Age | Commit message (Collapse) | Author | Files | Lines |
|
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>
|
|
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>
|
|
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>
|
|
pskb_may_pull() can change skb->data, so we need to re-load pkt_md
and ershdr at the right place.
Fixes: 94d7d8f29287 ("ip6_gre: add erspan v2 support")
Fixes: f551c91de262 ("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: 94d7d8f29287 ("ip6_gre: add erspan v2 support")
Fixes: f551c91de262 ("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>
|
|
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: 9525ae83959b ("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: 73970055450e ("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 e98a3aabf85f ("mdio_bus: don't
return NULL from mdiobus_scan()") which now causes sfp to print an
error message. Update for this change.
Fixes: 73970055450e ("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>
|
|
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>
|
|
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>
|
|
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>
|
|
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: 9802d86585db ("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: 92f0292b35a0 ("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>
|
|
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>
|
|
though bpf_call is still the same call instruction and
calling convention 'bpf to bpf' and 'bpf to helper' is the same
the interpreter has to oparate on 'struct bpf_insn *'.
To distinguish these two cases add a kernel internal opcode and
mark call insns with it.
This opcode is seen by interpreter only. JITs will never see it.
Also add tiny bit of debug code to aid interpreter debugging.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
add large semi-artificial XDP test with 18 functions to stress test
bpf call verification logic
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
strip always_inline from test_l4lb.c and compile it with -fno-inline
to let verifier go through 11 function with various function arguments
and return values
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
- recognize relocation emitted by llvm
- since all regular function will be kept in .text section and llvm
takes care of pc-relative offsets in bpf_call instruction
simply copy all of .text to relevant program section while adjusting
bpf_call instructions in program section to point to newly copied
body of instructions from .text
- do so for all programs in the elf file
- set all programs types to the one passed to bpf_prog_load()
Note for elf files with multiple programs that use different
functions in .text section we need to do 'linker' style logic.
This work is still TBD
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
adjust two tests, since verifier got smarter
and add new one to test stack_zero logic
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
programs with function calls are often passing various
pointers via stack. When all calls are inlined llvm
flattens stack accesses and optimizes away extra branches.
When functions are not inlined it becomes the job of
the verifier to recognize zero initialized stack to avoid
exploring paths that program will not take.
The following program would fail otherwise:
ptr = &buffer_on_stack;
*ptr = 0;
...
func_call(.., ptr, ...) {
if (..)
*ptr = bpf_map_lookup();
}
...
if (*ptr != 0) {
// Access (*ptr)->field is valid.
// Without stack_zero tracking such (*ptr)->field access
// will be rejected
}
since stack slots are no longer uniform invalid | spill | misc
add liveness marking to all slots, but do it in 8 byte chunks.
So if nothing was read or written in [fp-16, fp-9] range
it will be marked as LIVE_NONE.
If any byte in that range was read, it will be marked LIVE_READ
and stacksafe() check will perform byte-by-byte verification.
If all bytes in the range were written the slot will be
marked as LIVE_WRITTEN.
This significantly speeds up state equality comparison
and reduces total number of states processed.
before after
bpf_lb-DLB_L3.o 2051 2003
bpf_lb-DLB_L4.o 3287 3164
bpf_lb-DUNKNOWN.o 1080 1080
bpf_lxc-DDROP_ALL.o 24980 12361
bpf_lxc-DUNKNOWN.o 34308 16605
bpf_netdev.o 15404 10962
bpf_overlay.o 7191 6679
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Add extensive set of tests for bpf_call verification logic:
calls: basic sanity
calls: using r0 returned by callee
calls: callee is using r1
calls: callee using args1
calls: callee using wrong args2
calls: callee using two args
calls: callee changing pkt pointers
calls: two calls with args
calls: two calls with bad jump
calls: recursive call. test1
calls: recursive call. test2
calls: unreachable code
calls: invalid call
calls: jumping across function bodies. test1
calls: jumping across function bodies. test2
calls: call without exit
calls: call into middle of ld_imm64
calls: call into middle of other call
calls: two calls with bad fallthrough
calls: two calls with stack read
calls: two calls with stack write
calls: spill into caller stack frame
calls: two calls with stack write and void return
calls: ambiguous return value
calls: two calls that return map_value
calls: two calls that return map_value with bool condition
calls: two calls that return map_value with incorrect bool check
calls: two calls that receive map_value via arg=ptr_stack_of_caller. test1
calls: two calls that receive map_value via arg=ptr_stack_of_caller. test2
calls: two jumps that receive map_value via arg=ptr_stack_of_jumper. test3
calls: two calls that receive map_value_ptr_or_null via arg. test1
calls: two calls that receive map_value_ptr_or_null via arg. test2
calls: pkt_ptr spill into caller stack
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Allow arbitrary function calls from bpf function to another bpf function.
To recognize such set of bpf functions the verifier does:
1. runs control flow analysis to detect function boundaries
2. proceeds with verification of all functions starting from main(root) function
It recognizes that the stack of the caller can be accessed by the callee
(if the caller passed a pointer to its stack to the callee) and the callee
can store map_value and other pointers into the stack of the caller.
3. keeps track of the stack_depth of each function to make sure that total
stack depth is still less than 512 bytes
4. disallows pointers to the callee stack to be stored into the caller stack,
since they will be invalid as soon as the callee returns
5. to reuse all of the existing state_pruning logic each function call
is considered to be independent call from the verifier point of view.
The verifier pretends to inline all function calls it sees are being called.
It stores the callsite instruction index as part of the state to make sure
that two calls to the same callee from two different places in the caller
will be different from state pruning point of view
6. more safety checks are added to liveness analysis
Implementation details:
. struct bpf_verifier_state is now consists of all stack frames that
led to this function
. struct bpf_func_state represent one stack frame. It consists of
registers in the given frame and its stack
. propagate_liveness() logic had a premature optimization where
mark_reg_read() and mark_stack_slot_read() were manually inlined
with loop iterating over parents for each register or stack slot.
Undo this optimization to reuse more complex mark_*_read() logic
. skip_callee() logic is not necessary from safety point of view,
but without it mark_*_read() markings become too conservative,
since after returning from the funciton call a read of r6-r9
will incorrectly propagate the read marks into callee causing
inefficient pruning later
. mark_*_read() logic is now aware of control flow which makes it
more complex. In the future the plan is to rewrite liveness
to be hierarchical. So that liveness can be done within
basic block only and control flow will be responsible for
propagation of liveness information along cfg and between calls.
. tail_calls and ld_abs insns are not allowed in the programs with
bpf-to-bpf calls
. returning stack pointers to the caller or storing them into stack
frame of the caller is not allowed
Testing:
. no difference in cilium processed_insn numbers
. large number of tests follows in next patches
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
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.
New program layout:
r6 = r1 // some code
..
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. In the future the verifier may allow
calls to unresolved functions and will do dynamic linking.
This logic supports statically linked bpf functions only.
Such function boundary detection could have been done as part of
control flow graph building in check_cfg(), but it's cleaner to
separate function boundary detection vs control flow checks within
a subprogram (function) into logically indepedent steps.
Follow up patches may split check_cfg() further, but not check_subprogs().
Only allow bpf-to-bpf calls for root only and for non-hw-offloaded programs.
These restrictions can be relaxed in the future.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
This reverts commits 5c9d2d5c269c, c7da82b894e9, and e7fe7b5cae90.
We'll probably need to revisit this, but basically we should not
complicate the get_user_pages_fast() case, and checking the actual page
table protection key bits will require more care anyway, since the
protection keys depend on the exact state of the VM in question.
Particularly when doing a "remote" page lookup (ie in somebody elses VM,
not your own), you need to be much more careful than this was. Dave
Hansen says:
"So, the underlying bug here is that we now a get_user_pages_remote()
and then go ahead and do the p*_access_permitted() checks against the
current PKRU. This was introduced recently with the addition of the
new p??_access_permitted() calls.
We have checks in the VMA path for the "remote" gups and we avoid
consulting PKRU for them. This got missed in the pkeys selftests
because I did a ptrace read, but not a *write*. I also didn't
explicitly test it against something where a COW needed to be done"
It's also not entirely clear that it makes sense to check the protection
key bits at this level at all. But one possible eventual solution is to
make the get_user_pages_fast() case just abort if it sees protection key
bits set, which makes us fall back to the regular get_user_pages() case,
which then has a vma and can do the check there if we want to.
We'll see.
Somewhat related to this all: what we _do_ want to do some day is to
check the PAGE_USER bit - it should obviously always be set for user
pages, but it would be a good check to have back. Because we have no
generic way to test for it, we lost it as part of moving over from the
architecture-specific x86 GUP implementation to the generic one in
commit e585513b76f7 ("x86/mm/gup: Switch GUP to the generic
get_user_page_fast() implementation").
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|