From:   David Howells <dhowells@redhat.com>
To:     Steve French <smfrench@gmail.com>
Cc:     David Howells <dhowells@redhat.com>, Jens Axboe <axboe@kernel.dk>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Shyam Prasad N <nspmangalore@gmail.com>,
        Rohith Surabattula <rohiths.msft@gmail.com>,
        Tom Talpey <tom@talpey.com>,
        Stefan Metzmacher <metze@samba.org>,
        Christoph Hellwig <hch@infradead.org>,
        Matthew Wilcox <willy@infradead.org>,
        Jeff Layton <jlayton@kernel.org>, linux-cifs@vger.kernel.org,
        linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        Steve French <sfrench@samba.org>, linux-cachefs@redhat.com
Subject: [PATCH 09/17] netfs: Add a function to extract an iterator into a scatterlist
Date:   Thu, 16 Feb 2023 21:47:37 +0000
Message-Id: <20230216214745.3985496-10-dhowells@redhat.com>
In-Reply-To: <20230216214745.3985496-1-dhowells@redhat.com>
References: <20230216214745.3985496-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Provide a function for filling in a scatterlist from the list of pages
contained in an iterator.

If the iterator is UBUF- or IOBUF-type, the pages have a pin taken on them
(as FOLL_PIN).

If the iterator is BVEC-, KVEC- or XARRAY-type, no pin is taken on the
pages and it is left to the caller to manage their lifetime.  It cannot be
assumed that a ref can be validly taken, particularly in the case of a KVEC
iterator.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: Steve French <sfrench@samba.org>
cc: Shyam Prasad N <nspmangalore@gmail.com>
cc: Rohith Surabattula <rohiths.msft@gmail.com>
cc: linux-cachefs@redhat.com
cc: linux-cifs@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
---
 fs/netfs/iterator.c   | 268 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |   4 +
 mm/vmalloc.c          |   1 +
 3 files changed, 273 insertions(+)

diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
index 6f0d79080abc..80d7ff440cac 100644
--- a/fs/netfs/iterator.c
+++ b/fs/netfs/iterator.c
@@ -7,7 +7,9 @@
 
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 #include <linux/uio.h>
+#include <linux/scatterlist.h>
 #include <linux/netfs.h>
 #include "internal.h"
 
@@ -101,3 +103,269 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 	return npages;
 }
 EXPORT_SYMBOL_GPL(netfs_extract_user_iter);
+
+/*
+ * Extract and pin a list of up to sg_max pages from UBUF- or IOVEC-class
+ * iterators, and add them to the scatterlist.
+ */
+static ssize_t netfs_extract_user_to_sg(struct iov_iter *iter,
+					ssize_t maxsize,
+					struct sg_table *sgtable,
+					unsigned int sg_max,
+					iov_iter_extraction_t extraction_flags)
+{
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	struct page **pages;
+	unsigned int npages;
+	ssize_t ret = 0, res;
+	size_t len, off;
+
+	/* We decant the page list into the tail of the scatterlist */
+	pages = (void *)sgtable->sgl + array_size(sg_max, sizeof(struct scatterlist));
+	pages -= sg_max;
+
+	do {
+		res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max,
+					     extraction_flags, &off);
+		if (res < 0)
+			goto failed;
+
+		len = res;
+		maxsize -= len;
+		ret += len;
+		npages = DIV_ROUND_UP(off + len, PAGE_SIZE);
+		sg_max -= npages;
+
+		for (; npages < 0; npages--) {
+			struct page *page = *pages;
+			size_t seg = min_t(size_t, PAGE_SIZE - off, len);
+
+			*pages++ = NULL;
+			sg_set_page(sg, page, len, off);
+			sgtable->nents++;
+			sg++;
+			len -= seg;
+			off = 0;
+		}
+	} while (maxsize > 0 && sg_max > 0);
+
+	return ret;
+
+failed:
+	while (sgtable->nents > sgtable->orig_nents)
+		put_page(sg_page(&sgtable->sgl[--sgtable->nents]));
+	return res;
+}
+
+/*
+ * Extract up to sg_max pages from a BVEC-type iterator and add them to the
+ * scatterlist.  The pages are not pinned.
+ */
+static ssize_t netfs_extract_bvec_to_sg(struct iov_iter *iter,
+					ssize_t maxsize,
+					struct sg_table *sgtable,
+					unsigned int sg_max,
+					iov_iter_extraction_t extraction_flags)
+{
+	const struct bio_vec *bv = iter->bvec;
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	unsigned long start = iter->iov_offset;
+	unsigned int i;
+	ssize_t ret = 0;
+
+	for (i = 0; i < iter->nr_segs; i++) {
+		size_t off, len;
+
+		len = bv[i].bv_len;
+		if (start >= len) {
+			start -= len;
+			continue;
+		}
+
+		len = min_t(size_t, maxsize, len - start);
+		off = bv[i].bv_offset + start;
+
+		sg_set_page(sg, bv[i].bv_page, len, off);
+		sgtable->nents++;
+		sg++;
+		sg_max--;
+
+		ret += len;
+		maxsize -= len;
+		if (maxsize <= 0 || sg_max == 0)
+			break;
+		start = 0;
+	}
+
+	if (ret > 0)
+		iov_iter_advance(iter, ret);
+	return ret;
+}
+
+/*
+ * Extract up to sg_max pages from a KVEC-type iterator and add them to the
+ * scatterlist.  This can deal with vmalloc'd buffers as well as kmalloc'd or
+ * static buffers.  The pages are not pinned.
+ */
+static ssize_t netfs_extract_kvec_to_sg(struct iov_iter *iter,
+					ssize_t maxsize,
+					struct sg_table *sgtable,
+					unsigned int sg_max,
+					iov_iter_extraction_t extraction_flags)
+{
+	const struct kvec *kv = iter->kvec;
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	unsigned long start = iter->iov_offset;
+	unsigned int i;
+	ssize_t ret = 0;
+
+	for (i = 0; i < iter->nr_segs; i++) {
+		struct page *page;
+		unsigned long kaddr;
+		size_t off, len, seg;
+
+		len = kv[i].iov_len;
+		if (start >= len) {
+			start -= len;
+			continue;
+		}
+
+		kaddr = (unsigned long)kv[i].iov_base + start;
+		off = kaddr & ~PAGE_MASK;
+		len = min_t(size_t, maxsize, len - start);
+		kaddr &= PAGE_MASK;
+
+		maxsize -= len;
+		ret += len;
+		do {
+			seg = min_t(size_t, len, PAGE_SIZE - off);
+			if (is_vmalloc_or_module_addr((void *)kaddr))
+				page = vmalloc_to_page((void *)kaddr);
+			else
+				page = virt_to_page(kaddr);
+
+			sg_set_page(sg, page, len, off);
+			sgtable->nents++;
+			sg++;
+			sg_max--;
+
+			len -= seg;
+			kaddr += PAGE_SIZE;
+			off = 0;
+		} while (len > 0 && sg_max > 0);
+
+		if (maxsize <= 0 || sg_max == 0)
+			break;
+		start = 0;
+	}
+
+	if (ret > 0)
+		iov_iter_advance(iter, ret);
+	return ret;
+}
+
+/*
+ * Extract up to sg_max folios from an XARRAY-type iterator and add them to
+ * the scatterlist.  The pages are not pinned.
+ */
+static ssize_t netfs_extract_xarray_to_sg(struct iov_iter *iter,
+					  ssize_t maxsize,
+					  struct sg_table *sgtable,
+					  unsigned int sg_max,
+					  iov_iter_extraction_t extraction_flags)
+{
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	struct xarray *xa = iter->xarray;
+	struct folio *folio;
+	loff_t start = iter->xarray_start + iter->iov_offset;
+	pgoff_t index = start / PAGE_SIZE;
+	ssize_t ret = 0;
+	size_t offset, len;
+	XA_STATE(xas, xa, index);
+
+	rcu_read_lock();
+
+	xas_for_each(&xas, folio, ULONG_MAX) {
+		if (xas_retry(&xas, folio))
+			continue;
+		if (WARN_ON(xa_is_value(folio)))
+			break;
+		if (WARN_ON(folio_test_hugetlb(folio)))
+			break;
+
+		offset = offset_in_folio(folio, start);
+		len = min_t(size_t, maxsize, folio_size(folio) - offset);
+
+		sg_set_page(sg, folio_page(folio, 0), len, offset);
+		sgtable->nents++;
+		sg++;
+		sg_max--;
+
+		maxsize -= len;
+		ret += len;
+		if (maxsize <= 0 || sg_max == 0)
+			break;
+	}
+
+	rcu_read_unlock();
+	if (ret > 0)
+		iov_iter_advance(iter, ret);
+	return ret;
+}
+
+/**
+ * netfs_extract_iter_to_sg - Extract pages from an iterator and add ot an sglist
+ * @iter: The iterator to extract from
+ * @maxsize: The amount of iterator to copy
+ * @sgtable: The scatterlist table to fill in
+ * @sg_max: Maximum number of elements in @sgtable that may be filled
+ * @extraction_flags: Flags to qualify the request
+ *
+ * Extract the page fragments from the given amount of the source iterator and
+ * add them to a scatterlist that refers to all of those bits, to a maximum
+ * addition of @sg_max elements.
+ *
+ * The pages referred to by UBUF- and IOVEC-type iterators are extracted and
+ * pinned; BVEC-, KVEC- and XARRAY-type are extracted but aren't pinned; PIPE-
+ * and DISCARD-type are not supported.
+ *
+ * No end mark is placed on the scatterlist; that's left to the caller.
+ *
+ * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA
+ * be allowed on the pages extracted.
+ *
+ * If successul, @sgtable->nents is updated to include the number of elements
+ * added and the number of bytes added is returned.  @sgtable->orig_nents is
+ * left unaltered.
+ *
+ * The iov_iter_extract_mode() function should be used to query how cleanup
+ * should be performed.
+ */
+ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t maxsize,
+				 struct sg_table *sgtable, unsigned int sg_max,
+				 iov_iter_extraction_t extraction_flags)
+{
+	if (maxsize == 0)
+		return 0;
+
+	switch (iov_iter_type(iter)) {
+	case ITER_UBUF:
+	case ITER_IOVEC:
+		return netfs_extract_user_to_sg(iter, maxsize, sgtable, sg_max,
+						extraction_flags);
+	case ITER_BVEC:
+		return netfs_extract_bvec_to_sg(iter, maxsize, sgtable, sg_max,
+						extraction_flags);
+	case ITER_KVEC:
+		return netfs_extract_kvec_to_sg(iter, maxsize, sgtable, sg_max,
+						extraction_flags);
+	case ITER_XARRAY:
+		return netfs_extract_xarray_to_sg(iter, maxsize, sgtable, sg_max,
+						  extraction_flags);
+	default:
+		pr_err("%s(%u) unsupported\n", __func__, iov_iter_type(iter));
+		WARN_ON_ONCE(1);
+		return -EIO;
+	}
+}
+EXPORT_SYMBOL_GPL(netfs_extract_iter_to_sg);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index b11a84f6c32b..a1f3522daa69 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -300,6 +300,10 @@ void netfs_stats_show(struct seq_file *);
 ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
+struct sg_table;
+ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t len,
+				 struct sg_table *sgtable, unsigned int sg_max,
+				 iov_iter_extraction_t extraction_flags);
 
 /**
  * netfs_inode - Get the netfs inode context from the inode
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ca71de7c9d77..61f5bec0f2b6 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -656,6 +656,7 @@ int is_vmalloc_or_module_addr(const void *x)
 #endif
 	return is_vmalloc_addr(x);
 }
+EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr);
 
 /*
  * Walk a vmap address to the struct page it maps. Huge vmap mappings will