* [PATCH RFC 01/10] mm: page_frag: some minor refactoring before adding new API
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 02/10] net: rename skb_copy_to_page_nocache() helper Yunsheng Lin
` (8 subsequent siblings)
9 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM
Refactor common codes from __page_frag_alloc_va_align() to
__page_frag_cache_prepare() and __page_frag_cache_commit(),
so that the new API can make use of them.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
include/linux/page_frag_cache.h | 34 ++++++++++++++++++++++++++--
mm/page_frag_cache.c | 40 ++++++++++++++++++++++++++-------
2 files changed, 64 insertions(+), 10 deletions(-)
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 41a91df82631..5ae97f93a0a1 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -5,6 +5,7 @@
#include <linux/bits.h>
#include <linux/log2.h>
+#include <linux/mmdebug.h>
#include <linux/mm_types_task.h>
#include <linux/types.h>
@@ -39,8 +40,37 @@ static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
void page_frag_cache_drain(struct page_frag_cache *nc);
void __page_frag_cache_drain(struct page *page, unsigned int count);
-void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
- gfp_t gfp_mask, unsigned int align_mask);
+void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
+ struct page_frag *pfrag, gfp_t gfp_mask,
+ unsigned int align_mask);
+unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
+ struct page_frag *pfrag,
+ unsigned int used_sz);
+
+static inline unsigned int __page_frag_cache_commit(struct page_frag_cache *nc,
+ struct page_frag *pfrag,
+ unsigned int used_sz)
+{
+ VM_BUG_ON(!nc->pagecnt_bias);
+ nc->pagecnt_bias--;
+
+ return __page_frag_cache_commit_noref(nc, pfrag, used_sz);
+}
+
+static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
+ unsigned int fragsz, gfp_t gfp_mask,
+ unsigned int align_mask)
+{
+ struct page_frag page_frag;
+ void *va;
+
+ va = __page_frag_cache_prepare(nc, fragsz, &page_frag, gfp_mask,
+ align_mask);
+ if (likely(va))
+ __page_frag_cache_commit(nc, &page_frag, fragsz);
+
+ return va;
+}
static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
unsigned int fragsz, gfp_t gfp_mask,
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 3f7a203d35c6..f55d34cf7d43 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -90,9 +90,31 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
}
EXPORT_SYMBOL(__page_frag_cache_drain);
-void *__page_frag_alloc_align(struct page_frag_cache *nc,
- unsigned int fragsz, gfp_t gfp_mask,
- unsigned int align_mask)
+unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
+ struct page_frag *pfrag,
+ unsigned int used_sz)
+{
+ unsigned int orig_offset;
+
+ VM_BUG_ON(used_sz > pfrag->size);
+ VM_BUG_ON(pfrag->page != encoded_page_decode_page(nc->encoded_page));
+ VM_BUG_ON(pfrag->offset + pfrag->size >
+ (PAGE_SIZE << encoded_page_decode_order(nc->encoded_page)));
+
+ /* pfrag->offset might be bigger than the nc->offset due to alignment */
+ VM_BUG_ON(nc->offset > pfrag->offset);
+
+ orig_offset = nc->offset;
+ nc->offset = pfrag->offset + used_sz;
+
+ /* Return true size back to caller considering the offset alignment */
+ return nc->offset - orig_offset;
+}
+EXPORT_SYMBOL(__page_frag_cache_commit_noref);
+
+void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
+ struct page_frag *pfrag, gfp_t gfp_mask,
+ unsigned int align_mask)
{
unsigned long encoded_page = nc->encoded_page;
unsigned int size, offset;
@@ -114,6 +136,8 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
/* reset page count bias and offset to start of new frag */
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
nc->offset = 0;
+ } else {
+ page = encoded_page_decode_page(encoded_page);
}
size = PAGE_SIZE << encoded_page_decode_order(encoded_page);
@@ -132,8 +156,6 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
return NULL;
}
- page = encoded_page_decode_page(encoded_page);
-
if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
goto refill;
@@ -148,15 +170,17 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
/* reset page count bias and offset to start of new frag */
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+ nc->offset = 0;
offset = 0;
}
- nc->pagecnt_bias--;
- nc->offset = offset + fragsz;
+ pfrag->page = page;
+ pfrag->offset = offset;
+ pfrag->size = size - offset;
return encoded_page_decode_virt(encoded_page) + offset;
}
-EXPORT_SYMBOL(__page_frag_alloc_align);
+EXPORT_SYMBOL(__page_frag_cache_prepare);
/*
* Frees a page fragment allocated out of either a compound or order 0 page.
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 02/10] net: rename skb_copy_to_page_nocache() helper
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
2024-10-28 11:58 ` [PATCH RFC 01/10] mm: page_frag: some minor refactoring before adding new API Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 17:49 ` Alexander Duyck
2024-10-28 11:58 ` [PATCH RFC 03/10] mm: page_frag: update documentation for page_frag Yunsheng Lin
` (7 subsequent siblings)
9 siblings, 1 reply; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM, Eric Dumazet, Simon Horman, David Ahern
Rename skb_copy_to_page_nocache() to skb_copy_to_frag_nocache()
to avoid calling virt_to_page() as we are about to pass virtual
address directly.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
include/net/sock.h | 9 ++++-----
net/ipv4/tcp.c | 7 +++----
net/kcm/kcmsock.c | 7 +++----
3 files changed, 10 insertions(+), 13 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index 7464e9f9f47c..cf037c870e3b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2203,15 +2203,14 @@ static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
return err;
}
-static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from,
+static inline int skb_copy_to_frag_nocache(struct sock *sk,
+ struct iov_iter *from,
struct sk_buff *skb,
- struct page *page,
- int off, int copy)
+ char *va, int copy)
{
int err;
- err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off,
- copy, skb->len);
+ err = skb_do_copy_data_nocache(sk, skb, from, va, copy, skb->len);
if (err)
return err;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 82cc4a5633ce..d5d2fca8a688 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1219,10 +1219,9 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
if (!copy)
goto wait_for_space;
- err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
- pfrag->page,
- pfrag->offset,
- copy);
+ err = skb_copy_to_frag_nocache(sk, &msg->msg_iter, skb,
+ page_address(pfrag->page) +
+ pfrag->offset, copy);
if (err)
goto do_error;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 24aec295a51c..94719d4af5fa 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -856,10 +856,9 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (!sk_wmem_schedule(sk, copy))
goto wait_for_memory;
- err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
- pfrag->page,
- pfrag->offset,
- copy);
+ err = skb_copy_to_frag_nocache(sk, &msg->msg_iter, skb,
+ page_address(pfrag->page) +
+ pfrag->offset, copy);
if (err)
goto out_error;
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 03/10] mm: page_frag: update documentation for page_frag
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
2024-10-28 11:58 ` [PATCH RFC 01/10] mm: page_frag: some minor refactoring before adding new API Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 02/10] net: rename skb_copy_to_page_nocache() helper Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 04/10] mm: page_frag: introduce page_frag_alloc_abort() related API Yunsheng Lin
` (6 subsequent siblings)
9 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM, Jonathan Corbet, linux-doc
Update documentation about design, implementation and API usages
for page_frag.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
Documentation/mm/page_frags.rst | 110 +++++++++++++++++++++++++++++++-
include/linux/page_frag_cache.h | 54 ++++++++++++++++
mm/page_frag_cache.c | 12 +++-
3 files changed, 173 insertions(+), 3 deletions(-)
diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
index 503ca6cdb804..34e654c2956e 100644
--- a/Documentation/mm/page_frags.rst
+++ b/Documentation/mm/page_frags.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
==============
Page fragments
==============
@@ -40,4 +42,110 @@ page via a single call. The advantage to doing this is that it allows for
cleaning up the multiple references that were added to a page in order to
avoid calling get_page per allocation.
-Alexander Duyck, Nov 29, 2016.
+
+Architecture overview
+=====================
+
+.. code-block:: none
+
+ +----------------------+
+ | page_frag API caller |
+ +----------------------+
+ |
+ |
+ v
+ +------------------------------------------------------------------+
+ | request page fragment |
+ +------------------------------------------------------------------+
+ | | |
+ | | |
+ | Cache not enough |
+ | | |
+ | +-----------------+ |
+ | | reuse old cache |--Usable-->|
+ | +-----------------+ |
+ | | |
+ | Not usable |
+ | | |
+ | v |
+ Cache empty +-----------------+ |
+ | | drain old cache | |
+ | +-----------------+ |
+ | | |
+ v_________________________________v |
+ | |
+ | |
+ _________________v_______________ |
+ | | Cache is enough
+ | | |
+ PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE | |
+ | | |
+ | PAGE_SIZE >= PAGE_FRAG_CACHE_MAX_SIZE |
+ v | |
+ +----------------------------------+ | |
+ | refill cache with order > 0 page | | |
+ +----------------------------------+ | |
+ | | | |
+ | | | |
+ | Refill failed | |
+ | | | |
+ | v v |
+ | +------------------------------------+ |
+ | | refill cache with order 0 page | |
+ | +----------------------------------=-+ |
+ | | |
+ Refill succeed | |
+ | Refill succeed |
+ | | |
+ v v v
+ +------------------------------------------------------------------+
+ | allocate fragment from cache |
+ +------------------------------------------------------------------+
+
+API interface
+=============
+
+Depending on different aligning requirement, the page_frag API caller may call
+page_frag_*_align*() to ensure the returned virtual address or offset of the
+page is aligned according to the 'align/alignment' parameter. Note the size of
+the allocated fragment is not aligned, the caller needs to provide an aligned
+fragsz if there is an alignment requirement for the size of the fragment.
+
+.. kernel-doc:: include/linux/page_frag_cache.h
+ :identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
+ __page_frag_alloc_align page_frag_alloc_align page_frag_alloc
+
+.. kernel-doc:: mm/page_frag_cache.c
+ :identifiers: page_frag_cache_drain page_frag_free
+
+Coding examples
+===============
+
+Initialization and draining API
+-------------------------------
+
+.. code-block:: c
+
+ page_frag_cache_init(nc);
+ ...
+ page_frag_cache_drain(nc);
+
+
+Allocation & freeing API
+------------------------
+
+.. code-block:: c
+
+ void *va;
+
+ va = page_frag_alloc_align(nc, size, gfp, align);
+ if (!va)
+ goto do_error;
+
+ err = do_something(va, size);
+ if (err)
+ goto do_error;
+
+ ...
+
+ page_frag_free(va);
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 5ae97f93a0a1..a2b1127e8ac8 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -28,11 +28,28 @@ static inline bool encoded_page_decode_pfmemalloc(unsigned long encoded_page)
return !!(encoded_page & PAGE_FRAG_CACHE_PFMEMALLOC_BIT);
}
+/**
+ * page_frag_cache_init() - Init page_frag cache.
+ * @nc: page_frag cache from which to init
+ *
+ * Inline helper to initialize the page_frag cache.
+ */
static inline void page_frag_cache_init(struct page_frag_cache *nc)
{
nc->encoded_page = 0;
}
+/**
+ * page_frag_cache_is_pfmemalloc() - Check for pfmemalloc.
+ * @nc: page_frag cache from which to check
+ *
+ * Check if the current page in page_frag cache is allocated from the pfmemalloc
+ * reserves. It has the same calling context expectation as the allocation API.
+ *
+ * Return:
+ * true if the current page in page_frag cache is allocated from the pfmemalloc
+ * reserves, otherwise return false.
+ */
static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
{
return encoded_page_decode_pfmemalloc(nc->encoded_page);
@@ -57,6 +74,19 @@ static inline unsigned int __page_frag_cache_commit(struct page_frag_cache *nc,
return __page_frag_cache_commit_noref(nc, pfrag, used_sz);
}
+/**
+ * __page_frag_alloc_align() - Allocate a page fragment with aligning
+ * requirement.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align_mask: the requested aligning requirement for the 'va'
+ *
+ * Allocate a page fragment from page_frag cache with aligning requirement.
+ *
+ * Return:
+ * Virtual address of the page fragment, otherwise return NULL.
+ */
static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
unsigned int fragsz, gfp_t gfp_mask,
unsigned int align_mask)
@@ -72,6 +102,19 @@ static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
return va;
}
+/**
+ * page_frag_alloc_align() - Allocate a page fragment with aligning requirement.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache needs to be refilled
+ * @align: the requested aligning requirement for the fragment
+ *
+ * WARN_ON_ONCE() checking for @align before allocating a page fragment from
+ * page_frag cache with aligning requirement.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
unsigned int fragsz, gfp_t gfp_mask,
unsigned int align)
@@ -80,6 +123,17 @@ static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
}
+/**
+ * page_frag_alloc() - Allocate a page fragment.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Allocate a page fragment from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
static inline void *page_frag_alloc(struct page_frag_cache *nc,
unsigned int fragsz, gfp_t gfp_mask)
{
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index f55d34cf7d43..d014130fb893 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -70,6 +70,10 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
return page;
}
+/**
+ * page_frag_cache_drain - Drain the current page from page_frag cache.
+ * @nc: page_frag cache from which to drain
+ */
void page_frag_cache_drain(struct page_frag_cache *nc)
{
if (!nc->encoded_page)
@@ -182,8 +186,12 @@ void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
}
EXPORT_SYMBOL(__page_frag_cache_prepare);
-/*
- * Frees a page fragment allocated out of either a compound or order 0 page.
+/**
+ * page_frag_free - Free a page fragment.
+ * @addr: va of page fragment to be freed
+ *
+ * Free a page fragment allocated out of either a compound or order 0 page by
+ * virtual address.
*/
void page_frag_free(void *addr)
{
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 04/10] mm: page_frag: introduce page_frag_alloc_abort() related API
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
` (2 preceding siblings ...)
2024-10-28 11:58 ` [PATCH RFC 03/10] mm: page_frag: update documentation for page_frag Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 17:53 ` Alexander Duyck
2024-10-28 11:58 ` [PATCH RFC 05/10] mm: page_frag: introduce refill prepare & commit API Yunsheng Lin
` (5 subsequent siblings)
9 siblings, 1 reply; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM, Jonathan Corbet, linux-doc
For some case as tun_build_skb() without the needing of
using complicated prepare & commit API, add the abort API to
abort the operation of page_frag_alloc_*() related API for
error handling knowing that no one else is taking extra
reference to the just allocated fragment, and add abort_ref
API to only abort the reference counting of the allocated
fragment if it is already referenced by someone else.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
Documentation/mm/page_frags.rst | 7 +++++--
include/linux/page_frag_cache.h | 20 ++++++++++++++++++++
mm/page_frag_cache.c | 21 +++++++++++++++++++++
3 files changed, 46 insertions(+), 2 deletions(-)
diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
index 34e654c2956e..339e641beb53 100644
--- a/Documentation/mm/page_frags.rst
+++ b/Documentation/mm/page_frags.rst
@@ -114,9 +114,10 @@ fragsz if there is an alignment requirement for the size of the fragment.
.. kernel-doc:: include/linux/page_frag_cache.h
:identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
__page_frag_alloc_align page_frag_alloc_align page_frag_alloc
+ page_frag_alloc_abort
.. kernel-doc:: mm/page_frag_cache.c
- :identifiers: page_frag_cache_drain page_frag_free
+ :identifiers: page_frag_cache_drain page_frag_free page_frag_alloc_abort_ref
Coding examples
===============
@@ -143,8 +144,10 @@ Allocation & freeing API
goto do_error;
err = do_something(va, size);
- if (err)
+ if (err) {
+ page_frag_alloc_abort(nc, va, size);
goto do_error;
+ }
...
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index a2b1127e8ac8..c3347c97522c 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -141,5 +141,25 @@ static inline void *page_frag_alloc(struct page_frag_cache *nc,
}
void page_frag_free(void *addr);
+void page_frag_alloc_abort_ref(struct page_frag_cache *nc, void *va,
+ unsigned int fragsz);
+
+/**
+ * page_frag_alloc_abort - Abort the page fragment allocation.
+ * @nc: page_frag cache to which the page fragment is aborted back
+ * @va: virtual address of page fragment to be aborted
+ * @fragsz: size of the page fragment to be aborted
+ *
+ * It is expected to be called from the same context as the allocation API.
+ * Mostly used for error handling cases to abort the fragment allocation knowing
+ * that no one else is taking extra reference to the just aborted fragment, so
+ * that the aborted fragment can be reused.
+ */
+static inline void page_frag_alloc_abort(struct page_frag_cache *nc, void *va,
+ unsigned int fragsz)
+{
+ page_frag_alloc_abort_ref(nc, va, fragsz);
+ nc->offset -= fragsz;
+}
#endif
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index d014130fb893..4d5626da42ed 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -201,3 +201,24 @@ void page_frag_free(void *addr)
free_unref_page(page, compound_order(page));
}
EXPORT_SYMBOL(page_frag_free);
+
+/**
+ * page_frag_alloc_abort_ref - Abort the reference of allocated fragment.
+ * @nc: page_frag cache to which the page fragment is aborted back
+ * @va: virtual address of page fragment to be aborted
+ * @fragsz: size of the page fragment to be aborted
+ *
+ * It is expected to be called from the same context as the allocation API.
+ * Mostly used for error handling cases to abort the reference of allocated
+ * fragment if the fragment has been referenced for other usages, to aovid the
+ * atomic operation of page_frag_free() API.
+ */
+void page_frag_alloc_abort_ref(struct page_frag_cache *nc, void *va,
+ unsigned int fragsz)
+{
+ VM_BUG_ON(va + fragsz !=
+ encoded_page_decode_virt(nc->encoded_page) + nc->offset);
+
+ nc->pagecnt_bias++;
+}
+EXPORT_SYMBOL(page_frag_alloc_abort_ref);
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 05/10] mm: page_frag: introduce refill prepare & commit API
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
` (3 preceding siblings ...)
2024-10-28 11:58 ` [PATCH RFC 04/10] mm: page_frag: introduce page_frag_alloc_abort() related API Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 06/10] mm: page_frag: introduce alloc_refill " Yunsheng Lin
` (4 subsequent siblings)
9 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM, Jonathan Corbet, linux-doc
Currently page_frag only have a alloc API which returns
the virtual address of a fragment by a specific size.
There are many use cases that need minimum memory in order
for forward progress, but more performant if more memory is
available, and expect to use the 'struct page' of the
allocated fragment directly instead of the virtual address.
Currently skb_page_frag_refill() API is used to solve the
above use cases, but caller needs to know about the internal
detail and access the data field of 'struct page_frag' to
meet the requirement of the above use cases and its
implementation is similar to the one in mm subsystem.
To unify those two page_frag implementations, introduce a
prepare API to ensure minimum memory is satisfied and return
how much the actual memory is available to the caller. The
caller needs to either call the commit API to report how much
memory it actually uses, or not do so if deciding to not use
any memory.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
Documentation/mm/page_frags.rst | 43 ++++++++++++-
include/linux/page_frag_cache.h | 110 ++++++++++++++++++++++++++++++++
2 files changed, 152 insertions(+), 1 deletion(-)
diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
index 339e641beb53..4cfdbe7db55a 100644
--- a/Documentation/mm/page_frags.rst
+++ b/Documentation/mm/page_frags.rst
@@ -111,10 +111,18 @@ page is aligned according to the 'align/alignment' parameter. Note the size of
the allocated fragment is not aligned, the caller needs to provide an aligned
fragsz if there is an alignment requirement for the size of the fragment.
+There is a use case that needs minimum memory in order for forward progress, but
+more performant if more memory is available. By using the prepare and commit
+related API, the caller calls prepare API to requests the minimum memory it
+needs and prepare API will return the maximum size of the fragment returned. The
+caller needs to either call the commit API to report how much memory it actually
+uses, or not do so if deciding to not use any memory.
+
.. kernel-doc:: include/linux/page_frag_cache.h
:identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
__page_frag_alloc_align page_frag_alloc_align page_frag_alloc
- page_frag_alloc_abort
+ page_frag_alloc_abort __page_frag_refill_prepare_align
+ page_frag_refill_prepare_align page_frag_refill_prepare
.. kernel-doc:: mm/page_frag_cache.c
:identifiers: page_frag_cache_drain page_frag_free page_frag_alloc_abort_ref
@@ -152,3 +160,36 @@ Allocation & freeing API
...
page_frag_free(va);
+
+
+Refill Preparation & committing API
+-----------------------------------
+
+.. code-block:: c
+
+ struct page_frag page_frag, *pfrag;
+ bool merge = true;
+
+ pfrag = &page_frag;
+ if (!page_frag_refill_prepare(nc, 32U, pfrag, GFP_KERNEL))
+ goto wait_for_space;
+
+ copy = min_t(unsigned int, copy, pfrag->size);
+ if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) {
+ if (i >= max_skb_frags)
+ goto new_segment;
+
+ merge = false;
+ }
+
+ copy = mem_schedule(copy);
+ if (!copy)
+ goto wait_for_space;
+
+ if (merge) {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+ page_frag_refill_commit_noref(nc, pfrag, copy);
+ } else {
+ skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy);
+ page_frag_refill_commit(nc, pfrag, copy);
+ }
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index c3347c97522c..1e699334646a 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -140,6 +140,116 @@ static inline void *page_frag_alloc(struct page_frag_cache *nc,
return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
}
+/**
+ * __page_frag_refill_prepare_align() - Prepare refilling a page_frag with
+ * aligning requirement.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align_mask: the requested aligning requirement for the fragment
+ *
+ * Prepare refilling a page_frag from page_frag cache with aligning requirement.
+ *
+ * Return:
+ * True if prepare refilling succeeds, otherwise return false.
+ */
+static inline bool __page_frag_refill_prepare_align(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag,
+ gfp_t gfp_mask,
+ unsigned int align_mask)
+{
+ return !!__page_frag_cache_prepare(nc, fragsz, pfrag, gfp_mask,
+ align_mask);
+}
+
+/**
+ * page_frag_refill_prepare_align() - Prepare refilling a page_frag with
+ * aligning requirement.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache needs to be refilled
+ * @align: the requested aligning requirement for the fragment
+ *
+ * WARN_ON_ONCE() checking for @align before prepare refilling a page_frag from
+ * page_frag cache with aligning requirement.
+ *
+ * Return:
+ * True if prepare refilling succeeds, otherwise return false.
+ */
+static inline bool page_frag_refill_prepare_align(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag,
+ gfp_t gfp_mask,
+ unsigned int align)
+{
+ WARN_ON_ONCE(!is_power_of_2(align));
+ return __page_frag_refill_prepare_align(nc, fragsz, pfrag, gfp_mask,
+ -align);
+}
+
+/**
+ * page_frag_refill_prepare() - Prepare refilling a page_frag.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Prepare refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * True if refill succeeds, otherwise return false.
+ */
+static inline bool page_frag_refill_prepare(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag,
+ gfp_t gfp_mask)
+{
+ return __page_frag_refill_prepare_align(nc, fragsz, pfrag, gfp_mask,
+ ~0u);
+}
+
+/**
+ * page_frag_refill_commit - Commit a prepare refilling.
+ * @nc: page_frag cache from which to commit
+ * @pfrag: the page_frag to be committed
+ * @used_sz: size of the page fragment has been used
+ *
+ * Commit the actual used size for the refill that was prepared.
+ *
+ * Return:
+ * The true size of the fragment considering the offset alignment.
+ */
+static inline unsigned int page_frag_refill_commit(struct page_frag_cache *nc,
+ struct page_frag *pfrag,
+ unsigned int used_sz)
+{
+ return __page_frag_cache_commit(nc, pfrag, used_sz);
+}
+
+/**
+ * page_frag_refill_commit_noref - Commit a prepare refilling without taking
+ * refcount.
+ * @nc: page_frag cache from which to commit
+ * @pfrag: the page_frag to be committed
+ * @used_sz: size of the page fragment has been used
+ *
+ * Commit the prepare refilling by passing the actual used size, but not taking
+ * refcount. Mostly used for fragmemt coalescing case when the current fragment
+ * can share the same refcount with previous fragment.
+ *
+ * Return:
+ * The true size of the fragment considering the offset alignment.
+ */
+static inline unsigned int
+page_frag_refill_commit_noref(struct page_frag_cache *nc,
+ struct page_frag *pfrag, unsigned int used_sz)
+{
+ return __page_frag_cache_commit_noref(nc, pfrag, used_sz);
+}
+
void page_frag_free(void *addr);
void page_frag_alloc_abort_ref(struct page_frag_cache *nc, void *va,
unsigned int fragsz);
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 06/10] mm: page_frag: introduce alloc_refill prepare & commit API
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
` (4 preceding siblings ...)
2024-10-28 11:58 ` [PATCH RFC 05/10] mm: page_frag: introduce refill prepare & commit API Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 07/10] mm: page_frag: introduce probe related API Yunsheng Lin
` (3 subsequent siblings)
9 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM, Jonathan Corbet, linux-doc
Currently alloc related API returns virtual address of the
allocated fragment and refill related API returns page info
of the allocated fragment through 'struct page_frag'.
There are use cases that need both the virtual address and
page info of the allocated fragment. Introduce alloc_refill
API for those use cases.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
Documentation/mm/page_frags.rst | 45 +++++++++++++++++++++
include/linux/page_frag_cache.h | 71 +++++++++++++++++++++++++++++++++
2 files changed, 116 insertions(+)
diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
index 4cfdbe7db55a..dcfceee3b923 100644
--- a/Documentation/mm/page_frags.rst
+++ b/Documentation/mm/page_frags.rst
@@ -111,6 +111,9 @@ page is aligned according to the 'align/alignment' parameter. Note the size of
the allocated fragment is not aligned, the caller needs to provide an aligned
fragsz if there is an alignment requirement for the size of the fragment.
+Depending on different use cases, callers expecting to deal with va, or both va
+and page may call alloc or alloc_refill API accordingly.
+
There is a use case that needs minimum memory in order for forward progress, but
more performant if more memory is available. By using the prepare and commit
related API, the caller calls prepare API to requests the minimum memory it
@@ -123,6 +126,9 @@ uses, or not do so if deciding to not use any memory.
__page_frag_alloc_align page_frag_alloc_align page_frag_alloc
page_frag_alloc_abort __page_frag_refill_prepare_align
page_frag_refill_prepare_align page_frag_refill_prepare
+ __page_frag_alloc_refill_prepare_align
+ page_frag_alloc_refill_prepare_align
+ page_frag_alloc_refill_prepare
.. kernel-doc:: mm/page_frag_cache.c
:identifiers: page_frag_cache_drain page_frag_free page_frag_alloc_abort_ref
@@ -193,3 +199,42 @@ Refill Preparation & committing API
skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy);
page_frag_refill_commit(nc, pfrag, copy);
}
+
+
+Alloc_Refill Preparation & committing API
+-----------------------------------------
+
+.. code-block:: c
+
+ struct page_frag page_frag, *pfrag;
+ bool merge = true;
+ void *va;
+
+ pfrag = &page_frag;
+ va = page_frag_alloc_refill_prepare(nc, 32U, pfrag, GFP_KERNEL);
+ if (!va)
+ goto wait_for_space;
+
+ copy = min_t(unsigned int, copy, pfrag->size);
+ if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) {
+ if (i >= max_skb_frags)
+ goto new_segment;
+
+ merge = false;
+ }
+
+ copy = mem_schedule(copy);
+ if (!copy)
+ goto wait_for_space;
+
+ err = copy_from_iter_full_nocache(va, copy, iter);
+ if (err)
+ goto do_error;
+
+ if (merge) {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+ page_frag_refill_commit_noref(nc, pfrag, copy);
+ } else {
+ skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy);
+ page_frag_refill_commit(nc, pfrag, copy);
+ }
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 1e699334646a..329390afbe78 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -211,6 +211,77 @@ static inline bool page_frag_refill_prepare(struct page_frag_cache *nc,
~0u);
}
+/**
+ * __page_frag_alloc_refill_prepare_align() - Prepare allocating a fragment and
+ * refilling a page_frag with aligning requirement.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align_mask: the requested aligning requirement for the fragment.
+ *
+ * Prepare allocating a fragment and refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
+static inline void
+*__page_frag_alloc_refill_prepare_align(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag,
+ gfp_t gfp_mask, unsigned int align_mask)
+{
+ return __page_frag_cache_prepare(nc, fragsz, pfrag, gfp_mask, align_mask);
+}
+
+/**
+ * page_frag_alloc_refill_prepare_align() - Prepare allocating a fragment and
+ * refilling a page_frag with aligning requirement.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align: the requested aligning requirement for the fragment.
+ *
+ * WARN_ON_ONCE() checking for @align before prepare allocating a fragment and
+ * refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
+static inline void
+*page_frag_alloc_refill_prepare_align(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag, gfp_t gfp_mask,
+ unsigned int align)
+{
+ WARN_ON_ONCE(!is_power_of_2(align));
+ return __page_frag_alloc_refill_prepare_align(nc, fragsz, pfrag,
+ gfp_mask, -align);
+}
+
+/**
+ * page_frag_alloc_refill_prepare() - Prepare allocating a fragment and
+ * refilling a page_frag.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Prepare allocating a fragment and refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
+static inline void *page_frag_alloc_refill_prepare(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag,
+ gfp_t gfp_mask)
+{
+ return __page_frag_alloc_refill_prepare_align(nc, fragsz, pfrag,
+ gfp_mask, ~0u);
+}
+
/**
* page_frag_refill_commit - Commit a prepare refilling.
* @nc: page_frag cache from which to commit
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 07/10] mm: page_frag: introduce probe related API
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
` (5 preceding siblings ...)
2024-10-28 11:58 ` [PATCH RFC 06/10] mm: page_frag: introduce alloc_refill " Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 08/10] mm: page_frag: add testing for the newly added API Yunsheng Lin
` (2 subsequent siblings)
9 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM, Jonathan Corbet, linux-doc
Some usecase may need a bigger fragment if current fragment
can't be coalesced to previous fragment because more space
for some header may be needed if it is a new fragment. So
introduce probe related API to tell if there are minimum
remaining memory in the cache to be coalesced to the previous
fragment, in order to save memory as much as possible.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
Documentation/mm/page_frags.rst | 10 +++++++-
include/linux/page_frag_cache.h | 41 +++++++++++++++++++++++++++++++++
mm/page_frag_cache.c | 35 ++++++++++++++++++++++++++++
3 files changed, 85 insertions(+), 1 deletion(-)
diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
index dcfceee3b923..c39b3daa5ca5 100644
--- a/Documentation/mm/page_frags.rst
+++ b/Documentation/mm/page_frags.rst
@@ -119,7 +119,13 @@ more performant if more memory is available. By using the prepare and commit
related API, the caller calls prepare API to requests the minimum memory it
needs and prepare API will return the maximum size of the fragment returned. The
caller needs to either call the commit API to report how much memory it actually
-uses, or not do so if deciding to not use any memory.
+uses, or not do so if deciding to not use any memory. Some usecase may need a
+bigger fragment if the current fragment can't be coalesced to previous fragment
+because more space for some header may be needed if it is a new fragment, probe
+related API can be used to tell if there are minimum remaining memory in the
+cache to be coalesced to the previous fragment, in order to save memory as much
+as possible.
+
.. kernel-doc:: include/linux/page_frag_cache.h
:identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
@@ -129,9 +135,11 @@ uses, or not do so if deciding to not use any memory.
__page_frag_alloc_refill_prepare_align
page_frag_alloc_refill_prepare_align
page_frag_alloc_refill_prepare
+ page_frag_alloc_refill_probe page_frag_refill_probe
.. kernel-doc:: mm/page_frag_cache.c
:identifiers: page_frag_cache_drain page_frag_free page_frag_alloc_abort_ref
+ __page_frag_alloc_refill_probe_align
Coding examples
===============
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 329390afbe78..0f7e8da91a67 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -63,6 +63,10 @@ void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
struct page_frag *pfrag,
unsigned int used_sz);
+void *__page_frag_alloc_refill_probe_align(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag,
+ unsigned int align_mask);
static inline unsigned int __page_frag_cache_commit(struct page_frag_cache *nc,
struct page_frag *pfrag,
@@ -282,6 +286,43 @@ static inline void *page_frag_alloc_refill_prepare(struct page_frag_cache *nc,
gfp_mask, ~0u);
}
+/**
+ * page_frag_alloc_refill_probe() - Probe allocating a fragment and refilling
+ * a page_frag.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled
+ *
+ * Probe allocating a fragment and refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
+static inline void *page_frag_alloc_refill_probe(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag)
+{
+ return __page_frag_alloc_refill_probe_align(nc, fragsz, pfrag, ~0u);
+}
+
+/**
+ * page_frag_refill_probe() - Probe refilling a page_frag.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled
+ *
+ * Probe refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * True if refill succeeds, otherwise return false.
+ */
+static inline bool page_frag_refill_probe(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag)
+{
+ return !!page_frag_alloc_refill_probe(nc, fragsz, pfrag);
+}
+
/**
* page_frag_refill_commit - Commit a prepare refilling.
* @nc: page_frag cache from which to commit
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 4d5626da42ed..c2902bdf7350 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -116,6 +116,41 @@ unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
}
EXPORT_SYMBOL(__page_frag_cache_commit_noref);
+/**
+ * __page_frag_alloc_refill_probe_align() - Probe allocating a fragment and
+ * refilling a page_frag with aligning requirement.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @align_mask: the requested aligning requirement for the fragment.
+ *
+ * Probe allocating a fragment and refilling a page_frag from page_frag cache
+ * with aligning requirement.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
+void *__page_frag_alloc_refill_probe_align(struct page_frag_cache *nc,
+ unsigned int fragsz,
+ struct page_frag *pfrag,
+ unsigned int align_mask)
+{
+ unsigned long encoded_page = nc->encoded_page;
+ unsigned int size, offset;
+
+ size = PAGE_SIZE << encoded_page_decode_order(encoded_page);
+ offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask);
+ if (unlikely(!encoded_page || offset + fragsz > size))
+ return NULL;
+
+ pfrag->page = encoded_page_decode_page(encoded_page);
+ pfrag->size = size - offset;
+ pfrag->offset = offset;
+
+ return encoded_page_decode_virt(encoded_page) + offset;
+}
+EXPORT_SYMBOL(__page_frag_alloc_refill_probe_align);
+
void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
struct page_frag *pfrag, gfp_t gfp_mask,
unsigned int align_mask)
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 08/10] mm: page_frag: add testing for the newly added API
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
` (6 preceding siblings ...)
2024-10-28 11:58 ` [PATCH RFC 07/10] mm: page_frag: introduce probe related API Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 09/10] net: replace page_frag with page_frag_cache Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag Yunsheng Lin
9 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM, Shuah Khan, linux-kselftest
Add testing for the newly added prepare API, for both aligned
and non-aligned API, also probe API is also tested along with
prepare API.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
.../selftests/mm/page_frag/page_frag_test.c | 76 +++++++++++++++++--
tools/testing/selftests/mm/run_vmtests.sh | 4 +
tools/testing/selftests/mm/test_page_frag.sh | 27 +++++++
3 files changed, 102 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c
index e806c1866e36..3b3c32389def 100644
--- a/tools/testing/selftests/mm/page_frag/page_frag_test.c
+++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c
@@ -32,6 +32,10 @@ static bool test_align;
module_param(test_align, bool, 0);
MODULE_PARM_DESC(test_align, "use align API for testing");
+static bool test_prepare;
+module_param(test_prepare, bool, 0);
+MODULE_PARM_DESC(test_prepare, "use prepare API for testing");
+
static int test_alloc_len = 2048;
module_param(test_alloc_len, int, 0);
MODULE_PARM_DESC(test_alloc_len, "alloc len for testing");
@@ -74,6 +78,21 @@ static int page_frag_pop_thread(void *arg)
return 0;
}
+static void frag_frag_test_commit(struct page_frag_cache *nc,
+ struct page_frag *prepare_pfrag,
+ struct page_frag *probe_pfrag,
+ unsigned int used_sz)
+{
+ if (prepare_pfrag->page != probe_pfrag->page ||
+ prepare_pfrag->offset != probe_pfrag->offset ||
+ prepare_pfrag->size != probe_pfrag->size) {
+ force_exit = true;
+ WARN_ONCE(true, TEST_FAILED_PREFIX "wrong probed info\n");
+ }
+
+ page_frag_refill_commit(nc, prepare_pfrag, used_sz);
+}
+
static int page_frag_push_thread(void *arg)
{
struct ptr_ring *ring = arg;
@@ -86,15 +105,61 @@ static int page_frag_push_thread(void *arg)
int ret;
if (test_align) {
- va = page_frag_alloc_align(&test_nc, test_alloc_len,
- GFP_KERNEL, SMP_CACHE_BYTES);
+ if (test_prepare) {
+ struct page_frag prepare_frag, probe_frag;
+ void *probe_va;
+
+ va = page_frag_alloc_refill_prepare_align(&test_nc,
+ test_alloc_len,
+ &prepare_frag,
+ GFP_KERNEL,
+ SMP_CACHE_BYTES);
+
+ probe_va = __page_frag_alloc_refill_probe_align(&test_nc,
+ test_alloc_len,
+ &probe_frag,
+ -SMP_CACHE_BYTES);
+ if (va != probe_va) {
+ force_exit = true;
+ WARN_ONCE(true, TEST_FAILED_PREFIX "wrong va\n");
+ }
+
+ if (likely(va))
+ frag_frag_test_commit(&test_nc, &prepare_frag,
+ &probe_frag, test_alloc_len);
+ } else {
+ va = page_frag_alloc_align(&test_nc,
+ test_alloc_len,
+ GFP_KERNEL,
+ SMP_CACHE_BYTES);
+ }
if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) {
force_exit = true;
WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n");
}
} else {
- va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL);
+ if (test_prepare) {
+ struct page_frag prepare_frag, probe_frag;
+ void *probe_va;
+
+ va = page_frag_alloc_refill_prepare(&test_nc, test_alloc_len,
+ &prepare_frag, GFP_KERNEL);
+
+ probe_va = page_frag_alloc_refill_probe(&test_nc, test_alloc_len,
+ &probe_frag);
+
+ if (va != probe_va) {
+ force_exit = true;
+ WARN_ONCE(true, TEST_FAILED_PREFIX "wrong va\n");
+ }
+
+ if (likely(va))
+ frag_frag_test_commit(&test_nc, &prepare_frag,
+ &probe_frag, test_alloc_len);
+ } else {
+ va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL);
+ }
}
if (!va)
@@ -176,8 +241,9 @@ static int __init page_frag_test_init(void)
}
duration = (u64)ktime_us_delta(ktime_get(), start);
- pr_info("%d of iterations for %s testing took: %lluus\n", nr_test,
- test_align ? "aligned" : "non-aligned", duration);
+ pr_info("%d of iterations for %s %s API testing took: %lluus\n", nr_test,
+ test_align ? "aligned" : "non-aligned",
+ test_prepare ? "prepare" : "alloc", duration);
out:
ptr_ring_cleanup(&ptr_ring, NULL);
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 2c5394584af4..f6ff9080a6f2 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -464,6 +464,10 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh aligned
CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned
+CATEGORY="page_frag" run_test ./test_page_frag.sh aligned_prepare
+
+CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned_prepare
+
echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix
echo "1..${count_total}" | tap_output
diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh
index f55b105084cf..1c757fd11844 100755
--- a/tools/testing/selftests/mm/test_page_frag.sh
+++ b/tools/testing/selftests/mm/test_page_frag.sh
@@ -43,6 +43,8 @@ check_test_failed_prefix() {
SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1"
NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST"
ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1"
+NONALIGNED_PREPARE_PARAM="$NONALIGNED_PARAM test_prepare=1"
+ALIGNED_PREPARE_PARAM="$ALIGNED_PARAM test_prepare=1"
check_test_requirements()
{
@@ -77,6 +79,20 @@ run_aligned_check()
insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1
}
+run_nonaligned_prepare_check()
+{
+ echo "Run performance tests to evaluate how fast nonaligned prepare API is."
+
+ insmod $DRIVER $NONALIGNED_PREPARE_PARAM > /dev/null 2>&1
+}
+
+run_aligned_prepare_check()
+{
+ echo "Run performance tests to evaluate how fast aligned prepare API is."
+
+ insmod $DRIVER $ALIGNED_PREPARE_PARAM > /dev/null 2>&1
+}
+
run_smoke_check()
{
echo "Run smoke test."
@@ -87,6 +103,7 @@ run_smoke_check()
usage()
{
echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | "
+ echo "[ aligned_prepare ] | [ nonaligned_prepare ] | "
echo "manual parameters"
echo
echo "Valid tests and parameters:"
@@ -107,6 +124,12 @@ usage()
echo "# Performance testing for aligned alloc API"
echo "$0 aligned"
echo
+ echo "# Performance testing for nonaligned prepare API"
+ echo "$0 nonaligned_prepare"
+ echo
+ echo "# Performance testing for aligned prepare API"
+ echo "$0 aligned_prepare"
+ echo
exit 0
}
@@ -158,6 +181,10 @@ function run_test()
run_nonaligned_check
elif [[ "$1" = "aligned" ]]; then
run_aligned_check
+ elif [[ "$1" = "nonaligned_prepare" ]]; then
+ run_nonaligned_prepare_check
+ elif [[ "$1" = "aligned_prepare" ]]; then
+ run_aligned_prepare_check
else
run_manual_check $@
fi
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 09/10] net: replace page_frag with page_frag_cache
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
` (7 preceding siblings ...)
2024-10-28 11:58 ` [PATCH RFC 08/10] mm: page_frag: add testing for the newly added API Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag Yunsheng Lin
9 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM, Ayush Sawal, Andrew Lunn, Eric Dumazet,
Willem de Bruijn, Jason Wang, Ingo Molnar, Peter Zijlstra,
Juri Lelli, Vincent Guittot, Dietmar Eggemann, Steven Rostedt,
Ben Segall, Mel Gorman, Valentin Schneider, Simon Horman,
John Fastabend, Jakub Sitnicki, David Ahern, Matthieu Baerts,
Mat Martineau, Geliang Tang, Boris Pismenny, bpf, mptcp
Use the newly introduced prepare/probe/commit API to
replace page_frag with page_frag_cache for sk_page_frag().
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
.../chelsio/inline_crypto/chtls/chtls.h | 3 -
.../chelsio/inline_crypto/chtls/chtls_io.c | 101 +++++-------------
.../chelsio/inline_crypto/chtls/chtls_main.c | 3 -
drivers/net/tun.c | 47 ++++----
include/linux/sched.h | 2 +-
include/net/sock.h | 21 ++--
kernel/exit.c | 3 +-
kernel/fork.c | 3 +-
net/core/skbuff.c | 58 +++++-----
net/core/skmsg.c | 12 ++-
net/core/sock.c | 32 ++++--
net/ipv4/ip_output.c | 28 +++--
net/ipv4/tcp.c | 23 ++--
net/ipv4/tcp_output.c | 25 +++--
net/ipv6/ip6_output.c | 28 +++--
net/kcm/kcmsock.c | 18 ++--
net/mptcp/protocol.c | 47 ++++----
net/tls/tls_device.c | 100 ++++++++++-------
18 files changed, 293 insertions(+), 261 deletions(-)
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
index 21e0dfeff158..85ce0b2f1f3f 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
@@ -234,7 +234,6 @@ struct chtls_dev {
struct list_head list_node;
struct list_head rcu_node;
struct list_head na_node;
- unsigned int send_page_order;
int max_host_sndbuf;
u32 round_robin_cnt;
struct key_map kmap;
@@ -453,8 +452,6 @@ enum {
/* The ULP mode/submode of an skbuff */
#define skb_ulp_mode(skb) (ULP_SKB_CB(skb)->ulp_mode)
-#define TCP_PAGE(sk) (sk->sk_frag.page)
-#define TCP_OFF(sk) (sk->sk_frag.offset)
static inline struct chtls_dev *to_chtls_dev(struct tls_toe_device *tlsdev)
{
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
index d567e42e1760..7b1760ab55ba 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
@@ -825,12 +825,6 @@ void skb_entail(struct sock *sk, struct sk_buff *skb, int flags)
ULP_SKB_CB(skb)->flags = flags;
__skb_queue_tail(&csk->txq, skb);
sk->sk_wmem_queued += skb->truesize;
-
- if (TCP_PAGE(sk) && TCP_OFF(sk)) {
- put_page(TCP_PAGE(sk));
- TCP_PAGE(sk) = NULL;
- TCP_OFF(sk) = 0;
- }
}
static struct sk_buff *get_tx_skb(struct sock *sk, int size)
@@ -882,16 +876,12 @@ static void push_frames_if_head(struct sock *sk)
chtls_push_frames(csk, 1);
}
-static int chtls_skb_copy_to_page_nocache(struct sock *sk,
- struct iov_iter *from,
- struct sk_buff *skb,
- struct page *page,
- int off, int copy)
+static int chtls_skb_copy_to_va_nocache(struct sock *sk, struct iov_iter *from,
+ struct sk_buff *skb, char *va, int copy)
{
int err;
- err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) +
- off, copy, skb->len);
+ err = skb_do_copy_data_nocache(sk, skb, from, va, copy, skb->len);
if (err)
return err;
@@ -1114,82 +1104,45 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
if (err)
goto do_fault;
} else {
+ struct page_frag_cache *nc = &sk->sk_frag;
+ struct page_frag page_frag, *pfrag;
int i = skb_shinfo(skb)->nr_frags;
- struct page *page = TCP_PAGE(sk);
- int pg_size = PAGE_SIZE;
- int off = TCP_OFF(sk);
- bool merge;
-
- if (page)
- pg_size = page_size(page);
- if (off < pg_size &&
- skb_can_coalesce(skb, i, page, off)) {
+ bool merge = false;
+ void *va;
+
+ pfrag = &page_frag;
+ va = page_frag_alloc_refill_prepare(nc, 32U, pfrag,
+ sk->sk_allocation);
+ if (unlikely(!va))
+ goto wait_for_memory;
+
+ if (skb_can_coalesce(skb, i, pfrag->page,
+ pfrag->offset))
merge = true;
- goto copy;
- }
- merge = false;
- if (i == (is_tls_tx(csk) ? (MAX_SKB_FRAGS - 1) :
- MAX_SKB_FRAGS))
+ else if (i == (is_tls_tx(csk) ? (MAX_SKB_FRAGS - 1) :
+ MAX_SKB_FRAGS))
goto new_buf;
- if (page && off == pg_size) {
- put_page(page);
- TCP_PAGE(sk) = page = NULL;
- pg_size = PAGE_SIZE;
- }
-
- if (!page) {
- gfp_t gfp = sk->sk_allocation;
- int order = cdev->send_page_order;
-
- if (order) {
- page = alloc_pages(gfp | __GFP_COMP |
- __GFP_NOWARN |
- __GFP_NORETRY,
- order);
- if (page)
- pg_size <<= order;
- }
- if (!page) {
- page = alloc_page(gfp);
- pg_size = PAGE_SIZE;
- }
- if (!page)
- goto wait_for_memory;
- off = 0;
- }
-copy:
- if (copy > pg_size - off)
- copy = pg_size - off;
+ copy = min_t(int, copy, pfrag->size);
if (is_tls_tx(csk))
copy = min_t(int, copy, csk->tlshws.txleft);
- err = chtls_skb_copy_to_page_nocache(sk, &msg->msg_iter,
- skb, page,
- off, copy);
- if (unlikely(err)) {
- if (!TCP_PAGE(sk)) {
- TCP_PAGE(sk) = page;
- TCP_OFF(sk) = 0;
- }
+ err = chtls_skb_copy_to_va_nocache(sk, &msg->msg_iter,
+ skb, va, copy);
+ if (unlikely(err))
goto do_fault;
- }
+
/* Update the skb. */
if (merge) {
skb_frag_size_add(
&skb_shinfo(skb)->frags[i - 1],
copy);
+ page_frag_refill_commit_noref(nc, pfrag, copy);
} else {
- skb_fill_page_desc(skb, i, page, off, copy);
- if (off + copy < pg_size) {
- /* space left keep page */
- get_page(page);
- TCP_PAGE(sk) = page;
- } else {
- TCP_PAGE(sk) = NULL;
- }
+ skb_fill_page_desc(skb, i, pfrag->page,
+ pfrag->offset, copy);
+ page_frag_refill_commit(nc, pfrag, copy);
}
- TCP_OFF(sk) = off + copy;
}
if (unlikely(skb->len == mss))
tx_skb_finalize(skb);
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
index 96fd31d75dfd..7284269174c5 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
@@ -34,7 +34,6 @@ static DEFINE_MUTEX(notify_mutex);
static RAW_NOTIFIER_HEAD(listen_notify_list);
static struct proto chtls_cpl_prot, chtls_cpl_protv6;
struct request_sock_ops chtls_rsk_ops, chtls_rsk_opsv6;
-static uint send_page_order = (14 - PAGE_SHIFT < 0) ? 0 : 14 - PAGE_SHIFT;
static void register_listen_notifier(struct notifier_block *nb)
{
@@ -273,8 +272,6 @@ static void *chtls_uld_add(const struct cxgb4_lld_info *info)
INIT_WORK(&cdev->deferq_task, process_deferq);
spin_lock_init(&cdev->listen_lock);
spin_lock_init(&cdev->idr_lock);
- cdev->send_page_order = min_t(uint, get_order(32768),
- send_page_order);
cdev->max_host_sndbuf = 48 * 1024;
if (lldi->vr->key.size)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d7a865ef370b..4ca6590ef5fe 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1599,21 +1599,19 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile,
}
static struct sk_buff *__tun_build_skb(struct tun_file *tfile,
- struct page_frag *alloc_frag, char *buf,
- int buflen, int len, int pad)
+ char *buf, int buflen, int len, int pad)
{
struct sk_buff *skb = build_skb(buf, buflen);
- if (!skb)
+ if (!skb) {
+ page_frag_free(buf);
return ERR_PTR(-ENOMEM);
+ }
skb_reserve(skb, pad);
skb_put(skb, len);
skb_set_owner_w(skb, tfile->socket.sk);
- get_page(alloc_frag->page);
- alloc_frag->offset += buflen;
-
return skb;
}
@@ -1661,8 +1659,8 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
struct virtio_net_hdr *hdr,
int len, int *skb_xdp)
{
- struct page_frag *alloc_frag = ¤t->task_frag;
struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
+ struct page_frag_cache *nc = ¤t->task_frag;
struct bpf_prog *xdp_prog;
int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
char *buf;
@@ -1677,16 +1675,16 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
buflen += SKB_DATA_ALIGN(len + pad);
rcu_read_unlock();
- alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES);
- if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL)))
+ buf = page_frag_alloc_align(nc, buflen, GFP_KERNEL,
+ SMP_CACHE_BYTES);
+ if (unlikely(!buf))
return ERR_PTR(-ENOMEM);
- buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
- copied = copy_page_from_iter(alloc_frag->page,
- alloc_frag->offset + pad,
- len, from);
- if (copied != len)
+ copied = copy_from_iter(buf + pad, len, from);
+ if (copied != len) {
+ page_frag_alloc_abort(nc, buf, buflen);
return ERR_PTR(-EFAULT);
+ }
/* There's a small window that XDP may be set after the check
* of xdp_prog above, this should be rare and for simplicity
@@ -1694,8 +1692,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
*/
if (hdr->gso_type || !xdp_prog) {
*skb_xdp = 1;
- return __tun_build_skb(tfile, alloc_frag, buf, buflen, len,
- pad);
+ return __tun_build_skb(tfile, buf, buflen, len, pad);
}
*skb_xdp = 0;
@@ -1712,21 +1709,23 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
xdp_prepare_buff(&xdp, buf, pad, len, false);
act = bpf_prog_run_xdp(xdp_prog, &xdp);
- if (act == XDP_REDIRECT || act == XDP_TX) {
- get_page(alloc_frag->page);
- alloc_frag->offset += buflen;
- }
err = tun_xdp_act(tun, xdp_prog, &xdp, act);
if (err < 0) {
- if (act == XDP_REDIRECT || act == XDP_TX)
- put_page(alloc_frag->page);
+ if (act == XDP_REDIRECT || act == XDP_TX) {
+ page_frag_alloc_abort_ref(nc, buf, buflen);
+ goto out;
+ }
+
+ page_frag_alloc_abort(nc, buf, buflen);
goto out;
}
if (err == XDP_REDIRECT)
xdp_do_flush();
- if (err != XDP_PASS)
+ if (err != XDP_PASS) {
+ page_frag_alloc_abort(nc, buf, buflen);
goto out;
+ }
pad = xdp.data - xdp.data_hard_start;
len = xdp.data_end - xdp.data;
@@ -1735,7 +1734,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
rcu_read_unlock();
local_bh_enable();
- return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
+ return __tun_build_skb(tfile, buf, buflen, len, pad);
out:
bpf_net_ctx_clear(bpf_net_ctx);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bb343136ddd0..957ad219e509 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1379,7 +1379,7 @@ struct task_struct {
/* Cache last used pipe for splice(): */
struct pipe_inode_info *splice_pipe;
- struct page_frag task_frag;
+ struct page_frag_cache task_frag;
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info *delays;
diff --git a/include/net/sock.h b/include/net/sock.h
index cf037c870e3b..9b24f53c29e7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -303,7 +303,7 @@ struct sk_filter;
* @sk_stamp: time stamp of last packet received
* @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
* @sk_tsflags: SO_TIMESTAMPING flags
- * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag.
+ * @sk_use_task_frag: allow sk_page_frag_cache() to use current->task_frag.
* Sockets that can be used under memory reclaim should
* set this to false.
* @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock
@@ -462,7 +462,7 @@ struct sock {
struct sk_buff_head sk_write_queue;
u32 sk_dst_pending_confirm;
u32 sk_pacing_status; /* see enum sk_pacing */
- struct page_frag sk_frag;
+ struct page_frag_cache sk_frag;
struct timer_list sk_timer;
unsigned long sk_pacing_rate; /* bytes per second */
@@ -2491,22 +2491,22 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk)
}
/**
- * sk_page_frag - return an appropriate page_frag
+ * sk_page_frag_cache - return an appropriate page_frag_cache
* @sk: socket
*
- * Use the per task page_frag instead of the per socket one for
+ * Use the per task page_frag_cache instead of the per socket one for
* optimization when we know that we're in process context and own
* everything that's associated with %current.
*
* Both direct reclaim and page faults can nest inside other
- * socket operations and end up recursing into sk_page_frag()
- * while it's already in use: explicitly avoid task page_frag
+ * socket operations and end up recursing into sk_page_frag_cache()
+ * while it's already in use: explicitly avoid task page_frag_cache
* when users disable sk_use_task_frag.
*
* Return: a per task page_frag if context allows that,
* otherwise a per socket one.
*/
-static inline struct page_frag *sk_page_frag(struct sock *sk)
+static inline struct page_frag_cache *sk_page_frag_cache(struct sock *sk)
{
if (sk->sk_use_task_frag)
return ¤t->task_frag;
@@ -2514,7 +2514,12 @@ static inline struct page_frag *sk_page_frag(struct sock *sk)
return &sk->sk_frag;
}
-bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
+bool sk_page_frag_refill_prepare(struct sock *sk, struct page_frag_cache *nc,
+ struct page_frag *pfrag);
+
+void *sk_page_frag_alloc_refill_prepare(struct sock *sk,
+ struct page_frag_cache *nc,
+ struct page_frag *pfrag);
/*
* Default write policy as shown to user space via poll/select/SIGIO
diff --git a/kernel/exit.c b/kernel/exit.c
index 619f0014c33b..5f9b7f58098d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -974,8 +974,7 @@ void __noreturn do_exit(long code)
if (tsk->splice_pipe)
free_pipe_info(tsk->splice_pipe);
- if (tsk->task_frag.page)
- put_page(tsk->task_frag.page);
+ page_frag_cache_drain(&tsk->task_frag);
exit_task_stack_account(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 89ceb4a68af2..38be5b6e160a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -81,6 +81,7 @@
#include <linux/tty.h>
#include <linux/fs_struct.h>
#include <linux/magic.h>
+#include <linux/page_frag_cache.h>
#include <linux/perf_event.h>
#include <linux/posix-timers.h>
#include <linux/user-return-notifier.h>
@@ -1159,10 +1160,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
tsk->btrace_seq = 0;
#endif
tsk->splice_pipe = NULL;
- tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
tsk->worker_private = NULL;
+ page_frag_cache_init(&tsk->task_frag);
kcov_task_init(tsk);
kmsan_task_create(tsk);
kmap_local_fork(tsk);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6841e61a6bd0..684cd68ca4ab 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3062,25 +3062,6 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
put_page(spd->pages[i]);
}
-static struct page *linear_to_page(struct page *page, unsigned int *len,
- unsigned int *offset,
- struct sock *sk)
-{
- struct page_frag *pfrag = sk_page_frag(sk);
-
- if (!sk_page_frag_refill(sk, pfrag))
- return NULL;
-
- *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset);
-
- memcpy(page_address(pfrag->page) + pfrag->offset,
- page_address(page) + *offset, *len);
- *offset = pfrag->offset;
- pfrag->offset += *len;
-
- return pfrag->page;
-}
-
static bool spd_can_coalesce(const struct splice_pipe_desc *spd,
struct page *page,
unsigned int offset)
@@ -3091,6 +3072,37 @@ static bool spd_can_coalesce(const struct splice_pipe_desc *spd,
spd->partial[spd->nr_pages - 1].len == offset);
}
+static bool spd_fill_linear_page(struct splice_pipe_desc *spd,
+ struct page *page, unsigned int offset,
+ unsigned int *len, struct sock *sk)
+{
+ struct page_frag_cache *nc = sk_page_frag_cache(sk);
+ struct page_frag page_frag, *pfrag;
+ void *va;
+
+ pfrag = &page_frag;
+ va = sk_page_frag_alloc_refill_prepare(sk, nc, pfrag);
+ if (!va)
+ return true;
+
+ *len = min_t(unsigned int, *len, pfrag->size);
+ memcpy(va, page_address(page) + offset, *len);
+
+ if (spd_can_coalesce(spd, pfrag->page, pfrag->offset)) {
+ spd->partial[spd->nr_pages - 1].len += *len;
+ page_frag_refill_commit_noref(nc, pfrag, *len);
+ return false;
+ }
+
+ page_frag_refill_commit(nc, pfrag, *len);
+ spd->pages[spd->nr_pages] = pfrag->page;
+ spd->partial[spd->nr_pages].len = *len;
+ spd->partial[spd->nr_pages].offset = pfrag->offset;
+ spd->nr_pages++;
+
+ return false;
+}
+
/*
* Fill page/offset/length into spd, if it can hold more pages.
*/
@@ -3103,11 +3115,9 @@ static bool spd_fill_page(struct splice_pipe_desc *spd,
if (unlikely(spd->nr_pages == MAX_SKB_FRAGS))
return true;
- if (linear) {
- page = linear_to_page(page, len, &offset, sk);
- if (!page)
- return true;
- }
+ if (linear)
+ return spd_fill_linear_page(spd, page, offset, len, sk);
+
if (spd_can_coalesce(spd, page, offset)) {
spd->partial[spd->nr_pages - 1].len += *len;
return false;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index b1dcbd3be89e..65ca688d73f1 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -27,23 +27,25 @@ static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce)
int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
int elem_first_coalesce)
{
- struct page_frag *pfrag = sk_page_frag(sk);
+ struct page_frag_cache *nc = sk_page_frag_cache(sk);
u32 osize = msg->sg.size;
int ret = 0;
len -= msg->sg.size;
while (len > 0) {
+ struct page_frag page_frag, *pfrag;
struct scatterlist *sge;
u32 orig_offset;
int use, i;
- if (!sk_page_frag_refill(sk, pfrag)) {
+ pfrag = &page_frag;
+ if (!sk_page_frag_refill_prepare(sk, nc, pfrag)) {
ret = -ENOMEM;
goto msg_trim;
}
orig_offset = pfrag->offset;
- use = min_t(int, len, pfrag->size - orig_offset);
+ use = min_t(int, len, pfrag->size);
if (!sk_wmem_schedule(sk, use)) {
ret = -ENOMEM;
goto msg_trim;
@@ -57,6 +59,7 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
sg_page(sge) == pfrag->page &&
sge->offset + sge->length == orig_offset) {
sge->length += use;
+ page_frag_refill_commit_noref(nc, pfrag, use);
} else {
if (sk_msg_full(msg)) {
ret = -ENOSPC;
@@ -66,13 +69,12 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
sge = &msg->sg.data[msg->sg.end];
sg_unmark_end(sge);
sg_set_page(sge, pfrag->page, use, orig_offset);
- get_page(pfrag->page);
+ page_frag_refill_commit(nc, pfrag, use);
sk_msg_iter_next(msg, end);
}
sk_mem_charge(sk, use);
msg->sg.size += use;
- pfrag->offset += use;
len -= use;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 7f398bd07fb7..f79776162f0d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2270,10 +2270,7 @@ static void __sk_destruct(struct rcu_head *head)
pr_debug("%s: optmem leakage (%d bytes) detected\n",
__func__, atomic_read(&sk->sk_omem_alloc));
- if (sk->sk_frag.page) {
- put_page(sk->sk_frag.page);
- sk->sk_frag.page = NULL;
- }
+ page_frag_cache_drain(&sk->sk_frag);
/* We do not need to acquire sk->sk_peer_lock, we are the last user. */
put_cred(sk->sk_peer_cred);
@@ -3029,16 +3026,33 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
}
EXPORT_SYMBOL(skb_page_frag_refill);
-bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+bool sk_page_frag_refill_prepare(struct sock *sk, struct page_frag_cache *nc,
+ struct page_frag *pfrag)
{
- if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
+ if (likely(page_frag_refill_prepare(nc, 32U, pfrag, sk->sk_allocation)))
return true;
sk_enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
return false;
}
-EXPORT_SYMBOL(sk_page_frag_refill);
+EXPORT_SYMBOL(sk_page_frag_refill_prepare);
+
+void *sk_page_frag_alloc_refill_prepare(struct sock *sk,
+ struct page_frag_cache *nc,
+ struct page_frag *pfrag)
+{
+ void *va;
+
+ va = page_frag_alloc_refill_prepare(nc, 32U, pfrag, sk->sk_allocation);
+ if (likely(va))
+ return va;
+
+ sk_enter_memory_pressure(sk);
+ sk_stream_moderate_sndbuf(sk);
+ return NULL;
+}
+EXPORT_SYMBOL(sk_page_frag_alloc_refill_prepare);
void __lock_sock(struct sock *sk)
__releases(&sk->sk_lock.slock)
@@ -3560,8 +3574,8 @@ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid)
sk->sk_error_report = sock_def_error_report;
sk->sk_destruct = sock_def_destruct;
- sk->sk_frag.page = NULL;
- sk->sk_frag.offset = 0;
+ page_frag_cache_init(&sk->sk_frag);
+
sk->sk_peek_off = -1;
sk->sk_peer_pid = NULL;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0065b1996c94..7033ae387062 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -953,7 +953,7 @@ static int __ip_append_data(struct sock *sk,
struct flowi4 *fl4,
struct sk_buff_head *queue,
struct inet_cork *cork,
- struct page_frag *pfrag,
+ struct page_frag_cache *nc,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
@@ -1233,13 +1233,19 @@ static int __ip_append_data(struct sock *sk,
copy = err;
wmem_alloc_delta += copy;
} else if (!zc) {
+ struct page_frag page_frag, *pfrag;
int i = skb_shinfo(skb)->nr_frags;
+ void *va;
err = -ENOMEM;
- if (!sk_page_frag_refill(sk, pfrag))
+ pfrag = &page_frag;
+ va = sk_page_frag_alloc_refill_prepare(sk, nc, pfrag);
+ if (!va)
goto error;
skb_zcopy_downgrade_managed(skb);
+ copy = min_t(int, copy, pfrag->size);
+
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
err = -EMSGSIZE;
@@ -1247,18 +1253,18 @@ static int __ip_append_data(struct sock *sk,
goto error;
__skb_fill_page_desc(skb, i, pfrag->page,
- pfrag->offset, 0);
+ pfrag->offset, copy);
skb_shinfo(skb)->nr_frags = ++i;
- get_page(pfrag->page);
+ page_frag_refill_commit(nc, pfrag, copy);
+ } else {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1],
+ copy);
+ page_frag_refill_commit_noref(nc, pfrag, copy);
}
- copy = min_t(int, copy, pfrag->size - pfrag->offset);
- if (getfrag(from,
- page_address(pfrag->page) + pfrag->offset,
- offset, copy, skb->len, skb) < 0)
+
+ if (getfrag(from, va, offset, copy, skb->len, skb) < 0)
goto error_efault;
- pfrag->offset += copy;
- skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
skb_len_add(skb, copy);
wmem_alloc_delta += copy;
} else {
@@ -1373,7 +1379,7 @@ int ip_append_data(struct sock *sk, struct flowi4 *fl4,
}
return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base,
- sk_page_frag(sk), getfrag,
+ sk_page_frag_cache(sk), getfrag,
from, length, transhdrlen, flags);
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d5d2fca8a688..b213bedb62c1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1193,9 +1193,13 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
if (zc == 0) {
bool merge = true;
int i = skb_shinfo(skb)->nr_frags;
- struct page_frag *pfrag = sk_page_frag(sk);
+ struct page_frag_cache *nc = sk_page_frag_cache(sk);
+ struct page_frag page_frag, *pfrag;
+ void *va;
- if (!sk_page_frag_refill(sk, pfrag))
+ pfrag = &page_frag;
+ va = sk_page_frag_alloc_refill_prepare(sk, nc, pfrag);
+ if (!va)
goto wait_for_space;
if (!skb_can_coalesce(skb, i, pfrag->page,
@@ -1207,7 +1211,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
merge = false;
}
- copy = min_t(int, copy, pfrag->size - pfrag->offset);
+ copy = min_t(int, copy, pfrag->size);
if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) {
if (tcp_downgrade_zcopy_pure(sk, skb))
@@ -1220,20 +1224,19 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
goto wait_for_space;
err = skb_copy_to_frag_nocache(sk, &msg->msg_iter, skb,
- page_address(pfrag->page) +
- pfrag->offset, copy);
+ va, copy);
if (err)
goto do_error;
/* Update the skb. */
if (merge) {
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+ page_frag_refill_commit_noref(nc, pfrag, copy);
} else {
skb_fill_page_desc(skb, i, pfrag->page,
pfrag->offset, copy);
- page_ref_inc(pfrag->page);
+ page_frag_refill_commit(nc, pfrag, copy);
}
- pfrag->offset += copy;
} else if (zc == MSG_ZEROCOPY) {
/* First append to a fragless skb builds initial
* pure zerocopy skb
@@ -3393,11 +3396,7 @@ int tcp_disconnect(struct sock *sk, int flags)
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
- if (sk->sk_frag.page) {
- put_page(sk->sk_frag.page);
- sk->sk_frag.page = NULL;
- sk->sk_frag.offset = 0;
- }
+ page_frag_cache_drain(&sk->sk_frag);
sk_error_report(sk);
return 0;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 054244ce5117..9824f5a9c1be 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3970,9 +3970,11 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_request *fo = tp->fastopen_req;
- struct page_frag *pfrag = sk_page_frag(sk);
+ struct page_frag_cache *nc = sk_page_frag_cache(sk);
+ struct page_frag page_frag, *pfrag;
struct sk_buff *syn_data;
int space, err = 0;
+ void *va;
tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */
if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie))
@@ -3991,21 +3993,25 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
space = min_t(size_t, space, fo->size);
- if (space &&
- !skb_page_frag_refill(min_t(size_t, space, PAGE_SIZE),
- pfrag, sk->sk_allocation))
- goto fallback;
+ if (space) {
+ pfrag = &page_frag;
+ va = page_frag_alloc_refill_prepare(nc,
+ min_t(size_t, space, PAGE_SIZE),
+ pfrag, sk->sk_allocation);
+ if (!va)
+ goto fallback;
+ }
+
syn_data = tcp_stream_alloc_skb(sk, sk->sk_allocation, false);
if (!syn_data)
goto fallback;
memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
if (space) {
- space = min_t(size_t, space, pfrag->size - pfrag->offset);
+ space = min_t(size_t, space, pfrag->size);
space = tcp_wmem_schedule(sk, space);
}
if (space) {
- space = copy_page_from_iter(pfrag->page, pfrag->offset,
- space, &fo->data->msg_iter);
+ space = _copy_from_iter(va, space, &fo->data->msg_iter);
if (unlikely(!space)) {
tcp_skb_tsorted_anchor_cleanup(syn_data);
kfree_skb(syn_data);
@@ -4013,8 +4019,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
}
skb_fill_page_desc(syn_data, 0, pfrag->page,
pfrag->offset, space);
- page_ref_inc(pfrag->page);
- pfrag->offset += space;
+ page_frag_refill_commit(nc, pfrag, space);
skb_len_add(syn_data, space);
skb_zcopy_set(syn_data, fo->uarg, NULL);
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f7b4608bb316..d9e76a76b7ba 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1416,7 +1416,7 @@ static int __ip6_append_data(struct sock *sk,
struct sk_buff_head *queue,
struct inet_cork_full *cork_full,
struct inet6_cork *v6_cork,
- struct page_frag *pfrag,
+ struct page_frag_cache *nc,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, size_t length, int transhdrlen,
@@ -1762,13 +1762,19 @@ static int __ip6_append_data(struct sock *sk,
copy = err;
wmem_alloc_delta += copy;
} else if (!zc) {
+ struct page_frag page_frag, *pfrag;
int i = skb_shinfo(skb)->nr_frags;
+ void *va;
err = -ENOMEM;
- if (!sk_page_frag_refill(sk, pfrag))
+ pfrag = &page_frag;
+ va = sk_page_frag_alloc_refill_prepare(sk, nc, pfrag);
+ if (!va)
goto error;
skb_zcopy_downgrade_managed(skb);
+ copy = min_t(int, copy, pfrag->size);
+
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
err = -EMSGSIZE;
@@ -1776,18 +1782,18 @@ static int __ip6_append_data(struct sock *sk,
goto error;
__skb_fill_page_desc(skb, i, pfrag->page,
- pfrag->offset, 0);
+ pfrag->offset, copy);
skb_shinfo(skb)->nr_frags = ++i;
- get_page(pfrag->page);
+ page_frag_refill_commit(nc, pfrag, copy);
+ } else {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1],
+ copy);
+ page_frag_refill_commit_noref(nc, pfrag, copy);
}
- copy = min_t(int, copy, pfrag->size - pfrag->offset);
- if (getfrag(from,
- page_address(pfrag->page) + pfrag->offset,
- offset, copy, skb->len, skb) < 0)
+
+ if (getfrag(from, va, offset, copy, skb->len, skb) < 0)
goto error_efault;
- pfrag->offset += copy;
- skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
@@ -1850,7 +1856,7 @@ int ip6_append_data(struct sock *sk,
}
return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork,
- &np->cork, sk_page_frag(sk), getfrag,
+ &np->cork, sk_page_frag_cache(sk), getfrag,
from, length, transhdrlen, flags, ipc6);
}
EXPORT_SYMBOL_GPL(ip6_append_data);
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 94719d4af5fa..8f241a7173ed 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -804,9 +804,13 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
while (msg_data_left(msg)) {
bool merge = true;
int i = skb_shinfo(skb)->nr_frags;
- struct page_frag *pfrag = sk_page_frag(sk);
+ struct page_frag_cache *nc = sk_page_frag_cache(sk);
+ struct page_frag page_frag, *pfrag;
+ void *va;
- if (!sk_page_frag_refill(sk, pfrag))
+ pfrag = &page_frag;
+ va = sk_page_frag_alloc_refill_prepare(sk, nc, pfrag);
+ if (!va)
goto wait_for_memory;
if (!skb_can_coalesce(skb, i, pfrag->page,
@@ -851,14 +855,12 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (head != skb)
head->truesize += copy;
} else {
- copy = min_t(int, msg_data_left(msg),
- pfrag->size - pfrag->offset);
+ copy = min_t(int, msg_data_left(msg), pfrag->size);
if (!sk_wmem_schedule(sk, copy))
goto wait_for_memory;
err = skb_copy_to_frag_nocache(sk, &msg->msg_iter, skb,
- page_address(pfrag->page) +
- pfrag->offset, copy);
+ va, copy);
if (err)
goto out_error;
@@ -866,13 +868,13 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (merge) {
skb_frag_size_add(
&skb_shinfo(skb)->frags[i - 1], copy);
+ page_frag_refill_commit_noref(nc, pfrag, copy);
} else {
skb_fill_page_desc(skb, i, pfrag->page,
pfrag->offset, copy);
- get_page(pfrag->page);
+ page_frag_refill_commit(nc, pfrag, copy);
}
- pfrag->offset += copy;
}
copied += copy;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 1f5c63eb21f0..68c29d8cdee8 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -978,7 +978,6 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
}
/* we can append data to the given data frag if:
- * - there is space available in the backing page_frag
* - the data frag tail matches the current page_frag free offset
* - the data frag end sequence number matches the current write seq
*/
@@ -987,7 +986,6 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
const struct mptcp_data_frag *df)
{
return df && pfrag->page == df->page &&
- pfrag->size - pfrag->offset > 0 &&
pfrag->offset == (df->offset + df->data_len) &&
df->data_seq + df->data_len == msk->write_seq;
}
@@ -1103,14 +1101,20 @@ static void mptcp_enter_memory_pressure(struct sock *sk)
/* ensure we get enough memory for the frag hdr, beyond some minimal amount of
* data
*/
-static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+static void *mptcp_page_frag_alloc_refill_prepare(struct sock *sk,
+ struct page_frag_cache *nc,
+ struct page_frag *pfrag)
{
- if (likely(skb_page_frag_refill(32U + sizeof(struct mptcp_data_frag),
- pfrag, sk->sk_allocation)))
- return true;
+ unsigned int fragsz = 32U + sizeof(struct mptcp_data_frag);
+ void *va;
+
+ va = page_frag_alloc_refill_prepare(nc, fragsz, pfrag,
+ sk->sk_allocation);
+ if (likely(va))
+ return va;
mptcp_enter_memory_pressure(sk);
- return false;
+ return NULL;
}
static struct mptcp_data_frag *
@@ -1813,7 +1817,7 @@ static u32 mptcp_send_limit(const struct sock *sk)
static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- struct page_frag *pfrag;
+ struct page_frag_cache *nc;
size_t copied = 0;
int ret = 0;
long timeo;
@@ -1847,14 +1851,16 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (unlikely(sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)))
goto do_error;
- pfrag = sk_page_frag(sk);
+ nc = sk_page_frag_cache(sk);
while (msg_data_left(msg)) {
+ struct page_frag page_frag, *pfrag;
int total_ts, frag_truesize = 0;
struct mptcp_data_frag *dfrag;
bool dfrag_collapsed;
- size_t psize, offset;
u32 copy_limit;
+ size_t psize;
+ void *va;
/* ensure fitting the notsent_lowat() constraint */
copy_limit = mptcp_send_limit(sk);
@@ -1865,21 +1871,26 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
* page allocator
*/
dfrag = mptcp_pending_tail(sk);
- dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
+ pfrag = &page_frag;
+ va = page_frag_alloc_refill_probe(nc, 1, pfrag);
+ dfrag_collapsed = va && mptcp_frag_can_collapse_to(msk, pfrag,
+ dfrag);
if (!dfrag_collapsed) {
- if (!mptcp_page_frag_refill(sk, pfrag))
+ va = mptcp_page_frag_alloc_refill_prepare(sk, nc,
+ pfrag);
+ if (!va)
goto wait_for_memory;
dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset);
frag_truesize = dfrag->overhead;
+ va += dfrag->overhead;
}
/* we do not bound vs wspace, to allow a single packet.
* memory accounting will prevent execessive memory usage
* anyway
*/
- offset = dfrag->offset + dfrag->data_len;
- psize = pfrag->size - offset;
+ psize = pfrag->size - frag_truesize;
psize = min_t(size_t, psize, msg_data_left(msg));
psize = min_t(size_t, psize, copy_limit);
total_ts = psize + frag_truesize;
@@ -1887,8 +1898,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!sk_wmem_schedule(sk, total_ts))
goto wait_for_memory;
- ret = do_copy_data_nocache(sk, psize, &msg->msg_iter,
- page_address(dfrag->page) + offset);
+ ret = do_copy_data_nocache(sk, psize, &msg->msg_iter, va);
if (ret)
goto do_error;
@@ -1897,7 +1907,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
copied += psize;
dfrag->data_len += psize;
frag_truesize += psize;
- pfrag->offset += frag_truesize;
WRITE_ONCE(msk->write_seq, msk->write_seq + psize);
/* charge data on mptcp pending queue to the msk socket
@@ -1905,10 +1914,12 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
*/
sk_wmem_queued_add(sk, frag_truesize);
if (!dfrag_collapsed) {
- get_page(dfrag->page);
+ page_frag_refill_commit(nc, pfrag, frag_truesize);
list_add_tail(&dfrag->list, &msk->rtx_queue);
if (!msk->first_pending)
WRITE_ONCE(msk->first_pending, dfrag);
+ } else {
+ page_frag_refill_commit_noref(nc, pfrag, frag_truesize);
}
pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk,
dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index dc063c2c7950..0f020293fe10 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -253,8 +253,8 @@ static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx,
}
static void tls_append_frag(struct tls_record_info *record,
- struct page_frag *pfrag,
- int size)
+ struct page_frag_cache *nc,
+ struct page_frag *pfrag, int size)
{
skb_frag_t *frag;
@@ -262,15 +262,34 @@ static void tls_append_frag(struct tls_record_info *record,
if (skb_frag_page(frag) == pfrag->page &&
skb_frag_off(frag) + skb_frag_size(frag) == pfrag->offset) {
skb_frag_size_add(frag, size);
+ page_frag_refill_commit_noref(nc, pfrag, size);
} else {
++frag;
skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset,
size);
++record->num_frags;
+ page_frag_refill_commit(nc, pfrag, size);
+ }
+
+ record->len += size;
+}
+
+static void tls_append_dummy_frag(struct tls_record_info *record,
+ struct page_frag *pfrag, int size)
+{
+ skb_frag_t *frag;
+
+ frag = &record->frags[record->num_frags - 1];
+ if (skb_frag_page(frag) == pfrag->page &&
+ skb_frag_off(frag) + skb_frag_size(frag) == pfrag->offset) {
+ skb_frag_size_add(frag, size);
+ } else {
+ ++frag;
+ skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset, size);
+ ++record->num_frags;
get_page(pfrag->page);
}
- pfrag->offset += size;
record->len += size;
}
@@ -311,11 +330,11 @@ static int tls_push_record(struct sock *sk,
static void tls_device_record_close(struct sock *sk,
struct tls_context *ctx,
struct tls_record_info *record,
- struct page_frag *pfrag,
+ struct page_frag_cache *nc,
unsigned char record_type)
{
struct tls_prot_info *prot = &ctx->prot_info;
- struct page_frag dummy_tag_frag;
+ struct page_frag dummy_tag_frag, *pfrag;
/* append tag
* device will fill in the tag, we just need to append a placeholder
@@ -323,13 +342,16 @@ static void tls_device_record_close(struct sock *sk,
* increases frag count)
* if we can't allocate memory now use the dummy page
*/
- if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) &&
- !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) {
+ pfrag = &dummy_tag_frag;
+ if (unlikely(!page_frag_refill_probe(nc, prot->tag_size, pfrag) &&
+ !page_frag_refill_prepare(nc, prot->tag_size, pfrag,
+ sk->sk_allocation))) {
dummy_tag_frag.page = dummy_page;
dummy_tag_frag.offset = 0;
- pfrag = &dummy_tag_frag;
+ tls_append_dummy_frag(record, pfrag, prot->tag_size);
+ } else {
+ tls_append_frag(record, nc, pfrag, prot->tag_size);
}
- tls_append_frag(record, pfrag, prot->tag_size);
/* fill prepend */
tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]),
@@ -338,6 +360,7 @@ static void tls_device_record_close(struct sock *sk,
}
static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
+ struct page_frag_cache *nc,
struct page_frag *pfrag,
size_t prepend_size)
{
@@ -352,8 +375,7 @@ static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset,
prepend_size);
- get_page(pfrag->page);
- pfrag->offset += prepend_size;
+ page_frag_refill_commit(nc, pfrag, prepend_size);
record->num_frags = 1;
record->len = prepend_size;
@@ -361,33 +383,34 @@ static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
return 0;
}
-static int tls_do_allocation(struct sock *sk,
- struct tls_offload_context_tx *offload_ctx,
- struct page_frag *pfrag,
- size_t prepend_size)
+static void *tls_do_allocation(struct sock *sk,
+ struct tls_offload_context_tx *offload_ctx,
+ struct page_frag_cache *nc,
+ size_t prepend_size, struct page_frag *pfrag)
{
int ret;
if (!offload_ctx->open_record) {
- if (unlikely(!skb_page_frag_refill(prepend_size, pfrag,
- sk->sk_allocation))) {
+ void *va;
+
+ if (unlikely(!page_frag_refill_prepare(nc, prepend_size, pfrag,
+ sk->sk_allocation))) {
READ_ONCE(sk->sk_prot)->enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
- return -ENOMEM;
+ return NULL;
}
- ret = tls_create_new_record(offload_ctx, pfrag, prepend_size);
+ ret = tls_create_new_record(offload_ctx, nc, pfrag,
+ prepend_size);
if (ret)
- return ret;
+ return NULL;
- if (pfrag->size > pfrag->offset)
- return 0;
+ va = page_frag_alloc_refill_probe(nc, 1, pfrag);
+ if (va)
+ return va;
}
- if (!sk_page_frag_refill(sk, pfrag))
- return -ENOMEM;
-
- return 0;
+ return sk_page_frag_alloc_refill_prepare(sk, nc, pfrag);
}
static int tls_device_copy_data(void *addr, size_t bytes, struct iov_iter *i)
@@ -424,8 +447,8 @@ static int tls_push_data(struct sock *sk,
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
struct tls_record_info *record;
+ struct page_frag_cache *nc;
int tls_push_record_flags;
- struct page_frag *pfrag;
size_t orig_size = size;
u32 max_open_record_len;
bool more = false;
@@ -454,7 +477,7 @@ static int tls_push_data(struct sock *sk,
return rc;
}
- pfrag = sk_page_frag(sk);
+ nc = sk_page_frag_cache(sk);
/* TLS_HEADER_SIZE is not counted as part of the TLS record, and
* we need to leave room for an authentication tag.
@@ -462,8 +485,12 @@ static int tls_push_data(struct sock *sk,
max_open_record_len = TLS_MAX_PAYLOAD_SIZE +
prot->prepend_size;
do {
- rc = tls_do_allocation(sk, ctx, pfrag, prot->prepend_size);
- if (unlikely(rc)) {
+ struct page_frag page_frag, *pfrag;
+ void *va;
+
+ pfrag = &page_frag;
+ va = tls_do_allocation(sk, ctx, nc, prot->prepend_size, pfrag);
+ if (unlikely(!va)) {
rc = sk_stream_wait_memory(sk, &timeo);
if (!rc)
continue;
@@ -512,16 +539,15 @@ static int tls_push_data(struct sock *sk,
zc_pfrag.offset = off;
zc_pfrag.size = copy;
- tls_append_frag(record, &zc_pfrag, copy);
+ tls_append_dummy_frag(record, &zc_pfrag, copy);
} else if (copy) {
- copy = min_t(size_t, copy, pfrag->size - pfrag->offset);
+ copy = min_t(size_t, copy, pfrag->size);
- rc = tls_device_copy_data(page_address(pfrag->page) +
- pfrag->offset, copy,
- iter);
+ rc = tls_device_copy_data(va, copy, iter);
if (rc)
goto handle_error;
- tls_append_frag(record, pfrag, copy);
+
+ tls_append_frag(record, nc, pfrag, copy);
}
size -= copy;
@@ -539,7 +565,7 @@ static int tls_push_data(struct sock *sk,
if (done || record->len >= max_open_record_len ||
(record->num_frags >= MAX_SKB_FRAGS - 1)) {
tls_device_record_close(sk, tls_ctx, record,
- pfrag, record_type);
+ nc, record_type);
rc = tls_push_record(sk,
tls_ctx,
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
` (8 preceding siblings ...)
2024-10-28 11:58 ` [PATCH RFC 09/10] net: replace page_frag with page_frag_cache Yunsheng Lin
@ 2024-10-28 11:58 ` Yunsheng Lin
2024-10-28 23:27 ` Jakub Kicinski
9 siblings, 1 reply; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-28 11:58 UTC (permalink / raw)
To: davem, kuba, pabeni
Cc: netdev, linux-kernel, Yunsheng Lin, Alexander Duyck,
Andrew Morton, Linux-MM
After this patchset, page_frag is a small subsystem/library
on its own, so add an entry in MAINTAINERS to indicate the
new subsystem/library's maintainer, maillist, status and file
lists of page_frag.
Alexander is the original author of page_frag, add him in the
MAINTAINERS too.
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Linux-MM <linux-mm@kvack.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
MAINTAINERS | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index f39ab140710f..9f84f2e901f5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17399,6 +17399,18 @@ F: mm/page-writeback.c
F: mm/readahead.c
F: mm/truncate.c
+PAGE FRAG
+M: Alexander Duyck <alexander.duyck@gmail.com>
+M: Yunsheng Lin <linyunsheng@huawei.com>
+L: linux-mm@kvack.org
+L: netdev@vger.kernel.org
+S: Supported
+F: Documentation/mm/page_frags.rst
+F: include/linux/page_frag_cache.h
+F: mm/page_frag_cache.c
+F: tools/testing/selftests/mm/page_frag/
+F: tools/testing/selftests/mm/test_page_frag.sh
+
PAGE POOL
M: Jesper Dangaard Brouer <hawk@kernel.org>
M: Ilias Apalodimas <ilias.apalodimas@linaro.org>
--
2.33.0
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH RFC 02/10] net: rename skb_copy_to_page_nocache() helper
2024-10-28 11:58 ` [PATCH RFC 02/10] net: rename skb_copy_to_page_nocache() helper Yunsheng Lin
@ 2024-10-28 17:49 ` Alexander Duyck
0 siblings, 0 replies; 17+ messages in thread
From: Alexander Duyck @ 2024-10-28 17:49 UTC (permalink / raw)
To: Yunsheng Lin
Cc: davem, kuba, pabeni, netdev, linux-kernel, Andrew Morton,
Linux-MM, Eric Dumazet, Simon Horman, David Ahern
On Mon, Oct 28, 2024 at 5:05 AM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>
> Rename skb_copy_to_page_nocache() to skb_copy_to_frag_nocache()
> to avoid calling virt_to_page() as we are about to pass virtual
> address directly.
>
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> CC: Andrew Morton <akpm@linux-foundation.org>
> CC: Linux-MM <linux-mm@kvack.org>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
> include/net/sock.h | 9 ++++-----
> net/ipv4/tcp.c | 7 +++----
> net/kcm/kcmsock.c | 7 +++----
> 3 files changed, 10 insertions(+), 13 deletions(-)
Looks good to me.
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH RFC 04/10] mm: page_frag: introduce page_frag_alloc_abort() related API
2024-10-28 11:58 ` [PATCH RFC 04/10] mm: page_frag: introduce page_frag_alloc_abort() related API Yunsheng Lin
@ 2024-10-28 17:53 ` Alexander Duyck
2024-10-29 9:39 ` Yunsheng Lin
0 siblings, 1 reply; 17+ messages in thread
From: Alexander Duyck @ 2024-10-28 17:53 UTC (permalink / raw)
To: Yunsheng Lin
Cc: davem, kuba, pabeni, netdev, linux-kernel, Andrew Morton,
Linux-MM, Jonathan Corbet, linux-doc
On Mon, Oct 28, 2024 at 5:05 AM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>
> For some case as tun_build_skb() without the needing of
> using complicated prepare & commit API, add the abort API to
> abort the operation of page_frag_alloc_*() related API for
> error handling knowing that no one else is taking extra
> reference to the just allocated fragment, and add abort_ref
> API to only abort the reference counting of the allocated
> fragment if it is already referenced by someone else.
>
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> CC: Andrew Morton <akpm@linux-foundation.org>
> CC: Linux-MM <linux-mm@kvack.org>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
> Documentation/mm/page_frags.rst | 7 +++++--
> include/linux/page_frag_cache.h | 20 ++++++++++++++++++++
> mm/page_frag_cache.c | 21 +++++++++++++++++++++
> 3 files changed, 46 insertions(+), 2 deletions(-)
>
> diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
> index 34e654c2956e..339e641beb53 100644
> --- a/Documentation/mm/page_frags.rst
> +++ b/Documentation/mm/page_frags.rst
> @@ -114,9 +114,10 @@ fragsz if there is an alignment requirement for the size of the fragment.
> .. kernel-doc:: include/linux/page_frag_cache.h
> :identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
> __page_frag_alloc_align page_frag_alloc_align page_frag_alloc
> + page_frag_alloc_abort
>
> .. kernel-doc:: mm/page_frag_cache.c
> - :identifiers: page_frag_cache_drain page_frag_free
> + :identifiers: page_frag_cache_drain page_frag_free page_frag_alloc_abort_ref
>
> Coding examples
> ===============
> @@ -143,8 +144,10 @@ Allocation & freeing API
> goto do_error;
>
> err = do_something(va, size);
> - if (err)
> + if (err) {
> + page_frag_alloc_abort(nc, va, size);
> goto do_error;
> + }
>
> ...
>
> diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
> index a2b1127e8ac8..c3347c97522c 100644
> --- a/include/linux/page_frag_cache.h
> +++ b/include/linux/page_frag_cache.h
> @@ -141,5 +141,25 @@ static inline void *page_frag_alloc(struct page_frag_cache *nc,
> }
>
> void page_frag_free(void *addr);
> +void page_frag_alloc_abort_ref(struct page_frag_cache *nc, void *va,
> + unsigned int fragsz);
> +
> +/**
> + * page_frag_alloc_abort - Abort the page fragment allocation.
> + * @nc: page_frag cache to which the page fragment is aborted back
> + * @va: virtual address of page fragment to be aborted
> + * @fragsz: size of the page fragment to be aborted
> + *
> + * It is expected to be called from the same context as the allocation API.
> + * Mostly used for error handling cases to abort the fragment allocation knowing
> + * that no one else is taking extra reference to the just aborted fragment, so
> + * that the aborted fragment can be reused.
> + */
> +static inline void page_frag_alloc_abort(struct page_frag_cache *nc, void *va,
> + unsigned int fragsz)
> +{
> + page_frag_alloc_abort_ref(nc, va, fragsz);
> + nc->offset -= fragsz;
> +}
>
> #endif
> diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
> index d014130fb893..4d5626da42ed 100644
> --- a/mm/page_frag_cache.c
> +++ b/mm/page_frag_cache.c
> @@ -201,3 +201,24 @@ void page_frag_free(void *addr)
> free_unref_page(page, compound_order(page));
> }
> EXPORT_SYMBOL(page_frag_free);
> +
> +/**
> + * page_frag_alloc_abort_ref - Abort the reference of allocated fragment.
> + * @nc: page_frag cache to which the page fragment is aborted back
> + * @va: virtual address of page fragment to be aborted
> + * @fragsz: size of the page fragment to be aborted
> + *
> + * It is expected to be called from the same context as the allocation API.
> + * Mostly used for error handling cases to abort the reference of allocated
> + * fragment if the fragment has been referenced for other usages, to aovid the
> + * atomic operation of page_frag_free() API.
> + */
> +void page_frag_alloc_abort_ref(struct page_frag_cache *nc, void *va,
> + unsigned int fragsz)
> +{
> + VM_BUG_ON(va + fragsz !=
> + encoded_page_decode_virt(nc->encoded_page) + nc->offset);
> +
> + nc->pagecnt_bias++;
> +}
> +EXPORT_SYMBOL(page_frag_alloc_abort_ref);
It isn't clear to me why you split this over two functions. It seems
like you could just update the offset in this lower function rather
than do it in the upper one since you are passing all the arguments
here anyway.
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag
2024-10-28 11:58 ` [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag Yunsheng Lin
@ 2024-10-28 23:27 ` Jakub Kicinski
2024-10-29 9:40 ` Yunsheng Lin
0 siblings, 1 reply; 17+ messages in thread
From: Jakub Kicinski @ 2024-10-28 23:27 UTC (permalink / raw)
To: Yunsheng Lin
Cc: davem, pabeni, netdev, linux-kernel, Alexander Duyck,
Andrew Morton, Linux-MM
On Mon, 28 Oct 2024 19:58:50 +0800 Yunsheng Lin wrote:
> +M: Yunsheng Lin <linyunsheng@huawei.com>
Why is this line still here? You asked for a second opinion
and you got one from Paolo.
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH RFC 04/10] mm: page_frag: introduce page_frag_alloc_abort() related API
2024-10-28 17:53 ` Alexander Duyck
@ 2024-10-29 9:39 ` Yunsheng Lin
0 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-29 9:39 UTC (permalink / raw)
To: Alexander Duyck
Cc: davem, kuba, pabeni, netdev, linux-kernel, Andrew Morton,
Linux-MM, Jonathan Corbet, linux-doc
On 2024/10/29 1:53, Alexander Duyck wrote:
> On Mon, Oct 28, 2024 at 5:05 AM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>>
>> For some case as tun_build_skb() without the needing of
>> using complicated prepare & commit API, add the abort API to
>> abort the operation of page_frag_alloc_*() related API for
>> error handling knowing that no one else is taking extra
>> reference to the just allocated fragment, and add abort_ref
>> API to only abort the reference counting of the allocated
>> fragment if it is already referenced by someone else.
>>
...
>> +
>> +/**
>> + * page_frag_alloc_abort_ref - Abort the reference of allocated fragment.
>> + * @nc: page_frag cache to which the page fragment is aborted back
>> + * @va: virtual address of page fragment to be aborted
>> + * @fragsz: size of the page fragment to be aborted
>> + *
>> + * It is expected to be called from the same context as the allocation API.
>> + * Mostly used for error handling cases to abort the reference of allocated
>> + * fragment if the fragment has been referenced for other usages, to aovid the
>> + * atomic operation of page_frag_free() API.
>> + */
>> +void page_frag_alloc_abort_ref(struct page_frag_cache *nc, void *va,
>> + unsigned int fragsz)
>> +{
>> + VM_BUG_ON(va + fragsz !=
>> + encoded_page_decode_virt(nc->encoded_page) + nc->offset);
>> +
>> + nc->pagecnt_bias++;
>> +}
>> +EXPORT_SYMBOL(page_frag_alloc_abort_ref);
>
> It isn't clear to me why you split this over two functions. It seems
> like you could just update the offset in this lower function rather
> than do it in the upper one since you are passing all the arguments
> here anyway.
For the usecase in tun_build_skb(), There seems to be XDP_REDIRECT and
XDP_TX case that the allocated fragment has been referenced for other
usages even when xdp_do_redirect() or tun_xdp_tx() return error, so that
caller can call page_frag_alloc_abort_ref() to abort its reference
of the allocated fragment, but not abort the whole fragment for later
reuse.
As the doc mentioned above page_frag_alloc_abort_ref(), it is mainly to
avoid the atomic operation of page_frag_free() API when the caller has the
allocation context and has the all the arguments page_frag_alloc_abort_ref()
needs even though it might be a unlikely case if page_frag_alloc_abort() API
is already provided.
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag
2024-10-28 23:27 ` Jakub Kicinski
@ 2024-10-29 9:40 ` Yunsheng Lin
2024-10-29 14:33 ` Jakub Kicinski
0 siblings, 1 reply; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-29 9:40 UTC (permalink / raw)
To: Jakub Kicinski
Cc: davem, pabeni, netdev, linux-kernel, Alexander Duyck,
Andrew Morton, Linux-MM
On 2024/10/29 7:27, Jakub Kicinski wrote:
> On Mon, 28 Oct 2024 19:58:50 +0800 Yunsheng Lin wrote:
>> +M: Yunsheng Lin <linyunsheng@huawei.com>
>
> Why is this line still here? You asked for a second opinion
> and you got one from Paolo.
Because of the reason below?
https://lore.kernel.org/all/159495c8-71be-4a11-8c49-d528e8154841@huawei.com/
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag
2024-10-29 9:40 ` Yunsheng Lin
@ 2024-10-29 14:33 ` Jakub Kicinski
2024-10-30 11:32 ` Yunsheng Lin
0 siblings, 1 reply; 17+ messages in thread
From: Jakub Kicinski @ 2024-10-29 14:33 UTC (permalink / raw)
To: Yunsheng Lin
Cc: davem, pabeni, netdev, linux-kernel, Alexander Duyck,
Andrew Morton, Linux-MM
On Tue, 29 Oct 2024 17:40:08 +0800 Yunsheng Lin wrote:
> On 2024/10/29 7:27, Jakub Kicinski wrote:
> > On Mon, 28 Oct 2024 19:58:50 +0800 Yunsheng Lin wrote:
> >> +M: Yunsheng Lin <linyunsheng@huawei.com>
> >
> > Why is this line still here? You asked for a second opinion
> > and you got one from Paolo.
>
> Because of the reason below?
> https://lore.kernel.org/all/159495c8-71be-4a11-8c49-d528e8154841@huawei.com/
What is the reason in that link? You try to argue that the convention
doesn't exist or that your case is different? The maintainer tells you
their opinion in context of the posting.
It seems like you're more motivated by getting into MAINTAINERS than
by the work itself :/
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag
2024-10-29 14:33 ` Jakub Kicinski
@ 2024-10-30 11:32 ` Yunsheng Lin
0 siblings, 0 replies; 17+ messages in thread
From: Yunsheng Lin @ 2024-10-30 11:32 UTC (permalink / raw)
To: Jakub Kicinski
Cc: davem, pabeni, netdev, linux-kernel, Alexander Duyck,
Andrew Morton, Linux-MM
On 2024/10/29 22:33, Jakub Kicinski wrote:
> On Tue, 29 Oct 2024 17:40:08 +0800 Yunsheng Lin wrote:
>> On 2024/10/29 7:27, Jakub Kicinski wrote:
>>> On Mon, 28 Oct 2024 19:58:50 +0800 Yunsheng Lin wrote:
>>>> +M: Yunsheng Lin <linyunsheng@huawei.com>
>>>
>>> Why is this line still here? You asked for a second opinion
>>> and you got one from Paolo.
>>
>> Because of the reason below?
>> https://lore.kernel.org/all/159495c8-71be-4a11-8c49-d528e8154841@huawei.com/
>
> What is the reason in that link? You try to argue that the convention
> doesn't exist or that your case is different? The maintainer tells you
> their opinion in context of the posting.
I just argue that it seems natural and reasonable that someone being willing
and able to turn page_frag into a subsystem or library might become the
co-maintainer if she/he is also willing to co-maintain it.
>
> It seems like you're more motivated by getting into MAINTAINERS than
> by the work itself :/
For the 'MAINTAINERS ' part, I guess we all want some acknowledge in some
way for the work if that is the 'motivated ' you are referring to.
For the 'work itself' part, my previous work of supporting frag API, unifying
frag & non-frag API for page_pool, removing page frag implementation in vhost_net
and recent trying of fixing IOMMU crash problem all seem to be motivated more by
getting into MAINTAINERS in your eyes?
With all due respect, it would be good to have less of speculation like
above and focus on more technical discussion.
^ permalink raw reply [flat|nested] 17+ messages in thread
end of thread, other threads:[~2024-12-05 15:21 UTC | newest]
Thread overview: 17+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <20241028115850.3409893-1-linyunsheng@huawei.com>
2024-10-28 11:58 ` [PATCH RFC 01/10] mm: page_frag: some minor refactoring before adding new API Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 02/10] net: rename skb_copy_to_page_nocache() helper Yunsheng Lin
2024-10-28 17:49 ` Alexander Duyck
2024-10-28 11:58 ` [PATCH RFC 03/10] mm: page_frag: update documentation for page_frag Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 04/10] mm: page_frag: introduce page_frag_alloc_abort() related API Yunsheng Lin
2024-10-28 17:53 ` Alexander Duyck
2024-10-29 9:39 ` Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 05/10] mm: page_frag: introduce refill prepare & commit API Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 06/10] mm: page_frag: introduce alloc_refill " Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 07/10] mm: page_frag: introduce probe related API Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 08/10] mm: page_frag: add testing for the newly added API Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 09/10] net: replace page_frag with page_frag_cache Yunsheng Lin
2024-10-28 11:58 ` [PATCH RFC 10/10] mm: page_frag: add an entry in MAINTAINERS for page_frag Yunsheng Lin
2024-10-28 23:27 ` Jakub Kicinski
2024-10-29 9:40 ` Yunsheng Lin
2024-10-29 14:33 ` Jakub Kicinski
2024-10-30 11:32 ` Yunsheng Lin
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox