Currently NIC packet receiving performance based on page pool deteriorates
occasionally. To analysis the causes of this problem page allocation stats
are collected. Here are the stats when NIC rx performance deteriorates:
bandwidth(Gbits/s) 16.8 6.91
rx_pp_alloc_fast 13794308 21141869
rx_pp_alloc_slow 108625 166481
rx_pp_alloc_slow_h 0 0
rx_pp_alloc_empty 8192 8192
rx_pp_alloc_refill 0 0
rx_pp_alloc_waive 100433 158289
rx_pp_recycle_cached 0 0
rx_pp_recycle_cache_full 0 0
rx_pp_recycle_ring 362400 420281
rx_pp_recycle_ring_full 6064893 9709724
rx_pp_recycle_released_ref 0 0
The rx_pp_alloc_waive count indicates that a large number of pages' numa
node are inconsistent with the NIC device numa node. Therefore these pages
can't be reused by the page pool. As a result, many new pages would be
allocated by __page_pool_alloc_pages_slow which is time consuming. This
causes the NIC rx performance fluctuations.
The main reason of huge numa mismatch pages in page pool is that page pool
uses alloc_pages_bulk_array to allocate original pages. This function is
not suitable for page allocation in NUMA scenario. So this patch uses
alloc_pages_bulk_array_node which has a NUMA id input parameter to ensure
the NUMA consistent between NIC device and allocated pages.
Repeated NIC rx performance tests are performed 40 times. NIC rx bandwidth
is higher and more stable compared to the datas above. Here are three test
stats, the rx_pp_alloc_waive count is zero and rx_pp_alloc_slow which
indicates pages allocated from slow patch is relatively low.
bandwidth(Gbits/s) 93 93.9 93.8
rx_pp_alloc_fast 60066264 61266386 60938254
rx_pp_alloc_slow 16512 16517 16539
rx_pp_alloc_slow_ho 0 0 0
rx_pp_alloc_empty 16512 16517 16539
rx_pp_alloc_refill 473841 481910 481585
rx_pp_alloc_waive 0 0 0
rx_pp_recycle_cached 0 0 0
rx_pp_recycle_cache_full 0 0 0
rx_pp_recycle_ring 29754145 30358243 30194023
rx_pp_recycle_ring_full 0 0 0
rx_pp_recycle_released_ref 0 0 0
Signed-off-by: Jie Wang <wangjie125@huawei.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Link: https://lore.kernel.org/r/20220705113515.54342-1-huangguangbin2@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Currently If use page pool allocation stats to analysis a RX performance
degradation problem. These stats only count for pages allocate from
page_pool_alloc_pages. But nic drivers such as hns3 use
page_pool_dev_alloc_frag to allocate pages, so page stats in this API
should also be counted.
Signed-off-by: Jie Wang <wangjie125@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Introduce page_pool APIs to report stats through ethtool and reduce
duplicated code in each driver.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Adds a function page_pool_get_stats which can be used by drivers to obtain
stats for a specified page_pool.
Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Add per-cpu stats tracking page pool recycling events:
- cached: recycling placed page in the page pool cache
- cache_full: page pool cache was full
- ring: page placed into the ptr ring
- ring_full: page released from page pool because the ptr ring was full
- released_refcnt: page released (and not recycled) because refcnt > 1
Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Add per-pool statistics counters for the allocation path of a page pool.
These stats are incremented in softirq context, so no locking or per-cpu
variables are needed.
This code is disabled by default and a kernel config option is provided for
users who wish to enable them.
The statistics added are:
- fast: successful fast path allocations
- slow: slow path order-0 allocations
- slow_high_order: slow path high order allocations
- empty: ptr ring is empty, so a slow path allocation was forced.
- refill: an allocation which triggered a refill of the cache
- waive: pages obtained from the ptr ring that cannot be added to
the cache due to a NUMA mismatch.
Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Add three string sets related to timestamping information:
ETH_SS_SOF_TIMESTAMPING: SOF_TIMESTAMPING_* flags
ETH_SS_TS_TX_TYPES: timestamping Tx types
ETH_SS_TS_RX_FILTERS: timestamping Rx filters
These will be used for TIMESTAMP_GET request.
v2: avoid compiler warning ("enumeration value not handled in switch")
in net_hwtstamp_validate()
v3: omit dash in Tx type names ("one-step-*" -> "onestep-*"), suggested by
Richard Cochran
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
The 1588 standard defines one step operation for both Sync and
PDelay_Resp messages. Up until now, hardware with P2P one step has
been rare, and kernel support was lacking. This patch adds support of
the mode in anticipation of new hardware developments.
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
The ethtool netlink interface is going to be split into multiple files so
that it will be more convenient to put all of them in a separate directory
net/ethtool. Start by moving current ethtool.c with ioctl interface into
this directory and renaming it to ioctl.c.
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
There is no need to synchronize the account updating, so
use the relaxed atomic to avoid some memory barrier in the
data path.
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Currently page pool only support page recycling when there
is only one user of the page, and the split page reusing
implemented in the most driver can not use the page pool as
bing-pong way of reusing requires the multi user support in
page pool.
Those reusing or recycling has below limitations:
1. page from page pool can only be used be one user in order
for the page recycling to happen.
2. Bing-pong way of reusing in most driver does not support
multi desc using different part of the same page in order
to save memory.
So add multi-users support and frag page recycling in page
pool to overcome the above limitation.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
For 32 bit systems with 64 bit dma, dma_addr[1] is used to
store the upper 32 bit dma addr, those system should be rare
those days.
For normal system, the dma_addr[1] in 'struct page' is not
used, so we can reuse dma_addr[1] for storing frag count,
which means how many frags this page might be splited to.
In order to simplify the page frag support in the page pool,
the PAGE_POOL_DMA_USE_PP_FRAG_COUNT macro is added to indicate
the 32 bit systems with 64 bit dma, and the page frag support
in page pool is disabled for such system.
The newly added page_pool_set_frag_count() is called to reserve
the maximum frag count before any page frag is passed to the
user. The page_pool_atomic_sub_frag_count_return() is called
when user is done with the page frag.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Currently, page->pp is cleared and set everytime the page
is recycled, which is unnecessary.
So only set the page->pp when the page is added to the page
pool and only clear it when the page is released from the
page pool.
This is also a preparation to support allocating frag page
in page pool.
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
As mentioned in commit c07aea3ef4 ("mm: add a signature in
struct page"):
"The page->signature field is aliased to page->lru.next and
page->compound_head."
And as the comment in page_is_pfmemalloc():
"lru.next has bit 1 set if the page is allocated from the
pfmemalloc reserves. Callers may simply overwrite it if they
do not need to preserve that information."
The page->signature is OR’ed with PP_SIGNATURE when a page is
allocated in page pool, see __page_pool_alloc_pages_slow(),
and page->signature is checked directly with PP_SIGNATURE in
page_pool_return_skb_page(), which might cause resoure leaking
problem for a page from page pool if bit 1 of lru.next is set
for a pfmemalloc page. What happens here is that the original
pp->signature is OR'ed with PP_SIGNATURE after the allocation
in order to preserve any existing bits(such as the bit 1, used
to indicate a pfmemalloc page), so when those bits are present,
those page is not considered to be from page pool and the DMA
mapping of those pages will be left stale.
As bit 0 is for page->compound_head, So mask both bit 0/1 before
the checking in page_pool_return_skb_page(). And we will return
those pfmemalloc pages back to the page allocator after cleaning
up the DMA mapping.
Fixes: 6a5bcd84e8 ("page_pool: Allow drivers to hint on SKB recycling")
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
mainline inclusion
from mainline-v5.14-rc3
commit 2cc3aeb5ec
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I4CVS3
CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2cc3aeb5eccc
----------------------------------------------------------------------
As Alexander points out, when we are trying to recycle a cloned/expanded
SKB we might trigger a race. The recycling code relies on the
pp_recycle bit to trigger, which we carry over to cloned SKBs.
If that cloned SKB gets expanded or if we get references to the frags,
call skb_release_data() and overwrite skb->head, we are creating separate
instances accessing the same page frags. Since the skb_release_data()
will first try to recycle the frags, there's a potential race between
the original and cloned SKB, since both will have the pp_recycle bit set.
Fix this by explicitly those SKBs not recyclable.
The atomic_sub_return effectively limits us to a single release case,
and when we are calling skb_release_data we are also releasing the
option to perform the recycling, or releasing the pages from the page pool.
Fixes: 6a5bcd84e8 ("page_pool: Allow drivers to hint on SKB recycling")
Reported-by: Alexander Duyck <alexanderduyck@fb.com>
Suggested-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Yongxin Li <liyongxin1@huawei.com>
Signed-off-by: Junxin Chen <chenjunxin1@huawei.com>
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Up to now several high speed NICs have custom mechanisms of recycling
the allocated memory they use for their payloads.
Our page_pool API already has recycling capabilities that are always
used when we are running in 'XDP mode'. So let's tweak the API and the
kernel network stack slightly and allow the recycling to happen even
during the standard operation.
The API doesn't take into account 'split page' policies used by those
drivers currently, but can be extended once we have users for that.
The idea is to be able to intercept the packet on skb_release_data().
If it's a buffer coming from our page_pool API recycle it back to the
pool for further usage or just release the packet entirely.
To achieve that we introduce a bit in struct sk_buff (pp_recycle:1) and
a field in struct page (page->pp) to store the page_pool pointer.
Storing the information in page->pp allows us to recycle both SKBs and
their fragments.
We could have skipped the skb bit entirely, since identical information
can bederived from struct page. However, in an effort to affect the free path
as less as possible, reading a single bit in the skb which is already
in cache, is better that trying to derive identical information for the
page stored data.
The driver or page_pool has to take care of the sync operations on it's own
during the buffer recycling since the buffer is, after opting-in to the
recycling, never unmapped.
Since the gain on the drivers depends on the architecture, we are not
enabling recycling by default if the page_pool API is used on a driver.
In order to enable recycling the driver must call skb_mark_for_recycle()
to store the information we need for recycling in page->pp and
enabling the recycling bit, or page_pool_store_mem_info() for a fragment.
Co-developed-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Conflicts:
include/linux/skbuff.h
This is a prerequisite patch, the next one is enabling recycling of
skbs and fragments. Add an extra argument on __skb_frag_unref() to
handle recycling, and update the current users of the function with that.
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
This is needed by the page_pool to avoid recycling a page not allocated
via page_pool.
The page->signature field is aliased to page->lru.next and
page->compound_head, but it can't be set by mistake because the
signature value is a bad pointer, and can't trigger a false positive
in PageTail() because the last bit is 0.
Co-developed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
pool_page_reusable() is a leftover from pre-NUMA-aware times. For now,
this function is just a redundant wrapper over page_is_pfmemalloc(),
so inline it into its sole call site.
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
RX zerocopy fragment pages which are not allocated from the
system page pool require special handling. Give the callback
in skb_zcopy_clear() a chance to process them first.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Introduce the capability to batch page_pool ptr_ring refill since it is
usually run inside the driver NAPI tx completion loop.
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Link: https://lore.kernel.org/bpf/08dd249c9522c001313f520796faa777c4089e1c.1605267335.git.lorenzo@kernel.org
Reviewed-by: Yongxin Li <liyongxin1@huawei.com>
(fix conflicts: delete modifications to net/core/xdp.c)
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
There are cases where the page_pool need to refill with pages from the
page allocator. Some workloads cause the page_pool to release pages
instead of recycling these pages.
For these workload it can improve performance to bulk alloc pages from the
page-allocator to refill the alloc cache.
For XDP-redirect workload with 100G mlx5 driver (that use page_pool)
redirecting xdp_frame packets into a veth, that does XDP_PASS to create an
SKB from the xdp_frame, which then cannot return the page to the
page_pool.
Performance results under GitHub xdp-project[1]:
[1] https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org
Mel: The patch "net: page_pool: convert to use alloc_pages_bulk_array
variant" was squashed with this patch. From the test page, the array
variant was superior with one of the test results as follows.
Kernel XDP stats CPU pps Delta
Baseline XDP-RX CPU total 3,771,046 n/a
List XDP-RX CPU total 3,940,242 +4.49%
Array XDP-RX CPU total 4,249,224 +12.68%
Link: https://lkml.kernel.org/r/20210325114228.27719-10-mgorman@techsingularity.net
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Reviewed-by: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: David Miller <davem@davemloft.net>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
In preparation for next patch, move the dma mapping into its own function,
as this will make it easier to follow the changes.
[ilias.apalodimas: make page_pool_dma_map return boolean]
Link: https://lkml.kernel.org/r/20210325114228.27719-9-mgorman@techsingularity.net
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: David Miller <davem@davemloft.net>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Functions starting with __ usually indicate those which are exported,
but should not be called directly. Update some of those declared in the
API and make it more readable.
page_pool_unmap_page() and page_pool_release_page() were doing
exactly the same thing calling __page_pool_clean_page(). Let's
rename __page_pool_clean_page() to page_pool_release_page() and
export it in order to show up on perf logs and get rid of
page_pool_unmap_page().
Finally rename __page_pool_put_page() to page_pool_put_page() since we
can now directly call it from drivers and rename the existing
page_pool_put_page() to page_pool_put_full_page() since they do the same
thing but the latter is trying to sync the full DMA area.
This patch also updates netsec, mvneta and stmmac drivers which use
those functions.
Suggested-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Conflicts:
drivers/net/ethernet/marvell/mvneta.c
drivers/net/ethernet/socionext/netsec.c
net/core/page_pool.c
Abort the change in mvneta.c and netsec.c to fix the conflicts.
"do {} while" in page_pool_refill_alloc_cache will always
refill page once whether refill is true or false, and whether
alloc.count of pool is less than PP_ALLOC_CACHE_REFILL or not
this is wrong, and will cause overflow of pool->alloc.cache
the caller of __page_pool_get_cached should provide guarantee
that pool->alloc.cache is safe to access, so in_serving_softirq
should be removed as suggested by Jesper Dangaard Brouer in
https://patchwork.ozlabs.org/patch/1233713/
so fix this issue by calling page_pool_refill_alloc_cache()
only when pool->alloc.count is zero
Fixes: 44768decb7 ("page_pool: handle page recycle for NUMA_NO_NODE condition")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
When kernel is compiled without NUMA support, then page_pool NUMA
config setting (pool->p.nid) doesn't make any practical sense. The
compiler cannot see that it can remove the code paths.
This patch avoids reading pool->p.nid setting in case of !CONFIG_NUMA,
in allocation and numa check code, which helps compiler to see the
optimisation potential. It leaves update code intact to keep API the
same.
$ ./scripts/bloat-o-meter net/core/page_pool.o-numa-enabled \
net/core/page_pool.o-numa-disabled
add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-113 (-113)
Function old new delta
page_pool_create 401 398 -3
__page_pool_alloc_pages_slow 439 426 -13
page_pool_refill_alloc_cache 425 328 -97
Total: Before=3611, After=3498, chg -3.13%
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
The check in pool_page_reusable (page_to_nid(page) == pool->p.nid) is
not valid if page_pool was configured with pool->p.nid = NUMA_NO_NODE.
The goal of the NUMA changes in commit d5394610b1 ("page_pool: Don't
recycle non-reusable pages"), were to have RX-pages that belongs to the
same NUMA node as the CPU processing RX-packet during softirq/NAPI. As
illustrated by the performance measurements.
This patch moves the NAPI checks out of fast-path, and at the same time
solves the NUMA_NO_NODE issue.
First realize that alloc_pages_node() with pool->p.nid = NUMA_NO_NODE
will lookup current CPU nid (Numa ID) via numa_mem_id(), which is used
as the the preferred nid. It is only in rare situations, where
e.g. NUMA zone runs dry, that page gets doesn't get allocated from
preferred nid. The page_pool API allows drivers to control the nid
themselves via controlling pool->p.nid.
This patch moves the NAPI check to when alloc cache is refilled, via
dequeuing/consuming pages from the ptr_ring. Thus, we can allow placing
pages from remote NUMA into the ptr_ring, as the dequeue/consume step
will check the NUMA node. All current drivers using page_pool will
alloc/refill RX-ring from same CPU running softirq/NAPI process.
Drivers that control the nid explicitly, also use page_pool_update_nid
when changing nid runtime. To speed up transision to new nid the alloc
cache is now flushed on nid changes. This force pages to come from
ptr_ring, which does the appropate nid check.
For the NUMA_NO_NODE case, when a NIC IRQ is moved to another NUMA
node, we accept that transitioning the alloc cache doesn't happen
immediately. The preferred nid change runtime via consulting
numa_mem_id() based on the CPU processing RX-packets.
Notice, to avoid stressing the page buddy allocator and avoid doing too
much work under softirq with preempt disabled, the NUMA check at
ptr_ring dequeue will break the refill cycle, when detecting a NUMA
mismatch. This will cause a slower transition, but its done on purpose.
Fixes: d5394610b1 ("page_pool: Don't recycle non-reusable pages")
Reported-by: Li RongQing <lirongqing@baidu.com>
Reported-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Introduce the following parameters in order to add the possibility to sync
DMA memory for device before putting allocated pages in the page_pool
caches:
- PP_FLAG_DMA_SYNC_DEV: if set in page_pool_params flags, all pages that
the driver gets from page_pool will be DMA-synced-for-device according
to the length provided by the device driver. Please note DMA-sync-for-CPU
is still device driver responsibility
- offset: DMA address offset where the DMA engine starts copying rx data
- max_len: maximum DMA memory size page_pool is allowed to flush. This
is currently used in __page_pool_alloc_pages_slow routine when pages
are allocated from page allocator
These parameters are supposed to be set by device drivers.
This optimization reduces the length of the DMA-sync-for-device.
The optimization is valid because pages are initially
DMA-synced-for-device as defined via max_len. At RX time, the driver
will perform a DMA-sync-for-CPU on the memory for the packet length.
What is important is the memory occupied by packet payload, because
this is the area CPU is allowed to read and modify. As we don't track
cache-lines written into by the CPU, simply use the packet payload length
as dma_sync_size at page_pool recycle time. This also take into account
any tail-extend.
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
A page is NOT reusable when at least one of the following is true:
1) allocated when system was under some pressure. (page_is_pfmemalloc)
2) belongs to a different NUMA node than pool->p.nid.
To update pool->p.nid users should call page_pool_update_nid().
Holding on to such pages in the pool will hurt the consumer performance
when the pool migrates to a different numa node.
Performance testing:
XDP drop/tx rate and TCP single/multi stream, on mlx5 driver
while migrating rx ring irq from close to far numa:
mlx5 internal page cache was locally disabled to get pure page pool
results.
CPU: Intel(R) Xeon(R) CPU E5-2603 v4 @ 1.70GHz
NIC: Mellanox Technologies MT27700 Family [ConnectX-4] (100G)
XDP Drop/TX single core:
NUMA | XDP | Before | After
---------------------------------------
Close | Drop | 11 Mpps | 10.9 Mpps
Far | Drop | 4.4 Mpps | 5.8 Mpps
Close | TX | 6.5 Mpps | 6.5 Mpps
Far | TX | 3.5 Mpps | 4 Mpps
Improvement is about 30% drop packet rate, 15% tx packet rate for numa
far test.
No degradation for numa close tests.
TCP single/multi cpu/stream:
NUMA | #cpu | Before | After
--------------------------------------
Close | 1 | 18 Gbps | 18 Gbps
Far | 1 | 15 Gbps | 18 Gbps
Close | 12 | 80 Gbps | 80 Gbps
Far | 12 | 68 Gbps | 80 Gbps
In all test cases we see improvement for the far numa case, and no
impact on the close numa case.
The impact of adding a check per page is very negligible, and shows no
performance degradation whatsoever, also functionality wise it seems more
correct and more robust for page pool to verify when pages should be
recycled, since page pool can't guarantee where pages are coming from.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Add page_pool_update_nid() to be called by page pool consumers when they
detect numa node changes.
It will update the page pool nid value to start allocating from the new
effective numa node.
This is to mitigate page pool allocating pages from a wrong numa node,
where the pool was originally allocated, and holding on to pages that
belong to a different numa node, which causes performance degradation.
For pages that are already being consumed and could be returned to the
pool by the consumer, in next patch we will add a check per page to avoid
recycling them back to the pool and return them to the page allocator.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
This patch is to define a inline function skb_csum_is_sctp(), and
also replace all places where it checks if it's a SCTP CSUM skb.
This function would be used later in many networking drivers in
the following patches.
Suggested-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Sync code to the same with tk4 pub/lts/0017-kabi, except deleted rue
and wujing. Partners can submit pull requests to this branch, and we
can pick the commits to tk4 pub/lts/0017-kabi easly.
Signed-off-by: Jianping Liu <frankjpliu@tencent.com>
Gitee limit the repo's size to 3GB, to reduce the size of the code,
sync codes to ock 5.4.119-20.0009.21 in one commit.
Signed-off-by: Jianping Liu <frankjpliu@tencent.com>
Sync kernel codes to the same with 590eaf1fec ("Init Repo base on
linux 5.4.32 long term, and add base tlinux kernel interfaces."), which
is from tk4, and it is the base of tk4.
Signed-off-by: Jianping Liu <frankjpliu@tencent.com>
kobject_put() should only be called in error path.
Fixes: b8eb718348 ("net-sysfs: Fix reference count leak in rx|netdev_queue_add_kobject")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
kobject_init_and_add takes reference even when it fails. This has
to be given up by the caller in error handling. Otherwise memory
allocated by kobject_init_and_add is never freed. Originally found
by Syzkaller:
BUG: memory leak
unreferenced object 0xffff8880679f8b08 (size 8):
comm "netdev_register", pid 269, jiffies 4294693094 (age 12.132s)
hex dump (first 8 bytes):
72 78 2d 30 00 36 20 d4 rx-0.6 .
backtrace:
[<000000008c93818e>] __kmalloc_track_caller+0x16e/0x290
[<000000001f2e4e49>] kvasprintf+0xb1/0x140
[<000000007f313394>] kvasprintf_const+0x56/0x160
[<00000000aeca11c8>] kobject_set_name_vargs+0x5b/0x140
[<0000000073a0367c>] kobject_init_and_add+0xd8/0x170
[<0000000088838e4b>] net_rx_queue_update_kobjects+0x152/0x560
[<000000006be5f104>] netdev_register_kobject+0x210/0x380
[<00000000e31dab9d>] register_netdevice+0xa1b/0xf00
[<00000000f68b2465>] __tun_chr_ioctl+0x20d5/0x3dd0
[<000000004c50599f>] tun_chr_ioctl+0x2f/0x40
[<00000000bbd4c317>] do_vfs_ioctl+0x1c7/0x1510
[<00000000d4c59e8f>] ksys_ioctl+0x99/0xb0
[<00000000946aea81>] __x64_sys_ioctl+0x78/0xb0
[<0000000038d946e5>] do_syscall_64+0x16f/0x580
[<00000000e0aa5d8f>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[<00000000285b3d1a>] 0xffffffffffffffff
Cc: David Miller <davem@davemloft.net>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When setting the dump's time-stamp, use ktime_get_real in addition to
jiffies. This simplifies the user space implementation and bypasses
some inconsistent behavior with translating jiffies to current time.
The time taken is transformed into nsec, to comply with y2038 issue.
Fixes: c8e1da0bf9 ("devlink: Add health report functionality")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a race between driver code that does setup/cleanup of device
and devlink reload operation that in some drivers works with the same
code. Use after free could we easily obtained by running:
while true; do
echo "0000:00:10.0" >/sys/bus/pci/drivers/mlxsw_spectrum2/bind
devlink dev reload pci/0000:00:10.0 &
echo "0000:00:10.0" >/sys/bus/pci/drivers/mlxsw_spectrum2/unbind
done
Fix this by enabling reload only after setup of device is complete and
disabling it at the beginning of the cleanup process.
Reported-by: Ido Schimmel <idosch@mellanox.com>
Fixes: 2d8dc5bbf4 ("devlink: Add support for reload")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
sk_msg_trim() tries to only update curr pointer if it falls into
the trimmed region. The logic, however, does not take into the
account pointer wrapping that sk_msg_iter_var_prev() does nor
(as John points out) the fact that msg->sg is a ring buffer.
This means that when the message was trimmed completely, the new
curr pointer would have the value of MAX_MSG_FRAGS - 1, which is
neither smaller than any other value, nor would it actually be
correct.
Special case the trimming to 0 length a little bit and rework
the comparison between curr and end to take into account wrapping.
This bug caused the TLS code to not copy all of the message, if
zero copy filled in fewer sg entries than memcopy would need.
Big thanks to Alexander Potapenko for the non-KMSAN reproducer.
v2:
- take into account that msg->sg is a ring buffer (John).
Link: https://lore.kernel.org/netdev/20191030160542.30295-1-jakub.kicinski@netronome.com/ (v1)
Fixes: d829e9c411 ("tls: convert to generic sk_msg interface")
Reported-by: syzbot+f8495bff23a879a6d0bd@syzkaller.appspotmail.com
Reported-by: syzbot+6f50c99e8f6194bf363f@syzkaller.appspotmail.com
Co-developed-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When netdevice with offloaded BPF programs is destroyed
the programs are orphaned and removed from the program
IDA - their IDs get released (the programs may remain
accessible via existing open file descriptors and pinned
files). After IDs are released they are set to 0.
This confuses dev_change_xdp_fd() because it compares
the __dev_xdp_query() result where 0 means no program
with prog->aux->id where 0 means orphaned.
dev_change_xdp_fd() would have incorrectly returned success
even though it had not installed the program.
Since drivers already catch this case via bpf_offload_dev_match()
let them handle this case. The error message drivers produce in
this case ("program loaded for a different device") is in fact
correct as the orphaned program must had to be loaded for a
different device.
Fixes: c14a9f633d ("net: Don't call XDP_SETUP_PROG when nothing is changed")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A simple typo fix in the nl error message (fbd -> fdb).
CC: David Ahern <dsahern@gmail.com>
Fixes: 8c6e137fbc ("rtnetlink: Update rtnl_fdb_dump for strict data checking")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Busy polling usually runs without locks.
Let's use skb_queue_empty_lockless() instead of skb_queue_empty()
Also uses READ_ONCE() in __skb_try_recv_datagram() to address
a similar potential problem.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Many poll() handlers are lockless. Using skb_queue_empty_lockless()
instead of skb_queue_empty() is more appropriate.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
pull-request: bpf 2019-10-27
The following pull-request contains BPF updates for your *net* tree.
We've added 7 non-merge commits during the last 11 day(s) which contain
a total of 7 files changed, 66 insertions(+), 16 deletions(-).
The main changes are:
1) Fix two use-after-free bugs in relation to RCU in jited symbol exposure to
kallsyms, from Daniel Borkmann.
2) Fix NULL pointer dereference in AF_XDP rx-only sockets, from Magnus Karlsson.
3) Fix hang in netdev unregister for hash based devmap as well as another overflow
bug on 32 bit archs in memlock cost calculation, from Toke Høiland-Jørgensen.
4) Fix wrong memory access in LWT BPF programs on reroute due to invalid dst.
Also fix BPF selftests to use more compatible nc options, from Jiri Benc.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
memset() the structure ethtool_wolinfo that has padded bytes
but the padded bytes have not been zeroed out.
Signed-off-by: zhanglin <zhang.lin16@zte.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
In rtnl_net_notifyid(), we certainly can't pass a null GFP flag to
rtnl_notify(). A GFP_KERNEL flag would be fine in most circumstances,
but there are a few paths calling rtnl_net_notifyid() from atomic
context or from RCU critical sections. The later also precludes the use
of gfp_any() as it wouldn't detect the RCU case. Also, the nlmsg_new()
call is wrong too, as it uses GFP_KERNEL unconditionally.
Therefore, we need to pass the GFP flags as parameter and propagate it
through function calls until the proper flags can be determined.
In most cases, GFP_KERNEL is fine. The exceptions are:
* openvswitch: ovs_vport_cmd_get() and ovs_vport_cmd_dump()
indirectly call rtnl_net_notifyid() from RCU critical section,
* rtnetlink: rtmsg_ifinfo_build_skb() already receives GFP flags as
parameter.
Also, in ovs_vport_cmd_build_info(), let's change the GFP flags used
by nlmsg_new(). The function is allowed to sleep, so better make the
flags consistent with the ones used in the following
ovs_vport_cmd_fill_info() call.
Found by code inspection.
Fixes: 9a9634545c ("netns: notify netns id events")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jie Wang