summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2023-01-28 09:25:19 +0300
committerJakub Kicinski <kuba@kernel.org>2023-01-28 09:56:18 +0300
commitb568d3072a443fac22d35d6342f48ee27b811661 (patch)
treeccfc287070b55e4aeffb6a57e9e0434bc5b40c90 /drivers/infiniband/hw
parentc2ea552065e43d05bce240f53c3185fd3a066204 (diff)
parentff445b8397745ea94675162faa0e9b0079ca521d (diff)
downloadlinux-b568d3072a443fac22d35d6342f48ee27b811661.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Conflicts: drivers/net/ethernet/intel/ice/ice_main.c 418e53401e47 ("ice: move devlink port creation/deletion") 643ef23bd9dd ("ice: Introduce local var for readability") https://lore.kernel.org/all/20230127124025.0dacef40@canb.auug.org.au/ https://lore.kernel.org/all/20230124005714.3996270-1-anthony.l.nguyen@intel.com/ drivers/net/ethernet/engleder/tsnep_main.c 3d53aaef4332 ("tsnep: Fix TX queue stop/wake for multiple queues") 25faa6a4c5ca ("tsnep: Replace TX spin_lock with __netif_tx_lock") https://lore.kernel.org/all/20230127123604.36bb3e99@canb.auug.org.au/ net/netfilter/nf_conntrack_proto_sctp.c 13bd9b31a969 ("Revert "netfilter: conntrack: add sctp DATA_SENT state"") a44b7651489f ("netfilter: conntrack: unify established states for SCTP paths") f71cb8f45d09 ("netfilter: conntrack: sctp: use nf log infrastructure for invalid packets") https://lore.kernel.org/all/20230127125052.674281f9@canb.auug.org.au/ https://lore.kernel.org/all/d36076f3-6add-a442-6d4b-ead9f7ffff86@tessares.net/ Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'drivers/infiniband/hw')
-rw-r--r--drivers/infiniband/hw/hfi1/user_exp_rcv.c200
-rw-r--r--drivers/infiniband/hw/hfi1/user_exp_rcv.h3
2 files changed, 143 insertions, 60 deletions
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 186d30291260..b02f2f0809c8 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/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) {
- spin_lock(&fd->tid_lock);
- fd->tid_used += tididx;
- spin_unlock(&fd->tid_lock);
- 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;
+
+ /* 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 -= 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;
}
}
- /*
- * 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:
+ tinfo->tidcnt = tididx;
+ tinfo->length = mapped_pages * PAGE_SIZE;
+
+ if (copy_to_user(u64_to_user_ptr(tinfo->tidlist),
+ tidlist, sizeof(tidlist[0]) * tididx)) {
+ ret = -EFAULT;
+ goto fail_unprogram;
+ }
+
+ 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 @@ out_unmap:
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)
{
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
index 8c53e416bf84..f8ee997d0050 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h
+++ b/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;