| Age | Commit message (Collapse) | Author |
|---|
|
Reported to be needed as per fdo#70354 comment #61.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Not 100% confirmed, but seems to match from the few boards I've looked
at so far.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Was not able to obtain a trace of NVRM due to kernel version annoyances,
however, experimentally confirmed that the WAR we use on NV50/G8x boards
works here too.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
An upcoming patch will implement functionality that we don't use on any
NV40 chipset.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
An upcoming patch will implement functionality that we don't use on the
original NV50.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Increase clock timeout of some unknown engines in order to avoid failure
at high gpcclk rate.
This fixes IBUS read faults on my GF119 when reclocking is manually
enabled. Note that memory reclocking is completely broken and NvMemExec
has to be disabled to allow core clock reclocking only.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
I got confirmation that we can read and change the voltage with the same code.
The divider is also computed correctly on the gm204 we got our hands on.
Thanks to Yoshimo on IRC for executing the tests on his gm204!
Signed-off-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Let's ignore the other desktop Maxwells until I get my hands on one and confirm
that we still can change the voltage.
Signed-off-by: Martin Peres <martin.peres@free.fr>
|
|
Most Keplers actually use the GPIO-based voltage management instead of the new
PWM-based one. Use the GPIO mode as a fallback as it already gracefully handles
the case where no GPIOs exist.
All the Maxwells seem to use the PWM method though.
v2:
- Do not forget to commit the PWM configuration change!
Signed-off-by: Martin Peres <martin.peres@free.fr>
|
|
This patch is not ideal but it definitely beats a rewrite of the current
interface and is very self-contained.
Signed-off-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Signed-off-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
So far the DMA mask was not set for platform devices, which limited them
to a 32-bit physical space. Allow dma_set_mask() to be called for
non-PCI devices, and also take the IOMMU bit into account since it could
restrict the physically addressable space.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
The pci_dma_* functions are now superseeded in the kernel by the DMA
API. Make the conversion to this more generic API.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Use the IOMMU bit specified in platform data instead of hardcoding it to
the bit used by current Tegra GPUs.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Current Tegra code taking advantage of the IOMMU assumes a hardcoded
value for the IOMMU bit. Make it a platform property instead for
flexibility.
v2 (Ben Skeggs): remove nvkm dependence on drm structures
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
The Great Nouveau Refactoring Take II brought us a lot of goodness,
including acquire/release methods that are called before and after an
instobj is modified. These functions can be used as synchronization
points to manage CPU/GPU coherency if we modify an instobj using the
CPU.
This patch replaces the legacy and slow PRAMIN access for gk20a instmem
with CPU mappings and writes. A LRU list is used to unmap unused
mappings after a certain threshold (currently 1MB) of mapped instobjs is
reached. This allows mappings to be reused most of the time.
Accessing instobjs using the CPU requires to maintain the GPU L2 cache,
which we do in the acquire/release functions. This triggers a lot of L2
flushes/invalidates, but most of them are performed on an empty cache
(and thus return immediately), and overall context setup performance
greatly benefits from this (from 250ms to 160ms on Jetson TK1 for a
simple libdrm program).
Making L2 management more explicit should allow us to grab some more
performance in the future.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
No longer required in a lot of cases, as objects are identified over NVIF
via an alternate mechanism since the rework.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Allow clients to manually flush and invalidate L2. This will be useful
for Tegra systems for which we want to write instmem using the CPU.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
These are useful for systems without a coherent CPU/GPU bus. For such
systems we may need to maintain the L2 ourselves.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Reintroduce macros allowing us to test a register against a certain
mask, since this is the most common usage pattern for the more generic
nvkm_xsec macros and makes the code more concise and readable.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
Some devices may not have a PMU. Avoid a NULL pointer dereference in
such cases by checking whether the pointer given to nvkm_pmu_pgob() is
valid.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
On nv50+, we restrict the valid domains to just the one where the buffer
was originally created. However after the buffer is evicted to system
memory, we might move it back to a different domain that was not
originally valid. When sharing the buffer and retrieving its GEM_INFO
data, we still want the domain that will be valid for this buffer in a
pushbuf, not the one where it currently happens to be.
This resolves fdo#92504 and several others. These are due to suspend
evicting all buffers, making it more likely that they temporarily end up
in the wrong place.
Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=92504
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
|
In sg_common_write(), we free the block request and return -ENODEV if
the device is detached in the middle of the SG_IO ioctl().
Unfortunately, sg_finish_rem_req() also tries to free srp->rq, so we
end up freeing rq->cmd in the already free rq object, and then free
the object itself out from under the current user.
This ends up corrupting random memory via the list_head on the rq
object. The most common crash trace I saw is this:
------------[ cut here ]------------
kernel BUG at block/blk-core.c:1420!
Call Trace:
[<ffffffff81281eab>] blk_put_request+0x5b/0x80
[<ffffffffa0069e5b>] sg_finish_rem_req+0x6b/0x120 [sg]
[<ffffffffa006bcb9>] sg_common_write.isra.14+0x459/0x5a0 [sg]
[<ffffffff8125b328>] ? selinux_file_alloc_security+0x48/0x70
[<ffffffffa006bf95>] sg_new_write.isra.17+0x195/0x2d0 [sg]
[<ffffffffa006cef4>] sg_ioctl+0x644/0xdb0 [sg]
[<ffffffff81170f80>] do_vfs_ioctl+0x90/0x520
[<ffffffff81258967>] ? file_has_perm+0x97/0xb0
[<ffffffff811714a1>] SyS_ioctl+0x91/0xb0
[<ffffffff81602afb>] tracesys+0xdd/0xe2
RIP [<ffffffff81281e04>] __blk_put_request+0x154/0x1a0
The solution is straightforward: just set srp->rq to NULL in the
failure branch so that sg_finish_rem_req() doesn't attempt to re-free
it.
Additionally, since sg_rq_end_io() will never be called on the object
when this happens, we need to free memory backing ->cmd if it isn't
embedded in the object itself.
KASAN was extremely helpful in finding the root cause of this bug.
Signed-off-by: Calvin Owens <calvinowens@fb.com>
Acked-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
When probing devices-in-package for a c45 phy, device zero is the last
device to probe, however, if driver reads 0 from device zero,
c45_ids->devices_in_package is set to '0', the loop condition of probing
will be matched again, see codes below:
for (i = 1;i < num_ids && c45_ids->devices_in_package == 0;i++)
driver will run in a dead loop.
This patch restructures the bug and confusing loop, it provides a helper
function get_phy_c45_devs_in_pkg which to read devices-in-package registers
of a MMD, and rewrites the loop with using the helper function.
Signed-off-by: Shaohui Xie <Shaohui.Xie@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
There are some netdev features, which when disabled on an upper device,
such as a bonding master or a bridge, must be disabled and cannot be
re-enabled on underlying devices.
This is a rework of an earlier more heavy-handed appraoch, which simply
disables and prevents re-enabling of netdev features listed in a new
define in include/net/netdev_features.h, NETIF_F_UPPER_DISABLES. Any upper
device that disables a flag in that feature mask, the disabling will
propagate down the stack, and any lower device that has any upper device
with one of those flags disabled should not be able to enable said flag.
Initially, only LRO is included for proof of concept, and because this
code effectively does the same thing as dev_disable_lro(), though it will
also activate from the ethtool path, which was one of the goals here.
[root@dell-per730-01 ~]# ethtool -k bond0 |grep large
large-receive-offload: on
[root@dell-per730-01 ~]# ethtool -k p5p1 |grep large
large-receive-offload: on
[root@dell-per730-01 ~]# ethtool -K bond0 lro off
[root@dell-per730-01 ~]# ethtool -k bond0 |grep large
large-receive-offload: off
[root@dell-per730-01 ~]# ethtool -k p5p1 |grep large
large-receive-offload: off
dmesg dump:
[ 1033.277986] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2.
[ 1034.067949] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83
[ 1034.753612] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1.
[ 1035.591019] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71
This has been successfully tested with bnx2x, qlcnic and netxen network
cards as slaves in a bond interface. Turning LRO on or off on the master
also turns it on or off on each of the slaves, new slaves are added with
LRO in the same state as the master, and LRO can't be toggled on the
slaves.
Also, this should largely remove the need for dev_disable_lro(), and most,
if not all, of its call sites can be replaced by simply making sure
NETIF_F_LRO isn't included in the relevant device's feature flags.
Note that this patch is driven by bug reports from users saying it was
confusing that bonds and slaves had different settings for the same
features, and while it won't be 100% in sync if a lower device doesn't
support a feature like LRO, I think this is a good step in the right
direction.
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Nikolay Aleksandrov <razor@blackwall.org>
CC: Michal Kubecek <mkubecek@suse.cz>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
If MSI(X) interrupts are disabled via the kernel command line
(pci=nomsi), the pm8001 driver will kernel panic because it does not
detect that MSI interrupts are disabled and will soldier on and attempt to
configure MSI interrupts anyways. This leads to a kernel panic, most
likely because a required data structure is not available down the
line. Using the pci_msi_enabled() function in order to detect if MSI
interrupts are enabled before configuring them resolves this issue and
avoids a kernel panic when the module is loaded. Additionally, the
irq_vector structure must be initialized when legacy interrupts are
being used otherwise legacy interrupts will simply not function and
result in another panic.
Signed-off-by: Benjamin Rood <brood@attotech.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
The documentation for the 8070 and 8072 SPCv chip explicitly states that
a minimum of 500ms must elapse before issuing commands, otherwise the
SPCv may not process them and the firmware may get into an unrecoverable
state requiring a reboot. While the Linux guys will probably think this
is 'racy', it is called out in the chip documentation and inserting this
delay makes power management function properly.
Signed-off-by: Benjamin Rood <brood@attotech.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
ATTO adapters do not support this feature. If the firmware fails to be
ready, it should not check the examined registers in order to examine
the state of the feature in order to prevent undefined behavior.
Signed-off-by: Benjamin Rood <brood@attotech.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
PHY profiles are not saved in NVRAM on ATTO 12Gb SAS controllers.
Therefore, in order for the controller to function in a wide range of
configurations, the PHY profiles must be statically set. This patch
provides the necessary functionality to do so.
Signed-off-by: Benjamin Rood <brood@attotech.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
ATTO SAS controllers retrieve the SAS address from the NVRAM in a location
different from non-ATTO PMC Sierra SAS controllers. This patch makes the
necessary adjustments in order to retrieve the SAS address on these types
of adapters.
Signed-off-by: Benjamin Rood <brood@attotech.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
These PCI IDs allow the pm8001 driver to load against ATTO 12Gb SAS
controllers that use PMC Sierra 8070 and PMC Sierra 8072 SAS chips.
Signed-off-by: Benjamin Rood <brood@attotech.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
These SAS controllers support speeds up to 12Gb.
Signed-off-by: Benjamin Rood <brood@attotech.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Previuosly, all PMC Sierra 80xx controllers are assumed to be a
motherboard controller, except if the subsystem vendor ID was equal to
PCI_VENDOR_ID_ADAPTEC. The driver then attempts to load PHY settings
from NVRAM. While this may be correct behavior for most controllers, it
does not work with Adaptec and ATTO controllers since they do not store
PHY settings in NVRAM and choose to use either custom PHY settings or
chip defaults. Loading random values from NVRAM may cause the
controllers to malfunction in this edge case.
Signed-off-by: Benjamin Rood <brood@attotech.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
This patch fixes an issue seen with an IBM 2145 (SVC) where, following an error
injection test which results in paths going offline, when they came
back online, the path would timeout the REPORT_LUNS issued during the
scan. This timeout situation continued until retries were expired, resulting in
falling back to a sequential LUN scan. Then, since the target responds
with PQ=1, PDT=0 for all possible LUNs, due to the way the sequential
LUN scan code works, we end up adding 512 LUNs for each target, when there
is really only a small handful of LUNs that are actually present.
This patch increases the timeout used on the REPORT_LUNS to 30 seconds.
This patch solves the issue of 512 non existent LUNs showing up after
this event.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
When the IP stack passes SKBs the sfc driver puts them in 2 different TX
queues (called partners), one for checksummed and one for not checksummed.
If the SKB has xmit_more set the driver will delay pushing the work to the
NIC.
When later it does decide to push the buffers this patch ensures it also
pushes the partner queue, if that also has any delayed work. Before this
fix the work in the partner queue would be left for a long time and cause
a netdev watchdog.
Fixes: 70b33fb ("sfc: add support for skb->xmit_more")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The correct name of the RX descriptor 0 bit 30 is RDLE (receive descriptor
list end), not RDEL.
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
This is an issue on SMAP enabled CPUs and 32 bit apps running on 64 bit
OS. Do not access user memory from kernel code. The SMAP bit restricts
accessing user memory from kernel code.
Cc: <stable@vger.kernel.org>
Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
|
|
sit0 device allocates its percpu storage twice :
- One time in ipip6_tunnel_init()
- One time in ipip6_fb_tunnel_init()
Thus we leak 48 bytes per possible cpu per network namespace dismantle.
ipip6_fb_tunnel_init() can be much simpler and does not
return an error, and should be called after register_netdev()
Note that ipip6_tunnel_clone_6rd() also needs to be called
after register_netdev() (calling ipip6_tunnel_init())
Fixes: ebe084aafb7e ("sit: Use ipip6_tunnel_init as the ndo_init function.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Mahesh Bandewar says:
====================
re-org actor admin/oper key updates
I was observing machines entering into weird LACP state when the
partner is in passive mode. This issue is not because of the partners
in passive state but probably because of some operational key update
which is pushing the state-machine is that weird state. This was
happening randomly on about 1% of the machine (when the sample size
is a large set of machines with a variety of NICs/ports bonded).
In this patch-series I'm attempting to unify the logic of actor-key
/ operational-key changes to one place to avoid possible errors in
update. Also this eliminates the need for the event-handler to decide
if the key needs update.
After this patch-set none of the machines (from same sample set) were
exhibiting LACP-weirdness that was observed earlier.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Old logic of updating state-machine is not required since
ad_update_actor_keys() does it implicitly. The only loss is
the notification differentiation between speed vs. duplex
change. Now only one unified notification is printed.
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
actor_admin, and actor_oper key is changed at multiple locations in
the code. This patch brings all those updates into one location in
an attempt to avoid possible inconsistent updates causing LACP state
machine to go in weird state.
The unified place is ad_update_actor_key() with simple state-machine
logic -
(a) If port is "duplex" then only it can participate in LACP
(b) Speed change reinitializes the LACP state-machine.
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Eliminate 'else' clause by simply initializing variable
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Daniel Borkmann says:
====================
BPF updates
This set adds support for persistent maps/progs. Please see
individual patches for further details. A man-page update
to bpf(2) will be sent later on, also a iproute2 patch for
support in tc.
v1 -> v2:
- Reworked most of patch 4 and 5
- Rebased to latest net-next
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch adds a couple of stand-alone examples on how BPF_OBJ_PIN
and BPF_OBJ_GET commands can be used.
Example with maps:
# ./fds_example -F /sys/fs/bpf/m -P -m -k 1 -v 42
bpf: map fd:3 (Success)
bpf: pin ret:(0,Success)
bpf: fd:3 u->(1:42) ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m -G -m -k 1
bpf: get fd:3 (Success)
bpf: fd:3 l->(1):42 ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m -G -m -k 1 -v 24
bpf: get fd:3 (Success)
bpf: fd:3 u->(1:24) ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m -G -m -k 1
bpf: get fd:3 (Success)
bpf: fd:3 l->(1):24 ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m2 -P -m
bpf: map fd:3 (Success)
bpf: pin ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m2 -G -m -k 1
bpf: get fd:3 (Success)
bpf: fd:3 l->(1):0 ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/m2 -G -m
bpf: get fd:3 (Success)
Example with progs:
# ./fds_example -F /sys/fs/bpf/p -P -p
bpf: prog fd:3 (Success)
bpf: pin ret:(0,Success)
bpf sock:4 <- fd:3 attached ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/p -G -p
bpf: get fd:3 (Success)
bpf: sock:4 <- fd:3 attached ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/p2 -P -p -o ./sockex1_kern.o
bpf: prog fd:5 (Success)
bpf: pin ret:(0,Success)
bpf: sock:3 <- fd:5 attached ret:(0,Success)
# ./fds_example -F /sys/fs/bpf/p2 -G -p
bpf: get fd:3 (Success)
bpf: sock:4 <- fd:3 attached ret:(0,Success)
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This work adds support for "persistent" eBPF maps/programs. The term
"persistent" is to be understood that maps/programs have a facility
that lets them survive process termination. This is desired by various
eBPF subsystem users.
Just to name one example: tc classifier/action. Whenever tc parses
the ELF object, extracts and loads maps/progs into the kernel, these
file descriptors will be out of reach after the tc instance exits.
So a subsequent tc invocation won't be able to access/relocate on this
resource, and therefore maps cannot easily be shared, f.e. between the
ingress and egress networking data path.
The current workaround is that Unix domain sockets (UDS) need to be
instrumented in order to pass the created eBPF map/program file
descriptors to a third party management daemon through UDS' socket
passing facility. This makes it a bit complicated to deploy shared
eBPF maps or programs (programs f.e. for tail calls) among various
processes.
We've been brainstorming on how we could tackle this issue and various
approches have been tried out so far, which can be read up further in
the below reference.
The architecture we eventually ended up with is a minimal file system
that can hold map/prog objects. The file system is a per mount namespace
singleton, and the default mount point is /sys/fs/bpf/. Any subsequent
mounts within a given namespace will point to the same instance. The
file system allows for creating a user-defined directory structure.
The objects for maps/progs are created/fetched through bpf(2) with
two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor
along with a pathname is being passed to bpf(2) that in turn creates
(we call it eBPF object pinning) the file system nodes. Only the pathname
is being passed to bpf(2) for getting a new BPF file descriptor to an
existing node. The user can use that to access maps and progs later on,
through bpf(2). Removal of file system nodes is being managed through
normal VFS functions such as unlink(2), etc. The file system code is
kept to a very minimum and can be further extended later on.
The next step I'm working on is to add dump eBPF map/prog commands
to bpf(2), so that a specification from a given file descriptor can
be retrieved. This can be used by things like CRIU but also applications
can inspect the meta data after calling BPF_OBJ_GET.
Big thanks also to Alexei and Hannes who significantly contributed
in the design discussion that eventually let us end up with this
architecture here.
Reference: https://lkml.org/lkml/2015/10/15/925
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
We currently have duplicated cleanup code in bpf_prog_put() and
bpf_prog_put_rcu() cleanup paths. Back then we decided that it was
not worth it to make it a common helper called by both, but with
the recent addition of resource charging, we could have avoided
the fix in commit ac00737f4e81 ("bpf: Need to call bpf_prog_uncharge_memlock
from bpf_prog_put") if we would have had only a single, common path.
We can simplify it further by assigning aux->prog only once during
allocation time.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add a bpf_map_get() function that we're going to use later on and
align/clean the remaining helpers a bit so that we have them a bit
more consistent:
- __bpf_map_get() and __bpf_prog_get() that both work on the fd
struct, check whether the descriptor is eBPF and return the
pointer to the map/prog stored in the private data.
Also, we can return f.file->private_data directly, the function
signature is enough of a documentation already.
- bpf_map_get() and bpf_prog_get() that both work on u32 user fd,
call their respective __bpf_map_get()/__bpf_prog_get() variants,
and take a reference.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
