summaryrefslogtreecommitdiffstats
path: root/Documentation/networking
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-10-08 21:40:54 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2014-10-08 21:40:54 -0400
commit35a9ad8af0bb0fa3525e6d0d20e32551d226f38e (patch)
tree15b4b33206818886d9cff371fd2163e073b70568 /Documentation/networking
parentd5935b07da53f74726e2a65dd4281d0f2c70e5d4 (diff)
parent64b1f00a0830e1c53874067273a096b228d83d36 (diff)
downloadop-kernel-dev-35a9ad8af0bb0fa3525e6d0d20e32551d226f38e.zip
op-kernel-dev-35a9ad8af0bb0fa3525e6d0d20e32551d226f38e.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Most notable changes in here: 1) By far the biggest accomplishment, thanks to a large range of contributors, is the addition of multi-send for transmit. This is the result of discussions back in Chicago, and the hard work of several individuals. Now, when the ->ndo_start_xmit() method of a driver sees skb->xmit_more as true, it can choose to defer the doorbell telling the driver to start processing the new TX queue entires. skb->xmit_more means that the generic networking is guaranteed to call the driver immediately with another SKB to send. There is logic added to the qdisc layer to dequeue multiple packets at a time, and the handling mis-predicted offloads in software is now done with no locks held. Finally, pktgen is extended to have a "burst" parameter that can be used to test a multi-send implementation. Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4, virtio_net Adding support is almost trivial, so export more drivers to support this optimization soon. I want to thank, in no particular or implied order, Jesper Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann, David Tat, Hannes Frederic Sowa, and Rusty Russell. 2) PTP and timestamping support in bnx2x, from Michal Kalderon. 3) Allow adjusting the rx_copybreak threshold for a driver via ethtool, and add rx_copybreak support to enic driver. From Govindarajulu Varadarajan. 4) Significant enhancements to the generic PHY layer and the bcm7xxx driver in particular (EEE support, auto power down, etc.) from Florian Fainelli. 5) Allow raw buffers to be used for flow dissection, allowing drivers to determine the optimal "linear pull" size for devices that DMA into pools of pages. The objective is to get exactly the necessary amount of headers into the linear SKB area pre-pulled, but no more. The new interface drivers use is eth_get_headlen(). From WANG Cong, with driver conversions (several had their own by-hand duplicated implementations) by Alexander Duyck and Eric Dumazet. 6) Support checksumming more smoothly and efficiently for encapsulations, and add "foo over UDP" facility. From Tom Herbert. 7) Add Broadcom SF2 switch driver to DSA layer, from Florian Fainelli. 8) eBPF now can load programs via a system call and has an extensive testsuite. Alexei Starovoitov and Daniel Borkmann. 9) Major overhaul of the packet scheduler to use RCU in several major areas such as the classifiers and rate estimators. From John Fastabend. 10) Add driver for Intel FM10000 Ethernet Switch, from Alexander Duyck. 11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric Dumazet. 12) Add Datacenter TCP congestion control algorithm support, From Florian Westphal. 13) Reorganize sk_buff so that __copy_skb_header() is significantly faster. From Eric Dumazet" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits) netlabel: directly return netlbl_unlabel_genl_init() net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers net: description of dma_cookie cause make xmldocs warning cxgb4: clean up a type issue cxgb4: potential shift wrapping bug i40e: skb->xmit_more support net: fs_enet: Add NAPI TX net: fs_enet: Remove non NAPI RX r8169:add support for RTL8168EP net_sched: copy exts->type in tcf_exts_change() wimax: convert printk to pr_foo() af_unix: remove 0 assignment on static ipv6: Do not warn for informational ICMP messages, regardless of type. Update Intel Ethernet Driver maintainers list bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING tipc: fix bug in multicast congestion handling net: better IFF_XMIT_DST_RELEASE support net/mlx4_en: remove NETDEV_TX_BUSY 3c59x: fix bad split of cpu_to_le32(pci_map_single()) net: bcmgenet: fix Tx ring priority programming ...
Diffstat (limited to 'Documentation/networking')
-rw-r--r--Documentation/networking/dctcp.txt43
-rw-r--r--Documentation/networking/filter.txt271
-rw-r--r--Documentation/networking/ip-sysctl.txt40
-rw-r--r--Documentation/networking/pktgen.txt3
-rw-r--r--Documentation/networking/timestamping.txt368
-rw-r--r--Documentation/networking/timestamping/Makefile8
-rw-r--r--Documentation/networking/timestamping/txtimestamp.c469
7 files changed, 1110 insertions, 92 deletions
diff --git a/Documentation/networking/dctcp.txt b/Documentation/networking/dctcp.txt
new file mode 100644
index 0000000..0d5dfbc
--- /dev/null
+++ b/Documentation/networking/dctcp.txt
@@ -0,0 +1,43 @@
+DCTCP (DataCenter TCP)
+----------------------
+
+DCTCP is an enhancement to the TCP congestion control algorithm for data
+center networks and leverages Explicit Congestion Notification (ECN) in
+the data center network to provide multi-bit feedback to the end hosts.
+
+To enable it on end hosts:
+
+ sysctl -w net.ipv4.tcp_congestion_control=dctcp
+
+All switches in the data center network running DCTCP must support ECN
+marking and be configured for marking when reaching defined switch buffer
+thresholds. The default ECN marking threshold heuristic for DCTCP on
+switches is 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps,
+but might need further careful tweaking.
+
+For more details, see below documents:
+
+Paper:
+
+The algorithm is further described in detail in the following two
+SIGCOMM/SIGMETRICS papers:
+
+ i) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye,
+ Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan:
+ "Data Center TCP (DCTCP)", Data Center Networks session
+ Proc. ACM SIGCOMM, New Delhi, 2010.
+ http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+ http://www.sigcomm.org/ccr/papers/2010/October/1851275.1851192
+
+ii) Mohammad Alizadeh, Adel Javanmard, and Balaji Prabhakar:
+ "Analysis of DCTCP: Stability, Convergence, and Fairness"
+ Proc. ACM SIGMETRICS, San Jose, 2011.
+ http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
+
+IETF informational draft:
+
+ http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00
+
+DCTCP site:
+
+ http://simula.stanford.edu/~alizade/Site/DCTCP.html
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index f4db097..b1935f9 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -951,7 +951,7 @@ Size modifier is one of ...
Mode modifier is one of:
- BPF_IMM 0x00 /* classic BPF only, reserved in eBPF */
+ BPF_IMM 0x00 /* used for 32-bit mov in classic BPF and 64-bit in eBPF */
BPF_ABS 0x20
BPF_IND 0x40
BPF_MEM 0x60
@@ -995,6 +995,275 @@ BPF_XADD | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg
Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. Note that 1 and
2 byte atomic increments are not supported.
+eBPF has one 16-byte instruction: BPF_LD | BPF_DW | BPF_IMM which consists
+of two consecutive 'struct bpf_insn' 8-byte blocks and interpreted as single
+instruction that loads 64-bit immediate value into a dst_reg.
+Classic BPF has similar instruction: BPF_LD | BPF_W | BPF_IMM which loads
+32-bit immediate value into a register.
+
+eBPF verifier
+-------------
+The safety of the eBPF program is determined in two steps.
+
+First step does DAG check to disallow loops and other CFG validation.
+In particular it will detect programs that have unreachable instructions.
+(though classic BPF checker allows them)
+
+Second step starts from the first insn and descends all possible paths.
+It simulates execution of every insn and observes the state change of
+registers and stack.
+
+At the start of the program the register R1 contains a pointer to context
+and has type PTR_TO_CTX.
+If verifier sees an insn that does R2=R1, then R2 has now type
+PTR_TO_CTX as well and can be used on the right hand side of expression.
+If R1=PTR_TO_CTX and insn is R2=R1+R1, then R2=UNKNOWN_VALUE,
+since addition of two valid pointers makes invalid pointer.
+(In 'secure' mode verifier will reject any type of pointer arithmetic to make
+sure that kernel addresses don't leak to unprivileged users)
+
+If register was never written to, it's not readable:
+ bpf_mov R0 = R2
+ bpf_exit
+will be rejected, since R2 is unreadable at the start of the program.
+
+After kernel function call, R1-R5 are reset to unreadable and
+R0 has a return type of the function.
+
+Since R6-R9 are callee saved, their state is preserved across the call.
+ bpf_mov R6 = 1
+ bpf_call foo
+ bpf_mov R0 = R6
+ bpf_exit
+is a correct program. If there was R1 instead of R6, it would have
+been rejected.
+
+load/store instructions are allowed only with registers of valid types, which
+are PTR_TO_CTX, PTR_TO_MAP, FRAME_PTR. They are bounds and alignment checked.
+For example:
+ bpf_mov R1 = 1
+ bpf_mov R2 = 2
+ bpf_xadd *(u32 *)(R1 + 3) += R2
+ bpf_exit
+will be rejected, since R1 doesn't have a valid pointer type at the time of
+execution of instruction bpf_xadd.
+
+At the start R1 type is PTR_TO_CTX (a pointer to generic 'struct bpf_context')
+A callback is used to customize verifier to restrict eBPF program access to only
+certain fields within ctx structure with specified size and alignment.
+
+For example, the following insn:
+ bpf_ld R0 = *(u32 *)(R6 + 8)
+intends to load a word from address R6 + 8 and store it into R0
+If R6=PTR_TO_CTX, via is_valid_access() callback the verifier will know
+that offset 8 of size 4 bytes can be accessed for reading, otherwise
+the verifier will reject the program.
+If R6=FRAME_PTR, then access should be aligned and be within
+stack bounds, which are [-MAX_BPF_STACK, 0). In this example offset is 8,
+so it will fail verification, since it's out of bounds.
+
+The verifier will allow eBPF program to read data from stack only after
+it wrote into it.
+Classic BPF verifier does similar check with M[0-15] memory slots.
+For example:
+ bpf_ld R0 = *(u32 *)(R10 - 4)
+ bpf_exit
+is invalid program.
+Though R10 is correct read-only register and has type FRAME_PTR
+and R10 - 4 is within stack bounds, there were no stores into that location.
+
+Pointer register spill/fill is tracked as well, since four (R6-R9)
+callee saved registers may not be enough for some programs.
+
+Allowed function calls are customized with bpf_verifier_ops->get_func_proto()
+The eBPF verifier will check that registers match argument constraints.
+After the call register R0 will be set to return type of the function.
+
+Function calls is a main mechanism to extend functionality of eBPF programs.
+Socket filters may let programs to call one set of functions, whereas tracing
+filters may allow completely different set.
+
+If a function made accessible to eBPF program, it needs to be thought through
+from safety point of view. The verifier will guarantee that the function is
+called with valid arguments.
+
+seccomp vs socket filters have different security restrictions for classic BPF.
+Seccomp solves this by two stage verifier: classic BPF verifier is followed
+by seccomp verifier. In case of eBPF one configurable verifier is shared for
+all use cases.
+
+See details of eBPF verifier in kernel/bpf/verifier.c
+
+eBPF maps
+---------
+'maps' is a generic storage of different types for sharing data between kernel
+and userspace.
+
+The maps are accessed from user space via BPF syscall, which has commands:
+- create a map with given type and attributes
+ map_fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
+ using attr->map_type, attr->key_size, attr->value_size, attr->max_entries
+ returns process-local file descriptor or negative error
+
+- lookup key in a given map
+ err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
+ using attr->map_fd, attr->key, attr->value
+ returns zero and stores found elem into value or negative error
+
+- create or update key/value pair in a given map
+ err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
+ using attr->map_fd, attr->key, attr->value
+ returns zero or negative error
+
+- find and delete element by key in a given map
+ err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
+ using attr->map_fd, attr->key
+
+- to delete map: close(fd)
+ Exiting process will delete maps automatically
+
+userspace programs use this syscall to create/access maps that eBPF programs
+are concurrently updating.
+
+maps can have different types: hash, array, bloom filter, radix-tree, etc.
+
+The map is defined by:
+ . type
+ . max number of elements
+ . key size in bytes
+ . value size in bytes
+
+Understanding eBPF verifier messages
+------------------------------------
+
+The following are few examples of invalid eBPF programs and verifier error
+messages as seen in the log:
+
+Program with unreachable instructions:
+static struct bpf_insn prog[] = {
+ BPF_EXIT_INSN(),
+ BPF_EXIT_INSN(),
+};
+Error:
+ unreachable insn 1
+
+Program that reads uninitialized register:
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (bf) r0 = r2
+ R2 !read_ok
+
+Program that doesn't initialize R0 before exiting:
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (bf) r2 = r1
+ 1: (95) exit
+ R0 !read_ok
+
+Program that accesses stack out of bounds:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, 8, 0),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 +8) = 0
+ invalid stack off=8 size=8
+
+Program that doesn't initialize stack before passing its address into function:
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (bf) r2 = r10
+ 1: (07) r2 += -8
+ 2: (b7) r1 = 0x0
+ 3: (85) call 1
+ invalid indirect read from stack off -8+0 size 8
+
+Program that uses invalid map_fd=0 while calling to map_lookup_elem() function:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 -8) = 0
+ 1: (bf) r2 = r10
+ 2: (07) r2 += -8
+ 3: (b7) r1 = 0x0
+ 4: (85) call 1
+ fd 0 is not pointing to valid bpf_map
+
+Program that doesn't check return value of map_lookup_elem() before accessing
+map element:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 -8) = 0
+ 1: (bf) r2 = r10
+ 2: (07) r2 += -8
+ 3: (b7) r1 = 0x0
+ 4: (85) call 1
+ 5: (7a) *(u64 *)(r0 +0) = 0
+ R0 invalid mem access 'map_value_or_null'
+
+Program that correctly checks map_lookup_elem() returned value for NULL, but
+accesses the memory with incorrect alignment:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 -8) = 0
+ 1: (bf) r2 = r10
+ 2: (07) r2 += -8
+ 3: (b7) r1 = 1
+ 4: (85) call 1
+ 5: (15) if r0 == 0x0 goto pc+1
+ R0=map_ptr R10=fp
+ 6: (7a) *(u64 *)(r0 +4) = 0
+ misaligned access off 4 size 8
+
+Program that correctly checks map_lookup_elem() returned value for NULL and
+accesses memory with correct alignment in one side of 'if' branch, but fails
+to do so in the other side of 'if' branch:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ BPF_EXIT_INSN(),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 -8) = 0
+ 1: (bf) r2 = r10
+ 2: (07) r2 += -8
+ 3: (b7) r1 = 1
+ 4: (85) call 1
+ 5: (15) if r0 == 0x0 goto pc+2
+ R0=map_ptr R10=fp
+ 6: (7a) *(u64 *)(r0 +0) = 0
+ 7: (95) exit
+
+ from 5 to 8: R0=imm0 R10=fp
+ 8: (7a) *(u64 *)(r0 +0) = 1
+ R0 invalid mem access 'imm'
+
Testing
-------
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index caedb18..0307e28 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -65,6 +65,12 @@ neigh/default/gc_thresh1 - INTEGER
purge entries if there are fewer than this number.
Default: 128
+neigh/default/gc_thresh2 - INTEGER
+ Threshold when garbage collector becomes more aggressive about
+ purging entries. Entries older than 5 seconds will be cleared
+ when over this number.
+ Default: 512
+
neigh/default/gc_thresh3 - INTEGER
Maximum number of neighbor entries allowed. Increase this
when using large numbers of interfaces and when communicating
@@ -757,8 +763,21 @@ icmp_ratelimit - INTEGER
icmp_ratemask (see below) to specific targets.
0 to disable any limiting,
otherwise the minimal space between responses in milliseconds.
+ Note that another sysctl, icmp_msgs_per_sec limits the number
+ of ICMP packets sent on all targets.
+ Default: 1000
+
+icmp_msgs_per_sec - INTEGER
+ Limit maximal number of ICMP packets sent per second from this host.
+ Only messages whose type matches icmp_ratemask (see below) are
+ controlled by this limit.
Default: 1000
+icmp_msgs_burst - INTEGER
+ icmp_msgs_per_sec controls number of ICMP packets sent per second,
+ while icmp_msgs_burst controls the burst size of these packets.
+ Default: 50
+
icmp_ratemask - INTEGER
Mask made of ICMP types for which rates are being limited.
Significant bits: IHGFEDCBA9876543210
@@ -832,6 +851,11 @@ igmp_max_memberships - INTEGER
conf/all/* is special, changes the settings for all interfaces
+igmp_qrv - INTEGER
+ Controls the IGMP query robustness variable (see RFC2236 8.1).
+ Default: 2 (as specified by RFC2236 8.1)
+ Minimum: 1 (as specified by RFC6636 4.5)
+
log_martians - BOOLEAN
Log packets with impossible addresses to kernel log.
log_martians for the interface will be enabled if at least one of
@@ -935,14 +959,9 @@ accept_source_route - BOOLEAN
FALSE (host)
accept_local - BOOLEAN
- Accept packets with local source addresses. In combination
- with suitable routing, this can be used to direct packets
- between two local interfaces over the wire and have them
- accepted properly.
-
- rp_filter must be set to a non-zero value in order for
- accept_local to have an effect.
-
+ Accept packets with local source addresses. In combination with
+ suitable routing, this can be used to direct packets between two
+ local interfaces over the wire and have them accepted properly.
default FALSE
route_localnet - BOOLEAN
@@ -1140,6 +1159,11 @@ anycast_src_echo_reply - BOOLEAN
FALSE: disabled
Default: FALSE
+mld_qrv - INTEGER
+ Controls the MLD query robustness variable (see RFC3810 9.1).
+ Default: 2 (as specified by RFC3810 9.1)
+ Minimum: 1 (as specified by RFC6636 4.5)
+
IPv6 Fragmentation:
ip6frag_high_thresh - INTEGER
diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt
index 0dffc6e..6915c6b 100644
--- a/Documentation/networking/pktgen.txt
+++ b/Documentation/networking/pktgen.txt
@@ -99,6 +99,9 @@ Examples:
pgset "clone_skb 1" sets the number of copies of the same packet
pgset "clone_skb 0" use single SKB for all transmits
+ pgset "burst 8" uses xmit_more API to queue 8 copies of the same
+ packet and update HW tx queue tail pointer once.
+ "burst 1" is the default
pgset "pkt_size 9014" sets packet size to 9014
pgset "frags 5" packet will consist of 5 fragments
pgset "count 200000" sets number of packets to send, set to zero
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 897f942..412f45c 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -1,102 +1,307 @@
-The existing interfaces for getting network packages time stamped are:
+
+1. Control Interfaces
+
+The interfaces for receiving network packages timestamps are:
* SO_TIMESTAMP
- Generate time stamp for each incoming packet using the (not necessarily
- monotonous!) system time. Result is returned via recv_msg() in a
- control message as timeval (usec resolution).
+ Generates a timestamp for each incoming packet in (not necessarily
+ monotonic) system time. Reports the timestamp via recvmsg() in a
+ control message as struct timeval (usec resolution).
* SO_TIMESTAMPNS
- Same time stamping mechanism as SO_TIMESTAMP, but returns result as
- timespec (nsec resolution).
+ Same timestamping mechanism as SO_TIMESTAMP, but reports the
+ timestamp as struct timespec (nsec resolution).
* IP_MULTICAST_LOOP + SO_TIMESTAMP[NS]
- Only for multicasts: approximate send time stamp by receiving the looped
- packet and using its receive time stamp.
+ Only for multicast:approximate transmit timestamp obtained by
+ reading the looped packet receive timestamp.
-The following interface complements the existing ones: receive time
-stamps can be generated and returned for arbitrary packets and much
-closer to the point where the packet is really sent. Time stamps can
-be generated in software (as before) or in hardware (if the hardware
-has such a feature).
+* SO_TIMESTAMPING
+ Generates timestamps on reception, transmission or both. Supports
+ multiple timestamp sources, including hardware. Supports generating
+ timestamps for stream sockets.
-SO_TIMESTAMPING:
-Instructs the socket layer which kind of information should be collected
-and/or reported. The parameter is an integer with some of the following
-bits set. Setting other bits is an error and doesn't change the current
-state.
+1.1 SO_TIMESTAMP:
-Four of the bits are requests to the stack to try to generate
-timestamps. Any combination of them is valid.
+This socket option enables timestamping of datagrams on the reception
+path. Because the destination socket, if any, is not known early in
+the network stack, the feature has to be enabled for all packets. The
+same is true for all early receive timestamp options.
-SOF_TIMESTAMPING_TX_HARDWARE: try to obtain send time stamps in hardware
-SOF_TIMESTAMPING_TX_SOFTWARE: try to obtain send time stamps in software
-SOF_TIMESTAMPING_RX_HARDWARE: try to obtain receive time stamps in hardware
-SOF_TIMESTAMPING_RX_SOFTWARE: try to obtain receive time stamps in software
+For interface details, see `man 7 socket`.
+
+
+1.2 SO_TIMESTAMPNS:
+
+This option is identical to SO_TIMESTAMP except for the returned data type.
+Its struct timespec allows for higher resolution (ns) timestamps than the
+timeval of SO_TIMESTAMP (ms).
+
+
+1.3 SO_TIMESTAMPING:
+
+Supports multiple types of timestamp requests. As a result, this
+socket option takes a bitmap of flags, not a boolean. In
+
+ err = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, (void *) val, &val);
+
+val is an integer with any of the following bits set. Setting other
+bit returns EINVAL and does not change the current state.
-The other three bits control which timestamps will be reported in a
-generated control message. If none of these bits are set or if none of
-the set bits correspond to data that is available, then the control
-message will not be generated:
-SOF_TIMESTAMPING_SOFTWARE: report systime if available
-SOF_TIMESTAMPING_SYS_HARDWARE: report hwtimetrans if available (deprecated)
-SOF_TIMESTAMPING_RAW_HARDWARE: report hwtimeraw if available
+1.3.1 Timestamp Generation
-It is worth noting that timestamps may be collected for reasons other
-than being requested by a particular socket with
-SOF_TIMESTAMPING_[TR]X_(HARD|SOFT)WARE. For example, most drivers that
-can generate hardware receive timestamps ignore
-SOF_TIMESTAMPING_RX_HARDWARE. It is still a good idea to set that flag
-in case future drivers pay attention.
+Some bits are requests to the stack to try to generate timestamps. Any
+combination of them is valid. Changes to these bits apply to newly
+created packets, not to packets already in the stack. As a result, it
+is possible to selectively request timestamps for a subset of packets
+(e.g., for sampling) by embedding an send() call within two setsockopt
+calls, one to enable timestamp generation and one to disable it.
+Timestamps may also be generated for reasons other than being
+requested by a particular socket, such as when receive timestamping is
+enabled system wide, as explained earlier.
-If timestamps are reported, they will appear in a control message with
-cmsg_level==SOL_SOCKET, cmsg_type==SO_TIMESTAMPING, and a payload like
-this:
+SOF_TIMESTAMPING_RX_HARDWARE:
+ Request rx timestamps generated by the network adapter.
+
+SOF_TIMESTAMPING_RX_SOFTWARE:
+ Request rx timestamps when data enters the kernel. These timestamps
+ are generated just after a device driver hands a packet to the
+ kernel receive stack.
+
+SOF_TIMESTAMPING_TX_HARDWARE:
+ Request tx timestamps generated by the network adapter.
+
+SOF_TIMESTAMPING_TX_SOFTWARE:
+ Request tx timestamps when data leaves the kernel. These timestamps
+ are generated in the device driver as close as possible, but always
+ prior to, passing the packet to the network interface. Hence, they
+ require driver support and may not be available for all devices.
+
+SOF_TIMESTAMPING_TX_SCHED:
+ Request tx timestamps prior to entering the packet scheduler. Kernel
+ transmit latency is, if long, often dominated by queuing delay. The
+ difference between this timestamp and one taken at
+ SOF_TIMESTAMPING_TX_SOFTWARE will expose this latency independent
+ of protocol processing. The latency incurred in protocol
+ processing, if any, can be computed by subtracting a userspace
+ timestamp taken immediately before send() from this timestamp. On
+ machines with virtual devices where a transmitted packet travels
+ through multiple devices and, hence, multiple packet schedulers,
+ a timestamp is generated at each layer. This allows for fine
+ grained measurement of queuing delay.
+
+SOF_TIMESTAMPING_TX_ACK:
+ Request tx timestamps when all data in the send buffer has been
+ acknowledged. This only makes sense for reliable protocols. It is
+ currently only implemented for TCP. For that protocol, it may
+ over-report measurement, because the timestamp is generated when all
+ data up to and including the buffer at send() was acknowledged: the
+ cumulative acknowledgment. The mechanism ignores SACK and FACK.
+
+
+1.3.2 Timestamp Reporting
+
+The other three bits control which timestamps will be reported in a
+generated control message. Changes to the bits take immediate
+effect at the timestamp reporting locations in the stack. Timestamps
+are only reported for packets that also have the relevant timestamp
+generation request set.
+
+SOF_TIMESTAMPING_SOFTWARE:
+ Report any software timestamps when available.
+
+SOF_TIMESTAMPING_SYS_HARDWARE:
+ This option is deprecated and ignored.
+
+SOF_TIMESTAMPING_RAW_HARDWARE:
+ Report hardware timestamps as generated by
+ SOF_TIMESTAMPING_TX_HARDWARE when available.
+
+
+1.3.3 Timestamp Options
+
+The interface supports one option
+
+SOF_TIMESTAMPING_OPT_ID:
+
+ Generate a unique identifier along with each packet. A process can
+ have multiple concurrent timestamping requests outstanding. Packets
+ can be reordered in the transmit path, for instance in the packet
+ scheduler. In that case timestamps will be queued onto the error
+ queue out of order from the original send() calls. This option
+ embeds a counter that is incremented at send() time, to order
+ timestamps within a flow.
+
+ This option is implemented only for transmit timestamps. There, the
+ timestamp is always looped along with a struct sock_extended_err.
+ The option modifies field ee_info to pass an id that is unique
+ among all possibly concurrently outstanding timestamp requests for
+ that socket. In practice, it is a monotonically increasing u32
+ (that wraps).
+
+ In datagram sockets, the counter increments on each send call. In
+ stream sockets, it increments with every byte.
+
+
+1.4 Bytestream Timestamps
+
+The SO_TIMESTAMPING interface supports timestamping of bytes in a
+bytestream. Each request is interpreted as a request for when the
+entire contents of the buffer has passed a timestamping point. That
+is, for streams option SOF_TIMESTAMPING_TX_SOFTWARE will record
+when all bytes have reached the device driver, regardless of how
+many packets the data has been converted into.
+
+In general, bytestreams have no natural delimiters and therefore
+correlating a timestamp with data is non-trivial. A range of bytes
+may be split across segments, any segments may be merged (possibly
+coalescing sections of previously segmented buffers associated with
+independent send() calls). Segments can be reordered and the same
+byte range can coexist in multiple segments for protocols that
+implement retransmissions.
+
+It is essential that all timestamps implement the same semantics,
+regardless of these possible transformations, as otherwise they are
+incomparable. Handling "rare" corner cases differently from the
+simple case (a 1:1 mapping from buffer to skb) is insufficient
+because performance debugging often needs to focus on such outliers.
+
+In practice, timestamps can be correlated with segments of a
+bytestream consistently, if both semantics of the timestamp and the
+timing of measurement are chosen correctly. This challenge is no
+different from deciding on a strategy for IP fragmentation. There, the
+definition is that only the first fragment is timestamped. For
+bytestreams, we chose that a timestamp is generated only when all
+bytes have passed a point. SOF_TIMESTAMPING_TX_ACK as defined is easy to
+implement and reason about. An implementation that has to take into
+account SACK would be more complex due to possible transmission holes
+and out of order arrival.
+
+On the host, TCP can also break the simple 1:1 mapping from buffer to
+skbuff as a result of Nagle, cork, autocork, segmentation and GSO. The
+implementation ensures correctness in all cases by tracking the
+individual last byte passed to send(), even if it is no longer the
+last byte after an skbuff extend or merge operation. It stores the
+relevant sequence number in skb_shinfo(skb)->tskey. Because an skbuff
+has only one such field, only one timestamp can be generated.
+
+In rare cases, a timestamp request can be missed if two requests are
+collapsed onto the same skb. A process can detect this situation by
+enabling SOF_TIMESTAMPING_OPT_ID and comparing the byte offset at
+send time with the value returned for each timestamp. It can prevent
+the situation by always flushing the TCP stack in between requests,
+for instance by enabling TCP_NODELAY and disabling TCP_CORK and
+autocork.
+
+These precautions ensure that the timestamp is generated only when all
+bytes have passed a timestamp point, assuming that the network stack
+itself does not reorder the segments. The stack indeed tries to avoid
+reordering. The one exception is under administrator control: it is
+possible to construct a packet scheduler configuration that delays
+segments from the same stream differently. Such a setup would be
+unusual.
+
+
+2 Data Interfaces
+
+Timestamps are read using the ancillary data feature of recvmsg().
+See `man 3 cmsg` for details of this interface. The socket manual
+page (`man 7 socket`) describes how timestamps generated with
+SO_TIMESTAMP and SO_TIMESTAMPNS records can be retrieved.
+
+
+2.1 SCM_TIMESTAMPING records
+
+These timestamps are returned in a control message with cmsg_level
+SOL_SOCKET, cmsg_type SCM_TIMESTAMPING, and payload of type
struct scm_timestamping {
- struct timespec systime;
- struct timespec hwtimetrans;
- struct timespec hwtimeraw;
+ struct timespec ts[3];
};
-recvmsg() can be used to get this control message for regular incoming
-packets. For send time stamps the outgoing packet is looped back to
-the socket's error queue with the send time stamp(s) attached. It can
-be received with recvmsg(flags=MSG_ERRQUEUE). The call returns the
-original outgoing packet data including all headers preprended down to
-and including the link layer, the scm_timestamping control message and
-a sock_extended_err control message with ee_errno==ENOMSG and
-ee_origin==SO_EE_ORIGIN_TIMESTAMPING. A socket with such a pending
-bounced packet is ready for reading as far as select() is concerned.
-If the outgoing packet has to be fragmented, then only the first
-fragment is time stamped and returned to the sending socket.
-
-All three values correspond to the same event in time, but were
-generated in different ways. Each of these values may be empty (= all
-zero), in which case no such value was available. If the application
-is not interested in some of these values, they can be left blank to
-avoid the potential overhead of calculating them.
-
-systime is the value of the system time at that moment. This
-corresponds to the value also returned via SO_TIMESTAMP[NS]. If the
-time stamp was generated by hardware, then this field is
-empty. Otherwise it is filled in if SOF_TIMESTAMPING_SOFTWARE is
-set.
-
-hwtimeraw is the original hardware time stamp. Filled in if
-SOF_TIMESTAMPING_RAW_HARDWARE is set. No assumptions about its
-relation to system time should be made.
-
-hwtimetrans is always zero. This field is deprecated. It used to hold
-hw timestamps converted to system time. Instead, expose the hardware
-clock device on the NIC directly as a HW PTP clock source, to allow
-time conversion in userspace and optionally synchronize system time
-with a userspace PTP stack such as linuxptp. For the PTP clock API,
-see Documentation/ptp/ptp.txt.
-
-
-SIOCSHWTSTAMP, SIOCGHWTSTAMP:
+The structure can return up to three timestamps. This is a legacy
+feature. Only one field is non-zero at any time. Most timestamps
+are passed in ts[0]. Hardware timestamps are passed in ts[2].
+
+ts[1] used to hold hardware timestamps converted to system time.
+Instead, expose the hardware clock device on the NIC directly as
+a HW PTP clock source, to allow time conversion in userspace and
+optionally synchronize system time with a userspace PTP stack such
+as linuxptp. For the PTP clock API, see Documentation/ptp/ptp.txt.
+
+2.1.1 Transmit timestamps with MSG_ERRQUEUE
+
+For transmit timestamps the outgoing packet is looped back to the
+socket's error queue with the send timestamp(s) attached. A process
+receives the timestamps by calling recvmsg() with flag MSG_ERRQUEUE
+set and with a msg_control buffer sufficiently large to receive the
+relevant metadata structures. The recvmsg call returns the original
+outgoing data packet with two ancillary messages attached.
+
+A message of cm_level SOL_IP(V6) and cm_type IP(V6)_RECVERR
+embeds a struct sock_extended_err. This defines the error type. For
+timestamps, the ee_errno field is ENOMSG. The other ancillary message
+will have cm_level SOL_SOCKET and cm_type SCM_TIMESTAMPING. This
+embeds the struct scm_timestamping.
+
+
+2.1.1.2 Timestamp types
+
+The semantics of the three struct timespec are defined by field
+ee_info in the extended error structure. It contains a value of
+type SCM_TSTAMP_* to define the actual timestamp passed in
+scm_timestamping.
+
+The SCM_TSTAMP_* types are 1:1 matches to the SOF_TIMESTAMPING_*
+control fields discussed previously, with one exception. For legacy
+reasons, SCM_TSTAMP_SND is equal to zero and can be set for both
+SOF_TIMESTAMPING_TX_HARDWARE and SOF_TIMESTAMPING_TX_SOFTWARE. It
+is the first if ts[2] is non-zero, the second otherwise, in which
+case the timestamp is stored in ts[0].
+
+
+2.1.1.3 Fragmentation
+
+Fragmentation of outgoing datagrams is rare, but is possible, e.g., by
+explicitly disabling PMTU discovery. If an outgoing packet is fragmented,
+then only the first fragment is timestamped and returned to the sending
+socket.
+
+
+2.1.1.4 Packet Payload
+
+The calling application is often not interested in receiving the whole
+packet payload that it passed to the stack originally: the socket
+error queue mechanism is just a method to piggyback the timestamp on.
+In this case, the application can choose to read datagrams with a
+smaller buffer, possibly even of length 0. The payload is truncated
+accordingly. Until the process calls recvmsg() on the error queue,
+however, the full packet is queued, taking up budget from SO_RCVBUF.
+
+
+2.1.1.5 Blocking Read
+
+Reading from the error queue is always a non-blocking operation. To
+block waiting on a timestamp, use poll or select. poll() will return
+POLLERR in pollfd.revents if any data is ready on the error queue.
+There is no need to pass this flag in pollfd.events. This flag is
+ignored on request. See also `man 2 poll`.
+
+
+2.1.2 Receive timestamps
+
+On reception, there is no reason to read from the socket error queue.
+The SCM_TIMESTAMPING ancillary data is sent along with the packet data
+on a normal recvmsg(). Since this is not a socket error, it is not
+accompanied by a message SOL_IP(V6)/IP(V6)_RECVERROR. In this case,
+the meaning of the three fields in struct scm_timestamping is
+implicitly defined. ts[0] holds a software timestamp if set, ts[1]
+is again deprecated and ts[2] holds a hardware timestamp if set.
+
+
+3. Hardware Timestamping configuration: SIOCSHWTSTAMP and SIOCGHWTSTAMP
Hardware time stamping must also be initialized for each device driver
that is expected to do hardware time stamping. The parameter is defined in
@@ -167,8 +372,7 @@ enum {
*/
};
-
-DEVICE IMPLEMENTATION
+3.1 Hardware Timestamping Implementation: Device Drivers
A driver which supports hardware time stamping must support the
SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with
diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile
index 52ac67d..8c20dfa 100644
--- a/Documentation/networking/timestamping/Makefile
+++ b/Documentation/networking/timestamping/Makefile
@@ -1,8 +1,14 @@
+# To compile, from the source root
+#
+# make headers_install
+# make M=documentation
+
# List of programs to build
-hostprogs-y := hwtstamp_config timestamping
+hostprogs-y := hwtstamp_config timestamping txtimestamp
# Tell kbuild to always build the programs
always := $(hostprogs-y)
HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include
+HOSTCFLAGS_txtimestamp.o += -I$(objtree)/usr/include
HOSTCFLAGS_hwtstamp_config.o += -I$(objtree)/usr/include
diff --git a/Documentation/networking/timestamping/txtimestamp.c b/Documentation/networking/timestamping/txtimestamp.c
new file mode 100644
index 0000000..b32fc2a
--- /dev/null
+++ b/Documentation/networking/timestamping/txtimestamp.c
@@ -0,0 +1,469 @@
+/*
+ * Copyright 2014 Google Inc.
+ * Author: willemb@google.com (Willem de Bruijn)
+ *
+ * Test software tx timestamping, including
+ *
+ * - SCHED, SND and ACK timestamps
+ * - RAW, UDP and TCP
+ * - IPv4 and IPv6
+ * - various packet sizes (to test GSO and TSO)
+ *
+ * Consult the command line arguments for help on running
+ * the various testcases.
+ *
+ * This test requires a dummy TCP server.
+ * A simple `nc6 [-u] -l -p $DESTPORT` will do
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <arpa/inet.h>
+#include <asm/types.h>
+#include <error.h>
+#include <errno.h>
+#include <linux/errqueue.h>
+#include <linux/if_ether.h>
+#include <linux/net_tstamp.h>
+#include <netdb.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/udp.h>
+#include <netinet/tcp.h>
+#include <netpacket/packet.h>
+#include <poll.h>
+#include <stdarg.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/select.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+
+/* command line parameters */
+static int cfg_proto = SOCK_STREAM;
+static int cfg_ipproto = IPPROTO_TCP;
+static int cfg_num_pkts = 4;
+static int do_ipv4 = 1;
+static int do_ipv6 = 1;
+static int cfg_payload_len = 10;
+static uint16_t dest_port = 9000;
+
+static struct sockaddr_in daddr;
+static struct sockaddr_in6 daddr6;
+static struct timespec ts_prev;
+
+static void __print_timestamp(const char *name, struct timespec *cur,
+ uint32_t key, int payload_len)
+{
+ if (!(cur->tv_sec | cur->tv_nsec))
+ return;
+
+ fprintf(stderr, " %s: %lu s %lu us (seq=%u, len=%u)",
+ name, cur->tv_sec, cur->tv_nsec / 1000,
+ key, payload_len);
+
+ if ((ts_prev.tv_sec | ts_prev.tv_nsec)) {
+ int64_t cur_ms, prev_ms;
+
+ cur_ms = (long) cur->tv_sec * 1000 * 1000;
+ cur_ms += cur->tv_nsec / 1000;
+
+ prev_ms = (long) ts_prev.tv_sec * 1000 * 1000;
+ prev_ms += ts_prev.tv_nsec / 1000;
+
+ fprintf(stderr, " (%+ld us)", cur_ms - prev_ms);
+ }
+
+ ts_prev = *cur;
+ fprintf(stderr, "\n");
+}
+
+static void print_timestamp_usr(void)
+{
+ struct timespec ts;
+ struct timeval tv; /* avoid dependency on -lrt */
+
+ gettimeofday(&tv, NULL);
+ ts.tv_sec = tv.tv_sec;
+ ts.tv_nsec = tv.tv_usec * 1000;
+
+ __print_timestamp(" USR", &ts, 0, 0);
+}
+
+static void print_timestamp(struct scm_timestamping *tss, int tstype,
+ int tskey, int payload_len)
+{
+ const char *tsname;
+
+ switch (tstype) {
+ case SCM_TSTAMP_SCHED:
+ tsname = " ENQ";
+ break;
+ case SCM_TSTAMP_SND:
+ tsname = " SND";
+ break;
+ case SCM_TSTAMP_ACK:
+ tsname = " ACK";
+ break;
+ default:
+ error(1, 0, "unknown timestamp type: %u",
+ tstype);
+ }
+ __print_timestamp(tsname, &tss->ts[0], tskey, payload_len);
+}
+
+static void __poll(int fd)
+{
+ struct pollfd pollfd;
+ int ret;
+
+ memset(&pollfd, 0, sizeof(pollfd));
+ pollfd.fd = fd;
+ ret = poll(&pollfd, 1, 100);
+ if (ret != 1)
+ error(1, errno, "poll");
+}
+
+static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len)
+{
+ struct sock_extended_err *serr = NULL;
+ struct scm_timestamping *tss = NULL;
+ struct cmsghdr *cm;
+
+ for (cm = CMSG_FIRSTHDR(msg);
+ cm && cm->cmsg_len;
+ cm = CMSG_NXTHDR(msg, cm)) {
+ if (cm->cmsg_level == SOL_SOCKET &&
+ cm->cmsg_type == SCM_TIMESTAMPING) {
+ tss = (void *) CMSG_DATA(cm);
+ } else if ((cm->cmsg_level == SOL_IP &&
+ cm->cmsg_type == IP_RECVERR) ||
+ (cm->cmsg_level == SOL_IPV6 &&
+ cm->cmsg_type == IPV6_RECVERR)) {
+
+ serr = (void *) CMSG_DATA(cm);
+ if (serr->ee_errno != ENOMSG ||
+ serr->ee_origin != SO_EE_ORIGIN_TIMESTAMPING) {
+ fprintf(stderr, "unknown ip error %d %d\n",
+ serr->ee_errno,
+ serr->ee_origin);
+ serr = NULL;
+ }
+ } else
+ fprintf(stderr, "unknown cmsg %d,%d\n",
+ cm->cmsg_level, cm->cmsg_type);
+ }
+
+ if (serr && tss)
+ print_timestamp(tss, serr->ee_info, serr->ee_data, payload_len);
+}
+
+static int recv_errmsg(int fd)
+{
+ static char ctrl[1024 /* overprovision*/];
+ static struct msghdr msg;
+ struct iovec entry;
+ static char *data;
+ int ret = 0;
+
+ data = malloc(cfg_payload_len);
+ if (!data)
+ error(1, 0, "malloc");
+
+ memset(&msg, 0, sizeof(msg));
+ memset(&entry, 0, sizeof(entry));
+ memset(ctrl, 0, sizeof(ctrl));
+
+ entry.iov_base = data;
+ entry.iov_len = cfg_payload_len;
+ msg.msg_iov = &entry;
+ msg.msg_iovlen = 1;
+ msg.msg_name = NULL;
+ msg.msg_namelen = 0;
+ msg.msg_control = ctrl;
+ msg.msg_controllen = sizeof(ctrl);
+
+ ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+ if (ret == -1 && errno != EAGAIN)
+ error(1, errno, "recvmsg");
+
+ __recv_errmsg_cmsg(&msg, ret);
+
+ free(data);
+ return ret == -1;
+}
+
+static void do_test(int family, unsigned int opt)
+{
+ char *buf;
+ int fd, i, val, total_len;
+
+ if (family == IPPROTO_IPV6 && cfg_proto != SOCK_STREAM) {
+ /* due to lack of checksum generation code */
+ fprintf(stderr, "test: skipping datagram over IPv6\n");
+ return;
+ }
+
+ total_len = cfg_payload_len;
+ if (cfg_proto == SOCK_RAW) {
+ total_len += sizeof(struct udphdr);
+ if (cfg_ipproto == IPPROTO_RAW)
+ total_len += sizeof(struct iphdr);
+ }
+
+ buf = malloc(total_len);
+ if (!buf)
+ error(1, 0, "malloc");
+
+ fd = socket(family, cfg_proto, cfg_ipproto);
+ if (fd < 0)
+ error(1, errno, "socket");
+
+ if (cfg_proto == SOCK_STREAM) {
+ val = 1;
+ if (setsockopt(fd, IPPROTO_TCP, TCP_NODELAY,
+ (char*) &val, sizeof(val)))
+ error(1, 0, "setsockopt no nagle");
+
+ if (family == PF_INET) {
+ if (connect(fd, (void *) &daddr, sizeof(daddr)))
+ error(1, errno, "connect ipv4");
+ } else {
+ if (connect(fd, (void *) &daddr6, sizeof(daddr6)))
+ error(1, errno, "connect ipv6");
+ }
+ }
+
+ opt |= SOF_TIMESTAMPING_SOFTWARE |
+ SOF_TIMESTAMPING_OPT_ID;
+ if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING,
+ (char *) &opt, sizeof(opt)))
+ error(1, 0, "setsockopt timestamping");
+
+ for (i = 0; i < cfg_num_pkts; i++) {
+ memset(&ts_prev, 0, sizeof(ts_prev));
+ memset(buf, 'a' + i, total_len);
+ buf[total_len - 2] = '\n';
+ buf[total_len - 1] = '\0';
+
+ if (cfg_proto == SOCK_RAW) {
+ struct udphdr *udph;
+ int off = 0;
+
+ if (cfg_ipproto == IPPROTO_RAW) {
+ struct iphdr *iph = (void *) buf;
+
+ memset(iph, 0, sizeof(*iph));
+ iph->ihl = 5;
+ iph->version = 4;
+ iph->ttl = 2;
+ iph->daddr = daddr.sin_addr.s_addr;
+ iph->protocol = IPPROTO_UDP;
+ /* kernel writes saddr, csum, len */
+
+ off = sizeof(*iph);
+ }
+
+ udph = (void *) buf + off;
+ udph->source = ntohs(9000); /* random spoof */
+ udph->dest = ntohs(dest_port);
+ udph->len = ntohs(sizeof(*udph) + cfg_payload_len);
+ udph->check = 0; /* not allowed for IPv6 */
+ }
+
+ print_timestamp_usr();
+ if (cfg_proto != SOCK_STREAM) {
+ if (family == PF_INET)
+ val = sendto(fd, buf, total_len, 0, (void *) &daddr, sizeof(daddr));
+ else
+ val = sendto(fd, buf, total_len, 0, (void *) &daddr6, sizeof(daddr6));
+ } else {
+ val = send(fd, buf, cfg_payload_len, 0);
+ }
+ if (val != total_len)
+ error(1, errno, "send");
+
+ /* wait for all errors to be queued, else ACKs arrive OOO */
+ usleep(50 * 1000);
+
+ __poll(fd);
+
+ while (!recv_errmsg(fd)) {}
+ }
+
+ if (close(fd))
+ error(1, errno, "close");
+
+ free(buf);
+ usleep(400 * 1000);
+}
+
+static void __attribute__((noreturn)) usage(const char *filepath)
+{
+ fprintf(stderr, "\nUsage: %s [options] hostname\n"
+ "\nwhere options are:\n"
+ " -4: only IPv4\n"
+ " -6: only IPv6\n"
+ " -h: show this message\n"
+ " -l N: send N bytes at a time\n"
+ " -r: use raw\n"
+ " -R: use raw (IP_HDRINCL)\n"
+ " -p N: connect to port N\n"
+ " -u: use udp\n",
+ filepath);
+ exit(1);
+}
+
+static void parse_opt(int argc, char **argv)
+{
+ int proto_count = 0;
+ char c;
+
+ while ((c = getopt(argc, argv, "46hl:p:rRu")) != -1) {
+ switch (c) {
+ case '4':
+ do_ipv6 = 0;
+ break;
+ case '6':
+ do_ipv4 = 0;
+ break;
+ case 'r':
+ proto_count++;
+ cfg_proto = SOCK_RAW;
+ cfg_ipproto = IPPROTO_UDP;
+ break;
+ case 'R':
+ proto_count++;
+ cfg_proto = SOCK_RAW;
+ cfg_ipproto = IPPROTO_RAW;
+ break;
+ case 'u':
+ proto_count++;
+ cfg_proto = SOCK_DGRAM;
+ cfg_ipproto = IPPROTO_UDP;
+ break;
+ case 'l':
+ cfg_payload_len = strtoul(optarg, NULL, 10);
+ break;
+ case 'p':
+ dest_port = strtoul(optarg, NULL, 10);
+ break;
+ case 'h':
+ default:
+ usage(argv[0]);
+ }
+ }
+
+ if (!cfg_payload_len)
+ error(1, 0, "payload may not be nonzero");
+ if (cfg_proto != SOCK_STREAM && cfg_payload_len > 1472)
+ error(1, 0, "udp packet might exceed expected MTU");
+ if (!do_ipv4 && !do_ipv6)
+ error(1, 0, "pass -4 or -6, not both");
+ if (proto_count > 1)
+ error(1, 0, "pass -r, -R or -u, not multiple");
+
+ if (optind != argc - 1)
+ error(1, 0, "missing required hostname argument");
+}
+
+static void resolve_hostname(const char *hostname)
+{
+ struct addrinfo *addrs, *cur;
+ int have_ipv4 = 0, have_ipv6 = 0;
+
+ if (getaddrinfo(hostname, NULL, NULL, &addrs))
+ error(1, errno, "getaddrinfo");
+
+ cur = addrs;
+ while (cur && !have_ipv4 && !have_ipv6) {
+ if (!have_ipv4 && cur->ai_family == AF_INET) {
+ memcpy(&daddr, cur->ai_addr, sizeof(daddr));
+ daddr.sin_port = htons(dest_port);
+ have_ipv4 = 1;
+ }
+ else if (!have_ipv6 && cur->ai_family == AF_INET6) {
+ memcpy(&daddr6, cur->ai_addr, sizeof(daddr6));
+ daddr6.sin6_port = htons(dest_port);
+ have_ipv6 = 1;
+ }
+ cur = cur->ai_next;
+ }
+ if (addrs)
+ freeaddrinfo(addrs);
+
+ do_ipv4 &= have_ipv4;
+ do_ipv6 &= have_ipv6;
+}
+
+static void do_main(int family)
+{
+ fprintf(stderr, "family: %s\n",
+ family == PF_INET ? "INET" : "INET6");
+
+ fprintf(stderr, "test SND\n");
+ do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE);
+
+ fprintf(stderr, "test ENQ\n");
+ do_test(family, SOF_TIMESTAMPING_TX_SCHED);
+
+ fprintf(stderr, "test ENQ + SND\n");
+ do_test(family, SOF_TIMESTAMPING_TX_SCHED |
+ SOF_TIMESTAMPING_TX_SOFTWARE);
+
+ if (cfg_proto == SOCK_STREAM) {
+ fprintf(stderr, "\ntest ACK\n");
+ do_test(family, SOF_TIMESTAMPING_TX_ACK);
+
+ fprintf(stderr, "\ntest SND + ACK\n");
+ do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_TX_ACK);
+
+ fprintf(stderr, "\ntest ENQ + SND + ACK\n");
+ do_test(family, SOF_TIMESTAMPING_TX_SCHED |
+ SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_TX_ACK);
+ }
+}
+
+const char *sock_names[] = { NULL, "TCP", "UDP", "RAW" };
+
+int main(int argc, char **argv)
+{
+ if (argc == 1)
+ usage(argv[0]);
+
+ parse_opt(argc, argv);
+ resolve_hostname(argv[argc - 1]);
+
+ fprintf(stderr, "protocol: %s\n", sock_names[cfg_proto]);
+ fprintf(stderr, "payload: %u\n", cfg_payload_len);
+ fprintf(stderr, "server port: %u\n", dest_port);
+ fprintf(stderr, "\n");
+
+ if (do_ipv4)
+ do_main(PF_INET);
+ if (do_ipv6)
+ do_main(PF_INET6);
+
+ return 0;
+}
OpenPOWER on IntegriCloud