Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma fixes from Jason Gunthorpe:

 - Several hfi1 patches fixing some long standing driver bugs

 - Overflow when working with sg lists with elements greater than 4G

 - An rxe regression with object numbering after the mrs reach their
   limit

 - A theoretical problem with the scatterlist merging code

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  lib/scatterlist: Fix to calculate the last_pg properly
  IB/hfi1: Remove user expected buffer invalidate race
  IB/hfi1: Immediately remove invalid memory from hardware
  IB/hfi1: Fix expected receive setup error exit issues
  IB/hfi1: Reserve user expected TIDs
  IB/hfi1: Reject a zero-length user expected buffer
  RDMA/core: Fix ib block iterator counter overflow
  RDMA/rxe: Prevent faulty rkey generation
  RDMA/rxe: Fix inaccurate constants in rxe_type_info

drivers/infiniband/core/verbs.c

@@ -2957,15 +2957,18 @@ EXPORT_SYMBOL(__rdma_block_iter_start);
 bool __rdma_block_iter_next(struct ib_block_iter *biter)
 {
 	unsigned int block_offset;
+	unsigned int sg_delta;
 
 	if (!biter->__sg_nents || !biter->__sg)
 		return false;
 
 	biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance;
 	block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1);
-	biter->__sg_advance += BIT_ULL(biter->__pg_bit) - block_offset;
+	sg_delta = BIT_ULL(biter->__pg_bit) - block_offset;
 
-	if (biter->__sg_advance >= sg_dma_len(biter->__sg)) {
+	if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) {
+		biter->__sg_advance += sg_delta;
+	} else {
 		biter->__sg_advance = 0;
 		biter->__sg = sg_next(biter->__sg);
 		biter->__sg_nents--;

drivers/infiniband/hw/hfi1/user_exp_rcv.c

@@ -23,18 +23,25 @@ static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
 static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
 			      const struct mmu_notifier_range *range,
 			      unsigned long cur_seq);
+static bool tid_cover_invalidate(struct mmu_interval_notifier *mni,
+			         const struct mmu_notifier_range *range,
+			         unsigned long cur_seq);
 static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *,
 			    struct tid_group *grp,
 			    unsigned int start, u16 count,
 			    u32 *tidlist, unsigned int *tididx,
 			    unsigned int *pmapped);
-static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
-			      struct tid_group **grp);
+static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo);
+static void __clear_tid_node(struct hfi1_filedata *fd,
+			     struct tid_rb_node *node);
 static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node);
 
 static const struct mmu_interval_notifier_ops tid_mn_ops = {
 	.invalidate = tid_rb_invalidate,
 };
+static const struct mmu_interval_notifier_ops tid_cover_ops = {
+	.invalidate = tid_cover_invalidate,
+};
 
 /*
  * Initialize context and file private data needed for Expected
@@ -253,53 +260,65 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
 		tididx = 0, mapped, mapped_pages = 0;
 	u32 *tidlist = NULL;
 	struct tid_user_buf *tidbuf;
+	unsigned long mmu_seq = 0;
 
 	if (!PAGE_ALIGNED(tinfo->vaddr))
 		return -EINVAL;
+	if (tinfo->length == 0)
+		return -EINVAL;
 
 	tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL);
 	if (!tidbuf)
 		return -ENOMEM;
 
+	mutex_init(&tidbuf->cover_mutex);
 	tidbuf->vaddr = tinfo->vaddr;
 	tidbuf->length = tinfo->length;
 	tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets),
 				GFP_KERNEL);
 	if (!tidbuf->psets) {
-		kfree(tidbuf);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail_release_mem;
+	}
+
+	if (fd->use_mn) {
+		ret = mmu_interval_notifier_insert(
+			&tidbuf->notifier, current->mm,
+			tidbuf->vaddr, tidbuf->npages * PAGE_SIZE,
+			&tid_cover_ops);
+		if (ret)
+			goto fail_release_mem;
+		mmu_seq = mmu_interval_read_begin(&tidbuf->notifier);
 	}
 
 	pinned = pin_rcv_pages(fd, tidbuf);
 	if (pinned <= 0) {
-		kfree(tidbuf->psets);
-		kfree(tidbuf);
-		return pinned;
+		ret = (pinned < 0) ? pinned : -ENOSPC;
+		goto fail_unpin;
 	}
 
 	/* Find sets of physically contiguous pages */
 	tidbuf->n_psets = find_phys_blocks(tidbuf, pinned);
 
-	/*
-	 * We don't need to access this under a lock since tid_used is per
-	 * process and the same process cannot be in hfi1_user_exp_rcv_clear()
-	 * and hfi1_user_exp_rcv_setup() at the same time.
-	 */
+	/* Reserve the number of expected tids to be used. */
 	spin_lock(&fd->tid_lock);
 	if (fd->tid_used + tidbuf->n_psets > fd->tid_limit)
 		pageset_count = fd->tid_limit - fd->tid_used;
 	else
 		pageset_count = tidbuf->n_psets;
+	fd->tid_used += pageset_count;
 	spin_unlock(&fd->tid_lock);
 
-	if (!pageset_count)
-		goto bail;
+	if (!pageset_count) {
+		ret = -ENOSPC;
+		goto fail_unreserve;
+	}
 
 	ngroups = pageset_count / dd->rcv_entries.group_size;
 	tidlist = kcalloc(pageset_count, sizeof(*tidlist), GFP_KERNEL);
 	if (!tidlist) {
 		ret = -ENOMEM;
-		goto nomem;
+		goto fail_unreserve;
 	}
 
 	tididx = 0;
@@ -395,43 +414,78 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
 	}
 unlock:
 	mutex_unlock(&uctxt->exp_mutex);
-nomem:
 	hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx,
 		  mapped_pages, ret);
-	if (tididx) {
+
+	/* fail if nothing was programmed, set error if none provided */
+	if (tididx == 0) {
+		if (ret >= 0)
+			ret = -ENOSPC;
+		goto fail_unreserve;
+	}
+
+	/* adjust reserved tid_used to actual count */
 	spin_lock(&fd->tid_lock);
-		fd->tid_used += tididx;
+	fd->tid_used -= pageset_count - tididx;
 	spin_unlock(&fd->tid_lock);
+
+	/* unpin all pages not covered by a TID */
+	unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages,
+			false);
+
+	if (fd->use_mn) {
+		/* check for an invalidate during setup */
+		bool fail = false;
+
+		mutex_lock(&tidbuf->cover_mutex);
+		fail = mmu_interval_read_retry(&tidbuf->notifier, mmu_seq);
+		mutex_unlock(&tidbuf->cover_mutex);
+
+		if (fail) {
+			ret = -EBUSY;
+			goto fail_unprogram;
+		}
+	}
+
 	tinfo->tidcnt = tididx;
 	tinfo->length = mapped_pages * PAGE_SIZE;
 
 	if (copy_to_user(u64_to_user_ptr(tinfo->tidlist),
 			 tidlist, sizeof(tidlist[0]) * tididx)) {
-			/*
-			 * On failure to copy to the user level, we need to undo
-			 * everything done so far so we don't leak resources.
-			 */
-			tinfo->tidlist = (unsigned long)&tidlist;
-			hfi1_user_exp_rcv_clear(fd, tinfo);
-			tinfo->tidlist = 0;
 		ret = -EFAULT;
-			goto bail;
-		}
+		goto fail_unprogram;
 	}
 
-	/*
-	 * If not everything was mapped (due to insufficient RcvArray entries,
-	 * for example), unpin all unmapped pages so we can pin them nex time.
-	 */
-	if (mapped_pages != pinned)
-		unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages,
-				(pinned - mapped_pages), false);
-bail:
+	if (fd->use_mn)
+		mmu_interval_notifier_remove(&tidbuf->notifier);
+	kfree(tidbuf->pages);
 	kfree(tidbuf->psets);
+	kfree(tidbuf);
 	kfree(tidlist);
+	return 0;
+
+fail_unprogram:
+	/* unprogram, unmap, and unpin all allocated TIDs */
+	tinfo->tidlist = (unsigned long)tidlist;
+	hfi1_user_exp_rcv_clear(fd, tinfo);
+	tinfo->tidlist = 0;
+	pinned = 0;		/* nothing left to unpin */
+	pageset_count = 0;	/* nothing left reserved */
+fail_unreserve:
+	spin_lock(&fd->tid_lock);
+	fd->tid_used -= pageset_count;
+	spin_unlock(&fd->tid_lock);
+fail_unpin:
+	if (fd->use_mn)
+		mmu_interval_notifier_remove(&tidbuf->notifier);
+	if (pinned > 0)
+		unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false);
+fail_release_mem:
 	kfree(tidbuf->pages);
+	kfree(tidbuf->psets);
 	kfree(tidbuf);
-	return ret > 0 ? 0 : ret;
+	kfree(tidlist);
+	return ret;
 }
 
 int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd,
@@ -452,7 +506,7 @@ int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd,
 
 	mutex_lock(&uctxt->exp_mutex);
 	for (tididx = 0; tididx < tinfo->tidcnt; tididx++) {
-		ret = unprogram_rcvarray(fd, tidinfo[tididx], NULL);
+		ret = unprogram_rcvarray(fd, tidinfo[tididx]);
 		if (ret) {
 			hfi1_cdbg(TID, "Failed to unprogram rcv array %d",
 				  ret);
@@ -706,6 +760,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 	}
 
 	node->fdata = fd;
+	mutex_init(&node->invalidate_mutex);
 	node->phys = page_to_phys(pages[0]);
 	node->npages = npages;
 	node->rcventry = rcventry;
@@ -721,11 +776,6 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 			&tid_mn_ops);
 		if (ret)
 			goto out_unmap;
-		/*
-		 * FIXME: This is in the wrong order, the notifier should be
-		 * established before the pages are pinned by pin_rcv_pages.
-		 */
-		mmu_interval_read_begin(&node->notifier);
 	}
 	fd->entry_to_rb[node->rcventry - uctxt->expected_base] = node;
 
@@ -745,8 +795,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 	return -EFAULT;
 }
 
-static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
-			      struct tid_group **grp)
+static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo)
 {
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	struct hfi1_devdata *dd = uctxt->dd;
@@ -769,9 +818,6 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
 	if (!node || node->rcventry != (uctxt->expected_base + rcventry))
 		return -EBADF;
 
-	if (grp)
-		*grp = node->grp;
-
 	if (fd->use_mn)
 		mmu_interval_notifier_remove(&node->notifier);
 	cacheless_tid_rb_remove(fd, node);
@@ -779,23 +825,34 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
 	return 0;
 }
 
-static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
+static void __clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
 {
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 	struct hfi1_devdata *dd = uctxt->dd;
 
+	mutex_lock(&node->invalidate_mutex);
+	if (node->freed)
+		goto done;
+	node->freed = true;
+
 	trace_hfi1_exp_tid_unreg(uctxt->ctxt, fd->subctxt, node->rcventry,
 				 node->npages,
 				 node->notifier.interval_tree.start, node->phys,
 				 node->dma_addr);
 
-	/*
-	 * Make sure device has seen the write before we unpin the
-	 * pages.
-	 */
+	/* Make sure device has seen the write before pages are unpinned */
 	hfi1_put_tid(dd, node->rcventry, PT_INVALID_FLUSH, 0, 0);
 
 	unpin_rcv_pages(fd, NULL, node, 0, node->npages, true);
+done:
+	mutex_unlock(&node->invalidate_mutex);
+}
+
+static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
+{
+	struct hfi1_ctxtdata *uctxt = fd->uctxt;
+
+	__clear_tid_node(fd, node);
 
 	node->grp->used--;
 	node->grp->map &= ~(1 << (node->rcventry - node->grp->base));
@@ -854,10 +911,16 @@ static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
 	if (node->freed)
 		return true;
 
+	/* take action only if unmapping */
+	if (range->event != MMU_NOTIFY_UNMAP)
+		return true;
+
 	trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt,
 				 node->notifier.interval_tree.start,
 				 node->rcventry, node->npages, node->dma_addr);
-	node->freed = true;
+
+	/* clear the hardware rcvarray entry */
+	__clear_tid_node(fdata, node);
 
 	spin_lock(&fdata->invalid_lock);
 	if (fdata->invalid_tid_idx < uctxt->expected_count) {
@@ -887,6 +950,23 @@ static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
 	return true;
 }
 
+static bool tid_cover_invalidate(struct mmu_interval_notifier *mni,
+			         const struct mmu_notifier_range *range,
+			         unsigned long cur_seq)
+{
+	struct tid_user_buf *tidbuf =
+		container_of(mni, struct tid_user_buf, notifier);
+
+	/* take action only if unmapping */
+	if (range->event == MMU_NOTIFY_UNMAP) {
+		mutex_lock(&tidbuf->cover_mutex);
+		mmu_interval_set_seq(mni, cur_seq);
+		mutex_unlock(&tidbuf->cover_mutex);
+	}
+
+	return true;
+}
+
 static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
 				    struct tid_rb_node *tnode)
 {

drivers/infiniband/hw/hfi1/user_exp_rcv.h

@@ -16,6 +16,8 @@ struct tid_pageset {
 };
 
 struct tid_user_buf {
+	struct mmu_interval_notifier notifier;
+	struct mutex cover_mutex;
 	unsigned long vaddr;
 	unsigned long length;
 	unsigned int npages;
@@ -27,6 +29,7 @@ struct tid_user_buf {
 struct tid_rb_node {
 	struct mmu_interval_notifier notifier;
 	struct hfi1_filedata *fdata;
+	struct mutex invalidate_mutex; /* covers hw removal */
 	unsigned long phys;
 	struct tid_group *grp;
 	u32 rcventry;

drivers/infiniband/sw/rxe/rxe_param.h

@@ -98,11 +98,11 @@ enum rxe_device_param {
 	RXE_MAX_SRQ			= DEFAULT_MAX_VALUE - RXE_MIN_SRQ_INDEX,
 
 	RXE_MIN_MR_INDEX		= 0x00000001,
-	RXE_MAX_MR_INDEX		= DEFAULT_MAX_VALUE,
-	RXE_MAX_MR			= DEFAULT_MAX_VALUE - RXE_MIN_MR_INDEX,
-	RXE_MIN_MW_INDEX		= 0x00010001,
-	RXE_MAX_MW_INDEX		= 0x00020000,
-	RXE_MAX_MW			= 0x00001000,
+	RXE_MAX_MR_INDEX		= DEFAULT_MAX_VALUE >> 1,
+	RXE_MAX_MR			= RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX,
+	RXE_MIN_MW_INDEX		= RXE_MAX_MR_INDEX + 1,
+	RXE_MAX_MW_INDEX		= DEFAULT_MAX_VALUE,
+	RXE_MAX_MW			= RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX,
 
 	RXE_MAX_PKT_PER_ACK		= 64,
 

drivers/infiniband/sw/rxe/rxe_pool.c

@@ -23,16 +23,16 @@ static const struct rxe_type_info {
 		.size		= sizeof(struct rxe_ucontext),
 		.elem_offset	= offsetof(struct rxe_ucontext, elem),
 		.min_index	= 1,
-		.max_index	= UINT_MAX,
-		.max_elem	= UINT_MAX,
+		.max_index	= RXE_MAX_UCONTEXT,
+		.max_elem	= RXE_MAX_UCONTEXT,
 	},
 	[RXE_TYPE_PD] = {
 		.name		= "pd",
 		.size		= sizeof(struct rxe_pd),
 		.elem_offset	= offsetof(struct rxe_pd, elem),
 		.min_index	= 1,
-		.max_index	= UINT_MAX,
-		.max_elem	= UINT_MAX,
+		.max_index	= RXE_MAX_PD,
+		.max_elem	= RXE_MAX_PD,
 	},
 	[RXE_TYPE_AH] = {
 		.name		= "ah",
@@ -40,7 +40,7 @@ static const struct rxe_type_info {
 		.elem_offset	= offsetof(struct rxe_ah, elem),
 		.min_index	= RXE_MIN_AH_INDEX,
 		.max_index	= RXE_MAX_AH_INDEX,
-		.max_elem	= RXE_MAX_AH_INDEX - RXE_MIN_AH_INDEX + 1,
+		.max_elem	= RXE_MAX_AH,
 	},
 	[RXE_TYPE_SRQ] = {
 		.name		= "srq",
@@ -49,7 +49,7 @@ static const struct rxe_type_info {
 		.cleanup	= rxe_srq_cleanup,
 		.min_index	= RXE_MIN_SRQ_INDEX,
 		.max_index	= RXE_MAX_SRQ_INDEX,
-		.max_elem	= RXE_MAX_SRQ_INDEX - RXE_MIN_SRQ_INDEX + 1,
+		.max_elem	= RXE_MAX_SRQ,
 	},
 	[RXE_TYPE_QP] = {
 		.name		= "qp",
@@ -58,7 +58,7 @@ static const struct rxe_type_info {
 		.cleanup	= rxe_qp_cleanup,
 		.min_index	= RXE_MIN_QP_INDEX,
 		.max_index	= RXE_MAX_QP_INDEX,
-		.max_elem	= RXE_MAX_QP_INDEX - RXE_MIN_QP_INDEX + 1,
+		.max_elem	= RXE_MAX_QP,
 	},
 	[RXE_TYPE_CQ] = {
 		.name		= "cq",
@@ -66,8 +66,8 @@ static const struct rxe_type_info {
 		.elem_offset	= offsetof(struct rxe_cq, elem),
 		.cleanup	= rxe_cq_cleanup,
 		.min_index	= 1,
-		.max_index	= UINT_MAX,
-		.max_elem	= UINT_MAX,
+		.max_index	= RXE_MAX_CQ,
+		.max_elem	= RXE_MAX_CQ,
 	},
 	[RXE_TYPE_MR] = {
 		.name		= "mr",
@@ -76,7 +76,7 @@ static const struct rxe_type_info {
 		.cleanup	= rxe_mr_cleanup,
 		.min_index	= RXE_MIN_MR_INDEX,
 		.max_index	= RXE_MAX_MR_INDEX,
-		.max_elem	= RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX + 1,
+		.max_elem	= RXE_MAX_MR,
 	},
 	[RXE_TYPE_MW] = {
 		.name		= "mw",
@@ -85,7 +85,7 @@ static const struct rxe_type_info {
 		.cleanup	= rxe_mw_cleanup,
 		.min_index	= RXE_MIN_MW_INDEX,
 		.max_index	= RXE_MAX_MW_INDEX,
-		.max_elem	= RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX + 1,
+		.max_elem	= RXE_MAX_MW,
 	},
 };
 

lib/scatterlist.c

@@ -470,12 +470,16 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
 		return -EOPNOTSUPP;
 
 	if (sgt_append->prv) {
+		unsigned long next_pfn = (page_to_phys(sg_page(sgt_append->prv)) +
+			sgt_append->prv->offset + sgt_append->prv->length) / PAGE_SIZE;
+
 		if (WARN_ON(offset))
 			return -EINVAL;
 
 		/* Merge contiguous pages into the last SG */
 		prv_len = sgt_append->prv->length;
-		last_pg = sg_page(sgt_append->prv);
+		if (page_to_pfn(pages[0]) == next_pfn) {
+			last_pg = pfn_to_page(next_pfn - 1);
 			while (n_pages && pages_are_mergeable(pages[0], last_pg)) {
 				if (sgt_append->prv->length + PAGE_SIZE > max_segment)
 					break;
@@ -487,6 +491,7 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
 			if (!n_pages)
 				goto out;
 		}
+	}
 
 	/* compute number of contiguous chunks */
 	chunks = 1;