- 15 May, 2014 15 commits
-
-
Alexei Starovoitov authored
Maps all internal BPF instructions into x86_64 instructions. This patch replaces original BPF x64 JIT with internal BPF x64 JIT. sysctl net.core.bpf_jit_enable is reused as on/off switch. Performance: 1. old BPF JIT and internal BPF JIT generate equivalent x86_64 code. No performance difference is observed for filters that were JIT-able before Example assembler code for BPF filter "tcpdump port 22" original BPF -> old JIT: original BPF -> internal BPF -> new JIT: 0: push %rbp 0: push %rbp 1: mov %rsp,%rbp 1: mov %rsp,%rbp 4: sub $0x60,%rsp 4: sub $0x228,%rsp 8: mov %rbx,-0x8(%rbp) b: mov %rbx,-0x228(%rbp) // prologue 12: mov %r13,-0x220(%rbp) 19: mov %r14,-0x218(%rbp) 20: mov %r15,-0x210(%rbp) 27: xor %eax,%eax // clear A c: xor %ebx,%ebx 29: xor %r13,%r13 // clear X e: mov 0x68(%rdi),%r9d 2c: mov 0x68(%rdi),%r9d 12: sub 0x6c(%rdi),%r9d 30: sub 0x6c(%rdi),%r9d 16: mov 0xd8(%rdi),%r8 34: mov 0xd8(%rdi),%r10 3b: mov %rdi,%rbx 1d: mov $0xc,%esi 3e: mov $0xc,%esi 22: callq 0xffffffffe1021e15 43: callq 0xffffffffe102bd75 27: cmp $0x86dd,%eax 48: cmp $0x86dd,%rax 2c: jne 0x0000000000000069 4f: jne 0x000000000000009a 2e: mov $0x14,%esi 51: mov $0x14,%esi 33: callq 0xffffffffe1021e31 56: callq 0xffffffffe102bd91 38: cmp $0x84,%eax 5b: cmp $0x84,%rax 3d: je 0x0000000000000049 62: je 0x0000000000000074 3f: cmp $0x6,%eax 64: cmp $0x6,%rax 42: je 0x0000000000000049 68: je 0x0000000000000074 44: cmp $0x11,%eax 6a: cmp $0x11,%rax 47: jne 0x00000000000000c6 6e: jne 0x0000000000000117 49: mov $0x36,%esi 74: mov $0x36,%esi 4e: callq 0xffffffffe1021e15 79: callq 0xffffffffe102bd75 53: cmp $0x16,%eax 7e: cmp $0x16,%rax 56: je 0x00000000000000bf 82: je 0x0000000000000110 58: mov $0x38,%esi 88: mov $0x38,%esi 5d: callq 0xffffffffe1021e15 8d: callq 0xffffffffe102bd75 62: cmp $0x16,%eax 92: cmp $0x16,%rax 65: je 0x00000000000000bf 96: je 0x0000000000000110 67: jmp 0x00000000000000c6 98: jmp 0x0000000000000117 69: cmp $0x800,%eax 9a: cmp $0x800,%rax 6e: jne 0x00000000000000c6 a1: jne 0x0000000000000117 70: mov $0x17,%esi a3: mov $0x17,%esi 75: callq 0xffffffffe1021e31 a8: callq 0xffffffffe102bd91 7a: cmp $0x84,%eax ad: cmp $0x84,%rax 7f: je 0x000000000000008b b4: je 0x00000000000000c2 81: cmp $0x6,%eax b6: cmp $0x6,%rax 84: je 0x000000000000008b ba: je 0x00000000000000c2 86: cmp $0x11,%eax bc: cmp $0x11,%rax 89: jne 0x00000000000000c6 c0: jne 0x0000000000000117 8b: mov $0x14,%esi c2: mov $0x14,%esi 90: callq 0xffffffffe1021e15 c7: callq 0xffffffffe102bd75 95: test $0x1fff,%ax cc: test $0x1fff,%rax 99: jne 0x00000000000000c6 d3: jne 0x0000000000000117 d5: mov %rax,%r14 9b: mov $0xe,%esi d8: mov $0xe,%esi a0: callq 0xffffffffe1021e44 dd: callq 0xffffffffe102bd91 // MSH e2: and $0xf,%eax e5: shl $0x2,%eax e8: mov %rax,%r13 eb: mov %r14,%rax ee: mov %r13,%rsi a5: lea 0xe(%rbx),%esi f1: add $0xe,%esi a8: callq 0xffffffffe1021e0d f4: callq 0xffffffffe102bd6d ad: cmp $0x16,%eax f9: cmp $0x16,%rax b0: je 0x00000000000000bf fd: je 0x0000000000000110 ff: mov %r13,%rsi b2: lea 0x10(%rbx),%esi 102: add $0x10,%esi b5: callq 0xffffffffe1021e0d 105: callq 0xffffffffe102bd6d ba: cmp $0x16,%eax 10a: cmp $0x16,%rax bd: jne 0x00000000000000c6 10e: jne 0x0000000000000117 bf: mov $0xffff,%eax 110: mov $0xffff,%eax c4: jmp 0x00000000000000c8 115: jmp 0x000000000000011c c6: xor %eax,%eax 117: mov $0x0,%eax c8: mov -0x8(%rbp),%rbx 11c: mov -0x228(%rbp),%rbx // epilogue cc: leaveq 123: mov -0x220(%rbp),%r13 cd: retq 12a: mov -0x218(%rbp),%r14 131: mov -0x210(%rbp),%r15 138: leaveq 139: retq On fully cached SKBs both JITed functions take 12 nsec to execute. BPF interpreter executes the program in 30 nsec. The difference in generated assembler is due to the following: Old BPF imlements LDX_MSH instruction via sk_load_byte_msh() helper function inside bpf_jit.S. New JIT removes the helper and does it explicitly, so ldx_msh cost is the same for both JITs, but generated code looks longer. New JIT has 4 registers to save, so prologue/epilogue are larger, but the cost is within noise on x64. Old JIT checks whether first insn clears A and if not emits 'xor %eax,%eax'. New JIT clears %rax unconditionally. 2. old BPF JIT doesn't support ANC_NLATTR, ANC_PAY_OFFSET, ANC_RANDOM extensions. New JIT supports all BPF extensions. Performance of such filters improves 2-4 times depending on a filter. The longer the filter the higher performance gain. Synthetic benchmarks with many ancillary loads see 20x speedup which seems to be the maximum gain from JIT Notes: . net.core.bpf_jit_enable=2 + tools/net/bpf_jit_disasm is still functional and can be used to see generated assembler . there are two jit_compile() functions and code flow for classic filters is: sk_attach_filter() - load classic BPF bpf_jit_compile() - try to JIT from classic BPF sk_convert_filter() - convert classic to internal bpf_int_jit_compile() - JIT from internal BPF seccomp and tracing filters will just call bpf_int_jit_compile() Signed-off-by:Alexei Starovoitov <ast@plumgrid.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Alexei Starovoitov authored
Split bpf_jit_compile() into two functions to improve readability of for(pass++) loop. The change follows similar style of JIT compilers for arm, powerpc, s390 The body of new do_jit() was not reformatted to reduce noise in this patch, since the following patch replaces most of it. Tested with BPF testsuite. Signed-off-by:
-
David S. Miller authored
Phoebe Buckheister says: ==================== 802154: some cleanups and fixes This series adds some definitions for 802.15.4 header fields that were missing, changes 6lowpan fragmentation to be aware of security headers and fixes 802.15.4 datagram socket sendmsg(), which was entirely incompliant to date. Also a few minor changes to mac_cb handling, mark a single-use function static, and correctly check for EMSGSIZE conditions during wpan_header_create. Changes since v1: * rename mac_cb_alloc to mac_cb_init * catch all error cases of sendmsg() instead of only !conn && msg_name * redo 6lowpan fragmentation to not clone lower layer headers ==================== Signed-off-by: -
Phoebe Buckheister authored
This function is only used within the same translation unit, so mark it static. Signed-off-by:
Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> Signed-off-by:
-
Phoebe Buckheister authored
802.15.4 datagram sockets do not currently have a compliant sendmsg(). The destination address supplied is always ignored, and in unconnected mode, packets are broadcast instead of dropped with -EDESTADDRREQ. This patch fixes 802.15.4 dgram sockets to be compliant, i.e. !conn && !msg_name => -EDESTADDRREQ !conn && msg_name => send to msg_name conn && !msg_name => send to connected conn && msg_name => -EISCONN Signed-off-by:
-
Phoebe Buckheister authored
Currently, 6lowpan creates one 802.15.4 MAC header for the original packet the device was given by upper layers and reuses this header for all fragments, if fragmentation is required. This also reuses frame sequence numbers, which must not happen. 6lowpan also has issues with fragmentation in the presence of security headers, since those may imply the presence of trailing fields that are not accounted for by the fragmentation code right now. Fix both of these issues by properly allocating fragment skbs with headromm and tailroom as specified by the underlying device, create one header for each skb instead of reusing the original header, let the underlying device do the rest. Signed-off-by:
-
Phoebe Buckheister authored
The current mac_cb handling of ieee802154 is rather awkward and limited. Decompose the single flags field into multiple fields with the meanings of each subfield of the flags field to make future extensions (for example, link-layer security) easier. Also don't set the frame sequence number in upper layers, since that's a thing the MAC is supposed to set on frame transmit - we set it on header creation, but assuming that upper layers do not blindly duplicate our headers, this is fine. Signed-off-by:
-
Phoebe Buckheister authored
The current WPAN header creation code checks for EMSGSIZE conditions, but does not account for the MIC field that link layer security may add at the end of the frame. Now that we can accurately calculate the maximum payload size of packets, use that to check for EMSGSIZE conditions. Signed-off-by:
-
Phoebe Buckheister authored
When dealing with 802.15.4, one often has to know the maximum payload size for a given packet. This depends on many factors, one of which is whether or not a security header is present in the frame. These definitions and functions provide an easy way for any upper layer to calculate the maximum payload size for a packet. The first obvious user for this is 6lowpan, which duplicates this calculation and gets it partially wrong because it ignores security headers. Signed-off-by:
-
Markus Lottmann authored
This unifies the behaviour with other network device drivers and allows for a matching of the PCI device path in UDEV rules. Signed-off-by:
Markus Lottmann <markus.lottmann1986@gmail.com> Signed-off-by:
-
David S. Miller authored
> include/net/ip.h:211:5: warning: "CONFIG_SYSCTL" is not defined [-Wundef] > #if CONFIG_SYSCTL > ^ Reported-by:
Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
David S. Miller authored
George Cherian says: ==================== TI CPSW Cleanup This series does some minimal cleanups. -Conversion of pr_*() to dev_*() -Convert kzalloc to devm_kzalloc. ==================== Signed-off-by: -
George Cherian authored
Convert kzalloc() to devm_kzalloc(). Signed-off-by:
George Cherian <george.cherian@ti.com> Reviewed-by:
Felipe Balbi <balbi@ti.com> Signed-off-by:
-
George Cherian authored
Convert the lone pr_err() to dev_err() call. Signed-off-by:
-
George Cherian authored
Convert all pr_*() calls to dev_*() calls. No functional changes. Signed-off-by:
-
- 14 May, 2014 25 commits
-
-
Darek Marcinkiewicz authored
Sparse was reporting quite a few warnings for the driver. Those get fixed by this patch. Signed-off-by:
Dariusz Marcinkiewicz <reksio@newterm.pl> Signed-off-by:
-
Joe Perches authored
Missing a colon on definition use is a bit odd so change the macro for the 32 bit case to declare an __attribute__((unused)) and __deprecated variable. The __deprecated attribute will cause gcc to emit an error if the variable is actually used. Signed-off-by:
Joe Perches <joe@perches.com> Signed-off-by:
-
Jingoo Han authored
Use devm_ioremap_resource() because devm_request_and_ioremap() is obsoleted by devm_ioremap_resource(). Signed-off-by:
Jingoo Han <jg1.han@samsung.com> Acked-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
David S. Miller authored
Or Gerlitz says: ==================== Mellanox driver update 2014-05-12 This patchset introduce some small bug fixes: Eyal fixed some compilation and syntactic checkers warnings. Ido fixed a coruption in user priority mapping when changing number of channels. Shani fixed some other problems when modifying MAC address. Yuval fixed a problem when changing IRQ affinity during high traffic - IRQ changes got effective only after the first pause in traffic. This patchset was tested and applied over commit 93dccc59: "mdio_bus: fix devm_mdiobus_alloc_size export" Changes from V1: - applied feedback from Dave to use true/false and not 0/1 in patch 1/9 - removed the patch from Noa which adddressed a bug in flow steering table when using a bond device, as the fix might need to be in the bonding driver, this is now dicussed in the netdev thread "bonding directly changes underlying device address" Changes from V0: - Patch 1/9 - net/mlx4_core: Enforce irq affinity changes immediatly - Moved the new members to a hot cache line as Eric suggested ==================== Signed-off-by:
-
Eyal Perry authored
Adopt the "info: why not propagate 'ret' from parse_trans_rule()..." suggestion made by the smatch semantic checker on: drivers/net/ethernet/mellanox/mlx4/mcg.c:867 mlx4_flow_attach() Signed-off-by:
Eyal Perry <eyalpe@mellanox.com> Signed-off-by:
Amir Vadai <amirv@mellanox.com> Signed-off-by:
-
Eyal Perry authored
Using a positive value for error: MLX4_NET_TRANS_RULE_NUM instead of -EPROTONOSUPPORT, to remove compilation warning. Signed-off-by:
-
Shani Michaelli authored
This Patches solves an issue that could raise when modifying the device's MAC. It occurs due to a simultaneous access to priv->mac_hash from two contexts. The buggy scenario described below: Context 1: copy the new mac address to the dev->dev_addr field. Context 2: mlx4_en_do_uc_filter removes prev_mac entry from the mac_hash db since it is not in dev->uc and not equal to dev->dev_addr. Context 1: mlx4_en_do_set_mac() calls mlx4_en_replace_mac() to replace prev_mac with dev_addr but it fails to update the mac_hash db since it no longer contains prev_mac, therefore it returns with an error. The fix is to prevent mlx4_en_do_uc_filter from being executed by both of the context 1 calls described above, This is done by putting them both under the mdev->state_lock lock, it will solve this issue since mlx4_en_do_uc_filter is already protected by the mdev->state_lock. Reviewed-by:Shani Michaeli <shanim@mellanox.com> Signed-off-by:
-
Eyal Perry authored
Fix the "warn: suspicious bitop condition" made by the smatch semantic checker on: drivers/net/ethernet/mellanox/mlx4/main.c:509 mlx4_slave_cap() Signed-off-by:
-
Eyal Perry authored
Fix the "error: we previously assumed 'out_param' could be null" found by smatch semantic checker on: drivers/net/ethernet/mellanox/mlx4/cmd.c:506 mlx4_cmd_poll() drivers/net/ethernet/mellanox/mlx4/cmd.c:578 mlx4_cmd_wait() Signed-off-by:
-
Shani Michaelli authored
This patch fix an issue that happen when changing the MAC address when the port is down, described as follows: 1. Set the port down. 2. Change the MAC address - mlx4_en_set_mac() will change dev->dev_addr. 3. Set the port up - will result in mlx4_en_do_uc_filter that will remove the prev_mac entry from the mac_hash db. 4. Changing the MAC address again will eventually trigger the call to mlx4_en_replace_mac() in order to replace prev_mac with dev_addr but the prev_mac entry is already not exist in the mac_hash db therefore the operation fails. The fix is to set the prev_mac with the new MAC address so in step 3 above, after setting the port up mlx4_en_get_qp() is updating the mac_hash with the entry of dev_addr which is equal to prev_mac. Therefore in step 4, when calling mlx4_en_replace_mac, the entry related to prev_mac exist in mac_hash and the replace operation succeed. Reviewed-by:
-
Ido Shamay authored
When using ethtool set_channels, mlx4_en_setup_tc is always called, even when it was not configured. Fixed code to call mlx4_en_setup_tc() only if needed. Signed-off-by:
Ido Shamay <idos@mellanox.com> Signed-off-by:
-
Yuval Atias authored
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:
-
dingtianhong authored
When the physical MTU changes we should ensure that all existing MACVLAN dev MTU do not exceed the new lowerdev MTU. This patch adds that propagation. Signed-off-by:
Ding Tianhong <dingtianhong@huawei.com> Reviewed-by:
Jiri Pirko <jiri@resnulli.us> Signed-off-by:
-
wangweidong authored
In Documentation/networking/dccp.txt points that request_retries should be greater than 0. So make the extra1 to be &one instead of &zero. Signed-off-by:
Wang Weidong <wangweidong1@huawei.com> Signed-off-by:
Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by:
-
WANG Cong authored
Fengguang reported the following sparse warning: >> net/ipv6/proc.c:198:41: sparse: incorrect type in argument 1 (different address spaces) net/ipv6/proc.c:198:41: expected void [noderef] <asn:3>*mib net/ipv6/proc.c:198:41: got void [noderef] <asn:3>**pcpumib Fixes: commit 698365fa (net: clean up snmp stats code) Reported-by:
Fengguang Wu <fengguang.wu@intel.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by:
Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by:
-
WANG Cong authored
ip_local_port_range is already per netns, so should ip_local_reserved_ports be. And since it is none by default we don't actually need it when we don't enable CONFIG_SYSCTL. By the way, rename inet_is_reserved_local_port() to inet_is_local_reserved_port() Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by:
-
Laurent Pinchart authored
This helps increasing build testing coverage. Signed-off-by:
Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com> Acked-by:
Simon Horman <horms@verge.net.au> Signed-off-by:
-
David S. Miller authored
Jon Maloy says: ==================== tipc: bug fixes and improvements Intensive and extensive testing has revealed some rather infrequent problems related to flow control, buffer handling and link establishment. Commits ##1 to 4 deal with these problems. The remaining four commits are just code improvments, aiming at making the code more comprehensible and maintainable. There are no functional enhancements in this series. v2: Fixed a typo in commit log #2. Otherwise no changes from v1. ==================== Signed-off-by: -
Jon Paul Maloy authored
In order to reduce complexity and save a call level during message reception at port/socket level, we remove the function tipc_port_rcv() and merge its functionality into tipc_sk_rcv(). Signed-off-by:
Jon Maloy <jon.maloy@ericsson.com> Reviewed-by:
Ying Xue <ying.xue@windriver.com> Signed-off-by:
-
Jon Paul Maloy authored
The function tipc_disc_rcv(), which is handling received neighbor discovery messages, is perceived as messy, and it is hard to verify its correctness by code inspection. The fact that the task it is set to resolve is fairly complex does not make the situation better. In this commit we try to take a more systematic approach to the problem. We define a decision machine which takes three state flags as input, and produces three action flags as output. We then walk through all permutations of the state flags, and for each of them we describe verbally what is going on, plus that we set zero or more of the action flags. The action flags indicate what should be done once the decision machine has finished its job, while the last part of the function deals with performing those actions. Signed-off-by:
-
Jon Paul Maloy authored
TIPC currently handles two media specific addresses: Ethernet MAC addresses and InfiniBand addresses. Those are kept in three different formats: 1) A "raw" format as obtained from the device. This format is known only by the media specific adapter code in eth_media.c and ib_media.c. 2) A "generic" internal format, in the form of struct tipc_media_addr, which can be referenced and passed around by the generic media- unaware code. 3) A serialized version of the latter, to be conveyed in neighbor discovery messages. Conversion between the three formats can only be done by the media specific code, so we have function pointers for this purpose in struct tipc_media. Here, the media adapters can install their own conversion functions at startup. We now introduce a new such function, 'raw2addr()', whose purpose is to convert from format 1 to format 2 above. We also try to as far as possible uniform commenting, variable names and usage of these functions, with the purpose of making them more comprehensible. We can now also remove the function tipc_l2_media_addr_set(), whose job is done better by the new function. Finally, we expand the field for serialized addresses (format 3) in discovery messages from 20 to 32 bytes. This is permitted according to the spec, and reduces the risk of problems when we add new media in the future. Signed-off-by:
-
Jon Paul Maloy authored
The function tipc_link_frag_rcv() is in reality a re-entrant generic message reassemby function that has nothing in particular to do with the link, where it is defined now. This becomes obvious when we see the need to call the function from other places in the code. In this commit rename it to tipc_buf_append() and move it to the file msg.c. We also simplify its signature by moving the tail pointer to the control block of the head buffer, hence making the head buffer self-contained. Signed-off-by:
-
Jon Paul Maloy authored
The message reassembly function does not update the 'len' and 'data_len' fields of the head skbuff correctly when fragments are chained to it. This may sometimes lead to obsure errors, such as fragment reordering when we receive fragments which are cloned buffers. This commit fixes this, by ensuring that the two fields are updated correctly. Suggested-by:
Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by:
-
Jon Paul Maloy authored
In the current code, all incoming LINK_PROTOCOL messages, irrespective of type, nudge the "last message received" checkpoint, informing the link state machine that a message was received from the peer since last supervision timeout event. This inhibits the link from starting probing the peer unnecessarily. However, not only STATE messages are recorded as legitimate incoming traffic this way, but even RESET and ACTIVATE messages, which in reality are there to inform the link that the peer endpoint has been reset. At the same time, some RESET messages may be dropped instead of causing a link reset. This happens when the link endpoint thinks it is fully up and working, and the session number of the RESET is lower than or equal to the current link session. In such cases the RESET is perceived as a delayed remnant from an earlier session, or the current one, and dropped. Now, if a TIPC module is removed and then immediately reinserted, e.g. when using a script, RESET messages may arrive at the peer link endpoint before this one has had time to discover the failure. The RESET may be dropped because of the session number, but only after it has been recorded as a legitimate traffic event. Hence, the receiving link will not start probing, and not discover that the peer endpoint is down, at the same time ignoring the periodic RESET messages coming from that endpoint. We have ended up in a stale state where a failed link cannot be re-established. In this commit, we remedy this by nudging the checkpoint only for received STATE messages, not for RESET or ACTIVATE messages. Signed-off-by:
-
Jon Paul Maloy authored
The function net/core/sock.c::__release_sock() runs a tight loop to move buffers from the socket backlog queue to the receive queue. As a security measure, sk_backlog.len of the receiving socket is not set to zero until after the loop is finished, i.e., until the whole backlog queue has been transferred to the receive queue. During this transfer, the data that has already been moved is counted both in the backlog queue and the receive queue, hence giving an incorrect picture of the available queue space for new arriving buffers. This leads to unnecessary rejection of buffers by sk_add_backlog(), which in TIPC leads to unnecessarily broken connections. In this commit, we compensate for this double accounting by adding a counter that keeps track of it. The function socket.c::backlog_rcv() receives buffers one by one from __release_sock(), and adds them to the socket receive queue. If the transfer is successful, it increases a new atomic counter 'tipc_sock::dupl_rcvcnt' with 'truesize' of the transferred buffer. If a new buffer arrives during this transfer and finds the socket busy (owned), we attempt to add it to the backlog. However, when sk_add_backlog() is called, we adjust the 'limit' parameter with the value of the new counter, so that the risk of inadvertent rejection is eliminated. It should be noted that this change does not invalidate the original purpose of zeroing 'sk_backlog.len' after the full transfer. We set an upper limit for dupl_rcvcnt, so that if a 'wild' sender (i.e., one that doesn't respect the send window) keeps pumping in buffers to sk_add_backlog(), he will eventually reach an upper limit, (2 x TIPC_CONN_OVERLOAD_LIMIT). After that, no messages can be added to the backlog, and the connection will be broken. Ordinary, well- behaved senders will never reach this buffer limit at all. Signed-off-by:
-
