Directly use the platform device for generating the miibus name. This
removes the last user of bcm_enet_priv::mac_id and we can remove the
field.
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enabling the ephy clock for mac 1 is harmless, and the actual usage of
the ephy is not restricted to mac 0, so we might as well remove the
check.
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To reduce the reliance on device ids, pass the dma channel numbers to
the enet devices as platform data.
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that we have the individual clocks available as "enet" we
don't need to rely on the device id for them anymore.
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Haishuang Yan says:
====================
net: speedup geneve/vxlan tunnels dismantle
This patch series add batching to vxlan/geneve tunnels so that netns
dismantles are less costly.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Since we now hold RTNL lock in geneve_exit_net, it's better batch them
to speedup geneve tunnel dismantle.
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since we now hold RTNL lock in vxlan_exit_net, it's better to batch them
to speedup vxlan tunnels dismantle.
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since both first_tx_ctx and tx_skb are the head of tx ctx, it not
necessary to use two structure members to statically indicate
the head of tx ctx. So first_tx_ctx is removed.
CC: Srinivas Eeda <srinivas.eeda@oracle.com>
CC: Joe Jin <joe.jin@oracle.com>
CC: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan says:
====================
Introduce NETIF_F_GRO_HW
Introduce NETIF_F_GRO_HW feature flag and convert drivers that support
hardware GRO to use the new flag.
v5:
- Documentation changes requested by Alexander Duyck.
- bnx2x changes requested by Manish Chopra to enable LRO by default, and
disable GRO_HW if disable_tpa module parameter is set.
v4:
- more changes requested by Alexander Duyck:
- check GRO_HW/GRO dependency in drivers's ndo_fix_features().
- Reverse the order of RXCSUM and GRO_HW dependency check in
netdev_fix_features().
- No propagation in netdev_disable_gro_hw().
v3:
- Let driver's ndo_fix_features() disable NETIF_F_LRO when NETIF_F_GRO_HW
is set instead of doing it in common netdev_fix_features().
v2:
- NETIF_F_GRO_HW flag propagation between upper and lower devices not
required (see patch 1).
- NETIF_F_GRO_HW depends on NETIF_F_GRO and NETIF_F_RXCSUM.
- Add dev_disable_gro_hw() to disable GRO_HW for generic XDP.
- Use ndo_fix_features() on all 3 drivers to drop GRO_HW when it is not
supported
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Advertise NETIF_F_GRO_HW and set edev->gro_disable according to the
feature flag. Add qede_fix_features() to drop NETIF_F_GRO_HW if
XDP is running or MTU does not support GRO_HW or GRO is not set.
qede_change_mtu() also checks and disables GRO_HW if MTU is not
supported.
Cc: Ariel Elior <Ariel.Elior@cavium.com>
Cc: everest-linux-l2@cavium.com
Acked-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Acked-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Advertise NETIF_F_GRO_HW and turn on TPA_MODE_GRO when NETIF_F_GRO_HW
is set. Disable NETIF_F_GRO_HW in bnx2x_fix_features() if the MTU
does not support TPA_MODE_GRO or GRO is not set. bnx2x_change_mtu() also
needs to disable NETIF_F_GRO_HW if the MTU does not support it.
Original parameter disable_tpa will continue to disable LRO and GRO_HW.
Preserve the original behavior of enabling LRO by default. User has
to run ethtool -K to explicitly enable GRO_HW.
Cc: Ariel Elior <Ariel.Elior@cavium.com>
Cc: everest-linux-l2@cavium.com
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Acked-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Advertise NETIF_F_GRO_HW in hw_features if hardware GRO is supported.
In bnxt_fix_features(), disable GRO_HW and LRO if current hardware
configuration does not allow it. GRO_HW depends on GRO. GRO_HW is
also mutually exclusive with LRO. XDP setup will now rely on
bnxt_fix_features() to turn off aggregation. During chip init, turn on
or off hardware GRO based on NETIF_F_GRO_HW in features flag.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hardware should not aggregate any packets when generic XDP is installed.
Cc: Ariel Elior <Ariel.Elior@cavium.com>
Cc: everest-linux-l2@cavium.com
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce NETIF_F_GRO_HW feature flag for NICs that support hardware
GRO. With this flag, we can now independently turn on or off hardware
GRO when GRO is on. Previously, drivers were using NETIF_F_GRO to
control hardware GRO and so it cannot be independently turned on or
off without affecting GRO.
Hardware GRO (just like GRO) guarantees that packets can be re-segmented
by TSO/GSO to reconstruct the original packet stream. Logically,
GRO_HW should depend on GRO since it a subset, but we will let
individual drivers enforce this dependency as they see fit.
Since NETIF_F_GRO is not propagated between upper and lower devices,
NETIF_F_GRO_HW should follow suit since it is a subset of GRO. In other
words, a lower device can independent have GRO/GRO_HW enabled or disabled
and no feature propagation is required. This will preserve the current
GRO behavior. This can be changed later if we decide to propagate GRO/
GRO_HW/RXCSUM from upper to lower devices.
Cc: Ariel Elior <Ariel.Elior@cavium.com>
Cc: everest-linux-l2@cavium.com
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When CONFIG_PROC_FS is disabled, we will not use the prot_inuse
counter. This adds an #ifdef to hide the variable definition in
that case. This is not a bugfix. But we can save bytes when there
are many network namespace.
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Martin Zhang <zhangjunweimartin@didichuxing.com>
Signed-off-by: Tonghao Zhang <zhangtonghao@didichuxing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In some case, we want to know how many sockets are in use in
different _net_ namespaces. It's a key resource metric.
This patch add a member in struct netns_core. This is a counter
for socket-inuse in the _net_ namespace. The patch will add/sub
counter in the sk_alloc, sk_clone_lock and __sk_free.
This patch will not counter the socket created in kernel.
It's not very useful for userspace to know how many kernel
sockets we created.
The main reasons for doing this are that:
1. When linux calls the 'do_exit' for process to exit, the functions
'exit_task_namespaces' and 'exit_task_work' will be called sequentially.
'exit_task_namespaces' may have destroyed the _net_ namespace, but
'sock_release' called in 'exit_task_work' may use the _net_ namespace
if we counter the socket-inuse in sock_release.
2. socket and sock are in pair. More important, sock holds the _net_
namespace. We counter the socket-inuse in sock, for avoiding holding
_net_ namespace again in socket. It's a easy way to maintain the code.
Signed-off-by: Martin Zhang <zhangjunweimartin@didichuxing.com>
Signed-off-by: Tonghao Zhang <zhangtonghao@didichuxing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change the member name will make the code more readable.
This patch will be used in next patch.
Signed-off-by: Martin Zhang <zhangjunweimartin@didichuxing.com>
Signed-off-by: Tonghao Zhang <zhangtonghao@didichuxing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Simplify PCIe Completion Timeout setting by using the
pcie_capability_clear_and_set_word() interface. No functional change
intended.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
William Tu says:
====================
net: erspan: a couple fixes
Haishuang Yan reports a couple of issues (wrong return value,
pskb_may_pull) on erspan V1. Since erspan V2 is in net-next,
this series fix the similar issues on v2.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
pskb_may_pull() can change skb->data, so we need to re-load pkt_md
and ershdr at the right place.
Fixes: 94d7d8f292 ("ip6_gre: add erspan v2 support")
Fixes: f551c91de2 ("net: erspan: introduce erspan v2 for ip_gre")
Signed-off-by: William Tu <u9012063@gmail.com>
Cc: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If pskb_may_pull return failed, return PACKET_REJECT
instead of -ENOMEM.
Fixes: 94d7d8f292 ("ip6_gre: add erspan v2 support")
Fixes: f551c91de2 ("net: erspan: introduce erspan v2 for ip_gre")
Signed-off-by: William Tu <u9012063@gmail.com>
Cc: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Russell King says:
====================
More SFP/phylink fixes
This series fixes a few more bits with sfp/phylink, particularly
confusion with the right way to test for the RTNL mutex being
held, a change in 2016 to the mdiobus_scan() behaviour that wasn't
noticed, and a fix for reading module EEPROMs.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Use ASSERT_RTNL() rather than WARN_ON(!lockdep_rtnl_is_held()) which
stops working when lockdep fires, and we end up with lots of warnings.
Fixes: 9525ae8395 ("phylink: add phylink infrastructure")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
The EEPROM reading was trying to read from the second EEPROM address
if we requested the last byte from the SFF8079 EEPROM, which caused a
failure when the second EEPROM is not present. Discovered with a
S-RJ01 SFP module. Fix this.
Fixes: 7397005545 ("sfp: add SFP module support")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
The detection of a PHY changed in commit e98a3aabf8 ("mdio_bus: don't
return NULL from mdiobus_scan()") which now causes sfp to print an
error message. Update for this change.
Fixes: 7397005545 ("sfp: add SFP module support")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current HNCDSC handler takes the status flag from the AEN packet and
will update or change the current channel based on this flag and the
current channel status.
However the flag from the HNCDSC packet merely represents the host link
state. While the state of the host interface is potentially interesting
information it should not affect the state of the NCSI link. Indeed the
NCSI specification makes no mention of any recommended action related to
the host network controller driver state.
Update the HNCDSC handler to record the host network driver status but
take no other action.
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Acked-by: Jeremy Kerr <jk@ozlabs.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jerome Brunet says:
====================
net: phy: meson-gxl: clean-up and improvements
This patchset adds defines for the control registers and helpers to access
the banked registers. The goal being to make it easier to understand what
the driver actually does.
Then CONFIG_A6 settings is removed since this statement was without effect
Finally interrupt support is added, speeding things up a little
This series has been tested on the libretech-cc and khadas VIM
Changes since v2 [0]:
Drop LPA corruption fix which has been merged through net. Apart from this,
series remains the same.
[0]: https://lkml.kernel.org/r/20171207142715.32578-1-jbrunet@baylibre.com
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Following previous changes, join the other authors of this driver and
take the blame with them
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enable interrupt support in meson-gxl PHY driver
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The PHY performs just as well when left in its default configuration and
it makes senses because this poke gets reset just after init.
According to the documentation, all registers in the Analog/DSP bank are
reset when there is a mode switch from 10BT to 100BT. The bank is also
reset on power down and soft reset, so we will never see the value which
may have been set by the bootloader.
In the end, we have used the default configuration so far and there is no
reason to change now. Remove CONFIG_A6 poke to make this clear.
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the generic init function to populate some of the phydev
structure fields
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add read and write helpers to manipulate banked registers on this PHY
This helps clarify the settings applied to these registers and what the
driver actually does
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Define registers and bits in meson-gxl PHY driver to make a bit
more human friendly. No functional change.
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Always check phy_write return values. Better to be safe than sorry
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Edward Cree says:
====================
sfc: Initial X2000-series (Medford2) support
Basic PCI-level changes to support X2000-series NICs.
Also fix unexpected-PTP-event log messages, since the timestamp format has
been changed in these NICs and that causes us to fail to probe PTP (but we
still get the PPS events).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The timer mode register now has a separate field for the reload value.
Since we always use this timer with the reload (for interrupt moderation)
we set this to the same as the initial value.
Previous hardware ignores this field, so we can safely set these bits
on all hardware that uses this register.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The RX_L4_CLASS field has shrunk from 3 bits to 2 bits. The upper
bit was never used in previous hardware, so we can use the new
definition throughout.
The TSO OUTER_IPID field was previously spelt differently from the
external definitions.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Log a message if PTP probing fails; if we then, unexpectedly, get PTP
events, only log a message for the first one on each device.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Medford2 can also have 16k or 64k VI stride. This is reported by MCDI in
GET_CAPABILITIES, which fortunately is called before the driver does
anything sensitive to the VI stride (such as accessing or even allocating
VIs past the zeroth).
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support using BAR 0 on SFC9250, even though the driver doesn't bind to such
devices yet.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Borkmann says:
====================
pull-request: bpf-next 2017-12-18
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Allow arbitrary function calls from one BPF function to another BPF function.
As of today when writing BPF programs, __always_inline had to be used in
the BPF C programs for all functions, unnecessarily causing LLVM to inflate
code size. Handle this more naturally with support for BPF to BPF calls
such that this __always_inline restriction can be overcome. As a result,
it allows for better optimized code and finally enables to introduce core
BPF libraries in the future that can be reused out of different projects.
x86 and arm64 JIT support was added as well, from Alexei.
2) Add infrastructure for tagging functions as error injectable and allow for
BPF to return arbitrary error values when BPF is attached via kprobes on
those. This way of injecting errors generically eases testing and debugging
without having to recompile or restart the kernel. Tags for opting-in for
this facility are added with BPF_ALLOW_ERROR_INJECTION(), from Josef.
3) For BPF offload via nfp JIT, add support for bpf_xdp_adjust_head() helper
call for XDP programs. First part of this work adds handling of BPF
capabilities included in the firmware, and the later patches add support
to the nfp verifier part and JIT as well as some small optimizations,
from Jakub.
4) The bpftool now also gets support for basic cgroup BPF operations such
as attaching, detaching and listing current BPF programs. As a requirement
for the attach part, bpftool can now also load object files through
'bpftool prog load'. This reuses libbpf which we have in the kernel tree
as well. bpftool-cgroup man page is added along with it, from Roman.
5) Back then commit e87c6bc385 ("bpf: permit multiple bpf attachments for
a single perf event") added support for attaching multiple BPF programs
to a single perf event. Given they are configured through perf's ioctl()
interface, the interface has been extended with a PERF_EVENT_IOC_QUERY_BPF
command in this work in order to return an array of one or multiple BPF
prog ids that are currently attached, from Yonghong.
6) Various minor fixes and cleanups to the bpftool's Makefile as well
as a new 'uninstall' and 'doc-uninstall' target for removing bpftool
itself or prior installed documentation related to it, from Quentin.
7) Add CONFIG_CGROUP_BPF=y to the BPF kernel selftest config file which is
required for the test_dev_cgroup test case to run, from Naresh.
8) Fix reporting of XDP prog_flags for nfp driver, from Jakub.
9) Fix libbpf's exit code from the Makefile when libelf was not found in
the system, also from Jakub.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Things got moved around between the original bpf_override_return patches
and the final version, and now the ftrace kprobe dispatcher assumes if
you modified the ip that you also enabled preemption. Make a comment of
this and enable preemption, this fixes the lockdep splat that happened
when using this feature.
Fixes: 9802d86585 ("bpf: add a bpf_override_function helper")
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
netdev_bpf.flags is the input member for installing the program.
netdev_bpf.prog_flags is the output member for querying. Set
the correct one on query.
Fixes: 92f0292b35 ("net: xdp: report flags program was installed with on query")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
/bin/sh's exit does not recognize -1 as a number, leading to
the following error message:
/bin/sh: 1: exit: Illegal number: -1
Use 1 as the exit code.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Alexei Starovoitov says:
====================
First of all huge thank you to Daniel, John, Jakub, Edward and others who
reviewed multiple iterations of this patch set over the last many months
and to Dave and others who gave critical feedback during netconf/netdev.
The patch is solid enough and we thought through numerous corner cases,
but it's not the end. More followups with code reorg and features to follow.
TLDR: Allow arbitrary function calls from bpf function to another bpf function.
Since the beginning of bpf all bpf programs were represented as a single function
and program authors were forced to use always_inline for all functions
in their C code. That was causing llvm to unnecessary inflate the code size
and forcing developers to move code to header files with little code reuse.
With a bit of additional complexity teach verifier to recognize
arbitrary function calls from one bpf function to another as long as
all of functions are presented to the verifier as a single bpf program.
Extended program layout:
..
r1 = .. // arg1
r2 = .. // arg2
call pc+1 // function call pc-relative
exit
.. = r1 // access arg1
.. = r2 // access arg2
..
call pc+20 // second level of function call
...
It allows for better optimized code and finally allows to introduce
the core bpf libraries that can be reused in different projects,
since programs are no longer limited by single elf file.
With function calls bpf can be compiled into multiple .o files.
This patch is the first step. It detects programs that contain
multiple functions and checks that calls between them are valid.
It splits the sequence of bpf instructions (one program) into a set
of bpf functions that call each other. Calls to only known
functions are allowed. Since all functions are presented to
the verifier at once conceptually it is 'static linking'.
Future plans:
- introduce BPF_PROG_TYPE_LIBRARY and allow a set of bpf functions
to be loaded into the kernel that can be later linked to other
programs with concrete program types. Aka 'dynamic linking'.
- introduce function pointer type and indirect calls to allow
bpf functions call other dynamically loaded bpf functions while
the caller bpf function is already executing. Aka 'runtime linking'.
This will be more generic and more flexible alternative
to bpf_tail_calls.
FAQ:
Q: Interpreter and JIT changes mean that new instruction is introduced ?
A: No. The call instruction technically stays the same. Now it can call
both kernel helpers and other bpf functions.
Calling convention stays the same as well.
From uapi point of view the call insn got new 'relocation' BPF_PSEUDO_CALL
similar to BPF_PSEUDO_MAP_FD 'relocation' of bpf_ldimm64 insn.
Q: What had to change on LLVM side?
A: Trivial LLVM patch to allow calls was applied to upcoming 6.0 release:
https://reviews.llvm.org/rL318614
with few bugfixes as well.
Make sure to build the latest llvm to have bpf_call support.
More details in the patches.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Add some additional checks for few more corner cases.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
similar to x64 add support for bpf-to-bpf calls.
When program has calls to in-kernel helpers the target call offset
is known at JIT time and arm64 architecture needs 2 passes.
With bpf-to-bpf calls the dynamically allocated function start
is unknown until all functions of the program are JITed.
Therefore (just like x64) arm64 JIT needs one extra pass over
the program to emit correct call offsets.
Implementation detail:
Avoid being too clever in 64-bit immediate moves and
always use 4 instructions (instead of 3-4 depending on the address)
to make sure only one extra pass is needed.
If some future optimization would make it worth while to optimize
'call 64-bit imm' further, the JIT would need to do 4 passes
over the program instead of 3 as in this patch.
For typical bpf program address the mov needs 3 or 4 insns,
so unconditional 4 insns to save extra pass is a worthy trade off
at this state of JIT.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Typical JIT does several passes over bpf instructions to
compute total size and relative offsets of jumps and calls.
With multitple bpf functions calling each other all relative calls
will have invalid offsets intially therefore we need to additional
last pass over the program to emit calls with correct offsets.
For example in case of three bpf functions:
main:
call foo
call bpf_map_lookup
exit
foo:
call bar
exit
bar:
exit
We will call bpf_int_jit_compile() indepedently for main(), foo() and bar()
x64 JIT typically does 4-5 passes to converge.
After these initial passes the image for these 3 functions
will be good except call targets, since start addresses of
foo() and bar() are unknown when we were JITing main()
(note that call bpf_map_lookup will be resolved properly
during initial passes).
Once start addresses of 3 functions are known we patch
call_insn->imm to point to right functions and call
bpf_int_jit_compile() again which needs only one pass.
Additional safety checks are done to make sure this
last pass doesn't produce image that is larger or smaller
than previous pass.
When constant blinding is on it's applied to all functions
at the first pass, since doing it once again at the last
pass can change size of the JITed code.
Tested on x64 and arm64 hw with JIT on/off, blinding on/off.
x64 jits bpf-to-bpf calls correctly while arm64 falls back to interpreter.
All other JITs that support normal BPF_CALL will behave the same way
since bpf-to-bpf call is equivalent to bpf-to-kernel call from
JITs point of view.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
global bpf_jit_enable variable is tested multiple times in JITs,
blinding and verifier core. The malicious root can try to toggle
it while loading the programs. This race condition was accounted
for and there should be no issues, but it's safer to avoid
this race condition.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
