Rename the mac_link_state() method to mac_pcs_get_state() to make it
clear that it should be returning the MACs PCS current state, which
is used for inband negotiation rather than just reading back what the
MAC has been configured for. Update the documentation to explicitly
mention that this is for inband.

We drop the return value as well; most of phylink doesn't check the
return value and it is not clear what it should do on error - instead
arrange for state->link to be false.
Signed-off-by: NRussell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>

When receiving traffic, eth_type_trans() is high up on the perf top list,
because it's the first function which access the packet data.

Move the DMA unmap a bit higher, and put a prefetch just after it, so we
have more time to load the data into the cache.

The packet rate increase is about 14% with a tc drop test: 1620 => 1853 kpps
Signed-off-by: NMatteo Croce <mcroce@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the RX path we always sync against the maximum frame size for that pool.
Do the DMA sync and the unmap separately, so we can only sync by the
size of the received frame.
Signed-off-by: NMatteo Croce <mcroce@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Move some code down to remove a backward goto.
Signed-off-by: NMatteo Croce <mcroce@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Recycling in mvpp2 has gone long time ago, but two comment still refers
to it. Remove those two misleading comments as they generate confusion.

Fixes: 7ef7e1d9 ("net: mvpp2: drop useless fields in mvpp2_bm_pool and related code")
Signed-off-by: NMatteo Croce <mcroce@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Every mvpp2 unit can use up to 8 buffers mapped by the BM (the HW buffer
manager). The HW will place the frames in the buffer pool depending on the
frame size: short (< 128 bytes), long (< 1664) or jumbo (up to 9856).

As any unit can have up to 4 ports, the driver allocates only 2 pools,
one for small and one long frames, and share them between ports.
When the first port MTU is set higher than 1664 bytes, a third pool is
allocated for jumbo frames.

This shared allocation makes impossible to use percpu allocators,
and creates contention between HW queues.

If possible, i.e. if the number of possible CPU are less than 8 and jumbo
frames are not used, switch to a new scheme: allocate 8 per-cpu pools for
short and long frames and bind every pool to an RXQ.

When the first port MTU is set higher than 1664 bytes, the allocation
scheme is reverted to the old behaviour (3 shared pools), and when all
ports MTU are lowered, the per-cpu buffers are allocated again.
Signed-off-by: NMatteo Croce <mcroce@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Refactor mvpp2_bm_pool_create(), mvpp2_bm_pool_destroy() and
mvpp2_bm_pools_init() so that they accept a struct device instead
of a struct platform_device, as they just need platform_device->dev.

Removing such dependency makes the BM code more reusable in context
where we don't have a pointer to the platform_device.
Signed-off-by: NMatteo Croce <mcroce@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The tx_done_tasklet tasklet is used in invoke the hrtimer
(mvpp2_hr_timer_cb) in softirq context. This can be also achieved without
the tasklet but with HRTIMER_MODE_SOFT as hrtimer mode.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use devm_platform_ioremap_resource() to simplify the code a bit.
This is detected by coccinelle.
Reported-by: NHulk Robot <hulkci@huawei.com>
Signed-off-by: NYueHaibing <yuehaibing@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mvpp2 uses a delayed workqueue to gather traffic statistics.
On module removal the workqueue can be destroyed before calling
cancel_delayed_work_sync() on its works.
Fix it by moving the destroy_workqueue() call after mvpp2_port_remove().
Also remove an unneeded call to flush_workqueue()

    # rmmod mvpp2
    [ 2743.311722] mvpp2 f4000000.ethernet eth1: phy link down 10gbase-kr/10Gbps/Full
    [ 2743.320063] mvpp2 f4000000.ethernet eth1: Link is Down
    [ 2743.572263] mvpp2 f4000000.ethernet eth2: phy link down sgmii/1Gbps/Full
    [ 2743.580076] mvpp2 f4000000.ethernet eth2: Link is Down
    [ 2744.102169] mvpp2 f2000000.ethernet eth0: phy link down 10gbase-kr/10Gbps/Full
    [ 2744.110441] mvpp2 f2000000.ethernet eth0: Link is Down
    [ 2744.115614] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
    [ 2744.115615] Mem abort info:
    [ 2744.115616]   ESR = 0x96000005
    [ 2744.115617]   Exception class = DABT (current EL), IL = 32 bits
    [ 2744.115618]   SET = 0, FnV = 0
    [ 2744.115619]   EA = 0, S1PTW = 0
    [ 2744.115620] Data abort info:
    [ 2744.115621]   ISV = 0, ISS = 0x00000005
    [ 2744.115622]   CM = 0, WnR = 0
    [ 2744.115624] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000422681000
    [ 2744.115626] [0000000000000000] pgd=0000000000000000, pud=0000000000000000
    [ 2744.115630] Internal error: Oops: 96000005 [#1] SMP
    [ 2744.115632] Modules linked in: mvpp2(-) algif_hash af_alg nls_iso8859_1 nls_cp437 vfat fat xhci_plat_hcd m25p80 spi_nor xhci_hcd mtd usbcore i2c_mv64xxx sfp usb_common marvell10g phy_generic spi_orion mdio_i2c i2c_core mvmdio phylink sbsa_gwdt ip_tables x_tables autofs4 [last unloaded: mvpp2]
    [ 2744.115654] CPU: 3 PID: 8357 Comm: kworker/3:2 Not tainted 5.3.0-rc2 #1
    [ 2744.115655] Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT)
    [ 2744.115665] Workqueue: events_power_efficient phylink_resolve [phylink]
    [ 2744.115669] pstate: a0000085 (NzCv daIf -PAN -UAO)
    [ 2744.115675] pc : __queue_work+0x9c/0x4d8
    [ 2744.115677] lr : __queue_work+0x170/0x4d8
    [ 2744.115678] sp : ffffff801001bd50
    [ 2744.115680] x29: ffffff801001bd50 x28: ffffffc422597600
    [ 2744.115684] x27: ffffff80109ae6f0 x26: ffffff80108e4018
    [ 2744.115688] x25: 0000000000000003 x24: 0000000000000004
    [ 2744.115691] x23: ffffff80109ae6e0 x22: 0000000000000017
    [ 2744.115694] x21: ffffffc42c030000 x20: ffffffc42209e8f8
    [ 2744.115697] x19: 0000000000000000 x18: 0000000000000000
    [ 2744.115699] x17: 0000000000000000 x16: 0000000000000000
    [ 2744.115701] x15: 0000000000000010 x14: ffffffffffffffff
    [ 2744.115702] x13: ffffff8090e2b95f x12: ffffff8010e2b967
    [ 2744.115704] x11: ffffff8010906000 x10: 0000000000000040
    [ 2744.115706] x9 : ffffff80109223b8 x8 : ffffff80109223b0
    [ 2744.115707] x7 : ffffffc42bc00068 x6 : 0000000000000000
    [ 2744.115709] x5 : ffffffc42bc00000 x4 : 0000000000000000
    [ 2744.115710] x3 : 0000000000000000 x2 : 0000000000000000
    [ 2744.115712] x1 : 0000000000000008 x0 : ffffffc42c030000
    [ 2744.115714] Call trace:
    [ 2744.115716]  __queue_work+0x9c/0x4d8
    [ 2744.115718]  delayed_work_timer_fn+0x28/0x38
    [ 2744.115722]  call_timer_fn+0x3c/0x180
    [ 2744.115723]  expire_timers+0x60/0x168
    [ 2744.115724]  run_timer_softirq+0xbc/0x1e8
    [ 2744.115727]  __do_softirq+0x128/0x320
    [ 2744.115731]  irq_exit+0xa4/0xc0
    [ 2744.115734]  __handle_domain_irq+0x70/0xc0
    [ 2744.115735]  gic_handle_irq+0x58/0xa8
    [ 2744.115737]  el1_irq+0xb8/0x140
    [ 2744.115738]  console_unlock+0x3a0/0x568
    [ 2744.115740]  vprintk_emit+0x200/0x2a0
    [ 2744.115744]  dev_vprintk_emit+0x1c8/0x1e4
    [ 2744.115747]  dev_printk_emit+0x6c/0x7c
    [ 2744.115751]  __netdev_printk+0x104/0x1d8
    [ 2744.115752]  netdev_printk+0x60/0x70
    [ 2744.115756]  phylink_resolve+0x38c/0x3c8 [phylink]
    [ 2744.115758]  process_one_work+0x1f8/0x448
    [ 2744.115760]  worker_thread+0x54/0x500
    [ 2744.115762]  kthread+0x12c/0x130
    [ 2744.115764]  ret_from_fork+0x10/0x1c
    [ 2744.115768] Code: aa1403e0 97fffbbe aa0003f5 b4000700 (f9400261)

Fixes: 118d6298 ("net: mvpp2: add ethtool GOP statistics")
Signed-off-by: NLorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NMatteo Croce <mcroce@redhat.com>
Acked-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The hardware can only offload checksum calculation on first port due to
the Tx FIFO size limitation, and has a maximum L3 offset of 128 bytes.
Document this in a comment and move duplicated code in a function.

Fixes: 576193f2 ("net: mvpp2: jumbo frames support")
Signed-off-by: NMatteo Croce <mcroce@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The MTU change code can call napi_disable() with the device already down,
leading to a deadlock. Also, lot of code is duplicated unnecessarily.

Rework mvpp2_change_mtu() to avoid the deadlock and remove duplicated code.

Fixes: 3f518509 ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: NMatteo Croce <mcroce@redhat.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>

PPv2's XLGMAC can wait for 3 idle frames before triggering a link up
event. This can cause the link to be stuck low when there's traffic on
the interface, so disable this feature.

Fixes: 4bb04326 ("net: mvpp2: phylink support")
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Besides the MIB counters, some other useful counters can be exposed to
the user. This commit adds support for :

 - Per-port counters, that indicate FIFO drops and classifier drops,
 - Per-rxq counters,
 - Per-txq counters
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since we'll be adding support for other kind of internal counters, make
clear that the currently supported counters are the MIB counters.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When first configuring a port on PPv2, we want to clear the internal
counters so that we don't get values from previous boot stages.

However, we can't really clear these counters when resetting the MAC,
since there are valid reasons to do so while the port is being used,
such as when reconfiguring the interface mode with the PHY.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use a safe strscpy call to copy the ethtool stat strings into the
relevant buffers, instead of a memcpy that will be accessing
out-of-bound data.

Fixes: 118d6298 ("net: mvpp2: add ethtool GOP statistics")
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MVPP2_TXQ_SCHED_TOKEN_CNTR_REG() expects the logical queue id but
the current code is passing the global tx queue offset, so it ends
up writing to unknown registers (between 0x8280 and 0x82fc, which
seemed to be unused by the hardware). This fixes the issue by using
the logical queue id instead.

Fixes: 3f518509 ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The phylink_config structure will encapsulate a pointer to a struct
device and the operation type requested for this instance of PHYLINK.
This patch does not make any functional changes, it just transitions the
PHYLINK internals and all its users to the new API.

A pointer to a phylink_config structure will be passed to
phylink_create() instead of the net_device directly. Also, the same
phylink_config pointer will be passed back to all phylink_mac_ops
callbacks instead of the net_device. Using this mechanism, a PHYLINK
user can get the original net_device using a structure such as
'to_net_dev(config->dev)' or directly the structure containing the
phylink_config using a container_of call.

At the moment, only the PHYLINK_NETDEV is defined as a valid operation
type for PHYLINK. In this mode, a valid reference to a struct device
linked to the original net_device should be passed to PHYLINK through
the phylink_config structure.

This API changes is mainly driven by the necessity of adding a new
operation type in PHYLINK that disconnects the phy_device from the
net_device and also works when the net_device is lacking.
Signed-off-by: NIoana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: NVladimir Oltean <olteanv@gmail.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Reviewed-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Tested-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PPv2 controller has 8 RSS tables that are shared across all ports on
a given PPv2 instance. The previous implementation allocated one table
per port, leaving others unused.

By using RSS contexts, we can make use of multiple RSS tables per
port, one being the default table (always id 0), the other ones being
used as destinations for flow steering, in the same way as rx rings.

This commit introduces RSS contexts management in the PPv2 driver. We
always reserve one table per port, allocated when the port is probed.

The global table list is stored in the struct mvpp2, as it's a global
resource. Each port then maintains a list of indices in that global
table, that way each port can have it's own numbering scheme starting
from 0.

One limitation that seems unavoidable is that the hashing parameters are
shared across all RSS contexts for a given port. Hashing parameters for
ctx 0 will be applied to all contexts.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As of today, the classification offload implementation only supports 4
different rules to be offloaded. This number has been hardcoded in the
rule insertion function, and the wrong define is being used elsewhere.

Use the correct #define everywhere to make sure we always check for the
correct number of rules.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that the mvpp2 driver supports classification offloading, we must
add the NETIF_F_NTUPLE to the features list.

Since the current code doesn't allow disabling the feature, we don't set
the flag in dev->hw_features.

Fixes: 90b509b3 ("net: mvpp2: cls: Add Classification offload support")
Reported-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This commit introduces basic classification offloading support for the
PPv2 controller.

The PPv2 classifier has many classification engines, for now we only use
the C2 TCAM match engine.

This engine allows to perform ternary lookups on 64 bits keys (called
Header Extracted Key), that are built by extracting fields from the packet
header and concatenating them. At most 4 fields can be extracted for a
single lookup.

This basic implementation allows to build the HEK from the following
fields :
 - L4 source and destination ports (for UDP and TCP)

More fields are to be added in the future.

Classification flows are added through the ethtool interface, using the
newly introduced flow_rule infrastructure as an internal rule
representation, allowing to more easily implement tc flower rules if
need be.

The internal design for now allocates one range of 4 rules per port
due to the internal design of the flow table, which uses 22 sub-flows.

When inserting a classification rule, the rule is created in every
relevant sub-flow.

This low rule-count is a very simple design which reaches quickly the
limitations of the flow table ordering, but guarantees that the rule
ordering will always be respected.

This commit only introduces support for the "steer to rxq" action.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This commit renames some of the classifier functions to follow the
naming 'mvpp2_port_*' that's used for function that act on a given port.

This commit is purely cosmetic.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

int is not long enough to store all netdev_features, use the correct
dedicated type to store them when building the list of dev->features.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds calls in the stop() helper to ensure both MACs and
both PCS blocks are set in reset when the user manually sets a port
down. This is done so that we have the exact same block reset states at
boot time and when a port is set down.
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch sets both the XPCS and MPCS blocks in reset when they aren't
used. This is done both at boot time and when reconfiguring a port mode.
The advantage now is that only the PCS used is set out of reset when the
port is configured (10GKR uses the MCPS while RXAUI uses the XPCS).
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch makes sure both PPv2 MACs (GMAC + XLG MAC) are set in reset
while a port is reconfigured. This is done so that we make sure a MAC is
in a reset state when not used, as only one of the two will be set out
of reset after the port is configured properly.
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch reworks the way the XLG MAC is set in reset: the XLG MAC is
set in reset at probe time and taken out of this state only when used.
The idea is to move forward a situation where only the blocks used are
taken out of reset. This also has the effect to handle the GMAC and the
XLG MAC in a similar way (the GMAC already is set in reset at boot
time).
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch force the XLG MAC link state in the phylink link_up() and
link_down() helpers when not using in-band auto-negotiation. This mimics
what's already done for the GMAC and follows what's advised in the
phylink documentation.
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch improves the XLG configuration function, to only update the
XLG configuration register when a change is needed. This helps not
writing over and over the same XLG configuration each time phylink
request the MAC to be configured. This mimics the GMAC configuration
function.
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch modifies the port_disable() helper to always disable both the
GMAC and the XLG MAC when called. At boot time we do not know of a port
was enabled in the firmware/bootloader, and if so what mode was used
(hence which of the two MACs was used).

This also help in implementing a logic where all blocks are disabled
when not used, and only enabled regarding the current mode used on a
given port.
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The GMAC configuration helper modifies values in the auto-negotiation
register. Some of its values require the port to be forced down when
modifying their values. This patches fixes the check made on the bit to
be updated in this register, so that the port is forced down when
needed. This fix cases where some of those parameters were updated, but
not taken into account, such as when using RGMII interfaces.

Fixes: d14e078f ("net: marvell: mvpp2: only reprogram what is necessary on mac_config")
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The patch fixes the computation of RXQs being used by the PPv2 driver,
which is set depending on the PPv2 engine version and the queue mode
used. There are three cases:

- PPv2.1: 1 RXQ per CPU.
- PPV2.2 with MVPP2_QDIST_MULTI_MODE: 1 RXQ per CPU.
- PPv2.2 with MVPP2_QDIST_SINGLE_MODE: 1 RXQ is shared between the CPUs.

The PPv2 engine supports a maximum of 32 queues per port. This patch
adds a check so that we do not overstep this maximum.

It appeared the calculation was broken for PPv2.1 engines since
f8c6ba84, as PPv2.1 ports ended up with a single RXQ while they
needed 4. This patch fixes it.

Fixes: f8c6ba84 ("net: mvpp2: use only one rx queue per port per CPU")
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The Phylink validate function is the Marvell PPv2 driver makes a check
on the GoP id. This is valid an has to be done when using PPv2.2 engines
but makes no sense when using PPv2.1. The check done when using an RGMII
interface makes sure the GoP id is not 0, but this breaks PPv2.1. Fixes
it.

Fixes: 0fb628f0 ("net: mvpp2: fix phylink handling of invalid PHY modes")
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds a check on the PPv2 version in-use not to reconfigure
the port mode when an interface is updated when using PPv2.1 as the
functions called are PPv2.2 specific.
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We had a check in the mvpp2_mac_link_down() function (called by phylink)
to avoid disabling the port when link interrupts are used. It turned out
the interrupt can still be used with the port disabled. We can thus
remove this check.
Signed-off-by: NAntoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PPv2 controller is able to support 2.5G speeds, allowing to use
2.5GBASET in conjunction with PHYs that use 2500BASEX as their MII
interface when using this mode.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There are several places which make the decision whether to access the
XLGMAC vs GMAC that only check for PHY_INTERFACE_MODE_10GKR and not its
XAUI variant.  Switch these to use the new helper so that we have
consistency through the driver.
Signed-off-by: NRussell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>