atomic_t variables are currently used to implement reference
counters with the following properties:
- counter is initialized to 1 using atomic_set()
- a resource is freed upon counter reaching zero
- once counter reaches zero, its further
increments aren't allowed
- counter schema uses basic atomic operations
(set, inc, inc_not_zero, dec_and_test, etc.)
Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.
The variable mlx4_cq.refcount is used as pure reference counter.
Convert it to refcount_t and fix up the operations.
Suggested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: David 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: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug 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: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
All rx and rx netdev interrupts are handled by respectively
by mlx4_en_rx_irq() and mlx4_en_tx_irq() which simply schedule a NAPI.
But mlx4_eq_int() also fires a tasklet to service all items that were
queued via mlx4_add_cq_to_tasklet(), but this handler was not called
unless user cqe was handled.
This is very confusing, as "mpstat -I SCPU ..." show huge number of
tasklet invocations.
This patch saves this overhead, by carefully firing the tasklet directly
from mlx4_add_cq_to_tasklet(), removing four atomic operations per IRQ.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In function mlx4_cq_completion() and mlx4_cq_event(), the
radix_tree_lookup requires a rcu_read_lock.
This is mandatory: if another core frees the CQ, it could
run the radix_tree_node_rcu_free() call_rcu() callback while
its being used by the radix tree lookup function.
Additionally, in function mlx4_cq_event(), since we are adding
the rcu lock around the radix-tree lookup, we no longer need to take
the spinlock. Also, the synchronize_irq() call for the async event
eliminates the need for incrementing the cq reference count in
mlx4_cq_event().
Other changes:
1. In function mlx4_cq_free(), replace spin_lock_irq with spin_lock:
we no longer take this spinlock in the interrupt context.
The spinlock here, therefore, simply protects against different
threads simultaneously invoking mlx4_cq_free() for different cq's.
2. In function mlx4_cq_free(), we move the radix tree delete to before
the synchronize_irq() calls. This guarantees that we will not
access this cq during any subsequent interrupts, and therefore can
safely free the CQ after the synchronize_irq calls. The rcu_read_lock
in the interrupt handlers only needs to protect against corrupting the
radix tree; the interrupt handlers may access the cq outside the
rcu_read_lock due to the synchronize_irq calls which protect against
premature freeing of the cq.
3. In function mlx4_cq_event(), we change the mlx_warn message to mlx4_dbg.
4. We leave the cq reference count mechanism in place, because it is
still needed for the cq completion tasklet mechanism.
Fixes: 6d90aa5cf1 ("net/mlx4_core: Make sure there are no pending async events when freeing CQ")
Fixes: 225c7b1fee ("IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
problem description:
The current code sets UAR page size equal to system page size.
The ConnectX-3 and ConnectX-3 Pro HWs require minimum 128 UAR pages.
The mlx4 kernel drivers are not loaded if there is less than 128 UAR pages.
solution:
Always set UAR page to 4KB. This allows more UAR pages if the OS
has PAGE_SIZE larger than 4KB. For example, PowerPC kernel use 64KB
system page size, with 4MB uar region, there are 4MB/2/64KB = 32
uars (half for uar, half for blueflame). This does not meet minimum 128
UAR pages requirement. With 4KB UAR page, there are 4MB/2/4KB = 512 uars
which meet the minimum requirement.
Note that only codes in mlx4_core that deal with firmware know that uar
page size is 4KB. Codes that deal with usr page in cq and qp context
(mlx4_ib, mlx4_en and part of mlx4_core) still have the same assumption
that uar page size equals to system page size.
Note that with this implementation, on 64KB system page size kernel, there
are 16 uars per system page but only one uars is used. The other 15
uars are ignored because of the above assumption.
Regarding SR-IOV, mlx4_core in hypervisor will set the uar page size
to 4KB and mlx4_core code in virtual OS will obtain the uar page size from
firmware.
Regarding backward compatibility in SR-IOV, if hypervisor has this new code,
the virtual OS must be updated. If hypervisor has old code, and the virtual
OS has this new code, the new code will be backward compatible with the
old code. If the uar size is big enough, this new code in VF continues to
work with 64 KB uar page size (on PowerPc kernel). If the uar size does not
meet 128 uars requirement, this new code not loaded in VF and print the same
error message as the old code in Hypervisor.
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When freeing a CQ, we need to make sure there are no
asynchronous events (on the ASYNC EQ) that could
relate to this CQ before freeing it.
This is done by introducing synchronize_irq.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously, mlx4_en allocated EQs and used them exclusively.
This affected RoCE performance, as applications which are
events sensitive were limited to use only the legacy EQs.
Change that by introducing an EQ pool. This pool is managed
by mlx4_core. EQs are assigned to ports (when there are limited
number of EQs, multiple ports could be assigned to the same EQs).
An exception to this rule is the ASYNC EQ which handles various events.
Legacy EQs are completely removed as all EQs could be shared.
When a consumer (mlx4_ib/mlx4_en) requests an EQ, it asks for
EQ serving on a specific port. The core driver calculates which
EQ should be assigned to that request.
Because IRQs are shared between IB and Ethernet modules, their
names only include the PCI device BDF address.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously, we've fired all our completion callbacks straight from our ISR.
Some of those callbacks were lightweight (for example, mlx4_en's and
IPoIB napi callbacks), but some of them did more work (for example,
the user-space RDMA stack uverbs' completion handler). Besides that,
doing more than the minimal work in ISR is generally considered wrong,
it could even lead to a hard lockup of the system. Since when a lot
of completion events are generated by the hardware, the loop over those
events could be so long, that we'll get into a hard lockup by the system
watchdog.
In order to avoid that, add a new way of invoking completion events
callbacks. In the interrupt itself, we add the CQs which receive completion
event to a per-EQ list and schedule a tasklet. In the tasklet context
we loop over all the CQs in the list and invoke the user callback.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IRQ affinity notifier can only have a single notifier - cpu_rmap
notifier. Can't use it to track changes in IRQ affinity map.
Detect IRQ affinity changes by comparing CPU to current IRQ affinity map
during NAPI poll thread.
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Ben Hutchings <ben@decadent.org.uk>
Fixes: 2eacc23 ("net/mlx4_core: Enforce irq affinity changes immediatly")
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking updates from David Miller:
1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.
2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
Benniston.
3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
Mork.
4) BPF now has a "random" opcode, from Chema Gonzalez.
5) Add more BPF documentation and improve test framework, from Daniel
Borkmann.
6) Support TCP fastopen over ipv6, from Daniel Lee.
7) Add software TSO helper functions and use them to support software
TSO in mvneta and mv643xx_eth drivers. From Ezequiel Garcia.
8) Support software TSO in fec driver too, from Nimrod Andy.
9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.
10) Handle broadcasts more gracefully over macvlan when there are large
numbers of interfaces configured, from Herbert Xu.
11) Allow more control over fwmark used for non-socket based responses,
from Lorenzo Colitti.
12) Do TCP congestion window limiting based upon measurements, from Neal
Cardwell.
13) Support busy polling in SCTP, from Neal Horman.
14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.
15) Bridge promisc mode handling improvements from Vlad Yasevich.
16) Don't use inetpeer entries to implement ID generation any more, it
performs poorly, from Eric Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
tcp: fixing TLP's FIN recovery
net: fec: Add software TSO support
net: fec: Add Scatter/gather support
net: fec: Increase buffer descriptor entry number
net: fec: Factorize feature setting
net: fec: Enable IP header hardware checksum
net: fec: Factorize the .xmit transmit function
bridge: fix compile error when compiling without IPv6 support
bridge: fix smatch warning / potential null pointer dereference
via-rhine: fix full-duplex with autoneg disable
bnx2x: Enlarge the dorq threshold for VFs
bnx2x: Check for UNDI in uncommon branch
bnx2x: Fix 1G-baseT link
bnx2x: Fix link for KR with swapped polarity lane
sctp: Fix sk_ack_backlog wrap-around problem
net/core: Add VF link state control policy
net/fsl: xgmac_mdio is dependent on OF_MDIO
net/fsl: Make xgmac_mdio read error message useful
net_sched: drr: warn when qdisc is not work conserving
...
Modify the various routines used to allocate memory resources which
serve QPs in mlx4 to get an input GFP directive. Have the Ethernet
driver to use GFP_KERNEL in it's QP allocations as done prior to this
commit, and the IB driver to use GFP_NOIO when the IB verbs
IB_QP_CREATE_USE_GFP_NOIO QP creation flag is provided.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
During heavy traffic, napi is constatntly polling the complition queue
and no interrupt is fired. Because of that, changes to irq affinity are
ignored until traffic is stopped and resumed.
By registering to the irq notifier mechanism, and forcing interrupt when
affinity is changed, irq affinity changes will be immediatly enforced.
Signed-off-by: Yuval Atias <yuvala@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
None of these files are actually using any __init type directives
and hence don't need to include <linux/init.h>. Most are just a
left over from __devinit and __cpuinit removal, or simply due to
code getting copied from one driver to the next.
This covers everything under drivers/net except for wireless, which
has been submitted separately.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit f4ec9e9 "mlx4_core: Change bitmap allocator to work in round-robin fashion"
introduced round-robin allocation (via bitmap) for all resources which allocate
via a bitmap.
Round robin allocation is desirable for mcgs, counters, pd's, UARs, and xrcds.
These are simply numbers, with no involvement of ICM memory mapping.
Round robin is required for QPs, since we had a problem with immediate
reuse of a 24-bit QP number (commit f4ec9e9).
However, for other resources which use the bitmap allocator and involve
mapping ICM memory -- MPTs, CQs, SRQs -- round-robin is not desirable.
What happens in these cases is the following:
ICM memory is allocated and mapped in chunks of 256K.
Since the resource allocation index goes up monotonically, the allocator
will eventually require mapping a new chunk. Now, chunks are also unmapped
when their reference count goes back to zero. Thus, if a single app is
running and starts/exits frequently we will have the following situation:
When the app starts, a new chunk must be allocated and mapped.
When the app exits, the chunk reference count goes back to zero, and the
chunk is unmapped and freed. Therefore, the app must pay the cost of allocation
and mapping of ICM memory each time it runs (although the price is paid only when
allocating the initial entry in the new chunk).
For apps which allocate MPTs/SRQs/CQs and which operate as described above,
this presented a performance problem.
We therefore roll back the round-robin allocator modification for MPTs, CQs, SRQs.
Reported-by: Matthew Finlay <matt@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To guarantee that all unused fields in all FW commands for both inboxes
and outboxes are zeroed out, initialize the mailbox buffer to all zeroes.
This is especially important for SRIOV comm-channel virtual commands
(such as QUERY_FUNC_CAP), where if new fields are added to support new
features, the driver can depend on older kernels passing zeroes in these
fields.
In addition to zeroing out the mailbox buffer at allocation time, all
(now unnecessary) calls to memset by the callers of
mlx4_alloc_cmd_mailbox() are removed.
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The patch allows to enable/disable HW timestamping for incoming and/or
outgoing packets. It adds and initializes all structs and callbacks
needed by kernel TS API.
To enable/disable HW timestamping appropriate ioctl should be used.
Currently HWTSTAMP_FILTER_ALL/NONE and HWTSAMP_TX_ON/OFF only are
supported.
When enabling TS on receive flow - VLAN stripping will be disabled.
Also were made all relevant changes in RX/TX flows to consider TS request
and plant HW timestamps into relevant structures.
mlx4_ib was fixed to compile with new mlx4_cq_alloc() signature.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The set_param_l function assumes casting a u64 pointer to a u32 pointer
allows to access the lower 32bits, but it results in writing the upper
32 bits on big endian systems.
The fixed function reads the upper 32 bits of the 64 argument, and or's
them with the 32 bits of the 32-bit value passed to the function.
Since this is now a "read-modify-write" operation, we got many
"unintialized variable" warnings which needed to be fixed as well.
Reported-by: Alexander Schmidt <alexschm@de.ibm.com>.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Virtual Functions should not be aware their function number.
Signed-off-by: Marcel Apfelbaum <marcela@dev.mellanox.co.il>
Reviewed-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
The resource tracker is used to track usage of HCA resources by the different
guests.
Virtual functions (VFs) are attached to guest operating systems but
resources are allocated from the same pool and are assigned to VFs. It is
essential that hostile/buggy guests not be able to affect the operation of
other VFs, possibly attached to other guest OSs since ConnectX firmware is not
tolerant to misuse of resources.
The resource tracker module associates each resource with a VF and maintains
state information for the allocated object. It also defines allowed state
transitions and enforces them.
Relationships between resources are also referred to. For example, CQs are
pointed to by QPs, so it is forbidden to destroy a CQ if a QP refers to it.
ICM memory is always accessible through the primary function and hence it is
allocated by the owner of the primary function.
When a guest dies, an FLR is generated for all the VFs it owns and all the
resources it used are freed.
The tracked resource types are: QPs, CQs, SRQs, MPTs, MTTs, MACs, RES_EQs,
and XRCDNs.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
CQs are resources which are allocated and tracked by the PF driver.
In multifunction mode, the allocation and icm mapping is done in
the resource tracker (later patch in this sequence).
To accomplish this, we have "work" functions whose names start with
"__", and "request" functions (same name, no __). If we are operating
in multifunction mode, the request function actually results in
comm-channel commands being sent (ALLOC_RES or FREE_RES).
The PF-driver comm-channel handler will ultimately invoke the
"work" (__) function and return the result.
If we are not in multifunction mode, the "work" handler is invoked
immediately.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
For SRIOV, some Hypervisor commands can be executed directly (native = 1).
Others should go through the command wrapper flow (for tracking resource
usage, for example, or for changing some HCA configurations that slaves
need to be notified of).
This patch sets the groundwork for this capability -- adding the correct
value of "native" in each case.
Note that if SRIOV is not activated, this parameter has no effect.
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
These were getting the macros from an implicit module.h
include via device.h, but we are planning to clean that up.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
drivers/net: Add export.h to wireless/brcm80211/brcmfmac/bcmsdh.c
This relatively recently added file uses EXPORT_SYMBOL and hence
needs export.h included so that it is compatible with the module.h
split up work.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Moves the Mellanox driver into drivers/net/ethernet/mellanox/ and
make the necessary Kconfig and Makefile changes.
CC: Roland Dreier <roland@kernel.org>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Elena Reshetova