- 30 Sep, 2016 32 commits
-
-
David Howells authored
The call timer's concept of a call timeout (of which there are three) that is inactive is that it is the timeout has the same expiration time as the call expiration timeout (the expiration timer is never inactive). However, I'm not resetting the timeouts when they expire, leading to repeated processing of expired timeouts when other timeout events occur. Fix this by: (1) Move the timer expiry detection into rxrpc_set_timer() inside the locked section. This means that if a timeout is set that will expire immediately, we deal with it immediately. (2) If a timeout is at or before now then it has expired. When an expiry is detected, an event is raised, the timeout is automatically inactivated and the event processor is queued. (3) If a timeout is at or after the expiry timeout then it is inactive. Inactive timeouts do not contribute to the timer setting. (4) The call timer callback can now just call rxrpc_set_timer() to handle things. (5) The call processor work function now checks the event flags rather than checking the timeouts directly. Signed-off-by:David Howells <dhowells@redhat.com>
-
David Howells authored
Keep that call timeouts as ktimes rather than jiffies so that they can be expressed as functions of RTT. Signed-off-by: -
David Howells authored
Remove error from struct rxrpc_skb_priv as it is no longer used. Signed-off-by: -
David Howells authored
The offset field in struct rxrpc_skb_priv is unnecessary as the value can always be calculated. Signed-off-by: -
David Howells authored
When we receive an ACK from the peer that tells us what the peer's receive window (rwind) is, we should reduce ssthresh to rwind if rwind is smaller than ssthresh. Signed-off-by: -
David Howells authored
Switch to Congestion Avoidance mode at cwnd == ssthresh rather than relying on cwnd getting incremented beyond ssthresh and the window size, the mode being shifted and then cwnd being corrected. We need to make sure we switch into CA mode so that we stop marking every packet for ACK. Signed-off-by: -
David Howells authored
Actually display in the tx_data trace the retransmission note added in a previous patch. Signed-off-by: -
Calvin Owens authored
This implements ndo_poll_controller in net_device_ops callbacks for mlx5, which is necessary to use netconsole with this driver. Acked-By:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
Calvin Owens <calvinowens@fb.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jakub Kicinski authored
Set upper 32 bits of destination register to zeros after load from the context structure. Signed-off-by:
Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by:
-
David Decotigny authored
This also can address following UBSAN warnings: [ 36.640343] ================================================================================ [ 36.648772] UBSAN: Undefined behaviour in drivers/net/ethernet/mellanox/mlx4/fw.c:857:26 [ 36.656853] shift exponent 64 is too large for 32-bit type 'int' [ 36.663348] ================================================================================ [ 36.671783] ================================================================================ [ 36.680213] UBSAN: Undefined behaviour in drivers/net/ethernet/mellanox/mlx4/fw.c:861:27 [ 36.688297] shift exponent 35 is too large for 32-bit type 'int' [ 36.694702] ================================================================================ Tested: reboot with UBSAN, no warning. Signed-off-by:
David Decotigny <decot@googlers.com> Acked-by:
Eric Dumazet <edumazet@google.com> Reviewed-by:
Tariq Toukan <tariqt@mellanox.com> Signed-off-by:
-
Maciej Żenczykowski authored
This implements: https://tools.ietf.org/html/rfc7559 Backoff is performed according to RFC3315 section 14: https://tools.ietf.org/html/rfc3315#section-14 We allow setting /proc/sys/net/ipv6/conf/*/router_solicitations to a negative value meaning an unlimited number of retransmits, and we make this the new default (inline with the RFC). We also add a new setting: /proc/sys/net/ipv6/conf/*/router_solicitation_max_interval defaulting to 1 hour (per RFC recommendation). Signed-off-by:
Maciej Żenczykowski <maze@google.com> Acked-by:
Erik Kline <ek@google.com> Signed-off-by:
-
David S. Miller authored
Jia He says: ==================== Reduce cache miss for snmp_fold_field In a PowerPc server with large cpu number(160), besides commit a3a77372 ("net: Optimize snmp stat aggregation by walking all the percpu data at once"), I watched several other snmp_fold_field callsites which would cause high cache miss rate. test source code: ================ My simple test case, which read from the procfs items endlessly: /***********************************************************/ int main(int argc, char **argv) { int i; int fd = -1 ; int rdsize = 0; char buf[LINELEN+1]; buf[LINELEN] = 0; memset(buf,0,LINELEN); if(1 >= argc) { printf("file name empty\n"); return -1; } fd = open(argv[1], O_RDWR, 0644); if(0 > fd){ printf("open error\n"); return -2; } for(i=0;i<0xffffffff;i++) { while(0 < (rdsize = read(fd,buf,LINELEN))){ //nothing here } lseek(fd, 0, SEEK_SET); } close(fd); return 0; } /**********************************************************/ compile and run: ================ gcc test.c -o test perf stat -d -e cache-misses ./test /proc/net/snmp perf stat -d -e cache-misses ./test /proc/net/snmp6 perf stat -d -e cache-misses ./test /proc/net/sctp/snmp perf stat -d -e cache-misses ./test /proc/net/xfrm_stat before the patch set: ==================== Performance counter stats for 'system wide': 355911097 cache-misses [40.08%] 2356829300 L1-dcache-loads [60.04%] 355642645 L1-dcache-load-misses # 15.09% of all L1-dcache hits [60.02%] 346544541 LLC-loads [59.97%] 389763 LLC-load-misses # 0.11% of all LL-cache hits [40.02%] 6.245162638 seconds time elapsed After the patch set: =================== Performance counter stats for 'system wide': 194992476 cache-misses [40.03%] 6718051877 L1-dcache-loads [60.07%] 194871921 L1-dcache-load-misses # 2.90% of all L1-dcache hits [60.11%] 187632232 LLC-loads [60.04%] 464466 LLC-load-misses # 0.25% of all LL-cache hits [39.89%] 6.868422769 seconds time elapsed The cache-miss rate can be reduced from 15% to 2.9% changelog ========= v6: - correct v5 v5: - order local variables from longest to shortest line v4: - move memset into one block of if statement in snmp6_seq_show_item - remove the changes in netstat_seq_show considerred the stack usage is too large v3: - introduce generic interface (suggested by Marcelo Ricardo Leitner) - use max_t instead of self defined macro (suggested by David Miller) v2: - fix bug in udplite statistics. - snmp_seq_show is split into 2 parts ==================== Signed-off-by:
-
Jia He authored
This is to suppress the checkpatch.pl warning "Comparison to NULL could be written". No functional changes here. Signed-off-by:
Jia He <hejianet@gmail.com> Signed-off-by:
-
Jia He authored
The parameter items(is always ICMP6_MIB_MAX) is useless for __snmp6_fill_statsdev Signed-off-by:
-
Jia He authored
This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: -
Jia He authored
This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: -
Jia He authored
This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Signed-off-by: -
Jia He authored
This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to aggregate the data by going through all the items of each cpu sequentially. Then snmp_seq_show is split into 2 parts to avoid build warning "the frame size" larger than 1024. Signed-off-by: -
Jia He authored
This is to introduce the generic interfaces for snmp_get_cpu_field{,64}. It exchanges the two for-loops for collecting the percpu statistics data. This can aggregate the data by going through all the items of each cpu sequentially. Signed-off-by:Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by:
-
David S. Miller authored
Merge tag 'rxrpc-rewrite-20160929' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs David Howells says: ==================== rxrpc: Fixes and adjustments This set of patches contains some fixes and adjustments: (1) Connections for exclusive calls are being reused because the check to work out whether to set RXRPC_CONN_DONT_REUSE is checking where the parameters will be copied to (but haven't yet). (2) Make Tx loss-injection go through the normal return, so the state gets set correctly for what the code thinks it has done. Note lost Tx packets in the tx_data trace rather than the skb tracepoint. (3) Activate channels according to the current state from within the channel_lock to avoid someone changing it on us. (4) Reduce the local endpoint's services list to a single pointer as we don't allow service AF_RXRPC sockets to share UDP ports with other AF_RXRPC sockets, so there can't be more than one element in the list. (5) Request more ACKs in slow-start mode to help monitor the state driving the window configuration. (6) Display the serial number of the packet being ACK'd rather than the ACK packet's own serial number in the congestion trace as this can be related to other entries in the trace. ==================== Signed-off-by:
-
David S. Miller authored
Merge tag 'wireless-drivers-next-for-davem-2016-09-29' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next Kalle Valo says: wireless-drivers-next patches for 4.9 Major changes: iwlwifi * work for new hardware support continues * dynamic queue allocation stabilization * improvements in the MSIx code * multiqueue support work continues * new firmware version support (API 26) * add 8275 series support * add 9560 series support * add support for MU-MIMO sniffer * add support for RRM by scan * add support for "reverse" rx packet injection faking hw descriptors * migrate to devm memory allocation handling * Remove support for older firmwares (API older than -17 and -22) wl12xx * support booting the same rootfs with both wl12xx and wl18xx hostap * mark the driver as obsolete ath9k * disable RNG by default ==================== Signed-off-by:
-
David S. Miller authored
Vivien Didelot says: ==================== net: dsa: mv88e6xxx: Global (1) cosmetics The Global (1) internal SMI device of Marvell switches is a set of registers providing support to different units for MAC addresses (ATU), VLANs (VTU), PHY polling (PPU), etc. Chips (like 88E6060) may use a different address for it, or have subtleties in the units (e.g. different number of databases, changing how registers must be accessed), making it hard to maintain properly. This patchset is a first step to polish the Global (1) support, with no functional changes though. Here's basically what it does: - add helpers to access Global1 registers (same for Global2) - remove a few family checks (VTU/STU FID registers) - s/mv88e6xxx_vtu_stu_entry/mv88e6xxx_vtu_entry/ - add a per-chip mv88e6xxx_ops structure of function pointers: struct mv88e6xxx_ops { int (*get_eeprom)(struct mv88e6xxx_chip *chip, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct mv88e6xxx_chip *chip, struct ethtool_eeprom *eeprom, u8 *data); int (*set_switch_mac)(struct mv88e6xxx_chip *chip, u8 *addr); int (*phy_read)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int (*phy_write)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); }; Future patchsets will add ATU/VTU ops, software reset, etc. ==================== Signed-off-by: -
Vivien Didelot authored
Remove EEPROM flags in favor of new {get,set}_eeprom chip-wide functions in the mv88e6xxx_ops structure. Signed-off-by:Vivien Didelot <vivien.didelot@savoirfairelinux.com> Signed-off-by:
-
Vivien Didelot authored
Add a set_switch_mac chip-wide function to mv88e6xxx_ops and remove MV88E6XXX_FLAG_G2_SWITCH_MAC flags. Signed-off-by:
-
Vivien Didelot authored
Introduce a mv88e6xxx_ops structure to describe supported chip-wide functions and assign the correct variant to the chip models. For the moment, add only PHY access routines. This allows to get rid of the PHY ops structures and the usage of PHY flags. Signed-off-by:
-
Vivien Didelot authored
The mv88e6xxx_ops is used to describe how to access the chip registers. It can be through SMI (via an MDIO bus), or via another interface such as crafted remote management frames. The correct BUS operations structure is chosen at runtime, depending on the chip address and connectivity. We will need the mv88e6xxx_ops name for future chip-wide operation structure, thus rename mv88e6xxx_ops to more explicit mv88e6xxx_bus_ops. Signed-off-by:
-
Vivien Didelot authored
The STU (if the switch has one) is abstracted and accessed through the VTU operations and data registers. Thus rename the mv88e6xxx_vtu_stu_entry struct to mv88e6xxx_vtu_entry. Signed-off-by:
-
Vivien Didelot authored
Add an mv88e6xxx_num_ports helper instead of digging in the chip info structure. Signed-off-by:
-
Vivien Didelot authored
The mv88e6xxx_num_databases will be used by shared code, so move it inline to the header file. Signed-off-by:
-
Vivien Didelot authored
Add flags to describe the presence of Global 1 ATU FID register (0x01) and VTU FID register (0x02), instead of checking families. Signed-off-by:
-
Vivien Didelot authored
Similarly to the ports, phys, and Global SMI devices, abstract the SMI device address of the Global 2 registers in a few g2 static helpers. Signed-off-by:
-
Vivien Didelot authored
The Global (1) internal SMI device is an extended set of registers containing ATU, PPU, VTU, STU, etc. It is present on every switches, usually at SMI address 0x1B. But old models such as 88E6060 access it at address 0xF, thus using REG_GLOBAL is erroneous. Add a global1_addr info member used by mv88e6xxx_g1_{read,write} and mv88e6xxx_g1_wait helpers in a new global1.c file. This patch finally removes _mv88e6xxx_reg_{read,write}, in favor on the appropriate helpers. No functional changes here. Signed-off-by:
-
- 29 Sep, 2016 8 commits
-
-
David Howells authored
Note the serial number of the packet being ACK'd in the congestion management trace rather than the serial number of the ACK packet. Whilst the serial number of the ACK packet is useful for matching ACK packet in the output of wireshark, the serial number that the ACK is in response to is of more use in working out how different trace lines relate. Signed-off-by: -
David Howells authored
Set the request-ACK on more DATA packets whilst we're in slow start mode so that we get sufficient ACKs back to supply information to configure the window. Signed-off-by: -
David Howells authored
Reduce the rxrpc_local::services list to just a pointer as we don't permit multiple service endpoints to bind to a single transport endpoints (this is excluded by rxrpc_lookup_local()). The reason we don't allow this is that if you send a request to an AFS filesystem service, it will try to talk back to your cache manager on the port you sent from (this is how file change notifications are handled). To prevent someone from stealing your CM callbacks, we don't let AF_RXRPC sockets share a UDP socket if at least one of them has a service bound. Signed-off-by: -
David Howells authored
In rxrpc_activate_channels(), the connection cache state is checked outside of the lock, which means it can change whilst we're waking calls up, thereby changing whether or not we're allowed to wake calls up. Fix this by moving the check inside the locked region. The check to see if all the channels are currently busy can stay outside of the locked region. Whilst we're at it: (1) Split the locked section out into its own function so that we can call it from other places in a later patch. (2) Determine the mask of channels dependent on the state as we're going to add another state in a later patch that will restrict the number of simultaneous calls to 1 on a connection. Signed-off-by: -
David Howells authored
In rxrpc_send_data_packet() make the loss-injection path return through the same code as the transmission path so that the RTT determination is initiated and any future timer shuffling will be done, despite the packet having been binned. Whilst we're at it: (1) Add to the tx_data tracepoint an indication of whether or not we're retransmitting a data packet. (2) When we're deciding whether or not to request an ACK, rather than checking if we're in fast-retransmit mode check instead if we're retransmitting. (3) Don't invoke the lose_skb tracepoint when losing a Tx packet as we're not altering the sk_buff refcount nor are we just seeing it after getting it off the Tx list. (4) The rxrpc_skb_tx_lost note is then no longer used so remove it. (5) rxrpc_lose_skb() no longer needs to deal with rxrpc_skb_tx_lost. Signed-off-by: -
David Howells authored
Exclusive connections are currently reusable (which they shouldn't be) because rxrpc_alloc_client_connection() checks the exclusive flag in the rxrpc_connection struct before it's initialised from the function parameters. This means that the DONT_REUSE flag doesn't get set. Fix this by checking the function parameters for the exclusive flag. Signed-off-by: -
David S. Miller authored
Timur Tabi says: ==================== Add basic ACPI support to the Qualcomm Technologies EMAC driver This patch series adds support to the EMAC driver for extracting addresses, interrupts, and some _DSDs (properties) from ACPI. The first two patches clean up the code, and the third patch adds ACPI-specific functionality. The first patch fixes a bug with handling the platform_device for the internal PHY. This phy is treated as a separate device in both DT and ACPI, but since the platform is not released automatically when the driver unloads, managed functions like devm_ioremap_resource cannot be used. The second patch replaces of_get_mac_address with its platform-independent equivalent device_get_mac_address. The third patch parses the ACPI tables to obtain the platform_device for the primary EMAC node ("QCOM8070") and the internal phy node ("QCOM8071"). ==================== Signed-off-by: -
Timur Tabi authored
Add support for reading addresses, interrupts, and _DSD properties from ACPI tables, just like with device tree. The HID for the EMAC device itself is QCOM8070. The internal PHY is represented by a child node with a HID of QCOM8071. The EMAC also has some complex clock initialization requirements that are not represented by this patch. This will be addressed in a future patch. Signed-off-by:
Timur Tabi <timur@codeaurora.org> Signed-off-by:
-
