This patch caches doorbell address directly in struct mlx4_en_tx_ring.

This removes the need to bring in cpu caches whole struct mlx4_uar
in fast path.

Note that mlx4_uar is not guaranteed to be on a local node,
because mlx4_bf_alloc() uses a single free list (priv->bf_list)
regardless of its node parameter.

This kind of change does matter in presence of light/moderate traffic.
In high stress, this read-only line would be kept hot in caches.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: NTariq Toukan <tariqt@nvidia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The wrappers in include/linux/pci-dma-compat.h should go away.

The patch has been generated with the coccinelle script below.

It has been hand modified to use 'dma_set_mask_and_coherent()' instead of
'pci_set_dma_mask()/pci_set_consistent_dma_mask()' when applicable.
This is less verbose.

It has been compile tested.

@@
@@
-    PCI_DMA_BIDIRECTIONAL
+    DMA_BIDIRECTIONAL

@@
@@
-    PCI_DMA_TODEVICE
+    DMA_TO_DEVICE

@@
@@
-    PCI_DMA_FROMDEVICE
+    DMA_FROM_DEVICE

@@
@@
-    PCI_DMA_NONE
+    DMA_NONE

@@
expression e1, e2, e3;
@@
-    pci_alloc_consistent(e1, e2, e3)
+    dma_alloc_coherent(&e1->dev, e2, e3, GFP_)

@@
expression e1, e2, e3;
@@
-    pci_zalloc_consistent(e1, e2, e3)
+    dma_alloc_coherent(&e1->dev, e2, e3, GFP_)

@@
expression e1, e2, e3, e4;
@@
-    pci_free_consistent(e1, e2, e3, e4)
+    dma_free_coherent(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
-    pci_map_single(e1, e2, e3, e4)
+    dma_map_single(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
-    pci_unmap_single(e1, e2, e3, e4)
+    dma_unmap_single(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4, e5;
@@
-    pci_map_page(e1, e2, e3, e4, e5)
+    dma_map_page(&e1->dev, e2, e3, e4, e5)

@@
expression e1, e2, e3, e4;
@@
-    pci_unmap_page(e1, e2, e3, e4)
+    dma_unmap_page(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
-    pci_map_sg(e1, e2, e3, e4)
+    dma_map_sg(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
-    pci_unmap_sg(e1, e2, e3, e4)
+    dma_unmap_sg(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
-    pci_dma_sync_single_for_cpu(e1, e2, e3, e4)
+    dma_sync_single_for_cpu(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
-    pci_dma_sync_single_for_device(e1, e2, e3, e4)
+    dma_sync_single_for_device(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
-    pci_dma_sync_sg_for_cpu(e1, e2, e3, e4)
+    dma_sync_sg_for_cpu(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
-    pci_dma_sync_sg_for_device(e1, e2, e3, e4)
+    dma_sync_sg_for_device(&e1->dev, e2, e3, e4)

@@
expression e1, e2;
@@
-    pci_dma_mapping_error(e1, e2)
+    dma_mapping_error(&e1->dev, e2)

@@
expression e1, e2;
@@
-    pci_set_dma_mask(e1, e2)
+    dma_set_mask(&e1->dev, e2)

@@
expression e1, e2;
@@
-    pci_set_consistent_dma_mask(e1, e2)
+    dma_set_coherent_mask(&e1->dev, e2)
Signed-off-by: NChristophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In case error CQE was found while polling TX CQ, the QP is in error
state and all posted WQEs will generate error CQEs without any data
transmitted. Fix it by reopening the channels, via same method used for
TX timeout handling.

In addition add some more info on error CQE and WQE for debug.

Fixes: bd2f631d ("net/mlx4_en: Notify user when TX ring in error state")
Signed-off-by: NMoshe Shemesh <moshe@mellanox.com>
Signed-off-by: NTariq Toukan <tariqt@nvidia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Performance analysis counters are maintained under the MLX4_EN_PERF_STAT
definition, which is never set.
Clean them up, with all related structures and logic.
Signed-off-by: NTariq Toukan <tariqt@nvidia.com>
Reviewed-by: NMoshe Shemesh <moshe@nvidia.com>
Link: https://lore.kernel.org/r/20201118103427.4314-1-tariqt@nvidia.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

netcons calls napi_poll with a budget of 0 to transmit packets.
Handle this by:
 - skipping RX processing
 - do not try to recycle TX packets to the RX cache
Signed-off-by: NJonathan Lemon <jonathan.lemon@gmail.com>
Reviewed-by: NTariq Toukan <tariqt@nvidia.com>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

As part of the W=1 compliation series, these lines all created
warnings about unused variables that were assigned a value. Most
of them are from register reads, but some are just picking up
a return value from a function and never doing anything with it.

Fixed warnings:
.../ethernet/brocade/bna/bnad.c:3280:6: warning: variable ‘rx_count’ set but not used [-Wunused-but-set-variable]
.../ethernet/brocade/bna/bnad.c:3280:6: warning: variable ‘rx_count’ set but not used [-Wunused-but-set-variable]
.../ethernet/cortina/gemini.c:512:6: warning: variable ‘val’ set but not used [-Wunused-but-set-variable]
.../ethernet/cortina/gemini.c:2110:21: warning: variable ‘config0’ set but not used [-Wunused-but-set-variable]
.../ethernet/cavium/liquidio/octeon_device.c:1327:6: warning: variable ‘val32’ set but not used [-Wunused-but-set-variable]
.../ethernet/cavium/liquidio/octeon_device.c:1358:6: warning: variable ‘val32’ set but not used [-Wunused-but-set-variable]
.../ethernet/dec/tulip/media.c:322:8: warning: variable ‘setup’ set but not used [-Wunused-but-set-variable]
.../ethernet/dec/tulip/de4x5.c:4928:13: warning: variable ‘r3’ set but not used [-Wunused-but-set-variable]
.../ethernet/micrel/ksz884x.c:1652:7: warning: variable ‘dummy’ set but not used [-Wunused-but-set-variable]
.../ethernet/micrel/ksz884x.c:1652:7: warning: variable ‘dummy’ set but not used [-Wunused-but-set-variable]
.../ethernet/micrel/ksz884x.c:1652:7: warning: variable ‘dummy’ set but not used [-Wunused-but-set-variable]
.../ethernet/micrel/ksz884x.c:1652:7: warning: variable ‘dummy’ set but not used [-Wunused-but-set-variable]
.../ethernet/micrel/ksz884x.c:4981:6: warning: variable ‘rx_status’ set but not used [-Wunused-but-set-variable]
.../ethernet/micrel/ksz884x.c:6510:6: warning: variable ‘rc’ set but not used [-Wunused-but-set-variable]
.../ethernet/micrel/ksz884x.c:6087: warning: cannot understand function prototype: 'struct hw_regs '
.../ethernet/microchip/lan743x_main.c:161:6: warning: variable ‘int_en’ set but not used [-Wunused-but-set-variable]
.../ethernet/microchip/lan743x_main.c:1702:6: warning: variable ‘int_sts’ set but not used [-Wunused-but-set-variable]
.../ethernet/microchip/lan743x_main.c:3041:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable]
.../ethernet/natsemi/ns83820.c:603:6: warning: variable ‘tbisr’ set but not used [-Wunused-but-set-variable]
.../ethernet/natsemi/ns83820.c:1207:11: warning: variable ‘tanar’ set but not used [-Wunused-but-set-variable]
.../ethernet/marvell/mvneta.c:754:6: warning: variable ‘dummy’ set but not used [-Wunused-but-set-variable]
.../ethernet/neterion/vxge/vxge-traffic.c:33:6: warning: variable ‘val64’ set but not used [-Wunused-but-set-variable]
.../ethernet/neterion/vxge/vxge-traffic.c:160:6: warning: variable ‘val64’ set but not used [-Wunused-but-set-variable]
.../ethernet/neterion/vxge/vxge-traffic.c:490:6: warning: variable ‘val32’ set but not used [-Wunused-but-set-variable]
.../ethernet/neterion/vxge/vxge-traffic.c:2378:6: warning: variable ‘val64’ set but not used [-Wunused-but-set-variable]
.../ethernet/packetengines/yellowfin.c:1063:18: warning: variable ‘yf_size’ set but not used [-Wunused-but-set-variable]
.../ethernet/realtek/8139cp.c:1242:6: warning: variable ‘rc’ set but not used [-Wunused-but-set-variable]
.../ethernet/mellanox/mlx4/en_tx.c:858:6: warning: variable ‘ring_cons’ set but not used [-Wunused-but-set-variable]
.../ethernet/sis/sis900.c:792:6: warning: variable ‘status’ set but not used [-Wunused-but-set-variable]
.../ethernet/sfc/falcon/farch.c:878:11: warning: variable ‘rx_ev_pkt_type’ set but not used [-Wunused-but-set-variable]
.../ethernet/sfc/falcon/farch.c:877:23: warning: variable ‘rx_ev_mcast_pkt’ set but not used [-Wunused-but-set-variable]
.../ethernet/sfc/falcon/farch.c:877:7: warning: variable ‘rx_ev_hdr_type’ set but not used [-Wunused-but-set-variable]
.../ethernet/sfc/falcon/farch.c:876:7: warning: variable ‘rx_ev_other_err’ set but not used [-Wunused-but-set-variable]
.../ethernet/sfc/falcon/farch.c:1646:21: warning: variable ‘buftbl_min’ set but not used [-Wunused-but-set-variable]
.../ethernet/sfc/falcon/farch.c:2535:32: warning: variable ‘spec’ set but not used [-Wunused-but-set-variable]
.../ethernet/via/via-velocity.c:880:6: warning: variable ‘curr_status’ set but not used [-Wunused-but-set-variable]
.../ethernet/ti/tlan.c:656:6: warning: variable ‘rc’ set but not used [-Wunused-but-set-variable]
.../ethernet/ti/davinci_emac.c:1230:6: warning: variable ‘num_tx_pkts’ set but not used [-Wunused-but-set-variable]
.../ethernet/synopsys/dwc-xlgmac-common.c:516:8: warning: variable ‘str’ set but not used [-Wunused-but-set-variable]
.../ethernet/ti/cpsw_new.c:1662:22: warning: variable ‘priv’ set but not used [-Wunused-but-set-variable]

The register reads should be OK, because the current
implementation of readl and friends will always execute even
without an lvalue.

When it makes sense, just remove the lvalue assignment and the
local. Other times, just remove the offending code, and
occasionally, just mark the variable as maybe unused since it
could be used in an ifdef or debug scenario.

Only compile tested with W=1.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Acked-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We found a set but not used variable 'ring_cons' in mlx4_en_xmit(), it will
cause a warning when build the kernel. And after checking the commit record
of this function, we found that it was introduced by a previous patch.

So, We delete this redundant assignment code.

Fixes: 488a9b48 ("net/mlx4_en: Wake TX queues only when there's enough room")
Signed-off-by: NLuo Jiaxing <luojiaxing@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In order to benefit from the new napi_defer_hard_irqs feature,
we need to use napi_complete_done() variant in this driver.

RX path is already using it, this patch implements TX completion side.

mlx4_en_process_tx_cq() now returns the amount of retired packets,
instead of a boolean, so that mlx4_en_poll_tx_cq() can pass
this value to napi_complete_done().
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 9ecc2d86 ("net/mlx4_en: add xdp forwarding and data write support")
brought another indirect call in fast path.

Use INDIRECT_CALL_2() helper to avoid the cost of the indirect call
when/if CONFIG_RETPOLINE=y
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In preparation for unifying the skb_frag and bio_vec, use the fine
accessors which already exist and use skb_frag_t instead of
struct skb_frag_struct.
Signed-off-by: NMatthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

skb->xmit_more hint is now always 0. This switches the mellanox drivers
to the netdev_xmit_more() helper.

Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Boris Pismenny <borisp@mellanox.com>
Cc: Ilya Lesokhin <ilyal@mellanox.com>
Cc: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After the previous patch, all the callers of ndo_select_queue()
provide as a 'fallback' argument netdev_pick_tx.
The only exceptions are nested calls to ndo_select_queue(),
which pass down the 'fallback' available in the current scope
- still netdev_pick_tx.

We can drop such argument and replace fallback() invocation with
netdev_pick_tx(). This avoids an indirect call per xmit packet
in some scenarios (TCP syn, UDP unconnected, XDP generic, pktgen)
with device drivers implementing such ndo. It also clean the code
a bit.

Tested with ixgbe and CONFIG_FCOE=m

With pktgen using queue xmit:
threads		vanilla 	patched
		(kpps)		(kpps)
1		2334		2428
2		4166		4278
4		7895		8100

 v1 -> v2:
 - rebased after helper's name change
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

kzalloc_node(..., GFP_KERNEL, node) will attempt to allocate
memory as close as possible to the node.

There is no need to fallback to kzalloc() if this has failed.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

doorbell only depends on xmit_more and netif_tx_queue_stopped()

Using __netdev_tx_sent_queue() avoids messing with BQL stop flag,
and is more generic.

This patch increases performance on GSO workload by keeping
doorbells to the minimum required.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For most of these calls we can just pass NULL through to the fallback
function as the sb_dev. The only cases where we cannot are the cases where
we might be dealing with either an upper device or a driver that would
have configured things to support an sb_dev itself.

The only driver that has any significant change in this patch set should be
ixgbe as we can drop the redundant functionality that existed in both the
ndo_select_queue function and the fallback function that was passed through
to us.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch makes it so that instead of passing a void pointer as the
accel_priv we instead pass a net_device pointer as sb_dev. Making this
change allows us to pass the subordinate device through to the fallback
function eventually so that we can keep the actual code in the
ndo_select_queue call as focused on possible on the exception cases.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The code in the fallback path has supported XDP in conjunction with the Tx
traffic classification for TCs for over a year now. So instead of just
calling skb_tx_hash for every packet we are better off using the fallback
since that will record the Tx queue to the socket and then that can be used
instead of having to recompute the hash every time.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE()

Please do not apply this to mainline directly, instead please re-run the
coccinelle script shown below and apply its output.

For several reasons, it is desirable to use {READ,WRITE}_ONCE() in
preference to ACCESS_ONCE(), and new code is expected to use one of the
former. So far, there's been no reason to change most existing uses of
ACCESS_ONCE(), as these aren't harmful, and changing them results in
churn.

However, for some features, the read/write distinction is critical to
correct operation. To distinguish these cases, separate read/write
accessors must be used. This patch migrates (most) remaining
ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following
coccinelle script:

----
// Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and
// WRITE_ONCE()

// $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch

virtual patch

@ depends on patch @
expression E1, E2;
@@

- ACCESS_ONCE(E1) = E2
+ WRITE_ONCE(E1, E2)

@ depends on patch @
expression E;
@@

- ACCESS_ONCE(E)
+ READ_ONCE(E)
----
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Signed-off-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: davem@davemloft.net
Cc: linux-arch@vger.kernel.org
Cc: mpe@ellerman.id.au
Cc: shuah@kernel.org
Cc: snitzer@redhat.com
Cc: thor.thayer@linux.intel.com
Cc: tj@kernel.org
Cc: viro@zeniv.linux.org.uk
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

In XDP_TX, some fields in tx_info and tx_desc are constants across
all entries of the different XDP_TX rings.
Assign values to these fields on ring creation time, rather than in
data-path.

Patchset performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Single queue no-RSS optimization ON.

XDP_TX packet rate:
------------------------------
Before    | After     | Gain |
13.7 Mpps | 14.0 Mpps | %2.2 |
------------------------------
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Function mlx4_en_tx_write_desc() is not optimized to use of XDP xmit.
Use the relevant parts inline instead.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The struct net_device parameter was passed only to extract
struct mlx4_en_priv out of it.
Here we pass the priv parameter directly.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In TX data-path, we intentionally do not byte-swap, as documented
in code and in the cited commit log.
This fixes sparse warning:
en_tx.c:720:23: warning: incorrect type in argument 1 (different base types)
en_tx.c:720:23:    expected unsigned int [unsigned] [usertype] <noident>
en_tx.c:720:23:    got restricted __be32 [usertype] doorbell_qpn

Fixes: 492f5add ("net/mlx4_en: Doorbell is byteswapped in Little Endian archs")
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The kernel coding style is to treat sizeof as a function
(ie. with parenthesis) not as an operator.

Also use kcalloc and kmalloc_array
Signed-off-by: NStephen Hemminger <stephen@networkplumber.org>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adding visibility of resource usage of QPs, CQs and counters used by
virtual functions. This feature will be used to give the PF administrator
more data while debugging VF status. Usage info was added to ALLOC_RES
command, to notify the PF if the resource which is being reserved or
allocated for the VF will be used by kernel driver or by user verbs.

Updated reservation and allocation functions of QP, CQ and counter with
additional usage parameter.
Signed-off-by: NMoshe Shemesh <moshe@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The caller to the driver marks GFP_NOIO allocations with help
of memalloc_noio-* calls now. This makes redundant to pass down
to the driver gfp flags, which can be GFP_KERNEL only.

The patch removes the gfp flags argument and updates all driver paths.
Signed-off-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Currently the number of TX queues that are allocated doesn't depend
on the number of TCs, the module always loads with max num of UP
per channel.
In order to prevent the allocation of unnecessary memory, the
module will load with minimum number of UPs per channel, and the
user will be able to control the number of TX queues per channel
by changing the number of TC to 8 using the tc command.
The variable num_up will hold the information about the current
number of UPs.
Due to the change, needed to remove the lines that set the value of
UP to be different than zero in the func "mlx4_en_select_queue",
since now the num of TX queues that are allocated is only one per channel
in default.
In order not to force the UP to be zero in case of only one TC, added
a condition before forcing it in the func "mlx4_en_fill_qp_context".

Tested:
After the module is loaded with minimum number of UP per channel, to
increase num of TCs to 8, use:
tc qdisc add dev ens8 root mqprio num_tc 8
In order to decrease the number of TCs to minimum number of UP per channel,
use:
tc qdisc del dev ens8 root
Signed-off-by: NInbar Karmy <inbark@mellanox.com>
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Cc: Tarick Bedeir <tarick@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some code re-ordering, functionally equivalent.

- The !tx_info->inl check is evaluated anyway in both flows
  (common case/end case). Run it first, this might finish
  the flows earlier.
- dma_unmap calls are identical in both flows, get it out
  of the if block into the common area.

Performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

Gain is too small to be measurable, no degradation sensed.
Results are similar for IPv4 and IPv6.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Cc: kernel-team@fb.com
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Define LOG_TXBB_SIZE, log of TXBB_SIZE, and use it with a shift
operation instead of a multiplication with TXBB_SIZE.
Operations are equivalent as TXBB_SIZE is a power of two.

Performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

Gain is too small to be measurable, no degradation sensed.
Results are similar for IPv4 and IPv6.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Cc: kernel-team@fb.com
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of having their own NAPIs, XDP TX completion queues get
polled within the corresponding RX NAPI.
This prevents any possible race on TX ring prod/cons indices,
between the context that issues the transmits (RX NAPI) and the
context that handles the completions (was previously done in
a separate NAPI).

This also improves performance, as it decreases the number
of NAPIs running on a CPU, saving the overhead of syncing
and switching between the contexts.

Performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Single queue no-RSS optimization ON.

XDP_TX packet rate:
-------------------------------------
     | Before    | After     | Gain |
IPv4 | 12.0 Mpps | 13.8 Mpps |  15% |
IPv6 | 12.0 Mpps | 13.8 Mpps |  15% |
-------------------------------------
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Cc: kernel-team@fb.com
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Several performance improvements in XDP TX datapath,
including:
- Ring a single doorbell for XDP TX ring per NAPI budget,
  instead of doing it per a lower threshold (was 8).
  This includes removing the flow of immediate doorbell ringing
  in case of a full TX ring.
- Compiler branch predictor hints.
- Calculate values in compile time rather than in runtime.

Performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Single queue no-RSS optimization ON.

XDP_TX packet rate:
-------------------------------------
     | Before    | After     | Gain |
IPv4 | 10.3 Mpps | 12.0 Mpps |  17% |
IPv6 | 10.3 Mpps | 12.0 Mpps |  17% |
-------------------------------------
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Cc: kernel-team@fb.com
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Several small code and performance improvements in stack TX datapath,
including:
- Compiler branch predictor hints.
- Minimize variables scope.
- Move tx_info non-inline flow handling to a separate function.
- Calculate data_offset in compile time rather than in runtime
  (for !lso_header_size branch).
- Avoid trinary-operator ("?") when value can be preset in a matching
  branch.

Performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

Gain is too small to be measurable, no degradation sensed.
Results are similar for IPv4 and IPv6.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Cc: kernel-team@fb.com
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Several small performance improvements in TX CQ polling,
including:
- Compiler branch predictor hints.
- Minimize variables scope.
- More proper check of cq type.
- Use boolean instead of int for a binary indication.

Performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

Packet-rate tests for both regular stack and XDP use cases:
No noticeable gain, no degradation.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Cc: kernel-team@fb.com
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove owner argument, as it is obsolete and unused.
This also saves the overhead of calculating its value in data-path.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Cc: kernel-team@fb.com
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There are many code paths opencoding kvmalloc.  Let's use the helper
instead.  The main difference to kvmalloc is that those users are
usually not considering all the aspects of the memory allocator.  E.g.
allocation requests <= 32kB (with 4kB pages) are basically never failing
and invoke OOM killer to satisfy the allocation.  This sounds too
disruptive for something that has a reasonable fallback - the vmalloc.
On the other hand those requests might fallback to vmalloc even when the
memory allocator would succeed after several more reclaim/compaction
attempts previously.  There is no guarantee something like that happens
though.

This patch converts many of those places to kv[mz]alloc* helpers because
they are more conservative.

Link: http://lkml.kernel.org/r/20170306103327.2766-2-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> # Xen bits
Acked-by: NKees Cook <keescook@chromium.org>
Acked-by: NVlastimil Babka <vbabka@suse.cz>
Acked-by: Andreas Dilger <andreas.dilger@intel.com> # Lustre
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> # KVM/s390
Acked-by: Dan Williams <dan.j.williams@intel.com> # nvdim
Acked-by: David Sterba <dsterba@suse.com> # btrfs
Acked-by: Ilya Dryomov <idryomov@gmail.com> # Ceph
Acked-by: Tariq Toukan <tariqt@mellanox.com> # mlx4
Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx5
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Anton Vorontsov <anton@enomsg.org>
Cc: Colin Cross <ccross@android.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Santosh Raspatur <santosh@chelsio.com>
Cc: Hariprasad S <hariprasad@chelsio.com>
Cc: Yishai Hadas <yishaih@mellanox.com>
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: "Yan, Zheng" <zyan@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

mlx4 is the only driver in the tree making a point to recompute
shinfo->gso_segs.

Lets remove superfluous code.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We only need to store the page and dma address.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

No need to duplicate it for all queues and frags.

num_frags & log_rx_info become u8 to save space.
u8 accesses are a bit faster than u16 anyway.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Avoid reading num_tc directly from struct net_device, but use
the helper function netdev_get_num_tc.

Fixes: bc6a4744 ("net/mlx4_en: num cores tx rings for every UP")
Fixes: f5b6345b ("net/mlx4_en: User prio mapping gets corrupted when changing number of channels")
Signed-off-by: NAlaa Hleihel <alaa@mellanox.com>
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Reserve XDP_PACKET_HEADROOM for packet and enable bpf_xdp_adjust_head()
support.  This patch only affects the code path when XDP is active.

After testing, the tx_dropped counter is incremented if the xdp_prog sends
more than wire MTU.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Acked-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Goal is to reorganize this critical structure to increase performance.

ndo_start_xmit() should only dirty one cache line, and access as few
cache lines as possible.

Add sp_ (Slow Path) prefix to fields that are not used in fast path,
to make clear what is going on.

After this patch pahole reports something much better, as all
ndo_start_xmit() needed fields are packed into two cache lines instead
of seven or eight

struct mlx4_en_tx_ring {
	u32                        last_nr_txbb;         /*     0   0x4 */
	u32                        cons;                 /*   0x4   0x4 */
	long unsigned int          wake_queue;           /*   0x8   0x8 */
	struct netdev_queue *      tx_queue;             /*  0x10   0x8 */
	u32                        (*free_tx_desc)(struct mlx4_en_priv *, struct mlx4_en_tx_ring *, int, u8, u64, int); /*  0x18   0x8 */
	struct mlx4_en_rx_ring *   recycle_ring;         /*  0x20   0x8 */

	/* XXX 24 bytes hole, try to pack */

	/* --- cacheline 1 boundary (64 bytes) --- */
	u32                        prod;                 /*  0x40   0x4 */
	unsigned int               tx_dropped;           /*  0x44   0x4 */
	long unsigned int          bytes;                /*  0x48   0x8 */
	long unsigned int          packets;              /*  0x50   0x8 */
	long unsigned int          tx_csum;              /*  0x58   0x8 */
	long unsigned int          tso_packets;          /*  0x60   0x8 */
	long unsigned int          xmit_more;            /*  0x68   0x8 */
	struct mlx4_bf             bf;                   /*  0x70  0x18 */
	/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
	__be32                     doorbell_qpn;         /*  0x88   0x4 */
	__be32                     mr_key;               /*  0x8c   0x4 */
	u32                        size;                 /*  0x90   0x4 */
	u32                        size_mask;            /*  0x94   0x4 */
	u32                        full_size;            /*  0x98   0x4 */
	u32                        buf_size;             /*  0x9c   0x4 */
	void *                     buf;                  /*  0xa0   0x8 */
	struct mlx4_en_tx_info *   tx_info;              /*  0xa8   0x8 */
	int                        qpn;                  /*  0xb0   0x4 */
	u8                         queue_index;          /*  0xb4   0x1 */
	bool                       bf_enabled;           /*  0xb5   0x1 */
	bool                       bf_alloced;           /*  0xb6   0x1 */
	u8                         hwtstamp_tx_type;     /*  0xb7   0x1 */
	u8 *                       bounce_buf;           /*  0xb8   0x8 */
	/* --- cacheline 3 boundary (192 bytes) --- */
	long unsigned int          queue_stopped;        /*  0xc0   0x8 */
	struct mlx4_hwq_resources  sp_wqres;             /*  0xc8  0x58 */
	/* --- cacheline 4 boundary (256 bytes) was 32 bytes ago --- */
	struct mlx4_qp             sp_qp;                /* 0x120  0x30 */
	/* --- cacheline 5 boundary (320 bytes) was 16 bytes ago --- */
	struct mlx4_qp_context     sp_context;           /* 0x150  0xf8 */
	/* --- cacheline 9 boundary (576 bytes) was 8 bytes ago --- */
	cpumask_t                  sp_affinity_mask;     /* 0x248  0x20 */
	enum mlx4_qp_state         sp_qp_state;          /* 0x268   0x4 */
	u16                        sp_stride;            /* 0x26c   0x2 */
	u16                        sp_cqn;               /* 0x26e   0x2 */

	/* size: 640, cachelines: 10, members: 36 */
	/* sum members: 600, holes: 1, sum holes: 24 */
	/* padding: 16 */
};

Instead of this silly placement :

struct mlx4_en_tx_ring {
	u32                        last_nr_txbb;         /*     0   0x4 */
	u32                        cons;                 /*   0x4   0x4 */
	long unsigned int          wake_queue;           /*   0x8   0x8 */

	/* XXX 48 bytes hole, try to pack */

	/* --- cacheline 1 boundary (64 bytes) --- */
	u32                        prod;                 /*  0x40   0x4 */

	/* XXX 4 bytes hole, try to pack */

	long unsigned int          bytes;                /*  0x48   0x8 */
	long unsigned int          packets;              /*  0x50   0x8 */
	long unsigned int          tx_csum;              /*  0x58   0x8 */
	long unsigned int          tso_packets;          /*  0x60   0x8 */
	long unsigned int          xmit_more;            /*  0x68   0x8 */
	unsigned int               tx_dropped;           /*  0x70   0x4 */

	/* XXX 4 bytes hole, try to pack */

	struct mlx4_bf             bf;                   /*  0x78  0x18 */
	/* --- cacheline 2 boundary (128 bytes) was 16 bytes ago --- */
	long unsigned int          queue_stopped;        /*  0x90   0x8 */
	cpumask_t                  affinity_mask;        /*  0x98  0x10 */
	struct mlx4_qp             qp;                   /*  0xa8  0x30 */
	/* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */
	struct mlx4_hwq_resources  wqres;                /*  0xd8  0x58 */
	/* --- cacheline 4 boundary (256 bytes) was 48 bytes ago --- */
	u32                        size;                 /* 0x130   0x4 */
	u32                        size_mask;            /* 0x134   0x4 */
	u16                        stride;               /* 0x138   0x2 */

	/* XXX 2 bytes hole, try to pack */

	u32                        full_size;            /* 0x13c   0x4 */
	/* --- cacheline 5 boundary (320 bytes) --- */
	u16                        cqn;                  /* 0x140   0x2 */

	/* XXX 2 bytes hole, try to pack */

	u32                        buf_size;             /* 0x144   0x4 */
	__be32                     doorbell_qpn;         /* 0x148   0x4 */
	__be32                     mr_key;               /* 0x14c   0x4 */
	void *                     buf;                  /* 0x150   0x8 */
	struct mlx4_en_tx_info *   tx_info;              /* 0x158   0x8 */
	struct mlx4_en_rx_ring *   recycle_ring;         /* 0x160   0x8 */
	u32                        (*free_tx_desc)(struct mlx4_en_priv *, struct mlx4_en_tx_ring *, int, u8, u64, int); /* 0x168   0x8 */
	u8 *                       bounce_buf;           /* 0x170   0x8 */
	struct mlx4_qp_context     context;              /* 0x178  0xf8 */
	/* --- cacheline 9 boundary (576 bytes) was 48 bytes ago --- */
	int                        qpn;                  /* 0x270   0x4 */
	enum mlx4_qp_state         qp_state;             /* 0x274   0x4 */
	u8                         queue_index;          /* 0x278   0x1 */
	bool                       bf_enabled;           /* 0x279   0x1 */
	bool                       bf_alloced;           /* 0x27a   0x1 */

	/* XXX 5 bytes hole, try to pack */

	/* --- cacheline 10 boundary (640 bytes) --- */
	struct netdev_queue *      tx_queue;             /* 0x280   0x8 */
	int                        hwtstamp_tx_type;     /* 0x288   0x4 */

	/* size: 704, cachelines: 11, members: 36 */
	/* sum members: 587, holes: 6, sum holes: 65 */
	/* padding: 52 */
};
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reviewed-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>