From 2f7c68cb55ecb7331f2381deb497c27155f32faf Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 03 Jan 2024 09:43:39 +0000
Subject: [PATCH] update kernel to 5.10.198
---
kernel/drivers/infiniband/hw/hfi1/user_exp_rcv.c | 211 +++++++++++++++++++++++++++++++++++-----------------
1 files changed, 143 insertions(+), 68 deletions(-)
diff --git a/kernel/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/kernel/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index b94fc7f..0e0be6c 100644
--- a/kernel/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/kernel/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -65,17 +65,24 @@
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,
};
/*
@@ -195,15 +202,10 @@
static int pin_rcv_pages(struct hfi1_filedata *fd, struct tid_user_buf *tidbuf)
{
int pinned;
- unsigned int npages;
+ unsigned int npages = tidbuf->npages;
unsigned long vaddr = tidbuf->vaddr;
struct page **pages = NULL;
struct hfi1_devdata *dd = fd->uctxt->dd;
-
- /* Get the number of pages the user buffer spans */
- npages = num_user_pages(vaddr, tidbuf->length);
- if (!npages)
- return -EINVAL;
if (npages > fd->uctxt->expected_count) {
dd_dev_err(dd, "Expected buffer too big\n");
@@ -231,7 +233,6 @@
return pinned;
}
tidbuf->pages = pages;
- tidbuf->npages = npages;
fd->tid_n_pinned += pinned;
return pinned;
}
@@ -295,53 +296,66 @@
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->npages = num_user_pages(tidbuf->vaddr, tidbuf->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;
@@ -437,43 +451,78 @@
}
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:
- kfree(tidbuf->psets);
- kfree(tidlist);
+ 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);
- return ret > 0 ? 0 : ret;
+ 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);
+ kfree(tidlist);
+ return ret;
}
int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd,
@@ -494,7 +543,7 @@
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);
@@ -750,6 +799,7 @@
}
node->fdata = fd;
+ mutex_init(&node->invalidate_mutex);
node->phys = page_to_phys(pages[0]);
node->npages = npages;
node->rcventry = rcventry;
@@ -765,11 +815,6 @@
&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;
@@ -789,8 +834,7 @@
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;
@@ -813,9 +857,6 @@
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);
@@ -823,23 +864,34 @@
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));
@@ -898,10 +950,16 @@
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) {
@@ -931,6 +989,23 @@
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)
{
--
Gitblit v1.6.2