diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-17 11:18:18 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-17 11:18:18 -0700 |
commit | a1e16bc7d5f7ca3599d8a7f061841c93a563665e (patch) | |
tree | 73e557536e5dc52894e0e24439406db3510c5434 /lib | |
parent | 2a934b38c066ff221b08a9c703314a2a1c885dbd (diff) | |
parent | c7a198c700763ac89abbb166378f546aeb9afb33 (diff) | |
download | lwn-a1e16bc7d5f7ca3599d8a7f061841c93a563665e.tar.gz lwn-a1e16bc7d5f7ca3599d8a7f061841c93a563665e.zip |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull rdma updates from Jason Gunthorpe:
"A usual cycle for RDMA with a typical mix of driver and core subsystem
updates:
- Driver minor changes and bug fixes for mlx5, efa, rxe, vmw_pvrdma,
hns, usnic, qib, qedr, cxgb4, hns, bnxt_re
- Various rtrs fixes and updates
- Bug fix for mlx4 CM emulation for virtualization scenarios where
MRA wasn't working right
- Use tracepoints instead of pr_debug in the CM code
- Scrub the locking in ucma and cma to close more syzkaller bugs
- Use tasklet_setup in the subsystem
- Revert the idea that 'destroy' operations are not allowed to fail
at the driver level. This proved unworkable from a HW perspective.
- Revise how the umem API works so drivers make fewer mistakes using
it
- XRC support for qedr
- Convert uverbs objects RWQ and MW to new the allocation scheme
- Large queue entry sizes for hns
- Use hmm_range_fault() for mlx5 On Demand Paging
- uverbs APIs to inspect the GID table instead of sysfs
- Move some of the RDMA code for building large page SGLs into
lib/scatterlist"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (191 commits)
RDMA/ucma: Fix use after free in destroy id flow
RDMA/rxe: Handle skb_clone() failure in rxe_recv.c
RDMA/rxe: Move the definitions for rxe_av.network_type to uAPI
RDMA: Explicitly pass in the dma_device to ib_register_device
lib/scatterlist: Do not limit max_segment to PAGE_ALIGNED values
IB/mlx4: Convert rej_tmout radix-tree to XArray
RDMA/rxe: Fix bug rejecting all multicast packets
RDMA/rxe: Fix skb lifetime in rxe_rcv_mcast_pkt()
RDMA/rxe: Remove duplicate entries in struct rxe_mr
IB/hfi,rdmavt,qib,opa_vnic: Update MAINTAINERS
IB/rdmavt: Fix sizeof mismatch
MAINTAINERS: CISCO VIC LOW LATENCY NIC DRIVER
RDMA/bnxt_re: Fix sizeof mismatch for allocation of pbl_tbl.
RDMA/bnxt_re: Use rdma_umem_for_each_dma_block()
RDMA/umem: Move to allocate SG table from pages
lib/scatterlist: Add support in dynamic allocation of SG table from pages
tools/testing/scatterlist: Show errors in human readable form
tools/testing/scatterlist: Rejuvenate bit-rotten test
RDMA/ipoib: Set rtnl_link_ops for ipoib interfaces
RDMA/uverbs: Expose the new GID query API to user space
...
Diffstat (limited to 'lib')
-rw-r--r-- | lib/scatterlist.c | 133 |
1 files changed, 107 insertions, 26 deletions
diff --git a/lib/scatterlist.c b/lib/scatterlist.c index d94628fa3349..9a4992dc8e8c 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -365,6 +365,37 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) } EXPORT_SYMBOL(sg_alloc_table); +static struct scatterlist *get_next_sg(struct sg_table *table, + struct scatterlist *cur, + unsigned long needed_sges, + gfp_t gfp_mask) +{ + struct scatterlist *new_sg, *next_sg; + unsigned int alloc_size; + + if (cur) { + next_sg = sg_next(cur); + /* Check if last entry should be keeped for chainning */ + if (!sg_is_last(next_sg) || needed_sges == 1) + return next_sg; + } + + alloc_size = min_t(unsigned long, needed_sges, SG_MAX_SINGLE_ALLOC); + new_sg = sg_kmalloc(alloc_size, gfp_mask); + if (!new_sg) + return ERR_PTR(-ENOMEM); + sg_init_table(new_sg, alloc_size); + if (cur) { + __sg_chain(next_sg, new_sg); + table->orig_nents += alloc_size - 1; + } else { + table->sgl = new_sg; + table->orig_nents = alloc_size; + table->nents = 0; + } + return new_sg; +} + /** * __sg_alloc_table_from_pages - Allocate and initialize an sg table from * an array of pages @@ -373,30 +404,69 @@ EXPORT_SYMBOL(sg_alloc_table); * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) - * @max_segment: Maximum size of a scatterlist node in bytes (page aligned) + * @max_segment: Maximum size of a scatterlist element in bytes + * @prv: Last populated sge in sgt + * @left_pages: Left pages caller have to set after this call * @gfp_mask: GFP allocation mask * - * Description: - * Allocate and initialize an sg table from a list of pages. Contiguous - * ranges of the pages are squashed into a single scatterlist node up to the - * maximum size specified in @max_segment. An user may provide an offset at a - * start and a size of valid data in a buffer specified by the page array. - * The returned sg table is released by sg_free_table. + * Description: + * If @prv is NULL, allocate and initialize an sg table from a list of pages, + * else reuse the scatterlist passed in at @prv. + * Contiguous ranges of the pages are squashed into a single scatterlist + * entry up to the maximum size specified in @max_segment. A user may + * provide an offset at a start and a size of valid data in a buffer + * specified by the page array. * * Returns: - * 0 on success, negative error on failure + * Last SGE in sgt on success, PTR_ERR on otherwise. + * The allocation in @sgt must be released by sg_free_table. + * + * Notes: + * If this function returns non-0 (eg failure), the caller must call + * sg_free_table() to cleanup any leftover allocations. */ -int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, - unsigned int n_pages, unsigned int offset, - unsigned long size, unsigned int max_segment, - gfp_t gfp_mask) +struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt, + struct page **pages, unsigned int n_pages, unsigned int offset, + unsigned long size, unsigned int max_segment, + struct scatterlist *prv, unsigned int left_pages, + gfp_t gfp_mask) { - unsigned int chunks, cur_page, seg_len, i; - int ret; - struct scatterlist *s; + unsigned int chunks, cur_page, seg_len, i, prv_len = 0; + unsigned int added_nents = 0; + struct scatterlist *s = prv; - if (WARN_ON(!max_segment || offset_in_page(max_segment))) - return -EINVAL; + /* + * The algorithm below requires max_segment to be aligned to PAGE_SIZE + * otherwise it can overshoot. + */ + max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE); + if (WARN_ON(max_segment < PAGE_SIZE)) + return ERR_PTR(-EINVAL); + + if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && prv) + return ERR_PTR(-EOPNOTSUPP); + + if (prv) { + unsigned long paddr = (page_to_pfn(sg_page(prv)) * PAGE_SIZE + + prv->offset + prv->length) / + PAGE_SIZE; + + if (WARN_ON(offset)) + return ERR_PTR(-EINVAL); + + /* Merge contiguous pages into the last SG */ + prv_len = prv->length; + while (n_pages && page_to_pfn(pages[0]) == paddr) { + if (prv->length + PAGE_SIZE > max_segment) + break; + prv->length += PAGE_SIZE; + paddr++; + pages++; + n_pages--; + } + if (!n_pages) + goto out; + } /* compute number of contiguous chunks */ chunks = 1; @@ -410,13 +480,9 @@ int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, } } - ret = sg_alloc_table(sgt, chunks, gfp_mask); - if (unlikely(ret)) - return ret; - /* merging chunks and putting them into the scatterlist */ cur_page = 0; - for_each_sg(sgt->sgl, s, sgt->orig_nents, i) { + for (i = 0; i < chunks; i++) { unsigned int j, chunk_size; /* look for the end of the current chunk */ @@ -429,15 +495,30 @@ int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, break; } + /* Pass how many chunks might be left */ + s = get_next_sg(sgt, s, chunks - i + left_pages, gfp_mask); + if (IS_ERR(s)) { + /* + * Adjust entry length to be as before function was + * called. + */ + if (prv) + prv->length = prv_len; + return s; + } chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset; sg_set_page(s, pages[cur_page], min_t(unsigned long, size, chunk_size), offset); + added_nents++; size -= chunk_size; offset = 0; cur_page = j; } - - return 0; + sgt->nents += added_nents; +out: + if (!left_pages) + sg_mark_end(s); + return s; } EXPORT_SYMBOL(__sg_alloc_table_from_pages); @@ -465,8 +546,8 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, gfp_t gfp_mask) { - return __sg_alloc_table_from_pages(sgt, pages, n_pages, offset, size, - SCATTERLIST_MAX_SEGMENT, gfp_mask); + return PTR_ERR_OR_ZERO(__sg_alloc_table_from_pages(sgt, pages, n_pages, + offset, size, UINT_MAX, NULL, 0, gfp_mask)); } EXPORT_SYMBOL(sg_alloc_table_from_pages); |