supported PCI ids + * via MODULE_DEVICE_TABLE. We do not actually register a + * pci_driver, because the I/O Controller Hub has also other + * functions that probably will be registered by other drivers. + */ +static DEFINE_PCI_DEVICE_TABLE(lpc_ich_ids) = { + { PCI_VDEVICE(INTEL, 0x2410), LPC_ICH}, + { PCI_VDEVICE(INTEL, 0x2420), LPC_ICH0}, + { PCI_VDEVICE(INTEL, 0x2440), LPC_ICH2}, + { PCI_VDEVICE(INTEL, 0x244c), LPC_ICH2M}, + { PCI_VDEVICE(INTEL, 0x2480), LPC_ICH3}, + { PCI_VDEVICE(INTEL, 0x248c), LPC_ICH3M}, + { PCI_VDEVICE(INTEL, 0x24c0), LPC_ICH4}, + { PCI_VDEVICE(INTEL, 0x24cc), LPC_ICH4M}, + { PCI_VDEVICE(INTEL, 0x2450), LPC_CICH}, + { PCI_VDEVICE(INTEL, 0x24d0), LPC_ICH5}, + { PCI_VDEVICE(INTEL, 0x25a1), LPC_6300ESB}, + { PCI_VDEVICE(INTEL, 0x2640), LPC_ICH6}, + { PCI_VDEVICE(INTEL, 0x2641), LPC_ICH6M}, + { PCI_VDEVICE(INTEL, 0x2642), LPC_ICH6W}, + { PCI_VDEVICE(INTEL, 0x2670), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2671), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2672), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2673), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2674), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2675), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2676), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2677), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2678), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x2679), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x267a), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x267b), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x267c), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x267d), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x267e), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x267f), LPC_631XESB}, + { PCI_VDEVICE(INTEL, 0x27b8), LPC_ICH7}, + { PCI_VDEVICE(INTEL, 0x27b0), LPC_ICH7DH}, + { PCI_VDEVICE(INTEL, 0x27b9), LPC_ICH7M}, + { PCI_VDEVICE(INTEL, 0x27bd), LPC_ICH7MDH}, + { PCI_VDEVICE(INTEL, 0x27bc), LPC_NM10}, + { PCI_VDEVICE(INTEL, 0x2810), LPC_ICH8}, + { PCI_VDEVICE(INTEL, 0x2812), LPC_ICH8DH}, + { PCI_VDEVICE(INTEL, 0x2814), LPC_ICH8DO}, + { PCI_VDEVICE(INTEL, 0x2815), LPC_ICH8M}, + { PCI_VDEVICE(INTEL, 0x2811), LPC_ICH8ME}, + { PCI_VDEVICE(INTEL, 0x2918), LPC_ICH9}, + { PCI_VDEVICE(INTEL, 0x2916), LPC_ICH9R}, + { PCI_VDEVICE(INTEL, 0x2912), LPC_ICH9DH}, + { PCI_VDEVICE(INTEL, 0x2914), LPC_ICH9DO}, + { PCI_VDEVICE(INTEL, 0x2919), LPC_ICH9M}, + { PCI_VDEVICE(INTEL, 0x2917), LPC_ICH9ME}, + { PCI_VDEVICE(INTEL, 0x3a18), LPC_ICH10}, + { PCI_VDEVICE(INTEL, 0x3a16), LPC_ICH10R}, + { PCI_VDEVICE(INTEL, 0x3a1a), LPC_ICH10D}, + { PCI_VDEVICE(INTEL, 0x3a14), LPC_ICH10DO}, + { PCI_VDEVICE(INTEL, 0x3b00), LPC_PCH}, + { PCI_VDEVICE(INTEL, 0x3b01), LPC_PCHM}, + { PCI_VDEVICE(INTEL, 0x3b02), LPC_P55}, + { PCI_VDEVICE(INTEL, 0x3b03), LPC_PM55}, + { PCI_VDEVICE(INTEL, 0x3b06), LPC_H55}, + { PCI_VDEVICE(INTEL, 0x3b07), LPC_QM57}, + { PCI_VDEVICE(INTEL, 0x3b08), LPC_H57}, + { PCI_VDEVICE(INTEL, 0x3b09), LPC_HM55}, + { PCI_VDEVICE(INTEL, 0x3b0a), LPC_Q57}, + { PCI_VDEVICE(INTEL, 0x3b0b), LPC_HM57}, + { PCI_VDEVICE(INTEL, 0x3b0d), LPC_PCHMSFF}, + { PCI_VDEVICE(INTEL, 0x3b0f), LPC_QS57}, + { PCI_VDEVICE(INTEL, 0x3b12), LPC_3400}, + { PCI_VDEVICE(INTEL, 0x3b14), LPC_3420}, + { PCI_VDEVICE(INTEL, 0x3b16), LPC_3450}, + { PCI_VDEVICE(INTEL, 0x5031), LPC_EP80579}, + { PCI_VDEVICE(INTEL, 0x1c41), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c42), LPC_CPTD}, + { PCI_VDEVICE(INTEL, 0x1c43), LPC_CPTM}, + { PCI_VDEVICE(INTEL, 0x1c44), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c45), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c46), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c47), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c48), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c49), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c4a), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c4b), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c4c), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c4d), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c4e), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c4f), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c50), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c51), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c52), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c53), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c54), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c55), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c56), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c57), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c58), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c59), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c5a), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c5b), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c5c), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c5d), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c5e), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1c5f), LPC_CPT}, + { PCI_VDEVICE(INTEL, 0x1d40), LPC_PBG}, + { PCI_VDEVICE(INTEL, 0x1d41), LPC_PBG}, + { PCI_VDEVICE(INTEL, 0x2310), LPC_DH89XXCC}, + { PCI_VDEVICE(INTEL, 0x1e40), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e41), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e42), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e43), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e44), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e45), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e46), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e47), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e48), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e49), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e4a), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e4b), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e4c), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e4d), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e4e), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e4f), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e50), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e51), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e52), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e53), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e54), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e55), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e56), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e57), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e58), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e59), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e5a), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e5b), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e5c), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e5d), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e5e), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x1e5f), LPC_PPT}, + { PCI_VDEVICE(INTEL, 0x8c40), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c41), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c42), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c43), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c44), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c45), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c46), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c47), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c48), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c49), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c4a), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c4b), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c4c), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c4d), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c4e), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c4f), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c50), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c51), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c52), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c53), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c54), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c55), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c56), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c57), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c58), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c59), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c5a), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c5b), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c5c), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c5d), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c5e), LPC_LPT}, + { PCI_VDEVICE(INTEL, 0x8c5f), LPC_LPT}, + { 0, }, /* End of list */ +}; +MODULE_DEVICE_TABLE(pci, lpc_ich_ids); + +static void lpc_ich_restore_config_space(struct pci_dev *dev) +{ + if (lpc_ich_acpi_save >= 0) { + pci_write_config_byte(dev, ACPICTRL, lpc_ich_acpi_save); + lpc_ich_acpi_save = -1; + } + + if (lpc_ich_gpio_save >= 0) { + pci_write_config_byte(dev, GPIOCTRL, lpc_ich_gpio_save); + lpc_ich_gpio_save = -1; + } +} + +static void __devinit lpc_ich_enable_acpi_space(struct pci_dev *dev) +{ + u8 reg_save; + + pci_read_config_byte(dev, ACPICTRL, ®_save); + pci_write_config_byte(dev, ACPICTRL, reg_save | 0x10); + lpc_ich_acpi_save = reg_save; +} + +static void __devinit lpc_ich_enable_gpio_space(struct pci_dev *dev) +{ + u8 reg_save; + + pci_read_config_byte(dev, GPIOCTRL, ®_save); + pci_write_config_byte(dev, GPIOCTRL, reg_save | 0x10); + lpc_ich_gpio_save = reg_save; +} + +static void __devinit lpc_ich_finalize_cell(struct mfd_cell *cell, + const struct pci_device_id *id) +{ + cell->platform_data = &lpc_chipset_info[id->driver_data]; + cell->pdata_size = sizeof(struct lpc_ich_info); +} + +static int __devinit lpc_ich_init_gpio(struct pci_dev *dev, + const struct pci_device_id *id) +{ + u32 base_addr_cfg; + u32 base_addr; + int ret; + bool acpi_conflict = false; + struct resource *res; + + /* Setup power management base register */ + pci_read_config_dword(dev, ACPIBASE, &base_addr_cfg); + base_addr = base_addr_cfg & 0x0000ff80; + if (!base_addr) { + dev_err(&dev->dev, "I/O space for ACPI uninitialized\n"); + lpc_ich_cells[LPC_GPIO].num_resources--; + goto gpe0_done; + } + + res = &gpio_ich_res[ICH_RES_GPE0]; + res->start = base_addr + ACPIBASE_GPE_OFF; + res->end = base_addr + ACPIBASE_GPE_END; + ret = acpi_check_resource_conflict(res); + if (ret) { + /* + * This isn't fatal for the GPIO, but we have to make sure that + * the platform_device subsystem doesn't see this resource + * or it will register an invalid region. + */ + lpc_ich_cells[LPC_GPIO].num_resources--; + acpi_conflict = true; + } else { + lpc_ich_enable_acpi_space(dev); + } + +gpe0_done: + /* Setup GPIO base register */ + pci_read_config_dword(dev, GPIOBASE, &base_addr_cfg); + base_addr = base_addr_cfg & 0x0000ff80; + if (!base_addr) { + dev_err(&dev->dev, "I/O space for GPIO uninitialized\n"); + ret = -ENODEV; + goto gpio_done; + } + + /* Older devices provide fewer GPIO and have a smaller resource size. */ + res = &gpio_ich_res[ICH_RES_GPIO]; + res->start = base_addr; + switch (lpc_chipset_info[id->driver_data].gpio_version) { + case ICH_V5_GPIO: + case ICH_V10CORP_GPIO: + res->end = res->start + 128 - 1; + break; + default: + res->end = res->start + 64 - 1; + break; + } + + ret = acpi_check_resource_conflict(res); + if (ret) { + /* this isn't necessarily fatal for the GPIO */ + acpi_conflict = true; + goto gpio_done; + } + lpc_ich_enable_gpio_space(dev); + + lpc_ich_finalize_cell(&lpc_ich_cells[LPC_GPIO], id); + ret = mfd_add_devices(&dev->dev, -1, &lpc_ich_cells[LPC_GPIO], + 1, NULL, 0); + +gpio_done: + if (acpi_conflict) + pr_warn("Resource conflict(s) found affecting %s\n", + lpc_ich_cells[LPC_GPIO].name); + return ret; +} + +static int __devinit lpc_ich_probe(struct pci_dev *dev, + const struct pci_device_id *id) +{ + int ret; + bool cell_added = false; + + ret = lpc_ich_init_gpio(dev, id); + if (!ret) + cell_added = true; + + /* + * We only care if at least one or none of the cells registered + * successfully. + */ + if (!cell_added) { + lpc_ich_restore_config_space(dev); + return -ENODEV; + } + + return 0; +} + +static void __devexit lpc_ich_remove(struct pci_dev *dev) +{ + mfd_remove_devices(&dev->dev); + lpc_ich_restore_config_space(dev); +} + +static struct pci_driver lpc_ich_driver = { + .name = "lpc_ich", + .id_table = lpc_ich_ids, + .probe = lpc_ich_probe, + .remove = __devexit_p(lpc_ich_remove), +}; + +static int __init lpc_ich_init(void) +{ + return pci_register_driver(&lpc_ich_driver); +} + +static void __exit lpc_ich_exit(void) +{ + pci_unregister_driver(&lpc_ich_driver); +} + +module_init(lpc_ich_init); +module_exit(lpc_ich_exit); + +MODULE_AUTHOR("Aaron Sierra "); +MODULE_DESCRIPTION("LPC interface for Intel ICH"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h new file mode 100644 index 000000000000..91300b18219b --- /dev/null +++ b/include/linux/mfd/lpc_ich.h @@ -0,0 +1,41 @@ +/* + * linux/drivers/mfd/lpc_ich.h + * + * Copyright (c) 2012 Extreme Engineering Solution, Inc. + * Author: Aaron Sierra + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; see the file COPYING. If not, write to + * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + */ +#ifndef LPC_ICH_H +#define LPC_ICH_H + +/* GPIO resources */ +#define ICH_RES_GPIO 0 +#define ICH_RES_GPE0 1 + +/* GPIO compatibility */ +#define ICH_I3100_GPIO 0x401 +#define ICH_V5_GPIO 0x501 +#define ICH_V6_GPIO 0x601 +#define ICH_V7_GPIO 0x701 +#define ICH_V9_GPIO 0x801 +#define ICH_V10CORP_GPIO 0xa01 +#define ICH_V10CONS_GPIO 0xa11 + +struct lpc_ich_info { + char name[32]; + unsigned int gpio_version; +}; + +#endif -- cgit v1.2.3 From 4f304245bb6cfa665ff21b12c059499eafa8b725 Mon Sep 17 00:00:00 2001 From: Paul Parsons Date: Mon, 9 Apr 2012 13:18:31 +0100 Subject: mfd: Set asic3 DS1WM clock_rate The mfd/asic3 driver does not set the ds1wm_driver_data clock_rate field before passing the structure to the DS1WM w1 busmaster driver. This was not noticed before commit 26a6afb, because ds1wm_find_divisor() unintentionally returned the correct divisor when a zero clock_rate was passed in. However after that commit DS1WM fails a zero clock_rate: ds1wm ds1wm: no suitable divisor for 0Hz clock This patch sets the ds1wm_driver_data clock_rate field. Signed-off-by: Paul Parsons Acked-by: Philipp Zabel Signed-off-by: Samuel Ortiz --- drivers/mfd/asic3.c | 9 ++++++--- include/linux/mfd/asic3.h | 2 ++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c index f75dc6733f49..4c3ec8113e7e 100644 --- a/drivers/mfd/asic3.c +++ b/drivers/mfd/asic3.c @@ -894,10 +894,13 @@ static int __init asic3_mfd_probe(struct platform_device *pdev, asic3_mmc_resources[0].start >>= asic->bus_shift; asic3_mmc_resources[0].end >>= asic->bus_shift; - ret = mfd_add_devices(&pdev->dev, pdev->id, + if (pdata->clock_rate) { + ds1wm_pdata.clock_rate = pdata->clock_rate; + ret = mfd_add_devices(&pdev->dev, pdev->id, &asic3_cell_ds1wm, 1, mem, asic->irq_base); - if (ret < 0) - goto out; + if (ret < 0) + goto out; + } if (mem_sdio && (irq >= 0)) { ret = mfd_add_devices(&pdev->dev, pdev->id, diff --git a/include/linux/mfd/asic3.h b/include/linux/mfd/asic3.h index ed793b77a1c5..3fda7e589ccd 100644 --- a/include/linux/mfd/asic3.h +++ b/include/linux/mfd/asic3.h @@ -31,6 +31,8 @@ struct asic3_platform_data { unsigned int gpio_base; + unsigned int clock_rate; + struct asic3_led *leds; }; -- cgit v1.2.3 From 201cf052810d20814a77ca0e0045a2c1a3508a1f Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 18 Apr 2012 12:13:51 +0200 Subject: mfd: Add support for tps65910 device sleep Adding support for device sleep through the external input control signal "SLEEP". Changing the SLEEP signal state can switch the device into SLEEP and ACTIVE state. Also adding sleep configuration for different resources so that they should be keep on during sleep state of device. Signed-off-by: Laxman Dewangan Signed-off-by: Samuel Ortiz --- drivers/mfd/tps65910.c | 62 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/tps65910.h | 14 ++++++++++ 2 files changed, 76 insertions(+) (limited to 'include/linux') diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c index bf2b25ebf2ca..ae7f47b6e71b 100644 --- a/drivers/mfd/tps65910.c +++ b/drivers/mfd/tps65910.c @@ -90,6 +90,66 @@ static const struct regmap_config tps65910_regmap_config = { .cache_type = REGCACHE_RBTREE, }; +static int __init tps65910_sleepinit(struct tps65910 *tps65910, + struct tps65910_board *pmic_pdata) +{ + struct device *dev = NULL; + int ret = 0; + + dev = tps65910->dev; + + if (!pmic_pdata->en_dev_slp) + return 0; + + /* enabling SLEEP device state */ + ret = tps65910_set_bits(tps65910, TPS65910_DEVCTRL, + DEVCTRL_DEV_SLP_MASK); + if (ret < 0) { + dev_err(dev, "set dev_slp failed: %d\n", ret); + goto err_sleep_init; + } + + /* Return if there is no sleep keepon data. */ + if (!pmic_pdata->slp_keepon) + return 0; + + if (pmic_pdata->slp_keepon->therm_keepon) { + ret = tps65910_set_bits(tps65910, TPS65910_SLEEP_KEEP_RES_ON, + SLEEP_KEEP_RES_ON_THERM_KEEPON_MASK); + if (ret < 0) { + dev_err(dev, "set therm_keepon failed: %d\n", ret); + goto disable_dev_slp; + } + } + + if (pmic_pdata->slp_keepon->clkout32k_keepon) { + ret = tps65910_set_bits(tps65910, TPS65910_SLEEP_KEEP_RES_ON, + SLEEP_KEEP_RES_ON_CLKOUT32K_KEEPON_MASK); + if (ret < 0) { + dev_err(dev, "set clkout32k_keepon failed: %d\n", ret); + goto disable_dev_slp; + } + } + + if (pmic_pdata->slp_keepon->i2chs_keepon) { + ret = tps65910_set_bits(tps65910, TPS65910_SLEEP_KEEP_RES_ON, + SLEEP_KEEP_RES_ON_I2CHS_KEEPON_MASK); + if (ret < 0) { + dev_err(dev, "set i2chs_keepon failed: %d\n", ret); + goto disable_dev_slp; + } + } + + return 0; + +disable_dev_slp: + tps65910_clear_bits(tps65910, TPS65910_DEVCTRL, DEVCTRL_DEV_SLP_MASK); + +err_sleep_init: + return ret; +} + + static int tps65910_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { @@ -140,6 +200,8 @@ static int tps65910_i2c_probe(struct i2c_client *i2c, tps65910_irq_init(tps65910, init_data->irq, init_data); + tps65910_sleepinit(tps65910, pmic_plat_data); + kfree(init_data); return ret; diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index 1c6c2860d1a6..56903ad04283 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -783,6 +783,18 @@ #define TPS65910_SLEEP_CONTROL_EXT_INPUT_EN3 0x4 #define TPS65911_SLEEP_CONTROL_EXT_INPUT_SLEEP 0x8 +/* + * Sleep keepon data: Maintains the state in sleep mode + * @therm_keepon: Keep on the thermal monitoring in sleep state. + * @clkout32k_keepon: Keep on the 32KHz clock output in sleep state. + * @i2chs_keepon: Keep on high speed internal clock in sleep state. + */ +struct tps65910_sleep_keepon_data { + unsigned therm_keepon:1; + unsigned clkout32k_keepon:1; + unsigned i2chs_keepon:1; +}; + /** * struct tps65910_board * Board platform data may be used to initialize regulators. @@ -794,6 +806,8 @@ struct tps65910_board { int irq_base; int vmbch_threshold; int vmbch2_threshold; + bool en_dev_slp; + struct tps65910_sleep_keepon_data *slp_keepon; bool en_gpio_sleep[TPS6591X_MAX_NUM_GPIO]; unsigned long regulator_ext_sleep_control[TPS65910_NUM_REGS]; struct regulator_init_data *tps65910_pmic_init_data[TPS65910_NUM_REGS]; -- cgit v1.2.3 From 44f72e53382c9c673fd54c3bab67a6b9a2d4526e Mon Sep 17 00:00:00 2001 From: Virupax Sadashivpetimath Date: Tue, 17 Apr 2012 09:30:14 +0200 Subject: mfd: Add new resources on ab8500 AB8505 and AB9540 The AB8505 and AB9540 has extended support for micro USB resistance detection, used for detecting chargers. Let's register resources for this resource. Let's also split off the separate codec device for AB9540. Signed-off-by: Virupax Sadashivpetimath Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- drivers/mfd/ab8500-core.c | 60 +++++++++++++++++++++++++++++++++++---- include/linux/mfd/abx500/ab8500.h | 12 ++++++-- 2 files changed, 65 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c index 1f08704f7ae8..ae67612317a8 100644 --- a/drivers/mfd/ab8500-core.c +++ b/drivers/mfd/ab8500-core.c @@ -744,6 +744,39 @@ static struct resource __devinitdata ab8500_usb_resources[] = { }, }; +static struct resource __devinitdata ab8505_iddet_resources[] = { + { + .name = "KeyDeglitch", + .start = AB8505_INT_KEYDEGLITCH, + .end = AB8505_INT_KEYDEGLITCH, + .flags = IORESOURCE_IRQ, + }, + { + .name = "KP", + .start = AB8505_INT_KP, + .end = AB8505_INT_KP, + .flags = IORESOURCE_IRQ, + }, + { + .name = "IKP", + .start = AB8505_INT_IKP, + .end = AB8505_INT_IKP, + .flags = IORESOURCE_IRQ, + }, + { + .name = "IKR", + .start = AB8505_INT_IKR, + .end = AB8505_INT_IKR, + .flags = IORESOURCE_IRQ, + }, + { + .name = "KeyStuck", + .start = AB8505_INT_KEYSTUCK, + .end = AB8505_INT_KEYSTUCK, + .flags = IORESOURCE_IRQ, + }, +}; + static struct resource __devinitdata ab8500_temp_resources[] = { { .name = "AB8500_TEMP_WARM", @@ -802,10 +835,6 @@ static struct mfd_cell __devinitdata abx500_common_devs[] = { .num_resources = ARRAY_SIZE(ab8500_av_acc_detect_resources), .resources = ab8500_av_acc_detect_resources, }, - { - .name = "ab8500-codec", - }, - { .name = "ab8500-poweron-key", .num_resources = ARRAY_SIZE(ab8500_poweronkey_db_resources), @@ -845,6 +874,9 @@ static struct mfd_cell __devinitdata ab8500_devs[] = { .num_resources = ARRAY_SIZE(ab8500_usb_resources), .resources = ab8500_usb_resources, }, + { + .name = "ab8500-codec", + }, }; static struct mfd_cell __devinitdata ab9540_devs[] = { @@ -858,6 +890,18 @@ static struct mfd_cell __devinitdata ab9540_devs[] = { .num_resources = ARRAY_SIZE(ab8500_usb_resources), .resources = ab8500_usb_resources, }, + { + .name = "ab9540-codec", + }, +}; + +/* Device list common to ab9540 and ab8505 */ +static struct mfd_cell __devinitdata ab9540_ab8505_devs[] = { + { + .name = "ab-iddet", + .num_resources = ARRAY_SIZE(ab8505_iddet_resources), + .resources = ab8505_iddet_resources, + }, }; static ssize_t show_chip_id(struct device *dev, @@ -1125,8 +1169,14 @@ int __devinit ab8500_init(struct ab8500 *ab8500, enum ab8500_version version) ab8500->irq_base); else ret = mfd_add_devices(ab8500->dev, 0, ab8500_devs, - ARRAY_SIZE(ab9540_devs), NULL, + ARRAY_SIZE(ab8500_devs), NULL, + ab8500->irq_base); + + if (is_ab9540(ab8500) || is_ab8505(ab8500)) + ret = mfd_add_devices(ab8500->dev, 0, ab9540_ab8505_devs, + ARRAY_SIZE(ab9540_ab8505_devs), NULL, ab8500->irq_base); + if (ret) goto out_freeirq; diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index fccc3002f271..d798f5b6a55f 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -194,6 +194,14 @@ enum ab8500_version { #define AB9540_INT_GPIO52F 123 #define AB9540_INT_GPIO53F 124 #define AB9540_INT_GPIO54F 125 /* not 8505 */ +/* ab8500_irq_regoffset[16] -> IT[Source|Latch|Mask]25 */ +#define AB8505_INT_KEYSTUCK 128 +#define AB8505_INT_IKR 129 +#define AB8505_INT_IKP 130 +#define AB8505_INT_KP 131 +#define AB8505_INT_KEYDEGLITCH 132 +#define AB8505_INT_MODPWRSTATUSF 134 +#define AB8505_INT_MODPWRSTATUSR 135 /* * AB8500_AB9540_NR_IRQS is used when configuring the IRQ numbers for the @@ -203,8 +211,8 @@ enum ab8500_version { * which is larger. */ #define AB8500_NR_IRQS 112 -#define AB8505_NR_IRQS 128 -#define AB9540_NR_IRQS 128 +#define AB8505_NR_IRQS 136 +#define AB9540_NR_IRQS 136 /* This is set to the roof of any AB8500 chip variant IRQ counts */ #define AB8500_MAX_NR_IRQS AB9540_NR_IRQS -- cgit v1.2.3 From 112a80d29b529d4057777ac2cb4ec15ff5b6d210 Mon Sep 17 00:00:00 2001 From: Jonas Aaberg Date: Tue, 17 Apr 2012 09:30:33 +0200 Subject: mfd: Deny ab8500 suspend if i2c transfer is ongoing If we are in the middle of an I2C transfer we need to deny suspend of the AB8500 core. Implement an atomic reference counter for the I2C operations to make sure we don't do this. Signed-off-by: Jonas Aaberg Reviewed-by: Mattias Wallin Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- drivers/mfd/ab8500-core.c | 38 +++++++++++++++++++++++++++++++------- include/linux/mfd/abx500/ab8500.h | 6 +++++- 2 files changed, 36 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c index ae67612317a8..eee95606bdbb 100644 --- a/drivers/mfd/ab8500-core.c +++ b/drivers/mfd/ab8500-core.c @@ -161,9 +161,13 @@ static int set_register_interruptible(struct ab8500 *ab8500, u8 bank, static int ab8500_set_register(struct device *dev, u8 bank, u8 reg, u8 value) { + int ret; struct ab8500 *ab8500 = dev_get_drvdata(dev->parent); - return set_register_interruptible(ab8500, bank, reg, value); + atomic_inc(&ab8500->transfer_ongoing); + ret = set_register_interruptible(ab8500, bank, reg, value); + atomic_dec(&ab8500->transfer_ongoing); + return ret; } static int get_register_interruptible(struct ab8500 *ab8500, u8 bank, @@ -192,9 +196,13 @@ static int get_register_interruptible(struct ab8500 *ab8500, u8 bank, static int ab8500_get_register(struct device *dev, u8 bank, u8 reg, u8 *value) { + int ret; struct ab8500 *ab8500 = dev_get_drvdata(dev->parent); - return get_register_interruptible(ab8500, bank, reg, value); + atomic_inc(&ab8500->transfer_ongoing); + ret = get_register_interruptible(ab8500, bank, reg, value); + atomic_dec(&ab8500->transfer_ongoing); + return ret; } static int mask_and_set_register_interruptible(struct ab8500 *ab8500, u8 bank, @@ -241,11 +249,14 @@ out: static int ab8500_mask_and_set_register(struct device *dev, u8 bank, u8 reg, u8 bitmask, u8 bitvalues) { + int ret; struct ab8500 *ab8500 = dev_get_drvdata(dev->parent); - return mask_and_set_register_interruptible(ab8500, bank, reg, - bitmask, bitvalues); - + atomic_inc(&ab8500->transfer_ongoing); + ret= mask_and_set_register_interruptible(ab8500, bank, reg, + bitmask, bitvalues); + atomic_dec(&ab8500->transfer_ongoing); + return ret; } static struct abx500_ops ab8500_ops = { @@ -264,6 +275,7 @@ static void ab8500_irq_lock(struct irq_data *data) struct ab8500 *ab8500 = irq_data_get_irq_chip_data(data); mutex_lock(&ab8500->irq_lock); + atomic_inc(&ab8500->transfer_ongoing); } static void ab8500_irq_sync_unlock(struct irq_data *data) @@ -292,7 +304,7 @@ static void ab8500_irq_sync_unlock(struct irq_data *data) reg = AB8500_IT_MASK1_REG + ab8500->irq_reg_offset[i]; set_register_interruptible(ab8500, AB8500_INTERRUPT, reg, new); } - + atomic_dec(&ab8500->transfer_ongoing); mutex_unlock(&ab8500->irq_lock); } @@ -332,6 +344,8 @@ static irqreturn_t ab8500_irq(int irq, void *dev) dev_vdbg(ab8500->dev, "interrupt\n"); + atomic_inc(&ab8500->transfer_ongoing); + for (i = 0; i < ab8500->mask_size; i++) { int regoffset = ab8500->irq_reg_offset[i]; int status; @@ -355,9 +369,10 @@ static irqreturn_t ab8500_irq(int irq, void *dev) handle_nested_irq(ab8500->irq_base + line); value &= ~(1 << bit); + } while (value); } - + atomic_dec(&ab8500->transfer_ongoing); return IRQ_HANDLED; } @@ -411,6 +426,14 @@ static void ab8500_irq_remove(struct ab8500 *ab8500) } } +int ab8500_suspend(struct ab8500 *ab8500) +{ + if (atomic_read(&ab8500->transfer_ongoing)) + return -EINVAL; + else + return 0; +} + /* AB8500 GPIO Resources */ static struct resource __devinitdata ab8500_gpio_resources[] = { { @@ -1059,6 +1082,7 @@ int __devinit ab8500_init(struct ab8500 *ab8500, enum ab8500_version version) mutex_init(&ab8500->lock); mutex_init(&ab8500->irq_lock); + atomic_set(&ab8500->transfer_ongoing, 0); if (version != AB8500_VERSION_UNDEFINED) ab8500->version = version; diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index d798f5b6a55f..91dd3ef63e99 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -7,6 +7,7 @@ #ifndef MFD_AB8500_H #define MFD_AB8500_H +#include #include struct device; @@ -224,6 +225,7 @@ enum ab8500_version { * @dev: parent device * @lock: read/write operations lock * @irq_lock: genirq bus lock + * @transfer_ongoing: 0 if no transfer ongoing * @irq: irq line * @version: chip version id (e.g. ab8500 or ab9540) * @chip_id: chip revision id @@ -242,7 +244,7 @@ struct ab8500 { struct device *dev; struct mutex lock; struct mutex irq_lock; - + atomic_t transfer_ongoing; int irq_base; int irq; enum ab8500_version version; @@ -288,6 +290,8 @@ extern int __devinit ab8500_init(struct ab8500 *ab8500, enum ab8500_version version); extern int __devexit ab8500_exit(struct ab8500 *ab8500); +extern int ab8500_suspend(struct ab8500 *ab8500); + static inline int is_ab8500(struct ab8500 *ab) { return ab->version == AB8500_VERSION_AB8500; -- cgit v1.2.3 From 3a1556e8662cc425c433b463fcdae138908ca467 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 Apr 2012 13:48:18 -0400 Subject: NFSv2/v3: Simulate the change attribute Use the ctime to simulate a change attribute for NFSv2 and NFSv3. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/internal.h | 12 ++++++++++++ fs/nfs/nfs2xdr.c | 2 ++ fs/nfs/nfs3xdr.c | 3 +++ include/linux/nfs_xdr.h | 6 +++--- 5 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 60f7e4ec842c..a8f8de618d73 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -880,7 +880,7 @@ static int nfs_init_server(struct nfs_server *server, server->options = data->options; server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| - NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 0fd1efaf1cff..1855e8fea423 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -493,3 +493,15 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) PAGE_SIZE - 1) >> PAGE_SHIFT; } +/* + * Convert a struct timespec into a 64-bit change attribute + * + * This does approximately the same thing as timespec_to_ns(), + * but for calculation efficiency, we multiply the seconds by + * 1024*1024*1024. + */ +static inline +u64 nfs_timespec_to_change_attr(const struct timespec *ts) +{ + return ((u64)ts->tv_sec << 30) + ts->tv_nsec; +} diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 1f56000fabbd..c99008e9d8a4 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -313,6 +313,8 @@ static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr) p = xdr_decode_time(p, &fattr->atime); p = xdr_decode_time(p, &fattr->mtime); xdr_decode_time(p, &fattr->ctime); + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); + return 0; out_overflow: print_overflow_msg(__func__, xdr); diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 01e53e94f53d..ee284c2b2757 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -675,6 +675,7 @@ static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr) p = xdr_decode_nfstime3(p, &fattr->atime); p = xdr_decode_nfstime3(p, &fattr->mtime); xdr_decode_nfstime3(p, &fattr->ctime); + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); fattr->valid |= NFS_ATTR_FATTR_V3; return 0; @@ -725,12 +726,14 @@ static int decode_wcc_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) goto out_overflow; fattr->valid |= NFS_ATTR_FATTR_PRESIZE + | NFS_ATTR_FATTR_PRECHANGE | NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_PRECTIME; p = xdr_decode_size3(p, &fattr->pre_size); p = xdr_decode_nfstime3(p, &fattr->pre_mtime); xdr_decode_nfstime3(p, &fattr->pre_ctime); + fattr->pre_change_attr = nfs_timespec_to_change_attr(&fattr->pre_ctime); return 0; out_overflow: diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6deb8f097c42..bc3680885428 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -106,14 +106,14 @@ struct nfs_fattr { | NFS_ATTR_FATTR_FILEID \ | NFS_ATTR_FATTR_ATIME \ | NFS_ATTR_FATTR_MTIME \ - | NFS_ATTR_FATTR_CTIME) + | NFS_ATTR_FATTR_CTIME \ + | NFS_ATTR_FATTR_CHANGE) #define NFS_ATTR_FATTR_V2 (NFS_ATTR_FATTR \ | NFS_ATTR_FATTR_BLOCKS_USED) #define NFS_ATTR_FATTR_V3 (NFS_ATTR_FATTR \ | NFS_ATTR_FATTR_SPACE_USED) #define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \ - | NFS_ATTR_FATTR_SPACE_USED \ - | NFS_ATTR_FATTR_CHANGE) + | NFS_ATTR_FATTR_SPACE_USED) /* * Info on the file system -- cgit v1.2.3 From 90ff0c548d1220d31f80e498b587393895705e6c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 Apr 2012 13:48:18 -0400 Subject: NFSv4: Simplify the NFSv4 OPEN compound Get rid of the post-op GETATTR on the directory in order to reduce the amount of processing done on the server. The cost is that if we later need to stat() the directory, then we know that the ctime and mtime are likely to be invalid. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 11 +---------- fs/nfs/nfs4xdr.c | 18 +----------------- include/linux/nfs_xdr.h | 2 -- 3 files changed, 2 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2e0fbff37d1f..f01c3d1b54b7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -788,7 +788,6 @@ struct nfs4_opendata { struct nfs4_string owner_name; struct nfs4_string group_name; struct nfs_fattr f_attr; - struct nfs_fattr dir_attr; struct dentry *dir; struct dentry *dentry; struct nfs4_state_owner *owner; @@ -804,12 +803,10 @@ struct nfs4_opendata { static void nfs4_init_opendata_res(struct nfs4_opendata *p) { p->o_res.f_attr = &p->f_attr; - p->o_res.dir_attr = &p->dir_attr; p->o_res.seqid = p->o_arg.seqid; p->c_res.seqid = p->c_arg.seqid; p->o_res.server = p->o_arg.server; nfs_fattr_init(&p->f_attr); - nfs_fattr_init(&p->dir_attr); nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name); } @@ -843,7 +840,6 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.name = &dentry->d_name; p->o_arg.server = server; p->o_arg.bitmask = server->attr_bitmask; - p->o_arg.dir_bitmask = server->cache_consistency_bitmask; p->o_arg.claim = NFS4_OPEN_CLAIM_NULL; if (attrs != NULL && attrs->ia_valid != 0) { __be32 verf[2]; @@ -1611,8 +1607,6 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data) nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr); - nfs_refresh_inode(dir, o_res->dir_attr); - if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { status = _nfs4_proc_open_confirm(data); if (status != 0) @@ -1645,11 +1639,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) nfs_fattr_map_and_free_names(server, &data->f_attr); - if (o_arg->open_flags & O_CREAT) { + if (o_arg->open_flags & O_CREAT) update_changeattr(dir, &o_res->cinfo); - nfs_post_op_update_inode(dir, o_res->dir_attr); - } else - nfs_refresh_inode(dir, o_res->dir_attr); if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0) server->caps &= ~NFS_CAP_POSIX_LOCK; if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ac7a3b014d99..6e878dcc0d2d 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -431,20 +431,14 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_open_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_savefh_maxsz + \ encode_open_maxsz + \ encode_getfh_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ encode_getattr_maxsz) #define NFS4_dec_open_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_savefh_maxsz + \ decode_open_maxsz + \ decode_getfh_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_open_confirm_sz \ (compound_encode_hdr_maxsz + \ @@ -2191,12 +2185,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); - encode_savefh(xdr, &hdr); encode_open(xdr, args, &hdr); encode_getfh(xdr, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->dir_bitmask, &hdr); encode_nops(&hdr); } @@ -6073,9 +6064,6 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_putfh(xdr); - if (status) - goto out; - status = decode_savefh(xdr); if (status) goto out; status = decode_open(xdr, res); @@ -6083,11 +6071,7 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, goto out; if (decode_getfh(xdr, &res->fh) != 0) goto out; - if (decode_getfattr(xdr, res->f_attr, res->server) != 0) - goto out; - if (decode_restorefh(xdr) != 0) - goto out; - decode_getfattr(xdr, res->dir_attr, res->server); + decode_getfattr(xdr, res->f_attr, res->server); out: return status; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bc3680885428..92a929fc97c8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -338,7 +338,6 @@ struct nfs_openargs { const struct qstr * name; const struct nfs_server *server; /* Needed for ID mapping */ const u32 * bitmask; - const u32 * dir_bitmask; __u32 claim; struct nfs4_sequence_args seq_args; }; @@ -349,7 +348,6 @@ struct nfs_openres { struct nfs4_change_info cinfo; __u32 rflags; struct nfs_fattr * f_attr; - struct nfs_fattr * dir_attr; struct nfs_seqid * seqid; const struct nfs_server *server; fmode_t delegation_type; -- cgit v1.2.3 From 7c317fcfbae773e493ecee1c53738db774b1d0ca Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 Apr 2012 13:48:18 -0400 Subject: NFSv4: Simplify the NFSv4 CREATE compound Get rid of the post-op GETATTR on the directory in order to reduce the amount of processing done on the server. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 4 ---- fs/nfs/nfs4xdr.c | 19 +------------------ include/linux/nfs_xdr.h | 1 - 3 files changed, 1 insertion(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f01c3d1b54b7..619bc1eb157b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2994,7 +2994,6 @@ struct nfs4_createdata { struct nfs4_create_res res; struct nfs_fh fh; struct nfs_fattr fattr; - struct nfs_fattr dir_fattr; }; static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, @@ -3018,9 +3017,7 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, data->res.server = server; data->res.fh = &data->fh; data->res.fattr = &data->fattr; - data->res.dir_fattr = &data->dir_fattr; nfs_fattr_init(data->res.fattr); - nfs_fattr_init(data->res.dir_fattr); } return data; } @@ -3031,7 +3028,6 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ &data->arg.seq_args, &data->res.seq_res, 1); if (status == 0) { update_changeattr(dir, &data->res.dir_cinfo); - nfs_post_op_update_inode(dir, data->res.dir_fattr); status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); } return status; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 6e878dcc0d2d..1a70097a8dc7 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -647,20 +647,14 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_create_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_savefh_maxsz + \ encode_create_maxsz + \ encode_getfh_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ encode_getattr_maxsz) #define NFS4_dec_create_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_savefh_maxsz + \ decode_create_maxsz + \ decode_getfh_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_pathconf_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ @@ -2119,12 +2113,9 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->dir_fh, &hdr); - encode_savefh(xdr, &hdr); encode_create(xdr, args, &hdr); encode_getfh(xdr, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -5893,9 +5884,6 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_putfh(xdr); - if (status) - goto out; - status = decode_savefh(xdr); if (status) goto out; status = decode_create(xdr, &res->dir_cinfo); @@ -5904,12 +5892,7 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_getfh(xdr, res->fh); if (status) goto out; - if (decode_getfattr(xdr, res->fattr, res->server)) - goto out; - status = decode_restorefh(xdr); - if (status) - goto out; - decode_getfattr(xdr, res->dir_fattr, res->server); + decode_getfattr(xdr, res->fattr, res->server); out: return status; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 92a929fc97c8..696a17e047be 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -855,7 +855,6 @@ struct nfs4_create_res { struct nfs_fh * fh; struct nfs_fattr * fattr; struct nfs4_change_info dir_cinfo; - struct nfs_fattr * dir_fattr; struct nfs4_sequence_res seq_res; }; -- cgit v1.2.3 From 778d28172f710184855bcfeadcdd6b46997c4de2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 Apr 2012 13:48:19 -0400 Subject: NFSv4: Simplify the NFSv4 REMOVE, LINK and RENAME compounds Get rid of the post-op GETATTR on the directory in order to reduce the amount of processing done on the server. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 34 +++------------------------------- fs/nfs/nfs4xdr.c | 37 ++++--------------------------------- include/linux/nfs_xdr.h | 2 -- 3 files changed, 7 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 619bc1eb157b..c746b0cab499 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2775,7 +2775,6 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) .fh = NFS_FH(dir), .name.len = name->len, .name.name = name->name, - .bitmask = server->attr_bitmask, }; struct nfs_removeres res = { .server = server, @@ -2785,19 +2784,11 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) .rpc_argp = &args, .rpc_resp = &res, }; - int status = -ENOMEM; - - res.dir_attr = nfs_alloc_fattr(); - if (res.dir_attr == NULL) - goto out; + int status; status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); - if (status == 0) { + if (status == 0) update_changeattr(dir, &res.cinfo); - nfs_post_op_update_inode(dir, res.dir_attr); - } - nfs_free_fattr(res.dir_attr); -out: return status; } @@ -2819,7 +2810,6 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) struct nfs_removeargs *args = msg->rpc_argp; struct nfs_removeres *res = msg->rpc_resp; - args->bitmask = server->cache_consistency_bitmask; res->server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE]; nfs41_init_sequence(&args->seq_args, &res->seq_res, 1); @@ -2844,7 +2834,6 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir) if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN) return 0; update_changeattr(dir, &res->cinfo); - nfs_post_op_update_inode(dir, res->dir_attr); return 1; } @@ -2855,7 +2844,6 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir) struct nfs_renameres *res = msg->rpc_resp; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME]; - arg->bitmask = server->attr_bitmask; res->server = server; nfs41_init_sequence(&arg->seq_args, &res->seq_res, 1); } @@ -2881,9 +2869,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, return 0; update_changeattr(old_dir, &res->old_cinfo); - nfs_post_op_update_inode(old_dir, res->old_fattr); update_changeattr(new_dir, &res->new_cinfo); - nfs_post_op_update_inode(new_dir, res->new_fattr); return 1; } @@ -2896,7 +2882,6 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, .new_dir = NFS_FH(new_dir), .old_name = old_name, .new_name = new_name, - .bitmask = server->attr_bitmask, }; struct nfs_renameres res = { .server = server, @@ -2908,21 +2893,11 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, }; int status = -ENOMEM; - res.old_fattr = nfs_alloc_fattr(); - res.new_fattr = nfs_alloc_fattr(); - if (res.old_fattr == NULL || res.new_fattr == NULL) - goto out; - status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { update_changeattr(old_dir, &res.old_cinfo); - nfs_post_op_update_inode(old_dir, res.old_fattr); update_changeattr(new_dir, &res.new_cinfo); - nfs_post_op_update_inode(new_dir, res.new_fattr); } -out: - nfs_free_fattr(res.new_fattr); - nfs_free_fattr(res.old_fattr); return status; } @@ -2960,18 +2935,15 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr * int status = -ENOMEM; res.fattr = nfs_alloc_fattr(); - res.dir_attr = nfs_alloc_fattr(); - if (res.fattr == NULL || res.dir_attr == NULL) + if (res.fattr == NULL) goto out; status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { update_changeattr(dir, &res.cinfo); - nfs_post_op_update_inode(dir, res.dir_attr); nfs_post_op_update_inode(inode, res.fattr); } out: - nfs_free_fattr(res.dir_attr); nfs_free_fattr(res.fattr); return status; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1a70097a8dc7..49483f19c5d3 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -589,38 +589,29 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_remove_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_remove_maxsz + \ - encode_getattr_maxsz) + encode_remove_maxsz) #define NFS4_dec_remove_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_remove_maxsz + \ - decode_getattr_maxsz) + decode_remove_maxsz) #define NFS4_enc_rename_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_savefh_maxsz + \ encode_putfh_maxsz + \ - encode_rename_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ - encode_getattr_maxsz) + encode_rename_maxsz) #define NFS4_dec_rename_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_savefh_maxsz + \ decode_putfh_maxsz + \ - decode_rename_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ - decode_getattr_maxsz) + decode_rename_maxsz) #define NFS4_enc_link_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_savefh_maxsz + \ encode_putfh_maxsz + \ encode_link_maxsz + \ - encode_getattr_maxsz + \ encode_restorefh_maxsz + \ encode_getattr_maxsz) #define NFS4_dec_link_sz (compound_decode_hdr_maxsz + \ @@ -629,7 +620,6 @@ static int nfs4_stat_to_errno(int); decode_savefh_maxsz + \ decode_putfh_maxsz + \ decode_link_maxsz + \ - decode_getattr_maxsz + \ decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_symlink_sz (compound_encode_hdr_maxsz + \ @@ -2052,7 +2042,6 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); encode_remove(xdr, &args->name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2072,9 +2061,6 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, encode_savefh(xdr, &hdr); encode_putfh(xdr, args->new_dir, &hdr); encode_rename(xdr, args->old_name, args->new_name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2094,7 +2080,6 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, encode_savefh(xdr, &hdr); encode_putfh(xdr, args->dir_fh, &hdr); encode_link(xdr, args->name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_restorefh(xdr, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); @@ -5782,9 +5767,6 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_remove(xdr, &res->cinfo); - if (status) - goto out; - decode_getfattr(xdr, res->dir_attr, res->server); out: return status; } @@ -5814,15 +5796,6 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_rename(xdr, &res->old_cinfo, &res->new_cinfo); - if (status) - goto out; - /* Current FH is target directory */ - if (decode_getfattr(xdr, res->new_fattr, res->server)) - goto out; - status = decode_restorefh(xdr); - if (status) - goto out; - decode_getfattr(xdr, res->old_fattr, res->server); out: return status; } @@ -5858,8 +5831,6 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, * Note order: OP_LINK leaves the directory as the current * filehandle. */ - if (decode_getfattr(xdr, res->dir_attr, res->server)) - goto out; status = decode_restorefh(xdr); if (status) goto out; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 696a17e047be..2e53a3f1d2ff 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -540,7 +540,6 @@ struct nfs_commitres { struct nfs_removeargs { const struct nfs_fh *fh; struct qstr name; - const u32 * bitmask; struct nfs4_sequence_args seq_args; }; @@ -559,7 +558,6 @@ struct nfs_renameargs { const struct nfs_fh *new_dir; const struct qstr *old_name; const struct qstr *new_name; - const u32 *bitmask; struct nfs4_sequence_args seq_args; }; -- cgit v1.2.3 From d69ee9b85541a69a1092f5da675bd23256dc62af Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 1 May 2012 17:37:59 -0400 Subject: NFS: Adapt readdirplus to application usage patterns While the use of READDIRPLUS is significantly more efficient than READDIR followed by many LOOKUP calls, it is still less efficient than just READDIR if the attributes are not required. This patch tracks when lookups are attempted on the directory, and uses that information to selectively disable READDIRPLUS on that directory. The first 'readdir' call is always served using READDIRPLUS. Subsequent calls only use READDIRPLUS if there was a successful lookup or revalidation on a child in the mean time. Credit for the original idea should go to Neil Brown. See: http://www.spinics.net/lists/linux-nfs/msg19996.html However, the implementation in this patch differs from Neil's in that it focuses on tracking lookups rather than calls to stat(). Signed-off-by: Trond Myklebust Cc: Neil Brown --- fs/nfs/dir.c | 33 +++++++++++++++++++++++++++++++-- fs/nfs/inode.c | 2 -- include/linux/nfs_fs.h | 5 ----- 3 files changed, 31 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 82b42e2ea65c..d0884c0d9464 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -474,6 +474,29 @@ different: return 0; } +static +bool nfs_use_readdirplus(struct inode *dir, struct file *filp) +{ + if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS)) + return false; + if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags)) + return true; + if (filp->f_pos == 0) + return true; + return false; +} + +/* + * This function is called by the lookup code to request the use of + * readdirplus to accelerate any future lookups in the same + * directory. + */ +static +void nfs_advise_use_readdirplus(struct inode *dir) +{ + set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags); +} + static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) { @@ -874,7 +897,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) desc->file = filp; desc->dir_cookie = &dir_ctx->dir_cookie; desc->decode = NFS_PROTO(inode)->decode_dirent; - desc->plus = NFS_USE_READDIRPLUS(inode); + desc->plus = nfs_use_readdirplus(inode, filp) ? 1 : 0; nfs_block_sillyrename(dentry); res = nfs_revalidate_mapping(inode, filp->f_mapping); @@ -1114,7 +1137,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) if (!inode) { if (nfs_neg_need_reval(dir, dentry, nd)) goto out_bad; - goto out_valid; + goto out_valid_noent; } if (is_bad_inode(inode)) { @@ -1156,6 +1179,9 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) out_set_verifier: nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); out_valid: + /* Success: notify readdir to use READDIRPLUS */ + nfs_advise_use_readdirplus(dir); + out_valid_noent: dput(parent); dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is valid\n", __func__, dentry->d_parent->d_name.name, @@ -1311,6 +1337,9 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru if (IS_ERR(res)) goto out_unblock_sillyrename; + /* Success: notify readdir to use READDIRPLUS */ + nfs_advise_use_readdirplus(dir); + no_entry: res = d_materialise_unique(dentry, inode); if (res != NULL) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 0d53113207e5..9f17cd19e710 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -298,8 +298,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; - if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)) - set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8a88c16662c5..6cc7dbaf0695 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -314,11 +314,6 @@ static inline int nfs_server_capable(struct inode *inode, int cap) return NFS_SERVER(inode)->caps & cap; } -static inline int NFS_USE_READDIRPLUS(struct inode *inode) -{ - return test_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); -} - static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf) { dentry->d_time = verf; -- cgit v1.2.3 From b7b142d9fc056e98e6fdef82dca3e87067517340 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 7 May 2012 10:03:21 +0100 Subject: mfd: Convert wm8350 physical I/O to regmap API The driver still uses a custom cache implementation but the underlying physical I/O is now done using the regmap API, saving some code and avoiding allocating enormous scratch arrays on the stack. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm8350-core.c | 31 ++++++++---------------- drivers/mfd/wm8350-i2c.c | 53 ++++++++++++----------------------------- include/linux/mfd/wm8350/core.h | 9 ++----- 3 files changed, 27 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c index dd1caaac55e4..8a9b11ca076a 100644 --- a/drivers/mfd/wm8350-core.c +++ b/drivers/mfd/wm8350-core.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -74,7 +75,7 @@ static int wm8350_phys_read(struct wm8350 *wm8350, u8 reg, int num_regs, int bytes = num_regs * 2; dev_dbg(wm8350->dev, "volatile read\n"); - ret = wm8350->read_dev(wm8350, reg, bytes, (char *)dest); + ret = regmap_raw_read(wm8350->regmap, reg, dest, bytes); for (i = reg; i < reg + num_regs; i++) { /* Cache is CPU endian */ @@ -96,9 +97,6 @@ static int wm8350_read(struct wm8350 *wm8350, u8 reg, int num_regs, u16 *dest) int ret = 0; int bytes = num_regs * 2; - if (wm8350->read_dev == NULL) - return -ENODEV; - if ((reg + num_regs - 1) > WM8350_MAX_REGISTER) { dev_err(wm8350->dev, "invalid reg %x\n", reg + num_regs - 1); @@ -149,9 +147,6 @@ static int wm8350_write(struct wm8350 *wm8350, u8 reg, int num_regs, u16 *src) int end = reg + num_regs; int bytes = num_regs * 2; - if (wm8350->write_dev == NULL) - return -ENODEV; - if ((reg + num_regs - 1) > WM8350_MAX_REGISTER) { dev_err(wm8350->dev, "invalid reg %x\n", reg + num_regs - 1); @@ -182,7 +177,7 @@ static int wm8350_write(struct wm8350 *wm8350, u8 reg, int num_regs, u16 *src) } /* Actually write it out */ - return wm8350->write_dev(wm8350, reg, bytes, (char *)src); + return regmap_raw_write(wm8350->regmap, reg, src, bytes); } /* @@ -515,9 +510,8 @@ static int wm8350_create_cache(struct wm8350 *wm8350, int type, int mode) * a PMIC so the device many not be in a virgin state and we * can't rely on the silicon values. */ - ret = wm8350->read_dev(wm8350, 0, - sizeof(u16) * (WM8350_MAX_REGISTER + 1), - wm8350->reg_cache); + ret = regmap_raw_read(wm8350->regmap, 0, wm8350->reg_cache, + sizeof(u16) * (WM8350_MAX_REGISTER + 1)); if (ret < 0) { dev_err(wm8350->dev, "failed to read initial cache values\n"); @@ -570,35 +564,30 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq, struct wm8350_platform_data *pdata) { int ret; - u16 id1, id2, mask_rev; - u16 cust_id, mode, chip_rev; + unsigned int id1, id2, mask_rev; + unsigned int cust_id, mode, chip_rev; dev_set_drvdata(wm8350->dev, wm8350); /* get WM8350 revision and config mode */ - ret = wm8350->read_dev(wm8350, WM8350_RESET_ID, sizeof(id1), &id1); + ret = regmap_read(wm8350->regmap, WM8350_RESET_ID, &id1); if (ret != 0) { dev_err(wm8350->dev, "Failed to read ID: %d\n", ret); goto err; } - ret = wm8350->read_dev(wm8350, WM8350_ID, sizeof(id2), &id2); + ret = regmap_read(wm8350->regmap, WM8350_ID, &id2); if (ret != 0) { dev_err(wm8350->dev, "Failed to read ID: %d\n", ret); goto err; } - ret = wm8350->read_dev(wm8350, WM8350_REVISION, sizeof(mask_rev), - &mask_rev); + ret = regmap_read(wm8350->regmap, WM8350_REVISION, &mask_rev); if (ret != 0) { dev_err(wm8350->dev, "Failed to read revision: %d\n", ret); goto err; } - id1 = be16_to_cpu(id1); - id2 = be16_to_cpu(id2); - mask_rev = be16_to_cpu(mask_rev); - if (id1 != 0x6143) { dev_err(wm8350->dev, "Device with ID %x is not a WM8350\n", id1); diff --git a/drivers/mfd/wm8350-i2c.c b/drivers/mfd/wm8350-i2c.c index d955faaf27c4..271589f8e8e3 100644 --- a/drivers/mfd/wm8350-i2c.c +++ b/drivers/mfd/wm8350-i2c.c @@ -15,47 +15,18 @@ #include #include +#include #include #include #include #include +#include #include -static int wm8350_i2c_read_device(struct wm8350 *wm8350, char reg, - int bytes, void *dest) -{ - int ret; - - ret = i2c_master_send(wm8350->i2c_client, ®, 1); - if (ret < 0) - return ret; - ret = i2c_master_recv(wm8350->i2c_client, dest, bytes); - if (ret < 0) - return ret; - if (ret != bytes) - return -EIO; - return 0; -} - -static int wm8350_i2c_write_device(struct wm8350 *wm8350, char reg, - int bytes, void *src) -{ - /* we add 1 byte for device register */ - u8 msg[(WM8350_MAX_REGISTER << 1) + 1]; - int ret; - - if (bytes > ((WM8350_MAX_REGISTER << 1) + 1)) - return -EINVAL; - - msg[0] = reg; - memcpy(&msg[1], src, bytes); - ret = i2c_master_send(wm8350->i2c_client, msg, bytes + 1); - if (ret < 0) - return ret; - if (ret != bytes + 1) - return -EIO; - return 0; -} +static const struct regmap_config wm8350_regmap = { + .reg_bits = 8, + .val_bits = 16, +}; static int wm8350_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) @@ -67,11 +38,16 @@ static int wm8350_i2c_probe(struct i2c_client *i2c, if (wm8350 == NULL) return -ENOMEM; + wm8350->regmap = devm_regmap_init_i2c(i2c, &wm8350_regmap); + if (IS_ERR(wm8350->regmap)) { + ret = PTR_ERR(wm8350->regmap); + dev_err(&i2c->dev, "Failed to allocate register map: %d\n", + ret); + return ret; + } + i2c_set_clientdata(i2c, wm8350); wm8350->dev = &i2c->dev; - wm8350->i2c_client = i2c; - wm8350->read_dev = wm8350_i2c_read_device; - wm8350->write_dev = wm8350_i2c_write_device; ret = wm8350_device_init(wm8350, i2c->irq, i2c->dev.platform_data); if (ret < 0) @@ -80,6 +56,7 @@ static int wm8350_i2c_probe(struct i2c_client *i2c, return ret; err: + regmap_exit(wm8350->regmap); return ret; } diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h index 98fcc977e82b..9192b6404a73 100644 --- a/include/linux/mfd/wm8350/core.h +++ b/include/linux/mfd/wm8350/core.h @@ -602,6 +602,7 @@ extern const u16 wm8352_mode2_defaults[]; extern const u16 wm8352_mode3_defaults[]; struct wm8350; +struct regmap; struct wm8350_hwmon { struct platform_device *pdev; @@ -612,13 +613,7 @@ struct wm8350 { struct device *dev; /* device IO */ - union { - struct i2c_client *i2c_client; - struct spi_device *spi_device; - }; - int (*read_dev)(struct wm8350 *wm8350, char reg, int size, void *dest); - int (*write_dev)(struct wm8350 *wm8350, char reg, int size, - void *src); + struct regmap *regmap; u16 *reg_cache; struct mutex auxadc_mutex; -- cgit v1.2.3 From cc7a727941193e3e59be2e9f6522eb78bc7ee909 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 7 May 2012 10:03:22 +0100 Subject: mfd: Read CUST_ID from the wm8994 device Read CUST_ID from the device and log it for diagnostics. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm8994-core.c | 7 ++++--- include/linux/mfd/wm8994/core.h | 1 + include/linux/mfd/wm8994/registers.h | 3 +++ 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c index 9d7ca1e978fa..60e617549edd 100644 --- a/drivers/mfd/wm8994-core.c +++ b/drivers/mfd/wm8994-core.c @@ -500,7 +500,8 @@ static __devinit int wm8994_device_init(struct wm8994 *wm8994, int irq) ret); goto err_enable; } - wm8994->revision = ret; + wm8994->revision = ret & WM8994_CHIP_REV_MASK; + wm8994->cust_id = (ret & WM8994_CUST_ID_MASK) >> WM8994_CUST_ID_SHIFT; switch (wm8994->type) { case WM8994: @@ -553,8 +554,8 @@ static __devinit int wm8994_device_init(struct wm8994 *wm8994, int irq) break; } - dev_info(wm8994->dev, "%s revision %c\n", devname, - 'A' + wm8994->revision); + dev_info(wm8994->dev, "%s revision %c CUST_ID %02x\n", devname, + 'A' + wm8994->revision, wm8994->cust_id); switch (wm8994->type) { case WM1811: diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h index 9eff2a351ec5..d41bc7b8a86a 100644 --- a/include/linux/mfd/wm8994/core.h +++ b/include/linux/mfd/wm8994/core.h @@ -57,6 +57,7 @@ struct wm8994 { enum wm8994_type type; int revision; + int cust_id; struct device *dev; struct regmap *regmap; diff --git a/include/linux/mfd/wm8994/registers.h b/include/linux/mfd/wm8994/registers.h index 86e6a032a078..053548961c15 100644 --- a/include/linux/mfd/wm8994/registers.h +++ b/include/linux/mfd/wm8994/registers.h @@ -2212,6 +2212,9 @@ /* * R256 (0x100) - Chip Revision */ +#define WM8994_CUST_ID_MASK 0xFF00 /* CUST_ID - [15:8] */ +#define WM8994_CUST_ID_SHIFT 8 /* CUST_ID - [15:8] */ +#define WM8994_CUST_ID_WIDTH 8 /* CUST_ID - [15:8] */ #define WM8994_CHIP_REV_MASK 0x000F /* CHIP_REV - [3:0] */ #define WM8994_CHIP_REV_SHIFT 0 /* CHIP_REV - [3:0] */ #define WM8994_CHIP_REV_WIDTH 4 /* CHIP_REV - [3:0] */ -- cgit v1.2.3 From 35bdd29095ad614c5fb4a934bfd4f57a94dfd395 Mon Sep 17 00:00:00 2001 From: Alessandro Rubini Date: Thu, 12 Apr 2012 10:48:44 +0200 Subject: mfd: Add driver for STA2X11 MFD block This also introduces to export a function that is in the base sta2x11 support patches. The header will increase with other prototypes and constants over time. Signed-off-by: Alessandro Rubini Acked-by: Giancarlo Asnaghi Cc: Alan Cox Signed-off-by: Samuel Ortiz --- arch/x86/include/asm/sta2x11.h | 12 ++ drivers/mfd/Kconfig | 5 + drivers/mfd/Makefile | 1 + drivers/mfd/sta2x11-mfd.c | 467 ++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/sta2x11-mfd.h | 324 ++++++++++++++++++++++++++++ 5 files changed, 809 insertions(+) create mode 100644 arch/x86/include/asm/sta2x11.h create mode 100644 drivers/mfd/sta2x11-mfd.c create mode 100644 include/linux/mfd/sta2x11-mfd.h (limited to 'include/linux') diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h new file mode 100644 index 000000000000..e9d32df89ccc --- /dev/null +++ b/arch/x86/include/asm/sta2x11.h @@ -0,0 +1,12 @@ +/* + * Header file for STMicroelectronics ConneXt (STA2X11) IOHub + */ +#ifndef __ASM_STA2X11_H +#define __ASM_STA2X11_H + +#include + +/* This needs to be called from the MFD to configure its sub-devices */ +struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev); + +#endif /* __ASM_STA2X11_H */ diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index ef86a741b7e2..48eed22c65a5 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -906,6 +906,11 @@ config MFD_RC5T583 Additional drivers must be enabled in order to use the different functionality of the device. +config MFD_STA2X11 + bool "STA2X11 multi function device support" + depends on STA2X11 + select MFD_CORE + config MFD_ANATOP bool "Support for Freescale i.MX on-chip ANATOP controller" depends on SOC_IMX6Q diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 5dd6be7aa350..0dc55cbefa09 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_MFD_DAVINCI_VOICECODEC) += davinci_voicecodec.o obj-$(CONFIG_MFD_DM355EVM_MSP) += dm355evm_msp.o obj-$(CONFIG_MFD_TI_SSP) += ti-ssp.o +obj-$(CONFIG_MFD_STA2X11) += sta2x11-mfd.o obj-$(CONFIG_MFD_STMPE) += stmpe.o obj-$(CONFIG_STMPE_I2C) += stmpe-i2c.o obj-$(CONFIG_STMPE_SPI) += stmpe-spi.o diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c new file mode 100644 index 000000000000..d31fed07aefb --- /dev/null +++ b/drivers/mfd/sta2x11-mfd.c @@ -0,0 +1,467 @@ +/* + * Copyright (c) 2009-2011 Wind River Systems, Inc. + * Copyright (c) 2011 ST Microelectronics (Alessandro Rubini) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* This describes STA2X11 MFD chip for us, we may have several */ +struct sta2x11_mfd { + struct sta2x11_instance *instance; + spinlock_t lock; + struct list_head list; + void __iomem *sctl_regs; + void __iomem *apbreg_regs; +}; + +static LIST_HEAD(sta2x11_mfd_list); + +/* Three functions to act on the list */ +static struct sta2x11_mfd *sta2x11_mfd_find(struct pci_dev *pdev) +{ + struct sta2x11_instance *instance; + struct sta2x11_mfd *mfd; + + if (!pdev && !list_empty(&sta2x11_mfd_list)) { + pr_warning("%s: Unspecified device, " + "using first instance\n", __func__); + return list_entry(sta2x11_mfd_list.next, + struct sta2x11_mfd, list); + } + + instance = sta2x11_get_instance(pdev); + if (!instance) + return NULL; + list_for_each_entry(mfd, &sta2x11_mfd_list, list) { + if (mfd->instance == instance) + return mfd; + } + return NULL; +} + +static int __devinit sta2x11_mfd_add(struct pci_dev *pdev, gfp_t flags) +{ + struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev); + struct sta2x11_instance *instance; + + if (mfd) + return -EBUSY; + instance = sta2x11_get_instance(pdev); + if (!instance) + return -EINVAL; + mfd = kzalloc(sizeof(*mfd), flags); + if (!mfd) + return -ENOMEM; + INIT_LIST_HEAD(&mfd->list); + spin_lock_init(&mfd->lock); + mfd->instance = instance; + list_add(&mfd->list, &sta2x11_mfd_list); + return 0; +} + +static int __devexit mfd_remove(struct pci_dev *pdev) +{ + struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev); + + if (!mfd) + return -ENODEV; + list_del(&mfd->list); + kfree(mfd); + return 0; +} + +/* These two functions are exported and are not expected to fail */ +u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val) +{ + struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev); + u32 r; + unsigned long flags; + + if (!mfd) { + dev_warn(&pdev->dev, ": can't access sctl regs\n"); + return 0; + } + if (!mfd->sctl_regs) { + dev_warn(&pdev->dev, ": system ctl not initialized\n"); + return 0; + } + spin_lock_irqsave(&mfd->lock, flags); + r = readl(mfd->sctl_regs + reg); + r &= ~mask; + r |= val; + if (mask) + writel(r, mfd->sctl_regs + reg); + spin_unlock_irqrestore(&mfd->lock, flags); + return r; +} +EXPORT_SYMBOL(sta2x11_sctl_mask); + +u32 sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val) +{ + struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev); + u32 r; + unsigned long flags; + + if (!mfd) { + dev_warn(&pdev->dev, ": can't access apb regs\n"); + return 0; + } + if (!mfd->apbreg_regs) { + dev_warn(&pdev->dev, ": apb bridge not initialized\n"); + return 0; + } + spin_lock_irqsave(&mfd->lock, flags); + r = readl(mfd->apbreg_regs + reg); + r &= ~mask; + r |= val; + if (mask) + writel(r, mfd->apbreg_regs + reg); + spin_unlock_irqrestore(&mfd->lock, flags); + return r; +} +EXPORT_SYMBOL(sta2x11_apbreg_mask); + +/* Two debugfs files, for our registers (FIXME: one instance only) */ +#define REG(regname) {.name = #regname, .offset = SCTL_ ## regname} +static struct debugfs_reg32 sta2x11_sctl_regs[] = { + REG(SCCTL), REG(ARMCFG), REG(SCPLLCTL), REG(SCPLLFCTRL), + REG(SCRESFRACT), REG(SCRESCTRL1), REG(SCRESXTRL2), REG(SCPEREN0), + REG(SCPEREN1), REG(SCPEREN2), REG(SCGRST), REG(SCPCIPMCR1), + REG(SCPCIPMCR2), REG(SCPCIPMSR1), REG(SCPCIPMSR2), REG(SCPCIPMSR3), + REG(SCINTREN), REG(SCRISR), REG(SCCLKSTAT0), REG(SCCLKSTAT1), + REG(SCCLKSTAT2), REG(SCRSTSTA), +}; +#undef REG + +static struct debugfs_regset32 sctl_regset = { + .regs = sta2x11_sctl_regs, + .nregs = ARRAY_SIZE(sta2x11_sctl_regs), +}; + +#define REG(regname) {.name = #regname, .offset = regname} +static struct debugfs_reg32 sta2x11_apbreg_regs[] = { + REG(APBREG_BSR), REG(APBREG_PAER), REG(APBREG_PWAC), REG(APBREG_PRAC), + REG(APBREG_PCG), REG(APBREG_PUR), REG(APBREG_EMU_PCG), +}; +#undef REG + +static struct debugfs_regset32 apbreg_regset = { + .regs = sta2x11_apbreg_regs, + .nregs = ARRAY_SIZE(sta2x11_apbreg_regs), +}; + +static struct dentry *sta2x11_sctl_debugfs; +static struct dentry *sta2x11_apbreg_debugfs; + +/* Probe for the two platform devices */ +static int sta2x11_sctl_probe(struct platform_device *dev) +{ + struct pci_dev **pdev; + struct sta2x11_mfd *mfd; + struct resource *res; + + pdev = dev->dev.platform_data; + mfd = sta2x11_mfd_find(*pdev); + if (!mfd) + return -ENODEV; + + res = platform_get_resource(dev, IORESOURCE_MEM, 0); + if (!res) + return -ENOMEM; + + if (!request_mem_region(res->start, resource_size(res), + "sta2x11-sctl")) + return -EBUSY; + + mfd->sctl_regs = ioremap(res->start, resource_size(res)); + if (!mfd->sctl_regs) { + release_mem_region(res->start, resource_size(res)); + return -ENOMEM; + } + sctl_regset.base = mfd->sctl_regs; + sta2x11_sctl_debugfs = debugfs_create_regset32("sta2x11-sctl", + S_IFREG | S_IRUGO, + NULL, &sctl_regset); + return 0; +} + +static int sta2x11_apbreg_probe(struct platform_device *dev) +{ + struct pci_dev **pdev; + struct sta2x11_mfd *mfd; + struct resource *res; + + pdev = dev->dev.platform_data; + dev_dbg(&dev->dev, "%s: pdata is %p\n", __func__, pdev); + dev_dbg(&dev->dev, "%s: *pdata is %p\n", __func__, *pdev); + + mfd = sta2x11_mfd_find(*pdev); + if (!mfd) + return -ENODEV; + + res = platform_get_resource(dev, IORESOURCE_MEM, 0); + if (!res) + return -ENOMEM; + + if (!request_mem_region(res->start, resource_size(res), + "sta2x11-apbreg")) + return -EBUSY; + + mfd->apbreg_regs = ioremap(res->start, resource_size(res)); + if (!mfd->apbreg_regs) { + release_mem_region(res->start, resource_size(res)); + return -ENOMEM; + } + dev_dbg(&dev->dev, "%s: regbase %p\n", __func__, mfd->apbreg_regs); + + apbreg_regset.base = mfd->apbreg_regs; + sta2x11_apbreg_debugfs = debugfs_create_regset32("sta2x11-apbreg", + S_IFREG | S_IRUGO, + NULL, &apbreg_regset); + return 0; +} + +/* The two platform drivers */ +static struct platform_driver sta2x11_sctl_platform_driver = { + .driver = { + .name = "sta2x11-sctl", + .owner = THIS_MODULE, + }, + .probe = sta2x11_sctl_probe, +}; + +static int __init sta2x11_sctl_init(void) +{ + pr_info("%s\n", __func__); + return platform_driver_register(&sta2x11_sctl_platform_driver); +} + +static struct platform_driver sta2x11_platform_driver = { + .driver = { + .name = "sta2x11-apbreg", + .owner = THIS_MODULE, + }, + .probe = sta2x11_apbreg_probe, +}; + +static int __init sta2x11_apbreg_init(void) +{ + pr_info("%s\n", __func__); + return platform_driver_register(&sta2x11_platform_driver); +} + +/* + * What follows is the PCI device that hosts the above two pdevs. + * Each logic block is 4kB and they are all consecutive: we use this info. + */ + +/* Bar 0 */ +enum bar0_cells { + STA2X11_GPIO_0 = 0, + STA2X11_GPIO_1, + STA2X11_GPIO_2, + STA2X11_GPIO_3, + STA2X11_SCTL, + STA2X11_SCR, + STA2X11_TIME, +}; +/* Bar 1 */ +enum bar1_cells { + STA2X11_APBREG = 0, +}; +#define CELL_4K(_name, _cell) { \ + .name = _name, \ + .start = _cell * 4096, .end = _cell * 4096 + 4095, \ + .flags = IORESOURCE_MEM, \ + } + +static const __devinitconst struct resource gpio_resources[] = { + { + .name = "sta2x11_gpio", /* 4 consecutive cells, 1 driver */ + .start = 0, + .end = (4 * 4096) - 1, + .flags = IORESOURCE_MEM, + } +}; +static const __devinitconst struct resource sctl_resources[] = { + CELL_4K("sta2x11-sctl", STA2X11_SCTL), +}; +static const __devinitconst struct resource scr_resources[] = { + CELL_4K("sta2x11-scr", STA2X11_SCR), +}; +static const __devinitconst struct resource time_resources[] = { + CELL_4K("sta2x11-time", STA2X11_TIME), +}; + +static const __devinitconst struct resource apbreg_resources[] = { + CELL_4K("sta2x11-apbreg", STA2X11_APBREG), +}; + +#define DEV(_name, _r) \ + { .name = _name, .num_resources = ARRAY_SIZE(_r), .resources = _r, } + +static __devinitdata struct mfd_cell sta2x11_mfd_bar0[] = { + DEV("sta2x11-gpio", gpio_resources), /* offset 0: we add pdata later */ + DEV("sta2x11-sctl", sctl_resources), + DEV("sta2x11-scr", scr_resources), + DEV("sta2x11-time", time_resources), +}; + +static __devinitdata struct mfd_cell sta2x11_mfd_bar1[] = { + DEV("sta2x11-apbreg", apbreg_resources), +}; + +static int sta2x11_mfd_suspend(struct pci_dev *pdev, pm_message_t state) +{ + pci_save_state(pdev); + pci_disable_device(pdev); + pci_set_power_state(pdev, pci_choose_state(pdev, state)); + + return 0; +} + +static int sta2x11_mfd_resume(struct pci_dev *pdev) +{ + int err; + + pci_set_power_state(pdev, 0); + err = pci_enable_device(pdev); + if (err) + return err; + pci_restore_state(pdev); + + return 0; +} + +static int __devinit sta2x11_mfd_probe(struct pci_dev *pdev, + const struct pci_device_id *pci_id) +{ + int err, i; + struct sta2x11_gpio_pdata *gpio_data; + + dev_info(&pdev->dev, "%s\n", __func__); + + err = pci_enable_device(pdev); + if (err) { + dev_err(&pdev->dev, "Can't enable device.\n"); + return err; + } + + err = pci_enable_msi(pdev); + if (err) + dev_info(&pdev->dev, "Enable msi failed\n"); + + /* Read gpio config data as pci device's platform data */ + gpio_data = dev_get_platdata(&pdev->dev); + if (!gpio_data) + dev_warn(&pdev->dev, "no gpio configuration\n"); + + dev_dbg(&pdev->dev, "%s, gpio_data = %p (%p)\n", __func__, + gpio_data, &gpio_data); + dev_dbg(&pdev->dev, "%s, pdev = %p (%p)\n", __func__, + pdev, &pdev); + + /* platform data is the pci device for all of them */ + for (i = 0; i < ARRAY_SIZE(sta2x11_mfd_bar0); i++) { + sta2x11_mfd_bar0[i].pdata_size = sizeof(pdev); + sta2x11_mfd_bar0[i].platform_data = &pdev; + } + sta2x11_mfd_bar1[0].pdata_size = sizeof(pdev); + sta2x11_mfd_bar1[0].platform_data = &pdev; + + /* Record this pdev before mfd_add_devices: their probe looks for it */ + sta2x11_mfd_add(pdev, GFP_ATOMIC); + + + err = mfd_add_devices(&pdev->dev, -1, + sta2x11_mfd_bar0, + ARRAY_SIZE(sta2x11_mfd_bar0), + &pdev->resource[0], + 0); + if (err) { + dev_err(&pdev->dev, "mfd_add_devices[0] failed: %d\n", err); + goto err_disable; + } + + err = mfd_add_devices(&pdev->dev, -1, + sta2x11_mfd_bar1, + ARRAY_SIZE(sta2x11_mfd_bar1), + &pdev->resource[1], + 0); + if (err) { + dev_err(&pdev->dev, "mfd_add_devices[1] failed: %d\n", err); + goto err_disable; + } + + return 0; + +err_disable: + mfd_remove_devices(&pdev->dev); + pci_disable_device(pdev); + pci_disable_msi(pdev); + return err; +} + +static DEFINE_PCI_DEVICE_TABLE(sta2x11_mfd_tbl) = { + {PCI_DEVICE(PCI_VENDOR_ID_STMICRO, PCI_DEVICE_ID_STMICRO_GPIO)}, + {0,}, +}; + +static struct pci_driver sta2x11_mfd_driver = { + .name = "sta2x11-mfd", + .id_table = sta2x11_mfd_tbl, + .probe = sta2x11_mfd_probe, + .suspend = sta2x11_mfd_suspend, + .resume = sta2x11_mfd_resume, +}; + +static int __init sta2x11_mfd_init(void) +{ + pr_info("%s\n", __func__); + return pci_register_driver(&sta2x11_mfd_driver); +} + +/* + * All of this must be ready before "normal" devices like MMCI appear. + * But MFD (the pci device) can't be too early. The following choice + * prepares platform drivers very early and probe the PCI device later, + * but before other PCI devices. + */ +subsys_initcall(sta2x11_apbreg_init); +subsys_initcall(sta2x11_sctl_init); +rootfs_initcall(sta2x11_mfd_init); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Wind River"); +MODULE_DESCRIPTION("STA2x11 mfd for GPIO, SCTL and APBREG"); +MODULE_DEVICE_TABLE(pci, sta2x11_mfd_tbl); diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h new file mode 100644 index 000000000000..d179227e866f --- /dev/null +++ b/include/linux/mfd/sta2x11-mfd.h @@ -0,0 +1,324 @@ +/* + * Copyright (c) 2009-2011 Wind River Systems, Inc. + * Copyright (c) 2011 ST Microelectronics (Alessandro Rubini) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * The STMicroelectronics ConneXt (STA2X11) chip has several unrelated + * functions in one PCI endpoint functions. This driver simply + * registers the platform devices in this iomemregion and exports a few + * functions to access common registers + */ + +#ifndef __STA2X11_MFD_H +#define __STA2X11_MFD_H +#include +#include + +/* + * The MFD PCI block includes the GPIO peripherals and other register blocks. + * For GPIO, we have 32*4 bits (I use "gsta" for "gpio sta2x11".) + */ +#define GSTA_GPIO_PER_BLOCK 32 +#define GSTA_NR_BLOCKS 4 +#define GSTA_NR_GPIO (GSTA_GPIO_PER_BLOCK * GSTA_NR_BLOCKS) + +/* Pinconfig is set by the board definition: altfunc, pull-up, pull-down */ +struct sta2x11_gpio_pdata { + unsigned pinconfig[GSTA_NR_GPIO]; +}; + +/* Macros below lifted from sh_pfc.h, with minor differences */ +#define PINMUX_TYPE_NONE 0 +#define PINMUX_TYPE_FUNCTION 1 +#define PINMUX_TYPE_OUTPUT_LOW 2 +#define PINMUX_TYPE_OUTPUT_HIGH 3 +#define PINMUX_TYPE_INPUT 4 +#define PINMUX_TYPE_INPUT_PULLUP 5 +#define PINMUX_TYPE_INPUT_PULLDOWN 6 + +/* Give names to GPIO pins, like PXA does, taken from the manual */ +#define STA2X11_GPIO0 0 +#define STA2X11_GPIO1 1 +#define STA2X11_GPIO2 2 +#define STA2X11_GPIO3 3 +#define STA2X11_GPIO4 4 +#define STA2X11_GPIO5 5 +#define STA2X11_GPIO6 6 +#define STA2X11_GPIO7 7 +#define STA2X11_GPIO8_RGBOUT_RED7 8 +#define STA2X11_GPIO9_RGBOUT_RED6 9 +#define STA2X11_GPIO10_RGBOUT_RED5 10 +#define STA2X11_GPIO11_RGBOUT_RED4 11 +#define STA2X11_GPIO12_RGBOUT_RED3 12 +#define STA2X11_GPIO13_RGBOUT_RED2 13 +#define STA2X11_GPIO14_RGBOUT_RED1 14 +#define STA2X11_GPIO15_RGBOUT_RED0 15 +#define STA2X11_GPIO16_RGBOUT_GREEN7 16 +#define STA2X11_GPIO17_RGBOUT_GREEN6 17 +#define STA2X11_GPIO18_RGBOUT_GREEN5 18 +#define STA2X11_GPIO19_RGBOUT_GREEN4 19 +#define STA2X11_GPIO20_RGBOUT_GREEN3 20 +#define STA2X11_GPIO21_RGBOUT_GREEN2 21 +#define STA2X11_GPIO22_RGBOUT_GREEN1 22 +#define STA2X11_GPIO23_RGBOUT_GREEN0 23 +#define STA2X11_GPIO24_RGBOUT_BLUE7 24 +#define STA2X11_GPIO25_RGBOUT_BLUE6 25 +#define STA2X11_GPIO26_RGBOUT_BLUE5 26 +#define STA2X11_GPIO27_RGBOUT_BLUE4 27 +#define STA2X11_GPIO28_RGBOUT_BLUE3 28 +#define STA2X11_GPIO29_RGBOUT_BLUE2 29 +#define STA2X11_GPIO30_RGBOUT_BLUE1 30 +#define STA2X11_GPIO31_RGBOUT_BLUE0 31 +#define STA2X11_GPIO32_RGBOUT_VSYNCH 32 +#define STA2X11_GPIO33_RGBOUT_HSYNCH 33 +#define STA2X11_GPIO34_RGBOUT_DEN 34 +#define STA2X11_GPIO35_ETH_CRS_DV 35 +#define STA2X11_GPIO36_ETH_TXD1 36 +#define STA2X11_GPIO37_ETH_TXD0 37 +#define STA2X11_GPIO38_ETH_TX_EN 38 +#define STA2X11_GPIO39_MDIO 39 +#define STA2X11_GPIO40_ETH_REF_CLK 40 +#define STA2X11_GPIO41_ETH_RXD1 41 +#define STA2X11_GPIO42_ETH_RXD0 42 +#define STA2X11_GPIO43_MDC 43 +#define STA2X11_GPIO44_CAN_TX 44 +#define STA2X11_GPIO45_CAN_RX 45 +#define STA2X11_GPIO46_MLB_DAT 46 +#define STA2X11_GPIO47_MLB_SIG 47 +#define STA2X11_GPIO48_SPI0_CLK 48 +#define STA2X11_GPIO49_SPI0_TXD 49 +#define STA2X11_GPIO50_SPI0_RXD 50 +#define STA2X11_GPIO51_SPI0_FRM 51 +#define STA2X11_GPIO52_SPI1_CLK 52 +#define STA2X11_GPIO53_SPI1_TXD 53 +#define STA2X11_GPIO54_SPI1_RXD 54 +#define STA2X11_GPIO55_SPI1_FRM 55 +#define STA2X11_GPIO56_SPI2_CLK 56 +#define STA2X11_GPIO57_SPI2_TXD 57 +#define STA2X11_GPIO58_SPI2_RXD 58 +#define STA2X11_GPIO59_SPI2_FRM 59 +#define STA2X11_GPIO60_I2C0_SCL 60 +#define STA2X11_GPIO61_I2C0_SDA 61 +#define STA2X11_GPIO62_I2C1_SCL 62 +#define STA2X11_GPIO63_I2C1_SDA 63 +#define STA2X11_GPIO64_I2C2_SCL 64 +#define STA2X11_GPIO65_I2C2_SDA 65 +#define STA2X11_GPIO66_I2C3_SCL 66 +#define STA2X11_GPIO67_I2C3_SDA 67 +#define STA2X11_GPIO68_MSP0_RCK 68 +#define STA2X11_GPIO69_MSP0_RXD 69 +#define STA2X11_GPIO70_MSP0_RFS 70 +#define STA2X11_GPIO71_MSP0_TCK 71 +#define STA2X11_GPIO72_MSP0_TXD 72 +#define STA2X11_GPIO73_MSP0_TFS 73 +#define STA2X11_GPIO74_MSP0_SCK 74 +#define STA2X11_GPIO75_MSP1_CK 75 +#define STA2X11_GPIO76_MSP1_RXD 76 +#define STA2X11_GPIO77_MSP1_FS 77 +#define STA2X11_GPIO78_MSP1_TXD 78 +#define STA2X11_GPIO79_MSP2_CK 79 +#define STA2X11_GPIO80_MSP2_RXD 80 +#define STA2X11_GPIO81_MSP2_FS 81 +#define STA2X11_GPIO82_MSP2_TXD 82 +#define STA2X11_GPIO83_MSP3_CK 83 +#define STA2X11_GPIO84_MSP3_RXD 84 +#define STA2X11_GPIO85_MSP3_FS 85 +#define STA2X11_GPIO86_MSP3_TXD 86 +#define STA2X11_GPIO87_MSP4_CK 87 +#define STA2X11_GPIO88_MSP4_RXD 88 +#define STA2X11_GPIO89_MSP4_FS 89 +#define STA2X11_GPIO90_MSP4_TXD 90 +#define STA2X11_GPIO91_MSP5_CK 91 +#define STA2X11_GPIO92_MSP5_RXD 92 +#define STA2X11_GPIO93_MSP5_FS 93 +#define STA2X11_GPIO94_MSP5_TXD 94 +#define STA2X11_GPIO95_SDIO3_DAT3 95 +#define STA2X11_GPIO96_SDIO3_DAT2 96 +#define STA2X11_GPIO97_SDIO3_DAT1 97 +#define STA2X11_GPIO98_SDIO3_DAT0 98 +#define STA2X11_GPIO99_SDIO3_CLK 99 +#define STA2X11_GPIO100_SDIO3_CMD 100 +#define STA2X11_GPIO101 101 +#define STA2X11_GPIO102 102 +#define STA2X11_GPIO103 103 +#define STA2X11_GPIO104 104 +#define STA2X11_GPIO105_SDIO2_DAT3 105 +#define STA2X11_GPIO106_SDIO2_DAT2 106 +#define STA2X11_GPIO107_SDIO2_DAT1 107 +#define STA2X11_GPIO108_SDIO2_DAT0 108 +#define STA2X11_GPIO109_SDIO2_CLK 109 +#define STA2X11_GPIO110_SDIO2_CMD 110 +#define STA2X11_GPIO111 111 +#define STA2X11_GPIO112 112 +#define STA2X11_GPIO113 113 +#define STA2X11_GPIO114 114 +#define STA2X11_GPIO115_SDIO1_DAT3 115 +#define STA2X11_GPIO116_SDIO1_DAT2 116 +#define STA2X11_GPIO117_SDIO1_DAT1 117 +#define STA2X11_GPIO118_SDIO1_DAT0 118 +#define STA2X11_GPIO119_SDIO1_CLK 119 +#define STA2X11_GPIO120_SDIO1_CMD 120 +#define STA2X11_GPIO121 121 +#define STA2X11_GPIO122 122 +#define STA2X11_GPIO123 123 +#define STA2X11_GPIO124 124 +#define STA2X11_GPIO125_UART2_TXD 125 +#define STA2X11_GPIO126_UART2_RXD 126 +#define STA2X11_GPIO127_UART3_TXD 127 + +/* + * The APB bridge has its own registers, needed by our users as well. + * They are accessed with the following read/mask/write function. + */ +u32 sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val); + +/* CAN and MLB */ +#define APBREG_BSR 0x00 /* Bridge Status Reg */ +#define APBREG_PAER 0x08 /* Peripherals Address Error Reg */ +#define APBREG_PWAC 0x20 /* Peripheral Write Access Control reg */ +#define APBREG_PRAC 0x40 /* Peripheral Read Access Control reg */ +#define APBREG_PCG 0x60 /* Peripheral Clock Gating Reg */ +#define APBREG_PUR 0x80 /* Peripheral Under Reset Reg */ +#define APBREG_EMU_PCG 0xA0 /* Emulator Peripheral Clock Gating Reg */ + +#define APBREG_CAN (1 << 1) +#define APBREG_MLB (1 << 3) + +/* SARAC */ +#define APBREG_BSR_SARAC 0x100 /* Bridge Status Reg */ +#define APBREG_PAER_SARAC 0x108 /* Peripherals Address Error Reg */ +#define APBREG_PWAC_SARAC 0x120 /* Peripheral Write Access Control reg */ +#define APBREG_PRAC_SARAC 0x140 /* Peripheral Read Access Control reg */ +#define APBREG_PCG_SARAC 0x160 /* Peripheral Clock Gating Reg */ +#define APBREG_PUR_SARAC 0x180 /* Peripheral Under Reset Reg */ +#define APBREG_EMU_PCG_SARAC 0x1A0 /* Emulator Peripheral Clock Gating Reg */ + +#define APBREG_SARAC (1 << 2) + +/* + * The system controller has its own registers. Some of these are accessed + * by out users as well, using the following read/mask/write/function + */ +u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val); + +#define SCTL_SCCTL 0x00 /* System controller control register */ +#define SCTL_ARMCFG 0x04 /* ARM configuration register */ +#define SCTL_SCPLLCTL 0x08 /* PLL control status register */ +#define SCTL_SCPLLFCTRL 0x0c /* PLL frequency control register */ +#define SCTL_SCRESFRACT 0x10 /* PLL fractional input register */ +#define SCTL_SCRESCTRL1 0x14 /* Peripheral reset control 1 */ +#define SCTL_SCRESXTRL2 0x18 /* Peripheral reset control 2 */ +#define SCTL_SCPEREN0 0x1c /* Peripheral clock enable register 0 */ +#define SCTL_SCPEREN1 0x20 /* Peripheral clock enable register 1 */ +#define SCTL_SCPEREN2 0x24 /* Peripheral clock enable register 2 */ +#define SCTL_SCGRST 0x28 /* Peripheral global reset */ +#define SCTL_SCPCIPMCR1 0x30 /* PCI power management control 1 */ +#define SCTL_SCPCIPMCR2 0x34 /* PCI power management control 2 */ +#define SCTL_SCPCIPMSR1 0x38 /* PCI power management status 1 */ +#define SCTL_SCPCIPMSR2 0x3c /* PCI power management status 2 */ +#define SCTL_SCPCIPMSR3 0x40 /* PCI power management status 3 */ +#define SCTL_SCINTREN 0x44 /* Interrupt enable */ +#define SCTL_SCRISR 0x48 /* RAW interrupt status */ +#define SCTL_SCCLKSTAT0 0x4c /* Peripheral clocks status 0 */ +#define SCTL_SCCLKSTAT1 0x50 /* Peripheral clocks status 1 */ +#define SCTL_SCCLKSTAT2 0x54 /* Peripheral clocks status 2 */ +#define SCTL_SCRSTSTA 0x58 /* Reset status register */ + +#define SCTL_SCRESCTRL1_USB_PHY_POR (1 << 0) +#define SCTL_SCRESCTRL1_USB_OTG (1 << 1) +#define SCTL_SCRESCTRL1_USB_HRST (1 << 2) +#define SCTL_SCRESCTRL1_USB_PHY_HOST (1 << 3) +#define SCTL_SCRESCTRL1_SATAII (1 << 4) +#define SCTL_SCRESCTRL1_VIP (1 << 5) +#define SCTL_SCRESCTRL1_PER_MMC0 (1 << 6) +#define SCTL_SCRESCTRL1_PER_MMC1 (1 << 7) +#define SCTL_SCRESCTRL1_PER_GPIO0 (1 << 8) +#define SCTL_SCRESCTRL1_PER_GPIO1 (1 << 9) +#define SCTL_SCRESCTRL1_PER_GPIO2 (1 << 10) +#define SCTL_SCRESCTRL1_PER_GPIO3 (1 << 11) +#define SCTL_SCRESCTRL1_PER_MTU0 (1 << 12) +#define SCTL_SCRESCTRL1_KER_SPI0 (1 << 13) +#define SCTL_SCRESCTRL1_KER_SPI1 (1 << 14) +#define SCTL_SCRESCTRL1_KER_SPI2 (1 << 15) +#define SCTL_SCRESCTRL1_KER_MCI0 (1 << 16) +#define SCTL_SCRESCTRL1_KER_MCI1 (1 << 17) +#define SCTL_SCRESCTRL1_PRE_HSI2C0 (1 << 18) +#define SCTL_SCRESCTRL1_PER_HSI2C1 (1 << 19) +#define SCTL_SCRESCTRL1_PER_HSI2C2 (1 << 20) +#define SCTL_SCRESCTRL1_PER_HSI2C3 (1 << 21) +#define SCTL_SCRESCTRL1_PER_MSP0 (1 << 22) +#define SCTL_SCRESCTRL1_PER_MSP1 (1 << 23) +#define SCTL_SCRESCTRL1_PER_MSP2 (1 << 24) +#define SCTL_SCRESCTRL1_PER_MSP3 (1 << 25) +#define SCTL_SCRESCTRL1_PER_MSP4 (1 << 26) +#define SCTL_SCRESCTRL1_PER_MSP5 (1 << 27) +#define SCTL_SCRESCTRL1_PER_MMC (1 << 28) +#define SCTL_SCRESCTRL1_KER_MSP0 (1 << 29) +#define SCTL_SCRESCTRL1_KER_MSP1 (1 << 30) +#define SCTL_SCRESCTRL1_KER_MSP2 (1 << 31) + +#define SCTL_SCPEREN0_UART0 (1 << 0) +#define SCTL_SCPEREN0_UART1 (1 << 1) +#define SCTL_SCPEREN0_UART2 (1 << 2) +#define SCTL_SCPEREN0_UART3 (1 << 3) +#define SCTL_SCPEREN0_MSP0 (1 << 4) +#define SCTL_SCPEREN0_MSP1 (1 << 5) +#define SCTL_SCPEREN0_MSP2 (1 << 6) +#define SCTL_SCPEREN0_MSP3 (1 << 7) +#define SCTL_SCPEREN0_MSP4 (1 << 8) +#define SCTL_SCPEREN0_MSP5 (1 << 9) +#define SCTL_SCPEREN0_SPI0 (1 << 10) +#define SCTL_SCPEREN0_SPI1 (1 << 11) +#define SCTL_SCPEREN0_SPI2 (1 << 12) +#define SCTL_SCPEREN0_I2C0 (1 << 13) +#define SCTL_SCPEREN0_I2C1 (1 << 14) +#define SCTL_SCPEREN0_I2C2 (1 << 15) +#define SCTL_SCPEREN0_I2C3 (1 << 16) +#define SCTL_SCPEREN0_SVDO_LVDS (1 << 17) +#define SCTL_SCPEREN0_USB_HOST (1 << 18) +#define SCTL_SCPEREN0_USB_OTG (1 << 19) +#define SCTL_SCPEREN0_MCI0 (1 << 20) +#define SCTL_SCPEREN0_MCI1 (1 << 21) +#define SCTL_SCPEREN0_MCI2 (1 << 22) +#define SCTL_SCPEREN0_MCI3 (1 << 23) +#define SCTL_SCPEREN0_SATA (1 << 24) +#define SCTL_SCPEREN0_ETHERNET (1 << 25) +#define SCTL_SCPEREN0_VIC (1 << 26) +#define SCTL_SCPEREN0_DMA_AUDIO (1 << 27) +#define SCTL_SCPEREN0_DMA_SOC (1 << 28) +#define SCTL_SCPEREN0_RAM (1 << 29) +#define SCTL_SCPEREN0_VIP (1 << 30) +#define SCTL_SCPEREN0_ARM (1 << 31) + +#define SCTL_SCPEREN1_UART0 (1 << 0) +#define SCTL_SCPEREN1_UART1 (1 << 1) +#define SCTL_SCPEREN1_UART2 (1 << 2) +#define SCTL_SCPEREN1_UART3 (1 << 3) +#define SCTL_SCPEREN1_MSP0 (1 << 4) +#define SCTL_SCPEREN1_MSP1 (1 << 5) +#define SCTL_SCPEREN1_MSP2 (1 << 6) +#define SCTL_SCPEREN1_MSP3 (1 << 7) +#define SCTL_SCPEREN1_MSP4 (1 << 8) +#define SCTL_SCPEREN1_MSP5 (1 << 9) +#define SCTL_SCPEREN1_SPI0 (1 << 10) +#define SCTL_SCPEREN1_SPI1 (1 << 11) +#define SCTL_SCPEREN1_SPI2 (1 << 12) +#define SCTL_SCPEREN1_I2C0 (1 << 13) +#define SCTL_SCPEREN1_I2C1 (1 << 14) +#define SCTL_SCPEREN1_I2C2 (1 << 15) +#define SCTL_SCPEREN1_I2C3 (1 << 16) +#define SCTL_SCPEREN1_USB_PHY (1 << 17) + +#endif /* __STA2X11_MFD_H */ -- cgit v1.2.3 From 1fc9b1eade80b323f02a9cf7a29e1641eddf1052 Mon Sep 17 00:00:00 2001 From: Seth Heasley Date: Mon, 23 Apr 2012 09:23:56 -0700 Subject: pci_ids: Add Intel Centerton Legacy Block DeviceID This patch adds the Integrated Legacy Block DeviceID for the Centerton CPU. It will be used in the GPIO and Multifunction Devices driver. Signed-off-by: Seth Heasley Signed-off-by: Samuel Ortiz --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3329965ed63f..ab741b0d0074 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2506,6 +2506,7 @@ #define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 +#define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 #define PCI_DEVICE_ID_INTEL_8257X_SOL 0x1062 #define PCI_DEVICE_ID_INTEL_82573E_SOL 0x1085 #define PCI_DEVICE_ID_INTEL_82573L_SOL 0x108F -- cgit v1.2.3 From 16c5c023aac86228e3e94c4bf6d19708ea861a05 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 3 May 2012 12:26:36 +0200 Subject: mfd: Add LM3533 lighting-power core driver Add support for National Semiconductor / TI LM3533 lighting power chips. This is the core driver which provides register access over I2C and registers the ambient-light-sensor, LED and backlight sub-drivers. Signed-off-by: Johan Hovold Reviewed-by: Mark Brown Signed-off-by: Samuel Ortiz --- .../ABI/testing/sysfs-bus-i2c-devices-lm3533 | 38 ++ drivers/mfd/Kconfig | 13 + drivers/mfd/Makefile | 1 + drivers/mfd/lm3533-core.c | 717 +++++++++++++++++++++ drivers/mfd/lm3533-ctrlbank.c | 134 ++++ include/linux/mfd/lm3533.h | 89 +++ 6 files changed, 992 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-bus-i2c-devices-lm3533 create mode 100644 drivers/mfd/lm3533-core.c create mode 100644 drivers/mfd/lm3533-ctrlbank.c create mode 100644 include/linux/mfd/lm3533.h (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-i2c-devices-lm3533 b/Documentation/ABI/testing/sysfs-bus-i2c-devices-lm3533 new file mode 100644 index 000000000000..570072180b8d --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-i2c-devices-lm3533 @@ -0,0 +1,38 @@ +What: /sys/bus/i2c/devices/.../boost_freq +Date: April 2012 +KernelVersion: 3.5 +Contact: Johan Hovold +Description: + Set the boost converter switching frequency (0, 1), where + + 0 - 500Hz + 1 - 1000Hz + +What: /sys/bus/i2c/devices/.../boost_ovp +Date: April 2012 +KernelVersion: 3.5 +Contact: Johan Hovold +Description: + Set the boost converter over-voltage protection threshold + (0..3), where + + 0 - 16V + 1 - 24V + 2 - 32V + 3 - 40V + +What: /sys/bus/i2c/devices/.../output_hvled[n] +Date: April 2012 +KernelVersion: 3.5 +Contact: Johan Hovold +Description: + Set the controlling backlight device for high-voltage current + sink HVLED[n] (n = 1, 2) (0, 1). + +What: /sys/bus/i2c/devices/.../output_lvled[n] +Date: April 2012 +KernelVersion: 3.5 +Contact: Johan Hovold +Description: + Set the controlling led device for low-voltage current sink + LVLED[n] (n = 1..5) (0..3). diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 48eed22c65a5..211f5dee9b68 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -106,6 +106,19 @@ config UCB1400_CORE To compile this driver as a module, choose M here: the module will be called ucb1400_core. +config MFD_LM3533 + tristate "LM3533 Lighting Power chip" + depends on I2C + select MFD_CORE + select REGMAP_I2C + help + Say yes here to enable support for National Semiconductor / TI + LM3533 Lighting Power chips. + + This driver provides common support for accessing the device; + additional drivers must be enabled in order to use the LED, + backlight or ambient-light-sensor functionality of the device. + config TPS6105X tristate "TPS61050/61052 Boost Converters" depends on I2C diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 0dc55cbefa09..d3dae9567800 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -120,3 +120,4 @@ obj-$(CONFIG_MFD_INTEL_MSIC) += intel_msic.o obj-$(CONFIG_MFD_RC5T583) += rc5t583.o rc5t583-irq.o obj-$(CONFIG_MFD_S5M_CORE) += s5m-core.o s5m-irq.o obj-$(CONFIG_MFD_ANATOP) += anatop-mfd.o +obj-$(CONFIG_MFD_LM3533) += lm3533-core.o lm3533-ctrlbank.o diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c new file mode 100644 index 000000000000..75f4b7f5a4fd --- /dev/null +++ b/drivers/mfd/lm3533-core.c @@ -0,0 +1,717 @@ +/* + * lm3533-core.c -- LM3533 Core + * + * Copyright (C) 2011-2012 Texas Instruments + * + * Author: Johan Hovold + * + * 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. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + + +#define LM3533_BOOST_OVP_MAX 0x03 +#define LM3533_BOOST_OVP_MASK 0x06 +#define LM3533_BOOST_OVP_SHIFT 1 + +#define LM3533_BOOST_FREQ_MAX 0x01 +#define LM3533_BOOST_FREQ_MASK 0x01 +#define LM3533_BOOST_FREQ_SHIFT 0 + +#define LM3533_BL_ID_MASK 1 +#define LM3533_LED_ID_MASK 3 +#define LM3533_BL_ID_MAX 1 +#define LM3533_LED_ID_MAX 3 + +#define LM3533_HVLED_ID_MAX 2 +#define LM3533_LVLED_ID_MAX 5 + +#define LM3533_REG_OUTPUT_CONF1 0x10 +#define LM3533_REG_OUTPUT_CONF2 0x11 +#define LM3533_REG_BOOST_PWM 0x2c + +#define LM3533_REG_MAX 0xb2 + + +static struct mfd_cell lm3533_als_devs[] = { + { + .name = "lm3533-als", + .id = -1, + }, +}; + +static struct mfd_cell lm3533_bl_devs[] = { + { + .name = "lm3533-backlight", + .id = 0, + }, + { + .name = "lm3533-backlight", + .id = 1, + }, +}; + +static struct mfd_cell lm3533_led_devs[] = { + { + .name = "lm3533-leds", + .id = 0, + }, + { + .name = "lm3533-leds", + .id = 1, + }, + { + .name = "lm3533-leds", + .id = 2, + }, + { + .name = "lm3533-leds", + .id = 3, + }, +}; + +int lm3533_read(struct lm3533 *lm3533, u8 reg, u8 *val) +{ + int tmp; + int ret; + + ret = regmap_read(lm3533->regmap, reg, &tmp); + if (ret < 0) { + dev_err(lm3533->dev, "failed to read register %02x: %d\n", + reg, ret); + return ret; + } + + *val = tmp; + + dev_dbg(lm3533->dev, "read [%02x]: %02x\n", reg, *val); + + return ret; +} +EXPORT_SYMBOL_GPL(lm3533_read); + +int lm3533_write(struct lm3533 *lm3533, u8 reg, u8 val) +{ + int ret; + + dev_dbg(lm3533->dev, "write [%02x]: %02x\n", reg, val); + + ret = regmap_write(lm3533->regmap, reg, val); + if (ret < 0) { + dev_err(lm3533->dev, "failed to write register %02x: %d\n", + reg, ret); + } + + return ret; +} +EXPORT_SYMBOL_GPL(lm3533_write); + +int lm3533_update(struct lm3533 *lm3533, u8 reg, u8 val, u8 mask) +{ + int ret; + + dev_dbg(lm3533->dev, "update [%02x]: %02x/%02x\n", reg, val, mask); + + ret = regmap_update_bits(lm3533->regmap, reg, val, mask); + if (ret < 0) { + dev_err(lm3533->dev, "failed to update register %02x: %d\n", + reg, ret); + } + + return ret; +} +EXPORT_SYMBOL_GPL(lm3533_update); + +/* + * HVLED output config -- output hvled controlled by backlight bl + */ +static int lm3533_set_hvled_config(struct lm3533 *lm3533, u8 hvled, u8 bl) +{ + u8 val; + u8 mask; + int shift; + int ret; + + if (hvled == 0 || hvled > LM3533_HVLED_ID_MAX) + return -EINVAL; + + if (bl > LM3533_BL_ID_MAX) + return -EINVAL; + + shift = hvled - 1; + mask = LM3533_BL_ID_MASK << shift; + val = bl << shift; + + ret = lm3533_update(lm3533, LM3533_REG_OUTPUT_CONF1, val, mask); + if (ret) + dev_err(lm3533->dev, "failed to set hvled config\n"); + + return ret; +} + +/* + * LVLED output config -- output lvled controlled by LED led + */ +static int lm3533_set_lvled_config(struct lm3533 *lm3533, u8 lvled, u8 led) +{ + u8 reg; + u8 val; + u8 mask; + int shift; + int ret; + + if (lvled == 0 || lvled > LM3533_LVLED_ID_MAX) + return -EINVAL; + + if (led > LM3533_LED_ID_MAX) + return -EINVAL; + + if (lvled < 4) { + reg = LM3533_REG_OUTPUT_CONF1; + shift = 2 * lvled; + } else { + reg = LM3533_REG_OUTPUT_CONF2; + shift = 2 * (lvled - 4); + } + + mask = LM3533_LED_ID_MASK << shift; + val = led << shift; + + ret = lm3533_update(lm3533, reg, val, mask); + if (ret) + dev_err(lm3533->dev, "failed to set lvled config\n"); + + return ret; +} + +static void lm3533_enable(struct lm3533 *lm3533) +{ + if (gpio_is_valid(lm3533->gpio_hwen)) + gpio_set_value(lm3533->gpio_hwen, 1); +} + +static void lm3533_disable(struct lm3533 *lm3533) +{ + if (gpio_is_valid(lm3533->gpio_hwen)) + gpio_set_value(lm3533->gpio_hwen, 0); +} + +enum lm3533_attribute_type { + LM3533_ATTR_TYPE_BACKLIGHT, + LM3533_ATTR_TYPE_LED, +}; + +struct lm3533_device_attribute { + struct device_attribute dev_attr; + enum lm3533_attribute_type type; + union { + struct { + u8 id; + } output; + struct { + u8 reg; + u8 shift; + u8 mask; + u8 max; + } generic; + } u; +}; + +#define to_lm3533_dev_attr(_attr) \ + container_of(_attr, struct lm3533_device_attribute, dev_attr) + +static ssize_t show_lm3533_reg(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct lm3533 *lm3533 = dev_get_drvdata(dev); + struct lm3533_device_attribute *lattr = to_lm3533_dev_attr(attr); + u8 val; + int ret; + + ret = lm3533_read(lm3533, lattr->u.generic.reg, &val); + if (ret) + return ret; + + val = (val & lattr->u.generic.mask) >> lattr->u.generic.shift; + + return scnprintf(buf, PAGE_SIZE, "%u\n", val); +} + +static ssize_t store_lm3533_reg(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct lm3533 *lm3533 = dev_get_drvdata(dev); + struct lm3533_device_attribute *lattr = to_lm3533_dev_attr(attr); + u8 val; + int ret; + + if (kstrtou8(buf, 0, &val) || val > lattr->u.generic.max) + return -EINVAL; + + val = val << lattr->u.generic.shift; + ret = lm3533_update(lm3533, lattr->u.generic.reg, val, + lattr->u.generic.mask); + if (ret) + return ret; + + return len; +} + +#define GENERIC_ATTR(_reg, _max, _mask, _shift) \ + { .reg = _reg, \ + .max = _max, \ + .mask = _mask, \ + .shift = _shift } + +#define LM3533_GENERIC_ATTR(_name, _mode, _show, _store, _type, \ + _reg, _max, _mask, _shift) \ + struct lm3533_device_attribute lm3533_dev_attr_##_name = { \ + .dev_attr = __ATTR(_name, _mode, _show, _store), \ + .type = _type, \ + .u.generic = GENERIC_ATTR(_reg, _max, _mask, _shift) } + +#define LM3533_GENERIC_ATTR_RW(_name, _type, _reg, _max, _mask, _shift) \ + LM3533_GENERIC_ATTR(_name, S_IRUGO | S_IWUSR, \ + show_lm3533_reg, store_lm3533_reg, \ + _type, _reg, _max, _mask, _shift) + +#define LM3533_BOOST_ATTR_RW(_name, _NAME) \ + LM3533_GENERIC_ATTR_RW(_name, LM3533_ATTR_TYPE_BACKLIGHT, \ + LM3533_REG_BOOST_PWM, LM3533_##_NAME##_MAX, \ + LM3533_##_NAME##_MASK, LM3533_##_NAME##_SHIFT) +/* + * Boost Over Voltage Protection Select + * + * 0 - 16 V (default) + * 1 - 24 V + * 2 - 32 V + * 3 - 40 V + */ +static LM3533_BOOST_ATTR_RW(boost_ovp, BOOST_OVP); + +/* + * Boost Frequency Select + * + * 0 - 500 kHz (default) + * 1 - 1 MHz + */ +static LM3533_BOOST_ATTR_RW(boost_freq, BOOST_FREQ); + +static ssize_t show_output(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct lm3533 *lm3533 = dev_get_drvdata(dev); + struct lm3533_device_attribute *lattr = to_lm3533_dev_attr(attr); + int id = lattr->u.output.id; + u8 reg; + u8 val; + u8 mask; + int shift; + int ret; + + if (lattr->type == LM3533_ATTR_TYPE_BACKLIGHT) { + reg = LM3533_REG_OUTPUT_CONF1; + shift = id - 1; + mask = LM3533_BL_ID_MASK << shift; + } else { + if (id < 4) { + reg = LM3533_REG_OUTPUT_CONF1; + shift = 2 * id; + } else { + reg = LM3533_REG_OUTPUT_CONF2; + shift = 2 * (id - 4); + } + mask = LM3533_LED_ID_MASK << shift; + } + + ret = lm3533_read(lm3533, reg, &val); + if (ret) + return ret; + + val = (val & mask) >> shift; + + return scnprintf(buf, PAGE_SIZE, "%u\n", val); +} + +static ssize_t store_output(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct lm3533 *lm3533 = dev_get_drvdata(dev); + struct lm3533_device_attribute *lattr = to_lm3533_dev_attr(attr); + int id = lattr->u.output.id; + u8 val; + int ret; + + if (kstrtou8(buf, 0, &val)) + return -EINVAL; + + if (lattr->type == LM3533_ATTR_TYPE_BACKLIGHT) + ret = lm3533_set_hvled_config(lm3533, id, val); + else + ret = lm3533_set_lvled_config(lm3533, id, val); + + if (ret) + return ret; + + return len; +} + +#define LM3533_OUTPUT_ATTR(_name, _mode, _show, _store, _type, _id) \ + struct lm3533_device_attribute lm3533_dev_attr_##_name = \ + { .dev_attr = __ATTR(_name, _mode, _show, _store), \ + .type = _type, \ + .u.output = { .id = _id }, } + +#define LM3533_OUTPUT_ATTR_RW(_name, _type, _id) \ + LM3533_OUTPUT_ATTR(output_##_name, S_IRUGO | S_IWUSR, \ + show_output, store_output, _type, _id) + +#define LM3533_OUTPUT_HVLED_ATTR_RW(_nr) \ + LM3533_OUTPUT_ATTR_RW(hvled##_nr, LM3533_ATTR_TYPE_BACKLIGHT, _nr) +#define LM3533_OUTPUT_LVLED_ATTR_RW(_nr) \ + LM3533_OUTPUT_ATTR_RW(lvled##_nr, LM3533_ATTR_TYPE_LED, _nr) +/* + * Output config: + * + * output_hvled 0-1 + * output_lvled 0-3 + */ +static LM3533_OUTPUT_HVLED_ATTR_RW(1); +static LM3533_OUTPUT_HVLED_ATTR_RW(2); +static LM3533_OUTPUT_LVLED_ATTR_RW(1); +static LM3533_OUTPUT_LVLED_ATTR_RW(2); +static LM3533_OUTPUT_LVLED_ATTR_RW(3); +static LM3533_OUTPUT_LVLED_ATTR_RW(4); +static LM3533_OUTPUT_LVLED_ATTR_RW(5); + +static struct attribute *lm3533_attributes[] = { + &lm3533_dev_attr_boost_freq.dev_attr.attr, + &lm3533_dev_attr_boost_ovp.dev_attr.attr, + &lm3533_dev_attr_output_hvled1.dev_attr.attr, + &lm3533_dev_attr_output_hvled2.dev_attr.attr, + &lm3533_dev_attr_output_lvled1.dev_attr.attr, + &lm3533_dev_attr_output_lvled2.dev_attr.attr, + &lm3533_dev_attr_output_lvled3.dev_attr.attr, + &lm3533_dev_attr_output_lvled4.dev_attr.attr, + &lm3533_dev_attr_output_lvled5.dev_attr.attr, + NULL, +}; + +#define to_dev_attr(_attr) \ + container_of(_attr, struct device_attribute, attr) + +static mode_t lm3533_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct lm3533 *lm3533 = dev_get_drvdata(dev); + struct device_attribute *dattr = to_dev_attr(attr); + struct lm3533_device_attribute *lattr = to_lm3533_dev_attr(dattr); + enum lm3533_attribute_type type = lattr->type; + mode_t mode = attr->mode; + + if (!lm3533->have_backlights && type == LM3533_ATTR_TYPE_BACKLIGHT) + mode = 0; + else if (!lm3533->have_leds && type == LM3533_ATTR_TYPE_LED) + mode = 0; + + return mode; +}; + +static struct attribute_group lm3533_attribute_group = { + .is_visible = lm3533_attr_is_visible, + .attrs = lm3533_attributes +}; + +static int __devinit lm3533_device_als_init(struct lm3533 *lm3533) +{ + struct lm3533_platform_data *pdata = lm3533->dev->platform_data; + int ret; + + if (!pdata->als) + return 0; + + lm3533_als_devs[0].platform_data = pdata->als; + lm3533_als_devs[0].pdata_size = sizeof(*pdata->als); + + ret = mfd_add_devices(lm3533->dev, 0, lm3533_als_devs, 1, NULL, 0); + if (ret) { + dev_err(lm3533->dev, "failed to add ALS device\n"); + return ret; + } + + lm3533->have_als = 1; + + return 0; +} + +static int __devinit lm3533_device_bl_init(struct lm3533 *lm3533) +{ + struct lm3533_platform_data *pdata = lm3533->dev->platform_data; + int i; + int ret; + + if (!pdata->backlights || pdata->num_backlights == 0) + return 0; + + if (pdata->num_backlights > ARRAY_SIZE(lm3533_bl_devs)) + pdata->num_backlights = ARRAY_SIZE(lm3533_bl_devs); + + for (i = 0; i < pdata->num_backlights; ++i) { + lm3533_bl_devs[i].platform_data = &pdata->backlights[i]; + lm3533_bl_devs[i].pdata_size = sizeof(pdata->backlights[i]); + } + + ret = mfd_add_devices(lm3533->dev, 0, lm3533_bl_devs, + pdata->num_backlights, NULL, 0); + if (ret) { + dev_err(lm3533->dev, "failed to add backlight devices\n"); + return ret; + } + + lm3533->have_backlights = 1; + + return 0; +} + +static int __devinit lm3533_device_led_init(struct lm3533 *lm3533) +{ + struct lm3533_platform_data *pdata = lm3533->dev->platform_data; + int i; + int ret; + + if (!pdata->leds || pdata->num_leds == 0) + return 0; + + if (pdata->num_leds > ARRAY_SIZE(lm3533_led_devs)) + pdata->num_leds = ARRAY_SIZE(lm3533_led_devs); + + for (i = 0; i < pdata->num_leds; ++i) { + lm3533_led_devs[i].platform_data = &pdata->leds[i]; + lm3533_led_devs[i].pdata_size = sizeof(pdata->leds[i]); + } + + ret = mfd_add_devices(lm3533->dev, 0, lm3533_led_devs, + pdata->num_leds, NULL, 0); + if (ret) { + dev_err(lm3533->dev, "failed to add LED devices\n"); + return ret; + } + + lm3533->have_leds = 1; + + return 0; +} + +static int __devinit lm3533_device_init(struct lm3533 *lm3533) +{ + struct lm3533_platform_data *pdata = lm3533->dev->platform_data; + int ret; + + dev_dbg(lm3533->dev, "%s\n", __func__); + + if (!pdata) { + dev_err(lm3533->dev, "no platform data\n"); + return -EINVAL; + } + + lm3533->gpio_hwen = pdata->gpio_hwen; + + dev_set_drvdata(lm3533->dev, lm3533); + + if (gpio_is_valid(lm3533->gpio_hwen)) { + ret = gpio_request_one(lm3533->gpio_hwen, GPIOF_OUT_INIT_LOW, + "lm3533-hwen"); + if (ret < 0) { + dev_err(lm3533->dev, + "failed to request HWEN GPIO %d\n", + lm3533->gpio_hwen); + return ret; + } + } + + lm3533_enable(lm3533); + + lm3533_device_als_init(lm3533); + lm3533_device_bl_init(lm3533); + lm3533_device_led_init(lm3533); + + ret = sysfs_create_group(&lm3533->dev->kobj, &lm3533_attribute_group); + if (ret < 0) { + dev_err(lm3533->dev, "failed to create sysfs attributes\n"); + goto err_unregister; + } + + return 0; + +err_unregister: + mfd_remove_devices(lm3533->dev); + lm3533_disable(lm3533); + if (gpio_is_valid(lm3533->gpio_hwen)) + gpio_free(lm3533->gpio_hwen); + + return ret; +} + +static void __devexit lm3533_device_exit(struct lm3533 *lm3533) +{ + dev_dbg(lm3533->dev, "%s\n", __func__); + + sysfs_remove_group(&lm3533->dev->kobj, &lm3533_attribute_group); + + mfd_remove_devices(lm3533->dev); + lm3533_disable(lm3533); + if (gpio_is_valid(lm3533->gpio_hwen)) + gpio_free(lm3533->gpio_hwen); +} + +static bool lm3533_readable_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case 0x10 ... 0x2c: + case 0x30 ... 0x38: + case 0x40 ... 0x45: + case 0x50 ... 0x57: + case 0x60 ... 0x6e: + case 0x70 ... 0x75: + case 0x80 ... 0x85: + case 0x90 ... 0x95: + case 0xa0 ... 0xa5: + case 0xb0 ... 0xb2: + return true; + default: + return false; + } +} + +static bool lm3533_volatile_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case 0x34: /* zone */ + case 0x37 ... 0x38: /* adc */ + case 0xb0 ... 0xb1: /* fault */ + return true; + default: + return false; + } +} + +static bool lm3533_precious_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case 0x34: /* zone */ + return true; + default: + return false; + } +} + +static struct regmap_config regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = LM3533_REG_MAX, + .readable_reg = lm3533_readable_register, + .volatile_reg = lm3533_volatile_register, + .precious_reg = lm3533_precious_register, +}; + +static int __devinit lm3533_i2c_probe(struct i2c_client *i2c, + const struct i2c_device_id *id) +{ + struct lm3533 *lm3533; + int ret; + + dev_dbg(&i2c->dev, "%s\n", __func__); + + lm3533 = kzalloc(sizeof(*lm3533), GFP_KERNEL); + if (!lm3533) + return -ENOMEM; + + i2c_set_clientdata(i2c, lm3533); + + lm3533->regmap = regmap_init_i2c(i2c, ®map_config); + if (IS_ERR(lm3533->regmap)) { + ret = PTR_ERR(lm3533->regmap); + goto err_regmap; + } + + lm3533->dev = &i2c->dev; + lm3533->irq = i2c->irq; + + ret = lm3533_device_init(lm3533); + if (ret) + goto err_dev; + + return 0; + +err_dev: + regmap_exit(lm3533->regmap); +err_regmap: + kfree(lm3533); + + return ret; +} + +static int __devexit lm3533_i2c_remove(struct i2c_client *i2c) +{ + struct lm3533 *lm3533 = i2c_get_clientdata(i2c); + + dev_dbg(&i2c->dev, "%s\n", __func__); + + lm3533_device_exit(lm3533); + regmap_exit(lm3533->regmap); + + kfree(lm3533); + + return 0; +} + +static const struct i2c_device_id lm3533_i2c_ids[] = { + { "lm3533", 0 }, + { }, +}; +MODULE_DEVICE_TABLE(i2c, lm3533_i2c_ids); + +static struct i2c_driver lm3533_i2c_driver = { + .driver = { + .name = "lm3533", + .owner = THIS_MODULE, + }, + .id_table = lm3533_i2c_ids, + .probe = lm3533_i2c_probe, + .remove = __devexit_p(lm3533_i2c_remove), +}; + +static int __init lm3533_i2c_init(void) +{ + return i2c_add_driver(&lm3533_i2c_driver); +} +subsys_initcall(lm3533_i2c_init); + +static void __exit lm3533_i2c_exit(void) +{ + i2c_del_driver(&lm3533_i2c_driver); +} +module_exit(lm3533_i2c_exit); + +MODULE_AUTHOR("Johan Hovold "); +MODULE_DESCRIPTION("LM3533 Core"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mfd/lm3533-ctrlbank.c b/drivers/mfd/lm3533-ctrlbank.c new file mode 100644 index 000000000000..c2732a37c65a --- /dev/null +++ b/drivers/mfd/lm3533-ctrlbank.c @@ -0,0 +1,134 @@ +/* + * lm3533-ctrlbank.c -- LM3533 Generic Control Bank interface + * + * Copyright (C) 2011-2012 Texas Instruments + * + * Author: Johan Hovold + * + * 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. + */ + +#include +#include + +#include + + +#define LM3533_BRIGHTNESS_MAX 255 +#define LM3533_MAX_CURRENT_MAX 31 +#define LM3533_PWM_MAX 0x3f + +#define LM3533_REG_PWM_BASE 0x14 +#define LM3533_REG_MAX_CURRENT_BASE 0x1f +#define LM3533_REG_CTRLBANK_ENABLE 0x27 +#define LM3533_REG_BRIGHTNESS_BASE 0x40 + + +static inline u8 lm3533_ctrlbank_get_reg(struct lm3533_ctrlbank *cb, u8 base) +{ + return base + cb->id; +} + +int lm3533_ctrlbank_enable(struct lm3533_ctrlbank *cb) +{ + u8 mask; + int ret; + + dev_dbg(cb->dev, "%s - %d\n", __func__, cb->id); + + mask = 1 << cb->id; + ret = lm3533_update(cb->lm3533, LM3533_REG_CTRLBANK_ENABLE, + mask, mask); + if (ret) + dev_err(cb->dev, "failed to enable ctrlbank %d\n", cb->id); + + return ret; +} +EXPORT_SYMBOL_GPL(lm3533_ctrlbank_enable); + +int lm3533_ctrlbank_disable(struct lm3533_ctrlbank *cb) +{ + u8 mask; + int ret; + + dev_dbg(cb->dev, "%s - %d\n", __func__, cb->id); + + mask = 1 << cb->id; + ret = lm3533_update(cb->lm3533, LM3533_REG_CTRLBANK_ENABLE, 0, mask); + if (ret) + dev_err(cb->dev, "failed to disable ctrlbank %d\n", cb->id); + + return ret; +} +EXPORT_SYMBOL_GPL(lm3533_ctrlbank_disable); + +#define lm3533_ctrlbank_set(_name, _NAME) \ +int lm3533_ctrlbank_set_##_name(struct lm3533_ctrlbank *cb, u8 val) \ +{ \ + u8 reg; \ + int ret; \ + \ + if (val > LM3533_##_NAME##_MAX) \ + return -EINVAL; \ + \ + reg = lm3533_ctrlbank_get_reg(cb, LM3533_REG_##_NAME##_BASE); \ + ret = lm3533_write(cb->lm3533, reg, val); \ + if (ret) \ + dev_err(cb->dev, "failed to set " #_name "\n"); \ + \ + return ret; \ +} \ +EXPORT_SYMBOL_GPL(lm3533_ctrlbank_set_##_name); + +#define lm3533_ctrlbank_get(_name, _NAME) \ +int lm3533_ctrlbank_get_##_name(struct lm3533_ctrlbank *cb, u8 *val) \ +{ \ + u8 reg; \ + int ret; \ + \ + reg = lm3533_ctrlbank_get_reg(cb, LM3533_REG_##_NAME##_BASE); \ + ret = lm3533_read(cb->lm3533, reg, val); \ + if (ret) \ + dev_err(cb->dev, "failed to get " #_name "\n"); \ + \ + return ret; \ +} \ +EXPORT_SYMBOL_GPL(lm3533_ctrlbank_get_##_name); + +lm3533_ctrlbank_set(brightness, BRIGHTNESS); +lm3533_ctrlbank_get(brightness, BRIGHTNESS); + +/* + * Full scale current. + * + * Imax = 5 + val * 0.8 mA, e.g.: + * + * 0 - 5 mA + * ... + * 19 - 20.2 mA (default) + * ... + * 31 - 29.8 mA + */ +lm3533_ctrlbank_set(max_current, MAX_CURRENT); +lm3533_ctrlbank_get(max_current, MAX_CURRENT); + +/* + * PWM-input control mask: + * + * bit 5 - PWM-input enabled in Zone 4 + * bit 4 - PWM-input enabled in Zone 3 + * bit 3 - PWM-input enabled in Zone 2 + * bit 2 - PWM-input enabled in Zone 1 + * bit 1 - PWM-input enabled in Zone 0 + * bit 0 - PWM-input enabled + */ +lm3533_ctrlbank_set(pwm, PWM); +lm3533_ctrlbank_get(pwm, PWM); + + +MODULE_AUTHOR("Johan Hovold "); +MODULE_DESCRIPTION("LM3533 Control Bank interface"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h new file mode 100644 index 000000000000..75f85f3fbd90 --- /dev/null +++ b/include/linux/mfd/lm3533.h @@ -0,0 +1,89 @@ +/* + * lm3533.h -- LM3533 interface + * + * Copyright (C) 2011-2012 Texas Instruments + * + * Author: Johan Hovold + * + * 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 __LINUX_MFD_LM3533_H +#define __LINUX_MFD_LM3533_H + +#define LM3533_ATTR_RO(_name) \ + DEVICE_ATTR(_name, S_IRUGO, show_##_name, NULL) +#define LM3533_ATTR_RW(_name) \ + DEVICE_ATTR(_name, S_IRUGO | S_IWUSR , show_##_name, store_##_name) + +struct device; +struct regmap; + +struct lm3533 { + struct device *dev; + + struct regmap *regmap; + + int gpio_hwen; + int irq; + + unsigned have_als:1; + unsigned have_backlights:1; + unsigned have_leds:1; +}; + +struct lm3533_ctrlbank { + struct lm3533 *lm3533; + struct device *dev; + int id; +}; + +struct lm3533_als_platform_data { + unsigned pwm_mode:1; /* PWM input mode (default analog) */ +}; + +struct lm3533_bl_platform_data { + char *name; + u8 default_brightness; /* 0 - 255 */ + u8 max_current; /* 0 - 31 */ + u8 pwm; /* 0 - 0x3f */ +}; + +struct lm3533_led_platform_data { + char *name; + const char *default_trigger; + u8 max_current; /* 0 - 31 */ + u8 pwm; /* 0 - 0x3f */ +}; + +struct lm3533_platform_data { + int gpio_hwen; + + struct lm3533_als_platform_data *als; + + struct lm3533_bl_platform_data *backlights; + int num_backlights; + + struct lm3533_led_platform_data *leds; + int num_leds; +}; + +extern int lm3533_ctrlbank_enable(struct lm3533_ctrlbank *cb); +extern int lm3533_ctrlbank_disable(struct lm3533_ctrlbank *cb); + +extern int lm3533_ctrlbank_set_brightness(struct lm3533_ctrlbank *cb, u8 val); +extern int lm3533_ctrlbank_get_brightness(struct lm3533_ctrlbank *cb, u8 *val); +extern int lm3533_ctrlbank_set_max_current(struct lm3533_ctrlbank *cb, u8 val); +extern int lm3533_ctrlbank_get_max_current(struct lm3533_ctrlbank *cb, + u8 *val); +extern int lm3533_ctrlbank_set_pwm(struct lm3533_ctrlbank *cb, u8 val); +extern int lm3533_ctrlbank_get_pwm(struct lm3533_ctrlbank *cb, u8 *val); + +extern int lm3533_read(struct lm3533 *lm3533, u8 reg, u8 *val); +extern int lm3533_write(struct lm3533 *lm3533, u8 reg, u8 val); +extern int lm3533_update(struct lm3533 *lm3533, u8 reg, u8 val, u8 mask); + +#endif /* __LINUX_MFD_LM3533_H */ -- cgit v1.2.3 From 887c8ec7219fc8eba78bb8f44a74c660934e9b98 Mon Sep 17 00:00:00 2001 From: Aaron Sierra Date: Fri, 20 Apr 2012 14:14:11 -0500 Subject: watchdog: Convert iTCO_wdt driver to mfd model This patch converts the iTCO_wdt driver to use the multi-function device driver model. It uses resources discovered by the lpc_ich driver, so that it no longer does its own PCI scanning. Signed-off-by: Aaron Sierra Signed-off-by: Guenter Roeck Signed-off-by: Samuel Ortiz --- drivers/mfd/Kconfig | 3 +- drivers/mfd/lpc_ich.c | 171 ++++++++++- drivers/watchdog/Kconfig | 1 + drivers/watchdog/iTCO_vendor.h | 6 +- drivers/watchdog/iTCO_vendor_support.c | 43 ++- drivers/watchdog/iTCO_wdt.c | 529 +++++++-------------------------- include/linux/mfd/lpc_ich.h | 7 + 7 files changed, 313 insertions(+), 447 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 211f5dee9b68..1e9a7d5ec919 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -785,7 +785,8 @@ config LPC_ICH help The LPC bridge function of the Intel ICH provides support for many functional units. This driver provides needed support for - other drivers to control these functions, currently GPIO. + other drivers to control these functions, currently GPIO and + watchdog. config MFD_RDC321X tristate "Support for RDC-R321x southbridge" diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c index 7e3a7b6ab022..027cc8f86132 100644 --- a/drivers/mfd/lpc_ich.c +++ b/drivers/mfd/lpc_ich.c @@ -65,14 +65,42 @@ #define ACPIBASE 0x40 #define ACPIBASE_GPE_OFF 0x28 #define ACPIBASE_GPE_END 0x2f +#define ACPIBASE_SMI_OFF 0x30 +#define ACPIBASE_SMI_END 0x33 +#define ACPIBASE_TCO_OFF 0x60 +#define ACPIBASE_TCO_END 0x7f #define ACPICTRL 0x44 +#define ACPIBASE_GCS_OFF 0x3410 +#define ACPIBASE_GCS_END 0x3414 + #define GPIOBASE 0x48 #define GPIOCTRL 0x4C +#define RCBABASE 0xf0 + +#define wdt_io_res(i) wdt_res(0, i) +#define wdt_mem_res(i) wdt_res(ICH_RES_MEM_OFF, i) +#define wdt_res(b, i) (&wdt_ich_res[(b) + (i)]) + static int lpc_ich_acpi_save = -1; static int lpc_ich_gpio_save = -1; +static struct resource wdt_ich_res[] = { + /* ACPI - TCO */ + { + .flags = IORESOURCE_IO, + }, + /* ACPI - SMI */ + { + .flags = IORESOURCE_IO, + }, + /* GCS */ + { + .flags = IORESOURCE_MEM, + }, +}; + static struct resource gpio_ich_res[] = { /* GPIO */ { @@ -85,10 +113,17 @@ static struct resource gpio_ich_res[] = { }; enum lpc_cells { - LPC_GPIO = 0, + LPC_WDT = 0, + LPC_GPIO, }; static struct mfd_cell lpc_ich_cells[] = { + [LPC_WDT] = { + .name = "iTCO_wdt", + .num_resources = ARRAY_SIZE(wdt_ich_res), + .resources = wdt_ich_res, + .ignore_resource_conflicts = true, + }, [LPC_GPIO] = { .name = "gpio_ich", .num_resources = ARRAY_SIZE(gpio_ich_res), @@ -162,218 +197,276 @@ enum lpc_chipsets { struct lpc_ich_info lpc_chipset_info[] __devinitdata = { [LPC_ICH] = { .name = "ICH", + .iTCO_version = 1, }, [LPC_ICH0] = { .name = "ICH0", + .iTCO_version = 1, }, [LPC_ICH2] = { .name = "ICH2", + .iTCO_version = 1, }, [LPC_ICH2M] = { .name = "ICH2-M", + .iTCO_version = 1, }, [LPC_ICH3] = { .name = "ICH3-S", + .iTCO_version = 1, }, [LPC_ICH3M] = { .name = "ICH3-M", + .iTCO_version = 1, }, [LPC_ICH4] = { .name = "ICH4", + .iTCO_version = 1, }, [LPC_ICH4M] = { .name = "ICH4-M", + .iTCO_version = 1, }, [LPC_CICH] = { .name = "C-ICH", + .iTCO_version = 1, }, [LPC_ICH5] = { .name = "ICH5 or ICH5R", + .iTCO_version = 1, }, [LPC_6300ESB] = { .name = "6300ESB", + .iTCO_version = 1, }, [LPC_ICH6] = { .name = "ICH6 or ICH6R", + .iTCO_version = 2, .gpio_version = ICH_V6_GPIO, }, [LPC_ICH6M] = { .name = "ICH6-M", + .iTCO_version = 2, .gpio_version = ICH_V6_GPIO, }, [LPC_ICH6W] = { .name = "ICH6W or ICH6RW", + .iTCO_version = 2, .gpio_version = ICH_V6_GPIO, }, [LPC_631XESB] = { .name = "631xESB/632xESB", + .iTCO_version = 2, .gpio_version = ICH_V6_GPIO, }, [LPC_ICH7] = { .name = "ICH7 or ICH7R", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_ICH7DH] = { .name = "ICH7DH", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_ICH7M] = { .name = "ICH7-M or ICH7-U", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_ICH7MDH] = { .name = "ICH7-M DH", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_NM10] = { .name = "NM10", + .iTCO_version = 2, }, [LPC_ICH8] = { .name = "ICH8 or ICH8R", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_ICH8DH] = { .name = "ICH8DH", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_ICH8DO] = { .name = "ICH8DO", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_ICH8M] = { .name = "ICH8M", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_ICH8ME] = { .name = "ICH8M-E", + .iTCO_version = 2, .gpio_version = ICH_V7_GPIO, }, [LPC_ICH9] = { .name = "ICH9", + .iTCO_version = 2, .gpio_version = ICH_V9_GPIO, }, [LPC_ICH9R] = { .name = "ICH9R", + .iTCO_version = 2, .gpio_version = ICH_V9_GPIO, }, [LPC_ICH9DH] = { .name = "ICH9DH", + .iTCO_version = 2, .gpio_version = ICH_V9_GPIO, }, [LPC_ICH9DO] = { .name = "ICH9DO", + .iTCO_version = 2, .gpio_version = ICH_V9_GPIO, }, [LPC_ICH9M] = { .name = "ICH9M", + .iTCO_version = 2, .gpio_version = ICH_V9_GPIO, }, [LPC_ICH9ME] = { .name = "ICH9M-E", + .iTCO_version = 2, .gpio_version = ICH_V9_GPIO, }, [LPC_ICH10] = { .name = "ICH10", + .iTCO_version = 2, .gpio_version = ICH_V10CONS_GPIO, }, [LPC_ICH10R] = { .name = "ICH10R", + .iTCO_version = 2, .gpio_version = ICH_V10CONS_GPIO, }, [LPC_ICH10D] = { .name = "ICH10D", + .iTCO_version = 2, .gpio_version = ICH_V10CORP_GPIO, }, [LPC_ICH10DO] = { .name = "ICH10DO", + .iTCO_version = 2, .gpio_version = ICH_V10CORP_GPIO, }, [LPC_PCH] = { .name = "PCH Desktop Full Featured", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_PCHM] = { .name = "PCH Mobile Full Featured", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_P55] = { .name = "P55", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_PM55] = { .name = "PM55", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_H55] = { .name = "H55", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_QM57] = { .name = "QM57", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_H57] = { .name = "H57", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_HM55] = { .name = "HM55", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_Q57] = { .name = "Q57", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_HM57] = { .name = "HM57", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_PCHMSFF] = { .name = "PCH Mobile SFF Full Featured", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_QS57] = { .name = "QS57", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_3400] = { .name = "3400", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_3420] = { .name = "3420", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_3450] = { .name = "3450", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_EP80579] = { .name = "EP80579", + .iTCO_version = 2, }, [LPC_CPT] = { .name = "Cougar Point", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_CPTD] = { .name = "Cougar Point Desktop", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_CPTM] = { .name = "Cougar Point Mobile", + .iTCO_version = 2, .gpio_version = ICH_V5_GPIO, }, [LPC_PBG] = { .name = "Patsburg", + .iTCO_version = 2, }, [LPC_DH89XXCC] = { .name = "DH89xxCC", + .iTCO_version = 2, }, [LPC_PPT] = { .name = "Panther Point", + .iTCO_version = 2, }, [LPC_LPT] = { .name = "Lynx Point", + .iTCO_version = 2, }, }; @@ -666,12 +759,88 @@ gpio_done: return ret; } +static int __devinit lpc_ich_init_wdt(struct pci_dev *dev, + const struct pci_device_id *id) +{ + u32 base_addr_cfg; + u32 base_addr; + int ret; + bool acpi_conflict = false; + struct resource *res; + + /* Setup power management base register */ + pci_read_config_dword(dev, ACPIBASE, &base_addr_cfg); + base_addr = base_addr_cfg & 0x0000ff80; + if (!base_addr) { + dev_err(&dev->dev, "I/O space for ACPI uninitialized\n"); + ret = -ENODEV; + goto wdt_done; + } + + res = wdt_io_res(ICH_RES_IO_TCO); + res->start = base_addr + ACPIBASE_TCO_OFF; + res->end = base_addr + ACPIBASE_TCO_END; + ret = acpi_check_resource_conflict(res); + if (ret) { + acpi_conflict = true; + goto wdt_done; + } + + res = wdt_io_res(ICH_RES_IO_SMI); + res->start = base_addr + ACPIBASE_SMI_OFF; + res->end = base_addr + ACPIBASE_SMI_END; + ret = acpi_check_resource_conflict(res); + if (ret) { + acpi_conflict = true; + goto wdt_done; + } + lpc_ich_enable_acpi_space(dev); + + /* + * Get the Memory-Mapped GCS register. To get access to it + * we have to read RCBA from PCI Config space 0xf0 and use + * it as base. GCS = RCBA + ICH6_GCS(0x3410). + */ + if (lpc_chipset_info[id->driver_data].iTCO_version == 2) { + pci_read_config_dword(dev, RCBABASE, &base_addr_cfg); + base_addr = base_addr_cfg & 0xffffc000; + if (!(base_addr_cfg & 1)) { + pr_err("RCBA is disabled by hardware/BIOS, " + "device disabled\n"); + ret = -ENODEV; + goto wdt_done; + } + res = wdt_mem_res(ICH_RES_MEM_GCS); + res->start = base_addr + ACPIBASE_GCS_OFF; + res->end = base_addr + ACPIBASE_GCS_END; + ret = acpi_check_resource_conflict(res); + if (ret) { + acpi_conflict = true; + goto wdt_done; + } + } + + lpc_ich_finalize_cell(&lpc_ich_cells[LPC_WDT], id); + ret = mfd_add_devices(&dev->dev, -1, &lpc_ich_cells[LPC_WDT], + 1, NULL, 0); + +wdt_done: + if (acpi_conflict) + pr_warn("Resource conflict(s) found affecting %s\n", + lpc_ich_cells[LPC_WDT].name); + return ret; +} + static int __devinit lpc_ich_probe(struct pci_dev *dev, const struct pci_device_id *id) { int ret; bool cell_added = false; + ret = lpc_ich_init_wdt(dev, id); + if (!ret) + cell_added = true; + ret = lpc_ich_init_gpio(dev, id); if (!ret) cell_added = true; diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 37096246c937..a9ed0878abfc 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -563,6 +563,7 @@ config INTEL_SCU_WATCHDOG config ITCO_WDT tristate "Intel TCO Timer/Watchdog" depends on (X86 || IA64) && PCI + select LPC_ICH ---help--- Hardware driver for the intel TCO timer based watchdog devices. These drivers are included in the Intel 82801 I/O Controller diff --git a/drivers/watchdog/iTCO_vendor.h b/drivers/watchdog/iTCO_vendor.h index 9e27e6422f66..3c57b45537a2 100644 --- a/drivers/watchdog/iTCO_vendor.h +++ b/drivers/watchdog/iTCO_vendor.h @@ -1,8 +1,8 @@ /* iTCO Vendor Specific Support hooks */ #ifdef CONFIG_ITCO_VENDOR_SUPPORT -extern void iTCO_vendor_pre_start(unsigned long, unsigned int); -extern void iTCO_vendor_pre_stop(unsigned long); -extern void iTCO_vendor_pre_keepalive(unsigned long, unsigned int); +extern void iTCO_vendor_pre_start(struct resource *, unsigned int); +extern void iTCO_vendor_pre_stop(struct resource *); +extern void iTCO_vendor_pre_keepalive(struct resource *, unsigned int); extern void iTCO_vendor_pre_set_heartbeat(unsigned int); extern int iTCO_vendor_check_noreboot_on(void); #else diff --git a/drivers/watchdog/iTCO_vendor_support.c b/drivers/watchdog/iTCO_vendor_support.c index 2721d29ce243..b6b2f90b5d44 100644 --- a/drivers/watchdog/iTCO_vendor_support.c +++ b/drivers/watchdog/iTCO_vendor_support.c @@ -35,11 +35,6 @@ #include "iTCO_vendor.h" -/* iTCO defines */ -#define SMI_EN (acpibase + 0x30) /* SMI Control and Enable Register */ -#define TCOBASE (acpibase + 0x60) /* TCO base address */ -#define TCO1_STS (TCOBASE + 0x04) /* TCO1 Status Register */ - /* List of vendor support modes */ /* SuperMicro Pentium 3 Era 370SSE+-OEM1/P3TSSE */ #define SUPERMICRO_OLD_BOARD 1 @@ -82,24 +77,24 @@ MODULE_PARM_DESC(vendorsupport, "iTCO vendor specific support mode, default=" * 20.6 seconds. */ -static void supermicro_old_pre_start(unsigned long acpibase) +static void supermicro_old_pre_start(struct resource *smires) { unsigned long val32; /* Bit 13: TCO_EN -> 0 = Disables TCO logic generating an SMI# */ - val32 = inl(SMI_EN); + val32 = inl(smires->start); val32 &= 0xffffdfff; /* Turn off SMI clearing watchdog */ - outl(val32, SMI_EN); /* Needed to activate watchdog */ + outl(val32, smires->start); /* Needed to activate watchdog */ } -static void supermicro_old_pre_stop(unsigned long acpibase) +static void supermicro_old_pre_stop(struct resource *smires) { unsigned long val32; /* Bit 13: TCO_EN -> 1 = Enables the TCO logic to generate SMI# */ - val32 = inl(SMI_EN); + val32 = inl(smires->start); val32 |= 0x00002000; /* Turn on SMI clearing watchdog */ - outl(val32, SMI_EN); /* Needed to deactivate watchdog */ + outl(val32, smires->start); /* Needed to deactivate watchdog */ } /* @@ -270,66 +265,66 @@ static void supermicro_new_pre_set_heartbeat(unsigned int heartbeat) * Don't use this fix if you don't need to!!! */ -static void broken_bios_start(unsigned long acpibase) +static void broken_bios_start(struct resource *smires) { unsigned long val32; - val32 = inl(SMI_EN); + val32 = inl(smires->start); /* Bit 13: TCO_EN -> 0 = Disables TCO logic generating an SMI# Bit 0: GBL_SMI_EN -> 0 = No SMI# will be generated by ICH. */ val32 &= 0xffffdffe; - outl(val32, SMI_EN); + outl(val32, smires->start); } -static void broken_bios_stop(unsigned long acpibase) +static void broken_bios_stop(struct resource *smires) { unsigned long val32; - val32 = inl(SMI_EN); + val32 = inl(smires->start); /* Bit 13: TCO_EN -> 1 = Enables TCO logic generating an SMI# Bit 0: GBL_SMI_EN -> 1 = Turn global SMI on again. */ val32 |= 0x00002001; - outl(val32, SMI_EN); + outl(val32, smires->start); } /* * Generic Support Functions */ -void iTCO_vendor_pre_start(unsigned long acpibase, +void iTCO_vendor_pre_start(struct resource *smires, unsigned int heartbeat) { switch (vendorsupport) { case SUPERMICRO_OLD_BOARD: - supermicro_old_pre_start(acpibase); + supermicro_old_pre_start(smires); break; case SUPERMICRO_NEW_BOARD: supermicro_new_pre_start(heartbeat); break; case BROKEN_BIOS: - broken_bios_start(acpibase); + broken_bios_start(smires); break; } } EXPORT_SYMBOL(iTCO_vendor_pre_start); -void iTCO_vendor_pre_stop(unsigned long acpibase) +void iTCO_vendor_pre_stop(struct resource *smires) { switch (vendorsupport) { case SUPERMICRO_OLD_BOARD: - supermicro_old_pre_stop(acpibase); + supermicro_old_pre_stop(smires); break; case SUPERMICRO_NEW_BOARD: supermicro_new_pre_stop(); break; case BROKEN_BIOS: - broken_bios_stop(acpibase); + broken_bios_stop(smires); break; } } EXPORT_SYMBOL(iTCO_vendor_pre_stop); -void iTCO_vendor_pre_keepalive(unsigned long acpibase, unsigned int heartbeat) +void iTCO_vendor_pre_keepalive(struct resource *smires, unsigned int heartbeat) { if (vendorsupport == SUPERMICRO_NEW_BOARD) supermicro_new_pre_set_heartbeat(heartbeat); diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c index 9fecb95645a3..741528b032e2 100644 --- a/drivers/watchdog/iTCO_wdt.c +++ b/drivers/watchdog/iTCO_wdt.c @@ -66,316 +66,16 @@ #include /* For spin_lock/spin_unlock/... */ #include /* For copy_to_user/put_user/... */ #include /* For inb/outb/... */ +#include +#include #include "iTCO_vendor.h" -/* TCO related info */ -enum iTCO_chipsets { - TCO_ICH = 0, /* ICH */ - TCO_ICH0, /* ICH0 */ - TCO_ICH2, /* ICH2 */ - TCO_ICH2M, /* ICH2-M */ - TCO_ICH3, /* ICH3-S */ - TCO_ICH3M, /* ICH3-M */ - TCO_ICH4, /* ICH4 */ - TCO_ICH4M, /* ICH4-M */ - TCO_CICH, /* C-ICH */ - TCO_ICH5, /* ICH5 & ICH5R */ - TCO_6300ESB, /* 6300ESB */ - TCO_ICH6, /* ICH6 & ICH6R */ - TCO_ICH6M, /* ICH6-M */ - TCO_ICH6W, /* ICH6W & ICH6RW */ - TCO_631XESB, /* 631xESB/632xESB */ - TCO_ICH7, /* ICH7 & ICH7R */ - TCO_ICH7DH, /* ICH7DH */ - TCO_ICH7M, /* ICH7-M & ICH7-U */ - TCO_ICH7MDH, /* ICH7-M DH */ - TCO_NM10, /* NM10 */ - TCO_ICH8, /* ICH8 & ICH8R */ - TCO_ICH8DH, /* ICH8DH */ - TCO_ICH8DO, /* ICH8DO */ - TCO_ICH8M, /* ICH8M */ - TCO_ICH8ME, /* ICH8M-E */ - TCO_ICH9, /* ICH9 */ - TCO_ICH9R, /* ICH9R */ - TCO_ICH9DH, /* ICH9DH */ - TCO_ICH9DO, /* ICH9DO */ - TCO_ICH9M, /* ICH9M */ - TCO_ICH9ME, /* ICH9M-E */ - TCO_ICH10, /* ICH10 */ - TCO_ICH10R, /* ICH10R */ - TCO_ICH10D, /* ICH10D */ - TCO_ICH10DO, /* ICH10DO */ - TCO_PCH, /* PCH Desktop Full Featured */ - TCO_PCHM, /* PCH Mobile Full Featured */ - TCO_P55, /* P55 */ - TCO_PM55, /* PM55 */ - TCO_H55, /* H55 */ - TCO_QM57, /* QM57 */ - TCO_H57, /* H57 */ - TCO_HM55, /* HM55 */ - TCO_Q57, /* Q57 */ - TCO_HM57, /* HM57 */ - TCO_PCHMSFF, /* PCH Mobile SFF Full Featured */ - TCO_QS57, /* QS57 */ - TCO_3400, /* 3400 */ - TCO_3420, /* 3420 */ - TCO_3450, /* 3450 */ - TCO_EP80579, /* EP80579 */ - TCO_CPT, /* Cougar Point */ - TCO_CPTD, /* Cougar Point Desktop */ - TCO_CPTM, /* Cougar Point Mobile */ - TCO_PBG, /* Patsburg */ - TCO_DH89XXCC, /* DH89xxCC */ - TCO_PPT, /* Panther Point */ - TCO_LPT, /* Lynx Point */ -}; - -static struct { - char *name; - unsigned int iTCO_version; -} iTCO_chipset_info[] __devinitdata = { - {"ICH", 1}, - {"ICH0", 1}, - {"ICH2", 1}, - {"ICH2-M", 1}, - {"ICH3-S", 1}, - {"ICH3-M", 1}, - {"ICH4", 1}, - {"ICH4-M", 1}, - {"C-ICH", 1}, - {"ICH5 or ICH5R", 1}, - {"6300ESB", 1}, - {"ICH6 or ICH6R", 2}, - {"ICH6-M", 2}, - {"ICH6W or ICH6RW", 2}, - {"631xESB/632xESB", 2}, - {"ICH7 or ICH7R", 2}, - {"ICH7DH", 2}, - {"ICH7-M or ICH7-U", 2}, - {"ICH7-M DH", 2}, - {"NM10", 2}, - {"ICH8 or ICH8R", 2}, - {"ICH8DH", 2}, - {"ICH8DO", 2}, - {"ICH8M", 2}, - {"ICH8M-E", 2}, - {"ICH9", 2}, - {"ICH9R", 2}, - {"ICH9DH", 2}, - {"ICH9DO", 2}, - {"ICH9M", 2}, - {"ICH9M-E", 2}, - {"ICH10", 2}, - {"ICH10R", 2}, - {"ICH10D", 2}, - {"ICH10DO", 2}, - {"PCH Desktop Full Featured", 2}, - {"PCH Mobile Full Featured", 2}, - {"P55", 2}, - {"PM55", 2}, - {"H55", 2}, - {"QM57", 2}, - {"H57", 2}, - {"HM55", 2}, - {"Q57", 2}, - {"HM57", 2}, - {"PCH Mobile SFF Full Featured", 2}, - {"QS57", 2}, - {"3400", 2}, - {"3420", 2}, - {"3450", 2}, - {"EP80579", 2}, - {"Cougar Point", 2}, - {"Cougar Point Desktop", 2}, - {"Cougar Point Mobile", 2}, - {"Patsburg", 2}, - {"DH89xxCC", 2}, - {"Panther Point", 2}, - {"Lynx Point", 2}, - {NULL, 0} -}; - -/* - * This data only exists for exporting the supported PCI ids - * via MODULE_DEVICE_TABLE. We do not actually register a - * pci_driver, because the I/O Controller Hub has also other - * functions that probably will be registered by other drivers. - */ -static DEFINE_PCI_DEVICE_TABLE(iTCO_wdt_pci_tbl) = { - { PCI_VDEVICE(INTEL, 0x2410), TCO_ICH}, - { PCI_VDEVICE(INTEL, 0x2420), TCO_ICH0}, - { PCI_VDEVICE(INTEL, 0x2440), TCO_ICH2}, - { PCI_VDEVICE(INTEL, 0x244c), TCO_ICH2M}, - { PCI_VDEVICE(INTEL, 0x2480), TCO_ICH3}, - { PCI_VDEVICE(INTEL, 0x248c), TCO_ICH3M}, - { PCI_VDEVICE(INTEL, 0x24c0), TCO_ICH4}, - { PCI_VDEVICE(INTEL, 0x24cc), TCO_ICH4M}, - { PCI_VDEVICE(INTEL, 0x2450), TCO_CICH}, - { PCI_VDEVICE(INTEL, 0x24d0), TCO_ICH5}, - { PCI_VDEVICE(INTEL, 0x25a1), TCO_6300ESB}, - { PCI_VDEVICE(INTEL, 0x2640), TCO_ICH6}, - { PCI_VDEVICE(INTEL, 0x2641), TCO_ICH6M}, - { PCI_VDEVICE(INTEL, 0x2642), TCO_ICH6W}, - { PCI_VDEVICE(INTEL, 0x2670), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2671), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2672), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2673), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2674), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2675), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2676), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2677), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2678), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x2679), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x267a), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x267b), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x267c), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x267d), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x267e), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x267f), TCO_631XESB}, - { PCI_VDEVICE(INTEL, 0x27b8), TCO_ICH7}, - { PCI_VDEVICE(INTEL, 0x27b0), TCO_ICH7DH}, - { PCI_VDEVICE(INTEL, 0x27b9), TCO_ICH7M}, - { PCI_VDEVICE(INTEL, 0x27bd), TCO_ICH7MDH}, - { PCI_VDEVICE(INTEL, 0x27bc), TCO_NM10}, - { PCI_VDEVICE(INTEL, 0x2810), TCO_ICH8}, - { PCI_VDEVICE(INTEL, 0x2812), TCO_ICH8DH}, - { PCI_VDEVICE(INTEL, 0x2814), TCO_ICH8DO}, - { PCI_VDEVICE(INTEL, 0x2815), TCO_ICH8M}, - { PCI_VDEVICE(INTEL, 0x2811), TCO_ICH8ME}, - { PCI_VDEVICE(INTEL, 0x2918), TCO_ICH9}, - { PCI_VDEVICE(INTEL, 0x2916), TCO_ICH9R}, - { PCI_VDEVICE(INTEL, 0x2912), TCO_ICH9DH}, - { PCI_VDEVICE(INTEL, 0x2914), TCO_ICH9DO}, - { PCI_VDEVICE(INTEL, 0x2919), TCO_ICH9M}, - { PCI_VDEVICE(INTEL, 0x2917), TCO_ICH9ME}, - { PCI_VDEVICE(INTEL, 0x3a18), TCO_ICH10}, - { PCI_VDEVICE(INTEL, 0x3a16), TCO_ICH10R}, - { PCI_VDEVICE(INTEL, 0x3a1a), TCO_ICH10D}, - { PCI_VDEVICE(INTEL, 0x3a14), TCO_ICH10DO}, - { PCI_VDEVICE(INTEL, 0x3b00), TCO_PCH}, - { PCI_VDEVICE(INTEL, 0x3b01), TCO_PCHM}, - { PCI_VDEVICE(INTEL, 0x3b02), TCO_P55}, - { PCI_VDEVICE(INTEL, 0x3b03), TCO_PM55}, - { PCI_VDEVICE(INTEL, 0x3b06), TCO_H55}, - { PCI_VDEVICE(INTEL, 0x3b07), TCO_QM57}, - { PCI_VDEVICE(INTEL, 0x3b08), TCO_H57}, - { PCI_VDEVICE(INTEL, 0x3b09), TCO_HM55}, - { PCI_VDEVICE(INTEL, 0x3b0a), TCO_Q57}, - { PCI_VDEVICE(INTEL, 0x3b0b), TCO_HM57}, - { PCI_VDEVICE(INTEL, 0x3b0d), TCO_PCHMSFF}, - { PCI_VDEVICE(INTEL, 0x3b0f), TCO_QS57}, - { PCI_VDEVICE(INTEL, 0x3b12), TCO_3400}, - { PCI_VDEVICE(INTEL, 0x3b14), TCO_3420}, - { PCI_VDEVICE(INTEL, 0x3b16), TCO_3450}, - { PCI_VDEVICE(INTEL, 0x5031), TCO_EP80579}, - { PCI_VDEVICE(INTEL, 0x1c41), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c42), TCO_CPTD}, - { PCI_VDEVICE(INTEL, 0x1c43), TCO_CPTM}, - { PCI_VDEVICE(INTEL, 0x1c44), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c45), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c46), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c47), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c48), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c49), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c4a), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c4b), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c4c), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c4d), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c4e), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c4f), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c50), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c51), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c52), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c53), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c54), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c55), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c56), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c57), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c58), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c59), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c5a), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c5b), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c5c), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c5d), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c5e), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1c5f), TCO_CPT}, - { PCI_VDEVICE(INTEL, 0x1d40), TCO_PBG}, - { PCI_VDEVICE(INTEL, 0x1d41), TCO_PBG}, - { PCI_VDEVICE(INTEL, 0x2310), TCO_DH89XXCC}, - { PCI_VDEVICE(INTEL, 0x1e40), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e41), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e42), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e43), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e44), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e45), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e46), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e47), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e48), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e49), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e4a), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e4b), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e4c), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e4d), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e4e), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e4f), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e50), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e51), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e52), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e53), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e54), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e55), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e56), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e57), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e58), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e59), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e5a), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e5b), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e5c), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e5d), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e5e), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x1e5f), TCO_PPT}, - { PCI_VDEVICE(INTEL, 0x8c40), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c41), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c42), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c43), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c44), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c45), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c46), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c47), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c48), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c49), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c4a), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c4b), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c4c), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c4d), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c4e), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c4f), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c50), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c51), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c52), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c53), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c54), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c55), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c56), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c57), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c58), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c59), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c5a), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c5b), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c5c), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c5d), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c5e), TCO_LPT}, - { PCI_VDEVICE(INTEL, 0x8c5f), TCO_LPT}, - { 0, }, /* End of list */ -}; -MODULE_DEVICE_TABLE(pci, iTCO_wdt_pci_tbl); - /* Address definitions for the TCO */ /* TCO base address */ -#define TCOBASE (iTCO_wdt_private.ACPIBASE + 0x60) +#define TCOBASE (iTCO_wdt_private.tco_res->start) /* SMI Control and Enable Register */ -#define SMI_EN (iTCO_wdt_private.ACPIBASE + 0x30) +#define SMI_EN (iTCO_wdt_private.smi_res->start) #define TCO_RLD (TCOBASE + 0x00) /* TCO Timer Reload and Curr. Value */ #define TCOv1_TMR (TCOBASE + 0x01) /* TCOv1 Timer Initial Value */ @@ -393,19 +93,18 @@ static char expect_release; static struct { /* this is private data for the iTCO_wdt device */ /* TCO version/generation */ unsigned int iTCO_version; - /* The device's ACPIBASE address (TCOBASE = ACPIBASE+0x60) */ - unsigned long ACPIBASE; + struct resource *tco_res; + struct resource *smi_res; + struct resource *gcs_res; /* NO_REBOOT flag is Memory-Mapped GCS register bit 5 (TCO version 2)*/ unsigned long __iomem *gcs; /* the lock for io operations */ spinlock_t io_lock; + struct platform_device *dev; /* the PCI-device */ struct pci_dev *pdev; } iTCO_wdt_private; -/* the watchdog platform device */ -static struct platform_device *iTCO_wdt_platform_device; - /* module parameters */ #define WATCHDOG_HEARTBEAT 30 /* 30 sec default heartbeat */ static int heartbeat = WATCHDOG_HEARTBEAT; /* in seconds */ @@ -485,7 +184,7 @@ static int iTCO_wdt_start(void) spin_lock(&iTCO_wdt_private.io_lock); - iTCO_vendor_pre_start(iTCO_wdt_private.ACPIBASE, heartbeat); + iTCO_vendor_pre_start(iTCO_wdt_private.smi_res, heartbeat); /* disable chipset's NO_REBOOT bit */ if (iTCO_wdt_unset_NO_REBOOT_bit()) { @@ -519,7 +218,7 @@ static int iTCO_wdt_stop(void) spin_lock(&iTCO_wdt_private.io_lock); - iTCO_vendor_pre_stop(iTCO_wdt_private.ACPIBASE); + iTCO_vendor_pre_stop(iTCO_wdt_private.smi_res); /* Bit 11: TCO Timer Halt -> 1 = The TCO timer is disabled */ val = inw(TCO1_CNT); @@ -541,7 +240,7 @@ static int iTCO_wdt_keepalive(void) { spin_lock(&iTCO_wdt_private.io_lock); - iTCO_vendor_pre_keepalive(iTCO_wdt_private.ACPIBASE, heartbeat); + iTCO_vendor_pre_keepalive(iTCO_wdt_private.smi_res, heartbeat); /* Reload the timer by writing to the TCO Timer Counter register */ if (iTCO_wdt_private.iTCO_version == 2) @@ -786,83 +485,120 @@ static struct miscdevice iTCO_wdt_miscdev = { * Init & exit routines */ -static int __devinit iTCO_wdt_init(struct pci_dev *pdev, - const struct pci_device_id *ent, struct platform_device *dev) +static void __devexit iTCO_wdt_cleanup(void) +{ + /* Stop the timer before we leave */ + if (!nowayout) + iTCO_wdt_stop(); + + /* Deregister */ + misc_deregister(&iTCO_wdt_miscdev); + + /* release resources */ + release_region(iTCO_wdt_private.tco_res->start, + resource_size(iTCO_wdt_private.tco_res)); + release_region(iTCO_wdt_private.smi_res->start, + resource_size(iTCO_wdt_private.smi_res)); + if (iTCO_wdt_private.iTCO_version == 2) { + iounmap(iTCO_wdt_private.gcs); + release_mem_region(iTCO_wdt_private.gcs_res->start, + resource_size(iTCO_wdt_private.gcs_res)); + } + + iTCO_wdt_private.tco_res = NULL; + iTCO_wdt_private.smi_res = NULL; + iTCO_wdt_private.gcs_res = NULL; + iTCO_wdt_private.gcs = NULL; +} + +static int __devinit iTCO_wdt_probe(struct platform_device *dev) { - int ret; - u32 base_address; - unsigned long RCBA; + int ret = -ENODEV; unsigned long val32; + struct lpc_ich_info *ich_info = dev->dev.platform_data; + + if (!ich_info) + goto out; + + spin_lock_init(&iTCO_wdt_private.io_lock); + + iTCO_wdt_private.tco_res = + platform_get_resource(dev, IORESOURCE_IO, ICH_RES_IO_TCO); + if (!iTCO_wdt_private.tco_res) + goto out; + + iTCO_wdt_private.smi_res = + platform_get_resource(dev, IORESOURCE_IO, ICH_RES_IO_SMI); + if (!iTCO_wdt_private.smi_res) + goto out; + + iTCO_wdt_private.iTCO_version = ich_info->iTCO_version; + iTCO_wdt_private.dev = dev; + iTCO_wdt_private.pdev = to_pci_dev(dev->dev.parent); /* - * Find the ACPI/PM base I/O address which is the base - * for the TCO registers (TCOBASE=ACPIBASE + 0x60) - * ACPIBASE is bits [15:7] from 0x40-0x43 + * Get the Memory-Mapped GCS register, we need it for the + * NO_REBOOT flag (TCO v2). */ - pci_read_config_dword(pdev, 0x40, &base_address); - base_address &= 0x0000ff80; - if (base_address == 0x00000000) { - /* Something's wrong here, ACPIBASE has to be set */ - pr_err("failed to get TCOBASE address, device disabled by hardware/BIOS\n"); - return -ENODEV; - } - iTCO_wdt_private.iTCO_version = - iTCO_chipset_info[ent->driver_data].iTCO_version; - iTCO_wdt_private.ACPIBASE = base_address; - iTCO_wdt_private.pdev = pdev; - - /* Get the Memory-Mapped GCS register, we need it for the - NO_REBOOT flag (TCO v2). To get access to it you have to - read RCBA from PCI Config space 0xf0 and use it as base. - GCS = RCBA + ICH6_GCS(0x3410). */ if (iTCO_wdt_private.iTCO_version == 2) { - pci_read_config_dword(pdev, 0xf0, &base_address); - if ((base_address & 1) == 0) { - pr_err("RCBA is disabled by hardware/BIOS, device disabled\n"); - ret = -ENODEV; + iTCO_wdt_private.gcs_res = platform_get_resource(dev, + IORESOURCE_MEM, + ICH_RES_MEM_GCS); + + if (!iTCO_wdt_private.gcs_res) + goto out; + + if (!request_mem_region(iTCO_wdt_private.gcs_res->start, + resource_size(iTCO_wdt_private.gcs_res), dev->name)) { + ret = -EBUSY; goto out; } - RCBA = base_address & 0xffffc000; - iTCO_wdt_private.gcs = ioremap((RCBA + 0x3410), 4); + iTCO_wdt_private.gcs = ioremap(iTCO_wdt_private.gcs_res->start, + resource_size(iTCO_wdt_private.gcs_res)); + if (!iTCO_wdt_private.gcs) { + ret = -EIO; + goto unreg_gcs; + } } /* Check chipset's NO_REBOOT bit */ if (iTCO_wdt_unset_NO_REBOOT_bit() && iTCO_vendor_check_noreboot_on()) { pr_info("unable to reset NO_REBOOT flag, device disabled by hardware/BIOS\n"); ret = -ENODEV; /* Cannot reset NO_REBOOT bit */ - goto out_unmap; + goto unmap_gcs; } /* Set the NO_REBOOT bit to prevent later reboots, just for sure */ iTCO_wdt_set_NO_REBOOT_bit(); /* The TCO logic uses the TCO_EN bit in the SMI_EN register */ - if (!request_region(SMI_EN, 4, "iTCO_wdt")) { - pr_err("I/O address 0x%04lx already in use, device disabled\n", + if (!request_region(iTCO_wdt_private.smi_res->start, + resource_size(iTCO_wdt_private.smi_res), dev->name)) { + pr_err("I/O address 0x%04llx already in use, device disabled\n", SMI_EN); - ret = -EIO; - goto out_unmap; + ret = -EBUSY; + goto unmap_gcs; } if (turn_SMI_watchdog_clear_off >= iTCO_wdt_private.iTCO_version) { - /* Bit 13: TCO_EN -> 0 = Disables TCO logic generating an SMI# */ + /* + * Bit 13: TCO_EN -> 0 + * Disables TCO logic generating an SMI# + */ val32 = inl(SMI_EN); val32 &= 0xffffdfff; /* Turn off SMI clearing watchdog */ outl(val32, SMI_EN); } - /* The TCO I/O registers reside in a 32-byte range pointed to - by the TCOBASE value */ - if (!request_region(TCOBASE, 0x20, "iTCO_wdt")) { - pr_err("I/O address 0x%04lx already in use, device disabled\n", + if (!request_region(iTCO_wdt_private.tco_res->start, + resource_size(iTCO_wdt_private.tco_res), dev->name)) { + pr_err("I/O address 0x%04llx already in use, device disabled\n", TCOBASE); - ret = -EIO; - goto unreg_smi_en; + ret = -EBUSY; + goto unreg_smi; } - pr_info("Found a %s TCO device (Version=%d, TCOBASE=0x%04lx)\n", - iTCO_chipset_info[ent->driver_data].name, - iTCO_chipset_info[ent->driver_data].iTCO_version, - TCOBASE); + pr_info("Found a %s TCO device (Version=%d, TCOBASE=0x%04llx)\n", + ich_info->name, ich_info->iTCO_version, TCOBASE); /* Clear out the (probably old) status */ outw(0x0008, TCO1_STS); /* Clear the Time Out Status bit */ @@ -883,7 +619,7 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev, if (ret != 0) { pr_err("cannot register miscdev on minor=%d (err=%d)\n", WATCHDOG_MINOR, ret); - goto unreg_region; + goto unreg_tco; } pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n", @@ -891,62 +627,31 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev, return 0; -unreg_region: - release_region(TCOBASE, 0x20); -unreg_smi_en: - release_region(SMI_EN, 4); -out_unmap: +unreg_tco: + release_region(iTCO_wdt_private.tco_res->start, + resource_size(iTCO_wdt_private.tco_res)); +unreg_smi: + release_region(iTCO_wdt_private.smi_res->start, + resource_size(iTCO_wdt_private.smi_res)); +unmap_gcs: if (iTCO_wdt_private.iTCO_version == 2) iounmap(iTCO_wdt_private.gcs); -out: - iTCO_wdt_private.ACPIBASE = 0; - return ret; -} - -static void __devexit iTCO_wdt_cleanup(void) -{ - /* Stop the timer before we leave */ - if (!nowayout) - iTCO_wdt_stop(); - - /* Deregister */ - misc_deregister(&iTCO_wdt_miscdev); - release_region(TCOBASE, 0x20); - release_region(SMI_EN, 4); +unreg_gcs: if (iTCO_wdt_private.iTCO_version == 2) - iounmap(iTCO_wdt_private.gcs); - pci_dev_put(iTCO_wdt_private.pdev); - iTCO_wdt_private.ACPIBASE = 0; -} - -static int __devinit iTCO_wdt_probe(struct platform_device *dev) -{ - int ret = -ENODEV; - int found = 0; - struct pci_dev *pdev = NULL; - const struct pci_device_id *ent; - - spin_lock_init(&iTCO_wdt_private.io_lock); - - for_each_pci_dev(pdev) { - ent = pci_match_id(iTCO_wdt_pci_tbl, pdev); - if (ent) { - found++; - ret = iTCO_wdt_init(pdev, ent, dev); - if (!ret) - break; - } - } - - if (!found) - pr_info("No device detected\n"); + release_mem_region(iTCO_wdt_private.gcs_res->start, + resource_size(iTCO_wdt_private.gcs_res)); +out: + iTCO_wdt_private.tco_res = NULL; + iTCO_wdt_private.smi_res = NULL; + iTCO_wdt_private.gcs_res = NULL; + iTCO_wdt_private.gcs = NULL; return ret; } static int __devexit iTCO_wdt_remove(struct platform_device *dev) { - if (iTCO_wdt_private.ACPIBASE) + if (iTCO_wdt_private.tco_res || iTCO_wdt_private.smi_res) iTCO_wdt_cleanup(); return 0; @@ -977,23 +682,11 @@ static int __init iTCO_wdt_init_module(void) if (err) return err; - iTCO_wdt_platform_device = platform_device_register_simple(DRV_NAME, - -1, NULL, 0); - if (IS_ERR(iTCO_wdt_platform_device)) { - err = PTR_ERR(iTCO_wdt_platform_device); - goto unreg_platform_driver; - } - return 0; - -unreg_platform_driver: - platform_driver_unregister(&iTCO_wdt_driver); - return err; } static void __exit iTCO_wdt_cleanup_module(void) { - platform_device_unregister(iTCO_wdt_platform_device); platform_driver_unregister(&iTCO_wdt_driver); pr_info("Watchdog Module Unloaded\n"); } diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h index 91300b18219b..fec5256c3f5d 100644 --- a/include/linux/mfd/lpc_ich.h +++ b/include/linux/mfd/lpc_ich.h @@ -20,6 +20,12 @@ #ifndef LPC_ICH_H #define LPC_ICH_H +/* Watchdog resources */ +#define ICH_RES_IO_TCO 0 +#define ICH_RES_IO_SMI 1 +#define ICH_RES_MEM_OFF 2 +#define ICH_RES_MEM_GCS 0 + /* GPIO resources */ #define ICH_RES_GPIO 0 #define ICH_RES_GPE0 1 @@ -35,6 +41,7 @@ struct lpc_ich_info { char name[32]; + unsigned int iTCO_version; unsigned int gpio_version; }; -- cgit v1.2.3 From 1379f49ea91a28f5c023d041aab785c3de60c65d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 23 Apr 2012 14:28:44 +0200 Subject: mfd: Allow for const stmpe keyboard data Since it's not like we will re-arrange the keys at run-time, it seems proper to allow the keymap data to be const. This solves a compilation warning in ux500. Cc: Dmitry Torokhov Signed-off-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/stmpe.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index 8516fd1eaabc..f8d5b4d5843f 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -117,7 +117,7 @@ struct matrix_keymap_data; * @no_autorepeat: disable key autorepeat */ struct stmpe_keypad_platform_data { - struct matrix_keymap_data *keymap_data; + const struct matrix_keymap_data *keymap_data; unsigned int debounce_ms; unsigned int scan_count; bool no_autorepeat; -- cgit v1.2.3 From 3aff4ebb95b20ad8db2c1447e8c52097d89af5a7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 May 2012 14:30:35 -0400 Subject: NFS: Prevent a deadlock in the new writeback code We have to unlock the nfs_page before we call nfs_end_page_writeback to avoid races with functions that expect the page to be unlocked when PG_locked and PG_writeback are not set. The problem is that nfs_unlock_request also releases the nfs_page, causing a deadlock if the release of the nfs_open_context triggers an iput() while the PG_writeback flag is still set... The solution is to separate the unlocking and release of the nfs_page, so that we can do the former before nfs_end_page_writeback and the latter after. Signed-off-by: Trond Myklebust Cc: Fred Isaman --- fs/nfs/pagelist.c | 12 ++++++++++-- fs/nfs/write.c | 6 ++++-- include/linux/nfs_page.h | 1 + 3 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 33a21ca9b84b..69146f386989 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -128,10 +128,10 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, } /** - * nfs_unlock_request - Unlock request and wake up sleepers. + * nfs_unlock_request_dont_release - Unlock request and wake up sleepers. * @req: */ -void nfs_unlock_request(struct nfs_page *req) +void nfs_unlock_request_dont_release(struct nfs_page *req) { if (!NFS_WBACK_BUSY(req)) { printk(KERN_ERR "NFS: Invalid unlock attempted\n"); @@ -141,6 +141,14 @@ void nfs_unlock_request(struct nfs_page *req) clear_bit(PG_BUSY, &req->wb_flags); smp_mb__after_clear_bit(); wake_up_bit(&req->wb_flags, PG_BUSY); +} + +/** + * nfs_unlock_request - Unlock request and release the nfs_page + */ +void nfs_unlock_request(struct nfs_page *req) +{ + nfs_unlock_request_dont_release(req); nfs_release_request(req); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 6f263daac748..fd36b31ee72e 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -628,8 +628,9 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) remove_req: nfs_inode_remove_request(req); next: - nfs_unlock_request(req); + nfs_unlock_request_dont_release(req); nfs_end_page_writeback(page); + nfs_release_request(req); } out: hdr->release(hdr); @@ -1042,8 +1043,9 @@ static void nfs_redirty_request(struct nfs_page *req) struct page *page = req->wb_page; nfs_mark_request_dirty(req); - nfs_unlock_request(req); + nfs_unlock_request_dont_release(req); nfs_end_page_writeback(page); + nfs_release_request(req); } static void nfs_async_write_error(struct list_head *head) diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index f9ee9eba7f88..ef7504215446 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -96,6 +96,7 @@ extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *req); extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); +extern void nfs_unlock_request_dont_release(struct nfs_page *req); /* * Lock the page of an asynchronous request without getting a new reference -- cgit v1.2.3 From 7ad84aa9448571678c243f0c5ef383fbe5b50f4f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 May 2012 13:19:15 -0400 Subject: NFS: Clean up - simplify nfs_lock_request() We only have two places where we need to grab a reference when trying to lock the nfs_page. We're better off making that explicit. Signed-off-by: Trond Myklebust Cc: Fred Isaman --- fs/nfs/direct.c | 1 + fs/nfs/write.c | 11 ++++++----- include/linux/nfs_page.h | 14 ++------------ 3 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 257d0091148b..465ea84a2874 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -657,6 +657,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d break; } nfs_lock_request(req); + kref_get(&req->wb_kref); req->wb_index = pos >> PAGE_SHIFT; req->wb_offset = pos & ~PAGE_MASK; if (!nfs_pageio_add_request(desc, req)) { diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 83823294ffd2..553f7ef1079b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -260,10 +260,10 @@ static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblo req = nfs_page_find_request_locked(page); if (req == NULL) break; - if (nfs_lock_request_dontget(req)) + if (nfs_lock_request(req)) break; /* Note: If we hold the page lock, as is the case in nfs_writepage, - * then the call to nfs_lock_request_dontget() will always + * then the call to nfs_lock_request() will always * succeed provided that someone hasn't already marked the * request as dirty (in which case we don't care). */ @@ -406,7 +406,7 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) struct nfs_inode *nfsi = NFS_I(inode); /* Lock the request! */ - nfs_lock_request_dontget(req); + nfs_lock_request(req); spin_lock(&inode->i_lock); if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE)) @@ -651,6 +651,7 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, list_for_each_entry_safe(req, tmp, src, wb_list) { if (!nfs_lock_request(req)) continue; + kref_get(&req->wb_kref); if (cond_resched_lock(cinfo->lock)) list_safe_reset_next(req, tmp, wb_list); nfs_request_remove_commit_list(req, cinfo); @@ -741,7 +742,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, || end < req->wb_offset) goto out_flushme; - if (nfs_lock_request_dontget(req)) + if (nfs_lock_request(req)) break; /* The request is locked, so wait and then retry */ @@ -1717,7 +1718,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) req = nfs_page_find_request(page); if (req == NULL) break; - if (nfs_lock_request_dontget(req)) { + if (nfs_lock_request(req)) { nfs_clear_request_commit(req); nfs_inode_remove_request(req); /* diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index ef7504215446..263f30a5e10d 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -99,24 +99,14 @@ extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_request_dont_release(struct nfs_page *req); /* - * Lock the page of an asynchronous request without getting a new reference + * Lock the page of an asynchronous request */ -static inline int -nfs_lock_request_dontget(struct nfs_page *req) -{ - return !test_and_set_bit(PG_BUSY, &req->wb_flags); -} - static inline int nfs_lock_request(struct nfs_page *req) { - if (test_and_set_bit(PG_BUSY, &req->wb_flags)) - return 0; - kref_get(&req->wb_kref); - return 1; + return !test_and_set_bit(PG_BUSY, &req->wb_flags); } - /** * nfs_list_add_request - Insert a request into a list * @req: request -- cgit v1.2.3 From 1d1afcbc294cc7c788eb5c7b6b98e8d63caf002c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 May 2012 14:04:55 -0400 Subject: NFS: Clean up - Rename nfs_unlock_request and nfs_unlock_request_dont_release Function rename to ensure that the functionality of nfs_unlock_request() mirrors that of nfs_lock_request(). Then let nfs_unlock_and_release_request() do the work of what used to be called nfs_unlock_request()... Signed-off-by: Trond Myklebust Cc: Fred Isaman --- fs/nfs/direct.c | 10 +++++----- fs/nfs/pagelist.c | 11 ++++++----- fs/nfs/write.c | 12 ++++++------ include/linux/nfs_page.h | 2 +- 4 files changed, 18 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 465ea84a2874..845e20196803 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -488,7 +488,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) while (!list_empty(&failed)) { nfs_release_request(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } if (put_dreq(dreq)) @@ -521,7 +521,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_mark_request_commit(req, NULL, &cinfo); } else nfs_release_request(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) @@ -662,7 +662,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d req->wb_offset = pos & ~PAGE_MASK; if (!nfs_pageio_add_request(desc, req)) { result = desc->pg_error; - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); nfs_release_request(req); break; } @@ -739,7 +739,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) default: nfs_release_request(req); } - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } out_put: @@ -756,7 +756,7 @@ static void nfs_write_sync_pgio_error(struct list_head *head) req = nfs_list_entry(head->next); nfs_list_remove_request(req); nfs_release_request(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 69146f386989..aed913c833f4 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -128,10 +128,10 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, } /** - * nfs_unlock_request_dont_release - Unlock request and wake up sleepers. + * nfs_unlock_request - Unlock request and wake up sleepers. * @req: */ -void nfs_unlock_request_dont_release(struct nfs_page *req) +void nfs_unlock_request(struct nfs_page *req) { if (!NFS_WBACK_BUSY(req)) { printk(KERN_ERR "NFS: Invalid unlock attempted\n"); @@ -144,11 +144,12 @@ void nfs_unlock_request_dont_release(struct nfs_page *req) } /** - * nfs_unlock_request - Unlock request and release the nfs_page + * nfs_unlock_and_release_request - Unlock request and release the nfs_page + * @req: */ -void nfs_unlock_request(struct nfs_page *req) +void nfs_unlock_and_release_request(struct nfs_page *req) { - nfs_unlock_request_dont_release(req); + nfs_unlock_request(req); nfs_release_request(req); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 553f7ef1079b..8ffd7d5ed58b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -625,7 +625,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) remove_req: nfs_inode_remove_request(req); next: - nfs_unlock_request_dont_release(req); + nfs_unlock_request(req); nfs_end_page_writeback(req->wb_page); nfs_release_request(req); } @@ -812,7 +812,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page, nfs_grow_file(page, offset, count); nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes); nfs_mark_request_dirty(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); return 0; } @@ -1039,7 +1039,7 @@ static int nfs_do_multiple_writes(struct list_head *head, static void nfs_redirty_request(struct nfs_page *req) { nfs_mark_request_dirty(req); - nfs_unlock_request_dont_release(req); + nfs_unlock_request(req); nfs_end_page_writeback(req->wb_page); nfs_release_request(req); } @@ -1477,7 +1477,7 @@ void nfs_retry_commit(struct list_head *page_list, dec_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE); } - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } } EXPORT_SYMBOL_GPL(nfs_retry_commit); @@ -1555,7 +1555,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) dprintk(" mismatch\n"); nfs_mark_request_dirty(req); next: - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } nfs_init_cinfo(&cinfo, data->inode, data->dreq); if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) @@ -1726,7 +1726,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) * page as being dirty */ cancel_dirty_page(page, PAGE_CACHE_SIZE); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); break; } ret = nfs_wait_on_request(req); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 263f30a5e10d..88d166b555e8 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -96,7 +96,7 @@ extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *req); extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); -extern void nfs_unlock_request_dont_release(struct nfs_page *req); +extern void nfs_unlock_and_release_request(struct nfs_page *req); /* * Lock the page of an asynchronous request -- cgit v1.2.3 From 5af7df6b831ef9fd5fbde9d4bbd596f742cb2ad8 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 2 May 2012 16:54:42 +0300 Subject: mfd: Add regulator support for twl6040 VIO, V2V1 supplies twl6040 has three power supply source: VBAT needs to be connected to VBAT, VIO, and V2V1. Add regulator support for the VIO, V2V1 supplies. Initially handle the two supply together with bulk commands. Signed-off-by: Peter Ujfalusi Reviewed-by: Mark Brown Signed-off-by: Tero Kristo Signed-off-by: Samuel Ortiz --- drivers/mfd/twl6040-core.c | 33 +++++++++++++++++++++++++++++---- include/linux/mfd/twl6040.h | 2 ++ 2 files changed, 31 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/twl6040-core.c b/drivers/mfd/twl6040-core.c index 493f4a692747..7a92d95bfb60 100644 --- a/drivers/mfd/twl6040-core.c +++ b/drivers/mfd/twl6040-core.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -35,8 +36,10 @@ #include #include #include +#include #define VIBRACTRL_MEMBER(reg) ((reg == TWL6040_REG_VIBCTLL) ? 0 : 1) +#define TWL6040_NUM_SUPPLIES (2) int twl6040_reg_read(struct twl6040 *twl6040, unsigned int reg) { @@ -532,6 +535,21 @@ static int __devinit twl6040_probe(struct i2c_client *client, i2c_set_clientdata(client, twl6040); + twl6040->supplies[0].supply = "vio"; + twl6040->supplies[1].supply = "v2v1"; + ret = regulator_bulk_get(&client->dev, TWL6040_NUM_SUPPLIES, + twl6040->supplies); + if (ret != 0) { + dev_err(&client->dev, "Failed to get supplies: %d\n", ret); + goto regulator_get_err; + } + + ret = regulator_bulk_enable(TWL6040_NUM_SUPPLIES, twl6040->supplies); + if (ret != 0) { + dev_err(&client->dev, "Failed to enable supplies: %d\n", ret); + goto power_err; + } + twl6040->dev = &client->dev; twl6040->irq = client->irq; twl6040->irq_base = pdata->irq_base; @@ -552,13 +570,13 @@ static int __devinit twl6040_probe(struct i2c_client *client, ret = gpio_request_one(twl6040->audpwron, GPIOF_OUT_INIT_LOW, "audpwron"); if (ret) - goto gpio1_err; + goto gpio_err; } /* codec interrupt */ ret = twl6040_irq_init(twl6040); if (ret) - goto gpio2_err; + goto irq_init_err; ret = request_threaded_irq(twl6040->irq_base + TWL6040_IRQ_READY, NULL, twl6040_naudint_handler, 0, @@ -618,10 +636,14 @@ mfd_err: free_irq(twl6040->irq_base + TWL6040_IRQ_READY, twl6040); irq_err: twl6040_irq_exit(twl6040); -gpio2_err: +irq_init_err: if (gpio_is_valid(twl6040->audpwron)) gpio_free(twl6040->audpwron); -gpio1_err: +gpio_err: + regulator_bulk_disable(TWL6040_NUM_SUPPLIES, twl6040->supplies); +power_err: + regulator_bulk_free(TWL6040_NUM_SUPPLIES, twl6040->supplies); +regulator_get_err: i2c_set_clientdata(client, NULL); err: return ret; @@ -643,6 +665,9 @@ static int __devexit twl6040_remove(struct i2c_client *client) mfd_remove_devices(&client->dev); i2c_set_clientdata(client, NULL); + regulator_bulk_disable(TWL6040_NUM_SUPPLIES, twl6040->supplies); + regulator_bulk_free(TWL6040_NUM_SUPPLIES, twl6040->supplies); + return 0; } diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h index b15b5f03f5c4..6659487c31e7 100644 --- a/include/linux/mfd/twl6040.h +++ b/include/linux/mfd/twl6040.h @@ -27,6 +27,7 @@ #include #include +#include #define TWL6040_REG_ASICID 0x01 #define TWL6040_REG_ASICREV 0x02 @@ -203,6 +204,7 @@ struct regmap; struct twl6040 { struct device *dev; struct regmap *regmap; + struct regulator_bulk_data supplies[2]; /* supplies for vio, v2v1 */ struct mutex mutex; struct mutex io_mutex; struct mutex irq_mutex; -- cgit v1.2.3 From 3f7e82759c692df473675ed06fb90b20f1f225c3 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Tue, 8 May 2012 11:42:38 -0700 Subject: mfd: Commonize tps65910 regmap access through header This change removes the read/write callback functions in favor of common regmap accessors inside the header file. This change also makes use of regmap_read/write for single register access which maps better onto what this driver actually needs. Signed-off-by: Rhyland Klein Signed-off-by: Samuel Ortiz --- drivers/gpio/gpio-tps65910.c | 14 +++--- drivers/mfd/tps65910-irq.c | 34 ++++++------- drivers/mfd/tps65910.c | 40 ++++------------ drivers/regulator/tps65910-regulator.c | 88 ++++++++++++++++------------------ include/linux/mfd/tps65910.h | 29 +++++++++-- 5 files changed, 100 insertions(+), 105 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-tps65910.c b/drivers/gpio/gpio-tps65910.c index 7eef648a3351..bc155f2509ba 100644 --- a/drivers/gpio/gpio-tps65910.c +++ b/drivers/gpio/gpio-tps65910.c @@ -23,9 +23,9 @@ static int tps65910_gpio_get(struct gpio_chip *gc, unsigned offset) { struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio); - uint8_t val; + unsigned int val; - tps65910->read(tps65910, TPS65910_GPIO0 + offset, 1, &val); + tps65910_reg_read(tps65910, TPS65910_GPIO0 + offset, &val); if (val & GPIO_STS_MASK) return 1; @@ -39,10 +39,10 @@ static void tps65910_gpio_set(struct gpio_chip *gc, unsigned offset, struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio); if (value) - tps65910_set_bits(tps65910, TPS65910_GPIO0 + offset, + tps65910_reg_set_bits(tps65910, TPS65910_GPIO0 + offset, GPIO_SET_MASK); else - tps65910_clear_bits(tps65910, TPS65910_GPIO0 + offset, + tps65910_reg_clear_bits(tps65910, TPS65910_GPIO0 + offset, GPIO_SET_MASK); } @@ -54,7 +54,7 @@ static int tps65910_gpio_output(struct gpio_chip *gc, unsigned offset, /* Set the initial value */ tps65910_gpio_set(gc, offset, value); - return tps65910_set_bits(tps65910, TPS65910_GPIO0 + offset, + return tps65910_reg_set_bits(tps65910, TPS65910_GPIO0 + offset, GPIO_CFG_MASK); } @@ -62,7 +62,7 @@ static int tps65910_gpio_input(struct gpio_chip *gc, unsigned offset) { struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio); - return tps65910_clear_bits(tps65910, TPS65910_GPIO0 + offset, + return tps65910_reg_clear_bits(tps65910, TPS65910_GPIO0 + offset, GPIO_CFG_MASK); } @@ -102,7 +102,7 @@ void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base) int i; for (i = 0; i < tps65910->gpio.ngpio; ++i) { if (board_data->en_gpio_sleep[i]) { - ret = tps65910_set_bits(tps65910, + ret = tps65910_reg_set_bits(tps65910, TPS65910_GPIO0 + i, GPIO_SLEEP_MASK); if (ret < 0) dev_warn(tps65910->dev, diff --git a/drivers/mfd/tps65910-irq.c b/drivers/mfd/tps65910-irq.c index c9ed5c00a621..0f1ff7fbdc74 100644 --- a/drivers/mfd/tps65910-irq.c +++ b/drivers/mfd/tps65910-irq.c @@ -41,28 +41,28 @@ static inline int irq_to_tps65910_irq(struct tps65910 *tps65910, static irqreturn_t tps65910_irq(int irq, void *irq_data) { struct tps65910 *tps65910 = irq_data; + unsigned int reg; u32 irq_sts; u32 irq_mask; - u8 reg; int i; - tps65910->read(tps65910, TPS65910_INT_STS, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_STS, ®); irq_sts = reg; - tps65910->read(tps65910, TPS65910_INT_STS2, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_STS2, ®); irq_sts |= reg << 8; switch (tps65910_chip_id(tps65910)) { case TPS65911: - tps65910->read(tps65910, TPS65910_INT_STS3, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_STS3, ®); irq_sts |= reg << 16; } - tps65910->read(tps65910, TPS65910_INT_MSK, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_MSK, ®); irq_mask = reg; - tps65910->read(tps65910, TPS65910_INT_MSK2, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_MSK2, ®); irq_mask |= reg << 8; switch (tps65910_chip_id(tps65910)) { case TPS65911: - tps65910->read(tps65910, TPS65910_INT_MSK3, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_MSK3, ®); irq_mask |= reg << 16; } @@ -82,13 +82,13 @@ static irqreturn_t tps65910_irq(int irq, void *irq_data) /* Write the STS register back to clear IRQs we handled */ reg = irq_sts & 0xFF; irq_sts >>= 8; - tps65910->write(tps65910, TPS65910_INT_STS, 1, ®); + tps65910_reg_write(tps65910, TPS65910_INT_STS, reg); reg = irq_sts & 0xFF; - tps65910->write(tps65910, TPS65910_INT_STS2, 1, ®); + tps65910_reg_write(tps65910, TPS65910_INT_STS2, reg); switch (tps65910_chip_id(tps65910)) { case TPS65911: reg = irq_sts >> 8; - tps65910->write(tps65910, TPS65910_INT_STS3, 1, ®); + tps65910_reg_write(tps65910, TPS65910_INT_STS3, reg); } return IRQ_HANDLED; @@ -105,27 +105,27 @@ static void tps65910_irq_sync_unlock(struct irq_data *data) { struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data); u32 reg_mask; - u8 reg; + unsigned int reg; - tps65910->read(tps65910, TPS65910_INT_MSK, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_MSK, ®); reg_mask = reg; - tps65910->read(tps65910, TPS65910_INT_MSK2, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_MSK2, ®); reg_mask |= reg << 8; switch (tps65910_chip_id(tps65910)) { case TPS65911: - tps65910->read(tps65910, TPS65910_INT_MSK3, 1, ®); + tps65910_reg_read(tps65910, TPS65910_INT_MSK3, ®); reg_mask |= reg << 16; } if (tps65910->irq_mask != reg_mask) { reg = tps65910->irq_mask & 0xFF; - tps65910->write(tps65910, TPS65910_INT_MSK, 1, ®); + tps65910_reg_write(tps65910, TPS65910_INT_MSK, reg); reg = tps65910->irq_mask >> 8 & 0xFF; - tps65910->write(tps65910, TPS65910_INT_MSK2, 1, ®); + tps65910_reg_write(tps65910, TPS65910_INT_MSK2, reg); switch (tps65910_chip_id(tps65910)) { case TPS65911: reg = tps65910->irq_mask >> 16; - tps65910->write(tps65910, TPS65910_INT_MSK3, 1, ®); + tps65910_reg_write(tps65910, TPS65910_INT_MSK3, reg); } } mutex_unlock(&tps65910->irq_lock); diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c index 7a55af921e25..7dffbe1a50c6 100644 --- a/drivers/mfd/tps65910.c +++ b/drivers/mfd/tps65910.c @@ -37,30 +37,6 @@ static struct mfd_cell tps65910s[] = { }; -static int tps65910_i2c_read(struct tps65910 *tps65910, u8 reg, - int bytes, void *dest) -{ - return regmap_bulk_read(tps65910->regmap, reg, dest, bytes); -} - -static int tps65910_i2c_write(struct tps65910 *tps65910, u8 reg, - int bytes, void *src) -{ - return regmap_bulk_write(tps65910->regmap, reg, src, bytes); -} - -int tps65910_set_bits(struct tps65910 *tps65910, u8 reg, u8 mask) -{ - return regmap_update_bits(tps65910->regmap, reg, mask, mask); -} -EXPORT_SYMBOL_GPL(tps65910_set_bits); - -int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask) -{ - return regmap_update_bits(tps65910->regmap, reg, mask, 0); -} -EXPORT_SYMBOL_GPL(tps65910_clear_bits); - static bool is_volatile_reg(struct device *dev, unsigned int reg) { struct tps65910 *tps65910 = dev_get_drvdata(dev); @@ -102,7 +78,7 @@ static int __devinit tps65910_sleepinit(struct tps65910 *tps65910, return 0; /* enabling SLEEP device state */ - ret = tps65910_set_bits(tps65910, TPS65910_DEVCTRL, + ret = tps65910_reg_set_bits(tps65910, TPS65910_DEVCTRL, DEVCTRL_DEV_SLP_MASK); if (ret < 0) { dev_err(dev, "set dev_slp failed: %d\n", ret); @@ -114,7 +90,8 @@ static int __devinit tps65910_sleepinit(struct tps65910 *tps65910, return 0; if (pmic_pdata->slp_keepon->therm_keepon) { - ret = tps65910_set_bits(tps65910, TPS65910_SLEEP_KEEP_RES_ON, + ret = tps65910_reg_set_bits(tps65910, + TPS65910_SLEEP_KEEP_RES_ON, SLEEP_KEEP_RES_ON_THERM_KEEPON_MASK); if (ret < 0) { dev_err(dev, "set therm_keepon failed: %d\n", ret); @@ -123,7 +100,8 @@ static int __devinit tps65910_sleepinit(struct tps65910 *tps65910, } if (pmic_pdata->slp_keepon->clkout32k_keepon) { - ret = tps65910_set_bits(tps65910, TPS65910_SLEEP_KEEP_RES_ON, + ret = tps65910_reg_set_bits(tps65910, + TPS65910_SLEEP_KEEP_RES_ON, SLEEP_KEEP_RES_ON_CLKOUT32K_KEEPON_MASK); if (ret < 0) { dev_err(dev, "set clkout32k_keepon failed: %d\n", ret); @@ -132,7 +110,8 @@ static int __devinit tps65910_sleepinit(struct tps65910 *tps65910, } if (pmic_pdata->slp_keepon->i2chs_keepon) { - ret = tps65910_set_bits(tps65910, TPS65910_SLEEP_KEEP_RES_ON, + ret = tps65910_reg_set_bits(tps65910, + TPS65910_SLEEP_KEEP_RES_ON, SLEEP_KEEP_RES_ON_I2CHS_KEEPON_MASK); if (ret < 0) { dev_err(dev, "set i2chs_keepon failed: %d\n", ret); @@ -143,7 +122,8 @@ static int __devinit tps65910_sleepinit(struct tps65910 *tps65910, return 0; disable_dev_slp: - tps65910_clear_bits(tps65910, TPS65910_DEVCTRL, DEVCTRL_DEV_SLP_MASK); + tps65910_reg_clear_bits(tps65910, TPS65910_DEVCTRL, + DEVCTRL_DEV_SLP_MASK); err_sleep_init: return ret; @@ -176,8 +156,6 @@ static __devinit int tps65910_i2c_probe(struct i2c_client *i2c, tps65910->dev = &i2c->dev; tps65910->i2c_client = i2c; tps65910->id = id->driver_data; - tps65910->read = tps65910_i2c_read; - tps65910->write = tps65910_i2c_write; mutex_init(&tps65910->io_mutex); tps65910->regmap = regmap_init_i2c(i2c, &tps65910_regmap_config); diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c index 4a37c2b6367f..852b05b20de9 100644 --- a/drivers/regulator/tps65910-regulator.c +++ b/drivers/regulator/tps65910-regulator.c @@ -331,21 +331,16 @@ struct tps65910_reg { static inline int tps65910_read(struct tps65910_reg *pmic, u8 reg) { - u8 val; + unsigned int val; int err; - err = pmic->mfd->read(pmic->mfd, reg, 1, &val); + err = tps65910_reg_read(pmic->mfd, reg, &val); if (err) return err; return val; } -static inline int tps65910_write(struct tps65910_reg *pmic, u8 reg, u8 val) -{ - return pmic->mfd->write(pmic->mfd, reg, 1, &val); -} - static int tps65910_modify_bits(struct tps65910_reg *pmic, u8 reg, u8 set_mask, u8 clear_mask) { @@ -362,7 +357,7 @@ static int tps65910_modify_bits(struct tps65910_reg *pmic, u8 reg, data &= ~clear_mask; data |= set_mask; - err = tps65910_write(pmic, reg, data); + err = tps65910_reg_write(pmic->mfd, reg, data); if (err) dev_err(pmic->mfd->dev, "Write for reg 0x%x failed\n", reg); @@ -371,7 +366,7 @@ out: return err; } -static int tps65910_reg_read(struct tps65910_reg *pmic, u8 reg) +static int tps65910_reg_read_locked(struct tps65910_reg *pmic, u8 reg) { int data; @@ -385,13 +380,13 @@ static int tps65910_reg_read(struct tps65910_reg *pmic, u8 reg) return data; } -static int tps65910_reg_write(struct tps65910_reg *pmic, u8 reg, u8 val) +static int tps65910_reg_write_locked(struct tps65910_reg *pmic, u8 reg, u8 val) { int err; mutex_lock(&pmic->mutex); - err = tps65910_write(pmic, reg, val); + err = tps65910_reg_write(pmic->mfd, reg, val); if (err < 0) dev_err(pmic->mfd->dev, "Write for reg 0x%x failed\n", reg); @@ -476,7 +471,7 @@ static int tps65910_is_enabled(struct regulator_dev *dev) if (reg < 0) return reg; - value = tps65910_reg_read(pmic, reg); + value = tps65910_reg_read_locked(pmic, reg); if (value < 0) return value; @@ -493,7 +488,7 @@ static int tps65910_enable(struct regulator_dev *dev) if (reg < 0) return reg; - return tps65910_set_bits(mfd, reg, TPS65910_SUPPLY_STATE_ENABLED); + return tps65910_reg_set_bits(mfd, reg, TPS65910_SUPPLY_STATE_ENABLED); } static int tps65910_disable(struct regulator_dev *dev) @@ -506,7 +501,7 @@ static int tps65910_disable(struct regulator_dev *dev) if (reg < 0) return reg; - return tps65910_clear_bits(mfd, reg, TPS65910_SUPPLY_STATE_ENABLED); + return tps65910_reg_clear_bits(mfd, reg, TPS65910_SUPPLY_STATE_ENABLED); } static int tps65910_enable_time(struct regulator_dev *dev) @@ -532,9 +527,9 @@ static int tps65910_set_mode(struct regulator_dev *dev, unsigned int mode) LDO_ST_MODE_BIT); case REGULATOR_MODE_IDLE: value = LDO_ST_ON_BIT | LDO_ST_MODE_BIT; - return tps65910_set_bits(mfd, reg, value); + return tps65910_reg_set_bits(mfd, reg, value); case REGULATOR_MODE_STANDBY: - return tps65910_clear_bits(mfd, reg, LDO_ST_ON_BIT); + return tps65910_reg_clear_bits(mfd, reg, LDO_ST_ON_BIT); } return -EINVAL; @@ -549,7 +544,7 @@ static unsigned int tps65910_get_mode(struct regulator_dev *dev) if (reg < 0) return reg; - value = tps65910_reg_read(pmic, reg); + value = tps65910_reg_read_locked(pmic, reg); if (value < 0) return value; @@ -569,28 +564,28 @@ static int tps65910_get_voltage_dcdc_sel(struct regulator_dev *dev) switch (id) { case TPS65910_REG_VDD1: - opvsel = tps65910_reg_read(pmic, TPS65910_VDD1_OP); - mult = tps65910_reg_read(pmic, TPS65910_VDD1); + opvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD1_OP); + mult = tps65910_reg_read_locked(pmic, TPS65910_VDD1); mult = (mult & VDD1_VGAIN_SEL_MASK) >> VDD1_VGAIN_SEL_SHIFT; - srvsel = tps65910_reg_read(pmic, TPS65910_VDD1_SR); + srvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD1_SR); sr = opvsel & VDD1_OP_CMD_MASK; opvsel &= VDD1_OP_SEL_MASK; srvsel &= VDD1_SR_SEL_MASK; vselmax = 75; break; case TPS65910_REG_VDD2: - opvsel = tps65910_reg_read(pmic, TPS65910_VDD2_OP); - mult = tps65910_reg_read(pmic, TPS65910_VDD2); + opvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD2_OP); + mult = tps65910_reg_read_locked(pmic, TPS65910_VDD2); mult = (mult & VDD2_VGAIN_SEL_MASK) >> VDD2_VGAIN_SEL_SHIFT; - srvsel = tps65910_reg_read(pmic, TPS65910_VDD2_SR); + srvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD2_SR); sr = opvsel & VDD2_OP_CMD_MASK; opvsel &= VDD2_OP_SEL_MASK; srvsel &= VDD2_SR_SEL_MASK; vselmax = 75; break; case TPS65911_REG_VDDCTRL: - opvsel = tps65910_reg_read(pmic, TPS65911_VDDCTRL_OP); - srvsel = tps65910_reg_read(pmic, TPS65911_VDDCTRL_SR); + opvsel = tps65910_reg_read_locked(pmic, TPS65911_VDDCTRL_OP); + srvsel = tps65910_reg_read_locked(pmic, TPS65911_VDDCTRL_SR); sr = opvsel & VDDCTRL_OP_CMD_MASK; opvsel &= VDDCTRL_OP_SEL_MASK; srvsel &= VDDCTRL_SR_SEL_MASK; @@ -630,7 +625,7 @@ static int tps65910_get_voltage(struct regulator_dev *dev) if (reg < 0) return reg; - value = tps65910_reg_read(pmic, reg); + value = tps65910_reg_read_locked(pmic, reg); if (value < 0) return value; @@ -669,7 +664,7 @@ static int tps65911_get_voltage(struct regulator_dev *dev) reg = pmic->get_ctrl_reg(id); - value = tps65910_reg_read(pmic, reg); + value = tps65910_reg_read_locked(pmic, reg); switch (id) { case TPS65911_REG_LDO1: @@ -728,7 +723,7 @@ static int tps65910_set_voltage_dcdc_sel(struct regulator_dev *dev, tps65910_modify_bits(pmic, TPS65910_VDD1, (dcdc_mult << VDD1_VGAIN_SEL_SHIFT), VDD1_VGAIN_SEL_MASK); - tps65910_reg_write(pmic, TPS65910_VDD1_OP, vsel); + tps65910_reg_write_locked(pmic, TPS65910_VDD1_OP, vsel); break; case TPS65910_REG_VDD2: dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1; @@ -739,11 +734,11 @@ static int tps65910_set_voltage_dcdc_sel(struct regulator_dev *dev, tps65910_modify_bits(pmic, TPS65910_VDD2, (dcdc_mult << VDD2_VGAIN_SEL_SHIFT), VDD1_VGAIN_SEL_MASK); - tps65910_reg_write(pmic, TPS65910_VDD2_OP, vsel); + tps65910_reg_write_locked(pmic, TPS65910_VDD2_OP, vsel); break; case TPS65911_REG_VDDCTRL: vsel = selector + 3; - tps65910_reg_write(pmic, TPS65911_VDDCTRL_OP, vsel); + tps65910_reg_write_locked(pmic, TPS65911_VDDCTRL_OP, vsel); } return 0; @@ -994,10 +989,10 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic, /* External EN1 control */ if (ext_sleep_config & TPS65910_SLEEP_CONTROL_EXT_INPUT_EN1) - ret = tps65910_set_bits(mfd, + ret = tps65910_reg_set_bits(mfd, TPS65910_EN1_LDO_ASS + regoffs, bit_pos); else - ret = tps65910_clear_bits(mfd, + ret = tps65910_reg_clear_bits(mfd, TPS65910_EN1_LDO_ASS + regoffs, bit_pos); if (ret < 0) { dev_err(mfd->dev, @@ -1007,10 +1002,10 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic, /* External EN2 control */ if (ext_sleep_config & TPS65910_SLEEP_CONTROL_EXT_INPUT_EN2) - ret = tps65910_set_bits(mfd, + ret = tps65910_reg_set_bits(mfd, TPS65910_EN2_LDO_ASS + regoffs, bit_pos); else - ret = tps65910_clear_bits(mfd, + ret = tps65910_reg_clear_bits(mfd, TPS65910_EN2_LDO_ASS + regoffs, bit_pos); if (ret < 0) { dev_err(mfd->dev, @@ -1022,10 +1017,10 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic, if ((tps65910_chip_id(mfd) == TPS65910) && (id >= TPS65910_REG_VDIG1)) { if (ext_sleep_config & TPS65910_SLEEP_CONTROL_EXT_INPUT_EN3) - ret = tps65910_set_bits(mfd, + ret = tps65910_reg_set_bits(mfd, TPS65910_EN3_LDO_ASS + regoffs, bit_pos); else - ret = tps65910_clear_bits(mfd, + ret = tps65910_reg_clear_bits(mfd, TPS65910_EN3_LDO_ASS + regoffs, bit_pos); if (ret < 0) { dev_err(mfd->dev, @@ -1037,10 +1032,10 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic, /* Return if no external control is selected */ if (!(ext_sleep_config & EXT_SLEEP_CONTROL)) { /* Clear all sleep controls */ - ret = tps65910_clear_bits(mfd, + ret = tps65910_reg_clear_bits(mfd, TPS65910_SLEEP_KEEP_LDO_ON + regoffs, bit_pos); if (!ret) - ret = tps65910_clear_bits(mfd, + ret = tps65910_reg_clear_bits(mfd, TPS65910_SLEEP_SET_LDO_OFF + regoffs, bit_pos); if (ret < 0) dev_err(mfd->dev, @@ -1059,32 +1054,33 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic, (tps65910_chip_id(mfd) == TPS65911))) { int op_reg_add = pmic->get_ctrl_reg(id) + 1; int sr_reg_add = pmic->get_ctrl_reg(id) + 2; - int opvsel = tps65910_reg_read(pmic, op_reg_add); - int srvsel = tps65910_reg_read(pmic, sr_reg_add); + int opvsel = tps65910_reg_read_locked(pmic, op_reg_add); + int srvsel = tps65910_reg_read_locked(pmic, sr_reg_add); if (opvsel & VDD1_OP_CMD_MASK) { u8 reg_val = srvsel & VDD1_OP_SEL_MASK; - ret = tps65910_reg_write(pmic, op_reg_add, reg_val); + ret = tps65910_reg_write_locked(pmic, op_reg_add, + reg_val); if (ret < 0) { dev_err(mfd->dev, "Error in configuring op register\n"); return ret; } } - ret = tps65910_reg_write(pmic, sr_reg_add, 0); + ret = tps65910_reg_write_locked(pmic, sr_reg_add, 0); if (ret < 0) { dev_err(mfd->dev, "Error in settting sr register\n"); return ret; } } - ret = tps65910_clear_bits(mfd, + ret = tps65910_reg_clear_bits(mfd, TPS65910_SLEEP_KEEP_LDO_ON + regoffs, bit_pos); if (!ret) { if (ext_sleep_config & TPS65911_SLEEP_CONTROL_EXT_INPUT_SLEEP) - ret = tps65910_set_bits(mfd, + ret = tps65910_reg_set_bits(mfd, TPS65910_SLEEP_SET_LDO_OFF + regoffs, bit_pos); else - ret = tps65910_clear_bits(mfd, + ret = tps65910_reg_clear_bits(mfd, TPS65910_SLEEP_SET_LDO_OFF + regoffs, bit_pos); } if (ret < 0) @@ -1117,7 +1113,7 @@ static __devinit int tps65910_probe(struct platform_device *pdev) platform_set_drvdata(pdev, pmic); /* Give control of all register to control port */ - tps65910_set_bits(pmic->mfd, TPS65910_DEVCTRL, + tps65910_reg_set_bits(pmic->mfd, TPS65910_DEVCTRL, DEVCTRL_SR_CTL_I2C_SEL_MASK); switch(tps65910_chip_id(tps65910)) { diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index 56903ad04283..949f1da661d2 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -18,6 +18,7 @@ #define __LINUX_MFD_TPS65910_H #include +#include /* TPS chip id list */ #define TPS65910 0 @@ -823,8 +824,6 @@ struct tps65910 { struct regmap *regmap; struct mutex io_mutex; unsigned int id; - int (*read)(struct tps65910 *tps65910, u8 reg, int size, void *dest); - int (*write)(struct tps65910 *tps65910, u8 reg, int size, void *src); /* Client devices */ struct tps65910_pmic *pmic; @@ -847,8 +846,6 @@ struct tps65910_platform_data { int irq_base; }; -int tps65910_set_bits(struct tps65910 *tps65910, u8 reg, u8 mask); -int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask); void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base); int tps65910_irq_init(struct tps65910 *tps65910, int irq, struct tps65910_platform_data *pdata); @@ -859,4 +856,28 @@ static inline int tps65910_chip_id(struct tps65910 *tps65910) return tps65910->id; } +static inline int tps65910_reg_read(struct tps65910 *tps65910, u8 reg, + unsigned int *val) +{ + return regmap_read(tps65910->regmap, reg, val); +} + +static inline int tps65910_reg_write(struct tps65910 *tps65910, u8 reg, + unsigned int val) +{ + return regmap_write(tps65910->regmap, reg, val); +} + +static inline int tps65910_reg_set_bits(struct tps65910 *tps65910, u8 reg, + u8 mask) +{ + return regmap_update_bits(tps65910->regmap, reg, mask, mask); +} + +static inline int tps65910_reg_clear_bits(struct tps65910 *tps65910, u8 reg, + u8 mask) +{ + return regmap_update_bits(tps65910->regmap, reg, mask, 0); +} + #endif /* __LINUX_MFD_TPS65910_H */ -- cgit v1.2.3 From 9577e8c3fbc145b5d2a12d2fbc6a50031573c77d Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 9 May 2012 05:43:59 +1000 Subject: mfd: Define all twl-regulator feature flags in one place twl-regulator has a collection of feature flags, some defined in twl-core.c and one defined in i2c/twl.h. This is confusing for anyone adding a new feature flag. So collect them together and place them in twl.h immediately after the structure in which they are initially set. Signed-off-by: NeilBrown Signed-off-by: Samuel Ortiz --- drivers/mfd/twl-core.c | 7 ------- include/linux/i2c/twl.h | 8 ++++++-- 2 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c index 7c2267e71f8b..6fc90befa79e 100644 --- a/drivers/mfd/twl-core.c +++ b/drivers/mfd/twl-core.c @@ -224,13 +224,6 @@ #define HIGH_PERF_SQ (1 << 3) #define CK32K_LOWPWR_EN (1 << 7) - -/* chip-specific feature flags, for i2c_device_id.driver_data */ -#define TWL4030_VAUX2 BIT(0) /* pre-5030 voltage ranges */ -#define TPS_SUBSET BIT(1) /* tps659[23]0 have fewer LDOs */ -#define TWL5031 BIT(2) /* twl5031 has different registers */ -#define TWL6030_CLASS BIT(3) /* TWL6030 class */ - /*----------------------------------------------------------------------*/ /* is driver active, bound to a chip? */ diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index 1f90de0cfdbe..d1afedc00898 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -171,8 +171,6 @@ static inline int twl_class_is_ ##class(void) \ TWL_CLASS_IS(4030, TWL4030_CLASS_ID) TWL_CLASS_IS(6030, TWL6030_CLASS_ID) -#define TWL6025_SUBCLASS BIT(4) /* TWL6025 has changed registers */ - /* * Read and write single 8-bit registers */ @@ -746,6 +744,12 @@ struct twl_regulator_driver_data { void *data; unsigned long features; }; +/* chip-specific feature flags, for twl_regulator_driver_data.features */ +#define TWL4030_VAUX2 BIT(0) /* pre-5030 voltage ranges */ +#define TPS_SUBSET BIT(1) /* tps659[23]0 have fewer LDOs */ +#define TWL5031 BIT(2) /* twl5031 has different registers */ +#define TWL6030_CLASS BIT(3) /* TWL6030 class */ +#define TWL6025_SUBCLASS BIT(4) /* TWL6025 has changed registers */ /*----------------------------------------------------------------------*/ -- cgit v1.2.3 From 32df986e985921386b75b4bd1117102bf65fe095 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Fri, 11 May 2012 15:07:44 +0200 Subject: mfd: Register tps65910 gpios as an mfd device As gpio support for tps65910 is on gpio driver, registering gpio support as the mfd sub devices instead of calling gpio_init() from the core probe. Signed-off-by: Laxman Dewangan Signed-off-by: Samuel Ortiz --- drivers/mfd/Kconfig | 1 - drivers/mfd/tps65910.c | 6 +++--- include/linux/mfd/tps65910.h | 4 ---- 3 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 1e9a7d5ec919..b914483cd630 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -189,7 +189,6 @@ config MFD_TPS65910 bool "TPS65910 Power Management chip" depends on I2C=y && GPIOLIB select MFD_CORE - select GPIO_TPS65910 select REGMAP_I2C help if you say yes here you get support for the TPS65910 series of diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c index 22fa43070659..553574da3611 100644 --- a/drivers/mfd/tps65910.c +++ b/drivers/mfd/tps65910.c @@ -19,13 +19,15 @@ #include #include #include -#include #include #include #include #include static struct mfd_cell tps65910s[] = { + { + .name = "tps65910-gpio", + }, { .name = "tps65910-pmic", }, @@ -250,8 +252,6 @@ static __devinit int tps65910_i2c_probe(struct i2c_client *i2c, init_data->irq = pmic_plat_data->irq; init_data->irq_base = pmic_plat_data->irq_base; - tps65910_gpio_init(tps65910, pmic_plat_data->gpio_base); - tps65910_irq_init(tps65910, init_data->irq, init_data); tps65910_sleepinit(tps65910, pmic_plat_data); diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index 949f1da661d2..c2673ee5e70f 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -830,9 +830,6 @@ struct tps65910 { struct tps65910_rtc *rtc; struct tps65910_power *power; - /* GPIO Handling */ - struct gpio_chip gpio; - /* IRQ Handling */ struct mutex irq_lock; int chip_irq; @@ -846,7 +843,6 @@ struct tps65910_platform_data { int irq_base; }; -void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base); int tps65910_irq_init(struct tps65910 *tps65910, int irq, struct tps65910_platform_data *pdata); int tps65910_irq_exit(struct tps65910 *tps65910); -- cgit v1.2.3 From 879eed68265c8dcb2f2856ec96820fc93b7038c9 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 9 May 2012 22:53:48 +0100 Subject: mfd: Remove wm8400 custom cache implementation Save a useful amount of code by removing the custom cache implementation for wm8400 and using the regmap cache. Also simplify things by not separately reseting the CODEC registers, this is a sufficiently infrequent operation that we can simply invalidate the entire cache when this happens. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm8400-core.c | 251 ++++++------------------------------- include/linux/mfd/wm8400-private.h | 14 +-- 2 files changed, 42 insertions(+), 223 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm8400-core.c b/drivers/mfd/wm8400-core.c index 1189a17f0f25..9083b775e2b6 100644 --- a/drivers/mfd/wm8400-core.c +++ b/drivers/mfd/wm8400-core.c @@ -23,136 +23,16 @@ #include #include -static struct { - u16 readable; /* Mask of readable bits */ - u16 writable; /* Mask of writable bits */ - u16 vol; /* Mask of volatile bits */ - int is_codec; /* Register controlled by codec reset */ - u16 default_val; /* Value on reset */ -} reg_data[] = { - { 0xFFFF, 0xFFFF, 0x0000, 0, 0x6172 }, /* R0 */ - { 0x7000, 0x0000, 0x8000, 0, 0x0000 }, /* R1 */ - { 0xFF17, 0xFF17, 0x0000, 0, 0x0000 }, /* R2 */ - { 0xEBF3, 0xEBF3, 0x0000, 1, 0x6000 }, /* R3 */ - { 0x3CF3, 0x3CF3, 0x0000, 1, 0x0000 }, /* R4 */ - { 0xF1F8, 0xF1F8, 0x0000, 1, 0x4050 }, /* R5 */ - { 0xFC1F, 0xFC1F, 0x0000, 1, 0x4000 }, /* R6 */ - { 0xDFDE, 0xDFDE, 0x0000, 1, 0x01C8 }, /* R7 */ - { 0xFCFC, 0xFCFC, 0x0000, 1, 0x0000 }, /* R8 */ - { 0xEFFF, 0xEFFF, 0x0000, 1, 0x0040 }, /* R9 */ - { 0xEFFF, 0xEFFF, 0x0000, 1, 0x0040 }, /* R10 */ - { 0x27F7, 0x27F7, 0x0000, 1, 0x0004 }, /* R11 */ - { 0x01FF, 0x01FF, 0x0000, 1, 0x00C0 }, /* R12 */ - { 0x01FF, 0x01FF, 0x0000, 1, 0x00C0 }, /* R13 */ - { 0x1FEF, 0x1FEF, 0x0000, 1, 0x0000 }, /* R14 */ - { 0x0163, 0x0163, 0x0000, 1, 0x0100 }, /* R15 */ - { 0x01FF, 0x01FF, 0x0000, 1, 0x00C0 }, /* R16 */ - { 0x01FF, 0x01FF, 0x0000, 1, 0x00C0 }, /* R17 */ - { 0x1FFF, 0x0FFF, 0x0000, 1, 0x0000 }, /* R18 */ - { 0xFFFF, 0xFFFF, 0x0000, 1, 0x1000 }, /* R19 */ - { 0xFFFF, 0xFFFF, 0x0000, 1, 0x1010 }, /* R20 */ - { 0xFFFF, 0xFFFF, 0x0000, 1, 0x1010 }, /* R21 */ - { 0x0FDD, 0x0FDD, 0x0000, 1, 0x8000 }, /* R22 */ - { 0x1FFF, 0x1FFF, 0x0000, 1, 0x0800 }, /* R23 */ - { 0x0000, 0x01DF, 0x0000, 1, 0x008B }, /* R24 */ - { 0x0000, 0x01DF, 0x0000, 1, 0x008B }, /* R25 */ - { 0x0000, 0x01DF, 0x0000, 1, 0x008B }, /* R26 */ - { 0x0000, 0x01DF, 0x0000, 1, 0x008B }, /* R27 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R28 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R29 */ - { 0x0000, 0x0077, 0x0000, 1, 0x0066 }, /* R30 */ - { 0x0000, 0x0033, 0x0000, 1, 0x0022 }, /* R31 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0079 }, /* R32 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0079 }, /* R33 */ - { 0x0000, 0x0003, 0x0000, 1, 0x0003 }, /* R34 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0003 }, /* R35 */ - { 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R36 */ - { 0x0000, 0x003F, 0x0000, 1, 0x0100 }, /* R37 */ - { 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R38 */ - { 0x0000, 0x000F, 0x0000, 0, 0x0000 }, /* R39 */ - { 0x0000, 0x00FF, 0x0000, 1, 0x0000 }, /* R40 */ - { 0x0000, 0x01B7, 0x0000, 1, 0x0000 }, /* R41 */ - { 0x0000, 0x01B7, 0x0000, 1, 0x0000 }, /* R42 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R43 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R44 */ - { 0x0000, 0x00FD, 0x0000, 1, 0x0000 }, /* R45 */ - { 0x0000, 0x00FD, 0x0000, 1, 0x0000 }, /* R46 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R47 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R48 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R49 */ - { 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R50 */ - { 0x0000, 0x01B3, 0x0000, 1, 0x0180 }, /* R51 */ - { 0x0000, 0x0077, 0x0000, 1, 0x0000 }, /* R52 */ - { 0x0000, 0x0077, 0x0000, 1, 0x0000 }, /* R53 */ - { 0x0000, 0x00FF, 0x0000, 1, 0x0000 }, /* R54 */ - { 0x0000, 0x0001, 0x0000, 1, 0x0000 }, /* R55 */ - { 0x0000, 0x003F, 0x0000, 1, 0x0000 }, /* R56 */ - { 0x0000, 0x004F, 0x0000, 1, 0x0000 }, /* R57 */ - { 0x0000, 0x00FD, 0x0000, 1, 0x0000 }, /* R58 */ - { 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R59 */ - { 0x1FFF, 0x1FFF, 0x0000, 1, 0x0000 }, /* R60 */ - { 0xFFFF, 0xFFFF, 0x0000, 1, 0x0000 }, /* R61 */ - { 0x03FF, 0x03FF, 0x0000, 1, 0x0000 }, /* R62 */ - { 0x007F, 0x007F, 0x0000, 1, 0x0000 }, /* R63 */ - { 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R64 */ - { 0xDFFF, 0xDFFF, 0x0000, 0, 0x0000 }, /* R65 */ - { 0xDFFF, 0xDFFF, 0x0000, 0, 0x0000 }, /* R66 */ - { 0xDFFF, 0xDFFF, 0x0000, 0, 0x0000 }, /* R67 */ - { 0xDFFF, 0xDFFF, 0x0000, 0, 0x0000 }, /* R68 */ - { 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R69 */ - { 0xFFFF, 0xFFFF, 0x0000, 0, 0x4400 }, /* R70 */ - { 0x23FF, 0x23FF, 0x0000, 0, 0x0000 }, /* R71 */ - { 0xFFFF, 0xFFFF, 0x0000, 0, 0x4400 }, /* R72 */ - { 0x23FF, 0x23FF, 0x0000, 0, 0x0000 }, /* R73 */ - { 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R74 */ - { 0x000E, 0x000E, 0x0000, 0, 0x0008 }, /* R75 */ - { 0xE00F, 0xE00F, 0x0000, 0, 0x0000 }, /* R76 */ - { 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R77 */ - { 0x03C0, 0x03C0, 0x0000, 0, 0x02C0 }, /* R78 */ - { 0xFFFF, 0x0000, 0xffff, 0, 0x0000 }, /* R79 */ - { 0xFFFF, 0xFFFF, 0x0000, 0, 0x0000 }, /* R80 */ - { 0xFFFF, 0x0000, 0xffff, 0, 0x0000 }, /* R81 */ - { 0x2BFF, 0x0000, 0xffff, 0, 0x0000 }, /* R82 */ - { 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R83 */ - { 0x80FF, 0x80FF, 0x0000, 0, 0x00ff }, /* R84 */ -}; - -static int wm8400_read(struct wm8400 *wm8400, u8 reg, int num_regs, u16 *dest) +static bool wm8400_volatile(struct device *dev, unsigned int reg) { - int i, ret = 0; - - BUG_ON(reg + num_regs > ARRAY_SIZE(wm8400->reg_cache)); - - /* If there are any volatile reads then read back the entire block */ - for (i = reg; i < reg + num_regs; i++) - if (reg_data[i].vol) { - ret = regmap_bulk_read(wm8400->regmap, reg, dest, - num_regs); - return ret; - } - - /* Otherwise use the cache */ - memcpy(dest, &wm8400->reg_cache[reg], num_regs * sizeof(u16)); - - return 0; -} - -static int wm8400_write(struct wm8400 *wm8400, u8 reg, int num_regs, - u16 *src) -{ - int ret, i; - - BUG_ON(reg + num_regs > ARRAY_SIZE(wm8400->reg_cache)); - - for (i = 0; i < num_regs; i++) { - BUG_ON(!reg_data[reg + i].writable); - wm8400->reg_cache[reg + i] = src[i]; - ret = regmap_write(wm8400->regmap, reg, src[i]); - if (ret != 0) - return ret; + switch (reg) { + case WM8400_INTERRUPT_STATUS_1: + case WM8400_INTERRUPT_LEVELS: + case WM8400_SHUTDOWN_REASON: + return true; + default: + return false; } - - return 0; } /** @@ -165,13 +45,12 @@ static int wm8400_write(struct wm8400 *wm8400, u8 reg, int num_regs, */ u16 wm8400_reg_read(struct wm8400 *wm8400, u8 reg) { - u16 val; - - mutex_lock(&wm8400->io_lock); - - wm8400_read(wm8400, reg, 1, &val); + unsigned int val; + int ret; - mutex_unlock(&wm8400->io_lock); + ret = regmap_read(wm8400->regmap, reg, &val); + if (ret < 0) + return ret; return val; } @@ -179,62 +58,8 @@ EXPORT_SYMBOL_GPL(wm8400_reg_read); int wm8400_block_read(struct wm8400 *wm8400, u8 reg, int count, u16 *data) { - int ret; - - mutex_lock(&wm8400->io_lock); - - ret = wm8400_read(wm8400, reg, count, data); - - mutex_unlock(&wm8400->io_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(wm8400_block_read); - -/** - * wm8400_set_bits - Bitmask write - * - * @wm8400: Pointer to wm8400 control structure - * @reg: Register to access - * @mask: Mask of bits to change - * @val: Value to set for masked bits - */ -int wm8400_set_bits(struct wm8400 *wm8400, u8 reg, u16 mask, u16 val) -{ - u16 tmp; - int ret; - - mutex_lock(&wm8400->io_lock); - - ret = wm8400_read(wm8400, reg, 1, &tmp); - tmp = (tmp & ~mask) | val; - if (ret == 0) - ret = wm8400_write(wm8400, reg, 1, &tmp); - - mutex_unlock(&wm8400->io_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(wm8400_set_bits); - -/** - * wm8400_reset_codec_reg_cache - Reset cached codec registers to - * their default values. - */ -void wm8400_reset_codec_reg_cache(struct wm8400 *wm8400) -{ - int i; - - mutex_lock(&wm8400->io_lock); - - /* Reset all codec registers to their initial value */ - for (i = 0; i < ARRAY_SIZE(wm8400->reg_cache); i++) - if (reg_data[i].is_codec) - wm8400->reg_cache[i] = reg_data[i].default_val; - - mutex_unlock(&wm8400->io_lock); + return regmap_bulk_read(wm8400->regmap, reg, data, count); } -EXPORT_SYMBOL_GPL(wm8400_reset_codec_reg_cache); static int wm8400_register_codec(struct wm8400 *wm8400) { @@ -257,44 +82,24 @@ static int wm8400_register_codec(struct wm8400 *wm8400) static int wm8400_init(struct wm8400 *wm8400, struct wm8400_platform_data *pdata) { - u16 reg; - int ret, i; - - mutex_init(&wm8400->io_lock); + unsigned int reg; + int ret; dev_set_drvdata(wm8400->dev, wm8400); /* Check that this is actually a WM8400 */ - ret = regmap_read(wm8400->regmap, WM8400_RESET_ID, &i); + ret = regmap_read(wm8400->regmap, WM8400_RESET_ID, ®); if (ret != 0) { dev_err(wm8400->dev, "Chip ID register read failed\n"); return -EIO; } - if (i != reg_data[WM8400_RESET_ID].default_val) { - dev_err(wm8400->dev, "Device is not a WM8400, ID is %x\n", i); + if (reg != 0x6172) { + dev_err(wm8400->dev, "Device is not a WM8400, ID is %x\n", + reg); return -ENODEV; } - /* We don't know what state the hardware is in and since this - * is a PMIC we can't reset it safely so initialise the register - * cache from the hardware. - */ - ret = regmap_raw_read(wm8400->regmap, 0, wm8400->reg_cache, - ARRAY_SIZE(wm8400->reg_cache)); - if (ret != 0) { - dev_err(wm8400->dev, "Register cache read failed\n"); - return -EIO; - } - for (i = 0; i < ARRAY_SIZE(wm8400->reg_cache); i++) - wm8400->reg_cache[i] = be16_to_cpu(wm8400->reg_cache[i]); - - /* If the codec is in reset use hard coded values */ - if (!(wm8400->reg_cache[WM8400_POWER_MANAGEMENT_1] & WM8400_CODEC_ENA)) - for (i = 0; i < ARRAY_SIZE(wm8400->reg_cache); i++) - if (reg_data[i].is_codec) - wm8400->reg_cache[i] = reg_data[i].default_val; - - ret = wm8400_read(wm8400, WM8400_ID, 1, ®); + ret = regmap_read(wm8400->regmap, WM8400_ID, ®); if (ret != 0) { dev_err(wm8400->dev, "ID register read failed: %d\n", ret); return ret; @@ -334,8 +139,22 @@ static const struct regmap_config wm8400_regmap_config = { .reg_bits = 8, .val_bits = 16, .max_register = WM8400_REGISTER_COUNT - 1, + + .volatile_reg = wm8400_volatile, + + .cache_type = REGCACHE_RBTREE, }; +/** + * wm8400_reset_codec_reg_cache - Reset cached codec registers to + * their default values. + */ +void wm8400_reset_codec_reg_cache(struct wm8400 *wm8400) +{ + regmap_reinit_cache(wm8400->regmap, &wm8400_regmap_config); +} +EXPORT_SYMBOL_GPL(wm8400_reset_codec_reg_cache); + #if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) static int wm8400_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) diff --git a/include/linux/mfd/wm8400-private.h b/include/linux/mfd/wm8400-private.h index 0147b6968510..2de565b94d0c 100644 --- a/include/linux/mfd/wm8400-private.h +++ b/include/linux/mfd/wm8400-private.h @@ -24,19 +24,14 @@ #include #include #include - -struct regmap; +#include #define WM8400_REGISTER_COUNT 0x55 struct wm8400 { struct device *dev; - - struct mutex io_lock; struct regmap *regmap; - u16 reg_cache[WM8400_REGISTER_COUNT]; - struct platform_device regulators[6]; }; @@ -930,6 +925,11 @@ struct wm8400 { u16 wm8400_reg_read(struct wm8400 *wm8400, u8 reg); int wm8400_block_read(struct wm8400 *wm8400, u8 reg, int count, u16 *data); -int wm8400_set_bits(struct wm8400 *wm8400, u8 reg, u16 mask, u16 val); + +static inline int wm8400_set_bits(struct wm8400 *wm8400, u8 reg, + u16 mask, u16 val) +{ + return regmap_update_bits(wm8400->regmap, reg, mask, val); +} #endif -- cgit v1.2.3 From d9055dc501da6734e3cfea1ef236173bd8b645b1 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 10 May 2012 14:11:28 +0200 Subject: mfd: Add boost frequency and ovp to lm3533 platform data Add boost-frequency and over-voltage-protection settings to platform data. Signed-off-by: Johan Hovold Signed-off-by: Samuel Ortiz --- drivers/mfd/lm3533-core.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/lm3533.h | 15 ++++++++++++++ 2 files changed, 65 insertions(+) (limited to 'include/linux') diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c index 75f4b7f5a4fd..053438cff10a 100644 --- a/drivers/mfd/lm3533-core.c +++ b/drivers/mfd/lm3533-core.c @@ -138,6 +138,35 @@ int lm3533_update(struct lm3533 *lm3533, u8 reg, u8 val, u8 mask) } EXPORT_SYMBOL_GPL(lm3533_update); +static int lm3533_set_boost_freq(struct lm3533 *lm3533, + enum lm3533_boost_freq freq) +{ + int ret; + + ret = lm3533_update(lm3533, LM3533_REG_BOOST_PWM, + freq << LM3533_BOOST_FREQ_SHIFT, + LM3533_BOOST_FREQ_MASK); + if (ret) + dev_err(lm3533->dev, "failed to set boost frequency\n"); + + return ret; +} + + +static int lm3533_set_boost_ovp(struct lm3533 *lm3533, + enum lm3533_boost_ovp ovp) +{ + int ret; + + ret = lm3533_update(lm3533, LM3533_REG_BOOST_PWM, + ovp << LM3533_BOOST_OVP_SHIFT, + LM3533_BOOST_OVP_MASK); + if (ret) + dev_err(lm3533->dev, "failed to set boost ovp\n"); + + return ret; +} + /* * HVLED output config -- output hvled controlled by backlight bl */ @@ -521,6 +550,22 @@ static int __devinit lm3533_device_led_init(struct lm3533 *lm3533) return 0; } +static int __devinit lm3533_device_setup(struct lm3533 *lm3533, + struct lm3533_platform_data *pdata) +{ + int ret; + + ret = lm3533_set_boost_freq(lm3533, pdata->boost_freq); + if (ret) + return ret; + + ret = lm3533_set_boost_ovp(lm3533, pdata->boost_ovp); + if (ret) + return ret; + + return 0; +} + static int __devinit lm3533_device_init(struct lm3533 *lm3533) { struct lm3533_platform_data *pdata = lm3533->dev->platform_data; @@ -550,6 +595,10 @@ static int __devinit lm3533_device_init(struct lm3533 *lm3533) lm3533_enable(lm3533); + ret = lm3533_device_setup(lm3533, pdata); + if (ret) + goto err_disable; + lm3533_device_als_init(lm3533); lm3533_device_bl_init(lm3533); lm3533_device_led_init(lm3533); @@ -564,6 +613,7 @@ static int __devinit lm3533_device_init(struct lm3533 *lm3533) err_unregister: mfd_remove_devices(lm3533->dev); +err_disable: lm3533_disable(lm3533); if (gpio_is_valid(lm3533->gpio_hwen)) gpio_free(lm3533->gpio_hwen); diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h index 75f85f3fbd90..336113759fd1 100644 --- a/include/linux/mfd/lm3533.h +++ b/include/linux/mfd/lm3533.h @@ -59,9 +59,24 @@ struct lm3533_led_platform_data { u8 pwm; /* 0 - 0x3f */ }; +enum lm3533_boost_freq { + LM3533_BOOST_FREQ_500KHZ, + LM3533_BOOST_FREQ_1000KHZ, +}; + +enum lm3533_boost_ovp { + LM3533_BOOST_OVP_16V, + LM3533_BOOST_OVP_24V, + LM3533_BOOST_OVP_32V, + LM3533_BOOST_OVP_40V, +}; + struct lm3533_platform_data { int gpio_hwen; + enum lm3533_boost_ovp boost_ovp; + enum lm3533_boost_freq boost_freq; + struct lm3533_als_platform_data *als; struct lm3533_bl_platform_data *backlights; -- cgit v1.2.3 From 7af5e87dc5e6b6f413ba95b06e06ebf810687858 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 10 May 2012 19:18:28 +0200 Subject: mfd: Remove unused max-current lm3533 function The max-current attributes of the subdrivers have been dropped so remove the no longer used lm3533_ctrlbank_get_max_current function. Signed-off-by: Johan Hovold Signed-off-by: Samuel Ortiz --- drivers/mfd/lm3533-ctrlbank.c | 1 - include/linux/mfd/lm3533.h | 2 -- 2 files changed, 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/lm3533-ctrlbank.c b/drivers/mfd/lm3533-ctrlbank.c index c2732a37c65a..adf4c1a542a9 100644 --- a/drivers/mfd/lm3533-ctrlbank.c +++ b/drivers/mfd/lm3533-ctrlbank.c @@ -113,7 +113,6 @@ lm3533_ctrlbank_get(brightness, BRIGHTNESS); * 31 - 29.8 mA */ lm3533_ctrlbank_set(max_current, MAX_CURRENT); -lm3533_ctrlbank_get(max_current, MAX_CURRENT); /* * PWM-input control mask: diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h index 336113759fd1..7cfef9e4f41b 100644 --- a/include/linux/mfd/lm3533.h +++ b/include/linux/mfd/lm3533.h @@ -92,8 +92,6 @@ extern int lm3533_ctrlbank_disable(struct lm3533_ctrlbank *cb); extern int lm3533_ctrlbank_set_brightness(struct lm3533_ctrlbank *cb, u8 val); extern int lm3533_ctrlbank_get_brightness(struct lm3533_ctrlbank *cb, u8 *val); extern int lm3533_ctrlbank_set_max_current(struct lm3533_ctrlbank *cb, u8 val); -extern int lm3533_ctrlbank_get_max_current(struct lm3533_ctrlbank *cb, - u8 *val); extern int lm3533_ctrlbank_set_pwm(struct lm3533_ctrlbank *cb, u8 val); extern int lm3533_ctrlbank_get_pwm(struct lm3533_ctrlbank *cb, u8 *val); -- cgit v1.2.3 From 6fa4b9d802610116adf4b89c2f9bd155829aafd3 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 10 May 2012 19:18:29 +0200 Subject: mfd: Use SI-units for the lm3533 max-current interface Use SI-units (uA) for max-current interface (5000 - 29800 uA). Signed-off-by: Johan Hovold Signed-off-by: Samuel Ortiz --- drivers/mfd/lm3533-ctrlbank.c | 43 +++++++++++++++++++++++++++++-------------- include/linux/mfd/lm3533.h | 7 ++++--- 2 files changed, 33 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/lm3533-ctrlbank.c b/drivers/mfd/lm3533-ctrlbank.c index adf4c1a542a9..a4cb7a5220a7 100644 --- a/drivers/mfd/lm3533-ctrlbank.c +++ b/drivers/mfd/lm3533-ctrlbank.c @@ -17,8 +17,11 @@ #include +#define LM3533_MAX_CURRENT_MIN 5000 +#define LM3533_MAX_CURRENT_MAX 29800 +#define LM3533_MAX_CURRENT_STEP 800 + #define LM3533_BRIGHTNESS_MAX 255 -#define LM3533_MAX_CURRENT_MAX 31 #define LM3533_PWM_MAX 0x3f #define LM3533_REG_PWM_BASE 0x14 @@ -65,6 +68,31 @@ int lm3533_ctrlbank_disable(struct lm3533_ctrlbank *cb) } EXPORT_SYMBOL_GPL(lm3533_ctrlbank_disable); +/* + * Full-scale current. + * + * imax 5000 - 29800 uA (800 uA step) + */ +int lm3533_ctrlbank_set_max_current(struct lm3533_ctrlbank *cb, u16 imax) +{ + u8 reg; + u8 val; + int ret; + + if (imax < LM3533_MAX_CURRENT_MIN || imax > LM3533_MAX_CURRENT_MAX) + return -EINVAL; + + val = (imax - LM3533_MAX_CURRENT_MIN) / LM3533_MAX_CURRENT_STEP; + + reg = lm3533_ctrlbank_get_reg(cb, LM3533_REG_MAX_CURRENT_BASE); + ret = lm3533_write(cb->lm3533, reg, val); + if (ret) + dev_err(cb->dev, "failed to set max current\n"); + + return ret; +} +EXPORT_SYMBOL_GPL(lm3533_ctrlbank_set_max_current); + #define lm3533_ctrlbank_set(_name, _NAME) \ int lm3533_ctrlbank_set_##_name(struct lm3533_ctrlbank *cb, u8 val) \ { \ @@ -101,19 +129,6 @@ EXPORT_SYMBOL_GPL(lm3533_ctrlbank_get_##_name); lm3533_ctrlbank_set(brightness, BRIGHTNESS); lm3533_ctrlbank_get(brightness, BRIGHTNESS); -/* - * Full scale current. - * - * Imax = 5 + val * 0.8 mA, e.g.: - * - * 0 - 5 mA - * ... - * 19 - 20.2 mA (default) - * ... - * 31 - 29.8 mA - */ -lm3533_ctrlbank_set(max_current, MAX_CURRENT); - /* * PWM-input control mask: * diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h index 7cfef9e4f41b..9660febe93c2 100644 --- a/include/linux/mfd/lm3533.h +++ b/include/linux/mfd/lm3533.h @@ -47,15 +47,15 @@ struct lm3533_als_platform_data { struct lm3533_bl_platform_data { char *name; + u16 max_current; /* 5000 - 29800 uA (800 uA step) */ u8 default_brightness; /* 0 - 255 */ - u8 max_current; /* 0 - 31 */ u8 pwm; /* 0 - 0x3f */ }; struct lm3533_led_platform_data { char *name; const char *default_trigger; - u8 max_current; /* 0 - 31 */ + u16 max_current; /* 5000 - 29800 uA (800 uA step) */ u8 pwm; /* 0 - 0x3f */ }; @@ -91,7 +91,8 @@ extern int lm3533_ctrlbank_disable(struct lm3533_ctrlbank *cb); extern int lm3533_ctrlbank_set_brightness(struct lm3533_ctrlbank *cb, u8 val); extern int lm3533_ctrlbank_get_brightness(struct lm3533_ctrlbank *cb, u8 *val); -extern int lm3533_ctrlbank_set_max_current(struct lm3533_ctrlbank *cb, u8 val); +extern int lm3533_ctrlbank_set_max_current(struct lm3533_ctrlbank *cb, + u16 imax); extern int lm3533_ctrlbank_set_pwm(struct lm3533_ctrlbank *cb, u8 val); extern int lm3533_ctrlbank_get_pwm(struct lm3533_ctrlbank *cb, u8 *val); -- cgit v1.2.3 From 83871c00bb43f41d85dd15aba56a83bbb191eabc Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 14 May 2012 22:50:39 +0200 Subject: mfd: Add MAX77693 driver This patch adds MFD driver for MAX77693 to enable its sub devices. The MAX77693 is a multi-function devices. It includes PMIC, MUIC(Micro USB Interface Controller), flash LED control and haptic motor control. Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham Signed-off-by: Kyungmin Park Reviewed-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/Kconfig | 12 ++ drivers/mfd/Makefile | 1 + drivers/mfd/max77693.c | 217 +++++++++++++++++++++++++++++++++++ include/linux/mfd/max77693-private.h | 217 +++++++++++++++++++++++++++++++++++ include/linux/mfd/max77693.h | 37 ++++++ 5 files changed, 484 insertions(+) create mode 100644 drivers/mfd/max77693.c create mode 100644 include/linux/mfd/max77693-private.h create mode 100644 include/linux/mfd/max77693.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index af46ce019fc7..a0e1b834af61 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -420,6 +420,18 @@ config PMIC_ADP5520 individual components like LCD backlight, LEDs, GPIOs and Kepad under the corresponding menus. +config MFD_MAX77693 + bool "Maxim Semiconductor MAX77693 PMIC Support" + depends on I2C=y && GENERIC_HARDIRQS + select MFD_CORE + help + Say yes here to support for Maxim Semiconductor MAX77693. + This is a companion Power Management IC with Flash, Haptic, Charger, + and MUIC(Micro USB Interface Controller) controls on chip. + This driver provides common support for accessing the device; + additional drivers must be enabled in order to use the functionality + of the device. + config MFD_MAX8925 bool "Maxim Semiconductor MAX8925 PMIC Support" depends on I2C=y && GENERIC_HARDIRQS diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index d3dae9567800..db0262b34af6 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -78,6 +78,7 @@ obj-$(CONFIG_PMIC_DA9052) += da9052-core.o obj-$(CONFIG_MFD_DA9052_SPI) += da9052-spi.o obj-$(CONFIG_MFD_DA9052_I2C) += da9052-i2c.o +obj-$(CONFIG_MFD_MAX77693) += max77693.o max8925-objs := max8925-core.o max8925-i2c.o obj-$(CONFIG_MFD_MAX8925) += max8925.o obj-$(CONFIG_MFD_MAX8997) += max8997.o max8997-irq.o diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c new file mode 100644 index 000000000000..c852515e68c8 --- /dev/null +++ b/drivers/mfd/max77693.c @@ -0,0 +1,217 @@ +/* + * max77693.c - mfd core driver for the MAX 77693 + * + * Copyright (C) 2012 Samsung Electronics + * SangYoung Son + * + * This program is not provided / owned by Maxim Integrated Products. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * This driver is based on max8997.c + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define I2C_ADDR_PMIC (0xCC >> 1) /* Charger, Flash LED */ +#define I2C_ADDR_MUIC (0x4A >> 1) +#define I2C_ADDR_HAPTIC (0x90 >> 1) + +static struct mfd_cell max77693_devs[] = { + { .name = "max77693-pmic", }, + { .name = "max77693-charger", }, + { .name = "max77693-flash", }, + { .name = "max77693-muic", }, + { .name = "max77693-haptic", }, +}; + +int max77693_read_reg(struct regmap *map, u8 reg, u8 *dest) +{ + unsigned int val; + int ret; + + ret = regmap_read(map, reg, &val); + *dest = val; + + return ret; +} +EXPORT_SYMBOL_GPL(max77693_read_reg); + +int max77693_bulk_read(struct regmap *map, u8 reg, int count, u8 *buf) +{ + int ret; + + ret = regmap_bulk_read(map, reg, buf, count); + + return ret; +} +EXPORT_SYMBOL_GPL(max77693_bulk_read); + +int max77693_write_reg(struct regmap *map, u8 reg, u8 value) +{ + int ret; + + ret = regmap_write(map, reg, value); + + return ret; +} +EXPORT_SYMBOL_GPL(max77693_write_reg); + +int max77693_bulk_write(struct regmap *map, u8 reg, int count, u8 *buf) +{ + int ret; + + ret = regmap_bulk_write(map, reg, buf, count); + + return ret; +} +EXPORT_SYMBOL_GPL(max77693_bulk_write); + +int max77693_update_reg(struct regmap *map, u8 reg, u8 val, u8 mask) +{ + int ret; + + ret = regmap_update_bits(map, reg, mask, val); + + return ret; +} +EXPORT_SYMBOL_GPL(max77693_update_reg); + +static const struct regmap_config max77693_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = MAX77693_PMIC_REG_END, +}; + +static int max77693_i2c_probe(struct i2c_client *i2c, + const struct i2c_device_id *id) +{ + struct max77693_dev *max77693; + struct max77693_platform_data *pdata = i2c->dev.platform_data; + u8 reg_data; + int ret = 0; + + max77693 = devm_kzalloc(&i2c->dev, + sizeof(struct max77693_dev), GFP_KERNEL); + if (max77693 == NULL) + return -ENOMEM; + + max77693->regmap = devm_regmap_init_i2c(i2c, &max77693_regmap_config); + if (IS_ERR(max77693->regmap)) { + ret = PTR_ERR(max77693->regmap); + dev_err(max77693->dev,"failed to allocate register map: %d\n", + ret); + goto err_regmap; + } + + i2c_set_clientdata(i2c, max77693); + max77693->dev = &i2c->dev; + max77693->i2c = i2c; + max77693->irq = i2c->irq; + max77693->type = id->driver_data; + + if (!pdata) + goto err_regmap; + + max77693->wakeup = pdata->wakeup; + + mutex_init(&max77693->iolock); + + if (max77693_read_reg(max77693->regmap, + MAX77693_PMIC_REG_PMIC_ID2, ®_data) < 0) { + dev_err(max77693->dev, "device not found on this channel\n"); + ret = -ENODEV; + goto err_regmap; + } else + dev_info(max77693->dev, "device ID: 0x%x\n", reg_data); + + max77693->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC); + i2c_set_clientdata(max77693->muic, max77693); + + max77693->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC); + i2c_set_clientdata(max77693->haptic, max77693); + + pm_runtime_set_active(max77693->dev); + + ret = mfd_add_devices(max77693->dev, -1, max77693_devs, + ARRAY_SIZE(max77693_devs), NULL, 0); + if (ret < 0) + goto err_mfd; + + return ret; + +err_mfd: + i2c_unregister_device(max77693->muic); + i2c_unregister_device(max77693->haptic); +err_regmap: + kfree(max77693); + + return ret; +} + +static int max77693_i2c_remove(struct i2c_client *i2c) +{ + struct max77693_dev *max77693 = i2c_get_clientdata(i2c); + + mfd_remove_devices(max77693->dev); + i2c_unregister_device(max77693->muic); + i2c_unregister_device(max77693->haptic); + + return 0; +} + +static const struct i2c_device_id max77693_i2c_id[] = { + { "max77693", TYPE_MAX77693 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, max77693_i2c_id); + +static struct i2c_driver max77693_i2c_driver = { + .driver = { + .name = "max77693", + .owner = THIS_MODULE, + }, + .probe = max77693_i2c_probe, + .remove = max77693_i2c_remove, + .id_table = max77693_i2c_id, +}; + +static int __init max77693_i2c_init(void) +{ + return i2c_add_driver(&max77693_i2c_driver); +} +/* init early so consumer devices can complete system boot */ +subsys_initcall(max77693_i2c_init); + +static void __exit max77693_i2c_exit(void) +{ + i2c_del_driver(&max77693_i2c_driver); +} +module_exit(max77693_i2c_exit); + +MODULE_DESCRIPTION("MAXIM 77693 multi-function core driver"); +MODULE_AUTHOR("SangYoung, Son "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h new file mode 100644 index 000000000000..bf6077d3c43c --- /dev/null +++ b/include/linux/mfd/max77693-private.h @@ -0,0 +1,217 @@ +/* + * max77693-private.h - Voltage regulator driver for the Maxim 77693 + * + * Copyright (C) 2012 Samsung Electrnoics + * SangYoung Son + * + * This program is not provided / owned by Maxim Integrated Products. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __LINUX_MFD_MAX77693_PRIV_H +#define __LINUX_MFD_MAX77693_PRIV_H + +#include + +#define MAX77693_NUM_IRQ_MUIC_REGS 3 +#define MAX77693_REG_INVALID (0xff) + +/* Slave addr = 0xCC: PMIC, Charger, Flash LED */ +enum max77693_pmic_reg { + MAX77693_LED_REG_IFLASH1 = 0x00, + MAX77693_LED_REG_IFLASH2 = 0x01, + MAX77693_LED_REG_ITORCH = 0x02, + MAX77693_LED_REG_ITORCHTIMER = 0x03, + MAX77693_LED_REG_FLASH_TIMER = 0x04, + MAX77693_LED_REG_FLASH_EN = 0x05, + MAX77693_LED_REG_MAX_FLASH1 = 0x06, + MAX77693_LED_REG_MAX_FLASH2 = 0x07, + MAX77693_LED_REG_MAX_FLASH3 = 0x08, + MAX77693_LED_REG_MAX_FLASH4 = 0x09, + MAX77693_LED_REG_VOUT_CNTL = 0x0A, + MAX77693_LED_REG_VOUT_FLASH1 = 0x0B, + MAX77693_LED_REG_VOUT_FLASH2 = 0x0C, + MAX77693_LED_REG_FLASH_INT = 0x0E, + MAX77693_LED_REG_FLASH_INT_MASK = 0x0F, + MAX77693_LED_REG_FLASH_INT_STATUS = 0x10, + + MAX77693_PMIC_REG_PMIC_ID1 = 0x20, + MAX77693_PMIC_REG_PMIC_ID2 = 0x21, + MAX77693_PMIC_REG_INTSRC = 0x22, + MAX77693_PMIC_REG_INTSRC_MASK = 0x23, + MAX77693_PMIC_REG_TOPSYS_INT = 0x24, + MAX77693_PMIC_REG_TOPSYS_INT_MASK = 0x26, + MAX77693_PMIC_REG_TOPSYS_STAT = 0x28, + MAX77693_PMIC_REG_MAINCTRL1 = 0x2A, + MAX77693_PMIC_REG_LSCNFG = 0x2B, + + MAX77693_CHG_REG_CHG_INT = 0xB0, + MAX77693_CHG_REG_CHG_INT_MASK = 0xB1, + MAX77693_CHG_REG_CHG_INT_OK = 0xB2, + MAX77693_CHG_REG_CHG_DETAILS_00 = 0xB3, + MAX77693_CHG_REG_CHG_DETAILS_01 = 0xB4, + MAX77693_CHG_REG_CHG_DETAILS_02 = 0xB5, + MAX77693_CHG_REG_CHG_DETAILS_03 = 0xB6, + MAX77693_CHG_REG_CHG_CNFG_00 = 0xB7, + MAX77693_CHG_REG_CHG_CNFG_01 = 0xB8, + MAX77693_CHG_REG_CHG_CNFG_02 = 0xB9, + MAX77693_CHG_REG_CHG_CNFG_03 = 0xBA, + MAX77693_CHG_REG_CHG_CNFG_04 = 0xBB, + MAX77693_CHG_REG_CHG_CNFG_05 = 0xBC, + MAX77693_CHG_REG_CHG_CNFG_06 = 0xBD, + MAX77693_CHG_REG_CHG_CNFG_07 = 0xBE, + MAX77693_CHG_REG_CHG_CNFG_08 = 0xBF, + MAX77693_CHG_REG_CHG_CNFG_09 = 0xC0, + MAX77693_CHG_REG_CHG_CNFG_10 = 0xC1, + MAX77693_CHG_REG_CHG_CNFG_11 = 0xC2, + MAX77693_CHG_REG_CHG_CNFG_12 = 0xC3, + MAX77693_CHG_REG_CHG_CNFG_13 = 0xC4, + MAX77693_CHG_REG_CHG_CNFG_14 = 0xC5, + MAX77693_CHG_REG_SAFEOUT_CTRL = 0xC6, + + MAX77693_PMIC_REG_END, +}; + +/* Slave addr = 0x4A: MUIC */ +enum max77693_muic_reg { + MAX77693_MUIC_REG_ID = 0x00, + MAX77693_MUIC_REG_INT1 = 0x01, + MAX77693_MUIC_REG_INT2 = 0x02, + MAX77693_MUIC_REG_INT3 = 0x03, + MAX77693_MUIC_REG_STATUS1 = 0x04, + MAX77693_MUIC_REG_STATUS2 = 0x05, + MAX77693_MUIC_REG_STATUS3 = 0x06, + MAX77693_MUIC_REG_INTMASK1 = 0x07, + MAX77693_MUIC_REG_INTMASK2 = 0x08, + MAX77693_MUIC_REG_INTMASK3 = 0x09, + MAX77693_MUIC_REG_CDETCTRL1 = 0x0A, + MAX77693_MUIC_REG_CDETCTRL2 = 0x0B, + MAX77693_MUIC_REG_CTRL1 = 0x0C, + MAX77693_MUIC_REG_CTRL2 = 0x0D, + MAX77693_MUIC_REG_CTRL3 = 0x0E, + + MAX77693_MUIC_REG_END, +}; + +/* Slave addr = 0x90: Haptic */ +enum max77693_haptic_reg { + MAX77693_HAPTIC_REG_STATUS = 0x00, + MAX77693_HAPTIC_REG_CONFIG1 = 0x01, + MAX77693_HAPTIC_REG_CONFIG2 = 0x02, + MAX77693_HAPTIC_REG_CONFIG_CHNL = 0x03, + MAX77693_HAPTIC_REG_CONFG_CYC1 = 0x04, + MAX77693_HAPTIC_REG_CONFG_CYC2 = 0x05, + MAX77693_HAPTIC_REG_CONFIG_PER1 = 0x06, + MAX77693_HAPTIC_REG_CONFIG_PER2 = 0x07, + MAX77693_HAPTIC_REG_CONFIG_PER3 = 0x08, + MAX77693_HAPTIC_REG_CONFIG_PER4 = 0x09, + MAX77693_HAPTIC_REG_CONFIG_DUTY1 = 0x0A, + MAX77693_HAPTIC_REG_CONFIG_DUTY2 = 0x0B, + MAX77693_HAPTIC_REG_CONFIG_PWM1 = 0x0C, + MAX77693_HAPTIC_REG_CONFIG_PWM2 = 0x0D, + MAX77693_HAPTIC_REG_CONFIG_PWM3 = 0x0E, + MAX77693_HAPTIC_REG_CONFIG_PWM4 = 0x0F, + MAX77693_HAPTIC_REG_REV = 0x10, + + MAX77693_HAPTIC_REG_END, +}; + +enum max77693_irq_source { + LED_INT = 0, + TOPSYS_INT, + CHG_INT, + MUIC_INT1, + MUIC_INT2, + MUIC_INT3, + + MAX77693_IRQ_GROUP_NR, +}; + +enum max77693_irq { + /* PMIC - FLASH */ + MAX77693_LED_IRQ_FLED2_OPEN, + MAX77693_LED_IRQ_FLED2_SHORT, + MAX77693_LED_IRQ_FLED1_OPEN, + MAX77693_LED_IRQ_FLED1_SHORT, + MAX77693_LED_IRQ_MAX_FLASH, + + /* PMIC - TOPSYS */ + MAX77693_TOPSYS_IRQ_T120C_INT, + MAX77693_TOPSYS_IRQ_T140C_INT, + MAX77693_TOPSYS_IRQ_LOWSYS_INT, + + /* PMIC - Charger */ + MAX77693_CHG_IRQ_BYP_I, + MAX77693_CHG_IRQ_THM_I, + MAX77693_CHG_IRQ_BAT_I, + MAX77693_CHG_IRQ_CHG_I, + MAX77693_CHG_IRQ_CHGIN_I, + + /* MUIC INT1 */ + MAX77693_MUIC_IRQ_INT1_ADC, + MAX77693_MUIC_IRQ_INT1_ADC_LOW, + MAX77693_MUIC_IRQ_INT1_ADC_ERR, + MAX77693_MUIC_IRQ_INT1_ADC1K, + + /* MUIC INT2 */ + MAX77693_MUIC_IRQ_INT2_CHGTYP, + MAX77693_MUIC_IRQ_INT2_CHGDETREUN, + MAX77693_MUIC_IRQ_INT2_DCDTMR, + MAX77693_MUIC_IRQ_INT2_DXOVP, + MAX77693_MUIC_IRQ_INT2_VBVOLT, + MAX77693_MUIC_IRQ_INT2_VIDRM, + + /* MUIC INT3 */ + MAX77693_MUIC_IRQ_INT3_EOC, + MAX77693_MUIC_IRQ_INT3_CGMBC, + MAX77693_MUIC_IRQ_INT3_OVP, + MAX77693_MUIC_IRQ_INT3_MBCCHG_ERR, + MAX77693_MUIC_IRQ_INT3_CHG_ENABLED, + MAX77693_MUIC_IRQ_INT3_BAT_DET, + + MAX77693_IRQ_NR, +}; + +struct max77693_dev { + struct device *dev; + struct i2c_client *i2c; /* 0xCC , PMIC, Charger, Flash LED */ + struct i2c_client *muic; /* 0x4A , MUIC */ + struct i2c_client *haptic; /* 0x90 , Haptic */ + struct mutex iolock; + + int type; + + struct regmap *regmap; + struct regmap *regmap_muic; + struct regmap *regmap_haptic; + + int irq; + bool wakeup; +}; + +enum max77693_types { + TYPE_MAX77693, +}; + +extern int max77693_read_reg(struct regmap *map, u8 reg, u8 *dest); +extern int max77693_bulk_read(struct regmap *map, u8 reg, int count, + u8 *buf); +extern int max77693_write_reg(struct regmap *map, u8 reg, u8 value); +extern int max77693_bulk_write(struct regmap *map, u8 reg, int count, + u8 *buf); +extern int max77693_update_reg(struct regmap *map, u8 reg, u8 val, u8 mask); + +#endif /* __LINUX_MFD_MAX77693_PRIV_H */ diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h new file mode 100644 index 000000000000..5020b8616daa --- /dev/null +++ b/include/linux/mfd/max77693.h @@ -0,0 +1,37 @@ +/* + * max77693.h - Driver for the Maxim 77693 + * + * Copyright (C) 2012 Samsung Electrnoics + * SangYoung Son + * + * This program is not provided / owned by Maxim Integrated Products. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * This driver is based on max8997.h + * + * MAX77693 has PMIC, Charger, Flash LED, Haptic, MUIC devices. + * The devices share the same I2C bus and included in + * this mfd driver. + */ + +#ifndef __LINUX_MFD_MAX77693_H +#define __LINUX_MFD_MAX77693_H + +struct max77693_platform_data { + /* IRQ */ + int wakeup; +}; +#endif /* __LINUX_MFD_MAX77693_H */ -- cgit v1.2.3 From 6592ebb3979c1ec0e37eb06553ef5ce9d6f5f025 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 14 May 2012 22:54:20 +0200 Subject: mfd: Add MAX77693 irq handler This patch supports IRQ handling for MAX77693. Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham Signed-off-by: Kyungmin Park Signed-off-by: Samuel Ortiz --- drivers/mfd/Makefile | 2 +- drivers/mfd/max77693-irq.c | 309 +++++++++++++++++++++++++++++++++++++++++++ drivers/mfd/max77693.c | 32 +++++ include/linux/mfd/max77693.h | 1 - 4 files changed, 342 insertions(+), 2 deletions(-) create mode 100644 drivers/mfd/max77693-irq.c (limited to 'include/linux') diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index db0262b34af6..d7138510c880 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -78,7 +78,7 @@ obj-$(CONFIG_PMIC_DA9052) += da9052-core.o obj-$(CONFIG_MFD_DA9052_SPI) += da9052-spi.o obj-$(CONFIG_MFD_DA9052_I2C) += da9052-i2c.o -obj-$(CONFIG_MFD_MAX77693) += max77693.o +obj-$(CONFIG_MFD_MAX77693) += max77693.o max77693-irq.o max8925-objs := max8925-core.o max8925-i2c.o obj-$(CONFIG_MFD_MAX8925) += max8925.o obj-$(CONFIG_MFD_MAX8997) += max8997.o max8997-irq.o diff --git a/drivers/mfd/max77693-irq.c b/drivers/mfd/max77693-irq.c new file mode 100644 index 000000000000..2b403569e0a6 --- /dev/null +++ b/drivers/mfd/max77693-irq.c @@ -0,0 +1,309 @@ +/* + * max77693-irq.c - Interrupt controller support for MAX77693 + * + * Copyright (C) 2012 Samsung Electronics Co.Ltd + * SangYoung Son + * + * This program is not provided / owned by Maxim Integrated Products. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * This driver is based on max8997-irq.c + */ + +#include +#include +#include +#include +#include +#include +#include + +static const u8 max77693_mask_reg[] = { + [LED_INT] = MAX77693_LED_REG_FLASH_INT_MASK, + [TOPSYS_INT] = MAX77693_PMIC_REG_TOPSYS_INT_MASK, + [CHG_INT] = MAX77693_CHG_REG_CHG_INT_MASK, + [MUIC_INT1] = MAX77693_MUIC_REG_INTMASK1, + [MUIC_INT2] = MAX77693_MUIC_REG_INTMASK2, + [MUIC_INT3] = MAX77693_MUIC_REG_INTMASK3, +}; + +static struct regmap *max77693_get_regmap(struct max77693_dev *max77693, + enum max77693_irq_source src) +{ + switch (src) { + case LED_INT ... CHG_INT: + return max77693->regmap; + case MUIC_INT1 ... MUIC_INT3: + return max77693->regmap_muic; + default: + return ERR_PTR(-EINVAL); + } +} + +struct max77693_irq_data { + int mask; + enum max77693_irq_source group; +}; + +#define DECLARE_IRQ(idx, _group, _mask) \ + [(idx)] = { .group = (_group), .mask = (_mask) } +static const struct max77693_irq_data max77693_irqs[] = { + DECLARE_IRQ(MAX77693_LED_IRQ_FLED2_OPEN, LED_INT, 1 << 0), + DECLARE_IRQ(MAX77693_LED_IRQ_FLED2_SHORT, LED_INT, 1 << 1), + DECLARE_IRQ(MAX77693_LED_IRQ_FLED1_OPEN, LED_INT, 1 << 2), + DECLARE_IRQ(MAX77693_LED_IRQ_FLED1_SHORT, LED_INT, 1 << 3), + DECLARE_IRQ(MAX77693_LED_IRQ_MAX_FLASH, LED_INT, 1 << 4), + + DECLARE_IRQ(MAX77693_TOPSYS_IRQ_T120C_INT, TOPSYS_INT, 1 << 0), + DECLARE_IRQ(MAX77693_TOPSYS_IRQ_T140C_INT, TOPSYS_INT, 1 << 1), + DECLARE_IRQ(MAX77693_TOPSYS_IRQ_LOWSYS_INT, TOPSYS_INT, 1 << 3), + + DECLARE_IRQ(MAX77693_CHG_IRQ_BYP_I, CHG_INT, 1 << 0), + DECLARE_IRQ(MAX77693_CHG_IRQ_THM_I, CHG_INT, 1 << 2), + DECLARE_IRQ(MAX77693_CHG_IRQ_BAT_I, CHG_INT, 1 << 3), + DECLARE_IRQ(MAX77693_CHG_IRQ_CHG_I, CHG_INT, 1 << 4), + DECLARE_IRQ(MAX77693_CHG_IRQ_CHGIN_I, CHG_INT, 1 << 6), + + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT1_ADC, MUIC_INT1, 1 << 0), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT1_ADC_LOW, MUIC_INT1, 1 << 1), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT1_ADC_ERR, MUIC_INT1, 1 << 2), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT1_ADC1K, MUIC_INT1, 1 << 3), + + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_CHGTYP, MUIC_INT2, 1 << 0), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_CHGDETREUN, MUIC_INT2, 1 << 1), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_DCDTMR, MUIC_INT2, 1 << 2), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_DXOVP, MUIC_INT2, 1 << 3), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_VBVOLT, MUIC_INT2, 1 << 4), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_VIDRM, MUIC_INT2, 1 << 5), + + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_EOC, MUIC_INT3, 1 << 0), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_CGMBC, MUIC_INT3, 1 << 1), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_OVP, MUIC_INT3, 1 << 2), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_MBCCHG_ERR, MUIC_INT3, 1 << 3), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_CHG_ENABLED, MUIC_INT3, 1 << 4), + DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_BAT_DET, MUIC_INT3, 1 << 5), +}; + +static void max77693_irq_lock(struct irq_data *data) +{ + struct max77693_dev *max77693 = irq_get_chip_data(data->irq); + + mutex_lock(&max77693->irqlock); +} + +static void max77693_irq_sync_unlock(struct irq_data *data) +{ + struct max77693_dev *max77693 = irq_get_chip_data(data->irq); + int i; + + for (i = 0; i < MAX77693_IRQ_GROUP_NR; i++) { + u8 mask_reg = max77693_mask_reg[i]; + struct regmap *map = max77693_get_regmap(max77693, i); + + if (mask_reg == MAX77693_REG_INVALID || + IS_ERR_OR_NULL(map)) + continue; + max77693->irq_masks_cache[i] = max77693->irq_masks_cur[i]; + + max77693_write_reg(map, max77693_mask_reg[i], + max77693->irq_masks_cur[i]); + } + + mutex_unlock(&max77693->irqlock); +} + +static const inline struct max77693_irq_data * +irq_to_max77693_irq(struct max77693_dev *max77693, int irq) +{ + return &max77693_irqs[irq]; +} + +static void max77693_irq_mask(struct irq_data *data) +{ + struct max77693_dev *max77693 = irq_get_chip_data(data->irq); + const struct max77693_irq_data *irq_data = + irq_to_max77693_irq(max77693, data->irq); + + if (irq_data->group >= MUIC_INT1 && irq_data->group <= MUIC_INT3) + max77693->irq_masks_cur[irq_data->group] &= ~irq_data->mask; + else + max77693->irq_masks_cur[irq_data->group] |= irq_data->mask; +} + +static void max77693_irq_unmask(struct irq_data *data) +{ + struct max77693_dev *max77693 = irq_get_chip_data(data->irq); + const struct max77693_irq_data *irq_data = + irq_to_max77693_irq(max77693, data->irq); + + if (irq_data->group >= MUIC_INT1 && irq_data->group <= MUIC_INT3) + max77693->irq_masks_cur[irq_data->group] |= irq_data->mask; + else + max77693->irq_masks_cur[irq_data->group] &= ~irq_data->mask; +} + +static struct irq_chip max77693_irq_chip = { + .name = "max77693", + .irq_bus_lock = max77693_irq_lock, + .irq_bus_sync_unlock = max77693_irq_sync_unlock, + .irq_mask = max77693_irq_mask, + .irq_unmask = max77693_irq_unmask, +}; + +#define MAX77693_IRQSRC_CHG (1 << 0) +#define MAX77693_IRQSRC_TOP (1 << 1) +#define MAX77693_IRQSRC_FLASH (1 << 2) +#define MAX77693_IRQSRC_MUIC (1 << 3) +static irqreturn_t max77693_irq_thread(int irq, void *data) +{ + struct max77693_dev *max77693 = data; + u8 irq_reg[MAX77693_IRQ_GROUP_NR] = {}; + u8 irq_src; + int ret; + int i, cur_irq; + + ret = max77693_read_reg(max77693->regmap, MAX77693_PMIC_REG_INTSRC, + &irq_src); + if (ret < 0) { + dev_err(max77693->dev, "Failed to read interrupt source: %d\n", + ret); + return IRQ_NONE; + } + + if (irq_src & MAX77693_IRQSRC_CHG) + /* CHG_INT */ + ret = max77693_read_reg(max77693->regmap, MAX77693_CHG_REG_CHG_INT, + &irq_reg[CHG_INT]); + + if (irq_src & MAX77693_IRQSRC_TOP) + /* TOPSYS_INT */ + ret = max77693_read_reg(max77693->regmap, + MAX77693_PMIC_REG_TOPSYS_INT, &irq_reg[TOPSYS_INT]); + + if (irq_src & MAX77693_IRQSRC_FLASH) + /* LED_INT */ + ret = max77693_read_reg(max77693->regmap, + MAX77693_LED_REG_FLASH_INT, &irq_reg[LED_INT]); + + if (irq_src & MAX77693_IRQSRC_MUIC) + /* MUIC INT1 ~ INT3 */ + max77693_bulk_read(max77693->regmap, MAX77693_MUIC_REG_INT1, + MAX77693_NUM_IRQ_MUIC_REGS, &irq_reg[MUIC_INT1]); + + /* Apply masking */ + for (i = 0; i < MAX77693_IRQ_GROUP_NR; i++) { + if (i >= MUIC_INT1 && i <= MUIC_INT3) + irq_reg[i] &= max77693->irq_masks_cur[i]; + else + irq_reg[i] &= ~max77693->irq_masks_cur[i]; + } + + /* Report */ + for (i = 0; i < MAX77693_IRQ_NR; i++) { + if (irq_reg[max77693_irqs[i].group] & max77693_irqs[i].mask) { + cur_irq = irq_find_mapping(max77693->irq_domain, i); + if (cur_irq) + handle_nested_irq(cur_irq); + } + } + + return IRQ_HANDLED; +} + +int max77693_irq_resume(struct max77693_dev *max77693) +{ + if (max77693->irq) + max77693_irq_thread(0, max77693); + + return 0; +} + +static int max77693_irq_domain_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hw) +{ + struct max77693_dev *max77693 = d->host_data; + + irq_set_chip_data(irq, max77693); + irq_set_chip_and_handler(irq, &max77693_irq_chip, handle_edge_irq); + irq_set_nested_thread(irq, 1); +#ifdef CONFIG_ARM + set_irq_flags(irq, IRQF_VALID); +#else + irq_set_noprobe(irq); +#endif + return 0; +} + +static struct irq_domain_ops max77693_irq_domain_ops = { + .map = max77693_irq_domain_map, +}; + +int max77693_irq_init(struct max77693_dev *max77693) +{ + struct irq_domain *domain; + int i; + int ret; + + mutex_init(&max77693->irqlock); + + /* Mask individual interrupt sources */ + for (i = 0; i < MAX77693_IRQ_GROUP_NR; i++) { + struct regmap *map; + /* MUIC IRQ 0:MASK 1:NOT MASK */ + /* Other IRQ 1:MASK 0:NOT MASK */ + if (i >= MUIC_INT1 && i <= MUIC_INT3) { + max77693->irq_masks_cur[i] = 0x00; + max77693->irq_masks_cache[i] = 0x00; + } else { + max77693->irq_masks_cur[i] = 0xff; + max77693->irq_masks_cache[i] = 0xff; + } + map = max77693_get_regmap(max77693, i); + + if (IS_ERR_OR_NULL(map)) + continue; + if (max77693_mask_reg[i] == MAX77693_REG_INVALID) + continue; + if (i >= MUIC_INT1 && i <= MUIC_INT3) + max77693_write_reg(map, max77693_mask_reg[i], 0x00); + else + max77693_write_reg(map, max77693_mask_reg[i], 0xff); + } + + domain = irq_domain_add_linear(NULL, MAX77693_IRQ_NR, + &max77693_irq_domain_ops, max77693); + if (!domain) { + dev_err(max77693->dev, "could not create irq domain\n"); + return -ENODEV; + } + max77693->irq_domain = domain; + + ret = request_threaded_irq(max77693->irq, NULL, max77693_irq_thread, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + "max77693-irq", max77693); + + if (ret) + dev_err(max77693->dev, "Failed to request IRQ %d: %d\n", + max77693->irq, ret); + + return 0; +} + +void max77693_irq_exit(struct max77693_dev *max77693) +{ + if (max77693->irq) + free_irq(max77693->irq, max77693); +} diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c index c852515e68c8..e9e4278722f3 100644 --- a/drivers/mfd/max77693.c +++ b/drivers/mfd/max77693.c @@ -154,6 +154,10 @@ static int max77693_i2c_probe(struct i2c_client *i2c, max77693->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC); i2c_set_clientdata(max77693->haptic, max77693); + ret = max77693_irq_init(max77693); + if (ret < 0) + goto err_mfd; + pm_runtime_set_active(max77693->dev); ret = mfd_add_devices(max77693->dev, -1, max77693_devs, @@ -161,6 +165,8 @@ static int max77693_i2c_probe(struct i2c_client *i2c, if (ret < 0) goto err_mfd; + device_init_wakeup(max77693->dev, pdata->wakeup); + return ret; err_mfd: @@ -189,10 +195,36 @@ static const struct i2c_device_id max77693_i2c_id[] = { }; MODULE_DEVICE_TABLE(i2c, max77693_i2c_id); +static int max77693_suspend(struct device *dev) +{ + struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct max77693_dev *max77693 = i2c_get_clientdata(i2c); + + if (device_may_wakeup(dev)) + irq_set_irq_wake(max77693->irq, 1); + return 0; +} + +static int max77693_resume(struct device *dev) +{ + struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); + struct max77693_dev *max77693 = i2c_get_clientdata(i2c); + + if (device_may_wakeup(dev)) + irq_set_irq_wake(max77693->irq, 0); + return max77693_irq_resume(max77693); +} + +const struct dev_pm_ops max77693_pm = { + .suspend = max77693_suspend, + .resume = max77693_resume, +}; + static struct i2c_driver max77693_i2c_driver = { .driver = { .name = "max77693", .owner = THIS_MODULE, + .pm = &max77693_pm, }, .probe = max77693_i2c_probe, .remove = max77693_i2c_remove, diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h index 5020b8616daa..1d28ae90384e 100644 --- a/include/linux/mfd/max77693.h +++ b/include/linux/mfd/max77693.h @@ -31,7 +31,6 @@ #define __LINUX_MFD_MAX77693_H struct max77693_platform_data { - /* IRQ */ int wakeup; }; #endif /* __LINUX_MFD_MAX77693_H */ -- cgit v1.2.3 From cd99758ba3bde64347a8ece381cbae2fb5c745b2 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 14 May 2012 23:14:24 +0200 Subject: mfd: Convert wm831x to irq_domain The modern idiom is to use irq_domain to allocate interrupts. This is useful partly to allow further infrastructure to be based on the domains and partly because it makes it much easier to allocate virtual interrupts to devices as we don't need to allocate a contiguous range of interrupt numbers. Convert the wm831x driver over to this infrastructure, using a legacy IRQ mapping if an irq_base is specified in platform data and otherwise using a linear mapping, always registering the interrupts even if they won't ever be used. Only boards which need to use the GPIOs as interrupts should need to use an irq_base. This means that we can't use the MFD irq_base management since the unless we're using an explicit irq_base from platform data we can't rely on a linear mapping of interrupts. Instead we need to map things via the irq_domain - provide a conveniencem function wm831x_irq() to save a small amount of typing when doing so. Looking at this I couldn't clearly see anything the MFD core could do to make this nicer. Since we're not supporting device tree yet there's no meaningful advantage if we don't do this conversion in one, the fact that the interrupt resources are used for repeated IP blocks makes accessor functions for the irq_domain more trouble to do than they're worth. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/gpio/gpio-wm831x.c | 6 +- drivers/input/misc/wm831x-on.c | 2 +- drivers/input/touchscreen/wm831x-ts.c | 9 +-- drivers/mfd/Kconfig | 2 + drivers/mfd/wm831x-auxadc.c | 6 +- drivers/mfd/wm831x-core.c | 19 +++---- drivers/mfd/wm831x-irq.c | 101 +++++++++++++++++++++------------- drivers/power/wm831x_power.c | 21 ++++--- drivers/regulator/wm831x-dcdc.c | 24 +++++--- drivers/regulator/wm831x-isink.c | 4 +- drivers/regulator/wm831x-ldo.c | 10 ++-- drivers/rtc/rtc-wm831x.c | 2 +- include/linux/mfd/wm831x/core.h | 9 ++- 13 files changed, 131 insertions(+), 84 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-wm831x.c b/drivers/gpio/gpio-wm831x.c index deb949e75ec1..e56a2165641c 100644 --- a/drivers/gpio/gpio-wm831x.c +++ b/drivers/gpio/gpio-wm831x.c @@ -102,10 +102,8 @@ static int wm831x_gpio_to_irq(struct gpio_chip *chip, unsigned offset) struct wm831x_gpio *wm831x_gpio = to_wm831x_gpio(chip); struct wm831x *wm831x = wm831x_gpio->wm831x; - if (!wm831x->irq_base) - return -EINVAL; - - return wm831x->irq_base + WM831X_IRQ_GPIO_1 + offset; + return irq_create_mapping(wm831x->irq_domain, + WM831X_IRQ_GPIO_1 + offset); } static int wm831x_gpio_set_debounce(struct gpio_chip *chip, unsigned offset, diff --git a/drivers/input/misc/wm831x-on.c b/drivers/input/misc/wm831x-on.c index 47f18d6bce46..6790a812a1db 100644 --- a/drivers/input/misc/wm831x-on.c +++ b/drivers/input/misc/wm831x-on.c @@ -73,7 +73,7 @@ static int __devinit wm831x_on_probe(struct platform_device *pdev) { struct wm831x *wm831x = dev_get_drvdata(pdev->dev.parent); struct wm831x_on *wm831x_on; - int irq = platform_get_irq(pdev, 0); + int irq = wm831x_irq(wm831x, platform_get_irq(pdev, 0)); int ret; wm831x_on = kzalloc(sizeof(struct wm831x_on), GFP_KERNEL); diff --git a/drivers/input/touchscreen/wm831x-ts.c b/drivers/input/touchscreen/wm831x-ts.c index 4bc851a9dc3d..e83410721e38 100644 --- a/drivers/input/touchscreen/wm831x-ts.c +++ b/drivers/input/touchscreen/wm831x-ts.c @@ -260,15 +260,16 @@ static __devinit int wm831x_ts_probe(struct platform_device *pdev) * If we have a direct IRQ use it, otherwise use the interrupt * from the WM831x IRQ controller. */ + wm831x_ts->data_irq = wm831x_irq(wm831x, + platform_get_irq_byname(pdev, + "TCHDATA")); if (pdata && pdata->data_irq) wm831x_ts->data_irq = pdata->data_irq; - else - wm831x_ts->data_irq = platform_get_irq_byname(pdev, "TCHDATA"); + wm831x_ts->pd_irq = wm831x_irq(wm831x, + platform_get_irq_byname(pdev, "TCHPD")); if (pdata && pdata->pd_irq) wm831x_ts->pd_irq = pdata->pd_irq; - else - wm831x_ts->pd_irq = platform_get_irq_byname(pdev, "TCHPD"); if (pdata) wm831x_ts->pressure = pdata->pressure; diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index a0e1b834af61..8325c44c04c6 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -496,6 +496,7 @@ config MFD_WM831X_I2C select MFD_CORE select MFD_WM831X select REGMAP_I2C + select IRQ_DOMAIN depends on I2C=y && GENERIC_HARDIRQS help Support for the Wolfson Microelecronics WM831x and WM832x PMICs @@ -508,6 +509,7 @@ config MFD_WM831X_SPI select MFD_CORE select MFD_WM831X select REGMAP_SPI + select IRQ_DOMAIN depends on SPI_MASTER && GENERIC_HARDIRQS help Support for the Wolfson Microelecronics WM831x and WM832x PMICs diff --git a/drivers/mfd/wm831x-auxadc.c b/drivers/mfd/wm831x-auxadc.c index 87210954a066..6ee3018d8653 100644 --- a/drivers/mfd/wm831x-auxadc.c +++ b/drivers/mfd/wm831x-auxadc.c @@ -280,11 +280,11 @@ void wm831x_auxadc_init(struct wm831x *wm831x) mutex_init(&wm831x->auxadc_lock); INIT_LIST_HEAD(&wm831x->auxadc_pending); - if (wm831x->irq && wm831x->irq_base) { + if (wm831x->irq) { wm831x->auxadc_read = wm831x_auxadc_read_irq; - ret = request_threaded_irq(wm831x->irq_base + - WM831X_IRQ_AUXADC_DATA, + ret = request_threaded_irq(wm831x_irq(wm831x, + WM831X_IRQ_AUXADC_DATA), NULL, wm831x_auxadc_irq, 0, "auxadc", wm831x); if (ret < 0) { diff --git a/drivers/mfd/wm831x-core.c b/drivers/mfd/wm831x-core.c index 476e4d31a823..946698fd2dc6 100644 --- a/drivers/mfd/wm831x-core.c +++ b/drivers/mfd/wm831x-core.c @@ -1813,27 +1813,27 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq) case WM8310: ret = mfd_add_devices(wm831x->dev, wm831x_num, wm8310_devs, ARRAY_SIZE(wm8310_devs), - NULL, wm831x->irq_base); + NULL, 0); break; case WM8311: ret = mfd_add_devices(wm831x->dev, wm831x_num, wm8311_devs, ARRAY_SIZE(wm8311_devs), - NULL, wm831x->irq_base); + NULL, 0); if (!pdata || !pdata->disable_touch) mfd_add_devices(wm831x->dev, wm831x_num, touch_devs, ARRAY_SIZE(touch_devs), - NULL, wm831x->irq_base); + NULL, 0); break; case WM8312: ret = mfd_add_devices(wm831x->dev, wm831x_num, wm8312_devs, ARRAY_SIZE(wm8312_devs), - NULL, wm831x->irq_base); + NULL, 0); if (!pdata || !pdata->disable_touch) mfd_add_devices(wm831x->dev, wm831x_num, touch_devs, ARRAY_SIZE(touch_devs), - NULL, wm831x->irq_base); + NULL, 0); break; case WM8320: @@ -1842,7 +1842,7 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq) case WM8326: ret = mfd_add_devices(wm831x->dev, wm831x_num, wm8320_devs, ARRAY_SIZE(wm8320_devs), - NULL, wm831x->irq_base); + NULL, 0); break; default: @@ -1867,7 +1867,7 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq) if (ret & WM831X_XTAL_ENA) { ret = mfd_add_devices(wm831x->dev, wm831x_num, rtc_devs, ARRAY_SIZE(rtc_devs), - NULL, wm831x->irq_base); + NULL, 0); if (ret != 0) { dev_err(wm831x->dev, "Failed to add RTC: %d\n", ret); goto err_irq; @@ -1880,7 +1880,7 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq) /* Treat errors as non-critical */ ret = mfd_add_devices(wm831x->dev, wm831x_num, backlight_devs, ARRAY_SIZE(backlight_devs), NULL, - wm831x->irq_base); + 0); if (ret < 0) dev_err(wm831x->dev, "Failed to add backlight: %d\n", ret); @@ -1909,8 +1909,7 @@ void wm831x_device_exit(struct wm831x *wm831x) { wm831x_otp_exit(wm831x); mfd_remove_devices(wm831x->dev); - if (wm831x->irq_base) - free_irq(wm831x->irq_base + WM831X_IRQ_AUXADC_DATA, wm831x); + free_irq(wm831x_irq(wm831x, WM831X_IRQ_AUXADC_DATA), wm831x); wm831x_irq_exit(wm831x); } diff --git a/drivers/mfd/wm831x-irq.c b/drivers/mfd/wm831x-irq.c index 2be9628074bd..ecc9d6d62fad 100644 --- a/drivers/mfd/wm831x-irq.c +++ b/drivers/mfd/wm831x-irq.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -328,7 +329,7 @@ static inline int irq_data_to_status_reg(struct wm831x_irq_data *irq_data) static inline struct wm831x_irq_data *irq_to_wm831x_irq(struct wm831x *wm831x, int irq) { - return &wm831x_irqs[irq - wm831x->irq_base]; + return &wm831x_irqs[irq]; } static void wm831x_irq_lock(struct irq_data *data) @@ -374,7 +375,7 @@ static void wm831x_irq_enable(struct irq_data *data) { struct wm831x *wm831x = irq_data_get_irq_chip_data(data); struct wm831x_irq_data *irq_data = irq_to_wm831x_irq(wm831x, - data->irq); + data->hwirq); wm831x->irq_masks_cur[irq_data->reg - 1] &= ~irq_data->mask; } @@ -383,7 +384,7 @@ static void wm831x_irq_disable(struct irq_data *data) { struct wm831x *wm831x = irq_data_get_irq_chip_data(data); struct wm831x_irq_data *irq_data = irq_to_wm831x_irq(wm831x, - data->irq); + data->hwirq); wm831x->irq_masks_cur[irq_data->reg - 1] |= irq_data->mask; } @@ -393,7 +394,7 @@ static int wm831x_irq_set_type(struct irq_data *data, unsigned int type) struct wm831x *wm831x = irq_data_get_irq_chip_data(data); int irq; - irq = data->irq - wm831x->irq_base; + irq = data->hwirq; if (irq < WM831X_IRQ_GPIO_1 || irq > WM831X_IRQ_GPIO_11) { /* Ignore internal-only IRQs */ @@ -469,9 +470,11 @@ static irqreturn_t wm831x_irq_thread(int irq, void *data) * descriptors. */ if (primary & WM831X_TCHPD_INT) - handle_nested_irq(wm831x->irq_base + WM831X_IRQ_TCHPD); + handle_nested_irq(irq_find_mapping(wm831x->irq_domain, + WM831X_IRQ_TCHPD)); if (primary & WM831X_TCHDATA_INT) - handle_nested_irq(wm831x->irq_base + WM831X_IRQ_TCHDATA); + handle_nested_irq(irq_find_mapping(wm831x->irq_domain, + WM831X_IRQ_TCHDATA)); primary &= ~(WM831X_TCHDATA_EINT | WM831X_TCHPD_EINT); for (i = 0; i < ARRAY_SIZE(wm831x_irqs); i++) { @@ -507,7 +510,8 @@ static irqreturn_t wm831x_irq_thread(int irq, void *data) } if (*status & wm831x_irqs[i].mask) - handle_nested_irq(wm831x->irq_base + i); + handle_nested_irq(irq_find_mapping(wm831x->irq_domain, + i)); /* Simulate an edge triggered IRQ by polling the input * status. This is sucky but improves interoperability. @@ -516,7 +520,8 @@ static irqreturn_t wm831x_irq_thread(int irq, void *data) wm831x->gpio_level[i - WM831X_IRQ_GPIO_1]) { ret = wm831x_reg_read(wm831x, WM831X_GPIO_LEVEL); while (ret & 1 << (i - WM831X_IRQ_GPIO_1)) { - handle_nested_irq(wm831x->irq_base + i); + handle_nested_irq(irq_find_mapping(wm831x->irq_domain, + i)); ret = wm831x_reg_read(wm831x, WM831X_GPIO_LEVEL); } @@ -527,10 +532,34 @@ out: return IRQ_HANDLED; } +static int wm831x_irq_map(struct irq_domain *h, unsigned int virq, + irq_hw_number_t hw) +{ + irq_set_chip_data(virq, h->host_data); + irq_set_chip_and_handler(virq, &wm831x_irq_chip, handle_edge_irq); + irq_set_nested_thread(virq, 1); + + /* ARM needs us to explicitly flag the IRQ as valid + * and will set them noprobe when we do so. */ +#ifdef CONFIG_ARM + set_irq_flags(virq, IRQF_VALID); +#else + irq_set_noprobe(virq); +#endif + + return 0; +} + +static struct irq_domain_ops wm831x_irq_domain_ops = { + .map = wm831x_irq_map, + .xlate = irq_domain_xlate_twocell, +}; + int wm831x_irq_init(struct wm831x *wm831x, int irq) { struct wm831x_pdata *pdata = wm831x->dev->platform_data; - int i, cur_irq, ret; + struct irq_domain *domain; + int i, ret, irq_base; mutex_init(&wm831x->irq_lock); @@ -543,18 +572,33 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq) } /* Try to dynamically allocate IRQs if no base is specified */ - if (!pdata || !pdata->irq_base) - wm831x->irq_base = -1; + if (pdata && pdata->irq_base) { + irq_base = irq_alloc_descs(pdata->irq_base, 0, + WM831X_NUM_IRQS, 0); + if (irq_base < 0) { + dev_warn(wm831x->dev, "Failed to allocate IRQs: %d\n", + irq_base); + irq_base = 0; + } + } else { + irq_base = 0; + } + + if (irq_base) + domain = irq_domain_add_legacy(wm831x->dev->of_node, + ARRAY_SIZE(wm831x_irqs), + irq_base, 0, + &wm831x_irq_domain_ops, + wm831x); else - wm831x->irq_base = pdata->irq_base; + domain = irq_domain_add_linear(wm831x->dev->of_node, + ARRAY_SIZE(wm831x_irqs), + &wm831x_irq_domain_ops, + wm831x); - wm831x->irq_base = irq_alloc_descs(wm831x->irq_base, 0, - WM831X_NUM_IRQS, 0); - if (wm831x->irq_base < 0) { - dev_warn(wm831x->dev, "Failed to allocate IRQs: %d\n", - wm831x->irq_base); - wm831x->irq_base = 0; - return 0; + if (!domain) { + dev_warn(wm831x->dev, "Failed to allocate IRQ domain\n"); + return -EINVAL; } if (pdata && pdata->irq_cmos) @@ -566,24 +610,7 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq) WM831X_IRQ_OD, i); wm831x->irq = irq; - - /* Register them with genirq */ - for (cur_irq = wm831x->irq_base; - cur_irq < ARRAY_SIZE(wm831x_irqs) + wm831x->irq_base; - cur_irq++) { - irq_set_chip_data(cur_irq, wm831x); - irq_set_chip_and_handler(cur_irq, &wm831x_irq_chip, - handle_edge_irq); - irq_set_nested_thread(cur_irq, 1); - - /* ARM needs us to explicitly flag the IRQ as valid - * and will set them noprobe when we do so. */ -#ifdef CONFIG_ARM - set_irq_flags(cur_irq, IRQF_VALID); -#else - irq_set_noprobe(cur_irq); -#endif - } + wm831x->irq_domain = domain; if (irq) { /* Try to flag /IRQ as a wake source; there are a number of diff --git a/drivers/power/wm831x_power.c b/drivers/power/wm831x_power.c index 987332b71d8d..fc1ad9551182 100644 --- a/drivers/power/wm831x_power.c +++ b/drivers/power/wm831x_power.c @@ -565,7 +565,7 @@ static __devinit int wm831x_power_probe(struct platform_device *pdev) goto err_usb; } - irq = platform_get_irq_byname(pdev, "SYSLO"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "SYSLO")); ret = request_threaded_irq(irq, NULL, wm831x_syslo_irq, IRQF_TRIGGER_RISING, "System power low", power); @@ -575,7 +575,7 @@ static __devinit int wm831x_power_probe(struct platform_device *pdev) goto err_battery; } - irq = platform_get_irq_byname(pdev, "PWR SRC"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "PWR SRC")); ret = request_threaded_irq(irq, NULL, wm831x_pwr_src_irq, IRQF_TRIGGER_RISING, "Power source", power); @@ -586,7 +586,9 @@ static __devinit int wm831x_power_probe(struct platform_device *pdev) } for (i = 0; i < ARRAY_SIZE(wm831x_bat_irqs); i++) { - irq = platform_get_irq_byname(pdev, wm831x_bat_irqs[i]); + irq = wm831x_irq(wm831x, + platform_get_irq_byname(pdev, + wm831x_bat_irqs[i])); ret = request_threaded_irq(irq, NULL, wm831x_bat_irq, IRQF_TRIGGER_RISING, wm831x_bat_irqs[i], @@ -606,10 +608,10 @@ err_bat_irq: irq = platform_get_irq_byname(pdev, wm831x_bat_irqs[i]); free_irq(irq, power); } - irq = platform_get_irq_byname(pdev, "PWR SRC"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "PWR SRC")); free_irq(irq, power); err_syslo: - irq = platform_get_irq_byname(pdev, "SYSLO"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "SYSLO")); free_irq(irq, power); err_battery: if (power->have_battery) @@ -626,17 +628,20 @@ err_kmalloc: static __devexit int wm831x_power_remove(struct platform_device *pdev) { struct wm831x_power *wm831x_power = platform_get_drvdata(pdev); + struct wm831x *wm831x = wm831x_power->wm831x; int irq, i; for (i = 0; i < ARRAY_SIZE(wm831x_bat_irqs); i++) { - irq = platform_get_irq_byname(pdev, wm831x_bat_irqs[i]); + irq = wm831x_irq(wm831x, + platform_get_irq_byname(pdev, + wm831x_bat_irqs[i])); free_irq(irq, wm831x_power); } - irq = platform_get_irq_byname(pdev, "PWR SRC"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "PWR SRC")); free_irq(irq, wm831x_power); - irq = platform_get_irq_byname(pdev, "SYSLO"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "SYSLO")); free_irq(irq, wm831x_power); if (wm831x_power->have_battery) diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c index ff810e787eac..33b2f20a2932 100644 --- a/drivers/regulator/wm831x-dcdc.c +++ b/drivers/regulator/wm831x-dcdc.c @@ -565,7 +565,7 @@ static __devinit int wm831x_buckv_probe(struct platform_device *pdev) goto err; } - irq = platform_get_irq_byname(pdev, "UV"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")); ret = request_threaded_irq(irq, NULL, wm831x_dcdc_uv_irq, IRQF_TRIGGER_RISING, dcdc->name, dcdc); if (ret != 0) { @@ -574,7 +574,7 @@ static __devinit int wm831x_buckv_probe(struct platform_device *pdev) goto err_regulator; } - irq = platform_get_irq_byname(pdev, "HC"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "HC")); ret = request_threaded_irq(irq, NULL, wm831x_dcdc_oc_irq, IRQF_TRIGGER_RISING, dcdc->name, dcdc); if (ret != 0) { @@ -588,7 +588,8 @@ static __devinit int wm831x_buckv_probe(struct platform_device *pdev) return 0; err_uv: - free_irq(platform_get_irq_byname(pdev, "UV"), dcdc); + free_irq(wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")), + dcdc); err_regulator: regulator_unregister(dcdc->regulator); err: @@ -600,11 +601,14 @@ err: static __devexit int wm831x_buckv_remove(struct platform_device *pdev) { struct wm831x_dcdc *dcdc = platform_get_drvdata(pdev); + struct wm831x *wm831x = dcdc->wm831x; platform_set_drvdata(pdev, NULL); - free_irq(platform_get_irq_byname(pdev, "HC"), dcdc); - free_irq(platform_get_irq_byname(pdev, "UV"), dcdc); + free_irq(wm831x_irq(wm831x, platform_get_irq_byname(pdev, "HC")), + dcdc); + free_irq(wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")), + dcdc); regulator_unregister(dcdc->regulator); if (dcdc->dvs_gpio) gpio_free(dcdc->dvs_gpio); @@ -758,7 +762,7 @@ static __devinit int wm831x_buckp_probe(struct platform_device *pdev) goto err; } - irq = platform_get_irq_byname(pdev, "UV"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")); ret = request_threaded_irq(irq, NULL, wm831x_dcdc_uv_irq, IRQF_TRIGGER_RISING, dcdc->name, dcdc); if (ret != 0) { @@ -783,7 +787,8 @@ static __devexit int wm831x_buckp_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); - free_irq(platform_get_irq_byname(pdev, "UV"), dcdc); + free_irq(wm831x_irq(dcdc->wm831x, platform_get_irq_byname(pdev, "UV")), + dcdc); regulator_unregister(dcdc->regulator); return 0; @@ -883,7 +888,7 @@ static __devinit int wm831x_boostp_probe(struct platform_device *pdev) goto err; } - irq = platform_get_irq_byname(pdev, "UV"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")); ret = request_threaded_irq(irq, NULL, wm831x_dcdc_uv_irq, IRQF_TRIGGER_RISING, dcdc->name, dcdc); @@ -910,7 +915,8 @@ static __devexit int wm831x_boostp_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); - free_irq(platform_get_irq_byname(pdev, "UV"), dcdc); + free_irq(wm831x_irq(dcdc->wm831x, platform_get_irq_byname(pdev, "UV")), + dcdc); regulator_unregister(dcdc->regulator); kfree(dcdc); diff --git a/drivers/regulator/wm831x-isink.c b/drivers/regulator/wm831x-isink.c index b414e09c5620..1596947f603f 100644 --- a/drivers/regulator/wm831x-isink.c +++ b/drivers/regulator/wm831x-isink.c @@ -198,7 +198,7 @@ static __devinit int wm831x_isink_probe(struct platform_device *pdev) goto err; } - irq = platform_get_irq(pdev, 0); + irq = wm831x_irq(wm831x, platform_get_irq(pdev, 0)); ret = request_threaded_irq(irq, NULL, wm831x_isink_irq, IRQF_TRIGGER_RISING, isink->name, isink); if (ret != 0) { @@ -223,7 +223,7 @@ static __devexit int wm831x_isink_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); - free_irq(platform_get_irq(pdev, 0), isink); + free_irq(wm831x_irq(isink->wm831x, platform_get_irq(pdev, 0)), isink); regulator_unregister(isink->regulator); diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c index 641e9f6499d1..b09ba05ada6d 100644 --- a/drivers/regulator/wm831x-ldo.c +++ b/drivers/regulator/wm831x-ldo.c @@ -359,7 +359,7 @@ static __devinit int wm831x_gp_ldo_probe(struct platform_device *pdev) goto err; } - irq = platform_get_irq_byname(pdev, "UV"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")); ret = request_threaded_irq(irq, NULL, wm831x_ldo_uv_irq, IRQF_TRIGGER_RISING, ldo->name, ldo); @@ -385,7 +385,8 @@ static __devexit int wm831x_gp_ldo_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); - free_irq(platform_get_irq_byname(pdev, "UV"), ldo); + free_irq(wm831x_irq(ldo->wm831x, + platform_get_irq_byname(pdev, "UV")), ldo); regulator_unregister(ldo->regulator); return 0; @@ -624,7 +625,7 @@ static __devinit int wm831x_aldo_probe(struct platform_device *pdev) goto err; } - irq = platform_get_irq_byname(pdev, "UV"); + irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")); ret = request_threaded_irq(irq, NULL, wm831x_ldo_uv_irq, IRQF_TRIGGER_RISING, ldo->name, ldo); if (ret != 0) { @@ -647,7 +648,8 @@ static __devexit int wm831x_aldo_remove(struct platform_device *pdev) { struct wm831x_ldo *ldo = platform_get_drvdata(pdev); - free_irq(platform_get_irq_byname(pdev, "UV"), ldo); + free_irq(wm831x_irq(ldo->wm831x, platform_get_irq_byname(pdev, "UV")), + ldo); regulator_unregister(ldo->regulator); return 0; diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c index 3b6e6a67e765..59c6245e0421 100644 --- a/drivers/rtc/rtc-wm831x.c +++ b/drivers/rtc/rtc-wm831x.c @@ -396,7 +396,7 @@ static int wm831x_rtc_probe(struct platform_device *pdev) { struct wm831x *wm831x = dev_get_drvdata(pdev->dev.parent); struct wm831x_rtc *wm831x_rtc; - int alm_irq = platform_get_irq_byname(pdev, "ALM"); + int alm_irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "ALM")); int ret = 0; wm831x_rtc = devm_kzalloc(&pdev->dev, sizeof(*wm831x_rtc), GFP_KERNEL); diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 4b1211859f74..736191cc7e00 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -17,6 +17,7 @@ #include #include +#include #include #include @@ -338,6 +339,7 @@ #define WM831X_FLL_CLK_SRC_WIDTH 2 /* FLL_CLK_SRC - [1:0] */ struct regulator_dev; +struct irq_domain; #define WM831X_NUM_IRQ_REGS 5 #define WM831X_NUM_GPIO_REGS 16 @@ -367,7 +369,7 @@ struct wm831x { int irq; /* Our chip IRQ */ struct mutex irq_lock; - int irq_base; + struct irq_domain *irq_domain; int irq_masks_cur[WM831X_NUM_IRQ_REGS]; /* Currently active value */ int irq_masks_cache[WM831X_NUM_IRQ_REGS]; /* Cached hardware value */ @@ -417,6 +419,11 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq); void wm831x_irq_exit(struct wm831x *wm831x); void wm831x_auxadc_init(struct wm831x *wm831x); +static inline int wm831x_irq(struct wm831x *wm831x, int irq) +{ + return irq_create_mapping(wm831x->irq_domain, irq); +} + extern struct regmap_config wm831x_regmap_config; #endif -- cgit v1.2.3 From b09530ef844f0bf29ed3677080c02b179be84818 Mon Sep 17 00:00:00 2001 From: Richard Zhao Date: Sun, 13 May 2012 09:18:02 +0800 Subject: mfd: Make anatop register accessor more flexible and rename meaningfully - rename to anatop_read_reg and anatop_write_reg - anatop_read_reg directly return reg value - anatop_write_reg write reg with mask Signed-off-by: Richard Zhao Reviewed-by: Ying-Chun Liu (PaulLiu) Signed-off-by: Samuel Ortiz --- drivers/mfd/anatop-mfd.c | 35 +++++++++++------------------------ drivers/regulator/anatop-regulator.c | 18 ++++++++---------- include/linux/mfd/anatop.h | 4 ++-- 3 files changed, 21 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/anatop-mfd.c b/drivers/mfd/anatop-mfd.c index 2af42480635e..6da06341f6c9 100644 --- a/drivers/mfd/anatop-mfd.c +++ b/drivers/mfd/anatop-mfd.c @@ -41,39 +41,26 @@ #include #include -u32 anatop_get_bits(struct anatop *adata, u32 addr, int bit_shift, - int bit_width) +u32 anatop_read_reg(struct anatop *adata, u32 addr) { - u32 val, mask; - - if (bit_width == 32) - mask = ~0; - else - mask = (1 << bit_width) - 1; - - val = readl(adata->ioreg + addr); - val = (val >> bit_shift) & mask; - - return val; + return readl(adata->ioreg + addr); } -EXPORT_SYMBOL_GPL(anatop_get_bits); +EXPORT_SYMBOL_GPL(anatop_read_reg); -void anatop_set_bits(struct anatop *adata, u32 addr, int bit_shift, - int bit_width, u32 data) +void anatop_write_reg(struct anatop *adata, u32 addr, u32 data, u32 mask) { - u32 val, mask; + u32 val; - if (bit_width == 32) - mask = ~0; - else - mask = (1 << bit_width) - 1; + data &= mask; spin_lock(&adata->reglock); - val = readl(adata->ioreg + addr) & ~(mask << bit_shift); - writel((data << bit_shift) | val, adata->ioreg + addr); + val = readl(adata->ioreg + addr); + val &= ~mask; + val |= data; + writel(val, adata->ioreg + addr); spin_unlock(&adata->reglock); } -EXPORT_SYMBOL_GPL(anatop_set_bits); +EXPORT_SYMBOL_GPL(anatop_write_reg); static const struct of_device_id of_anatop_match[] = { { .compatible = "fsl,imx6q-anatop", }, diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c index 81fd606e47bc..0a3408570d0a 100644 --- a/drivers/regulator/anatop-regulator.c +++ b/drivers/regulator/anatop-regulator.c @@ -47,7 +47,7 @@ static int anatop_set_voltage(struct regulator_dev *reg, int min_uV, int max_uV, unsigned *selector) { struct anatop_regulator *anatop_reg = rdev_get_drvdata(reg); - u32 val, sel; + u32 val, sel, mask; int uv; uv = min_uV; @@ -71,11 +71,10 @@ static int anatop_set_voltage(struct regulator_dev *reg, int min_uV, val = anatop_reg->min_bit_val + sel; *selector = sel; dev_dbg(®->dev, "%s: calculated val %d\n", __func__, val); - anatop_set_bits(anatop_reg->mfd, - anatop_reg->control_reg, - anatop_reg->vol_bit_shift, - anatop_reg->vol_bit_width, - val); + mask = ((1 << anatop_reg->vol_bit_width) - 1) << + anatop_reg->vol_bit_shift; + val <<= anatop_reg->vol_bit_shift; + anatop_write_reg(anatop_reg->mfd, anatop_reg->control_reg, val, mask); return 0; } @@ -88,10 +87,9 @@ static int anatop_get_voltage_sel(struct regulator_dev *reg) if (!anatop_reg->control_reg) return -ENOTSUPP; - val = anatop_get_bits(anatop_reg->mfd, - anatop_reg->control_reg, - anatop_reg->vol_bit_shift, - anatop_reg->vol_bit_width); + val = anatop_read_reg(anatop_reg->mfd, anatop_reg->control_reg); + val = (val & ((1 << anatop_reg->vol_bit_width) - 1)) >> + anatop_reg->vol_bit_shift; return val - anatop_reg->min_bit_val; } diff --git a/include/linux/mfd/anatop.h b/include/linux/mfd/anatop.h index 22c1007d3ec5..7f92acf03d9e 100644 --- a/include/linux/mfd/anatop.h +++ b/include/linux/mfd/anatop.h @@ -34,7 +34,7 @@ struct anatop { spinlock_t reglock; }; -extern u32 anatop_get_bits(struct anatop *, u32, int, int); -extern void anatop_set_bits(struct anatop *, u32, int, int, u32); +extern u32 anatop_read_reg(struct anatop *, u32); +extern void anatop_write_reg(struct anatop *, u32, u32, u32); #endif /* __LINUX_MFD_ANATOP_H */ -- cgit v1.2.3 From 21f7541d8861fdcdff663c68903e961ca1b06dc6 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Fri, 18 May 2012 11:52:19 +0200 Subject: mfd: Add tps65910-irq devicetree init and irqdomain support This change changes the tps65910-irq code to use irqdomain, and support initialization from devicetree. This assumes that the irq_base in the platform data is -1 if devicetree is used. Signed-off-by: Rhyland Klein Signed-off-by: Samuel Ortiz --- drivers/mfd/Kconfig | 1 + drivers/mfd/tps65910-irq.c | 96 ++++++++++++++++++++++++++++---------------- include/linux/mfd/tps65910.h | 1 + 3 files changed, 64 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 6da82ded3371..b819eea1775a 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -190,6 +190,7 @@ config MFD_TPS65910 depends on I2C=y && GPIOLIB select MFD_CORE select REGMAP_I2C + select IRQ_DOMAIN help if you say yes here you get support for the TPS65910 series of Power Management chips. diff --git a/drivers/mfd/tps65910-irq.c b/drivers/mfd/tps65910-irq.c index 0f1ff7fbdc74..09aab3e4776d 100644 --- a/drivers/mfd/tps65910-irq.c +++ b/drivers/mfd/tps65910-irq.c @@ -20,15 +20,10 @@ #include #include #include +#include #include #include -static inline int irq_to_tps65910_irq(struct tps65910 *tps65910, - int irq) -{ - return (irq - tps65910->irq_base); -} - /* * This is a threaded IRQ handler so can access I2C/SPI. Since all * interrupts are clear on read the IRQ line will be reasserted and @@ -76,7 +71,7 @@ static irqreturn_t tps65910_irq(int irq, void *irq_data) if (!(irq_sts & (1 << i))) continue; - handle_nested_irq(tps65910->irq_base + i); + handle_nested_irq(irq_find_mapping(tps65910->domain, i)); } /* Write the STS register back to clear IRQs we handled */ @@ -135,14 +130,14 @@ static void tps65910_irq_enable(struct irq_data *data) { struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data); - tps65910->irq_mask &= ~( 1 << irq_to_tps65910_irq(tps65910, data->irq)); + tps65910->irq_mask &= ~(1 << data->hwirq); } static void tps65910_irq_disable(struct irq_data *data) { struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data); - tps65910->irq_mask |= ( 1 << irq_to_tps65910_irq(tps65910, data->irq)); + tps65910->irq_mask |= (1 << data->hwirq); } #ifdef CONFIG_PM_SLEEP @@ -164,10 +159,35 @@ static struct irq_chip tps65910_irq_chip = { .irq_set_wake = tps65910_irq_set_wake, }; +static int tps65910_irq_map(struct irq_domain *h, unsigned int virq, + irq_hw_number_t hw) +{ + struct tps65910 *tps65910 = h->host_data; + + irq_set_chip_data(virq, tps65910); + irq_set_chip_and_handler(virq, &tps65910_irq_chip, handle_edge_irq); + irq_set_nested_thread(virq, 1); + + /* ARM needs us to explicitly flag the IRQ as valid + * and will set them noprobe when we do so. */ +#ifdef CONFIG_ARM + set_irq_flags(virq, IRQF_VALID); +#else + irq_set_noprobe(virq); +#endif + + return 0; +} + +static struct irq_domain_ops tps65910_domain_ops = { + .map = tps65910_irq_map, + .xlate = irq_domain_xlate_twocell, +}; + int tps65910_irq_init(struct tps65910 *tps65910, int irq, struct tps65910_platform_data *pdata) { - int ret, cur_irq; + int ret; int flags = IRQF_ONESHOT; if (!irq) { @@ -175,17 +195,11 @@ int tps65910_irq_init(struct tps65910 *tps65910, int irq, return -EINVAL; } - if (!pdata || !pdata->irq_base) { - dev_warn(tps65910->dev, "No interrupt support, no IRQ base\n"); + if (!pdata) { + dev_warn(tps65910->dev, "No interrupt support, no pdata\n"); return -EINVAL; } - tps65910->irq_mask = 0xFFFFFF; - - mutex_init(&tps65910->irq_lock); - tps65910->chip_irq = irq; - tps65910->irq_base = pdata->irq_base; - switch (tps65910_chip_id(tps65910)) { case TPS65910: tps65910->irq_num = TPS65910_NUM_IRQ; @@ -195,22 +209,36 @@ int tps65910_irq_init(struct tps65910 *tps65910, int irq, break; } - /* Register with genirq */ - for (cur_irq = tps65910->irq_base; - cur_irq < tps65910->irq_num + tps65910->irq_base; - cur_irq++) { - irq_set_chip_data(cur_irq, tps65910); - irq_set_chip_and_handler(cur_irq, &tps65910_irq_chip, - handle_edge_irq); - irq_set_nested_thread(cur_irq, 1); - - /* ARM needs us to explicitly flag the IRQ as valid - * and will set them noprobe when we do so. */ -#ifdef CONFIG_ARM - set_irq_flags(cur_irq, IRQF_VALID); -#else - irq_set_noprobe(cur_irq); -#endif + if (pdata->irq_base > 0) { + pdata->irq_base = irq_alloc_descs(pdata->irq_base, 0, + tps65910->irq_num, -1); + if (pdata->irq_base < 0) { + dev_warn(tps65910->dev, "Failed to alloc IRQs: %d\n", + pdata->irq_base); + return pdata->irq_base; + } + } + + tps65910->irq_mask = 0xFFFFFF; + + mutex_init(&tps65910->irq_lock); + tps65910->chip_irq = irq; + tps65910->irq_base = pdata->irq_base; + + if (pdata->irq_base > 0) + tps65910->domain = irq_domain_add_legacy(tps65910->dev->of_node, + tps65910->irq_num, + pdata->irq_base, + 0, + &tps65910_domain_ops, tps65910); + else + tps65910->domain = irq_domain_add_linear(tps65910->dev->of_node, + tps65910->irq_num, + &tps65910_domain_ops, tps65910); + + if (!tps65910->domain) { + dev_err(tps65910->dev, "Failed to create IRQ domain\n"); + return -ENOMEM; } ret = request_threaded_irq(irq, NULL, tps65910_irq, flags, diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index c2673ee5e70f..ab04e901e57e 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -836,6 +836,7 @@ struct tps65910 { int irq_base; int irq_num; u32 irq_mask; + struct irq_domain *domain; }; struct tps65910_platform_data { -- cgit v1.2.3 From 16e5e204c92800aad4e7db52d289565cc82240ce Mon Sep 17 00:00:00 2001 From: Ashish Jangam Date: Fri, 18 May 2012 12:19:18 +0200 Subject: mfd: Add ADC support to the DA9052/53 core This patch adds ADC support to the DA9052/53 core. Tested on smdkv6410 and i.mx53 QS boards. Signed-off-by: Ashish Jangam Signed-off-by: Samuel Ortiz --- drivers/mfd/da9052-core.c | 140 ++++++++++++++++++++++++++++++++++++++ include/linux/mfd/da9052/da9052.h | 19 ++++++ 2 files changed, 159 insertions(+) (limited to 'include/linux') diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c index 7ff313fe9fb1..5036cf5fc077 100644 --- a/drivers/mfd/da9052-core.c +++ b/drivers/mfd/da9052-core.c @@ -318,6 +318,135 @@ static bool da9052_reg_volatile(struct device *dev, unsigned int reg) } } +/* + * TBAT look-up table is computed from the R90 reg (8 bit register) + * reading as below. The battery temperature is in milliCentigrade + * TBAT = (1/(t1+1/298) - 273) * 1000 mC + * where t1 = (1/B)* ln(( ADCval * 2.5)/(R25*ITBAT*255)) + * Default values are R25 = 10e3, B = 3380, ITBAT = 50e-6 + * Example: + * R25=10E3, B=3380, ITBAT=50e-6, ADCVAL=62d calculates + * TBAT = 20015 mili degrees Centrigrade + * +*/ +static const int32_t tbat_lookup[255] = { + 183258, 144221, 124334, 111336, 101826, 94397, 88343, 83257, + 78889, 75071, 71688, 68656, 65914, 63414, 61120, 59001, + 570366, 55204, 53490, 51881, 50364, 48931, 47574, 46285, + 45059, 43889, 42772, 41703, 40678, 39694, 38748, 37838, + 36961, 36115, 35297, 34507, 33743, 33002, 32284, 31588, + 30911, 30254, 29615, 28994, 28389, 27799, 27225, 26664, + 26117, 25584, 25062, 24553, 24054, 23567, 23091, 22624, + 22167, 21719, 21281, 20851, 20429, 20015, 19610, 19211, + 18820, 18436, 18058, 17688, 17323, 16965, 16612, 16266, + 15925, 15589, 15259, 14933, 14613, 14298, 13987, 13681, + 13379, 13082, 12788, 12499, 12214, 11933, 11655, 11382, + 11112, 10845, 10582, 10322, 10066, 9812, 9562, 9315, + 9071, 8830, 8591, 8356, 8123, 7893, 7665, 7440, + 7218, 6998, 6780, 6565, 6352, 6141, 5933, 5726, + 5522, 5320, 5120, 4922, 4726, 4532, 4340, 4149, + 3961, 3774, 3589, 3406, 3225, 3045, 2867, 2690, + 2516, 2342, 2170, 2000, 1831, 1664, 1498, 1334, + 1171, 1009, 849, 690, 532, 376, 221, 67, + -84, -236, -386, -535, -683, -830, -975, -1119, + -1263, -1405, -1546, -1686, -1825, -1964, -2101, -2237, + -2372, -2506, -2639, -2771, -2902, -3033, -3162, -3291, + -3418, -3545, -3671, -3796, -3920, -4044, -4166, -4288, + -4409, -4529, -4649, -4767, -4885, -5002, -5119, -5235, + -5349, -5464, -5577, -5690, -5802, -5913, -6024, -6134, + -6244, -6352, -6461, -6568, -6675, -6781, -6887, -6992, + -7096, -7200, -7303, -7406, -7508, -7609, -7710, -7810, + -7910, -8009, -8108, -8206, -8304, -8401, -8497, -8593, + -8689, -8784, -8878, -8972, -9066, -9159, -9251, -9343, + -9435, -9526, -9617, -9707, -9796, -9886, -9975, -10063, + -10151, -10238, -10325, -10412, -10839, -10923, -11007, -11090, + -11173, -11256, -11338, -11420, -11501, -11583, -11663, -11744, + -11823, -11903, -11982 +}; + +static const u8 chan_mux[DA9052_ADC_VBBAT + 1] = { + [DA9052_ADC_VDDOUT] = DA9052_ADC_MAN_MUXSEL_VDDOUT, + [DA9052_ADC_ICH] = DA9052_ADC_MAN_MUXSEL_ICH, + [DA9052_ADC_TBAT] = DA9052_ADC_MAN_MUXSEL_TBAT, + [DA9052_ADC_VBAT] = DA9052_ADC_MAN_MUXSEL_VBAT, + [DA9052_ADC_IN4] = DA9052_ADC_MAN_MUXSEL_AD4, + [DA9052_ADC_IN5] = DA9052_ADC_MAN_MUXSEL_AD5, + [DA9052_ADC_IN6] = DA9052_ADC_MAN_MUXSEL_AD6, + [DA9052_ADC_VBBAT] = DA9052_ADC_MAN_MUXSEL_VBBAT +}; + +int da9052_adc_manual_read(struct da9052 *da9052, unsigned char channel) +{ + int ret; + unsigned short calc_data; + unsigned short data; + unsigned char mux_sel; + + if (channel > DA9052_ADC_VBBAT) + return -EINVAL; + + mutex_lock(&da9052->auxadc_lock); + + /* Channel gets activated on enabling the Conversion bit */ + mux_sel = chan_mux[channel] | DA9052_ADC_MAN_MAN_CONV; + + ret = da9052_reg_write(da9052, DA9052_ADC_MAN_REG, mux_sel); + if (ret < 0) + goto err; + + /* Wait for an interrupt */ + if (!wait_for_completion_timeout(&da9052->done, + msecs_to_jiffies(500))) { + dev_err(da9052->dev, + "timeout waiting for ADC conversion interrupt\n"); + ret = -ETIMEDOUT; + goto err; + } + + ret = da9052_reg_read(da9052, DA9052_ADC_RES_H_REG); + if (ret < 0) + goto err; + + calc_data = (unsigned short)ret; + data = calc_data << 2; + + ret = da9052_reg_read(da9052, DA9052_ADC_RES_L_REG); + if (ret < 0) + goto err; + + calc_data = (unsigned short)(ret & DA9052_ADC_RES_LSB); + data |= calc_data; + + ret = data; + +err: + mutex_unlock(&da9052->auxadc_lock); + return ret; +} +EXPORT_SYMBOL_GPL(da9052_adc_manual_read); + +static irqreturn_t da9052_auxadc_irq(int irq, void *irq_data) +{ + struct da9052 *da9052 = irq_data; + + complete(&da9052->done); + + return IRQ_HANDLED; +} + +int da9052_adc_read_temp(struct da9052 *da9052) +{ + int tbat; + + tbat = da9052_reg_read(da9052, DA9052_TBAT_RES_REG); + if (tbat <= 0) + return tbat; + + /* ARRAY_SIZE check is not needed since TBAT is a 8-bit register */ + return tbat_lookup[tbat - 1]; +} +EXPORT_SYMBOL_GPL(da9052_adc_read_temp); + static struct resource da9052_rtc_resource = { .name = "ALM", .start = DA9052_IRQ_ALARM, @@ -646,6 +775,9 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id) struct irq_desc *desc; int ret; + mutex_init(&da9052->auxadc_lock); + init_completion(&da9052->done); + if (pdata && pdata->init != NULL) pdata->init(da9052); @@ -666,6 +798,12 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id) desc = irq_to_desc(da9052->chip_irq); da9052->irq_base = regmap_irq_chip_get_base(desc->action->dev_id); + ret = request_threaded_irq(DA9052_IRQ_ADC_EOM, NULL, da9052_auxadc_irq, + IRQF_TRIGGER_LOW | IRQF_ONESHOT, + "adc irq", da9052); + if (ret != 0) + dev_err(da9052->dev, "DA9052 ADC IRQ failed ret=%d\n", ret); + ret = mfd_add_devices(da9052->dev, -1, da9052_subdev_info, ARRAY_SIZE(da9052_subdev_info), NULL, 0); if (ret) @@ -674,6 +812,7 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id) return 0; err: + free_irq(DA9052_IRQ_ADC_EOM, da9052); mfd_remove_devices(da9052->dev); regmap_err: return ret; @@ -681,6 +820,7 @@ regmap_err: void da9052_device_exit(struct da9052 *da9052) { + free_irq(DA9052_IRQ_ADC_EOM, da9052); regmap_del_irq_chip(da9052->chip_irq, irq_get_irq_data(da9052->irq_base)->chip_data); mfd_remove_devices(da9052->dev); diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h index 7ffbd6e9e7fc..b990cca1d9ee 100644 --- a/include/linux/mfd/da9052/da9052.h +++ b/include/linux/mfd/da9052/da9052.h @@ -33,6 +33,18 @@ #include +/* Common - HWMON Channel Definations */ +#define DA9052_ADC_VDDOUT 0 +#define DA9052_ADC_ICH 1 +#define DA9052_ADC_TBAT 2 +#define DA9052_ADC_VBAT 3 +#define DA9052_ADC_IN4 4 +#define DA9052_ADC_IN5 5 +#define DA9052_ADC_IN6 6 +#define DA9052_ADC_TSI 7 +#define DA9052_ADC_TJUNC 8 +#define DA9052_ADC_VBBAT 9 + #define DA9052_IRQ_DCIN 0 #define DA9052_IRQ_VBUS 1 #define DA9052_IRQ_DCINREM 2 @@ -79,12 +91,19 @@ struct da9052 { struct device *dev; struct regmap *regmap; + struct mutex auxadc_lock; + struct completion done; + int irq_base; u8 chip_id; int chip_irq; }; +/* ADC API */ +int da9052_adc_manual_read(struct da9052 *da9052, unsigned char channel); +int da9052_adc_read_temp(struct da9052 *da9052); + /* Device I/O API */ static inline int da9052_reg_read(struct da9052 *da9052, unsigned char reg) { -- cgit v1.2.3 From 1fe17a24e2fe0a9554d19a4249eb2d80050ecb8c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 18 May 2012 17:02:02 +0100 Subject: mfd: Emulate active low IRQs as well as active high IRQs for wm831x As with the existing emulation this should not be used in production systems but is useful for test purposes. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- drivers/mfd/wm831x-irq.c | 24 +++++++++++++++++++----- include/linux/mfd/wm831x/core.h | 3 ++- 2 files changed, 21 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm831x-irq.c b/drivers/mfd/wm831x-irq.c index ecc9d6d62fad..804e56ec99eb 100644 --- a/drivers/mfd/wm831x-irq.c +++ b/drivers/mfd/wm831x-irq.c @@ -413,22 +413,25 @@ static int wm831x_irq_set_type(struct irq_data *data, unsigned int type) * do the update here as we can be called with the bus lock * held. */ + wm831x->gpio_level_low[irq] = false; + wm831x->gpio_level_high[irq] = false; switch (type) { case IRQ_TYPE_EDGE_BOTH: wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_INT_MODE; - wm831x->gpio_level[irq] = false; break; case IRQ_TYPE_EDGE_RISING: wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_POL; - wm831x->gpio_level[irq] = false; break; case IRQ_TYPE_EDGE_FALLING: wm831x->gpio_update[irq] = 0x10000; - wm831x->gpio_level[irq] = false; break; case IRQ_TYPE_LEVEL_HIGH: wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_POL; - wm831x->gpio_level[irq] = true; + wm831x->gpio_level_high[irq] = true; + break; + case IRQ_TYPE_LEVEL_LOW: + wm831x->gpio_update[irq] = 0x10000; + wm831x->gpio_level_low[irq] = true; break; default: return -EINVAL; @@ -517,7 +520,7 @@ static irqreturn_t wm831x_irq_thread(int irq, void *data) * status. This is sucky but improves interoperability. */ if (primary == WM831X_GP_INT && - wm831x->gpio_level[i - WM831X_IRQ_GPIO_1]) { + wm831x->gpio_level_high[i - WM831X_IRQ_GPIO_1]) { ret = wm831x_reg_read(wm831x, WM831X_GPIO_LEVEL); while (ret & 1 << (i - WM831X_IRQ_GPIO_1)) { handle_nested_irq(irq_find_mapping(wm831x->irq_domain, @@ -526,6 +529,17 @@ static irqreturn_t wm831x_irq_thread(int irq, void *data) WM831X_GPIO_LEVEL); } } + + if (primary == WM831X_GP_INT && + wm831x->gpio_level_low[i - WM831X_IRQ_GPIO_1]) { + ret = wm831x_reg_read(wm831x, WM831X_GPIO_LEVEL); + while (!(ret & 1 << (i - WM831X_IRQ_GPIO_1))) { + handle_nested_irq(irq_find_mapping(wm831x->irq_domain, + i)); + ret = wm831x_reg_read(wm831x, + WM831X_GPIO_LEVEL); + } + } } out: diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 736191cc7e00..4a3b83a77614 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -384,7 +384,8 @@ struct wm831x { /* Used by the interrupt controller code to post writes */ int gpio_update[WM831X_NUM_GPIO_REGS]; - bool gpio_level[WM831X_NUM_GPIO_REGS]; + bool gpio_level_high[WM831X_NUM_GPIO_REGS]; + bool gpio_level_low[WM831X_NUM_GPIO_REGS]; struct mutex auxadc_lock; struct list_head auxadc_pending; -- cgit v1.2.3 From e3c0fb7ef515852619932b0da993baa2d107684d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:45:24 -0400 Subject: NFS: Add NFSDBG_STATE fs/nfs/nfs4state.c does not yet have any dprintk() call sites, and I'm about to introduce some. We will need a new flag for enabling them. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/nfs4renewd.c | 2 +- fs/nfs/nfs4state.c | 2 ++ include/linux/nfs_fs.h | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index dc484c0eae7f..6930bec91bca 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -49,7 +49,7 @@ #include "nfs4_fs.h" #include "delegation.h" -#define NFSDBG_FACILITY NFSDBG_PROC +#define NFSDBG_FACILITY NFSDBG_STATE void nfs4_renew_state(struct work_struct *work) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 7f0fcfc1fe9d..f8c06dec6563 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -57,6 +57,8 @@ #include "internal.h" #include "pnfs.h" +#define NFSDBG_FACILITY NFSDBG_STATE + #define OPENOWNER_POOL_SIZE 8 const nfs4_stateid zero_stateid; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6cc7dbaf0695..80a9385b88ab 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -634,6 +634,7 @@ nfs_fileid_to_ino_t(u64 fileid) #define NFSDBG_FSCACHE 0x0800 #define NFSDBG_PNFS 0x1000 #define NFSDBG_PNFS_LD 0x2000 +#define NFSDBG_STATE 0x4000 #define NFSDBG_ALL 0xFFFF #ifdef __KERNEL__ -- cgit v1.2.3 From 722baafc9e638714a69aa66e9ed24ef961ff350c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:44:22 -0400 Subject: NFS: Fix comment misspelling in struct nfs_client definition Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 7073fc74481c..5498e9d9ba84 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -79,7 +79,7 @@ struct nfs_client { u32 cl_seqid; /* The flags used for obtaining the clientid during EXCHANGE_ID */ u32 cl_exchange_flags; - struct nfs4_session *cl_session; /* sharred session */ + struct nfs4_session *cl_session; /* shared session */ #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE -- cgit v1.2.3 From 79d4e1f0d8910f0214a57832ca6d589640d572c0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:44:31 -0400 Subject: NFS: Use proper naming conventions for NFSv4.1 server scope fields Clean up: When naming fields and data types, follow established conventions to facilitate accurate grep/cscope searches. Additionally, for consistency, move the scope field into the NFSv4- specific part of the nfs_client, and free that memory in the logic that shuts down NFSv4 nfs_clients. Introduced by commit 99fe60d0 "nfs41: exchange_id operation", April 1 2009. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/nfs4_fs.h | 2 +- fs/nfs/nfs4proc.c | 18 ++++++++++-------- include/linux/nfs_fs_sb.h | 4 ++-- include/linux/nfs_xdr.h | 4 ++-- 5 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index b4e2199c32b3..471fc9b927a9 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -237,6 +237,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) nfs_idmap_delete(clp); rpc_destroy_wait_queue(&clp->cl_rpcwaitq); + kfree(clp->cl_serverscope); } /* idr_remove_all is not needed as all id's are removed by nfs_put_client */ @@ -305,7 +306,6 @@ static void nfs_free_client(struct nfs_client *clp) put_net(clp->net); kfree(clp->cl_hostname); - kfree(clp->server_scope); kfree(clp->impl_id); kfree(clp); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index edeef71f957a..b14bcc3c132d 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -338,7 +338,7 @@ extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags); extern void nfs41_handle_recall_slot(struct nfs_client *clp); extern void nfs41_handle_server_scope(struct nfs_client *, - struct server_scope **); + struct nfs41_server_scope **); extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp); extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl); extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0f4e54033abf..94494f24bb12 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5052,7 +5052,8 @@ out_inval: } static bool -nfs41_same_server_scope(struct server_scope *a, struct server_scope *b) +nfs41_same_server_scope(struct nfs41_server_scope *a, + struct nfs41_server_scope *b) { if (a->server_scope_sz == b->server_scope_sz && memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0) @@ -5099,7 +5100,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) clp->cl_rpcclient->cl_nodename, clp->cl_rpcclient->cl_auth->au_flavor); - res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL); + res.server_scope = kzalloc(sizeof(struct nfs41_server_scope), + GFP_KERNEL); if (unlikely(!res.server_scope)) { status = -ENOMEM; goto out; @@ -5123,18 +5125,18 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) kfree(res.impl_id); if (!status) { - if (clp->server_scope && - !nfs41_same_server_scope(clp->server_scope, + if (clp->cl_serverscope && + !nfs41_same_server_scope(clp->cl_serverscope, res.server_scope)) { dprintk("%s: server_scope mismatch detected\n", __func__); set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state); - kfree(clp->server_scope); - clp->server_scope = NULL; + kfree(clp->cl_serverscope); + clp->cl_serverscope = NULL; } - if (!clp->server_scope) { - clp->server_scope = res.server_scope; + if (!clp->cl_serverscope) { + clp->cl_serverscope = res.server_scope; goto out; } } diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 5498e9d9ba84..900d733668eb 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -17,7 +17,7 @@ struct nfs4_sequence_args; struct nfs4_sequence_res; struct nfs_server; struct nfs4_minor_version_ops; -struct server_scope; +struct nfs41_server_scope; struct nfs41_impl_id; /* @@ -80,13 +80,13 @@ struct nfs_client { /* The flags used for obtaining the clientid during EXCHANGE_ID */ u32 cl_exchange_flags; struct nfs4_session *cl_session; /* shared session */ + struct nfs41_server_scope *cl_serverscope; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif - struct server_scope *server_scope; /* from exchange_id */ struct nfs41_impl_id *impl_id; /* from exchange_id */ struct net *net; }; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2e53a3f1d2ff..c420b8d60a55 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1104,7 +1104,7 @@ struct server_owner { char major_id[NFS4_OPAQUE_LIMIT]; }; -struct server_scope { +struct nfs41_server_scope { uint32_t server_scope_sz; char server_scope[NFS4_OPAQUE_LIMIT]; }; @@ -1118,7 +1118,7 @@ struct nfs41_impl_id { struct nfs41_exchange_id_res { struct nfs_client *client; u32 flags; - struct server_scope *server_scope; + struct nfs41_server_scope *server_scope; struct nfs41_impl_id *impl_id; }; -- cgit v1.2.3 From 591555465ec513c42416392d392fd56866cb220c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:44:41 -0400 Subject: NFS: Use proper naming conventions for nfs_client.impl_id field Clean up: When naming fields and data types, follow established conventions to facilitate accurate grep/cscope searches. Additionally, for consistency, move the impl_id field into the NFSv4- specific part of the nfs_client, and free that memory in the logic that shuts down NFSv4 nfs_clients. Introduced by commit 7d2ed9ac "NFSv4: parse and display server implementation ids," Fri Feb 17, 2012. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/nfs4proc.c | 12 ++++++------ fs/nfs/super.c | 4 ++-- include/linux/nfs_fs_sb.h | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 471fc9b927a9..39db1beb92f8 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -238,6 +238,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) rpc_destroy_wait_queue(&clp->cl_rpcwaitq); kfree(clp->cl_serverscope); + kfree(clp->cl_implid); } /* idr_remove_all is not needed as all id's are removed by nfs_put_client */ @@ -306,7 +307,6 @@ static void nfs_free_client(struct nfs_client *clp) put_net(clp->net); kfree(clp->cl_hostname); - kfree(clp->impl_id); kfree(clp); dprintk("<-- nfs_free_client()\n"); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 94494f24bb12..daa4e1b17313 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5119,8 +5119,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) if (!status) { /* use the most recent implementation id */ - kfree(clp->impl_id); - clp->impl_id = res.impl_id; + kfree(clp->cl_implid); + clp->cl_implid = res.impl_id; } else kfree(res.impl_id); @@ -5144,12 +5144,12 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) out_server_scope: kfree(res.server_scope); out: - if (clp->impl_id) + if (clp->cl_implid) dprintk("%s: Server Implementation ID: " "domain: %s, name: %s, date: %llu,%u\n", - __func__, clp->impl_id->domain, clp->impl_id->name, - clp->impl_id->date.seconds, - clp->impl_id->date.nseconds); + __func__, clp->cl_implid->domain, clp->cl_implid->name, + clp->cl_implid->date.seconds, + clp->cl_implid->date.nseconds); dprintk("<-- %s status= %d\n", __func__, status); return status; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index a973eb101a92..ff656c022684 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -796,8 +796,8 @@ static void show_pnfs(struct seq_file *m, struct nfs_server *server) static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss) { - if (nfss->nfs_client && nfss->nfs_client->impl_id) { - struct nfs41_impl_id *impl_id = nfss->nfs_client->impl_id; + if (nfss->nfs_client && nfss->nfs_client->cl_implid) { + struct nfs41_impl_id *impl_id = nfss->nfs_client->cl_implid; seq_printf(m, "\n\timpl_id:\tname='%s',domain='%s'," "date='%llu,%u'", impl_id->name, impl_id->domain, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 900d733668eb..773e02135903 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -81,13 +81,13 @@ struct nfs_client { u32 cl_exchange_flags; struct nfs4_session *cl_session; /* shared session */ struct nfs41_server_scope *cl_serverscope; + struct nfs41_impl_id *cl_implid; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif - struct nfs41_impl_id *impl_id; /* from exchange_id */ struct net *net; }; -- cgit v1.2.3 From 73ea666c2bb536f2862cefdb3e014ed62b262ba5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:44:50 -0400 Subject: NFS: Use proper naming conventions for the nfs_client.net field Clean up: When naming fields and data types, follow established conventions to facilitate accurate grep/cscope searches. Introduced by commit e50a7a1a "NFS: make NFS client allocated per network namespace context," Tue Jan 10, 2012. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayoutdev.c | 2 +- fs/nfs/client.c | 22 +++++++++++----------- fs/nfs/idmap.c | 4 ++-- fs/nfs/nfs4filelayoutdev.c | 2 +- include/linux/nfs_fs_sb.h | 2 +- 5 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c index a5c88a554d92..c96554245ccf 100644 --- a/fs/nfs/blocklayout/blocklayoutdev.c +++ b/fs/nfs/blocklayout/blocklayoutdev.c @@ -123,7 +123,7 @@ nfs4_blk_decode_device(struct nfs_server *server, uint8_t *dataptr; DECLARE_WAITQUEUE(wq, current); int offset, len, i, rc; - struct net *net = server->nfs_client->net; + struct net *net = server->nfs_client->cl_net; struct nfs_net *nn = net_generic(net, nfs_net_id); struct bl_dev_msg *reply = &nn->bl_mount_reply; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 39db1beb92f8..9b9df71df09a 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -65,7 +65,7 @@ static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq); static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) { int ret = 0; - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); if (clp->rpc_ops->version != 4 || minorversion != 0) return ret; @@ -174,7 +174,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ clp->cl_rpcclient = ERR_PTR(-EINVAL); clp->cl_proto = cl_init->proto; - clp->net = get_net(cl_init->net); + clp->cl_net = get_net(cl_init->net); #ifdef CONFIG_NFS_V4 err = nfs_get_cb_ident_idr(clp, cl_init->minorversion); @@ -252,7 +252,7 @@ void nfs_cleanup_cb_ident_idr(struct net *net) /* nfs_client_lock held */ static void nfs_cb_idr_remove_locked(struct nfs_client *clp) { - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); if (clp->cl_cb_ident) idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident); @@ -305,7 +305,7 @@ static void nfs_free_client(struct nfs_client *clp) if (clp->cl_machine_cred != NULL) put_rpccred(clp->cl_machine_cred); - put_net(clp->net); + put_net(clp->cl_net); kfree(clp->cl_hostname); kfree(clp); @@ -323,7 +323,7 @@ void nfs_put_client(struct nfs_client *clp) return; dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count)); - nn = net_generic(clp->net, nfs_net_id); + nn = net_generic(clp->cl_net, nfs_net_id); if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) { list_del(&clp->cl_share_link); @@ -661,7 +661,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp, { struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { - .net = clp->net, + .net = clp->cl_net, .protocol = clp->cl_proto, .address = (struct sockaddr *)&clp->cl_addr, .addrsize = clp->cl_addrlen, @@ -715,7 +715,7 @@ static int nfs_start_lockd(struct nfs_server *server) .nfs_version = clp->rpc_ops->version, .noresvport = server->flags & NFS_MOUNT_NORESVPORT ? 1 : 0, - .net = clp->net, + .net = clp->cl_net, }; if (nlm_init.nfs_version > 3) @@ -1060,7 +1060,7 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve static void nfs_server_insert_lists(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); spin_lock(&nn->nfs_client_lock); list_add_tail_rcu(&server->client_link, &clp->cl_superblocks); @@ -1077,7 +1077,7 @@ static void nfs_server_remove_lists(struct nfs_server *server) if (clp == NULL) return; - nn = net_generic(clp->net, nfs_net_id); + nn = net_generic(clp->cl_net, nfs_net_id); spin_lock(&nn->nfs_client_lock); list_del_rcu(&server->client_link); if (list_empty(&clp->cl_superblocks)) @@ -1486,7 +1486,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, .rpc_ops = &nfs_v4_clientops, .proto = ds_proto, .minorversion = mds_clp->cl_minorversion, - .net = mds_clp->net, + .net = mds_clp->cl_net, }; struct rpc_timeout ds_timeout; struct nfs_client *clp; @@ -1709,7 +1709,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, rpc_protocol(parent_server->client), parent_server->client->cl_timeout, parent_client->cl_mvops->minor_version, - parent_client->net); + parent_client->cl_net); if (error < 0) goto error; diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 3e8edbe71ec6..2eaecf9d8db7 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -415,7 +415,7 @@ static int __nfs_idmap_register(struct dentry *dir, static void nfs_idmap_unregister(struct nfs_client *clp, struct rpc_pipe *pipe) { - struct net *net = clp->net; + struct net *net = clp->cl_net; struct super_block *pipefs_sb; pipefs_sb = rpc_get_sb_net(net); @@ -429,7 +429,7 @@ static int nfs_idmap_register(struct nfs_client *clp, struct idmap *idmap, struct rpc_pipe *pipe) { - struct net *net = clp->net; + struct net *net = clp->cl_net; struct super_block *pipefs_sb; int err = 0; diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index bf49b78db1b3..c610f84ff030 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -629,7 +629,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags) mp_count = be32_to_cpup(p); /* multipath count */ for (j = 0; j < mp_count; j++) { - da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->net, + da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->cl_net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 773e02135903..59410b365ba4 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -88,7 +88,7 @@ struct nfs_client { struct fscache_cookie *fscache; /* client index cache cookie */ #endif - struct net *net; + struct net *cl_net; }; /* -- cgit v1.2.3 From f092075dd33ea04000590e8ffea65c2e7d03d764 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:45:41 -0400 Subject: NFS: Always use the same SETCLIENTID boot verifier Currently our NFS client assigns a unique SETCLIENTID boot verifier for each server IP address it knows about. It's set to CURRENT_TIME when the struct nfs_client for that server IP is created. During the SETCLIENTID operation, our client also presents an nfs_client_id4 string to servers, as an identifier on which the server can hang all of this client's NFSv4 state. Our client's nfs_client_id4 string is unique for each server IP address. An NFSv4 server is obligated to wipe all NFSv4 state associated with an nfs_client_id4 string when the client presents the same nfs_client_id4 string along with a changed SETCLIENTID boot verifier. When our client unmounts the last of a server's shares, it destroys that server's struct nfs_client. The next time the client mounts that NFS server, it creates a fresh struct nfs_client with a fresh boot verifier. On seeing the fresh verifer, the server wipes any previous NFSv4 state associated with that nfs_client_id4. However, NFSv4.1 clients are supposed to present the same nfs_client_id4 string to all servers. And, to support Transparent State Migration, the same nfs_client_id4 string should be presented to all NFSv4.0 servers so they recognize that migrated state for this client belongs with state a server may already have for this client. (This is known as the Uniform Client String model). If the nfs_client_id4 string is the same but the boot verifier changes for each server IP address, SETCLIENTID and EXCHANGE_ID operations from such a client could unintentionally result in a server wiping a client's previously obtained lease. Thus, if our NFS client is going to use a fixed nfs_client_id4 string, either for NFSv4.0 or NFSv4.1 mounts, our NFS client should use a boot verifier that does not change depending on server IP address. Replace our current per-nfs_client boot verifier with a per-nfs_net boot verifier. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/netns.h | 5 +++++ fs/nfs/nfs4proc.c | 14 ++++++++------ fs/nfs/nfs4xdr.c | 5 ++++- include/linux/nfs_fs_sb.h | 3 --- 5 files changed, 18 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 9b9df71df09a..af9b7e4b9df2 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -184,7 +184,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ spin_lock_init(&clp->cl_lock); INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state); rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); - clp->cl_boot_time = CURRENT_TIME; clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; clp->cl_minorversion = cl_init->minorversion; clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; @@ -1813,6 +1812,7 @@ void nfs_clients_init(struct net *net) idr_init(&nn->cb_ident_idr); #endif spin_lock_init(&nn->nfs_client_lock); + nn->boot_time = CURRENT_TIME; } #ifdef CONFIG_PROC_FS diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index aa14ec303e94..8a6394edb8b0 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -1,3 +1,7 @@ +/* + * NFS-private data for each "struct net". Accessed with net_generic(). + */ + #ifndef __NFS_NETNS_H__ #define __NFS_NETNS_H__ @@ -20,6 +24,7 @@ struct nfs_net { struct idr cb_ident_idr; /* Protected by nfs_client_lock */ #endif spinlock_t nfs_client_lock; + struct timespec boot_time; }; extern int nfs_net_id; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 81ccdbbb43e8..9e9334a172cf 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -64,6 +64,7 @@ #include "iostat.h" #include "callback.h" #include "pnfs.h" +#include "netns.h" #define NFSDBG_FACILITY NFSDBG_PROC @@ -3903,8 +3904,8 @@ wait_on_recovery: return -EAGAIN; } -static void nfs4_construct_boot_verifier(struct nfs_client *clp, - nfs4_verifier *bootverf) +static void nfs4_init_boot_verifier(const struct nfs_client *clp, + nfs4_verifier *bootverf) { __be32 verf[2]; @@ -3914,8 +3915,9 @@ static void nfs4_construct_boot_verifier(struct nfs_client *clp, verf[0] = 0; verf[1] = (__be32)(NSEC_PER_SEC + 1); } else { - verf[0] = (__be32)clp->cl_boot_time.tv_sec; - verf[1] = (__be32)clp->cl_boot_time.tv_nsec; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + verf[0] = (__be32)nn->boot_time.tv_sec; + verf[1] = (__be32)nn->boot_time.tv_nsec; } memcpy(bootverf->data, verf, sizeof(bootverf->data)); } @@ -3939,7 +3941,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, int loop = 0; int status; - nfs4_construct_boot_verifier(clp, &sc_verifier); + nfs4_init_boot_verifier(clp, &sc_verifier); for(;;) { rcu_read_lock(); @@ -5099,7 +5101,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) dprintk("--> %s\n", __func__); BUG_ON(clp == NULL); - nfs4_construct_boot_verifier(clp, &verifier); + nfs4_init_boot_verifier(clp, &verifier); args.id_len = scnprintf(args.id, sizeof(args.id), "%s/%s/%u", diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index db040e971932..12b99825a1c1 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -53,9 +53,11 @@ #include #include #include + #include "nfs4_fs.h" #include "internal.h" #include "pnfs.h" +#include "netns.h" #define NFSDBG_FACILITY NFSDBG_XDR @@ -1702,6 +1704,7 @@ static void encode_create_session(struct xdr_stream *xdr, char machine_name[NFS4_MAX_MACHINE_NAME_LEN]; uint32_t len; struct nfs_client *clp = args->client; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); u32 max_resp_sz_cached; /* @@ -1743,7 +1746,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */ /* authsys_parms rfc1831 */ - *p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ + *p++ = (__be32)nn->boot_time.tv_nsec; /* stamp */ p = xdr_encode_opaque(p, machine_name, len); *p++ = cpu_to_be32(0); /* UID */ *p++ = cpu_to_be32(0); /* GID */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 59410b365ba4..fbec57d6dc0a 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -61,9 +61,6 @@ struct nfs_client { struct rpc_wait_queue cl_rpcwaitq; - /* used for the setclientid verifier */ - struct timespec cl_boot_time; - /* idmapper */ struct idmap * cl_idmap; -- cgit v1.2.3 From 8cab4c390b43fe34c07bd33799c1bc24be648122 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:45:59 -0400 Subject: NFS: Refactor nfs_get_client(): initialize nfs_client Clean up: Continue to rationalize the locking in nfs_get_client() by moving the logic that handles the case where a matching server IP address is not found. When we support server trunking detection, client initialization may return a different nfs_client struct than was passed to it. Change the synopsis of the init_client methods to return an nfs_client. The client initialization logic in nfs_get_client() is not much more than a wrapper around ->init_client. It's simpler to keep the little bits of error handling in the version-specific init_client methods. No behavior change is expected. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 76 +++++++++++++++++++++++++++---------------------- fs/nfs/internal.h | 4 +-- include/linux/nfs_xdr.h | 3 +- 3 files changed, 46 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 5f19f9577730..8a4b3c2c5a2b 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -546,7 +546,6 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, int noresvport) { struct nfs_client *clp, *new = NULL; - int error; struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id); dprintk("--> nfs_get_client(%s,v%u)\n", @@ -563,8 +562,13 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, nfs_free_client(new); return nfs_found_client(cl_init, clp); } - if (new) - goto install_client; + if (new) { + list_add(&new->cl_share_link, &nn->nfs_client_list); + spin_unlock(&nn->nfs_client_lock); + return cl_init->rpc_ops->init_client(new, + timeparms, ip_addr, + authflavour, noresvport); + } spin_unlock(&nn->nfs_client_lock); @@ -574,21 +578,6 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n", cl_init->hostname ?: "", PTR_ERR(new)); return new; - - /* install a new client and return with it unready */ -install_client: - clp = new; - list_add(&clp->cl_share_link, &nn->nfs_client_list); - spin_unlock(&nn->nfs_client_lock); - - error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr, - authflavour, noresvport); - if (error < 0) { - nfs_put_client(clp); - return ERR_PTR(error); - } - dprintk("--> nfs_get_client() = %p [new]\n", clp); - return clp; } /* @@ -813,10 +802,19 @@ static int nfs_init_server_rpcclient(struct nfs_server *server, return 0; } -/* - * Initialise an NFS2 or NFS3 client +/** + * nfs_init_client - Initialise an NFS2 or NFS3 client + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: IP presentation address (not used) + * @authflavor: authentication flavor for underlying RPC transport + * @noresvport: set if RPC transport can use an ephemeral source port + * + * Returns pointer to an NFS client, or an ERR_PTR value. */ -int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, +struct nfs_client *nfs_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, const char *ip_addr, rpc_authflavor_t authflavour, int noresvport) { @@ -825,7 +823,7 @@ int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, if (clp->cl_cons_state == NFS_CS_READY) { /* the client is already initialised */ dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp); - return 0; + return clp; } /* @@ -837,12 +835,13 @@ int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, if (error < 0) goto error; nfs_mark_client_ready(clp, NFS_CS_READY); - return 0; + return clp; error: nfs_mark_client_ready(clp, error); + nfs_put_client(clp); dprintk("<-- nfs_init_client() = xerror %d\n", error); - return error; + return ERR_PTR(error); } /* @@ -1358,14 +1357,22 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) return nfs4_init_callback(clp); } -/* - * Initialise an NFS4 client record +/** + * nfs4_init_client - Initialise an NFS4 client record + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: callback IP address in presentation format + * @authflavor: authentication flavor for underlying RPC transport + * @noresvport: set if RPC transport can use an ephemeral source port + * + * Returns pointer to an NFS client, or an ERR_PTR value. */ -int nfs4_init_client(struct nfs_client *clp, - const struct rpc_timeout *timeparms, - const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport) +struct nfs_client *nfs4_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr, + rpc_authflavor_t authflavour, + int noresvport) { char buf[INET6_ADDRSTRLEN + 1]; int error; @@ -1373,7 +1380,7 @@ int nfs4_init_client(struct nfs_client *clp, if (clp->cl_cons_state == NFS_CS_READY) { /* the client is initialised already */ dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp); - return 0; + return clp; } /* Check NFS protocol revision and initialize RPC op vector */ @@ -1413,12 +1420,13 @@ int nfs4_init_client(struct nfs_client *clp, if (!nfs4_has_session(clp)) nfs_mark_client_ready(clp, NFS_CS_READY); - return 0; + return clp; error: nfs_mark_client_ready(clp, error); + nfs_put_client(clp); dprintk("<-- nfs4_init_client() = xerror %d\n", error); - return error; + return ERR_PTR(error); } /* diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 989959a59f07..3a9e80c9524b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -238,7 +238,7 @@ extern int nfs4_init_ds_session(struct nfs_client *clp); /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); -extern int nfs_init_client(struct nfs_client *clp, +extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, rpc_authflavor_t authflavour, int noresvport); @@ -373,7 +373,7 @@ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, /* nfs4proc.c */ extern void __nfs4_read_done_cb(struct nfs_read_data *); -extern int nfs4_init_client(struct nfs_client *clp, +extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, rpc_authflavor_t authflavour, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c420b8d60a55..0c521cd496a7 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1397,7 +1397,8 @@ struct nfs_rpc_ops { struct nfs_open_context *ctx, int open_flags, struct iattr *iattr); - int (*init_client) (struct nfs_client *, const struct rpc_timeout *, + struct nfs_client * + (*init_client) (struct nfs_client *, const struct rpc_timeout *, const char *, rpc_authflavor_t, int); }; -- cgit v1.2.3 From 4bf590e08f6db3395c181618a4c14f1c39b7c4af Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:46:07 -0400 Subject: NFS: Add nfs_client behavior flags "noresvport" and "discrtry" can be passed to nfs_create_rpc_client() by setting flags in the passed-in nfs_client. This change makes it easy to add new flags. Note that these settings are now "sticky" over the lifetime of a struct nfs_client, and may even be copied when an nfs_client is cloned. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 42 ++++++++++++++++++++---------------------- fs/nfs/internal.h | 6 ++---- include/linux/nfs_fs_sb.h | 3 +++ include/linux/nfs_xdr.h | 2 +- 4 files changed, 26 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8a4b3c2c5a2b..34b2e68c5249 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -131,6 +131,7 @@ const struct rpc_program nfsacl_program = { #endif /* CONFIG_NFS_V3_ACL */ struct nfs_client_initdata { + unsigned long init_flags; const char *hostname; const struct sockaddr *addr; size_t addrlen; @@ -542,8 +543,7 @@ static struct nfs_client * nfs_get_client(const struct nfs_client_initdata *cl_init, const struct rpc_timeout *timeparms, const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport) + rpc_authflavor_t authflavour) { struct nfs_client *clp, *new = NULL; struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id); @@ -565,9 +565,10 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, if (new) { list_add(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); + new->cl_flags = cl_init->init_flags; return cl_init->rpc_ops->init_client(new, timeparms, ip_addr, - authflavour, noresvport); + authflavour); } spin_unlock(&nn->nfs_client_lock); @@ -651,8 +652,7 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, */ static int nfs_create_rpc_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - rpc_authflavor_t flavor, - int discrtry, int noresvport) + rpc_authflavor_t flavor) { struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { @@ -667,9 +667,9 @@ static int nfs_create_rpc_client(struct nfs_client *clp, .authflavor = flavor, }; - if (discrtry) + if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_DISCRTRY; - if (noresvport) + if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; if (!IS_ERR(clp->cl_rpcclient)) @@ -809,14 +809,12 @@ static int nfs_init_server_rpcclient(struct nfs_server *server, * @timeparms: timeout parameters for underlying RPC transport * @ip_addr: IP presentation address (not used) * @authflavor: authentication flavor for underlying RPC transport - * @noresvport: set if RPC transport can use an ephemeral source port * * Returns pointer to an NFS client, or an ERR_PTR value. */ struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, rpc_authflavor_t authflavour, - int noresvport) + const char *ip_addr, rpc_authflavor_t authflavour) { int error; @@ -830,8 +828,7 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp, * Create a client RPC handle for doing FSSTAT with UNIX auth only * - RFC 2623, sec 2.3.2 */ - error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX, - 0, noresvport); + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); if (error < 0) goto error; nfs_mark_client_ready(clp, NFS_CS_READY); @@ -881,10 +878,11 @@ static int nfs_init_server(struct nfs_server *server, nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, data->timeo, data->retrans); + if (data->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); /* Allocate or find a client reference we can use */ - clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX, - data->flags & NFS_MOUNT_NORESVPORT); + clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX); if (IS_ERR(clp)) { dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp)); return PTR_ERR(clp); @@ -1364,15 +1362,13 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) * @timeparms: timeout parameters for underlying RPC transport * @ip_addr: callback IP address in presentation format * @authflavor: authentication flavor for underlying RPC transport - * @noresvport: set if RPC transport can use an ephemeral source port * * Returns pointer to an NFS client, or an ERR_PTR value. */ struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport) + rpc_authflavor_t authflavour) { char buf[INET6_ADDRSTRLEN + 1]; int error; @@ -1386,8 +1382,8 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, /* Check NFS protocol revision and initialize RPC op vector */ clp->rpc_ops = &nfs_v4_clientops; - error = nfs_create_rpc_client(clp, timeparms, authflavour, - 1, noresvport); + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + error = nfs_create_rpc_client(clp, timeparms, authflavour); if (error < 0) goto error; @@ -1455,9 +1451,11 @@ static int nfs4_set_client(struct nfs_server *server, dprintk("--> nfs4_set_client()\n"); + if (server->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); + /* Allocate or find a client reference we can use */ - clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour, - server->flags & NFS_MOUNT_NORESVPORT); + clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour); if (IS_ERR(clp)) { error = PTR_ERR(clp); goto error; @@ -1512,7 +1510,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, */ nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, - mds_clp->cl_rpcclient->cl_auth->au_flavor, 0); + mds_clp->cl_rpcclient->cl_auth->au_flavor); dprintk("<-- %s %p\n", __func__, clp); return clp; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3a9e80c9524b..547f24f17d16 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -240,8 +240,7 @@ extern int nfs4_init_ds_session(struct nfs_client *clp); void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, rpc_authflavor_t authflavour, - int noresvport); + const char *ip_addr, rpc_authflavor_t authflavour); /* dir.c */ extern int nfs_access_cache_shrinker(struct shrinker *shrink, @@ -376,8 +375,7 @@ extern void __nfs4_read_done_cb(struct nfs_read_data *); extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport); + rpc_authflavor_t authflavour); extern int _nfs4_call_sync(struct rpc_clnt *clnt, struct nfs_server *server, struct rpc_message *msg, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index fbec57d6dc0a..3a99f5252340 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -35,6 +35,9 @@ struct nfs_client { #define NFS_CS_RENEWD 3 /* - renewd started */ #define NFS_CS_STOP_RENEW 4 /* no more state to renew */ #define NFS_CS_CHECK_LEASE_TIME 5 /* need to check lease time */ + unsigned long cl_flags; /* behavior switches */ +#define NFS_CS_NORESVPORT 0 /* - use ephemeral src port */ +#define NFS_CS_DISCRTRY 1 /* - disconnect on RPC retry */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0c521cd496a7..07048c012dec 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1399,7 +1399,7 @@ struct nfs_rpc_ops { struct iattr *iattr); struct nfs_client * (*init_client) (struct nfs_client *, const struct rpc_timeout *, - const char *, rpc_authflavor_t, int); + const char *, rpc_authflavor_t); }; /* -- cgit v1.2.3 From acdeb69d9c5934a678a732b4e24770326bf9471e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 21 May 2012 22:46:16 -0400 Subject: NFS: EXCHANGE_ID should save the server major and minor ID Save the server major and minor ID results from EXCHANGE_ID, as they are needed for detecting server trunking. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 1 + fs/nfs/nfs4proc.c | 17 ++++++++++++++++- fs/nfs/nfs4xdr.c | 13 ++++++++----- include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 3 ++- 5 files changed, 28 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 34b2e68c5249..3c144689f9e4 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -237,6 +237,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) nfs_idmap_delete(clp); rpc_destroy_wait_queue(&clp->cl_rpcwaitq); + kfree(clp->cl_serverowner); kfree(clp->cl_serverscope); kfree(clp->cl_implid); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9e9334a172cf..0d46fe449f0b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5109,11 +5109,18 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) clp->cl_rpcclient->cl_nodename, clp->cl_rpcclient->cl_auth->au_flavor); + res.server_owner = kzalloc(sizeof(struct nfs41_server_owner), + GFP_KERNEL); + if (unlikely(res.server_owner == NULL)) { + status = -ENOMEM; + goto out; + } + res.server_scope = kzalloc(sizeof(struct nfs41_server_scope), GFP_KERNEL); if (unlikely(res.server_scope == NULL)) { status = -ENOMEM; - goto out; + goto out_server_owner; } res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_KERNEL); @@ -5126,6 +5133,12 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) if (status == 0) status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags); + if (status == 0) { + kfree(clp->cl_serverowner); + clp->cl_serverowner = res.server_owner; + res.server_owner = NULL; + } + if (status == 0) { /* use the most recent implementation id */ kfree(clp->cl_implid); @@ -5150,6 +5163,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) } } +out_server_owner: + kfree(res.server_owner); out_server_scope: kfree(res.server_scope); out: diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 12b99825a1c1..5ad2b2c2aecb 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5144,24 +5144,27 @@ static int decode_exchange_id(struct xdr_stream *xdr, if (dummy != SP4_NONE) return -EIO; - /* Throw away minor_id */ + /* server_owner4.so_minor_id */ p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; + p = xdr_decode_hyper(p, &res->server_owner->minor_id); - /* Throw away Major id */ + /* server_owner4.so_major_id */ status = decode_opaque_inline(xdr, &dummy, &dummy_str); if (unlikely(status)) return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(res->server_owner->major_id, dummy_str, dummy); + res->server_owner->major_id_sz = dummy; - /* Save server_scope */ + /* server_scope4 */ status = decode_opaque_inline(xdr, &dummy, &dummy_str); if (unlikely(status)) return status; - if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) return -EIO; - memcpy(res->server_scope->server_scope, dummy_str, dummy); res->server_scope->server_scope_sz = dummy; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 3a99f5252340..fbb78fb09bd2 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -80,6 +80,7 @@ struct nfs_client { /* The flags used for obtaining the clientid during EXCHANGE_ID */ u32 cl_exchange_flags; struct nfs4_session *cl_session; /* shared session */ + struct nfs41_server_owner *cl_serverowner; struct nfs41_server_scope *cl_serverscope; struct nfs41_impl_id *cl_implid; #endif /* CONFIG_NFS_V4 */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 07048c012dec..0872f32c8eef 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1098,7 +1098,7 @@ struct nfs41_exchange_id_args { u32 flags; }; -struct server_owner { +struct nfs41_server_owner { uint64_t minor_id; uint32_t major_id_sz; char major_id[NFS4_OPAQUE_LIMIT]; @@ -1118,6 +1118,7 @@ struct nfs41_impl_id { struct nfs41_exchange_id_res { struct nfs_client *client; u32 flags; + struct nfs41_server_owner *server_owner; struct nfs41_server_scope *server_scope; struct nfs41_impl_id *impl_id; }; -- cgit v1.2.3 From 730a3d01b1e1e3ba102a5a4d3d5dcfecd55326b6 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 18 May 2012 20:22:45 +0200 Subject: mfd: Add r_select to lm3533 platform data Add resistor-select parameter to the platform data. Signed-off-by: Johan Hovold Signed-off-by: Samuel Ortiz --- include/linux/mfd/lm3533.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h index 9660febe93c2..594bc591f256 100644 --- a/include/linux/mfd/lm3533.h +++ b/include/linux/mfd/lm3533.h @@ -43,6 +43,7 @@ struct lm3533_ctrlbank { struct lm3533_als_platform_data { unsigned pwm_mode:1; /* PWM input mode (default analog) */ + u8 r_select; /* 1 - 127 (ignored in PWM-mode) */ }; struct lm3533_bl_platform_data { -- cgit v1.2.3 From cb8d8654570c257d2ec5f7fa089e18b338314317 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Sat, 19 May 2012 02:01:41 +0530 Subject: mfd: Save device node parsed platform data for tps65910 sub devices Save the allocated memory to store the parsed device node information to the global device structure so that sub devices can directly use this pointer. In this way, the sub devices does not require to re-allocate the memory for storing the sub-devices specific device node information. Signed-off-by: Laxman Dewangan Signed-off-by: Samuel Ortiz --- drivers/mfd/tps65910.c | 6 +++++- include/linux/mfd/tps65910.h | 3 +++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c index 18b30cf45e5b..05d449b33693 100644 --- a/drivers/mfd/tps65910.c +++ b/drivers/mfd/tps65910.c @@ -209,14 +209,17 @@ static __devinit int tps65910_i2c_probe(struct i2c_client *i2c, { struct tps65910 *tps65910; struct tps65910_board *pmic_plat_data; + struct tps65910_board *of_pmic_plat_data = NULL; struct tps65910_platform_data *init_data; int ret = 0; int chip_id = id->driver_data; pmic_plat_data = dev_get_platdata(&i2c->dev); - if (!pmic_plat_data && i2c->dev.of_node) + if (!pmic_plat_data && i2c->dev.of_node) { pmic_plat_data = tps65910_parse_dt(i2c, &chip_id); + of_pmic_plat_data = pmic_plat_data; + } if (!pmic_plat_data) return -EINVAL; @@ -229,6 +232,7 @@ static __devinit int tps65910_i2c_probe(struct i2c_client *i2c, if (tps65910 == NULL) return -ENOMEM; + tps65910->of_plat_data = of_pmic_plat_data; i2c_set_clientdata(i2c, tps65910); tps65910->dev = &i2c->dev; tps65910->i2c_client = i2c; diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index ab04e901e57e..dd8dc0a6c462 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -830,6 +830,9 @@ struct tps65910 { struct tps65910_rtc *rtc; struct tps65910_power *power; + /* Device node parsed board data */ + struct tps65910_board *of_plat_data; + /* IRQ Handling */ struct mutex irq_lock; int chip_irq; -- cgit v1.2.3 From 78302a194c0ddf4438e50e3f9b327a6dce6bc8fc Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Wed, 23 May 2012 13:28:33 +0200 Subject: mfd: Fix max77693 build failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Without it we get: drivers/mfd/max77693.c: In function ‘max77693_i2c_probe’: drivers/mfd/max77693.c:157:2: error: implicit declaration of function ‘max77693_irq_init’ [-Werror=implicit-function-declaration] drivers/mfd/max77693.c: In function ‘max77693_resume’: drivers/mfd/max77693.c:215:2: error: implicit declaration of function ‘max77693_irq_resume’ [-Werror=implicit-function-declaration] drivers/mfd/max77693-irq.c: In function ‘max77693_irq_lock’: drivers/mfd/max77693-irq.c:104:2: error: ‘struct max77693_dev’ has no member named ‘irqlock’ drivers/mfd/max77693-irq.c: In function ‘max77693_irq_sync_unlock’: drivers/mfd/max77693-irq.c:119:11: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cache’ drivers/mfd/max77693-irq.c:119:42: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c:122:13: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c:125:24: error: ‘struct max77693_dev’ has no member named ‘irqlock’ drivers/mfd/max77693-irq.c: In function ‘max77693_irq_mask’: drivers/mfd/max77693-irq.c:141:11: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c:143:11: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c: In function ‘max77693_irq_unmask’: drivers/mfd/max77693-irq.c:153:11: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c:155:11: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c: In function ‘max77693_irq_thread’: drivers/mfd/max77693-irq.c:209:26: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c:211:27: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c:217:39: error: ‘struct max77693_dev’ has no member named ‘irq_domain’ drivers/mfd/max77693-irq.c: In function ‘max77693_irq_init’: drivers/mfd/max77693-irq.c:260:2: error: ‘struct max77693_dev’ has no member named ‘irqlock’ drivers/mfd/max77693-irq.c:268:12: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c:269:12: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cache’ drivers/mfd/max77693-irq.c:271:12: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cur’ drivers/mfd/max77693-irq.c:272:12: error: ‘struct max77693_dev’ has no member named ‘irq_masks_cache’ drivers/mfd/max77693-irq.c:292:10: error: ‘struct max77693_dev’ has no member named ‘irq_domain’ Signed-off-by: Samuel Ortiz --- include/linux/mfd/max77693-private.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index bf6077d3c43c..68263c5fa53c 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -198,8 +198,14 @@ struct max77693_dev { struct regmap *regmap_muic; struct regmap *regmap_haptic; + struct irq_domain *irq_domain; + int irq; + int irq_gpio; bool wakeup; + struct mutex irqlock; + int irq_masks_cur[MAX77693_IRQ_GROUP_NR]; + int irq_masks_cache[MAX77693_IRQ_GROUP_NR]; }; enum max77693_types { @@ -214,4 +220,8 @@ extern int max77693_bulk_write(struct regmap *map, u8 reg, int count, u8 *buf); extern int max77693_update_reg(struct regmap *map, u8 reg, u8 val, u8 mask); +extern int max77693_irq_init(struct max77693_dev *max77686); +extern void max77693_irq_exit(struct max77693_dev *max77686); +extern int max77693_irq_resume(struct max77693_dev *max77686); + #endif /* __LINUX_MFD_MAX77693_PRIV_H */ -- cgit v1.2.3 From 88034c3d88c2c48b215f2cc5eb22e564aa817f9c Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Wed, 23 May 2012 05:02:34 -0400 Subject: NFSv4.1 mdsthreshold attribute xdr We only support one layout type per file system, so one threshold_item4 per mdsthreshold4. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 125 +++++++++++++++++++++++++++++++++++++++++++++++- include/linux/nfs4.h | 7 +++ include/linux/nfs_xdr.h | 10 ++++ 3 files changed, 140 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 5ad2b2c2aecb..edb8ac7fce0e 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -101,9 +101,12 @@ static int nfs4_stat_to_errno(int); #define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2)) #define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) #define nfs4_group_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) +/* We support only one layout type per file system */ +#define decode_mdsthreshold_maxsz (1 + 1 + nfs4_fattr_bitmap_maxsz + 1 + 8) /* This is based on getfattr, which uses the most attributes: */ #define nfs4_fattr_value_maxsz (1 + (1 + 2 + 2 + 4 + 2 + 1 + 1 + 2 + 2 + \ - 3 + 3 + 3 + nfs4_owner_maxsz + nfs4_group_maxsz)) + 3 + 3 + 3 + nfs4_owner_maxsz + \ + nfs4_group_maxsz + decode_mdsthreshold_maxsz)) #define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \ nfs4_fattr_value_maxsz) #define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz) @@ -1172,6 +1175,16 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c bitmask[1] & nfs4_fattr_bitmap[1], hdr); } +static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask, + struct compound_hdr *hdr) +{ + encode_getattr_three(xdr, + bitmask[0] & nfs4_fattr_bitmap[0], + bitmask[1] & nfs4_fattr_bitmap[1], + bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD, + hdr); +} + static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) { encode_getattr_three(xdr, @@ -2164,7 +2177,7 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, encode_putfh(xdr, args->fh, &hdr); encode_open(xdr, args, &hdr); encode_getfh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); + encode_getfattr_open(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -4186,6 +4199,110 @@ xdr_error: return status; } +static int decode_threshold_hint(struct xdr_stream *xdr, + uint32_t *bitmap, + uint64_t *res, + uint32_t hint_bit) +{ + __be32 *p; + + *res = 0; + if (likely(bitmap[0] & hint_bit)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_first_threshold_item4(struct xdr_stream *xdr, + struct nfs4_threshold *res) +{ + __be32 *p, *savep; + uint32_t bitmap[3] = {0,}, attrlen; + int status; + + /* layout type */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + res->l_type = be32_to_cpup(p); + + /* thi_hintset bitmap */ + status = decode_attr_bitmap(xdr, bitmap); + if (status < 0) + goto xdr_error; + + /* thi_hintlist length */ + status = decode_attr_length(xdr, &attrlen, &savep); + if (status < 0) + goto xdr_error; + /* thi_hintlist */ + status = decode_threshold_hint(xdr, bitmap, &res->rd_sz, THRESHOLD_RD); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->wr_sz, THRESHOLD_WR); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->rd_io_sz, + THRESHOLD_RD_IO); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->wr_io_sz, + THRESHOLD_WR_IO); + if (status < 0) + goto xdr_error; + + status = verify_attr_len(xdr, savep, attrlen); + res->bm = bitmap[0]; + + dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n", + __func__, res->bm, res->rd_sz, res->wr_sz, res->rd_io_sz, + res->wr_io_sz); +xdr_error: + dprintk("%s ret=%d!\n", __func__, status); + return status; +} + +/* + * Thresholds on pNFS direct I/O vrs MDS I/O + */ +static int decode_attr_mdsthreshold(struct xdr_stream *xdr, + uint32_t *bitmap, + struct nfs4_threshold *res) +{ + __be32 *p; + int status = 0; + uint32_t num; + + if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U))) + return -EIO; + if (likely(bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + num = be32_to_cpup(p); + if (num == 0) + return 0; + if (num > 1) + printk(KERN_INFO "%s: Warning: Multiple pNFS layout " + "drivers per filesystem not supported\n", + __func__); + + status = decode_first_threshold_item4(xdr, res); + } + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fattr *fattr, struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc, @@ -4292,6 +4409,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; + status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold); + if (status < 0) + goto xdr_error; + xdr_error: dprintk("%s: xdr returned %d\n", __func__, -status); return status; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 0987146b0637..72b6bada0d79 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -526,6 +526,13 @@ enum lock_type4 { #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) +#define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) + +/* MDS threshold bitmap bits */ +#define THRESHOLD_RD (1UL << 0) +#define THRESHOLD_WR (1UL << 1) +#define THRESHOLD_RD_IO (1UL << 2) +#define THRESHOLD_WR_IO (1UL << 3) #define NFSPROC4_NULL 0 #define NFSPROC4_COMPOUND 1 diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0872f32c8eef..201c312152fb 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -35,6 +35,15 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid return a->major == b->major && a->minor == b->minor; } +struct nfs4_threshold { + __u32 bm; + __u32 l_type; + __u64 rd_sz; + __u64 wr_sz; + __u64 rd_io_sz; + __u64 wr_io_sz; +}; + struct nfs_fattr { unsigned int valid; /* which fields are valid */ umode_t mode; @@ -67,6 +76,7 @@ struct nfs_fattr { unsigned long gencount; struct nfs4_string *owner_name; struct nfs4_string *group_name; + struct nfs4_threshold *mdsthreshold; /* pNFS threshold hints */ }; #define NFS_ATTR_FATTR_TYPE (1U << 0) -- cgit v1.2.3 From 82be417aa37c05116e310b0f2171187ea389f89b Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Wed, 23 May 2012 05:02:35 -0400 Subject: NFSv4.1 cache mdsthreshold values on OPEN Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 2 ++ fs/nfs/nfs4proc.c | 38 +++++++++++++++++++++++++++++++++----- fs/nfs/pnfs.c | 12 ++++++++++++ fs/nfs/pnfs.h | 21 +++++++++++++++++++++ include/linux/nfs_fs.h | 1 + 5 files changed, 69 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 9ad81ce0c40f..889f7e5e92e1 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -641,6 +641,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); + ctx->mdsthreshold = NULL; return ctx; } @@ -669,6 +670,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) put_rpccred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); + kfree(ctx->mdsthreshold); kfree(ctx); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8f39bb3ca1b3..e725736ff288 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1782,7 +1782,14 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, struct /* * Returns a referenced nfs4_state */ -static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode, int flags, struct iattr *sattr, struct rpc_cred *cred, struct nfs4_state **res) +static int _nfs4_do_open(struct inode *dir, + struct dentry *dentry, + fmode_t fmode, + int flags, + struct iattr *sattr, + struct rpc_cred *cred, + struct nfs4_state **res, + struct nfs4_threshold **ctx_th) { struct nfs4_state_owner *sp; struct nfs4_state *state = NULL; @@ -1807,6 +1814,11 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode if (opendata == NULL) goto err_put_state_owner; + if (ctx_th && server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) { + opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); + if (!opendata->f_attr.mdsthreshold) + goto err_opendata_put; + } if (dentry->d_inode != NULL) opendata->state = nfs4_get_open_state(dentry->d_inode, sp); @@ -1832,11 +1844,19 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode nfs_setattr_update_inode(state->inode, sattr); nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr); } + + if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) + *ctx_th = opendata->f_attr.mdsthreshold; + else + kfree(opendata->f_attr.mdsthreshold); + opendata->f_attr.mdsthreshold = NULL; + nfs4_opendata_put(opendata); nfs4_put_state_owner(sp); *res = state; return 0; err_opendata_put: + kfree(opendata->f_attr.mdsthreshold); nfs4_opendata_put(opendata); err_put_state_owner: nfs4_put_state_owner(sp); @@ -1846,14 +1866,21 @@ out_err: } -static struct nfs4_state *nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode, int flags, struct iattr *sattr, struct rpc_cred *cred) +static struct nfs4_state *nfs4_do_open(struct inode *dir, + struct dentry *dentry, + fmode_t fmode, + int flags, + struct iattr *sattr, + struct rpc_cred *cred, + struct nfs4_threshold **ctx_th) { struct nfs4_exception exception = { }; struct nfs4_state *res; int status; do { - status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred, &res); + status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred, + &res, ctx_th); if (status == 0) break; /* NOTE: BAD_SEQID means the server and client disagree about the @@ -2177,7 +2204,8 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags struct nfs4_state *state; /* Protect against concurrent sillydeletes */ - state = nfs4_do_open(dir, ctx->dentry, ctx->mode, open_flags, attr, ctx->cred); + state = nfs4_do_open(dir, ctx->dentry, ctx->mode, open_flags, attr, + ctx->cred, &ctx->mdsthreshold); if (IS_ERR(state)) return ERR_CAST(state); ctx->state = state; @@ -2779,7 +2807,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, fmode = ctx->mode; } sattr->ia_mode &= ~current_umask(); - state = nfs4_do_open(dir, de, fmode, flags, sattr, cred); + state = nfs4_do_open(dir, de, fmode, flags, sattr, cred, NULL); d_drop(dentry); if (IS_ERR(state)) { status = PTR_ERR(state); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5d09a36b2cd8..cbcb6aea58a3 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1630,3 +1630,15 @@ out_free: kfree(data); goto out; } + +struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) +{ + struct nfs4_threshold *thp; + + thp = kzalloc(sizeof(*thp), GFP_NOFS); + if (!thp) { + dprintk("%s mdsthreshold allocation failed\n", __func__); + return NULL; + } + return thp; +} diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 7980756b2f57..29fd23c0efdc 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -227,6 +227,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head, const struct nfs_pgio_completion_ops *compl_ops); int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head, const struct nfs_pgio_completion_ops *compl_ops); +struct nfs4_threshold *pnfs_mdsthreshold_alloc(void); /* nfs4_deviceid_flags */ enum { @@ -360,6 +361,14 @@ static inline int pnfs_return_layout(struct inode *ino) return 0; } +static inline bool +pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, + struct nfs_server *nfss) +{ + return (dst && src && src->bm != 0 && + nfss->pnfs_curr_ld->id == src->l_type); +} + #ifdef NFS_DEBUG void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id); #else @@ -485,6 +494,18 @@ static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync) return 0; } +static inline bool +pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, + struct nfs_server *nfss) +{ + return false; +} + +static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) +{ + return NULL; +} + #endif /* CONFIG_NFS_V4_1 */ #endif /* FS_NFS_PNFS_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 80a9385b88ab..ce910cb7d761 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -102,6 +102,7 @@ struct nfs_open_context { int error; struct list_head list; + struct nfs4_threshold *mdsthreshold; }; struct nfs_open_dir_context { -- cgit v1.2.3 From 2701d086dbfca03b2d28b25c6dc11dd78d0e26ad Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 24 May 2012 13:13:24 -0400 Subject: NFSv4.1 add nfs_inode book keeping for mdsthreshold Keep track of the number of bytes read or written via buffered, direct, and mem-mapped i/o for use by mdsthreshold size_io hints. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 2 ++ fs/nfs/file.c | 1 + fs/nfs/inode.c | 2 ++ fs/nfs/pnfs.c | 3 +++ fs/nfs/read.c | 2 ++ include/linux/nfs_fs.h | 3 +++ 6 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index c47a46eaf905..23d170bc44f4 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -447,6 +447,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos); if (!result) result = nfs_direct_wait(dreq); + NFS_I(inode)->read_io += result; out_release: nfs_direct_req_release(dreq); out: @@ -785,6 +786,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } nfs_pageio_complete(&desc); + NFS_I(dreq->inode)->write_io += desc.pg_bytes_written; /* * If no bytes were started, return the error, and let the diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 8eda8a6644c3..56311ca5f9f8 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -424,6 +424,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, if (status < 0) return status; + NFS_I(mapping->host)->write_io += copied; return copied; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 889f7e5e92e1..a6f5fbbe9b9c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -323,6 +323,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_gid = -2; inode->i_blocks = 0; memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + nfsi->write_io = 0; + nfsi->read_io = 0; nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index cbcb6aea58a3..6620606f2687 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -395,6 +395,9 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, dprintk("%s:Begin lo %p\n", __func__, lo); if (list_empty(&lo->plh_segs)) { + /* Reset MDS Threshold I/O counters */ + NFS_I(lo->plh_inode)->write_io = 0; + NFS_I(lo->plh_inode)->read_io = 0; if (!test_and_set_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags)) put_layout_hdr_locked(lo); return 0; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 2cfdd7785411..86ced7836214 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -152,6 +152,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); + NFS_I(inode)->read_io += pgio.pg_bytes_written; return 0; } @@ -656,6 +657,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); nfs_pageio_complete(&pgio); + NFS_I(inode)->read_io += pgio.pg_bytes_written; npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index ce910cb7d761..b23cfc120edb 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -202,6 +202,9 @@ struct nfs_inode { /* pNFS layout information */ struct pnfs_layout_hdr *layout; #endif /* CONFIG_NFS_V4*/ + /* how many bytes have been written/read and how many bytes queued up */ + __u64 write_io; + __u64 read_io; #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; #endif -- cgit v1.2.3 From 7c44f1ae4a21458a1ea3d6482ffb3136f1df6d2b Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 24 May 2012 13:22:50 -0400 Subject: nfs4.1: add BIND_CONN_TO_SESSION operation This patch adds the BIND_CONN_TO_SESSION operation which is needed for upcoming SP4_MACH_CRED work and useful for recovering from broken connections without destroying the session. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4proc.c | 54 ++++++++++++++++++++++++++++ fs/nfs/nfs4xdr.c | 95 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfs4.h | 5 +++ include/linux/nfs_xdr.h | 6 ++++ 5 files changed, 161 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index e6da02124c4e..2c7f1cf85b8f 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -211,6 +211,7 @@ struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *); extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); +extern int nfs4_proc_bind_conn_to_session(struct nfs_client *); extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e725736ff288..e8988c000e7f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5099,6 +5099,60 @@ nfs41_same_server_scope(struct nfs41_server_scope *a, return false; } +/* + * nfs4_proc_bind_conn_to_session() + * + * The 4.1 client currently uses the same TCP connection for the + * fore and backchannel. + */ +int nfs4_proc_bind_conn_to_session(struct nfs_client *clp) +{ + int status; + struct nfs41_bind_conn_to_session_res res; + struct rpc_message msg = { + .rpc_proc = + &nfs4_procedures[NFSPROC4_CLNT_BIND_CONN_TO_SESSION], + .rpc_argp = clp, + .rpc_resp = &res, + }; + + dprintk("--> %s\n", __func__); + BUG_ON(clp == NULL); + + res.session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS); + if (unlikely(res.session == NULL)) { + status = -ENOMEM; + goto out; + } + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + if (status == 0) { + if (memcmp(res.session->sess_id.data, + clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) { + dprintk("NFS: %s: Session ID mismatch\n", __func__); + status = -EIO; + goto out_session; + } + if (res.dir != NFS4_CDFS4_BOTH) { + dprintk("NFS: %s: Unexpected direction from server\n", + __func__); + status = -EIO; + goto out_session; + } + if (res.use_conn_in_rdma_mode) { + dprintk("NFS: %s: Server returned RDMA mode = true\n", + __func__); + status = -EIO; + goto out_session; + } + } +out_session: + kfree(res.session); +out: + dprintk("<-- %s status= %d\n", __func__, status); + return status; +} + /* * nfs4_proc_exchange_id() * diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index edb8ac7fce0e..a6b95b766220 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -326,6 +326,16 @@ static int nfs4_stat_to_errno(int); 1 /* csr_flags */ + \ decode_channel_attrs_maxsz + \ decode_channel_attrs_maxsz) +#define encode_bind_conn_to_session_maxsz (op_encode_hdr_maxsz + \ + /* bctsa_sessid */ \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* bctsa_dir */ + \ + 1 /* bctsa_use_conn_in_rdma_mode */) +#define decode_bind_conn_to_session_maxsz (op_decode_hdr_maxsz + \ + /* bctsr_sessid */ \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* bctsr_dir */ + \ + 1 /* bctsr_use_conn_in_rdma_mode */) #define encode_destroy_session_maxsz (op_encode_hdr_maxsz + 4) #define decode_destroy_session_maxsz (op_decode_hdr_maxsz) #define encode_sequence_maxsz (op_encode_hdr_maxsz + \ @@ -719,6 +729,12 @@ static int nfs4_stat_to_errno(int); decode_putfh_maxsz + \ decode_secinfo_maxsz) #if defined(CONFIG_NFS_V4_1) +#define NFS4_enc_bind_conn_to_session_sz \ + (compound_encode_hdr_maxsz + \ + encode_bind_conn_to_session_maxsz) +#define NFS4_dec_bind_conn_to_session_sz \ + (compound_decode_hdr_maxsz + \ + decode_bind_conn_to_session_maxsz) #define NFS4_enc_exchange_id_sz \ (compound_encode_hdr_maxsz + \ encode_exchange_id_maxsz) @@ -1669,6 +1685,20 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru #if defined(CONFIG_NFS_V4_1) /* NFSv4.1 operations */ +static void encode_bind_conn_to_session(struct xdr_stream *xdr, + struct nfs4_session *session, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION, + decode_bind_conn_to_session_maxsz, hdr); + encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + p = xdr_reserve_space(xdr, 8); + *p++ = cpu_to_be32(NFS4_CDFC4_BACK_OR_BOTH); + *p = 0; /* use_conn_in_rdma_mode = False */ +} + static void encode_exchange_id(struct xdr_stream *xdr, struct nfs41_exchange_id_args *args, struct compound_hdr *hdr) @@ -2629,6 +2659,22 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, } #if defined(CONFIG_NFS_V4_1) +/* + * BIND_CONN_TO_SESSION request + */ +static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_client *clp) +{ + struct compound_hdr hdr = { + .minorversion = clp->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_bind_conn_to_session(xdr, clp->cl_session, &hdr); + encode_nops(&hdr); +} + /* * EXCHANGE_ID request */ @@ -5366,6 +5412,37 @@ static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN); } +static int decode_bind_conn_to_session(struct xdr_stream *xdr, + struct nfs41_bind_conn_to_session_res *res) +{ + __be32 *p; + int status; + + status = decode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION); + if (!status) + status = decode_sessionid(xdr, &res->session->sess_id); + if (unlikely(status)) + return status; + + /* dir flags, rdma mode bool */ + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + + res->dir = be32_to_cpup(p++); + if (res->dir == 0 || res->dir > NFS4_CDFS4_BOTH) + return -EIO; + if (be32_to_cpup(p) == 0) + res->use_conn_in_rdma_mode = false; + else + res->use_conn_in_rdma_mode = true; + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_create_session(struct xdr_stream *xdr, struct nfs41_create_session_res *res) { @@ -6647,6 +6724,22 @@ out: } #if defined(CONFIG_NFS_V4_1) +/* + * Decode BIND_CONN_TO_SESSION response + */ +static int nfs4_xdr_dec_bind_conn_to_session(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_bind_conn_to_session(xdr, res); + return status; +} + /* * Decode EXCHANGE_ID response */ @@ -7128,6 +7221,8 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner), PROC(SECINFO, enc_secinfo, dec_secinfo), #if defined(CONFIG_NFS_V4_1) + PROC(BIND_CONN_TO_SESSION, + enc_bind_conn_to_session, dec_bind_conn_to_session), PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id), PROC(CREATE_SESSION, enc_create_session, dec_create_session), PROC(DESTROY_SESSION, enc_destroy_session, dec_destroy_session), diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 72b6bada0d79..a2b71cbfc44a 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -69,6 +69,10 @@ #define NFS4_CDFC4_FORE_OR_BOTH 0x3 #define NFS4_CDFC4_BACK_OR_BOTH 0x7 +#define NFS4_CDFS4_FORE 0x1 +#define NFS4_CDFS4_BACK 0x2 +#define NFS4_CDFS4_BOTH 0x3 + #define NFS4_SET_TO_SERVER_TIME 0 #define NFS4_SET_TO_CLIENT_TIME 1 @@ -589,6 +593,7 @@ enum { NFSPROC4_CLNT_SECINFO, /* nfs41 */ + NFSPROC4_CLNT_BIND_CONN_TO_SESSION, NFSPROC4_CLNT_EXCHANGE_ID, NFSPROC4_CLNT_CREATE_SESSION, NFSPROC4_CLNT_DESTROY_SESSION, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 201c312152fb..6387fc0097fe 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1125,6 +1125,12 @@ struct nfs41_impl_id { struct nfstime4 date; }; +struct nfs41_bind_conn_to_session_res { + struct nfs4_session *session; + u32 dir; + bool use_conn_in_rdma_mode; +}; + struct nfs41_exchange_id_res { struct nfs_client *client; u32 flags; -- cgit v1.2.3 From ad24ecfbcddfa88541bccc980e753aeda8bf4031 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 25 May 2012 17:11:42 -0400 Subject: NFSv4.1: Move NFSPROC4_CLNT_BIND_CONN_TO_SESSION to the end of the operations For backward compatibility with nfs-utils. Signed-off-by: Trond Myklebust Cc: Weston Andros Adamson --- fs/nfs/nfs4xdr.c | 4 ++-- include/linux/nfs4.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index a6b95b766220..1d4d259c5b3c 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7221,8 +7221,6 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner), PROC(SECINFO, enc_secinfo, dec_secinfo), #if defined(CONFIG_NFS_V4_1) - PROC(BIND_CONN_TO_SESSION, - enc_bind_conn_to_session, dec_bind_conn_to_session), PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id), PROC(CREATE_SESSION, enc_create_session, dec_create_session), PROC(DESTROY_SESSION, enc_destroy_session, dec_destroy_session), @@ -7237,6 +7235,8 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid), PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid), PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist), + PROC(BIND_CONN_TO_SESSION, + enc_bind_conn_to_session, dec_bind_conn_to_session), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index a2b71cbfc44a..54006a997dd0 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -593,7 +593,6 @@ enum { NFSPROC4_CLNT_SECINFO, /* nfs41 */ - NFSPROC4_CLNT_BIND_CONN_TO_SESSION, NFSPROC4_CLNT_EXCHANGE_ID, NFSPROC4_CLNT_CREATE_SESSION, NFSPROC4_CLNT_DESTROY_SESSION, @@ -608,6 +607,7 @@ enum { NFSPROC4_CLNT_TEST_STATEID, NFSPROC4_CLNT_FREE_STATEID, NFSPROC4_CLNT_GETDEVICELIST, + NFSPROC4_CLNT_BIND_CONN_TO_SESSION, }; /* nfs41 types */ -- cgit v1.2.3 From 662455391040a783b89d0232e743c27c23617dbd Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 25 May 2012 17:18:09 -0400 Subject: NFSv4.1: Add DESTROY_CLIENTID Ensure that we destroy our lease on last unmount Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 1 + fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4proc.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/nfs4xdr.c | 52 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfs4.h | 1 + 5 files changed, 114 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index a50bdfbbc429..7d108753af81 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -209,6 +209,7 @@ static void nfs4_shutdown_session(struct nfs_client *clp) if (nfs4_has_session(clp)) { nfs4_deviceid_purge_client(clp); nfs4_destroy_session(clp->cl_session); + nfs4_destroy_clientid(clp); } } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index f7307304320a..b20b5164f70a 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -214,6 +214,7 @@ extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setcli extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred); extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); +extern int nfs4_destroy_clientid(struct nfs_client *clp); extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3fdff0cd558d..485a6c0cdc40 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5261,6 +5261,65 @@ out: return status; } +static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, + struct rpc_cred *cred) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_CLIENTID], + .rpc_argp = clp, + .rpc_cred = cred, + }; + int status; + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + if (status) + pr_warn("NFS: Got error %d from the server %s on " + "DESTROY_CLIENTID.", status, clp->cl_hostname); + return status; +} + +static int nfs4_proc_destroy_clientid(struct nfs_client *clp, + struct rpc_cred *cred) +{ + unsigned int loop; + int ret; + + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { + ret = _nfs4_proc_destroy_clientid(clp, cred); + switch (ret) { + case -NFS4ERR_DELAY: + case -NFS4ERR_CLIENTID_BUSY: + ssleep(1); + break; + default: + return ret; + } + } + return 0; +} + +int nfs4_destroy_clientid(struct nfs_client *clp) +{ + struct rpc_cred *cred; + int ret = 0; + + if (clp->cl_mvops->minor_version < 1) + goto out; + if (clp->cl_exchange_flags == 0) + goto out; + cred = nfs4_get_exchange_id_cred(clp); + ret = nfs4_proc_destroy_clientid(clp, cred); + if (cred) + put_rpccred(cred); + switch (ret) { + case 0: + case -NFS4ERR_STALE_CLIENTID: + clp->cl_exchange_flags = 0; + } +out: + return ret; +} + struct nfs4_get_lease_time_data { struct nfs4_get_lease_time_args *args; struct nfs4_get_lease_time_res *res; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1d4d259c5b3c..b9ce3fdb862a 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -338,6 +338,8 @@ static int nfs4_stat_to_errno(int); 1 /* bctsr_use_conn_in_rdma_mode */) #define encode_destroy_session_maxsz (op_encode_hdr_maxsz + 4) #define decode_destroy_session_maxsz (op_decode_hdr_maxsz) +#define encode_destroy_clientid_maxsz (op_encode_hdr_maxsz + 2) +#define decode_destroy_clientid_maxsz (op_decode_hdr_maxsz) #define encode_sequence_maxsz (op_encode_hdr_maxsz + \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 4) #define decode_sequence_maxsz (op_decode_hdr_maxsz + \ @@ -751,6 +753,10 @@ static int nfs4_stat_to_errno(int); encode_destroy_session_maxsz) #define NFS4_dec_destroy_session_sz (compound_decode_hdr_maxsz + \ decode_destroy_session_maxsz) +#define NFS4_enc_destroy_clientid_sz (compound_encode_hdr_maxsz + \ + encode_destroy_clientid_maxsz) +#define NFS4_dec_destroy_clientid_sz (compound_decode_hdr_maxsz + \ + decode_destroy_clientid_maxsz) #define NFS4_enc_sequence_sz \ (compound_decode_hdr_maxsz + \ encode_sequence_maxsz) @@ -1804,6 +1810,14 @@ static void encode_destroy_session(struct xdr_stream *xdr, encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); } +static void encode_destroy_clientid(struct xdr_stream *xdr, + uint64_t clientid, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DESTROY_CLIENTID, decode_destroy_clientid_maxsz, hdr); + encode_uint64(xdr, clientid); +} + static void encode_reclaim_complete(struct xdr_stream *xdr, struct nfs41_reclaim_complete_args *args, struct compound_hdr *hdr) @@ -2723,6 +2737,22 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * a DESTROY_CLIENTID request + */ +static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_client *clp) +{ + struct compound_hdr hdr = { + .minorversion = clp->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_destroy_clientid(xdr, clp->cl_clientid, &hdr); + encode_nops(&hdr); +} + /* * a SEQUENCE request */ @@ -5479,6 +5509,11 @@ static int decode_destroy_session(struct xdr_stream *xdr, void *dummy) return decode_op_hdr(xdr, OP_DESTROY_SESSION); } +static int decode_destroy_clientid(struct xdr_stream *xdr, void *dummy) +{ + return decode_op_hdr(xdr, OP_DESTROY_CLIENTID); +} + static int decode_reclaim_complete(struct xdr_stream *xdr, void *dummy) { return decode_op_hdr(xdr, OP_RECLAIM_COMPLETE); @@ -6788,6 +6823,22 @@ static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp, return status; } +/* + * Decode DESTROY_CLIENTID response + */ +static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_destroy_clientid(xdr, res); + return status; +} + /* * Decode SEQUENCE response */ @@ -7237,6 +7288,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist), PROC(BIND_CONN_TO_SESSION, enc_bind_conn_to_session, dec_bind_conn_to_session), + PROC(DESTROY_CLIENTID, enc_destroy_clientid, dec_destroy_clientid), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 54006a997dd0..af2d2fa30eee 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -608,6 +608,7 @@ enum { NFSPROC4_CLNT_FREE_STATEID, NFSPROC4_CLNT_GETDEVICELIST, NFSPROC4_CLNT_BIND_CONN_TO_SESSION, + NFSPROC4_CLNT_DESTROY_CLIENTID, }; /* nfs41 types */ -- cgit v1.2.3 From 32b0131069c5bebf52368a9fe170f8d58b78fa8d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 26 May 2012 13:41:04 -0400 Subject: NFSv4.1: Don't clobber the seqid if exchange_id returns a confirmed clientid If the EXCHGID4_FLAG_CONFIRMED_R flag is set, the client is in theory supposed to already know the correct value of the seqid, in which case RFC5661 states that it should ignore the value returned. Also ensure that if the sanity check in nfs4_check_cl_exchange_flags fails, then we must not change the nfs_client fields. Finally, clean up the code: we don't need to retest the value of 'status' unless it can change. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 17 +++++++++-------- fs/nfs/nfs4xdr.c | 7 +++---- include/linux/nfs_xdr.h | 3 ++- 3 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 485a6c0cdc40..9f0a96fe6212 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5171,7 +5171,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER, }; struct nfs41_exchange_id_res res = { - .client = clp, + 0 }; int status; struct rpc_message msg = { @@ -5214,22 +5214,22 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); if (status == 0) - status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags); + status = nfs4_check_cl_exchange_flags(res.flags); if (status == 0) { + clp->cl_clientid = res.clientid; + clp->cl_exchange_flags = (res.flags & ~EXCHGID4_FLAG_CONFIRMED_R); + if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R)) + clp->cl_seqid = res.seqid; + kfree(clp->cl_serverowner); clp->cl_serverowner = res.server_owner; res.server_owner = NULL; - } - if (status == 0) { /* use the most recent implementation id */ kfree(clp->cl_implid); clp->cl_implid = res.impl_id; - } else - kfree(res.impl_id); - if (status == 0) { if (clp->cl_serverscope != NULL && !nfs41_same_server_scope(clp->cl_serverscope, res.server_scope)) { @@ -5244,7 +5244,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) clp->cl_serverscope = res.server_scope; goto out; } - } + } else + kfree(res.impl_id); out_server_owner: kfree(res.server_owner); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index b9ce3fdb862a..ee4a74db95d0 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5319,7 +5319,6 @@ static int decode_exchange_id(struct xdr_stream *xdr, uint32_t dummy; char *dummy_str; int status; - struct nfs_client *clp = res->client; uint32_t impl_id_count; status = decode_op_hdr(xdr, OP_EXCHANGE_ID); @@ -5329,12 +5328,12 @@ static int decode_exchange_id(struct xdr_stream *xdr, p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - xdr_decode_hyper(p, &clp->cl_clientid); + xdr_decode_hyper(p, &res->clientid); p = xdr_inline_decode(xdr, 12); if (unlikely(!p)) goto out_overflow; - clp->cl_seqid = be32_to_cpup(p++); - clp->cl_exchange_flags = be32_to_cpup(p++); + res->seqid = be32_to_cpup(p++); + res->flags = be32_to_cpup(p++); /* We ask for SP4_NONE */ dummy = be32_to_cpup(p); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6387fc0097fe..d1a7bf51c326 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1132,7 +1132,8 @@ struct nfs41_bind_conn_to_session_res { }; struct nfs41_exchange_id_res { - struct nfs_client *client; + u64 clientid; + u32 seqid; u32 flags; struct nfs41_server_owner *server_owner; struct nfs41_server_scope *server_scope; -- cgit v1.2.3 From af2e840971dee21ba9b87e9ecee7d5cc6109baaa Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Tue, 29 May 2012 15:06:14 -0700 Subject: pagemap.h: fix warning about possibly used before init var Commit f56f821feb7b ("mm: extend prefault helpers to fault in more than PAGE_SIZE") added in the new functions: fault_in_multipages_writeable() and fault_in_multipages_readable(). However, we currently see: include/linux/pagemap.h:492: warning: 'ret' may be used uninitialized in this function include/linux/pagemap.h:492: note: 'ret' was declared here Unlike a lot of gcc nags, this one appears somewhat legit. i.e. passing in an invalid negative value of "size" does make it look like all the conditionals in there would be bypassed and the uninitialized value would be returned. Signed-off-by: Paul Gortmaker Cc: Daniel Vetter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index efa26b4da8d2..7cfad3bbb0cc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -460,11 +460,11 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size) */ static inline int fault_in_multipages_writeable(char __user *uaddr, int size) { - int ret; + int ret = 0; char __user *end = uaddr + size - 1; if (unlikely(size == 0)) - return 0; + return ret; /* * Writing zeroes into userspace here is OK, because we know that if @@ -489,11 +489,11 @@ static inline int fault_in_multipages_readable(const char __user *uaddr, int size) { volatile char c; - int ret; + int ret = 0; const char __user *end = uaddr + size - 1; if (unlikely(size == 0)) - return 0; + return ret; while (uaddr <= end) { ret = __get_user(c, uaddr); -- cgit v1.2.3 From e709ffd6169ccd259eb5874e853303e91e94e829 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Tue, 29 May 2012 15:06:18 -0700 Subject: mm: remove swap token code The swap token code no longer fits in with the current VM model. It does not play well with cgroups or the better NUMA placement code in development, since we have only one swap token globally. It also has the potential to mess with scalability of the system, by increasing the number of non-reclaimable pages on the active and inactive anon LRU lists. Last but not least, the swap token code has been broken for a year without complaints, as reported by Konstantin Khlebnikov. This suggests we no longer have much use for it. The days of sub-1G memory systems with heavy use of swap are over. If we ever need thrashing reducing code in the future, we will have to implement something that does scale. Signed-off-by: Rik van Riel Cc: Konstantin Khlebnikov Acked-by: Johannes Weiner Cc: Mel Gorman Cc: Hugh Dickins Acked-by: Bob Picco Acked-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 11 --- include/linux/swap.h | 35 ---------- include/trace/events/vmscan.h | 82 ---------------------- kernel/fork.c | 9 --- mm/Makefile | 2 +- mm/memcontrol.c | 1 - mm/memory.c | 2 +- mm/rmap.c | 6 -- mm/thrash.c | 155 ------------------------------------------ mm/vmscan.c | 6 -- 10 files changed, 2 insertions(+), 307 deletions(-) delete mode 100644 mm/thrash.c (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 26574c726121..dad95bdd06d7 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -345,17 +345,6 @@ struct mm_struct { /* Architecture-specific MM context */ mm_context_t context; - /* Swap token stuff */ - /* - * Last value of global fault stamp as seen by this process. - * In other words, this value gives an indication of how long - * it has been since this task got the token. - * Look at mm/thrash.c - */ - unsigned int faultstamp; - unsigned int token_priority; - unsigned int last_interval; - unsigned long flags; /* Must use atomic bitops to access the bits */ struct core_state *core_state; /* coredumping support */ diff --git a/include/linux/swap.h b/include/linux/swap.h index b1fd5c7925fe..bc3073ce95cc 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -355,23 +355,6 @@ extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; -/* linux/mm/thrash.c */ -extern struct mm_struct *swap_token_mm; -extern void grab_swap_token(struct mm_struct *); -extern void __put_swap_token(struct mm_struct *); -extern void disable_swap_token(struct mem_cgroup *memcg); - -static inline int has_swap_token(struct mm_struct *mm) -{ - return (mm == swap_token_mm); -} - -static inline void put_swap_token(struct mm_struct *mm) -{ - if (has_swap_token(mm)) - __put_swap_token(mm); -} - #ifdef CONFIG_CGROUP_MEM_RES_CTLR extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); @@ -476,24 +459,6 @@ static inline swp_entry_t get_swap_page(void) return entry; } -/* linux/mm/thrash.c */ -static inline void put_swap_token(struct mm_struct *mm) -{ -} - -static inline void grab_swap_token(struct mm_struct *mm) -{ -} - -static inline int has_swap_token(struct mm_struct *mm) -{ - return 0; -} - -static inline void disable_swap_token(struct mem_cgroup *memcg) -{ -} - static inline void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) { diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index f64560e204bc..572195459d58 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -395,88 +395,6 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive, show_reclaim_flags(__entry->reclaim_flags)) ); -TRACE_EVENT(replace_swap_token, - TP_PROTO(struct mm_struct *old_mm, - struct mm_struct *new_mm), - - TP_ARGS(old_mm, new_mm), - - TP_STRUCT__entry( - __field(struct mm_struct*, old_mm) - __field(unsigned int, old_prio) - __field(struct mm_struct*, new_mm) - __field(unsigned int, new_prio) - ), - - TP_fast_assign( - __entry->old_mm = old_mm; - __entry->old_prio = old_mm ? old_mm->token_priority : 0; - __entry->new_mm = new_mm; - __entry->new_prio = new_mm->token_priority; - ), - - TP_printk("old_token_mm=%p old_prio=%u new_token_mm=%p new_prio=%u", - __entry->old_mm, __entry->old_prio, - __entry->new_mm, __entry->new_prio) -); - -DECLARE_EVENT_CLASS(put_swap_token_template, - TP_PROTO(struct mm_struct *swap_token_mm), - - TP_ARGS(swap_token_mm), - - TP_STRUCT__entry( - __field(struct mm_struct*, swap_token_mm) - ), - - TP_fast_assign( - __entry->swap_token_mm = swap_token_mm; - ), - - TP_printk("token_mm=%p", __entry->swap_token_mm) -); - -DEFINE_EVENT(put_swap_token_template, put_swap_token, - TP_PROTO(struct mm_struct *swap_token_mm), - TP_ARGS(swap_token_mm) -); - -DEFINE_EVENT_CONDITION(put_swap_token_template, disable_swap_token, - TP_PROTO(struct mm_struct *swap_token_mm), - TP_ARGS(swap_token_mm), - TP_CONDITION(swap_token_mm != NULL) -); - -TRACE_EVENT_CONDITION(update_swap_token_priority, - TP_PROTO(struct mm_struct *mm, - unsigned int old_prio, - struct mm_struct *swap_token_mm), - - TP_ARGS(mm, old_prio, swap_token_mm), - - TP_CONDITION(mm->token_priority != old_prio), - - TP_STRUCT__entry( - __field(struct mm_struct*, mm) - __field(unsigned int, old_prio) - __field(unsigned int, new_prio) - __field(struct mm_struct*, swap_token_mm) - __field(unsigned int, swap_token_prio) - ), - - TP_fast_assign( - __entry->mm = mm; - __entry->old_prio = old_prio; - __entry->new_prio = mm->token_priority; - __entry->swap_token_mm = swap_token_mm; - __entry->swap_token_prio = swap_token_mm ? swap_token_mm->token_priority : 0; - ), - - TP_printk("mm=%p old_prio=%u new_prio=%u swap_token_mm=%p token_prio=%u", - __entry->mm, __entry->old_prio, __entry->new_prio, - __entry->swap_token_mm, __entry->swap_token_prio) -); - #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ diff --git a/kernel/fork.c b/kernel/fork.c index 47b4e4f379f9..5b13eea2e757 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -614,7 +614,6 @@ void mmput(struct mm_struct *mm) list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } - put_swap_token(mm); if (mm->binfmt) module_put(mm->binfmt->module); mmdrop(mm); @@ -831,10 +830,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk) memcpy(mm, oldmm, sizeof(*mm)); mm_init_cpumask(mm); - /* Initializing for Swap token stuff */ - mm->token_priority = 0; - mm->last_interval = 0; - #ifdef CONFIG_TRANSPARENT_HUGEPAGE mm->pmd_huge_pte = NULL; #endif @@ -913,10 +908,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) goto fail_nomem; good_mm: - /* Initializing for Swap token stuff */ - mm->token_priority = 0; - mm->last_interval = 0; - tsk->mm = mm; tsk->active_mm = mm; return 0; diff --git a/mm/Makefile b/mm/Makefile index 8aada89efbbb..ccecbf9818f5 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -25,7 +25,7 @@ endif obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o obj-$(CONFIG_BOUNCE) += bounce.o -obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o +obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o obj-$(CONFIG_HAS_DMA) += dmapool.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o obj-$(CONFIG_NUMA) += mempolicy.o diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f342778a0c0a..92675fe8a2ef 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5598,7 +5598,6 @@ static void mem_cgroup_move_task(struct cgroup *cont, if (mm) { if (mc.to) mem_cgroup_move_charge(mm); - put_swap_token(mm); mmput(mm); } if (mc.to) diff --git a/mm/memory.c b/mm/memory.c index e40f6759ba98..2bf9e110437c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2908,7 +2908,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry); if (!page) { - grab_swap_token(mm); /* Contend for token _before_ read-in */ page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vma, address); if (!page) { @@ -2938,6 +2937,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, } locked = lock_page_or_retry(page, mm, flags); + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; diff --git a/mm/rmap.c b/mm/rmap.c index 5b5ad584ffb7..0f3b7cda2a24 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -755,12 +755,6 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); } - /* Pretend the page is referenced if the task has the - swap token and is in the middle of a page fault. */ - if (mm != current->mm && has_swap_token(mm) && - rwsem_is_locked(&mm->mmap_sem)) - referenced++; - (*mapcount)--; if (referenced) diff --git a/mm/thrash.c b/mm/thrash.c deleted file mode 100644 index 57ad495dbd54..000000000000 --- a/mm/thrash.c +++ /dev/null @@ -1,155 +0,0 @@ -/* - * mm/thrash.c - * - * Copyright (C) 2004, Red Hat, Inc. - * Copyright (C) 2004, Rik van Riel - * Released under the GPL, see the file COPYING for details. - * - * Simple token based thrashing protection, using the algorithm - * described in: http://www.cse.ohio-state.edu/hpcs/WWW/HTML/publications/abs05-1.html - * - * Sep 2006, Ashwin Chaugule - * Improved algorithm to pass token: - * Each task has a priority which is incremented if it contended - * for the token in an interval less than its previous attempt. - * If the token is acquired, that task's priority is boosted to prevent - * the token from bouncing around too often and to let the task make - * some progress in its execution. - */ - -#include -#include -#include -#include -#include - -#include - -#define TOKEN_AGING_INTERVAL (0xFF) - -static DEFINE_SPINLOCK(swap_token_lock); -struct mm_struct *swap_token_mm; -static struct mem_cgroup *swap_token_memcg; - -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) -{ - struct mem_cgroup *memcg; - - memcg = try_get_mem_cgroup_from_mm(mm); - if (memcg) - css_put(mem_cgroup_css(memcg)); - - return memcg; -} -#else -static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) -{ - return NULL; -} -#endif - -void grab_swap_token(struct mm_struct *mm) -{ - int current_interval; - unsigned int old_prio = mm->token_priority; - static unsigned int global_faults; - static unsigned int last_aging; - - global_faults++; - - current_interval = global_faults - mm->faultstamp; - - if (!spin_trylock(&swap_token_lock)) - return; - - /* First come first served */ - if (!swap_token_mm) - goto replace_token; - - /* - * Usually, we don't need priority aging because long interval faults - * makes priority decrease quickly. But there is one exception. If the - * token owner task is sleeping, it never make long interval faults. - * Thus, we need a priority aging mechanism instead. The requirements - * of priority aging are - * 1) An aging interval is reasonable enough long. Too short aging - * interval makes quick swap token lost and decrease performance. - * 2) The swap token owner task have to get priority aging even if - * it's under sleep. - */ - if ((global_faults - last_aging) > TOKEN_AGING_INTERVAL) { - swap_token_mm->token_priority /= 2; - last_aging = global_faults; - } - - if (mm == swap_token_mm) { - mm->token_priority += 2; - goto update_priority; - } - - if (current_interval < mm->last_interval) - mm->token_priority++; - else { - if (likely(mm->token_priority > 0)) - mm->token_priority--; - } - - /* Check if we deserve the token */ - if (mm->token_priority > swap_token_mm->token_priority) - goto replace_token; - -update_priority: - trace_update_swap_token_priority(mm, old_prio, swap_token_mm); - -out: - mm->faultstamp = global_faults; - mm->last_interval = current_interval; - spin_unlock(&swap_token_lock); - return; - -replace_token: - mm->token_priority += 2; - trace_replace_swap_token(swap_token_mm, mm); - swap_token_mm = mm; - swap_token_memcg = swap_token_memcg_from_mm(mm); - last_aging = global_faults; - goto out; -} - -/* Called on process exit. */ -void __put_swap_token(struct mm_struct *mm) -{ - spin_lock(&swap_token_lock); - if (likely(mm == swap_token_mm)) { - trace_put_swap_token(swap_token_mm); - swap_token_mm = NULL; - swap_token_memcg = NULL; - } - spin_unlock(&swap_token_lock); -} - -static bool match_memcg(struct mem_cgroup *a, struct mem_cgroup *b) -{ - if (!a) - return true; - if (!b) - return true; - if (a == b) - return true; - return false; -} - -void disable_swap_token(struct mem_cgroup *memcg) -{ - /* memcg reclaim don't disable unrelated mm token. */ - if (match_memcg(memcg, swap_token_memcg)) { - spin_lock(&swap_token_lock); - if (match_memcg(memcg, swap_token_memcg)) { - trace_disable_swap_token(swap_token_mm); - swap_token_mm = NULL; - swap_token_memcg = NULL; - } - spin_unlock(&swap_token_lock); - } -} diff --git a/mm/vmscan.c b/mm/vmscan.c index 33dc256033b5..ca46080bb074 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2352,8 +2352,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, for (priority = DEF_PRIORITY; priority >= 0; priority--) { sc->nr_scanned = 0; - if (!priority) - disable_swap_token(sc->target_mem_cgroup); aborted_reclaim = shrink_zones(priority, zonelist, sc); /* @@ -2704,10 +2702,6 @@ loop_again: unsigned long lru_pages = 0; int has_under_min_watermark_zone = 0; - /* The swap token gets in the way of swapout... */ - if (!priority) - disable_swap_token(NULL); - all_zones_ok = 1; balanced = 0; -- cgit v1.2.3 From 0ce72d4f7333248efbef1f3309770c7edb1b2625 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 29 May 2012 15:06:24 -0700 Subject: mm: do_migrate_pages(): rename arguments s/from_nodes/from and s/to_nodes/to/. The "_nodes" is redundant - it duplicates the argument's type. Done in a fit of irritation over 80-col issues :( Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Larry Woodman Cc: Mel Gorman Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 9 ++++----- mm/mempolicy.c | 18 +++++++++--------- 2 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 7c727a90d70d..4aa42732e47f 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -225,8 +225,8 @@ static inline void check_highest_zone(enum zone_type k) policy_zone = k; } -int do_migrate_pages(struct mm_struct *mm, - const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags); +int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS @@ -354,9 +354,8 @@ static inline bool mempolicy_nodemask_intersects(struct task_struct *tsk, return false; } -static inline int do_migrate_pages(struct mm_struct *mm, - const nodemask_t *from_nodes, - const nodemask_t *to_nodes, int flags) +static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to, int flags) { return 0; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d3c5de47ff6d..f15c1b24ca18 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -950,8 +950,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, * * Returns the number of page that could not be moved. */ -int do_migrate_pages(struct mm_struct *mm, - const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags) +int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to, int flags) { int busy = 0; int err; @@ -963,7 +963,7 @@ int do_migrate_pages(struct mm_struct *mm, down_read(&mm->mmap_sem); - err = migrate_vmas(mm, from_nodes, to_nodes, flags); + err = migrate_vmas(mm, from, to, flags); if (err) goto out; @@ -998,7 +998,7 @@ int do_migrate_pages(struct mm_struct *mm, * moved to an empty node, then there is nothing left worth migrating. */ - tmp = *from_nodes; + tmp = *from; while (!nodes_empty(tmp)) { int s,d; int source = -1; @@ -1021,11 +1021,11 @@ int do_migrate_pages(struct mm_struct *mm, * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ - if ((nodes_weight(*from_nodes) != nodes_weight(*to_nodes)) && - (node_isset(s, *to_nodes))) + if ((nodes_weight(*from) != nodes_weight(*to)) && + (node_isset(s, *to))) continue; - d = node_remap(s, *from_nodes, *to_nodes); + d = node_remap(s, *from, *to); if (s == d) continue; @@ -1085,8 +1085,8 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, { } -int do_migrate_pages(struct mm_struct *mm, - const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags) +int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to, int flags) { return -ENOSYS; } -- cgit v1.2.3 From c3ac9a8ade65ccbfd145fbff895ae8d8d62d09b0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 29 May 2012 15:06:25 -0700 Subject: mm: memcg: count pte references from every member of the reclaimed hierarchy The rmap walker checking page table references has historically ignored references from VMAs that were not part of the memcg that was being reclaimed during memcg hard limit reclaim. When transitioning global reclaim to memcg hierarchy reclaim, I missed that bit and now references from outside a memcg are ignored even during global reclaim. Reverting back to traditional behaviour - count all references during global reclaim and only mind references of the memcg being reclaimed during limit reclaim would be one option. However, the more generic idea is to ignore references exactly then when they are outside the hierarchy that is currently under reclaim; because only then will their reclamation be of any use to help the pressure situation. It makes no sense to ignore references from a sibling memcg and then evict a page that will be immediately refaulted by that sibling which contributes to the same usage of the common ancestor under reclaim. The solution: make the rmap walker ignore references from VMAs that are not part of the hierarchy that is being reclaimed. Flat limit reclaim will stay the same, hierarchical limit reclaim will mind the references only to pages that the hierarchy owns. Global reclaim, since it reclaims from all memcgs, will be fixed to regard all references. [akpm@linux-foundation.org: name the args in the declaration] Signed-off-by: Johannes Weiner Reported-by: Konstantin Khlebnikov Acked-by: Konstantin Khlebnikov Cc: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: Li Zefan Cc: Li Zefan Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 ++++++- mm/memcontrol.c | 16 +++++++++++----- mm/vmscan.c | 6 ++++-- 3 files changed, 21 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f94efd2f6c27..18ea0b7baf32 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -79,6 +79,8 @@ extern void mem_cgroup_uncharge_cache_page(struct page *page); extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order); +bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, + struct mem_cgroup *memcg); int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg); extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); @@ -92,10 +94,13 @@ static inline int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) { struct mem_cgroup *memcg; + int match; + rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference((mm)->owner)); + match = __mem_cgroup_same_or_subtree(cgroup, memcg); rcu_read_unlock(); - return cgroup == memcg; + return match; } extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index faad98e6d17d..4f71219cc53e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1149,17 +1149,23 @@ struct lruvec *mem_cgroup_lru_move_lists(struct zone *zone, * Checks whether given mem is same or in the root_mem_cgroup's * hierarchy subtree */ -static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, - struct mem_cgroup *memcg) +bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, + struct mem_cgroup *memcg) { - bool ret; - if (root_memcg == memcg) return true; if (!root_memcg->use_hierarchy) return false; + return css_is_ancestor(&memcg->css, &root_memcg->css); +} + +static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, + struct mem_cgroup *memcg) +{ + bool ret; + rcu_read_lock(); - ret = css_is_ancestor(&memcg->css, &root_memcg->css); + ret = __mem_cgroup_same_or_subtree(root_memcg, memcg); rcu_read_unlock(); return ret; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 68e5819d0f1b..8fffc65a84de 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -645,7 +645,8 @@ static enum page_references page_check_references(struct page *page, int referenced_ptes, referenced_page; unsigned long vm_flags; - referenced_ptes = page_referenced(page, 1, mz->mem_cgroup, &vm_flags); + referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup, + &vm_flags); referenced_page = TestClearPageReferenced(page); /* @@ -1513,7 +1514,8 @@ static void shrink_active_list(unsigned long nr_to_scan, } } - if (page_referenced(page, 0, mz->mem_cgroup, &vm_flags)) { + if (page_referenced(page, 0, sc->target_mem_cgroup, + &vm_flags)) { nr_rotated += hpage_nr_pages(page); /* * Identify referenced, file-backed active pages and -- cgit v1.2.3 From baf05aa9271bdbc07d3160035a231abc5fbd429a Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Tue, 29 May 2012 15:06:27 -0700 Subject: bug: introduce BUILD_BUG_ON_INVALID() macro Sometimes we want to check some expressions correctness at compile time. "(void)(e);" or "if (e);" can be dangerous if the expression has side-effects, and gcc sometimes generates a lot of code, even if the expression has no effect. This patch introduces macro BUILD_BUG_ON_INVALID() for such checks, it forces a compilation error if expression is invalid without any extra code. [Cast to "long" required because sizeof does not work for bit-fields.] Signed-off-by: Konstantin Khlebnikov Cc: Linus Torvalds Cc: Geert Uytterhoeven Cc: "H. Peter Anvin" Cc: Cong Wang Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bug.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bug.h b/include/linux/bug.h index 72961c39576a..aaac4bba6f5c 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -30,6 +30,13 @@ struct pt_regs; #define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) #define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); })) +/* + * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the + * expression but avoids the generation of any code, even if that expression + * has side-effects. + */ +#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) + /** * BUILD_BUG_ON - break compile if a condition is true. * @condition: the condition which the compiler should know is false. -- cgit v1.2.3 From 02602a18c32d76f0e0f50eefa91b2d53c8a3a751 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Tue, 29 May 2012 15:06:28 -0700 Subject: bug: completely remove code generated by disabled VM_BUG_ON() Even if CONFIG_DEBUG_VM=n gcc genereates code for some VM_BUG_ON() for example VM_BUG_ON(!PageCompound(page) || !PageHead(page)); in do_huge_pmd_wp_page() generates 114 bytes of code. But they mostly disappears when I split this VM_BUG_ON into two: -VM_BUG_ON(!PageCompound(page) || !PageHead(page)); +VM_BUG_ON(!PageCompound(page)); +VM_BUG_ON(!PageHead(page)); weird... but anyway after this patch code disappears completely. add/remove: 0/0 grow/shrink: 7/97 up/down: 135/-1784 (-1649) Signed-off-by: Konstantin Khlebnikov Cc: Linus Torvalds Cc: Geert Uytterhoeven Cc: "H. Peter Anvin" Cc: Cong Wang Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmdebug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index c04ecfe03f7f..580bd587d916 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -4,7 +4,7 @@ #ifdef CONFIG_DEBUG_VM #define VM_BUG_ON(cond) BUG_ON(cond) #else -#define VM_BUG_ON(cond) do { (void)(cond); } while (0) +#define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond) #endif #ifdef CONFIG_DEBUG_VIRTUAL -- cgit v1.2.3 From 9295b7a07c859a42346221b5839be0ae612333b0 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Tue, 29 May 2012 15:06:30 -0700 Subject: kbuild: install kernel-page-flags.h Programs using /proc/kpageflags need to know about the various flags. The provides them and the comments in the file indicate that it is supposed to be used by user-level code. But the file is not installed. Install the headers and mark the unstable flags as out-of-bounds. The page-type tool is also adjusted to not duplicate the definitions Signed-off-by: Ulrich Drepper Acked-by: KOSAKI Motohiro Acked-by: Fengguang Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 1 + include/linux/kernel-page-flags.h | 4 ++++ tools/vm/page-types.c | 28 +--------------------------- 3 files changed, 6 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 4cd59b95858f..7185b8f15ced 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -225,6 +225,7 @@ header-y += kd.h header-y += kdev_t.h header-y += kernel.h header-y += kernelcapi.h +header-y += kernel-page-flags.h header-y += keyboard.h header-y += keyctl.h header-y += l2tp.h diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h index 26a65711676f..a1bdf6966357 100644 --- a/include/linux/kernel-page-flags.h +++ b/include/linux/kernel-page-flags.h @@ -32,6 +32,8 @@ #define KPF_KSM 21 #define KPF_THP 22 +#ifdef __KERNEL__ + /* kernel hacking assistances * WARNING: subject to change, never rely on them! */ @@ -44,4 +46,6 @@ #define KPF_ARCH 38 #define KPF_UNCACHED 39 +#endif /* __KERNEL__ */ + #endif /* LINUX_KERNEL_PAGE_FLAGS_H */ diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 7dab7b25b5c6..f77c96bec7eb 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -35,6 +35,7 @@ #include #include #include "../../include/linux/magic.h" +#include "../../include/linux/kernel-page-flags.h" #ifndef MAX_PATH @@ -73,33 +74,6 @@ #define KPF_BYTES 8 #define PROC_KPAGEFLAGS "/proc/kpageflags" -/* copied from kpageflags_read() */ -#define KPF_LOCKED 0 -#define KPF_ERROR 1 -#define KPF_REFERENCED 2 -#define KPF_UPTODATE 3 -#define KPF_DIRTY 4 -#define KPF_LRU 5 -#define KPF_ACTIVE 6 -#define KPF_SLAB 7 -#define KPF_WRITEBACK 8 -#define KPF_RECLAIM 9 -#define KPF_BUDDY 10 - -/* [11-20] new additions in 2.6.31 */ -#define KPF_MMAP 11 -#define KPF_ANON 12 -#define KPF_SWAPCACHE 13 -#define KPF_SWAPBACKED 14 -#define KPF_COMPOUND_HEAD 15 -#define KPF_COMPOUND_TAIL 16 -#define KPF_HUGE 17 -#define KPF_UNEVICTABLE 18 -#define KPF_HWPOISON 19 -#define KPF_NOPAGE 20 -#define KPF_KSM 21 -#define KPF_THP 22 - /* [32-] kernel hacking assistances */ #define KPF_RESERVED 32 #define KPF_MLOCKED 33 -- cgit v1.2.3 From 2099597401c7710c00b0d7c32b24a44a193836e1 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Tue, 29 May 2012 15:06:31 -0700 Subject: mm: move is_vma_temporary_stack() declaration to huge_mm.h When transparent_hugepage_enabled() is used outside mm/, such as in arch/x86/xx/tlb.c: + if (!cpu_has_invlpg || vma->vm_flags & VM_HUGETLB + || transparent_hugepage_enabled(vma)) { + flush_tlb_mm(vma->vm_mm); is_vma_temporary_stack() isn't referenced in huge_mm.h, so it has compile errors: arch/x86/mm/tlb.c: In function `flush_tlb_range': arch/x86/mm/tlb.c:324:4: error: implicit declaration of function `is_vma_temporary_stack' [-Werror=implicit-function-declaration] Since is_vma_temporay_stack() is just used in rmap.c and huge_memory.c, it is better to move it to huge_mm.h from rmap.h to avoid such errors. Signed-off-by: Alex Shi Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 ++ include/linux/rmap.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index c8af7a2efb52..4c59b1131187 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -59,6 +59,8 @@ extern pmd_t *page_check_address_pmd(struct page *page, #define HPAGE_PMD_MASK HPAGE_MASK #define HPAGE_PMD_SIZE HPAGE_SIZE +extern bool is_vma_temporary_stack(struct vm_area_struct *vma); + #define transparent_hugepage_enabled(__vma) \ ((transparent_hugepage_flags & \ (1< Date: Tue, 29 May 2012 15:06:36 -0700 Subject: mm: remove sparsemem allocation details from the bootmem allocator alloc_bootmem_section() derives allocation area constraints from the specified sparsemem section. This is a bit specific for a generic memory allocator like bootmem, though, so move it over to sparsemem. As __alloc_bootmem_node_nopanic() already retries failed allocations with relaxed area constraints, the fallback code in sparsemem.c can be removed and the code becomes a bit more compact overall. [akpm@linux-foundation.org: fix build] Signed-off-by: Johannes Weiner Acked-by: Tejun Heo Acked-by: David S. Miller Cc: Yinghai Lu Cc: Gavin Shan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 3 --- mm/bootmem.c | 22 ---------------------- mm/nobootmem.c | 22 ---------------------- mm/sparse.c | 25 ++++++++++++------------- 4 files changed, 12 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 1a0cd270bb7a..324fe08ea3b1 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -135,9 +135,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, extern int reserve_bootmem_generic(unsigned long addr, unsigned long size, int flags); -extern void *alloc_bootmem_section(unsigned long size, - unsigned long section_nr); - #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP extern void *alloc_remap(int nid, unsigned long size); #else diff --git a/mm/bootmem.c b/mm/bootmem.c index 9d0f26664b3b..d1c7a79d6f3a 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -803,28 +803,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, } -#ifdef CONFIG_SPARSEMEM -/** - * alloc_bootmem_section - allocate boot memory from a specific section - * @size: size of the request in bytes - * @section_nr: sparse map section to allocate from - * - * Return NULL on failure. - */ -void * __init alloc_bootmem_section(unsigned long size, - unsigned long section_nr) -{ - bootmem_data_t *bdata; - unsigned long pfn, goal; - - pfn = section_nr_to_pfn(section_nr); - goal = pfn << PAGE_SHIFT; - bdata = &bootmem_node_data[early_pfn_to_nid(pfn)]; - - return alloc_bootmem_bdata(bdata, size, SMP_CACHE_BYTES, goal, 0); -} -#endif - #ifndef ARCH_LOW_ADDRESS_LIMIT #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL #endif diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 9f4048149f64..d23415c001bc 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -355,28 +355,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, return __alloc_bootmem_node(pgdat, size, align, goal); } -#ifdef CONFIG_SPARSEMEM -/** - * alloc_bootmem_section - allocate boot memory from a specific section - * @size: size of the request in bytes - * @section_nr: sparse map section to allocate from - * - * Return NULL on failure. - */ -void * __init alloc_bootmem_section(unsigned long size, - unsigned long section_nr) -{ - unsigned long pfn, goal, limit; - - pfn = section_nr_to_pfn(section_nr); - goal = pfn << PAGE_SHIFT; - limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT; - - return __alloc_memory_core_early(early_pfn_to_nid(pfn), size, - SMP_CACHE_BYTES, goal, limit); -} -#endif - #ifndef ARCH_LOW_ADDRESS_LIMIT #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL #endif diff --git a/mm/sparse.c b/mm/sparse.c index a8bc7d364deb..6a4bf9160e85 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -273,10 +273,10 @@ static unsigned long *__kmalloc_section_usemap(void) #ifdef CONFIG_MEMORY_HOTREMOVE static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, - unsigned long count) + unsigned long size) { - unsigned long section_nr; - + pg_data_t *host_pgdat; + unsigned long goal; /* * A page may contain usemaps for other sections preventing the * page being freed and making a section unremovable while @@ -287,8 +287,10 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, * from the same section as the pgdat where possible to avoid * this problem. */ - section_nr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT); - return alloc_bootmem_section(usemap_size() * count, section_nr); + goal = __pa(pgdat) & PAGE_SECTION_MASK; + host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT)); + return __alloc_bootmem_node_nopanic(host_pgdat, size, + SMP_CACHE_BYTES, goal); } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) @@ -332,9 +334,9 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap) #else static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, - unsigned long count) + unsigned long size) { - return NULL; + return alloc_bootmem_node_nopanic(pgdat, size); } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) @@ -352,13 +354,10 @@ static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map, int size = usemap_size(); usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid), - usemap_count); + size * usemap_count); if (!usemap) { - usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count); - if (!usemap) { - printk(KERN_WARNING "%s: allocation failed\n", __func__); - return; - } + printk(KERN_WARNING "%s: allocation failed\n", __func__); + return; } for (pnum = pnum_begin; pnum < pnum_end; pnum++) { -- cgit v1.2.3 From 5ceb9ce6fe9462a298bb2cd5c9f1ca6cb80a0199 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 29 May 2012 15:06:37 -0700 Subject: mm: compaction: handle incorrect MIGRATE_UNMOVABLE type pageblocks When MIGRATE_UNMOVABLE pages are freed from MIGRATE_UNMOVABLE type pageblock (and some MIGRATE_MOVABLE pages are left in it) waiting until an allocation takes ownership of the block may take too long. The type of the pageblock remains unchanged so the pageblock cannot be used as a migration target during compaction. Fix it by: * Adding enum compact_mode (COMPACT_ASYNC_[MOVABLE,UNMOVABLE], and COMPACT_SYNC) and then converting sync field in struct compact_control to use it. * Adding nr_pageblocks_skipped field to struct compact_control and tracking how many destination pageblocks were of MIGRATE_UNMOVABLE type. If COMPACT_ASYNC_MOVABLE mode compaction ran fully in try_to_compact_pages() (COMPACT_COMPLETE) it implies that there is not a suitable page for allocation. In this case then check how if there were enough MIGRATE_UNMOVABLE pageblocks to try a second pass in COMPACT_ASYNC_UNMOVABLE mode. * Scanning the MIGRATE_UNMOVABLE pageblocks (during COMPACT_SYNC and COMPACT_ASYNC_UNMOVABLE compaction modes) and building a count based on finding PageBuddy pages, page_count(page) == 0 or PageLRU pages. If all pages within the MIGRATE_UNMOVABLE pageblock are in one of those three sets change the whole pageblock type to MIGRATE_MOVABLE. My particular test case (on a ARM EXYNOS4 device with 512 MiB, which means 131072 standard 4KiB pages in 'Normal' zone) is to: - allocate 120000 pages for kernel's usage - free every second page (60000 pages) of memory just allocated - allocate and use 60000 pages from user space - free remaining 60000 pages of kernel memory (now we have fragmented memory occupied mostly by user space pages) - try to allocate 100 order-9 (2048 KiB) pages for kernel's usage The results: - with compaction disabled I get 11 successful allocations - with compaction enabled - 14 successful allocations - with this patch I'm able to get all 100 successful allocations NOTE: If we can make kswapd aware of order-0 request during compaction, we can enhance kswapd with changing mode to COMPACT_ASYNC_FULL (COMPACT_ASYNC_MOVABLE + COMPACT_ASYNC_UNMOVABLE). Please see the following thread: http://marc.info/?l=linux-mm&m=133552069417068&w=2 [minchan@kernel.org: minor cleanups] Cc: Mel Gorman Cc: Minchan Kim Cc: Rik van Riel Cc: Marek Szyprowski Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 19 ++++++ mm/compaction.c | 142 +++++++++++++++++++++++++++++++++++++-------- mm/internal.h | 9 ++- mm/page_alloc.c | 8 +-- 4 files changed, 150 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 51a90b7f2d60..e988037abd2a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -1,6 +1,8 @@ #ifndef _LINUX_COMPACTION_H #define _LINUX_COMPACTION_H +#include + /* Return values for compact_zone() and try_to_compact_pages() */ /* compaction didn't start as it was not possible or direct reclaim was more suitable */ #define COMPACT_SKIPPED 0 @@ -11,6 +13,23 @@ /* The full zone was compacted */ #define COMPACT_COMPLETE 3 +/* + * compaction supports three modes + * + * COMPACT_ASYNC_MOVABLE uses asynchronous migration and only scans + * MIGRATE_MOVABLE pageblocks as migration sources and targets. + * COMPACT_ASYNC_UNMOVABLE uses asynchronous migration and only scans + * MIGRATE_MOVABLE pageblocks as migration sources. + * MIGRATE_UNMOVABLE pageblocks are scanned as potential migration + * targets and convers them to MIGRATE_MOVABLE if possible + * COMPACT_SYNC uses synchronous migration and scans all pageblocks + */ +enum compact_mode { + COMPACT_ASYNC_MOVABLE, + COMPACT_ASYNC_UNMOVABLE, + COMPACT_SYNC, +}; + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, diff --git a/mm/compaction.c b/mm/compaction.c index da7d35ea5103..840ee288e296 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -235,7 +235,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ - if (!cc->sync) + if (cc->mode != COMPACT_SYNC) return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -303,7 +303,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, * satisfies the allocation */ pageblock_nr = low_pfn >> pageblock_order; - if (!cc->sync && last_pageblock_nr != pageblock_nr && + if (cc->mode != COMPACT_SYNC && + last_pageblock_nr != pageblock_nr && !migrate_async_suitable(get_pageblock_migratetype(page))) { low_pfn += pageblock_nr_pages; low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1; @@ -324,7 +325,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, continue; } - if (!cc->sync) + if (cc->mode != COMPACT_SYNC) mode |= ISOLATE_ASYNC_MIGRATE; /* Try isolate the page */ @@ -357,27 +358,90 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, #endif /* CONFIG_COMPACTION || CONFIG_CMA */ #ifdef CONFIG_COMPACTION +/* + * Returns true if MIGRATE_UNMOVABLE pageblock was successfully + * converted to MIGRATE_MOVABLE type, false otherwise. + */ +static bool rescue_unmovable_pageblock(struct page *page) +{ + unsigned long pfn, start_pfn, end_pfn; + struct page *start_page, *end_page; + + pfn = page_to_pfn(page); + start_pfn = pfn & ~(pageblock_nr_pages - 1); + end_pfn = start_pfn + pageblock_nr_pages; + + start_page = pfn_to_page(start_pfn); + end_page = pfn_to_page(end_pfn); + + /* Do not deal with pageblocks that overlap zones */ + if (page_zone(start_page) != page_zone(end_page)) + return false; + + for (page = start_page, pfn = start_pfn; page < end_page; pfn++, + page++) { + if (!pfn_valid_within(pfn)) + continue; + + if (PageBuddy(page)) { + int order = page_order(page); + + pfn += (1 << order) - 1; + page += (1 << order) - 1; + + continue; + } else if (page_count(page) == 0 || PageLRU(page)) + continue; + + return false; + } + + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + move_freepages_block(page_zone(page), page, MIGRATE_MOVABLE); + return true; +} -/* Returns true if the page is within a block suitable for migration to */ -static bool suitable_migration_target(struct page *page) +enum smt_result { + GOOD_AS_MIGRATION_TARGET, + FAIL_UNMOVABLE_TARGET, + FAIL_BAD_TARGET, +}; + +/* + * Returns GOOD_AS_MIGRATION_TARGET if the page is within a block + * suitable for migration to, FAIL_UNMOVABLE_TARGET if the page + * is within a MIGRATE_UNMOVABLE block, FAIL_BAD_TARGET otherwise. + */ +static enum smt_result suitable_migration_target(struct page *page, + struct compact_control *cc) { int migratetype = get_pageblock_migratetype(page); /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) - return false; + return FAIL_BAD_TARGET; /* If the page is a large free page, then allow migration */ if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; + return GOOD_AS_MIGRATION_TARGET; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(migratetype)) - return true; + if (cc->mode != COMPACT_ASYNC_UNMOVABLE && + migrate_async_suitable(migratetype)) + return GOOD_AS_MIGRATION_TARGET; + + if (cc->mode == COMPACT_ASYNC_MOVABLE && + migratetype == MIGRATE_UNMOVABLE) + return FAIL_UNMOVABLE_TARGET; + + if (cc->mode != COMPACT_ASYNC_MOVABLE && + migratetype == MIGRATE_UNMOVABLE && + rescue_unmovable_pageblock(page)) + return GOOD_AS_MIGRATION_TARGET; /* Otherwise skip the block */ - return false; + return FAIL_BAD_TARGET; } /* @@ -410,6 +474,13 @@ static void isolate_freepages(struct zone *zone, zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; + /* + * isolate_freepages() may be called more than once during + * compact_zone_order() run and we want only the most recent + * count. + */ + cc->nr_pageblocks_skipped = 0; + /* * Isolate free pages until enough are available to migrate the * pages on cc->migratepages. We stop searching if the migrate @@ -418,6 +489,7 @@ static void isolate_freepages(struct zone *zone, for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; pfn -= pageblock_nr_pages) { unsigned long isolated; + enum smt_result ret; if (!pfn_valid(pfn)) continue; @@ -434,9 +506,12 @@ static void isolate_freepages(struct zone *zone, continue; /* Check the block is suitable for migration */ - if (!suitable_migration_target(page)) + ret = suitable_migration_target(page, cc); + if (ret != GOOD_AS_MIGRATION_TARGET) { + if (ret == FAIL_UNMOVABLE_TARGET) + cc->nr_pageblocks_skipped++; continue; - + } /* * Found a block suitable for isolating free pages from. Now * we disabled interrupts, double check things are ok and @@ -445,12 +520,14 @@ static void isolate_freepages(struct zone *zone, */ isolated = 0; spin_lock_irqsave(&zone->lock, flags); - if (suitable_migration_target(page)) { + ret = suitable_migration_target(page, cc); + if (ret == GOOD_AS_MIGRATION_TARGET) { end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn); isolated = isolate_freepages_block(pfn, end_pfn, freelist, false); nr_freepages += isolated; - } + } else if (ret == FAIL_UNMOVABLE_TARGET) + cc->nr_pageblocks_skipped++; spin_unlock_irqrestore(&zone->lock, flags); /* @@ -682,8 +759,9 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) nr_migrate = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, false, - cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC); + (unsigned long)&cc->freepages, false, + (cc->mode == COMPACT_SYNC) ? MIGRATE_SYNC_LIGHT + : MIGRATE_ASYNC); update_nr_listpages(cc); nr_remaining = cc->nr_migratepages; @@ -712,7 +790,8 @@ out: static unsigned long compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, - bool sync) + enum compact_mode mode, + unsigned long *nr_pageblocks_skipped) { struct compact_control cc = { .nr_freepages = 0, @@ -720,12 +799,17 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, - .sync = sync, + .mode = mode, }; + unsigned long rc; + INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); - return compact_zone(zone, &cc); + rc = compact_zone(zone, &cc); + *nr_pageblocks_skipped = cc.nr_pageblocks_skipped; + + return rc; } int sysctl_extfrag_threshold = 500; @@ -750,6 +834,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, struct zoneref *z; struct zone *zone; int rc = COMPACT_SKIPPED; + unsigned long nr_pageblocks_skipped; + enum compact_mode mode; /* * Check whether it is worth even starting compaction. The order check is @@ -766,12 +852,22 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync); + mode = sync ? COMPACT_SYNC : COMPACT_ASYNC_MOVABLE; +retry: + status = compact_zone_order(zone, order, gfp_mask, mode, + &nr_pageblocks_skipped); rc = max(status, rc); /* If a normal allocation would succeed, stop compacting */ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0)) break; + + if (rc == COMPACT_COMPLETE && mode == COMPACT_ASYNC_MOVABLE) { + if (nr_pageblocks_skipped) { + mode = COMPACT_ASYNC_UNMOVABLE; + goto retry; + } + } } return rc; @@ -805,7 +901,7 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) if (ok && cc->order > zone->compact_order_failed) zone->compact_order_failed = cc->order + 1; /* Currently async compaction is never deferred. */ - else if (!ok && cc->sync) + else if (!ok && cc->mode == COMPACT_SYNC) defer_compaction(zone, cc->order); } @@ -820,7 +916,7 @@ int compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .sync = false, + .mode = COMPACT_ASYNC_MOVABLE, }; return __compact_pgdat(pgdat, &cc); @@ -830,7 +926,7 @@ static int compact_node(int nid) { struct compact_control cc = { .order = -1, - .sync = true, + .mode = COMPACT_SYNC, }; return __compact_pgdat(NODE_DATA(nid), &cc); diff --git a/mm/internal.h b/mm/internal.h index 8b0fc8da8028..4194ab9dc19b 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -94,6 +94,9 @@ extern void putback_lru_page(struct page *page); /* * in mm/page_alloc.c */ +extern void set_pageblock_migratetype(struct page *page, int migratetype); +extern int move_freepages_block(struct zone *zone, struct page *page, + int migratetype); extern void __free_pages_bootmem(struct page *page, unsigned int order); extern void prep_compound_page(struct page *page, unsigned long order); #ifdef CONFIG_MEMORY_FAILURE @@ -101,6 +104,7 @@ extern bool is_free_buddy_page(struct page *page); #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA +#include /* * in mm/compaction.c @@ -119,11 +123,14 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ + enum compact_mode mode; /* Compaction mode */ int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; + + /* Number of UNMOVABLE destination pageblocks skipped during scan */ + unsigned long nr_pageblocks_skipped; }; unsigned long diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 84f2c599d5d4..457b4de122f4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -219,7 +219,7 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; -static void set_pageblock_migratetype(struct page *page, int migratetype) +void set_pageblock_migratetype(struct page *page, int migratetype) { if (unlikely(page_group_by_mobility_disabled)) @@ -954,8 +954,8 @@ static int move_freepages(struct zone *zone, return pages_moved; } -static int move_freepages_block(struct zone *zone, struct page *page, - int migratetype) +int move_freepages_block(struct zone *zone, struct page *page, + int migratetype) { unsigned long start_pfn, end_pfn; struct page *start_page, *end_page; @@ -5657,7 +5657,7 @@ static int __alloc_contig_migrate_range(unsigned long start, unsigned long end) .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .sync = true, + .mode = COMPACT_SYNC, }; INIT_LIST_HEAD(&cc.migratepages); -- cgit v1.2.3 From bde05d1ccd512696b09db9dd2e5f33ad19152605 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 29 May 2012 15:06:38 -0700 Subject: shmem: replace page if mapping excludes its zone The GMA500 GPU driver uses GEM shmem objects, but with a new twist: the backing RAM has to be below 4GB. Not a problem while the boards supported only 4GB: but now Intel's D2700MUD boards support 8GB, and their GMA3600 is managed by the GMA500 driver. shmem/tmpfs has never pretended to support hardware restrictions on the backing memory, but it might have appeared to do so before v3.1, and even now it works fine until a page is swapped out then back in. When read_cache_page_gfp() supplied a freshly allocated page for copy, that compensated for whatever choice might have been made by earlier swapin readahead; but swapoff was likely to destroy the illusion. We'd like to continue to support GMA500, so now add a new shmem_should_replace_page() check on the zone when about to move a page from swapcache to filecache (in swapin and swapoff cases), with shmem_replace_page() to allocate and substitute a suitable page (given gma500/gem.c's mapping_set_gfp_mask GFP_KERNEL | __GFP_DMA32). This does involve a minor extension to mem_cgroup_replace_page_cache() (the page may or may not have already been charged); and I've removed a comment and call to mem_cgroup_uncharge_cache_page(), which in fact is always a no-op while PageSwapCache. Also removed optimization of an unlikely path in shmem_getpage_gfp(), now that we need to check PageSwapCache more carefully (a racing caller might already have made the copy). And at one point shmem_unuse_inode() needs to use the hitherto private page_swapcount(), to guard against racing with inode eviction. It would make sense to extend shmem_should_replace_page(), to cover cpuset and NUMA mempolicy restrictions too, but set that aside for now: needs a cleanup of shmem mempolicy handling, and more testing, and ought to handle swap faults in do_swap_page() as well as shmem. Signed-off-by: Hugh Dickins Cc: Christoph Hellwig Acked-by: KAMEZAWA Hiroyuki Cc: Alan Cox Cc: Stephane Marchesin Cc: Andi Kleen Cc: Dave Airlie Cc: Daniel Vetter Cc: Rob Clark Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 +++ mm/memcontrol.c | 17 +++++-- mm/shmem.c | 141 ++++++++++++++++++++++++++++++++++++++++++++------- mm/swapfile.c | 2 +- 4 files changed, 142 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index bc3073ce95cc..d965c4bfab3a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -351,6 +351,7 @@ extern int swap_type_of(dev_t, sector_t, struct block_device **); extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); +extern int page_swapcount(struct page *); extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; @@ -445,6 +446,11 @@ static inline void delete_from_swap_cache(struct page *page) { } +static inline int page_swapcount(struct page *page) +{ + return 0; +} + #define reuse_swap_page(page) (page_mapcount(page) == 1) static inline int try_to_free_swap(struct page *page) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4f71219cc53e..d7ce417cae7c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3373,7 +3373,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg = NULL; struct page_cgroup *pc; enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; @@ -3383,11 +3383,20 @@ void mem_cgroup_replace_page_cache(struct page *oldpage, pc = lookup_page_cgroup(oldpage); /* fix accounting on old pages */ lock_page_cgroup(pc); - memcg = pc->mem_cgroup; - mem_cgroup_charge_statistics(memcg, false, -1); - ClearPageCgroupUsed(pc); + if (PageCgroupUsed(pc)) { + memcg = pc->mem_cgroup; + mem_cgroup_charge_statistics(memcg, false, -1); + ClearPageCgroupUsed(pc); + } unlock_page_cgroup(pc); + /* + * When called from shmem_replace_page(), in some cases the + * oldpage has already been charged, and in some cases not. + */ + if (!memcg) + return; + if (PageSwapBacked(oldpage)) type = MEM_CGROUP_CHARGE_TYPE_SHMEM; diff --git a/mm/shmem.c b/mm/shmem.c index be5af34a070d..db72d8e44ec6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -103,6 +103,9 @@ static unsigned long shmem_default_max_inodes(void) } #endif +static bool shmem_should_replace_page(struct page *page, gfp_t gfp); +static int shmem_replace_page(struct page **pagep, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index); static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type); @@ -604,12 +607,13 @@ static void shmem_evict_inode(struct inode *inode) * If swap found in inode, free it and move page from swapcache to filecache. */ static int shmem_unuse_inode(struct shmem_inode_info *info, - swp_entry_t swap, struct page *page) + swp_entry_t swap, struct page **pagep) { struct address_space *mapping = info->vfs_inode.i_mapping; void *radswap; pgoff_t index; - int error; + gfp_t gfp; + int error = 0; radswap = swp_to_radix_entry(swap); index = radix_tree_locate_item(&mapping->page_tree, radswap); @@ -625,22 +629,37 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, if (shmem_swaplist.next != &info->swaplist) list_move_tail(&shmem_swaplist, &info->swaplist); + gfp = mapping_gfp_mask(mapping); + if (shmem_should_replace_page(*pagep, gfp)) { + mutex_unlock(&shmem_swaplist_mutex); + error = shmem_replace_page(pagep, gfp, info, index); + mutex_lock(&shmem_swaplist_mutex); + /* + * We needed to drop mutex to make that restrictive page + * allocation; but the inode might already be freed by now, + * and we cannot refer to inode or mapping or info to check. + * However, we do hold page lock on the PageSwapCache page, + * so can check if that still has our reference remaining. + */ + if (!page_swapcount(*pagep)) + error = -ENOENT; + } + /* * We rely on shmem_swaplist_mutex, not only to protect the swaplist, * but also to hold up shmem_evict_inode(): so inode cannot be freed * beneath us (pagelock doesn't help until the page is in pagecache). */ - error = shmem_add_to_page_cache(page, mapping, index, + if (!error) + error = shmem_add_to_page_cache(*pagep, mapping, index, GFP_NOWAIT, radswap); - /* which does mem_cgroup_uncharge_cache_page on error */ - if (error != -ENOMEM) { /* * Truncation and eviction use free_swap_and_cache(), which * only does trylock page: if we raced, best clean up here. */ - delete_from_swap_cache(page); - set_page_dirty(page); + delete_from_swap_cache(*pagep); + set_page_dirty(*pagep); if (!error) { spin_lock(&info->lock); info->swapped--; @@ -660,7 +679,14 @@ int shmem_unuse(swp_entry_t swap, struct page *page) struct list_head *this, *next; struct shmem_inode_info *info; int found = 0; - int error; + int error = 0; + + /* + * There's a faint possibility that swap page was replaced before + * caller locked it: it will come back later with the right page. + */ + if (unlikely(!PageSwapCache(page))) + goto out; /* * Charge page using GFP_KERNEL while we can wait, before taking @@ -676,7 +702,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page) list_for_each_safe(this, next, &shmem_swaplist) { info = list_entry(this, struct shmem_inode_info, swaplist); if (info->swapped) - found = shmem_unuse_inode(info, swap, page); + found = shmem_unuse_inode(info, swap, &page); else list_del_init(&info->swaplist); cond_resched(); @@ -685,8 +711,6 @@ int shmem_unuse(swp_entry_t swap, struct page *page) } mutex_unlock(&shmem_swaplist_mutex); - if (!found) - mem_cgroup_uncharge_cache_page(page); if (found < 0) error = found; out: @@ -855,6 +879,84 @@ static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) } #endif +/* + * When a page is moved from swapcache to shmem filecache (either by the + * usual swapin of shmem_getpage_gfp(), or by the less common swapoff of + * shmem_unuse_inode()), it may have been read in earlier from swap, in + * ignorance of the mapping it belongs to. If that mapping has special + * constraints (like the gma500 GEM driver, which requires RAM below 4GB), + * we may need to copy to a suitable page before moving to filecache. + * + * In a future release, this may well be extended to respect cpuset and + * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); + * but for now it is a simple matter of zone. + */ +static bool shmem_should_replace_page(struct page *page, gfp_t gfp) +{ + return page_zonenum(page) > gfp_zone(gfp); +} + +static int shmem_replace_page(struct page **pagep, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + struct page *oldpage, *newpage; + struct address_space *swap_mapping; + pgoff_t swap_index; + int error; + + oldpage = *pagep; + swap_index = page_private(oldpage); + swap_mapping = page_mapping(oldpage); + + /* + * We have arrived here because our zones are constrained, so don't + * limit chance of success by further cpuset and node constraints. + */ + gfp &= ~GFP_CONSTRAINT_MASK; + newpage = shmem_alloc_page(gfp, info, index); + if (!newpage) + return -ENOMEM; + VM_BUG_ON(shmem_should_replace_page(newpage, gfp)); + + *pagep = newpage; + page_cache_get(newpage); + copy_highpage(newpage, oldpage); + + VM_BUG_ON(!PageLocked(oldpage)); + __set_page_locked(newpage); + VM_BUG_ON(!PageUptodate(oldpage)); + SetPageUptodate(newpage); + VM_BUG_ON(!PageSwapBacked(oldpage)); + SetPageSwapBacked(newpage); + VM_BUG_ON(!swap_index); + set_page_private(newpage, swap_index); + VM_BUG_ON(!PageSwapCache(oldpage)); + SetPageSwapCache(newpage); + + /* + * Our caller will very soon move newpage out of swapcache, but it's + * a nice clean interface for us to replace oldpage by newpage there. + */ + spin_lock_irq(&swap_mapping->tree_lock); + error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage, + newpage); + __inc_zone_page_state(newpage, NR_FILE_PAGES); + __dec_zone_page_state(oldpage, NR_FILE_PAGES); + spin_unlock_irq(&swap_mapping->tree_lock); + BUG_ON(error); + + mem_cgroup_replace_page_cache(oldpage, newpage); + lru_cache_add_anon(newpage); + + ClearPageSwapCache(oldpage); + set_page_private(oldpage, 0); + + unlock_page(oldpage); + page_cache_release(oldpage); + page_cache_release(oldpage); + return 0; +} + /* * shmem_getpage_gfp - find page in cache, or get from swap, or allocate * @@ -923,19 +1025,20 @@ repeat: /* We have to do this with page locked to prevent races */ lock_page(page); + if (!PageSwapCache(page) || page->mapping) { + error = -EEXIST; /* try again */ + goto failed; + } if (!PageUptodate(page)) { error = -EIO; goto failed; } wait_on_page_writeback(page); - /* Someone may have already done it for us */ - if (page->mapping) { - if (page->mapping == mapping && - page->index == index) - goto done; - error = -EEXIST; - goto failed; + if (shmem_should_replace_page(page, gfp)) { + error = shmem_replace_page(&page, gfp, info, index); + if (error) + goto failed; } error = mem_cgroup_cache_charge(page, current->mm, @@ -998,7 +1101,7 @@ repeat: if (sgp == SGP_DIRTY) set_page_dirty(page); } -done: + /* Perhaps the file has been truncated since we checked */ if (sgp != SGP_WRITE && ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { diff --git a/mm/swapfile.c b/mm/swapfile.c index fafc26d1b1dc..b0c86e92f42c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -601,7 +601,7 @@ void swapcache_free(swp_entry_t entry, struct page *page) * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ -static inline int page_swapcount(struct page *page) +int page_swapcount(struct page *page) { int count = 0; struct swap_info_struct *p; -- cgit v1.2.3 From 17cf28afea2a1112f240a3a2da8af883be024811 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 29 May 2012 15:06:41 -0700 Subject: mm/fs: remove truncate_range Remove vmtruncate_range(), and remove the truncate_range method from struct inode_operations: only tmpfs ever supported it, and tmpfs has now converted over to using the fallocate method of file_operations. Update Documentation accordingly, adding (setlease and) fallocate lines. And while we're in mm.h, remove duplicate declarations of shmem_lock() and shmem_file_setup(): everyone is now using the ones in shmem_fs.h. Based-on-patch-by: Cong Wang Signed-off-by: Hugh Dickins Cc: Christoph Hellwig Cc: Cong Wang Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/Locking | 2 -- Documentation/filesystems/vfs.txt | 13 ++++++++----- fs/bad_inode.c | 1 - include/linux/fs.h | 1 - include/linux/mm.h | 4 ---- mm/shmem.c | 1 - mm/truncate.c | 25 ------------------------- 7 files changed, 8 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 4fca82e5276e..d449e632e6a0 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -60,7 +60,6 @@ ata *); ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); - void (*truncate_range)(struct inode *, loff_t, loff_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); locking rules: @@ -87,7 +86,6 @@ setxattr: yes getxattr: no listxattr: no removexattr: yes -truncate_range: yes fiemap: no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on victim. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 0d0492028082..ef19f91a0f12 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -363,7 +363,6 @@ struct inode_operations { ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); - void (*truncate_range)(struct inode *, loff_t, loff_t); }; Again, all methods are called without any locks being held, unless @@ -472,9 +471,6 @@ otherwise noted. removexattr: called by the VFS to remove an extended attribute from a file. This method is called by removexattr(2) system call. - truncate_range: a method provided by the underlying filesystem to truncate a - range of blocks , i.e. punch a hole somewhere in a file. - The Address Space Object ======================== @@ -760,7 +756,7 @@ struct file_operations ---------------------- This describes how the VFS can manipulate an open file. As of kernel -2.6.22, the following members are defined: +3.5, the following members are defined: struct file_operations { struct module *owner; @@ -790,6 +786,8 @@ struct file_operations { int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int); + int (*setlease)(struct file *, long arg, struct file_lock **); + long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len); }; Again, all methods are called without any locks being held, unless @@ -858,6 +856,11 @@ otherwise noted. splice_read: called by the VFS to splice data from file to a pipe. This method is used by the splice(2) system call + setlease: called by the VFS to set or release a file lock lease. + setlease has the file_lock_lock held and must not sleep. + + fallocate: called by the VFS to preallocate blocks or punch a hole. + Note that the file operations are implemented by the specific filesystem in which the inode resides. When opening a device node (character or block special) most filesystems will call special diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 37268c5bb98b..1b35d6bd06b0 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -292,7 +292,6 @@ static const struct inode_operations bad_inode_ops = .getxattr = bad_inode_getxattr, .listxattr = bad_inode_listxattr, .removexattr = bad_inode_removexattr, - /* truncate_range returns void */ }; diff --git a/include/linux/fs.h b/include/linux/fs.h index cdc1a9630948..038076b27ea4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1681,7 +1681,6 @@ struct inode_operations { ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); - void (*truncate_range)(struct inode *, loff_t, loff_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); } ____cacheline_aligned; diff --git a/include/linux/mm.h b/include/linux/mm.h index 7d5c37f24c63..aa20bafa40f6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -871,8 +871,6 @@ extern void pagefault_out_of_memory(void); extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); -int shmem_lock(struct file *file, int lock, struct user_struct *user); -struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); int shmem_zero_setup(struct vm_area_struct *); extern int can_do_mlock(void); @@ -951,11 +949,9 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); extern int vmtruncate(struct inode *inode, loff_t offset); -extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); - int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU diff --git a/mm/shmem.c b/mm/shmem.c index 7e54ff1c63e1..f368d0acb52c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2541,7 +2541,6 @@ static const struct file_operations shmem_file_operations = { static const struct inode_operations shmem_inode_operations = { .setattr = shmem_setattr, - .truncate_range = shmem_truncate_range, #ifdef CONFIG_TMPFS_XATTR .setxattr = shmem_setxattr, .getxattr = shmem_getxattr, diff --git a/mm/truncate.c b/mm/truncate.c index 61a183b89df6..75801acdaac7 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -602,31 +602,6 @@ int vmtruncate(struct inode *inode, loff_t newsize) } EXPORT_SYMBOL(vmtruncate); -int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend) -{ - struct address_space *mapping = inode->i_mapping; - loff_t holebegin = round_up(lstart, PAGE_SIZE); - loff_t holelen = 1 + lend - holebegin; - - /* - * If the underlying filesystem is not going to provide - * a way to truncate a range of blocks (punch a hole) - - * we should return failure right now. - */ - if (!inode->i_op->truncate_range) - return -ENOSYS; - - mutex_lock(&inode->i_mutex); - inode_dio_wait(inode); - unmap_mapping_range(mapping, holebegin, holelen, 1); - inode->i_op->truncate_range(inode, lstart, lend); - /* unmap again to remove racily COWed private pages */ - unmap_mapping_range(mapping, holebegin, holelen, 1); - mutex_unlock(&inode->i_mutex); - - return 0; -} - /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode -- cgit v1.2.3 From a7f638f999ff42310e9582273b1fe25ea6e469ba Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 29 May 2012 15:06:47 -0700 Subject: mm, oom: normalize oom scores to oom_score_adj scale only for userspace The oom_score_adj scale ranges from -1000 to 1000 and represents the proportion of memory available to the process at allocation time. This means an oom_score_adj value of 300, for example, will bias a process as though it was using an extra 30.0% of available memory and a value of -350 will discount 35.0% of available memory from its usage. The oom killer badness heuristic also uses this scale to report the oom score for each eligible process in determining the "best" process to kill. Thus, it can only differentiate each process's memory usage by 0.1% of system RAM. On large systems, this can end up being a large amount of memory: 256MB on 256GB systems, for example. This can be fixed by having the badness heuristic to use the actual memory usage in scoring threads and then normalizing it to the oom_score_adj scale for userspace. This results in better comparison between eligible threads for kill and no change from the userspace perspective. Suggested-by: KOSAKI Motohiro Tested-by: Dave Jones Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 5 +++-- include/linux/oom.h | 5 +++-- mm/oom_kill.c | 44 ++++++++++++++++---------------------------- 3 files changed, 22 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/base.c b/fs/proc/base.c index d2d3108a611c..d7d711876b6a 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -411,12 +411,13 @@ static const struct file_operations proc_lstats_operations = { static int proc_oom_score(struct task_struct *task, char *buffer) { + unsigned long totalpages = totalram_pages + total_swap_pages; unsigned long points = 0; read_lock(&tasklist_lock); if (pid_alive(task)) - points = oom_badness(task, NULL, NULL, - totalram_pages + total_swap_pages); + points = oom_badness(task, NULL, NULL, totalpages) * + 1000 / totalpages; read_unlock(&tasklist_lock); return sprintf(buffer, "%lu\n", points); } diff --git a/include/linux/oom.h b/include/linux/oom.h index 3d7647536b03..e4c29bc72e70 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -43,8 +43,9 @@ enum oom_constraint { extern void compare_swap_oom_score_adj(int old_val, int new_val); extern int test_set_oom_score_adj(int new_val); -extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, - const nodemask_t *nodemask, unsigned long totalpages); +extern unsigned long oom_badness(struct task_struct *p, + struct mem_cgroup *memcg, const nodemask_t *nodemask, + unsigned long totalpages); extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 9f09a1fde9f9..ed0e19677360 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -180,10 +180,10 @@ static bool oom_unkillable_task(struct task_struct *p, * predictable as possible. The goal is to return the highest value for the * task consuming the most memory to avoid subsequent oom failures. */ -unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, - const nodemask_t *nodemask, unsigned long totalpages) +unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, + const nodemask_t *nodemask, unsigned long totalpages) { - long points; + unsigned long points; if (oom_unkillable_task(p, memcg, nodemask)) return 0; @@ -197,22 +197,12 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, return 0; } - /* - * The memory controller may have a limit of 0 bytes, so avoid a divide - * by zero, if necessary. - */ - if (!totalpages) - totalpages = 1; - /* * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + p->mm->nr_ptes; - points += get_mm_counter(p->mm, MM_SWAPENTS); - - points *= 1000; - points /= totalpages; + points = get_mm_rss(p->mm) + p->mm->nr_ptes + + get_mm_counter(p->mm, MM_SWAPENTS); task_unlock(p); /* @@ -220,23 +210,20 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * implementation used by LSMs. */ if (has_capability_noaudit(p, CAP_SYS_ADMIN)) - points -= 30; + points -= 30 * totalpages / 1000; /* * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may * either completely disable oom killing or always prefer a certain * task. */ - points += p->signal->oom_score_adj; + points += p->signal->oom_score_adj * totalpages / 1000; /* - * Never return 0 for an eligible task that may be killed since it's - * possible that no single user task uses more than 0.1% of memory and - * no single admin tasks uses more than 3.0%. + * Never return 0 for an eligible task regardless of the root bonus and + * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here). */ - if (points <= 0) - return 1; - return (points < 1000) ? points : 1000; + return points ? points : 1; } /* @@ -314,7 +301,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, { struct task_struct *g, *p; struct task_struct *chosen = NULL; - *ppoints = 0; + unsigned long chosen_points = 0; do_each_thread(g, p) { unsigned int points; @@ -354,7 +341,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, */ if (p == current) { chosen = p; - *ppoints = 1000; + chosen_points = ULONG_MAX; } else if (!force_kill) { /* * If this task is not being ptraced on exit, @@ -367,12 +354,13 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, } points = oom_badness(p, memcg, nodemask, totalpages); - if (points > *ppoints) { + if (points > chosen_points) { chosen = p; - *ppoints = points; + chosen_points = points; } } while_each_thread(g, p); + *ppoints = chosen_points * 1000 / totalpages; return chosen; } @@ -572,7 +560,7 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, } check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); - limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT; + limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; read_lock(&tasklist_lock); p = select_bad_process(&points, limit, memcg, NULL, false); if (p && PTR_ERR(p) != -1UL) -- cgit v1.2.3 From 5bf5f03c271907978489868a4c72aeb42b5127d2 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Tue, 29 May 2012 15:06:49 -0700 Subject: mm: fix slab->page flags corruption Transparent huge pages can change page->flags (PG_compound_lock) without taking Slab lock. Since THP can not break slab pages we can safely access compound page without taking compound lock. Specifically this patch fixes a race between compound_unlock() and slab functions which perform page-flags updates. This can occur when get_page()/put_page() is called on a page from slab. [akpm@linux-foundation.org: tweak comment text, fix comment layout, fix label indenting] Reported-by: Amey Bhide Signed-off-by: Pravin B Shelar Reviewed-by: Christoph Lameter Acked-by: Andrea Arcangeli Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/swap.c | 37 +++++++++++++++++++++++++++++++++++-- 2 files changed, 37 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index aa20bafa40f6..ce26716238c3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -321,6 +321,7 @@ static inline int is_vmalloc_or_module_addr(const void *x) static inline void compound_lock(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE + VM_BUG_ON(PageSlab(page)); bit_spin_lock(PG_compound_lock, &page->flags); #endif } @@ -328,6 +329,7 @@ static inline void compound_lock(struct page *page) static inline void compound_unlock(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE + VM_BUG_ON(PageSlab(page)); bit_spin_unlock(PG_compound_lock, &page->flags); #endif } diff --git a/mm/swap.c b/mm/swap.c index 5c13f1338972..6fdd72ec15b0 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -82,6 +82,25 @@ static void put_compound_page(struct page *page) if (likely(page != page_head && get_page_unless_zero(page_head))) { unsigned long flags; + + /* + * THP can not break up slab pages so avoid taking + * compound_lock(). Slab performs non-atomic bit ops + * on page->flags for better performance. In particular + * slab_unlock() in slub used to be a hot path. It is + * still hot on arches that do not support + * this_cpu_cmpxchg_double(). + */ + if (PageSlab(page_head)) { + if (PageTail(page)) { + if (put_page_testzero(page_head)) + VM_BUG_ON(1); + + atomic_dec(&page->_mapcount); + goto skip_lock_tail; + } else + goto skip_lock; + } /* * page_head wasn't a dangling pointer but it * may not be a head page anymore by the time @@ -92,10 +111,10 @@ static void put_compound_page(struct page *page) if (unlikely(!PageTail(page))) { /* __split_huge_page_refcount run before us */ compound_unlock_irqrestore(page_head, flags); - VM_BUG_ON(PageHead(page_head)); +skip_lock: if (put_page_testzero(page_head)) __put_single_page(page_head); - out_put_single: +out_put_single: if (put_page_testzero(page)) __put_single_page(page); return; @@ -115,6 +134,8 @@ static void put_compound_page(struct page *page) VM_BUG_ON(atomic_read(&page_head->_count) <= 0); VM_BUG_ON(atomic_read(&page->_count) != 0); compound_unlock_irqrestore(page_head, flags); + +skip_lock_tail: if (put_page_testzero(page_head)) { if (PageHead(page_head)) __put_compound_page(page_head); @@ -162,6 +183,18 @@ bool __get_page_tail(struct page *page) struct page *page_head = compound_trans_head(page); if (likely(page != page_head && get_page_unless_zero(page_head))) { + + /* Ref to put_compound_page() comment. */ + if (PageSlab(page_head)) { + if (likely(PageTail(page))) { + __get_page_tail_foll(page, false); + return true; + } else { + put_page(page_head); + return false; + } + } + /* * page_head wasn't a dangling pointer but it * may not be a head page anymore by the time -- cgit v1.2.3 From 4b91355e9dc9ac1eb3d69e56de093899ff2677ef Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 29 May 2012 15:06:51 -0700 Subject: memcg: fix/change behavior of shared anon at moving task This patch changes memcg's behavior at task_move(). At task_move(), the kernel scans a task's page table and move the changes for mapped pages from source cgroup to target cgroup. There has been a bug at handling shared anonymous pages for a long time. Before patch: - The spec says 'shared anonymous pages are not moved.' - The implementation was 'shared anonymoys pages may be moved'. If page_mapcount <=2, shared anonymous pages's charge were moved. After patch: - The spec says 'all anonymous pages are moved'. - The implementation is 'all anonymous pages are moved'. Considering usage of memcg, this will not affect user's experience. 'shared anonymous' pages only exists between a tree of processes which don't do exec(). Moving one of process without exec() seems not sane. For example, libcgroup will not be affected by this change. (Anyway, no one noticed the implementation for a long time...) Below is a discussion log: - current spec/implementation are complex - Now, shared file caches are moved - It adds unclear check as page_mapcount(). To do correct check, we should check swap users, etc. - No one notice this implementation behavior. So, no one get benefit from the design. - In general, once task is moved to a cgroup for running, it will not be moved.... - Finally, we have control knob as memory.move_charge_at_immigrate. Here is a patch to allow moving shared pages, completely. This makes memcg simpler and fix current broken code. Suggested-by: Hugh Dickins Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Naoya Horiguchi Cc: Glauber Costa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memory.txt | 9 ++++----- include/linux/swap.h | 9 --------- mm/memcontrol.c | 22 ++++++++++++++-------- mm/swapfile.c | 31 ------------------------------- 4 files changed, 18 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index e479007f1a75..6a066a270fc5 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -184,12 +184,14 @@ behind this approach is that a cgroup that aggressively uses a shared page will eventually get charged for it (once it is uncharged from the cgroup that brought it in -- this will happen on memory pressure). +But see section 8.2: when moving a task to another cgroup, its pages may +be recharged to the new cgroup, if move_charge_at_immigrate has been chosen. + Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used. When you do swapoff and make swapped-out pages of shmem(tmpfs) to be backed into memory in force, charges for pages are accounted against the caller of swapoff rather than the users of shmem. - 2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP) Swap Extension allows you to record charge for swap. A swapped-in page is @@ -615,8 +617,7 @@ memory cgroup. bit | what type of charges would be moved ? -----+------------------------------------------------------------------------ 0 | A charge of an anonymous page(or swap of it) used by the target task. - | Those pages and swaps must be used only by the target task. You must - | enable Swap Extension(see 2.4) to enable move of swap charges. + | You must enable Swap Extension(see 2.4) to enable move of swap charges. -----+------------------------------------------------------------------------ 1 | A charge of file pages(normal file, tmpfs file(e.g. ipc shared memory) | and swaps of tmpfs file) mmapped by the target task. Unlike the case of @@ -629,8 +630,6 @@ memory cgroup. 8.3 TODO -- Implement madvise(2) to let users decide the vma to be moved or not to be - moved. - All of moving charge operations are done under cgroup_mutex. It's not good behavior to hold the mutex too long, so we may need some trick. diff --git a/include/linux/swap.h b/include/linux/swap.h index d965c4bfab3a..49c0fa9ef5cf 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -359,7 +359,6 @@ struct backing_dev_info; #ifdef CONFIG_CGROUP_MEM_RES_CTLR extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); -extern int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep); #else static inline void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) @@ -470,14 +469,6 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) { } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -static inline int -mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep) -{ - return 0; -} -#endif - #endif /* CONFIG_SWAP */ #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d7ce417cae7c..e7db70f3d2d6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5154,7 +5154,7 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma, return NULL; if (PageAnon(page)) { /* we don't move shared anon */ - if (!move_anon() || page_mapcount(page) > 2) + if (!move_anon()) return NULL; } else if (!move_file()) /* we ignore mapcount for file pages */ @@ -5165,26 +5165,32 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma, return page; } +#ifdef CONFIG_SWAP static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, unsigned long addr, pte_t ptent, swp_entry_t *entry) { - int usage_count; struct page *page = NULL; swp_entry_t ent = pte_to_swp_entry(ptent); if (!move_anon() || non_swap_entry(ent)) return NULL; - usage_count = mem_cgroup_count_swap_user(ent, &page); - if (usage_count > 1) { /* we don't move shared anon */ - if (page) - put_page(page); - return NULL; - } + /* + * Because lookup_swap_cache() updates some statistics counter, + * we call find_get_page() with swapper_space directly. + */ + page = find_get_page(&swapper_space, ent.val); if (do_swap_account) entry->val = ent.val; return page; } +#else +static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t ptent, swp_entry_t *entry) +{ + return NULL; +} +#endif static struct page *mc_handle_file_pte(struct vm_area_struct *vma, unsigned long addr, pte_t ptent, swp_entry_t *entry) diff --git a/mm/swapfile.c b/mm/swapfile.c index b0c86e92f42c..457b10baef59 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -717,37 +717,6 @@ int free_swap_and_cache(swp_entry_t entry) return p != NULL; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -/** - * mem_cgroup_count_swap_user - count the user of a swap entry - * @ent: the swap entry to be checked - * @pagep: the pointer for the swap cache page of the entry to be stored - * - * Returns the number of the user of the swap entry. The number is valid only - * for swaps of anonymous pages. - * If the entry is found on swap cache, the page is stored to pagep with - * refcount of it being incremented. - */ -int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep) -{ - struct page *page; - struct swap_info_struct *p; - int count = 0; - - page = find_get_page(&swapper_space, ent.val); - if (page) - count += page_mapcount(page); - p = swap_info_get(ent); - if (p) { - count += swap_count(p->swap_map[swp_offset(ent)]); - spin_unlock(&swap_lock); - } - - *pagep = page; - return count; -} -#endif - #ifdef CONFIG_HIBERNATION /* * Find the swap type that corresponds to given device (if any). -- cgit v1.2.3 From 89abfab133ef1f5902abafb744df72793213ac19 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 29 May 2012 15:06:53 -0700 Subject: mm/memcg: move reclaim_stat into lruvec With mem_cgroup_disabled() now explicit, it becomes clear that the zone_reclaim_stat structure actually belongs in lruvec, per-zone when memcg is disabled but per-memcg per-zone when it's enabled. We can delete mem_cgroup_get_reclaim_stat(), and change update_page_reclaim_stat() to update just the one set of stats, the one which get_scan_count() will actually use. Signed-off-by: Hugh Dickins Signed-off-by: Konstantin Khlebnikov Acked-by: KAMEZAWA Hiroyuki Acked-by: Michal Hocko Reviewed-by: Minchan Kim Reviewed-by: Michal Hocko Cc: Glauber Costa Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 9 --------- include/linux/mmzone.h | 29 ++++++++++++++--------------- mm/memcontrol.c | 27 +++++++-------------------- mm/page_alloc.c | 8 ++++---- mm/swap.c | 14 ++++---------- mm/vmscan.c | 5 +---- 6 files changed, 30 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 18ea0b7baf32..cfe9050ad8da 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -126,8 +126,6 @@ int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid, unsigned int lrumask); -struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, - struct zone *zone); struct zone_reclaim_stat* mem_cgroup_get_reclaim_stat_from_page(struct page *page); extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, @@ -356,13 +354,6 @@ mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid, return 0; } - -static inline struct zone_reclaim_stat* -mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, struct zone *zone) -{ - return NULL; -} - static inline struct zone_reclaim_stat* mem_cgroup_get_reclaim_stat_from_page(struct page *page) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4871e31ae277..1b89861eedc0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -185,8 +185,22 @@ static inline int is_unevictable_lru(enum lru_list lru) return (lru == LRU_UNEVICTABLE); } +struct zone_reclaim_stat { + /* + * The pageout code in vmscan.c keeps track of how many of the + * mem/swap backed and file backed pages are refeferenced. + * The higher the rotated/scanned ratio, the more valuable + * that cache is. + * + * The anon LRU stats live in [0], file LRU stats in [1] + */ + unsigned long recent_rotated[2]; + unsigned long recent_scanned[2]; +}; + struct lruvec { struct list_head lists[NR_LRU_LISTS]; + struct zone_reclaim_stat reclaim_stat; }; /* Mask used at gathering information at once (see memcontrol.c) */ @@ -313,19 +327,6 @@ enum zone_type { #error ZONES_SHIFT -- too many zones configured adjust calculation #endif -struct zone_reclaim_stat { - /* - * The pageout code in vmscan.c keeps track of how many of the - * mem/swap backed and file backed pages are refeferenced. - * The higher the rotated/scanned ratio, the more valuable - * that cache is. - * - * The anon LRU stats live in [0], file LRU stats in [1] - */ - unsigned long recent_rotated[2]; - unsigned long recent_scanned[2]; -}; - struct zone { /* Fields commonly accessed by the page allocator */ @@ -407,8 +408,6 @@ struct zone { spinlock_t lru_lock; struct lruvec lruvec; - struct zone_reclaim_stat reclaim_stat; - unsigned long pages_scanned; /* since last reclaim */ unsigned long flags; /* zone flags, see below */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 30f938c86453..00c8898dbb81 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -138,7 +138,6 @@ struct mem_cgroup_per_zone { struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1]; - struct zone_reclaim_stat reclaim_stat; struct rb_node tree_node; /* RB tree node */ unsigned long long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ @@ -1243,16 +1242,6 @@ int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone) return (active > inactive); } -struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, - struct zone *zone) -{ - int nid = zone_to_nid(zone); - int zid = zone_idx(zone); - struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid); - - return &mz->reclaim_stat; -} - struct zone_reclaim_stat * mem_cgroup_get_reclaim_stat_from_page(struct page *page) { @@ -1268,7 +1257,7 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page) /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */ smp_rmb(); mz = page_cgroup_zoneinfo(pc->mem_cgroup, page); - return &mz->reclaim_stat; + return &mz->lruvec.reclaim_stat; } #define mem_cgroup_from_res_counter(counter, member) \ @@ -4216,21 +4205,19 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, { int nid, zid; struct mem_cgroup_per_zone *mz; + struct zone_reclaim_stat *rstat; unsigned long recent_rotated[2] = {0, 0}; unsigned long recent_scanned[2] = {0, 0}; for_each_online_node(nid) for (zid = 0; zid < MAX_NR_ZONES; zid++) { mz = mem_cgroup_zoneinfo(memcg, nid, zid); + rstat = &mz->lruvec.reclaim_stat; - recent_rotated[0] += - mz->reclaim_stat.recent_rotated[0]; - recent_rotated[1] += - mz->reclaim_stat.recent_rotated[1]; - recent_scanned[0] += - mz->reclaim_stat.recent_scanned[0]; - recent_scanned[1] += - mz->reclaim_stat.recent_scanned[1]; + recent_rotated[0] += rstat->recent_rotated[0]; + recent_rotated[1] += rstat->recent_rotated[1]; + recent_scanned[0] += rstat->recent_scanned[0]; + recent_scanned[1] += rstat->recent_scanned[1]; } cb->fill(cb, "recent_rotated_anon", recent_rotated[0]); cb->fill(cb, "recent_rotated_file", recent_rotated[1]); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4fc462b5fcf1..8cbfc38e68ac 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4410,10 +4410,10 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, zone_pcp_init(zone); for_each_lru(lru) INIT_LIST_HEAD(&zone->lruvec.lists[lru]); - zone->reclaim_stat.recent_rotated[0] = 0; - zone->reclaim_stat.recent_rotated[1] = 0; - zone->reclaim_stat.recent_scanned[0] = 0; - zone->reclaim_stat.recent_scanned[1] = 0; + zone->lruvec.reclaim_stat.recent_rotated[0] = 0; + zone->lruvec.reclaim_stat.recent_rotated[1] = 0; + zone->lruvec.reclaim_stat.recent_scanned[0] = 0; + zone->lruvec.reclaim_stat.recent_scanned[1] = 0; zap_zone_vm_stats(zone); zone->flags = 0; if (!size) diff --git a/mm/swap.c b/mm/swap.c index 6fdd72ec15b0..0503ad705e7c 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -312,21 +312,15 @@ void rotate_reclaimable_page(struct page *page) static void update_page_reclaim_stat(struct zone *zone, struct page *page, int file, int rotated) { - struct zone_reclaim_stat *reclaim_stat = &zone->reclaim_stat; - struct zone_reclaim_stat *memcg_reclaim_stat; + struct zone_reclaim_stat *reclaim_stat; - memcg_reclaim_stat = mem_cgroup_get_reclaim_stat_from_page(page); + reclaim_stat = mem_cgroup_get_reclaim_stat_from_page(page); + if (!reclaim_stat) + reclaim_stat = &zone->lruvec.reclaim_stat; reclaim_stat->recent_scanned[file]++; if (rotated) reclaim_stat->recent_rotated[file]++; - - if (!memcg_reclaim_stat) - return; - - memcg_reclaim_stat->recent_scanned[file]++; - if (rotated) - memcg_reclaim_stat->recent_rotated[file]++; } static void __activate_page(struct page *page, void *arg) diff --git a/mm/vmscan.c b/mm/vmscan.c index 52fac58b4461..e234ada18747 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -149,10 +149,7 @@ static bool global_reclaim(struct scan_control *sc) static struct zone_reclaim_stat *get_reclaim_stat(struct mem_cgroup_zone *mz) { - if (!mem_cgroup_disabled()) - return mem_cgroup_get_reclaim_stat(mz->mem_cgroup, mz->zone); - - return &mz->zone->reclaim_stat; + return &mem_cgroup_zone_lruvec(mz->zone, mz->mem_cgroup)->reclaim_stat; } static unsigned long zone_nr_lru_pages(struct mem_cgroup_zone *mz, -- cgit v1.2.3