| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Reported on the Turris forum, mvneta provokes kernel warnings in the
architecture DMA mapping code when mvneta_setup_txqs() fails to
allocate memory. This happens because when mvneta_cleanup_txqs() is
called in the mvneta_stop() path, we leave pointers in the structure
that have been freed.
Then on mvneta_open(), we call mvneta_setup_txqs(), which starts
allocating memory. On memory allocation failure, mvneta_cleanup_txqs()
will walk all the queues freeing any non-NULL pointers - which includes
pointers that were previously freed in mvneta_stop().
Fix this by setting these pointers to NULL to prevent double-freeing
of the same memory.
Fixes: 2adb719d74f6 ("net: mvneta: Implement software TSO")
Link: https://forum.turris.cz/t/random-kernel-exceptions-on-hbl-tos-7-0/18865/8
Signed-off-by: Russell King (Oracle) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
Since commit 31c8db2c4fa7 ("ice: implement devlink reinit action"), the ice
driver does support driver re-initialization via devlink reload. Remove the
stale comment indicating that the driver lacks this support from the
ice_devlink_ops structure.
Signed-off-by: Jacob Keller <[email protected]>
Cc: Michal Swiatkowski <[email protected]>
Reviewed-by: Michal Swiatkowski <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
phydev is assigned a value right away, no need to initialize it.
Signed-off-by: Wolfram Sang <[email protected]>
Reviewed-by: Geert Uytterhoeven <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2023-03-28
Dragos Tatulea says:
====================
net/mlx5e: RX, Drop page_cache and fully use page_pool
For page allocation on the rx path, the mlx5e driver has been using an
internal page cache in tandem with the page pool. The internal page
cache uses a queue for page recycling which has the issue of head of
queue blocking.
This patch series drops the internal page_cache altogether and uses the
page_pool to implement everything that was done by the page_cache
before:
* Let the page_pool handle dma mapping and unmapping.
* Use fragmented pages with fragment counter instead of tracking via
page ref.
* Enable skb recycling.
The patch series has the following effects on the rx path:
* Improved performance for the cases when there was low page recycling
due to head of queue blocking in the internal page_cache. The test
for this was running a single iperf TCP stream to a rx queue
which is bound on the same cpu as the application.
|-------------+--------+--------+------+---------|
| rq type | before | after | unit | diff |
|-------------+--------+--------+------+---------|
| striding rq | 30.1 | 31.4 | Gbps | 4.14 % |
| legacy rq | 30.2 | 33.0 | Gbps | 8.48 % |
|-------------+--------+--------+------+---------|
* Small XDP performance degradation. The test was is XDP drop
program running on a single rx queue with small packets incoming
it looks like this:
|-------------+----------+----------+------+---------|
| rq type | before | after | unit | diff |
|-------------+----------+----------+------+---------|
| striding rq | 19725449 | 18544617 | pps | -6.37 % |
| legacy rq | 19879931 | 18631841 | pps | -6.70 % |
|-------------+----------+----------+------+---------|
This will be handled in a different patch series by adding support for
multi-packet per page.
* For other cases the performance is roughly the same.
The above numbers were obtained on the following system:
24 core Intel(R) Xeon(R) Platinum 8380 CPU @ 2.30GHz
32 GB RAM
ConnectX-7 single port
The breakdown on the patch series is the following:
* Preparations for introducing the mlx5e_frag_page struct.
* Delete the mlx5e_page_cache struct.
* Enable dma mapping from page_pool.
* Enable skb recycling and fragment counting.
* Do deferred release of pages (just before alloc) to ensure better
page_pool cache utilization.
====================
* tag 'mlx5-updates-2023-03-28' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
net/mlx5e: RX, Remove unnecessary recycle parameter and page_cache stats
net/mlx5e: RX, Break the wqe bulk refill in smaller chunks
net/mlx5e: RX, Increase WQE bulk size for legacy rq
net/mlx5e: RX, Split off release path for xsk buffers for legacy rq
net/mlx5e: RX, Defer page release in legacy rq for better recycling
net/mlx5e: RX, Change wqe last_in_page field from bool to bit flags
net/mlx5e: RX, Defer page release in striding rq for better recycling
net/mlx5e: RX, Rename xdp_xmit_bitmap to a more generic name
net/mlx5e: RX, Enable skb page recycling through the page_pool
net/mlx5e: RX, Enable dma map and sync from page_pool allocator
net/mlx5e: RX, Remove internal page_cache
net/mlx5e: RX, Store SHAMPO header pages in array
net/mlx5e: RX, Remove alloc unit layout constraint for striding rq
net/mlx5e: RX, Remove alloc unit layout constraint for legacy rq
net/mlx5e: RX, Remove mlx5e_alloc_unit argument in page allocation
====================
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
bnxt_fw_to_ethtool_speed() is missing the case statement for 200G
link speed reported by firmware. As a result, ethtool will report
unknown speed when the firmware reports 200G link speed.
Fixes: 532262ba3b84 ("bnxt_en: ethtool: support PAM4 link speeds up to 200G")
Signed-off-by: Michael Chan <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
Fix 57502 and 57508 NPAR description string entries. The typos
caused these devices to not match up with lspci output.
Fixes: 49c98421e6ab ("bnxt_en: Add PCI IDs for 57500 series NPAR devices.")
Reviewed-by: Pavan Chebbi <[email protected]>
Signed-off-by: Kalesh AP <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
When the selftest command fails, driver is not reporting the failure
by updating the "test->flags" when bnxt_close_nic() fails.
Fixes: eb51365846bc ("bnxt_en: Add basic ethtool -t selftest support.")
Reviewed-by: Pavan Chebbi <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>
Signed-off-by: Kalesh AP <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
Fix invalid registers dump from ethtool -d ethX after adapter self test
by ethtool -t ethY. It causes invalid data display.
The problem was caused by overwriting i40e_reg_list[].elements
which is common for ethtool self test and dump.
Fixes: 22dd9ae8afcc ("i40e: Rework register diagnostic")
Signed-off-by: Radoslaw Tyl <[email protected]>
Reviewed-by: Michal Swiatkowski <[email protected]>
Tested-by: Arpana Arland <[email protected]> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <[email protected]>
Reviewed-by: Leon Romanovsky <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2023-03-28 (ice)
This series contains updates to ice driver only.
Jesse fixes mismatched header documentation reported when building with
W=1.
Brett restricts setting of VSI context to only applicable fields for the
given ICE_AQ_VSI_PROP_Q_OPT_VALID bit.
Junfeng adds check when adding Flow Director filters that conflict with
existing filter rules.
Jakob Koschel adds interim variable for iterating to prevent possible
misuse after looping.
* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue:
ice: fix invalid check for empty list in ice_sched_assoc_vsi_to_agg()
ice: add profile conflict check for AVF FDIR
ice: Fix ice_cfg_rdma_fltr() to only update relevant fields
ice: fix W=1 headers mismatch
====================
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
clang 16.0.0 with W=1 reports:
drivers/net/ethernet/amazon/ena/ena_netdev.c:1901:6: error: variable 'tx_bytes' set but not used [-Werror,-Wunused-but-set-variable]
u32 tx_bytes = 0;
The variable is not used so remove it.
Signed-off-by: Simon Horman <[email protected]>
Acked-by: Shay Agroskin <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
The h and the f letters are swapped so it unlocks the wrong lock.
Fixes: 577f0d1b1c5f ("octeon_ep: add separate mailbox command and response queues")
Signed-off-by: Dan Carpenter <[email protected]>
Reviewed-by: Leon Romanovsky <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
build_skb() no longer accepts slab buffers. Since slab use is fairly
uncommon we prefer the drivers to call a separate slab_build_skb()
function appropriately.
bnx2x uses the old semantics where size of 0 meant buffer from slab.
It sets the fp->rx_frag_size to 0 for MTUs which don't fit in a page.
It needs to call slab_build_skb().
This fixes the WARN_ONCE() of incorrect API use seen with bnx2x.
Reported-by: Thomas Voegtle <[email protected]>
Link: https://lore.kernel.org/all/[email protected]/
Fixes: ce098da1497c ("skbuff: Introduce slab_build_skb()")
Reviewed-by: Leon Romanovsky <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
The HNS3 driver supports Wake-on-LAN, which can wake up
the server from power off state to power on state by magic
packet or magic security packet.
ChangeLog:
v1->v2:
Deleted the debugfs function that overlaps with the ethtool function
from suggestion of Andrew Lunn.
v2->v3:
Return the wol configuration stored in driver,
suggested by Alexander H Duyck.
v3->v4:
Add a helper to go from netdev to the local struct,
suggested by Simon Horman and Jakub Kicinski.
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: Hao Lan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
A 'foreign' rule is one for which the net_dev is not the sfc netdevice
or any of its representors. The driver registers indirect flow blocks
for tunnel netdevs so that it can offload decap rules. For example:
tc filter add dev vxlan0 parent ffff: protocol ipv4 flower \
enc_src_ip 10.1.0.2 enc_dst_ip 10.1.0.1 \
enc_key_id 1000 enc_dst_port 4789 \
action tunnel_key unset \
action mirred egress redirect dev $REPRESENTOR
When notified of a rule like this, register an encap match on the IP
and dport tuple (creating an Outer Rule table entry) and insert an MAE
action rule to perform the decapsulation and deliver to the representee.
Moved efx_tc_delete_rule() below efx_tc_flower_release_encap_match() to
avoid the need for a forward declaration.
Signed-off-by: Edward Cree <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Add a hashtable to detect duplicate and conflicting matches. If match
is not a duplicate, call MAE functions to add/remove it from OR table.
Calling code not added yet, so mark the new functions as unused.
Signed-off-by: Edward Cree <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
An encap match corresponds to an entry in the exact-match Outer Rule
table; the lookup response includes the encap type (protocol) allowing
the hardware to continue parsing into the inner headers.
Signed-off-by: Edward Cree <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Translate the fields from flow dissector into struct efx_tc_match.
In efx_tc_flower_replace(), reject filters that match on them, because
only 'foreign' filters (i.e. those for which the ingress dev is not
the sfc netdev or any of its representors, e.g. a tunnel netdev) can
use them.
Signed-off-by: Edward Cree <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Extend the MAE caps check to validate that the hardware supports these
outer-header matches where used by the driver.
Extend efx_mae_populate_match_criteria() to fill in the outer rule ID
and VNI match fields.
Nothing yet populates these match fields, nor creates outer rules.
Signed-off-by: Edward Cree <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Includes an explanation of the lifetime of the 'cursor' action-set `act`.
Signed-off-by: Edward Cree <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Some code defines the IPv6 wildcard address as a local variable and
use it with memcmp() or ipv6_addr_equal().
Let's use in6addr_any and ipv6_addr_any() instead.
Signed-off-by: Kuniyuki Iwashima <[email protected]>
Reviewed-by: Mark Bloch <[email protected]>
Reviewed-by: David Ahern <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2023-03-20
mlx5 dynamic msix
This patch series adds support for dynamic msix vectors allocation in mlx5.
Eli Cohen Says:
================
The following series of patches modifies mlx5_core to work with the
dynamic MSIX API. Currently, mlx5_core allocates all the interrupt
vectors it needs and distributes them amongst the consumers. With the
introduction of dynamic MSIX support, which allows for allocation of
interrupts more than once, we now allocate vectors as we need them.
This allows other drivers running on top of mlx5_core to allocate
interrupt vectors for their own use. An example for this is mlx5_vdpa,
which uses these vectors to propagate interrupts directly from the
hardware to the vCPU [1].
As a preparation for using this series, a use after free issue is fixed
in lib/cpu_rmap.c and the allocator for rmap entries has been modified.
A complementary API for irq_cpu_rmap_add() has also been introduced.
[1] https://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux.git/patch/?id=0f2bf1fcae96a83b8c5581854713c9fc3407556e
================
* tag 'mlx5-updates-2023-03-20' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
net/mlx5: Provide external API for allocating vectors
net/mlx5: Use one completion vector if eth is disabled
net/mlx5: Refactor calculation of required completion vectors
net/mlx5: Move devlink registration before mlx5_load
net/mlx5: Use dynamic msix vectors allocation
net/mlx5: Refactor completion irq request/release code
net/mlx5: Improve naming of pci function vectors
net/mlx5: Use newer affinity descriptor
net/mlx5: Modify struct mlx5_irq to use struct msi_map
net/mlx5: Fix wrong comment
net/mlx5e: Coding style fix, add empty line
lib: cpu_rmap: Add irq_cpu_rmap_remove to complement irq_cpu_rmap_add
lib: cpu_rmap: Use allocator for rmap entries
lib: cpu_rmap: Avoid use after free on rmap->obj array entries
====================
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
clang with W=1 reports
drivers/net/ethernet/8390/axnet_cs.c:653:9: error: variable
'xfer_count' set but not used [-Werror,-Wunused-but-set-variable]
int xfer_count = count;
^
This variable is not used so remove it.
Signed-off-by: Tom Rix <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
Using the QDMA tx scheduler to throttle tx to line speed works fine for
switch ports, but apparently caused a regression on non-switch ports.
Based on a number of tests, it seems that this throttling can be safely
dropped without re-introducing the issues on switch ports that the
tx scheduling changes resolved.
Link: https://lore.kernel.org/netdev/trinity-92c3826f-c2c8-40af-8339-bc6d0d3ffea4-1678213958520@3c-app-gmx-bs16/
Fixes: f63959c7eec3 ("net: ethernet: mtk_eth_soc: implement multi-queue support for per-port queues")
Reported-by: Frank Wunderlich <[email protected]>
Reported-by: Daniel Golle <[email protected]>
Tested-by: Daniel Golle <[email protected]>
Signed-off-by: Felix Fietkau <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
This reverts commit ce1fdb065695f49ef6f126d35c1abbfe645d62d5. It turned
out this actually introduces a race condition. netif_running() is not a
suitable check for get_stats.
Reported-by: Sergey Shtylyov <[email protected]>
Signed-off-by: Wolfram Sang <[email protected]>
Reviewed-by: Sergey Shtylyov <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
The cited commit caused the following build break in mlx5 due to a change
in size of MAX_SKB_FRAGS.
error: format '%lu' expects argument of type 'long unsigned int',
but argument 7 has type 'unsigned int' [-Werror=format=]
Fix this by explicit casting.
Fixes: 3948b05950fd ("net: introduce a config option to tweak MAX_SKB_FRAGS")
Signed-off-by: Saeed Mahameed <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
The recycle parameter used during page release is no longer
necessary: the page pool can detect when the page cannot be
recycled to the cache or ring without any outside hint.
The page pool will also take care of cleaning up after itself
once all the inflight pages have been released. So no need to
explicitly release pages to the system.
Remove the internal page_cache stats as the mlx5e_page_cache
struct no longer exists.
Delete the documentation entries along with the stats.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
To avoid overflowing the page pool's cache, don't release the
whole bulk which is usually larger than the cache refill size.
Group release+alloc instead into cache refill units that
allow releasing to the cache and then allocating from the cache.
A refill_unit variable is added as a iteration unit over the
wqe_bulk when doing release+alloc.
For a single ring, single core, default MTU (1500) TCP stream
test the number of pages allocated from the cache directly
(rx_pp_recycle_cached) increases from 0% to 52%:
+---------------------------------------------+
| Page Pool stats (/sec) | Before | After |
+-------------------------+---------+---------+
|rx_pp_alloc_fast | 2145422 | 2193802 |
|rx_pp_alloc_slow | 2 | 0 |
|rx_pp_alloc_empty | 2 | 0 |
|rx_pp_alloc_refill | 34059 | 16634 |
|rx_pp_alloc_waive | 0 | 0 |
|rx_pp_recycle_cached | 0 | 1145818 |
|rx_pp_recycle_cache_full | 0 | 0 |
|rx_pp_recycle_ring | 2179361 | 1064616 |
|rx_pp_recycle_ring_full | 121 | 0 |
+---------------------------------------------+
With this patch, the performance for legacy rq for the above test is
back to baseline.
Signed-off-by: Dragos Tatulea <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Deferred page release was added to legacy rq but its desired effect
(driver releases last fragment to page pool cache) is not yet visible
due to the WQE bulks being too small.
This patch increases the WQE bulk size to span 512 KB and clip it to
one quarter of the rx queue size.
Signed-off-by: Dragos Tatulea <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Don't mix xsk buffer releases with page releases anymore. This is
needed for handling of deferred page release.
Add a new bulk free function for xsk buffers from wqe frags.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Currently, fragmented pages from the page pool can be released
in two ways:
1) In the mlx5e driver when trimming off the unused fragments AND the
associated skb fragments have been released. This path allows
recycling of pages to the page pool cache (allow_direct == true).
2) On the skb release path (last fragment release), which
will always release pages to the page pool ring
(allow_direct == false).
Whichever is releasing the last fragment will be decisive on
where the page gets released: the cache or the ring. So we
obviously want to maximize for doing the release from 1.
This patch does that by deferring the release of page fragments
right before requesting new ones from the page pool. A flag is
added to make sure that there's no release before first alloc
and that XDP_TX fragments are not released prematurely.
This is a preparation patch that doesn't unlock the performance
improvements yet. A followup patch will do that.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Change the bool flag to a bitfield as we'll use it in a downstream patch
in the series to add signaling about skipping a fragment release.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Currently, for striding RQ, fragmented pages from the page pool can
get released in two ways:
1) In the mlx5e driver when trimming off the unused fragments AND the
associated skb fragments have been released. This path allows
recycling of pages to the page pool cache (allow_direct == true).
2) On the skb release path (last fragment release), which
will always release pages to the page pool ring
(allow_direct == false).
Whichever is releasing the last fragment will be decisive on
where the page gets released: the cache or the ring. So we
obviously want to maximize for doing the release from 1.
This patch does that by deferring the release of page fragments
right before requesting new ones from the page pool. Extra care
needs to be taken for the corner cases:
* On first call, make sure that release is not called. The
skip_release_bitmap is used for this purpose.
* On rq shutdown, make sure that all wqes that were not
in the linked list are released.
For a single ring, single core, default MTU (1500) TCP stream
test the number of pages allocated from the cache directly
(rx_pp_recycle_cached) increases from 31 % to 98 %:
+----------------------------------------------+
| Page Pool stats (/sec) | Before | After |
+-------------------------+---------+----------+
|rx_pp_alloc_fast | 2137754 | 2261033 |
|rx_pp_alloc_slow | 47 | 9 |
|rx_pp_alloc_empty | 47 | 9 |
|rx_pp_alloc_refill | 23230 | 819 |
|rx_pp_alloc_waive | 0 | 0 |
|rx_pp_recycle_cached | 672182 | 2209015 |
|rx_pp_recycle_cache_full | 1789 | 0 |
|rx_pp_recycle_ring | 1485848 | 52259 |
|rx_pp_recycle_ring_full | 3003 | 584 |
+----------------------------------------------+
With this patch, the performance in striding rq for the above test is
back to baseline.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
The xdp_xmit_bitmap currently serves only one purpose: to avoid
releasing pages that are still in use due to XDP TX.
A following patch will use this bitmap in a slightly different context
but for the same purpose. So rename the bitmap to a more generic name
that reflects the purpose not the context.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Start using the page_pool skb recycling api to recycle all pages back to
the page pool and stop using atomic page reference counting.
The mlx5e driver used to manage in-flight pages using page refcounting:
for each fragment there were 2 atomic write operations happening (one
for building the skb and one on skb release).
The page_pool api introduced a method to track page fragments more
optimally:
* The page's pp_fragment_count is set to a large bias on page alloc
(1 x atomic write operation).
* The driver tracks the actual page fragments in a non atomic variable.
* When the skb is recycled, pp_fragment_count is decremented
(atomic write operation).
* When page is released in the driver, the unused number of fragments
(relative to the bias) is deducted from pp_fragment_count (atomic
write operation).
* Last page defragmentation will only be an atomic read.
So in total there are `number of fragments + 1` atomic write ops. As
opposed to previously: `2 * frags` atomic writes ops.
Pages are wrapped in a mlx5e_frag_page structure which also contains the
number of fragments. This makes it easy to count the fragments in the
driver.
This change brings performance improvements for the case when the old rx
page_cache had low recycling rates due to head of queue blocking. For a
iperf3 TCP test with a single stream, on a single core (iperf and receive
queue running on same core), the following improvements can be noticed:
* Striding rq:
- before (net-next baseline): bitrate = 30.1 Gbits/sec
- after : bitrate = 31.4 Gbits/sec (diff: 4.14 %)
* Legacy rq:
- before (net-next baseline): bitrate = 30.2 Gbits/sec
- after : bitrate = 33.0 Gbits/sec (diff: 8.48 %)
There are 2 temporary performance degradations introduced:
1) TCP streams that had a good recycling rate with the old page_cache
have a degradation for both striding and linear rq. This is due to
very low page pool cache recycling: the pages are released during skb
recycle which will release pages to the page pool ring for safety.
The following patches in this series will tackle this problem by
deferring the page release in the driver to increase the
chance of having pages recycled to the cache.
2) XDP performance is now lower (4-5 %) due to the higher number of
atomic operations used for fragment management. But this opens the
door for supporting multiple packets per page in XDP, which will
bring a big gain.
Otherwise, performance is similar to baseline.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Remove driver dma mapping and unmapping of pages. Let the
page_pool api do it.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
This patch removes the internal rx page_cache and uses the generic
page_pool api only. It used to be that the page_pool couldn't handle all
the mlx5 driver usecases, but with the introduction of skb recycling and
page fragmentaton in the page_pool full switch can now be made. Some
benfits of this transition:
* Better page recycling in the cases when the page_cache was suffering
from head of queue blocking. The page_pool doesn't have this issue.
* DMA mapping/unmapping can be managed by the page_pool.
* mlx5e_rq size reduced by more than 50% due to the page_cache array
being deleted.
This patch only removes the page_cache. Downstream patches will enable
the required page_pool features and will add further fine-tuning.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Save allocated SHAMPO header pages to an array to which the
mlx5e_dma_info page will point to.
This change is a preparation for introducing mlx5e_frag_page structure
in a downstream patch. There's no new functionality introduced.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
This change removes the usage of mlx5e_alloc_unit union for
striding rq. The change is more straightforward than legacy rq as
the alloc units union is already in place.
This patch only moves things around: instead of an array of unions make
it a union of arrays. This has the effect that each mlx5e_mpw_info will
allocate the largest possible size of the array member. For xsk this
means that the array of xdp_buff pointers for the wqe will still be
contiguous, but there will be some extra unused bytes at the end of the
array.
As further patch in the series will add the mlx5e_frag_page struct for
which the described size constraint will no longer hold.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
The mlx5e_alloc_unit union is conveniently used to store arrays of
pointers to struct page or struct xdp_buff (for xsk). The union is
currently expected to have the size of a pointer for xsk batch
allocations to work. This is conveniet for the current state of the
code but makes it impossible to add a structure of a different size
to the alloc unit.
A further patch in the series will add the mlx5e_frag_page struct for
which the described size constraint will no longer hold.
This change removes the usage of mlx5e_alloc_unit union for legacy rq:
- A union of arrays is introduced (mlx5e_alloc_units) to replace the
array of unions to allow structures of different sizes.
- Each fragment has a pointer to a unit in the mlx5e_alloc_units array.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
Change internal page cache and page pool api to use a struct page **
instead of a mlx5e_alloc_unit *.
This is the first change in a series which is meant to remove the
mlx5e_alloc_unit altogether.
Signed-off-by: Dragos Tatulea <[email protected]>
Reviewed-by: Tariq Toukan <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
|
|
The code implicitly assumes that the list iterator finds a correct
handle. If 'vsi_handle' is not found the 'old_agg_vsi_info' was
pointing to an bogus memory location. For safety a separate list
iterator variable should be used to make the != NULL check on
'old_agg_vsi_info' correct under any circumstances.
Additionally Linus proposed to avoid any use of the list iterator
variable after the loop, in the attempt to move the list iterator
variable declaration into the macro to avoid any potential misuse after
the loop. Using it in a pointer comparison after the loop is undefined
behavior and should be omitted if possible [1].
Fixes: 37c592062b16 ("ice: remove the VSI info from previous agg")
Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ [1]
Signed-off-by: Jakob Koschel <[email protected]>
Tested-by: Arpana Arland <[email protected]> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <[email protected]>
|
|
Add profile conflict check while adding some FDIR rules to avoid
unexpected flow behavior, rules may have conflict including:
IPv4 <---> {IPv4_UDP, IPv4_TCP, IPv4_SCTP}
IPv6 <---> {IPv6_UDP, IPv6_TCP, IPv6_SCTP}
For example, when we create an FDIR rule for IPv4, this rule will work
on packets including IPv4, IPv4_UDP, IPv4_TCP and IPv4_SCTP. But if we
then create an FDIR rule for IPv4_UDP and then destroy it, the first
FDIR rule for IPv4 cannot work on pkt IPv4_UDP then.
To prevent this unexpected behavior, we add restriction in software
when creating FDIR rules by adding necessary profile conflict check.
Fixes: 1f7ea1cd6a37 ("ice: Enable FDIR Configure for AVF")
Signed-off-by: Junfeng Guo <[email protected]>
Tested-by: Rafal Romanowski <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
The current implementation causes ice_vsi_update() to update all VSI
fields based on the cached VSI context. This also assumes that the
ICE_AQ_VSI_PROP_Q_OPT_VALID bit is set. This can cause problems if the
VSI context is not correctly synced by the driver. Fix this by only
updating the fields that correspond to ICE_AQ_VSI_PROP_Q_OPT_VALID.
Also, make sure to save the updated result in the cached VSI context
on success.
Fixes: 348048e724a0 ("ice: Implement iidc operations")
Co-developed-by: Robert Malz <[email protected]>
Signed-off-by: Robert Malz <[email protected]>
Signed-off-by: Brett Creeley <[email protected]>
Signed-off-by: Jesse Brandeburg <[email protected]>
Reviewed-by: Piotr Raczynski <[email protected]>
Tested-by: Jakub Andrysiak <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
make modules W=1 returns:
.../ice/ice_txrx_lib.c:448: warning: Function parameter or member 'first_idx' not described in 'ice_finalize_xdp_rx'
.../ice/ice_txrx.c:948: warning: Function parameter or member 'ntc' not described in 'ice_get_rx_buf'
.../ice/ice_txrx.c:1038: warning: Excess function parameter 'rx_buf' description in 'ice_construct_skb'
Fix these warnings by adding and deleting the deviant arguments.
Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Fixes: d7956d81f150 ("ice: Pull out next_to_clean bump out of ice_put_rx_buf()")
CC: Maciej Fijalkowski <[email protected]>
Signed-off-by: Jesse Brandeburg <[email protected]>
Reviewed-by: Piotr Raczynski <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
By default, the tagged ingress packets to the switch from the host port
P0 get internal switch priority assigned equal to the DMA CPPI channel
number they came from, unless CPSW_P0_CONTROL_REG.RX_REMAP_VLAN is enabled.
This causes issues with applying QoS policies and mapping packets on
external port fifos, because the default configuration is vlan_aware and
DMA CPPI channels are shared between all external ports.
Hence enable CPSW_P0_CONTROL_REG.RX_REMAP_VLAN so packet will preserve
internal switch priority assigned following the VLAN(priority) tag no
matter through which DMA CPPI Channels packets enter the switch.
Signed-off-by: Grygorii Strashko <[email protected]>
Signed-off-by: Siddharth Vadapalli <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>
|
|
Enable rate limiting TX DMA queues for CPSW interface by configuring the
rate in absolute Mb/s units per TX queue.
Example:
ethtool -L eth0 tx 4
echo 100 > /sys/class/net/eth0/queues/tx-0/tx_maxrate
echo 200 > /sys/class/net/eth0/queues/tx-1/tx_maxrate
echo 50 > /sys/class/net/eth0/queues/tx-2/tx_maxrate
echo 30 > /sys/class/net/eth0/queues/tx-3/tx_maxrate
# disable
echo 0 > /sys/class/net/eth0/queues/tx-0/tx_maxrate
Signed-off-by: Grygorii Strashko <[email protected]>
Signed-off-by: Siddharth Vadapalli <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>
|
|
SMSC911x doesn't need mdiobus suspend/resume, that's why it sets
'mac_managed_pm'. However, setting it needs to be moved from init to
probe, so mdiobus PM functions will really never be called (e.g. when
the interface is not up yet during suspend/resume).
Fixes: 3ce9f2bef755 ("net: smsc911x: Stop and start PHY during suspend and resume")
Suggested-by: Heiner Kallweit <[email protected]>
Signed-off-by: Wolfram Sang <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>
|
|
In PPPoE add all IPv4 header option length to the parser
and adjust the L3 and L4 offset accordingly.
Currently the L4 match does not work with PPPoE and
all packets are matched as L3 IP4 OPT.
Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: Sven Auhagen <[email protected]>
Signed-off-by: Paolo Abeni <[email protected]>
|
|
The mvpp2 parser entry for QinQ has the inner and outer VLAN
in the wrong order.
Fix the problem by swapping them.
Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: Sven Auhagen <[email protected]>
Reviewed-by: Marcin Wojtas <[email protected]>
Signed-off-by: Paolo Abeni <[email protected]>
|
|
Add missing IP Fragmentation Flag.
Fixes: f9358e12a0af ("net: mvpp2: split ingress traffic into multiple flows")
Signed-off-by: Sven Auhagen <[email protected]>
Reviewed-by: Marcin Wojtas <[email protected]>
Signed-off-by: Paolo Abeni <[email protected]>
|