add new map type BPF_MAP_TYPE_HASH and its implementation
- maps are created/destroyed by userspace. Both userspace and eBPF programs
can lookup/update/delete elements from the map
- eBPF programs can be called in_irq(), so use spin_lock_irqsave() mechanism
for concurrent updates
- key/value are opaque range of bytes (aligned to 8 bytes)
- user space provides 3 configuration attributes via BPF syscall:
key_size, value_size, max_entries
- map takes care of allocating/freeing key/value pairs
- map_update_elem() must fail to insert new element when max_entries
limit is reached to make sure that eBPF programs cannot exhaust memory
- map_update_elem() replaces elements in an atomic way
- optimized for speed of lookup() which can be called multiple times from
eBPF program which itself is triggered by high volume of events
. in the future JIT compiler may recognize lookup() call and optimize it
further, since key_size is constant for life of eBPF program
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
the current meaning of BPF_MAP_UPDATE_ELEM syscall command is:
either update existing map element or create a new one.
Initially the plan was to add a new command to handle the case of
'create new element if it didn't exist', but 'flags' style looks
cleaner and overall diff is much smaller (more code reused), so add 'flags'
attribute to BPF_MAP_UPDATE_ELEM command with the following meaning:
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
bpf_update_elem(fd, key, value, BPF_NOEXIST) call can fail with EEXIST
if element already exists.
bpf_update_elem(fd, key, value, BPF_EXIST) can fail with ENOENT
if element doesn't exist.
Userspace will call it as:
int bpf_update_elem(int fd, void *key, void *value, __u64 flags)
{
union bpf_attr attr = {
.map_fd = fd,
.key = ptr_to_u64(key),
.value = ptr_to_u64(value),
.flags = flags;
};
return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}
First two bits of 'flags' are used to encode style of bpf_update_elem() command.
Bits 2-63 are reserved for future use.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
Intel Wired LAN Driver Updates 2014-11-18
This series contains updates to i40e only.
Shannon provides a patch to clean up the driver to only warn once that
PTP is not supported when linked at 100Mbps.
Mitch provides a fix for i40e where the VF interrupt processing takes
a long time and it is possible that we could lose a VFLR event if it
happens while processing a VFLR on another VF. To correct this situation,
we enable the VFLR interrupt cause before we begin processing any pending
resets.
Neerav provides several patches to update DCB support in i40e. When
there are DCB configuration changes based on DCBx, the firmware suspends
the port's Tx and generates an event to the PF. The PF is then
responsible to reconfigure the PF VSIs and switching topology as per the
updated DCB configuration and then resume the port's Tx by calling the
"Resume Port Tx" AQ command, so add this call to the flow that handles
DCB re-configuration in the PF. Allow the driver to query and use DCB
configuration from firmware when firmware DCBx agent is in CEE mode.
Add a check whether LLDP Agent's default AdminStatus is enabled or
disabled on a given port, and sets DCBx status to disabled if the
status is disabled. Fix an issue when the port TC configuration
changes as a result of DCBx and the driver modifies the enabled TCs for
the VEBs it manages but does not update the enabled_tc value that
was cached on a per VEB basis. Add a new PF state so that if a port's
Tx is in suspended state the Tx queue disable flow would just put the
request for the queue to be disabled and return without waiting for the
queue to be actually disabled. Allows the driver to enable/disable
the XPS based on the number of TCs being enabled for the given VSI.
v2: Dropped patch "i40e: Handle a single mss packet with more than 8 frags"
while we rework the patch after we test a bit more based on feedback from
Eric Dumazet.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Due to DCBX configuration change if the VSI needs to use more than 1 TC;
it needs to disable the XPS maps that were set when operating in 1 TC mode.
Without disabling XPS the netdev layer will select queues based on those
settings and not use the TC queue mapping to make the queue selection.
This patch allows the driver to enable/disable the XPS based on the number
of TCs being enabled for the given VSI.
Change-ID: Idc4dec47a672d2a509f6d7fe11ed1ee65b4f0e08
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Tested-By: Jack Morgan <jack.morgan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When PFC is enabled we should not proceed with setting the link flow control
parameters. Also, always report the link flow Tx/Rx settings as off when
PFC is enabled.
Change-ID: Ib09ec58afdf0b2e587ac9d8851a5c80ad58206c4
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Tested-By: Jack Morgan <jack.morgan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
FCoE VSI Tx queue disable times out when reconfiguring as a result of
DCB TC configuration change event.
The hardware allows us to skip disabling and enabling of Tx queues for
VSIs with single TC enabled. As FCoE VSI is configured to have only
single TC we skip it from disable/enable flow.
Change-ID: Ia73ff3df8785ba2aa3db91e6f2c9005e61ebaec2
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Tested-By: Jack Morgan <jack.morgan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When DCB TC configuration changes the firmware suspends the port's Tx.
Now, as DCB TCs may have changed the PF driver tries to reconfigure the
TC configuration of the VSIs it manages. As part of this process it disables
the VSI queues but the Tx queue disable will not complete as the port's
Tx has been suspended. So, waiting for Tx queues to go to disable state
in this flow may lead to detection of Tx queue disable timeout errors.
Hence, this patch adds a new PF state so that if a port's Tx is in
suspended state the Tx queue disable flow would just put the request for
the queue to be disabled and return without waiting for the queue to be
actually disabled.
Once the VSI(s) TC reconfiguration has been done and driver has called
firmware AQC "Resume PF Traffic" the driver checks the Tx queues requested
to be disabled are actually disabled before re-enabling them again.
Change-ID: If3e03ce4813a4e342dbd5a1eb1d2861e952b7544
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Tested-By: Jack Morgan <jack.morgan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When the port TC configuration changes as a result of DCBx the driver
modifies the enabled TCs for the VEBs it manages. But, in the process
it did not update the enabled_tc value that it caches on a per VEB basis.
So, when the next reconfiguration event occurs where the number of TC
value is same as the value cached in enabled_tc for a given VEB; driver
does not modify it's TC configuration by calling appropriate AQ command
believing it is running with the same configuration as requested.
Now, as the VEB is not actually enabled for the TCs that are there any
TC configuration command for VSI attached to that VEB with TCs that are
not enabled for the VEB fails.
This patch fixes this issue.
Change-ID: Ife5694469b05494228e0d850429ea1734738cf29
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Tested-By: Jack Morgan <jack.morgan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch adds a check whether LLDP Agent's default AdminStatus is
enabled or disabled on a given port. If it is disabled then it sets
the DCBX status to disabled as well; and would not query firmware for
any DCBX configuration data.
Change-ID: I73c0b9f0adbf4cae177d14914b20a48c9a8f50fd
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Tested-By: Jack Morgan <jack.morgan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This patch allows i40e driver to query and use DCB configuration from
firmware when firmware DCBX agent is in CEE mode.
Change-ID: I30f92a67eb890f0f024f35339696e6e83d49a274
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Tested-By: Jack Morgan <jack.morgan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When there are DCB configuration changes based on DCBX the firmware suspends
the port's Tx and generates an event to the PF. The PF is then responsible
to reconfigure the PF VSIs and switching topology as per the updated DCB
configuration and then resume the port's Tx by calling the "Resume Port Tx"
AQ command.
This patch adds this call to the flow that handles DCB re-configuration in
the PF.
Change-ID: I5b860ad48abfbf379b003143c4d3453e2ed5cc1c
Signed-off-by: Neerav Parikh <neerav.parikh@intel.com>
Tested-By: Jack Morgan <jack.morgan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Bumping minor version as this will be the second SW release and it
should be 1.
Change-ID: If0bd102095d2f059ae0c9b7f4ad625535ffbbdee
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
VF interrupt processing takes a looooong time, and it's possible that we
could lose a VFLR event if it happens while we're processing a VFLR on
another VF. This would leave the VF in a semi-permanent reset state,
which would not be cleared until yet another VF experiences a VFLR.
To correct this situation, we enable the VFLR interrupt cause before we
begin processing any pending resets. This means that any VFLR that
occurs during reset processing will generate another interrupt and this
routine will get called again.
This change may cause a spurious interrupt when multiple VFLRs occur
very close together in time. If this happens, then this routine will be
called again and it will detect no outstanding VFLR events and do
nothing. No harm, no foul.
Change-ID: Id0451f3e6e73a2cf6db1668296c71e129b59dc19
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Only warn once that PTP is not supported when linked at 100Mbit.
Yes, using a static this way means that this once-only message is not
port specific, but once only for the life of the driver, regardless of
the number of ports. That should be plenty.
Change-ID: Ie6476530056df408452e195ef06afd4f57caa4b2
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Eric Dumazet says:
====================
net: provide common RSS key infrastructure
RSS (Receive Side Scaling) uses a 40 bytes key to provide hash for incoming
packets to select appropriate incoming queue on NIC.
Hash algo (Toeplitz) is also well known and documented by Microsoft
(search for "Verifying the RSS Hash Calculation")
Problem is that some drivers use a well known key.
It makes very easy for attackers to target one particular RX queue,
knowing that number of RX queues is a power of two, or at least some
small number.
Other drivers use a random value per port, making difficult
tuning on bonding setups.
Lets add a common infrastructure, so that host gets an unique
RSS key, and drivers do not have to worry about this.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Use of well known RSS key increases attack surface.
Switch to a random one, using generic helper so that all
ports share a common key.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Shreyas Bhatewara <sbhatewara@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use of well known RSS key increases attack surface.
Switch to a random one, using generic helper so that all
ports share a common key.
Also provide ethtool -x support to fetch RSS key
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexei Starovoitov
David S. Miller
Denis Kirjanov
Neerav Parikh
Catherine Sullivan
Mitch Williams
Shannon Nelson
Eric Dumazet