)]}' { "log": [ { "commit": "3b59bf081622b6446db77ad06c93fe23677bc533", "tree": "3f4bb5a27c90cc86994a1f6d3c53fbf9208003cb", "parents": [ "e45836fafe157df137a837093037f741ad8f4c90", "bbdb32cb5b73597386913d052165423b9d736145" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 21:04:47 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 21:04:47 2012 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next\n\nPull networking merge from David Miller:\n \"1) Move ixgbe driver over to purely page based buffering on receive.\n From Alexander Duyck.\n\n 2) Add receive packet steering support to e1000e, from Bruce Allan.\n\n 3) Convert TCP MD5 support over to RCU, from Eric Dumazet.\n\n 4) Reduce cpu usage in handling out-of-order TCP packets on modern\n systems, also from Eric Dumazet.\n\n 5) Support the IP{,V6}_UNICAST_IF socket options, making the wine\n folks happy, from Erich Hoover.\n\n 6) Support VLAN trunking from guests in hyperv driver, from Haiyang\n Zhang.\n\n 7) Support byte-queue-limtis in r8169, from Igor Maravic.\n\n 8) Outline code intended for IP_RECVTOS in IP_PKTOPTIONS existed but\n was never properly implemented, Jiri Benc fixed that.\n\n 9) 64-bit statistics support in r8169 and 8139too, from Junchang Wang.\n\n 10) Support kernel side dump filtering by ctmark in netfilter\n ctnetlink, from Pablo Neira Ayuso.\n\n 11) Support byte-queue-limits in gianfar driver, from Paul Gortmaker.\n\n 12) Add new peek socket options to assist with socket migration, from\n Pavel Emelyanov.\n\n 13) Add sch_plug packet scheduler whose queue is controlled by\n userland daemons using explicit freeze and release commands. From\n Shriram Rajagopalan.\n\n 14) Fix FCOE checksum offload handling on transmit, from Yi Zou.\"\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1846 commits)\n Fix pppol2tp getsockname()\n Remove printk from rds_sendmsg\n ipv6: fix incorrent ipv6 ipsec packet fragment\n cpsw: Hook up default ndo_change_mtu.\n net: qmi_wwan: fix build error due to cdc-wdm dependecy\n netdev: driver: ethernet: Add TI CPSW driver\n netdev: driver: ethernet: add cpsw address lookup engine support\n phy: add am79c874 PHY support\n mlx4_core: fix race on comm channel\n bonding: send igmp report for its master\n fs_enet: Add MPC5125 FEC support and PHY interface selection\n net: bpf_jit: fix BPF_S_LDX_B_MSH compilation\n net: update the usage of CHECKSUM_UNNECESSARY\n fcoe: use CHECKSUM_UNNECESSARY instead of CHECKSUM_PARTIAL on tx\n net: do not do gso for CHECKSUM_UNNECESSARY in netif_needs_gso\n ixgbe: Fix issues with SR-IOV loopback when flow control is disabled\n net/hyperv: Fix the code handling tx busy\n ixgbe: fix namespace issues when FCoE/DCB is not enabled\n rtlwifi: Remove unused ETH_ADDR_LEN defines\n igbvf: Use ETH_ALEN\n ...\n\nFix up fairly trivial conflicts in drivers/isdn/gigaset/interface.c and\ndrivers/net/usb/{Kconfig,qmi_wwan.c} as per David.\n" }, { "commit": "e45836fafe157df137a837093037f741ad8f4c90", "tree": "cba5fdef1fd2e70f3610c78dbcb56ebd1be67654", "parents": [ "0d9cabdccedb79ee5f27b77ff51f29a9e7d23275", "e06ffa1ede4146cbc261d90f5dff3d63fe2e9d7a" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 18:13:22 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 18:13:22 2012 -0700" }, "message": "Merge branch \u0027for-3.4\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq\n\nPull workqueue changes from Tejun Heo:\n \"This contains only one commit which cleans up UP allocation path a\n bit.\"\n\n* \u0027for-3.4\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:\n workqueue: use percpu allocator for cwq on UP\n" }, { "commit": "0d9cabdccedb79ee5f27b77ff51f29a9e7d23275", "tree": "8bfb64c3672d058eb90aec3c3a9c4f61cef9097c", "parents": [ "701085b219016d38f105b031381b9cee6200253a", "3ce3230a0cff484e5130153f244d4fb8a56b3a8b" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 18:11:21 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 18:11:21 2012 -0700" }, "message": "Merge branch \u0027for-3.4\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup\n\nPull cgroup changes from Tejun Heo:\n \"Out of the 8 commits, one fixes a long-standing locking issue around\n tasklist walking and others are cleanups.\"\n\n* \u0027for-3.4\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:\n cgroup: Walk task list under tasklist_lock in cgroup_enable_task_cg_list\n cgroup: Remove wrong comment on cgroup_enable_task_cg_list()\n cgroup: remove cgroup_subsys argument from callbacks\n cgroup: remove extra calls to find_existing_css_set\n cgroup: replace tasklist_lock with rcu_read_lock\n cgroup: simplify double-check locking in cgroup_attach_proc\n cgroup: move struct cgroup_pidlist out from the header file\n cgroup: remove cgroup_attach_task_current_cg()\n" }, { "commit": "701085b219016d38f105b031381b9cee6200253a", "tree": "5111f137c507c8537d5d2c8e4203f0e6e4942bcb", "parents": [ "b6e238dceed36891cc633167afe7151f1f3d83c5" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Mon Mar 19 17:04:01 2012 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 14:16:50 2012 -0700" }, "message": "exec: move de_thread()-\u003esetmax_mm_hiwater_rss() into exec_mmap()\n\nMinor cleanup. de_thread()-\u003esetmax_mm_hiwater_rss() looks a bit\nstrange, move it into exec_mmap() which plays with old_mm.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b6e238dceed36891cc633167afe7151f1f3d83c5", "tree": "eef4928c1a0cb1b56eb20f8d0ee592709d533f10", "parents": [ "e636825346b36a07ccfc8e30946d52855e21f681" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Mon Mar 19 17:03:41 2012 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 14:16:50 2012 -0700" }, "message": "exit_signal: fix the \"parent has changed security domain\" logic\n\nexit_notify() changes -\u003eexit_signal if the parent already did exec.\nThis doesn\u0027t really work, we are not going to send the signal now\nif there is another live thread or the exiting task is traced. The\nparent can exec before the last dies or the tracer detaches.\n\nMove this check into do_notify_parent() which actually sends the\nsignal.\n\nThe user-visible change is that we do not change -\u003eexit_signal,\nand thus the exiting task is still \"clone children\" for\ndo_wait()-\u003eeligible_child(__WCLONE). Hopefully this is fine, the\ncurrent logic is racy anyway.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e636825346b36a07ccfc8e30946d52855e21f681", "tree": "128c37b3102223a95ce03b856766c33e4d077114", "parents": [ "5f8aadd8b9966d71a77bba52b9d499cc2f38269f" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Mon Mar 19 17:03:22 2012 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 14:16:50 2012 -0700" }, "message": "exit_signal: simplify the \"we have changed execution domain\" logic\n\nexit_notify() checks \"tsk-\u003eself_exec_id !\u003d tsk-\u003eparent_exec_id\"\nto handle the \"we have changed execution domain\" case.\n\nWe can change do_thread() to always set -\u003eexit_signal \u003d SIGCHLD\nand remove this check to simplify the code.\n\nWe could change setup_new_exec() instead, this looks more logical\nbecause it increments -\u003eself_exec_id. But note that de_thread()\nalready resets -\u003eexit_signal if it changes the leader, let\u0027s keep\nboth changes close to each other.\n\nNote that we change -\u003eexit_signal lockless, this changes the rules.\nThereafter -\u003eexit_signal is not stable under tasklist but this is\nfine, the only possible change is OLDSIG -\u003e SIGCHLD. This can race\nwith eligible_child() but the race is harmless. We can race with\nreparent_leader() which changes our -\u003eexit_signal in parallel, but\nit does the same change to SIGCHLD.\n\nThe noticeable user-visible change is that the execing task is not\n\"visible\" to do_wait()-\u003eeligible_child(__WCLONE) right after exec.\nTo me this looks more logical, and this is consistent with mt case.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5f8aadd8b9966d71a77bba52b9d499cc2f38269f", "tree": "229735d79edf0c4cc82ac00ba1abaee63040ff6e", "parents": [ "ed378a52dabf77b406b447fd3238f83ea24b71fa" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed Mar 14 19:55:38 2012 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 14:16:50 2012 -0700" }, "message": "CLONE_PARENT shouldn\u0027t allow to set -\u003eexit_signal\n\nThe child must not control its -\u003eexit_signal, it is the parent who\ndecides which signal the child should use for notification.\n\nThis means that CLONE_PARENT should not use \"clone_flags \u0026 CSIGNAL\",\nthe forking task is the sibling of the new process and their parent\ndoesn\u0027t control exit_signal in this case.\n\nThis patch uses -\u003eexit_signal of the forking process, but perhaps\nwe should simply use SIGCHLD.\n\nWe read group_leader-\u003eexit_signal lockless, this can race with the\nORIGINAL_SIGNAL -\u003e SIGCHLD transition, but this is fine.\n\nPotentially this change allows to kill self_exec_id/parent_exec_id.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "bbdb32cb5b73597386913d052165423b9d736145", "tree": "7eaad4e895ed2947eb75d6320df8460c01d1bf6c", "parents": [ "a6506e1486181975d318344143aca722b2b91621" ], "author": { "name": "Benjamin LaHaise", "email": "bcrl@kvack.org", "time": "Tue Mar 20 03:57:54 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Mar 20 16:12:11 2012 -0400" }, "message": "Fix pppol2tp getsockname()\n\nWhile testing L2TP functionality, I came across a bug in getsockname(). The\nIP address returned within the pppol2tp_addr\u0027s addr memember was not being\nset to the IP address in use. This bug is caused by using inet_sk() on the\nwrong socket (the L2TP socket rather than the underlying UDP socket), and was\nlikely introduced during the addition of L2TPv3 support.\n\nSigned-off-by: Benjamin LaHaise \u003cbcrl@kvack.org\u003e\nSigned-off-by: James Chapman \u003cjchapman@katalix.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a6506e1486181975d318344143aca722b2b91621", "tree": "3ce23cc057dc6c3dc3e643653882853379df5677", "parents": [ "1f85851e17b64cabd089a8a8839dddebc627948c" ], "author": { "name": "Dave Jones", "email": "davej@redhat.com", "time": "Mon Mar 19 13:01:07 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Mar 20 16:12:11 2012 -0400" }, "message": "Remove printk from rds_sendmsg\n\nno socket layer outputs a message for this error and neither should rds.\n\nSigned-off-by: Dave Jones \u003cdavej@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ed378a52dabf77b406b447fd3238f83ea24b71fa", "tree": "07e1a7ec2d1c08767ee81b9910f5912b80502632", "parents": [ "843ec558f91b8e8fdb6efc908f2c0506407cc750", "11207b6fe05438b2e87a26435cd98db3d55e6fa7" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:26:30 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:26:30 2012 -0700" }, "message": "Merge tag \u0027usb-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb\n\nPull USB merge for 3.4-rc1 from Greg KH:\n \"Here\u0027s the big USB merge for the 3.4-rc1 merge window.\n\n Lots of gadget driver reworks here, driver updates, xhci changes, some\n new drivers added, usb-serial core reworking to fix some bugs, and\n other various minor things.\n\n There are some patches touching arch code, but they have all been\n acked by the various arch maintainers.\"\n\n* tag \u0027usb-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb: (302 commits)\n net: qmi_wwan: add support for ZTE MF820D\n USB: option: add ZTE MF820D\n usb: gadget: f_fs: Remove lock is held before freeing checks\n USB: option: make interface blacklist work again\n usb/ub: deprecate \u0026 schedule for removal the \"Low Performance USB Block\" driver\n USB: ohci-pxa27x: add clk_prepare/clk_unprepare calls\n USB: use generic platform driver on ath79\n USB: EHCI: Add a generic platform device driver\n USB: OHCI: Add a generic platform device driver\n USB: ftdi_sio: new PID: LUMEL PD12\n USB: ftdi_sio: add support for FT-X series devices\n USB: serial: mos7840: Fixed MCS7820 device attach problem\n usb: Don\u0027t make USB_ARCH_HAS_{XHCI,OHCI,EHCI} depend on USB_SUPPORT.\n usb gadget: fix a section mismatch when compiling g_ffs with CONFIG_USB_FUNCTIONFS_ETH\n USB: ohci-nxp: Remove i2c_write(), use smbus\n USB: ohci-nxp: Support for LPC32xx\n USB: ohci-nxp: Rename symbols from pnx4008 to nxp\n USB: OHCI-HCD: Rename ohci-pnx4008 to ohci-nxp\n usb: gadget: Kconfig: fix typo for \u0027different\u0027\n usb: dwc3: pci: fix another failure path in dwc3_pci_probe()\n ...\n" }, { "commit": "843ec558f91b8e8fdb6efc908f2c0506407cc750", "tree": "1866dccbc298390fc8686875942324075fd83f9d", "parents": [ "71e7ff2578c3bc67fd893a9ba7f69fd563f271de", "fb8ebec00b04f921ea1614a7303f1a8e5e9e47c5" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:24:39 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:24:39 2012 -0700" }, "message": "Merge tag \u0027tty-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty\n\nPull TTY/serial patches from Greg KH:\n \"tty and serial merge for 3.4-rc1\n\n Here\u0027s the big serial and tty merge for the 3.4-rc1 tree.\n\n There\u0027s loads of fixes and reworks in here from Jiri for the tty\n layer, and a number of patches from Alan to help try to wrestle the vt\n layer into a sane model.\n\n Other than that, lots of driver updates and fixes, and other minor\n stuff, all detailed in the shortlog.\"\n\n* tag \u0027tty-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty: (132 commits)\n serial: pxa: add clk_prepare/clk_unprepare calls\n TTY: Wrong unicode value copied in con_set_unimap()\n serial: PL011: clear pending interrupts\n serial: bfin-uart: Don\u0027t access tty circular buffer in TX DMA interrupt after it is reset.\n vt: NULL dereference in vt_do_kdsk_ioctl()\n tty: serial: vt8500: fix annotations for probe/remove\n serial: remove back and forth conversions in serial_out_sync\n serial: use serial_port_in/out vs serial_in/out in 8250\n serial: introduce generic port in/out helpers\n serial: reduce number of indirections in 8250 code\n serial: delete useless void casts in 8250.c\n serial: make 8250\u0027s serial_in shareable to other drivers.\n serial: delete last unused traces of pausing I/O in 8250\n pch_uart: Add module parameter descriptions\n pch_uart: Use existing default_baud in setup_console\n pch_uart: Add user_uartclk parameter\n pch_uart: Add Fish River Island II uart clock quirks\n pch_uart: Use uartclk instead of base_baud\n mpc5200b/uart: select more tolerant uart prescaler on low baudrates\n tty: moxa: fix bit test in moxa_start()\n ...\n" }, { "commit": "71e7ff2578c3bc67fd893a9ba7f69fd563f271de", "tree": "07f8f6e950f54f745857c6be07a5186fd68a74d2", "parents": [ "4a52246302f01596f0edf7b4a3e6425e23479192", "bc01caf53da4de53361376734707336de8fff839" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:23:18 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:23:18 2012 -0700" }, "message": "Merge tag \u0027staging-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging\n\nPull big staging driver updates from Greg KH:\n \"Here is the big drivers/staging/ merge for 3.4-rc1\n\n Lots of new driver updates here, with the addition of a few new ones,\n and only one moving out of the staging tree to the \"real\" part of the\n kernel (the hyperv scsi driver, acked by the scsi maintainer).\n\n There are also loads of cleanups, fixes, and other minor things in\n here, all self-contained in the drivers/staging/ tree.\n\n Overall we reversed the recent trend by adding more lines than we\n removed:\n 379 files changed, 37952 insertions(+), 14153 deletions(-)\"\n\n* tag \u0027staging-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging: (360 commits)\n staging/zmem: Use lockdep_assert_held instead of spin_is_locked\n Staging: rtl8187se: r8180_wx.c: Cleaned up comments\n Staging: rtl8187se: r8180_wx.c: Removed old comments\n Staging: rtl8187se: r8180_dm.c: Removed old comments\n Staging: android: ram_console.c:\n Staging: rtl8187se: r8180_dm.c: Fix comments\n Staging: rtl8187se: r8180_dm.c: Fix spacing issues\n Staging: rtl8187se: r8180_dm.c Fixed indentation issues\n Staging: rtl8187se: r8180_dm.c: Fix brackets\n Staging: rtl8187se: r8180_dm.c: Removed spaces before tab stop\n staging: vme: fix section mismatches in linux-next 20120314\n Staging: rtl8187se: r8180_core.c: Fix some long line issues\n Staging: rtl8187se: r8180_core.c: Fix some spacing issues\n Staging: rtl8187se: r8180_core.c: Removed trailing spaces\n staging: mei: remove driver internal versioning\n Staging: rtl8187se: r8180_core.c: Cleaned up if statement\n staging: ozwpan depends on NET\n staging: ozwpan: added maintainer for ozwpan driver\n staging/mei: propagate error codes up in the write flow\n drivers:staging:mei Fix some typos in staging/mei\n ...\n" }, { "commit": "4a52246302f01596f0edf7b4a3e6425e23479192", "tree": "f384d86722d3ccfc875e3e5e8d8726e993a922ee", "parents": [ "9f9d2760da8c7f94fae119fac3e13d5a1702f8f0", "adc80ae60eae24a43a357bf5b30fb496f34aa605" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:16:20 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:16:20 2012 -0700" }, "message": "Merge tag \u0027driver-core-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core\n\nPull driver core patches for 3.4-rc1 from Greg KH:\n \"Here\u0027s the big driver core merge for 3.4-rc1.\n\n Lots of various things here, sysfs fixes/tweaks (with the nlink\n breakage reverted), dynamic debugging updates, w1 drivers, hyperv\n driver updates, and a variety of other bits and pieces, full\n information in the shortlog.\"\n\n* tag \u0027driver-core-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (78 commits)\n Tools: hv: Support enumeration from all the pools\n Tools: hv: Fully support the new KVP verbs in the user level daemon\n Drivers: hv: Support the newly introduced KVP messages in the driver\n Drivers: hv: Add new message types to enhance KVP\n regulator: Support driver probe deferral\n Revert \"sysfs: Kill nlink counting.\"\n uevent: send events in correct order according to seqnum (v3)\n driver core: minor comment formatting cleanups\n driver core: move the deferred probe pointer into the private area\n drivercore: Add driver probe deferral mechanism\n DS2781 Maxim Stand-Alone Fuel Gauge battery and w1 slave drivers\n w1_bq27000: Only one thread can access the bq27000 at a time.\n w1_bq27000 - remove w1_bq27000_write\n w1_bq27000: remove unnecessary NULL test.\n sysfs: Fix memory leak in sysfs_sd_setsecdata().\n intel_idle: Revert change of auto_demotion_disable_flags for Nehalem\n w1: Fix w1_bq27000\n driver-core: documentation: fix up Greg\u0027s email address\n powernow-k6: Really enable auto-loading\n powernow-k7: Fix CPU family number\n ...\n" }, { "commit": "9f9d2760da8c7f94fae119fac3e13d5a1702f8f0", "tree": "e244a2969edceff750478e7d98355b76ef30aa0f", "parents": [ "ad2a8e6078a16d3b61b530f1447110841c36ae56", "b222258ac11cae3e0350fe5992ad164a7b128103" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:15:18 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:15:18 2012 -0700" }, "message": "Merge tag \u0027char-misc-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc\n\nPull char and misc patches for 3.4-rc1 from Greg KH:\n \"Not much here, just a few minor fixes and some conversions to the\n module_*_driver() functions, making the codebase smaller.\"\n\n* tag \u0027char-misc-3.3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:\n misc: bmp085: Use unsigned long to store jiffies\n char/ramoops: included linux/err.h twice\n misc: bmp085: Handle jiffies overflow correctly\n misc: fsa9480: Remove obsolete cleanup for clientdata\n char: Fix typo in tlclk.c\n char: Fix typo in viotape.c\n cs5535-mfgpt: don\u0027t call __init function from __devinit\n MISC: convert drivers/misc/* to use module_spi_driver()\n MISC: convert drivers/misc/* to use module_i2c_driver()\n MISC: convert drivers/misc/* to use module_platform_driver()\n" }, { "commit": "ad2a8e6078a16d3b61b530f1447110841c36ae56", "tree": "f926ff62ed28c3bec8527a94b0ac5e46556e8e38", "parents": [ "161f7a7161191ab9c2e97f787829ef8dd2b95771" ], "author": { "name": "Dan Carpenter", "email": "dan.carpenter@oracle.com", "time": "Tue Mar 20 16:58:06 2012 +0000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 11:14:38 2012 -0700" }, "message": "AFS: checking wrong bit in afs_readpages()\n\nWe should be testing \"if (vnode-\u003eflags \u0026 (1 \u003c\u003c 4))\" instead of\n\"if (vnode-\u003eflags \u0026 4) {\". The current test checks if the data was\nmodified instead of deleted.\n\nSigned-off-by: Dan Carpenter \u003cdan.carpenter@oracle.com\u003e\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "161f7a7161191ab9c2e97f787829ef8dd2b95771", "tree": "9776d3f963c7f0d247b7fb324eab4811a1302f67", "parents": [ "2ba68940c893c8f0bfc8573c041254251bb6aeab", "a078c6d0e6288fad6d83fb6d5edd91ddb7b6ab33" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:32:09 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:32:09 2012 -0700" }, "message": "Merge branch \u0027timers-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip\n\nPull timer changes for v3.4 from Ingo Molnar\n\n* \u0027timers-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)\n ntp: Fix integer overflow when setting time\n math: Introduce div64_long\n cs5535-clockevt: Allow the MFGPT IRQ to be shared\n cs5535-clockevt: Don\u0027t ignore MFGPT on SMP-capable kernels\n x86/time: Eliminate unused irq0_irqs counter\n clocksource: scx200_hrt: Fix the build\n x86/tsc: Reduce the TSC sync check time for core-siblings\n timer: Fix bad idle check on irq entry\n nohz: Remove ts-\u003eEinidle checks before restarting the tick\n nohz: Remove update_ts_time_stat from tick_nohz_start_idle\n clockevents: Leave the broadcast device in shutdown mode when not needed\n clocksource: Load the ACPI PM clocksource asynchronously\n clocksource: scx200_hrt: Convert scx200 to use clocksource_register_hz\n clocksource: Get rid of clocksource_calc_mult_shift()\n clocksource: dbx500: convert to clocksource_register_hz()\n clocksource: scx200_hrt: use pr_\u003clevel\u003e instead of printk\n time: Move common updates to a function\n time: Reorder so the hot data is together\n time: Remove most of xtime_lock usage in timekeeping.c\n ntp: Add ntp_lock to replace xtime_locking\n ...\n" }, { "commit": "2ba68940c893c8f0bfc8573c041254251bb6aeab", "tree": "fa83ebb01d32abd98123fa28f9f6f0b3eaeee25d", "parents": [ "9c2b957db1772ebf942ae7a9346b14eba6c8ca66", "600e145882802d6ccbfe2c4aea243d97caeb91a9" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:31:44 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:31:44 2012 -0700" }, "message": "Merge branch \u0027sched-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip\n\nPull scheduler changes for v3.4 from Ingo Molnar\n\n* \u0027sched-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)\n printk: Make it compile with !CONFIG_PRINTK\n sched/x86: Fix overflow in cyc2ns_offset\n sched: Fix nohz load accounting -- again!\n sched: Update yield() docs\n printk/sched: Introduce special printk_sched() for those awkward moments\n sched/nohz: Correctly initialize \u0027next_balance\u0027 in \u0027nohz\u0027 idle balancer\n sched: Cleanup cpu_active madness\n sched: Fix load-balance wreckage\n sched: Clean up parameter passing of proc_sched_autogroup_set_nice()\n sched: Ditch per cgroup task lists for load-balancing\n sched: Rename load-balancing fields\n sched: Move load-balancing arguments into helper struct\n sched/rt: Do not submit new work when PI-blocked\n sched/rt: Prevent idle task boosting\n sched/wait: Add __wake_up_all_locked() API\n sched/rt: Document scheduler related skip-resched-check sites\n sched/rt: Use schedule_preempt_disabled()\n sched/rt: Add schedule_preempt_disabled()\n sched/rt: Do not throttle when PI boosting\n sched/rt: Keep period timer ticking when rt throttling is active\n ...\n" }, { "commit": "9c2b957db1772ebf942ae7a9346b14eba6c8ca66", "tree": "0dbb83e57260ea7fc0dc421f214d5f1b26262005", "parents": [ "0bbfcaff9b2a69c71a95e6902253487ab30cb498", "bea95c152dee1791dd02cbc708afbb115bb00f9a" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:29:15 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:29:15 2012 -0700" }, "message": "Merge branch \u0027perf-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip\n\nPull perf events changes for v3.4 from Ingo Molnar:\n\n - New \"hardware based branch profiling\" feature both on the kernel and\n the tooling side, on CPUs that support it. (modern x86 Intel CPUs\n with the \u0027LBR\u0027 hardware feature currently.)\n\n This new feature is basically a sophisticated \u0027magnifying glass\u0027 for\n branch execution - something that is pretty difficult to extract from\n regular, function histogram centric profiles.\n\n The simplest mode is activated via \u0027perf record -b\u0027, and the result\n looks like this in perf report:\n\n\t$ perf record -b any_call,u -e cycles:u branchy\n\n\t$ perf report -b --sort\u003dsymbol\n\t 52.34% [.] main [.] f1\n\t 24.04% [.] f1 [.] f3\n\t 23.60% [.] f1 [.] f2\n\t 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow\n\t 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn\n\t 0.01% [k] _IO_vfprintf_internal [k] strchrnul\n\t 0.01% [k] __printf [k] _IO_vfprintf_internal\n\t 0.01% [k] main [k] __printf\n\n This output shows from/to branch columns and shows the highest\n percentage (from,to) jump combinations - i.e. the most likely taken\n branches in the system. \"branches\" can also include function calls\n and any other synchronous and asynchronous transitions of the\n instruction pointer that are not \u0027next instruction\u0027 - such as system\n calls, traps, interrupts, etc.\n\n This feature comes with (hopefully intuitive) flat ascii and TUI\n support in perf report.\n\n - Various \u0027perf annotate\u0027 visual improvements for us assembly junkies.\n It will now recognize function calls in the TUI and by hitting enter\n you can follow the call (recursively) and back, amongst other\n improvements.\n\n - Multiple threads/processes recording support in perf record, perf\n stat, perf top - which is activated via a comma-list of PIDs:\n\n\tperf top -p 21483,21485\n\tperf stat -p 21483,21485 -ddd\n\tperf record -p 21483,21485\n\n - Support for per UID views, via the --uid paramter to perf top, perf\n report, etc. For example \u0027perf top --uid mingo\u0027 will only show the\n tasks that I am running, excluding other users, root, etc.\n\n - Jump label restructurings and improvements - this includes the\n factoring out of the (hopefully much clearer) include/linux/static_key.h\n generic facility:\n\n\tstruct static_key key \u003d STATIC_KEY_INIT_FALSE;\n\n\t...\n\n\tif (static_key_false(\u0026key))\n\t do unlikely code\n\telse\n\t do likely code\n\n\t...\n\tstatic_key_slow_inc();\n\t...\n\tstatic_key_slow_inc();\n\t...\n\n The static_key_false() branch will be generated into the code with as\n little impact to the likely code path as possible. the\n static_key_slow_*() APIs flip the branch via live kernel code patching.\n\n This facility can now be used more widely within the kernel to\n micro-optimize hot branches whose likelihood matches the static-key\n usage and fast/slow cost patterns.\n\n - SW function tracer improvements: perf support and filtering support.\n\n - Various hardenings of the perf.data ABI, to make older perf.data\u0027s\n smoother on newer tool versions, to make new features integrate more\n smoothly, to support cross-endian recording/analyzing workflows\n better, etc.\n\n - Restructuring of the kprobes code, the splitting out of \u0027optprobes\u0027,\n and a corner case bugfix.\n\n - Allow the tracing of kernel console output (printk).\n\n - Improvements/fixes to user-space RDPMC support, allowing user-space\n self-profiling code to extract PMU counts without performing any\n system calls, while playing nice with the kernel side.\n\n - \u0027perf bench\u0027 improvements\n\n - ... and lots of internal restructurings, cleanups and fixes that made\n these features possible. And, as usual this list is incomplete as\n there were also lots of other improvements\n\n* \u0027perf-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)\n perf report: Fix annotate double quit issue in branch view mode\n perf report: Remove duplicate annotate choice in branch view mode\n perf/x86: Prettify pmu config literals\n perf report: Enable TUI in branch view mode\n perf report: Auto-detect branch stack sampling mode\n perf record: Add HEADER_BRANCH_STACK tag\n perf record: Provide default branch stack sampling mode option\n perf tools: Make perf able to read files from older ABIs\n perf tools: Fix ABI compatibility bug in print_event_desc()\n perf tools: Enable reading of perf.data files from different ABI rev\n perf: Add ABI reference sizes\n perf report: Add support for taken branch sampling\n perf record: Add support for sampling taken branch\n perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK\n x86/kprobes: Split out optprobe related code to kprobes-opt.c\n x86/kprobes: Fix a bug which can modify kernel code permanently\n x86/kprobes: Fix instruction recovery on optimized path\n perf: Add callback to flush branch_stack on context switch\n perf: Disable PERF_SAMPLE_BRANCH_* when not supported\n perf/x86: Add LBR software filter support for Intel CPUs\n ...\n" }, { "commit": "0bbfcaff9b2a69c71a95e6902253487ab30cb498", "tree": "f422bbfb8ba57909bf6e43f1d560b3f056cc3c61", "parents": [ "5928a2b60cfdbad730f93696acab142d0b607280", "e04268b0effc0ceea366c50b3107baad9edadafa" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:28:56 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:28:56 2012 -0700" }, "message": "Merge branch \u0027irq-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip\n\nPull irq/core changes for v3.4 from Ingo Molnar\n\n* \u0027irq-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:\n genirq: Remove paranoid warnons and bogus fixups\n genirq: Flush the irq thread on synchronization\n genirq: Get rid of unnecessary IRQTF_DIED flag\n genirq: No need to check IRQTF_DIED before stopping a thread handler\n genirq: Get rid of unnecessary irqaction field in task_struct\n genirq: Fix incorrect check for forced IRQ thread handler\n softirq: Reduce invoke_softirq() code duplication\n genirq: Fix long-term regression in genirq irq_set_irq_type() handling\n x86-32/irq: Don\u0027t switch to irq stack for a user-mode irq\n" }, { "commit": "5928a2b60cfdbad730f93696acab142d0b607280", "tree": "49bb21c9219673e61bad7a7c9202c7f25f5fe1be", "parents": [ "5ed59af85077d28875a3a137b21933aaf1b4cd50", "bdd4431c8d071491a68a65d9457996f222b5ecd3" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 17:12:34 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 20 10:10:18 2012 -0700" }, "message": "Merge branch \u0027core-rcu-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip\n\nPull RCU changes for v3.4 from Ingo Molnar. The major features of this\nseries are:\n\n - making RCU more aggressive about entering dyntick-idle mode in order\n to improve energy efficiency\n\n - converting a few more call_rcu()s to kfree_rcu()s\n\n - applying a number of rcutree fixes and cleanups to rcutiny\n\n - removing CONFIG_SMP #ifdefs from treercu\n\n - allowing RCU CPU stall times to be set via sysfs\n\n - adding CPU-stall capability to rcutorture\n\n - adding more RCU-abuse diagnostics\n\n - updating documentation\n\n - fixing yet more issues located by the still-ongoing top-to-bottom\n inspection of RCU, this time with a special focus on the CPU-hotplug\n code path.\n\n* \u0027core-rcu-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)\n rcu: Stop spurious warnings from synchronize_sched_expedited\n rcu: Hold off RCU_FAST_NO_HZ after timer posted\n rcu: Eliminate softirq-mediated RCU_FAST_NO_HZ idle-entry loop\n rcu: Add RCU_NONIDLE() for idle-loop RCU read-side critical sections\n rcu: Allow nesting of rcu_idle_enter() and rcu_idle_exit()\n rcu: Remove redundant check for rcu_head misalignment\n PTR_ERR should be called before its argument is cleared.\n rcu: Convert WARN_ON_ONCE() in rcu_lock_acquire() to lockdep\n rcu: Trace only after NULL-pointer check\n rcu: Call out dangers of expedited RCU primitives\n rcu: Rework detection of use of RCU by offline CPUs\n lockdep: Add CPU-idle/offline warning to lockdep-RCU splat\n rcu: No interrupt disabling for rcu_prepare_for_idle()\n rcu: Move synchronize_sched_expedited() to rcutree.c\n rcu: Check for illegal use of RCU from offlined CPUs\n rcu: Update stall-warning documentation\n rcu: Add CPU-stall capability to rcutorture\n rcu: Make documentation give more realistic rcutorture duration\n rcutorture: Permit holding off CPU-hotplug operations during boot\n rcu: Print scheduling-clock information on RCU CPU stall-warning messages\n ...\n" }, { "commit": "1f85851e17b64cabd089a8a8839dddebc627948c", "tree": "a7a23af86a8241f09cff1602786bd7e26a120d17", "parents": [ "5c473ed26dba609622c9a625f896f8f59d86066c" ], "author": { "name": "Gao feng", "email": "gaofeng@cn.fujitsu.com", "time": "Mon Mar 19 22:36:10 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Mar 20 05:39:34 2012 -0400" }, "message": "ipv6: fix incorrent ipv6 ipsec packet fragment\n\nSince commit 299b0767(ipv6: Fix IPsec slowpath fragmentation problem)\nIn func ip6_append_data,after call skb_put(skb, fraglen + dst_exthdrlen)\nthe skb-\u003elen contains dst_exthdrlen,and we don\u0027t reduce dst_exthdrlen at last\nThis will make fraggap\u003e0 in next \"while cycle\",and cause the size of skb incorrent\n\nFix this by reserve headroom for dst_exthdrlen.\n\nSigned-off-by: Gao feng \u003cgaofeng@cn.fujitsu.com\u003e\nAcked-by: Steffen Klassert \u003csteffen.klassert@secunet.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5c473ed26dba609622c9a625f896f8f59d86066c", "tree": "ea455d5791f56108db322aaddef03361cd310d99", "parents": [ "74cba4a85e92650f29be0e2d2ba1c282002d1168" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Mar 20 00:33:59 2012 -0400" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Mar 20 00:33:59 2012 -0400" }, "message": "cpsw: Hook up default ndo_change_mtu.\n\nReported-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5ed59af85077d28875a3a137b21933aaf1b4cd50", "tree": "d225d654de47ebe480a59d479ae5b3cc7c90cd71", "parents": [ "b7f077d7bc28649f6bd369fadec01219e725a9c6", "81b40539e748b108d143a5e38526ab00a6a784b6" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 17:11:15 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 17:11:15 2012 -0700" }, "message": "Merge branch \u0027core-locking-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip\n\nPull core/locking changes for v3.4 from Ingo Molnar\n\n* \u0027core-locking-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:\n futex: Simplify return logic\n futex: Cover all PI opcodes with cmpxchg enabled check\n" }, { "commit": "b7f077d7bc28649f6bd369fadec01219e725a9c6", "tree": "4e8f0959a8e522452ff8117c232f277b14e7bf07", "parents": [ "b0e37d7ac6ba937c3776ff5111ff6a7fa832fb4f", "1b198bb04ad72669d4bd6575fc9945ed595bfee0" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 17:10:38 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 17:10:38 2012 -0700" }, "message": "Merge branch \u0027core-iommu-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip\n\nPull core/iommu changes for v3.4 from Ingo Molnar\n\n* \u0027core-iommu-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:\n x86/iommu/intel: Increase the number of iommus supported to MAX_IO_APICS\n x86/iommu/intel: Fix identity mapping for sandy bridge\n" }, { "commit": "b0e37d7ac6ba937c3776ff5111ff6a7fa832fb4f", "tree": "fdb86783c464825a77223e49cc24f632e319d2df", "parents": [ "6d7d1a0dc735ea8412769edae7154885021107a9", "bfcfaa77bdf0f775263e906015982a608df01c76" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 16:37:28 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 16:37:28 2012 -0700" }, "message": "Merge branch \u0027dcache-word-accesses\u0027\n\n* branch \u0027dcache-word-accesses\u0027:\n vfs: use \u0027unsigned long\u0027 accesses for dcache name comparison and hashing\n\nThis does the name hashing and lookup using word-sized accesses when\nthat is efficient, namely on x86 (although any little-endian machine\nwith good unaligned accesses would do).\n\nIt does very much depend on little-endian logic, but it\u0027s a very hot\ncouple of functions under some real loads, and this patch improves the\nperformance of __d_lookup_rcu() and link_path_walk() by up to about 30%.\nGiving a 10% improvement on some very pathname-heavy benchmarks.\n\nBecause we do make unaligned accesses past the filename, the\noptimization is disabled when CONFIG_DEBUG_PAGEALLOC is active, and we\neffectively depend on the fact that on x86 we don\u0027t really ever have the\nlast page of usable RAM followed immediately by any IO memory (due to\nACPI tables, BIOS buffer areas etc).\n\nSome of the bit operations we do are a bit \"subtle\". It\u0027s commented,\nbut you do need to really think about the code. Or just consider it\nblack magic.\n\nThanks to people on G+ for some of the optimized bit tricks.\n" }, { "commit": "6d7d1a0dc735ea8412769edae7154885021107a9", "tree": "9ccf7b36be77b61cdb1491f262be95592c731858", "parents": [ "c16fa4f2ad19908a47c63d8fa436a1178438c7e7" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 16:19:53 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 19 16:19:53 2012 -0700" }, "message": "vfs: get rid of batshit-insane pointless dentry hash calculations\n\nFor some odd historical reason, the final mixing round for the dentry\ncache hash table lookup had an insane \"xor with big constant\" logic. In\ntwo places.\n\nThe big constant that is being xor\u0027ed is GOLDEN_RATIO_PRIME, which is a\nfairly random-looking number that is designed to be *multiplied* with so\nthat the bits get spread out over a whole long-word.\n\nBut xor\u0027ing with it is insane. It doesn\u0027t really even change the hash -\nit really only shifts the hash around in the hash table. To make\nmatters worse, the insane big constant is different on 32-bit and 64-bit\nbuilds, even though the name hash bits we use are always 32-bit (and the\nbits from the pointer we mix in effectively are too).\n\nIt\u0027s all total voodoo programming, in other words.\n\nNow, some testing and analysis of the hash chains shows that the rest of\nthe hash function seems to be fairly good. It does pick the right bits\nof the parent dentry pointer, for example, and while it\u0027s generally a\nbad idea to use an xor to mix down the upper bits (because if there is a\nrepeating pattern, the xor can cause \"destructive interference\"), it\nseems to not have been a disaster.\n\nFor example, replacing the hash with the normal \"hash_long()\" code (that\nuses the GOLDEN_RATIO_PRIME constant correctly, btw) actually just makes\nthe hash worse. The hand-picked hash knew which bits of the pointer had\nthe highest entropy, and hash_long() ends up mixing bits less optimally\nat least in some trivial tests.\n\nSo the hash function overall seems fine, it just has that really odd\n\"shift result around by a constant xor\".\n\nSo get rid of the silly xor, and replace the down-mixing of the bits\nwith an add instead of an xor that tends to not have the same kind of\ndestructive interference issues. Some stats on the resulting hash\nchains shows that they look statistically identical before and after,\nbut the code is simpler and no longer makes you go \"WTF?\".\n\nAlso, the incoming hash really is just \"unsigned int\", not a long, and\nthere\u0027s no real point to worry about the high 26 bits of the dentry\npointer for the 64-bit case, because they are all going to be identical\nanyway.\n\nSo also change the hashing to be done in the more natural \u0027unsigned int\u0027\nthat is the real size of the actual hashed data anyway.\n\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "74cba4a85e92650f29be0e2d2ba1c282002d1168", "tree": "eda4f51147ec2422d49a212c661da56f00cfe984", "parents": [ "df828598a755732e717b0adca82f884e44d37576" ], "author": { "name": "Bjørn Mork", "email": "bjorn@mork.no", "time": "Mon Mar 19 07:48:29 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 18:17:18 2012 -0400" }, "message": "net: qmi_wwan: fix build error due to cdc-wdm dependecy\n\nFixes:\n\ndrivers/built-in.o: In function `qmi_wwan_bind_shared\u0027:\nqmi_wwan.c:(.text+0x25b686): undefined reference to `usb_cdc_wdm_register\u0027\nmake[1]: *** [.tmp_vmlinux1] Error 1\n\nReported-by: Randy Dunlap \u003crdunlap@xenotime.net\u003e\nSigned-off-by: Bjørn Mork \u003cbjorn@mork.no\u003e\nAcked-by: Randy Dunlap \u003crdunlap@xenotime.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "df828598a755732e717b0adca82f884e44d37576", "tree": "26d260fd85a57efa14cc4be65ebd702f35879be4", "parents": [ "db82173f23c5289118142fc76111f99ff809df89" ], "author": { "name": "Mugunthan V N", "email": "mugunthanvnm@ti.com", "time": "Sun Mar 18 20:17:54 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 18:02:05 2012 -0400" }, "message": "netdev: driver: ethernet: Add TI CPSW driver\n\nThis patch adds support for TI\u0027s CPSW driver.\n\nThe three port switch gigabit ethernet subsystem provides ethernet packet\ncommunication and can be configured as an ethernet switch. Supports\n10/100/1000 Mbps.\n\nSigned-off-by: Cyril Chemparathy \u003ccyril@ti.com\u003e\nSigned-off-by: Sriramakrishnan A G \u003csrk@ti.com\u003e\nSigned-off-by: Mugunthan V N \u003cmugunthanvnm@ti.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "db82173f23c5289118142fc76111f99ff809df89", "tree": "d355682ddfb2fca988322ae88660788999d64767", "parents": [ "49099122a403b907dc12a5e66033678a07c68ba3" ], "author": { "name": "Mugunthan V N", "email": "mugunthanvnm@ti.com", "time": "Sun Mar 18 20:17:53 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 18:02:05 2012 -0400" }, "message": "netdev: driver: ethernet: add cpsw address lookup engine support\n\nTI CPSW ethernet switch has a built-in address lookup engine. This patch adds\nthe code necessary for programming this module.\n\nSigned-off-by: Cyril Chemparathy \u003ccyril@ti.com\u003e\nSigned-off-by: Mugunthan V N \u003cmugunthanvnm@ti.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "49099122a403b907dc12a5e66033678a07c68ba3", "tree": "6531b7cca21ea91ca6285bfedff244ce10a07292", "parents": [ "58a3de0592454c216c68427fa3c31a34823f5115" ], "author": { "name": "Heiko Schocher", "email": "hs@denx.de", "time": "Sun Mar 18 11:03:05 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 18:02:05 2012 -0400" }, "message": "phy: add am79c874 PHY support\n\nSigned-off-by: Heiko Schocher \u003chs@denx.de\u003e\nSigned-off-by: Anatolij Gustschin \u003cagust@denx.de\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "58a3de0592454c216c68427fa3c31a34823f5115", "tree": "0db88951509d01bb815e3357aafd41ba9ef2ee0e", "parents": [ "1c3ac4289a0e4d60cbd4787b4a91de4a0c785df1" ], "author": { "name": "Eugenia Emantayev", "email": "eugenia@mellanox.co.il", "time": "Sun Mar 18 04:32:08 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 18:02:05 2012 -0400" }, "message": "mlx4_core: fix race on comm channel\n\nPrevent race condition between commands on comm channel.\nHappened while unloading the driver when switching from\nevent to polling mode. VF got completion on the last command\nbefore switching to polling mode, but toggle was not changed.\nAfter the fix - VF will not write the next command before\ntoggle is updated.\n\nSigned-off-by: Eugenia Emantayev \u003ceugenia@mellanox.co.il\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1c3ac4289a0e4d60cbd4787b4a91de4a0c785df1", "tree": "01a3a0806e24d869b2e0df5e8e8fb0aaeb91bd4e", "parents": [ "ba568335b089e0a27829e3a6117a7e1bf957ad07" ], "author": { "name": "Peter Pan(潘卫平)", "email": "panweiping3@gmail.com", "time": "Sat Mar 17 17:23:27 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 18:02:05 2012 -0400" }, "message": "bonding: send igmp report for its master\n\nLiang Zheng(lzheng@redhat.com) found that in the following topo,\nbonding does not send igmp report when we trigger a fail-over of bonding.\n\neth0--\n |-- bond0 -- br0\neth1--\n\nmodprobe bonding mode\u003d1 miimon\u003d100 resend_igmp\u003d10\nifconfig bond0 up\nifenslave bond0 eth0 eth1\n\nbrctl addbr br0\nifconfig br0 192.168.100.2/24 up\nbrctl addif br0 bond0\n\nAdd 192.168.100.2(br0) into a multicast group, like 224.10.10.10,\nthen trigger a fali-over in bonding.\nYou can see that parameter \"resend_igmp\" does not work.\n\nThe reason is that when we add br0 into a multicast group,\nit does not propagate multicast knowledge down to its ports.\n\nIf we choose to propagate multicast knowledge down to all ports for bridge,\nthen we have to track every change that is done to bridge, and keep a backup\nfor all ports. It is hard to track, I think.\n\nInstead I choose to modify bonding to send igmp report for its master.\n\nChangelog:\nV2: correct comments\nV3: move this check into bond_resend_igmp_join_requests()\nV4: only send igmp reports if bond is enslaved to a bridge\n\nSigned-off-by: Weiping Pan \u003cpanweiping3@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ba568335b089e0a27829e3a6117a7e1bf957ad07", "tree": "460d6569c4ad623ec8f1aee8d0fcb571b3ac1b4d", "parents": [ "dc72d99dabb870ca5bd6d9fff674be853bb4a88d" ], "author": { "name": "Vladimir Ermakov", "email": "vooon341@gmail.com", "time": "Sat Mar 17 13:10:50 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 18:02:05 2012 -0400" }, "message": "fs_enet: Add MPC5125 FEC support and PHY interface selection\n\nAdd compatible string for MPC5125 FEC. The FEC on MPC5125 additionally\nsupports RMII PHY interface. Configure controller/PHY interface type\naccording to the optional phy-connection-type property in the ethernet\nnode. This property should be either \"rmii\" or \"mii\".\n\nSigned-off-by: Vladimir Ermakov \u003cvooon341@gmail.com\u003e\nSigned-off-by: Anatolij Gustschin \u003cagust@denx.de\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "dc72d99dabb870ca5bd6d9fff674be853bb4a88d", "tree": "20fbc871a5f19e4e243425d78c5a2e50cbb66912", "parents": [ "3af79302b400e05b45e377993a8870869500466b" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Sun Mar 18 02:40:48 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 17:41:44 2012 -0400" }, "message": "net: bpf_jit: fix BPF_S_LDX_B_MSH compilation\n\nMatt Evans spotted that x86 bpf_jit was incorrectly handling negative\nconstant offsets in BPF_S_LDX_B_MSH instruction.\n\nWe need to abort JIT compilation like we do in common_load so that\nfilter uses the interpreter code and can call __load_pointer()\n\nReference: http://lists.openwall.net/netdev/2011/07/19/11\n\nThanks to Indan Zupancic to bring back this issue.\n\nReported-by: Matt Evans \u003cmatt@ozlabs.org\u003e\nReported-by: Indan Zupancic \u003cindan@nul.nu\u003e\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3af79302b400e05b45e377993a8870869500466b", "tree": "d273210736e14576bbc49009ece005c62f1bb3e8", "parents": [ "cf64bc8f093581d0697b65ea8dd04bdd27a676b0" ], "author": { "name": "Yi Zou", "email": "yi.zou@intel.com", "time": "Mon Mar 19 11:12:41 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 17:37:35 2012 -0400" }, "message": "net: update the usage of CHECKSUM_UNNECESSARY\n\nAs suggested by Ben, this adds the clarification on the usage of\nCHECKSUM_UNNECESSARY on the outgoing patch. Also add the usage\ndescription of NETIF_F_FCOE_CRC and CHECKSUM_UNNECESSARY\nfor the kernel FCoE protocol driver.\n\nThis is a follow-up to the following:\nhttp://patchwork.ozlabs.org/patch/147315/\n\nSigned-off-by: Yi Zou \u003cyi.zou@intel.com\u003e\nCc: Ben Hutchings \u003cbhutchings@solarflare.com\u003e\nCc: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\nCc: www.Open-FCoE.org \u003cdevel@open-fcoe.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cf64bc8f093581d0697b65ea8dd04bdd27a676b0", "tree": "1ed362ce0741169c3b4f6f5e574334279283d92a", "parents": [ "cdbee74ce74cd66de42a6f6d0edfa74fa9a66f2a" ], "author": { "name": "Yi Zou", "email": "yi.zou@intel.com", "time": "Fri Mar 16 23:08:12 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 17:37:35 2012 -0400" }, "message": "fcoe: use CHECKSUM_UNNECESSARY instead of CHECKSUM_PARTIAL on tx\n\nFix a bug when using \u0027ethtool -K ethx tx off\u0027 to turn off tx ip checksum,\nFCoE CRC offload should not be impacte. The skb_checksum_help() is needed\nonly if it\u0027s not FCoE traffic for ip checksum, regardless of ethtool toggling\nthe tx ip checksum on or off. Instead of using CHECKSUM_PARTIAL, we will\nuse CHECKSUM_UNNECESSARY as a proper indication to avoid sw ip checksum\non FCoE frames.\n\nRef. to original discussion thread:\nhttp://patchwork.ozlabs.org/patch/146567/\n\nCC: \"James E.J. Bottomley\" \u003cJBottomley@parallels.com\u003e\nCC: Robert Love \u003crobert.w.love@intel.com\u003e\nSigned-off-by: Yi Zou \u003cyi.zou@intel.com\u003e\nTested-by: Ross Brattain \u003cross.b.brattain@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cdbee74ce74cd66de42a6f6d0edfa74fa9a66f2a", "tree": "a474de30581af399a5024dd69bfa67dced47b8c5", "parents": [ "8f4a0a3d9f9706da5a9d053fe39854c160250ddc" ], "author": { "name": "Yi Zou", "email": "yi.zou@intel.com", "time": "Fri Mar 16 23:08:11 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 17:37:35 2012 -0400" }, "message": "net: do not do gso for CHECKSUM_UNNECESSARY in netif_needs_gso\n\nThis is related to fixing the bug of dropping FCoE frames when disabling tx ip\nchecksum by \u0027ethtool -K ethx tx off\u0027. The FCoE protocol stack driver would\nuse CHECKSUM_UNNECESSARY on tx path instead of CHECKSUM_PARTIAL (as indicated in\nthe 2/2 of this series). To do so, netif_needs_gso() has to be changed here to\nnot do gso for both CHECKSUM_PARTIAL and CHECKSUM_UNNECESSARY.\n\nRef. to original discussion thread:\nhttp://patchwork.ozlabs.org/patch/146567/\n\nSigned-off-by: Yi Zou \u003cyi.zou@intel.com\u003e\nTested-by: Ross Brattain \u003cross.b.brattain@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8f4a0a3d9f9706da5a9d053fe39854c160250ddc", "tree": "1e7c4af740002a3d0ee2a5982b27cdeb1d18f13b", "parents": [ "da24e906cbfc08171d24a2b7cf66fad565fdd121" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Fri Mar 16 23:07:34 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 17:37:21 2012 -0400" }, "message": "ixgbe: Fix issues with SR-IOV loopback when flow control is disabled\n\nThis patch allows us to avoid a Tx hang when SR-IOV is enabled. This hang\ncan be triggered by sending small packets at a rate that was triggering Rx\nmissed errors from the adapter while the internal Tx switch and at least\none VF are enabled.\n\nThis was all due to the fact that under heavy stress the Rx FIFO never\ndrained below the flow control high water mark. This resulted in the Tx\nFIFO being head of line blocked due to the fact that it relies on the flow\ncontrol high water mark to determine when it is acceptable for the Tx to\nplace a packet in the Rx FIFO.\n\nThe resolution for this is to set the FCRTH value to the RXPBSIZE - 32 so\nthat even if the ring is almost completely full we can still place Tx\npackets on the Rx ring and drop incoming Rx traffic if we do not have\nsufficient space available in the Rx FIFO.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Sibai Li \u003csibai.li@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "da24e906cbfc08171d24a2b7cf66fad565fdd121", "tree": "4ce4464bb570ed4ff67298b724ef676000e4b08a", "parents": [ "f24fd89ab5148d00f58aaf1d8999e9966fc7215c" ], "author": { "name": "Haiyang Zhang", "email": "haiyangz@microsoft.com", "time": "Mon Mar 19 17:27:06 2012 -0400" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 17:27:06 2012 -0400" }, "message": "net/hyperv: Fix the code handling tx busy\n\nInstead of dropping the packet, we keep the skb buffer, and return\nNETDEV_TX_BUSY to let upper layer retry send. This will not cause\nendless loop, because the host is taking data away from ring buffer,\nand we have called the stop_queue before returning NETDEV_TX_BUSY.\n\nThe stop_queue was called in the function netvsc_send() in file \nnetvsc.c, then it returns to rndis_filter_send(), which returns to\nnetvsc_start_xmit() in file netvsc_drv.c. So the NETDEV_TX_BUSY is\nindeed returned AFTER queue is stopped.\n\nSigned-off-by: Haiyang Zhang \u003chaiyangz@microsoft.com\u003e\nReviewed-by: K. Y. Srinivasan \u003ckys@microsoft.com\u003e\nAcked-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f24fd89ab5148d00f58aaf1d8999e9966fc7215c", "tree": "63497b88c2fcaf49fa5dc21a33e5ce35d30dede6", "parents": [ "fb04121417b32329f92a260b490da8434d704e3d", "8af3c33f4dab8c20c0a0eb1a7e00d2303d7f47eb" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 17:24:27 2012 -0400" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 17:24:27 2012 -0400" }, "message": "Merge branch \u0027master\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next\n" }, { "commit": "8af3c33f4dab8c20c0a0eb1a7e00d2303d7f47eb", "tree": "4213b4f6c0014783cc89d340a04611ed7cfa4e15", "parents": [ "567d2de291b5ddb83654c5e87c14b4c6fa7216ed" ], "author": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Feb 18 07:08:14 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 13:59:11 2012 -0700" }, "message": "ixgbe: fix namespace issues when FCoE/DCB is not enabled\n\nResolve namespace issues when FCoE or DCB is not enabled.\nThe issue is with certain configurations we end up with namespace\nproblems. A simple example:\n\nixgbe_main.c\n - defines func A()\n - uses func A()\n\nixgbe_fcoe.c\n - uses func A()\n\nixgbe.h\n - has prototype for func A()\n\nFor default (FCoE included) all is good. But when it isn\u0027t the namespace\nchecker complains about how func A() could be static.\n\nTo resolve this, created a ixgbe_lib file to contain functions used\nby DCB/FCoE and their helper functions so that they are always in\nnamespace whether or not DCB/FCoE is enabled.\n\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\nTested-by: Phil Schmitt \u003cphillip.j.schmitt@intel.com\u003e\n" }, { "commit": "fb04121417b32329f92a260b490da8434d704e3d", "tree": "6118542d17ab7ac3782b790be51bd0850bc4ca2c", "parents": [ "449e39d9d7a889f4467ca7c590390e4a0f610b70" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Sun Mar 18 17:37:59 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:09 2012 -0400" }, "message": "rtlwifi: Remove unused ETH_ADDR_LEN defines\n\nJust neatening.\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "449e39d9d7a889f4467ca7c590390e4a0f610b70", "tree": "0df5da259e3722792160ec88e53a0e080b69e506", "parents": [ "c81f212450e4d85ed1ed3777316e8355caeb3848" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Sun Mar 18 17:37:58 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:08 2012 -0400" }, "message": "igbvf: Use ETH_ALEN\n\nRemove an unnecessary #define and use memcpy\ninstead of a loop to copy an ethernet address.\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c81f212450e4d85ed1ed3777316e8355caeb3848", "tree": "2ccf702e7fde4961519232d9bb57f7db67539d12", "parents": [ "a3f671b3152919e72af261333402c0f1272bdf59" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Sun Mar 18 17:37:57 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:08 2012 -0400" }, "message": "atlx: Use ETH_ALEN\n\nNo need for yet another #define for this.\n\nConvert NODE_ADDRESS_SIZE use to ETH_ALEN and remove #define.\nUse memcpy instead of a loop to copy an address.\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a3f671b3152919e72af261333402c0f1272bdf59", "tree": "4bb2731792b7c312dfb104813784153dc6a96fa6", "parents": [ "c8628155ece363487b57d33441ea0359018c0fa7" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Sun Mar 18 17:37:56 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:08 2012 -0400" }, "message": "if_vlan: Remove VLAN_ETH_ALEN define and the 1 use of it\n\nJust use ETH_ALEN.\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c8628155ece363487b57d33441ea0359018c0fa7", "tree": "a3a4e89d3f66208f4145bb2ed401e464474a8d9f", "parents": [ "e86b291962cbf477e35d983d312428cf737bc0f8" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Sun Mar 18 11:07:47 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:08 2012 -0400" }, "message": "tcp: reduce out_of_order memory use\n\nWith increasing receive window sizes, but speed of light not improved\nthat much, out of order queue can contain a huge number of skbs, waiting\nto be moved to receive_queue when missing packets can fill the holes.\n\nSome devices happen to use fat skbs (truesize of 4096 + sizeof(struct\nsk_buff)) to store regular (MTU \u003c\u003d 1500) frames. This makes highly\nprobable sk_rmem_alloc hits sk_rcvbuf limit, which can be 4Mbytes in\nmany cases.\n\nWhen limit is hit, tcp stack calls tcp_collapse_ofo_queue(), a true\nlatency killer and cpu cache blower.\n\nDoing the coalescing attempt each time we add a frame in ofo queue\npermits to keep memory use tight and in many cases avoid the\ntcp_collapse() thing later.\n\nTested on various wireless setups (b43, ath9k, ...) known to use big skb\ntruesize, this patch removed the \"packets collapsed in receive queue due\nto low socket buffer\" I had before.\n\nThis also reduced average memory used by tcp sockets.\n\nWith help from Neal Cardwell.\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: Neal Cardwell \u003cncardwell@google.com\u003e\nCc: Yuchung Cheng \u003cycheng@google.com\u003e\nCc: H.K. Jerry Chu \u003chkchu@google.com\u003e\nCc: Tom Herbert \u003ctherbert@google.com\u003e\nCc: Ilpo Järvinen \u003cilpo.jarvinen@helsinki.fi\u003e\nAcked-by: Neal Cardwell \u003cncardwell@google.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e86b291962cbf477e35d983d312428cf737bc0f8", "tree": "11520ec988be8644df08684004512c35881e21b5", "parents": [ "de1288041d01120559d53ebd98e0f92476ee56d3" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Sun Mar 18 11:06:44 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:07 2012 -0400" }, "message": "tcp: introduce tcp_data_queue_ofo\n\nSplit tcp_data_queue() in two parts for better readability.\n\ntcp_data_queue_ofo() is responsible for queueing incoming skb into out\nof order queue.\n\nChange code layout so that the skb_set_owner_r() is performed only if\nskb is not dropped.\n\nThis is a preliminary patch before \"reduce out_of_order memory use\"\nfollowing patch.\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: Neal Cardwell \u003cncardwell@google.com\u003e\nCc: Yuchung Cheng \u003cycheng@google.com\u003e\nCc: H.K. Jerry Chu \u003chkchu@google.com\u003e\nCc: Tom Herbert \u003ctherbert@google.com\u003e\nCc: Ilpo Järvinen \u003cilpo.jarvinen@helsinki.fi\u003e\nAcked-by: Neal Cardwell \u003cncardwell@google.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "de1288041d01120559d53ebd98e0f92476ee56d3", "tree": "564ff51d2be23eb4f1c9d5d008538af245767d22", "parents": [ "cb4dca277694f6c53bf6daf0f5c609dda32e4656" ], "author": { "name": "Dmitry Kravkov", "email": "dmitry@broadcom.com", "time": "Sun Mar 18 10:33:45 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:07 2012 -0400" }, "message": "bnx2x: validate FW trace prior to its printing\n\nSigned-off-by: Dmitry Kravkov \u003cdmitry@broadcom.com\u003e\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: Eilon Greenstein \u003ceilong@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cb4dca277694f6c53bf6daf0f5c609dda32e4656", "tree": "8fc3b86f357d9fd3e8b591582cb058ce2117daf1", "parents": [ "9e62e912e56742af7eb7e0eeba3c7af4bb2f8537" ], "author": { "name": "Yuval Mintz", "email": "yuvalmin@broadcom.com", "time": "Sun Mar 18 10:33:44 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:07 2012 -0400" }, "message": "bnx2x: consistent statistics for old FW\n\nPreviously applied patch making the bnx2x statistics consistent\ndid not apply to old FWs. This remedies it, extending the consistent\nbehaviour to all drivers.\n\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: Eilon Greenstein \u003ceilong@broadcom.com\u003e\nReported-by: Michal Schmidt \u003cmschmidt@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9e62e912e56742af7eb7e0eeba3c7af4bb2f8537", "tree": "ad3f5843da71faccdf633dc8011e7dc647593da8", "parents": [ "910b220290a4568ebf7ecc368bd3d1d8236d2335" ], "author": { "name": "Dmitry Kravkov", "email": "dmitry@broadcom.com", "time": "Sun Mar 18 10:33:43 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:07 2012 -0400" }, "message": "bnx2x: changed iscsi/fcoe mac init and macros\n\nThis includes changes in macros to better distinguish between the two\nprotocols, and slightly changed the way their macs are set.\nNotice this file contains string print lines with more than 80 characters,\nas to not break prints.\n\nSigned-off-by: Dmitry Kravkov \u003cdmitry@broadcom.com\u003e\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: Eilon Greenstein \u003ceilong@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "910b220290a4568ebf7ecc368bd3d1d8236d2335", "tree": "01ee654920ce1e7cb1dd516e6328ad86b2716229", "parents": [ "9d4884f9d470cd696d7a7cd7a6d7099d13909dd9" ], "author": { "name": "Dmitry Kravkov", "email": "dmitry@broadcom.com", "time": "Sun Mar 18 10:33:42 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:07 2012 -0400" }, "message": "bnx2x: added TLV_NOT_FOUND flags to the dcb\n\nThe new error flags are supported by the bnx2x FW.\n\nSigned-off-by: Dmitry Kravkov \u003cdmitry@broadcom.com\u003e\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: Eilon Greenstein \u003ceilong@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9d4884f9d470cd696d7a7cd7a6d7099d13909dd9", "tree": "46eb42d9025535e2ddcf7ec04466c74dfb6d0b27", "parents": [ "c315a4ef55b9afa0373fbb10f8567d59f81247c9" ], "author": { "name": "Dmitry Kravkov", "email": "dmitry@broadcom.com", "time": "Sun Mar 18 10:33:41 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:07 2012 -0400" }, "message": "bnx2x: changed initial dcb configuration\n\nThe changes were mostly made to enable back-to-back data flow with dcb.\nOther changes were simply deemed as a better \u0027clean\u0027 initial configuration.\n\nSigned-off-by: Dmitry Kravkov \u003cdmitry@broadcom.com\u003e\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c315a4ef55b9afa0373fbb10f8567d59f81247c9", "tree": "ce173ae34f969b2b452ae911122120ab9643c5c2", "parents": [ "3b60306690569927951be09160e80a8af9c94db4" ], "author": { "name": "Yuval Mintz", "email": "yuvalmin@broadcom.com", "time": "Sun Mar 18 10:33:40 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:07 2012 -0400" }, "message": "bnx2x: removed dcb unused code\n\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: Eilon Greenstein \u003ceilong@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3b60306690569927951be09160e80a8af9c94db4", "tree": "e6d1c2207f954c1375573964c245ed0ff5de82a5", "parents": [ "51c1a580b1e07d58eb063f9f4a70aea8ad32fe23" ], "author": { "name": "Yuval Mintz", "email": "yuvalmin@broadcom.com", "time": "Sun Mar 18 10:33:39 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:53:06 2012 -0400" }, "message": "bnx2x: reduced sparse warnings\n\nThis patch reduces sparse warnings in the bnx2x code,\nmostly by changing functions into static and changing\ninitialization of structures.\n\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: Eilon Greenstein \u003ceilong@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "51c1a580b1e07d58eb063f9f4a70aea8ad32fe23", "tree": "83243fae1f89d3b705117a8f609bc427eb389c98", "parents": [ "d8290ae54c88cab9f199a84125bd5fda9f48b032" ], "author": { "name": "Merav Sicron", "email": "meravs@broadcom.com", "time": "Sun Mar 18 10:33:38 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:52:48 2012 -0400" }, "message": "bnx2x: revised driver prints\n\nWe\u0027ve revised driver prints, changing the mask of existing prints\nto allow better control over the debug messages, added prints to\nerror scenarios, removed unnecessary prints and corrected some spelling.\nPlease note that this patch contains lines with over 80 characters,\nas string messages were kept in a single line.\n\nSigned-off-by: Merav Sicron \u003cmeravs@broadcom.com\u003e\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: Eilon Greenstein \u003ceilong@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d8290ae54c88cab9f199a84125bd5fda9f48b032", "tree": "366d526d28ff3b9702ce6820bf9bc7a48a6d3888", "parents": [ "f1f3ee1bcc996e21f122442fd8c34de51622c76a" ], "author": { "name": "Yuval Mintz", "email": "yuvalmin@broadcom.com", "time": "Sun Mar 18 10:33:37 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:52:18 2012 -0400" }, "message": "bnx2x: added \u0027likely\u0027 to fast-path skb existence\n\nSigned-off-by: Yuval Mintz \u003cyuvalmin@broadcom.com\u003e\nSigned-off-by: Eilon Greenstein \u003ceilong@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f1f3ee1bcc996e21f122442fd8c34de51622c76a", "tree": "dd7dadc565c33a09133a46dfd2ec5ac1ecee6d6e", "parents": [ "456d9c962bb5824423fa93277c8f7f5b2e3d5e1c" ], "author": { "name": "Ajit Khaparde", "email": "ajit.khaparde@emulex.com", "time": "Sun Mar 18 06:23:41 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:52:17 2012 -0400" }, "message": "be2net: fix programming of VLAN tags for VF\n\nSigned-off-by: Ajit Khaparde \u003cajit.khaparde@emulex.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "456d9c962bb5824423fa93277c8f7f5b2e3d5e1c", "tree": "bc581c70dfcdf26c91efeea86eb0d594977f9c98", "parents": [ "fbc13f018c0043146f8eccc7d6a6c0e66339e2d5" ], "author": { "name": "Ajit Khaparde", "email": "ajit.khaparde@emulex.com", "time": "Sun Mar 18 06:23:31 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:52:17 2012 -0400" }, "message": "be2net: Fix number of vlan slots in flex mode\n\nIn flex10 mode the number of vlan slots supported is halved.\n\nSigned-off-by: Ajit Khaparde \u003cajit.khaparde@emulex.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fbc13f018c0043146f8eccc7d6a6c0e66339e2d5", "tree": "6b4a162c091dbd8f0757c68a07cecd314779a239", "parents": [ "4762f6cec4455f3bbe4ca82c100fe5d85d3c02a2" ], "author": { "name": "Ajit Khaparde", "email": "ajit.khaparde@emulex.com", "time": "Sun Mar 18 06:23:21 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:52:17 2012 -0400" }, "message": "be2net: Program secondary UC MAC address into MAC filter\n\nSigned-off-by: Ajit Khaparde \u003cajit.khaparde@emulex.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4762f6cec4455f3bbe4ca82c100fe5d85d3c02a2", "tree": "51cf21b4a949b8a3292019f81447d8a9a719d7e3", "parents": [ "277074777cd9c004b1ac32689772370c38fd00e2" ], "author": { "name": "Ajit Khaparde", "email": "ajit.khaparde@emulex.com", "time": "Sun Mar 18 06:23:11 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:52:17 2012 -0400" }, "message": "be2net: enable WOL by default if h/w supports it\n\nSigned-off-by: Ajit Khaparde \u003cajit.khaparde@emulex.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "277074777cd9c004b1ac32689772370c38fd00e2", "tree": "c8a1e7586cc9b16bcd662db6735acca6b9c5c558", "parents": [ "4da0bd736552e6377b407b3c3d3ae518ebbdd269", "5407b14c6792d6ff122ecb1a2a6acffad60ef389" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:46:22 2012 -0400" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 19 16:46:22 2012 -0400" }, "message": "Merge branch \u0027gianfar-bql\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux\n" }, { "commit": "567d2de291b5ddb83654c5e87c14b4c6fa7216ed", "tree": "db6880b7bf8ced1a59c1ea47d60ae22408292914", "parents": [ "ef6afc0caceebb3b49cd384f8c634f89f5089997" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Sat Feb 11 07:18:57 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 13:43:34 2012 -0700" }, "message": "ixgbe: Correct flag values set by ixgbe_fix_features\n\nThis patch replaces the variable name data with the variable name features\nfor ixgbe_fix_features and ixgbe_set_features. This helps to make some\nissues more obvious such as the fact that we were disabling Rx VLAN tag\nstripping when we should have been forcing it to be enabled when DCB is\nenabled.\n\nIn addition there was deprecated code present that was disabling the LRO\nflag if we had the itr value set too low. I have updated this logic so\nthat we will now allow the LRO flag to be set, but will not enable RSC\nuntil the rx-usecs value is high enough to allow enough time for Rx packet\ncoalescing.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "ef6afc0caceebb3b49cd384f8c634f89f5089997", "tree": "fd95d484357deca295bad8ab978e8a5d137590c8", "parents": [ "581330ba7b219fec0587452bd72fe5635c30c4ae" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:53 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 02:03:15 2012 -0700" }, "message": "ixgbe: Add support for enabling UDP RSS via the ethtool rx-flow-hash command\n\nThis patch adds support for enabling or disabling UDP RSS via the\nethtool -N rx-flow-hash command.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "581330ba7b219fec0587452bd72fe5635c30c4ae", "tree": "e0a516ba9a16b7a7356aadfc0493bc447d63e8e9", "parents": [ "6ca435078822d9728318dee49ba4f2ff8a2ead24" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:47 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 02:02:21 2012 -0700" }, "message": "ixgbe: Whitespace cleanups\n\nThis patch contains several fixes for formatting in regards to whitespace.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Phil Schmitt \u003cphillip.j.schmitt@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "6ca435078822d9728318dee49ba4f2ff8a2ead24", "tree": "e4ebabd2d72aa67f49546fac32c025b1654739db", "parents": [ "35937c055a691a125cf52343cd671f6190ae5b3b" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:42 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 02:01:28 2012 -0700" }, "message": "ixgbe: Two minor fixes for RSS and FDIR set queues functions\n\nThis change fixes two minor issues. The first was the fact that we were\nsetting the return value to false twice in the set_rss_queues function.\nThe second is the fact that we should have been using \"min_t(int,\" instead\nof \"min((int)\" in set_fdir_queues.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "35937c055a691a125cf52343cd671f6190ae5b3b", "tree": "b3be16e0db98e8679b9f0dd8c5fbfc72ee6ee9cd", "parents": [ "eb01b9759e733c0ede11d35e3cde5b3c24ab32c9" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:37 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 02:00:32 2012 -0700" }, "message": "ixgbe: drop err_eeprom tag which is at same location as err_sw_init\n\nThe err_eeprom and err_sw_init tags both go to the same location. So\ninstead of maintaining two tags this patch combines them so we only use\nerr_sw_init.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "eb01b9759e733c0ede11d35e3cde5b3c24ab32c9", "tree": "11211eb5b108b24fd4ae47caa8175c64ae500430", "parents": [ "6bb78cfb50bfbaf90646a80448ee8de2372e292a" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:27 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 01:58:58 2012 -0700" }, "message": "ixgbe: Move poll routine in order to improve readability\n\nThis change relocates the ixgbe_poll routine so it is right next to the\ninterrupt routine that schedules and calls it.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "6bb78cfb50bfbaf90646a80448ee8de2372e292a", "tree": "5258daf5977698179a4fd8c7362a8728c7ccb5ff", "parents": [ "d3ee42944393895374e2f321f54e9a701e9f965c" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:22 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 01:57:23 2012 -0700" }, "message": "ixgbe: cleanup logic for the service timer and VF hang detection\n\nThis change just cleans up some of the logic in the service_timer function\nso that we can avoid unnecessary swapping of the ready value between true to\nfalse and back to true.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "d3ee42944393895374e2f321f54e9a701e9f965c", "tree": "a281e0308cd66eddce36d7958f935059ca1358d6", "parents": [ "244e27ad4d9e561c688c4da3383fec890be832d0" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:16 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 01:54:36 2012 -0700" }, "message": "ixgbe: Update layout of ixgbe_ring structure to improve cache performance\n\nThis change makes it so that only the 2nd cache line in the ring structure\nshould see frequent updates. The advantage to this is that it should\nreduce the amount of cross CPU cache bouncing since only the 2nd cache line\nwill be changing between most network transactions.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "244e27ad4d9e561c688c4da3383fec890be832d0", "tree": "7a9c91b3341783ee7054c2d7f9b0febb66b7fdcc", "parents": [ "4da0bd736552e6377b407b3c3d3ae518ebbdd269" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:11 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Mar 19 01:38:42 2012 -0700" }, "message": "ixgbe: Store Tx flags and protocol information to tx_buffer sooner\n\nThis change makes it so that we store the tx_flags and protocol information\nto the tx_buffer_info structure sooner. This allows us to avoid unnecessary\nread/write transactions since we are placing the data in the final location\nearlier.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "4da0bd736552e6377b407b3c3d3ae518ebbdd269", "tree": "f0da9f843b8033565c3ca4103fccb17a60688326", "parents": [ "81a430ac1b88b0702c57d2513e247317e810e04d", "c16fa4f2ad19908a47c63d8fa436a1178438c7e7" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Mar 18 23:29:41 2012 -0400" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Mar 18 23:29:41 2012 -0400" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net\n" }, { "commit": "c16fa4f2ad19908a47c63d8fa436a1178438c7e7", "tree": "0f06ac618a5b12cfd11088fbc8c541e6012fbf5f", "parents": [ "93dc6107a76daed81c07f50215fa6ae77691634f" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Mar 18 16:15:34 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Mar 18 16:15:34 2012 -0700" }, "message": "Linux 3.3\n" }, { "commit": "5407b14c6792d6ff122ecb1a2a6acffad60ef389", "tree": "f405e986ed2b718f3a3bae81cd50bbe5b18f5b53", "parents": [ "1571df8f2d470a2b0cb3d48ffdffbc83c5924ef5" ], "author": { "name": "Paul Gortmaker", "email": "paul.gortmaker@windriver.com", "time": "Sun Mar 18 17:11:22 2012 -0400" }, "committer": { "name": "Paul Gortmaker", "email": "paul.gortmaker@windriver.com", "time": "Sun Mar 18 17:11:22 2012 -0400" }, "message": "gianfar: use netif_tx_queue_stopped instead of __netif_subqueue_stopped\n\nThe __netif_subqueue_stopped() just does the following:\n\n struct netdev_queue *txq \u003d netdev_get_tx_queue(dev, queue_index);\n return netif_tx_queue_stopped(txq);\n\nand since we already have the txq in scope, we can just call that\ndirectly in this case.\n\nSuggested-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: Paul Gortmaker \u003cpaul.gortmaker@windriver.com\u003e\n" }, { "commit": "93dc6107a76daed81c07f50215fa6ae77691634f", "tree": "b104aeb2798f60f06fd9f7abda5ae9ef5219e0bb", "parents": [ "c579bc7e316e7e3f3b56df5e17f623325caa9783" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Fri Mar 16 16:34:03 2012 -0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Mar 18 12:25:04 2012 -0700" }, "message": "Don\u0027t limit non-nested epoll paths\n\nCommit 28d82dc1c4ed (\"epoll: limit paths\") that I did to limit the\nnumber of possible wakeup paths in epoll is causing a few applications\nto longer work (dovecot for one).\n\nThe original patch is really about limiting the amount of epoll nesting\n(since epoll fds can be attached to other fds). Thus, we probably can\nallow an unlimited number of paths of depth 1. My current patch limits\nit at 1000. And enforce the limits on paths that have a greater depth.\n\nThis is captured in: https://bugzilla.redhat.com/show_bug.cgi?id\u003d681578\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c579bc7e316e7e3f3b56df5e17f623325caa9783", "tree": "fd057d71e237552436fb98f4bfb435b5c8e45787", "parents": [ "96ee0499c59810736dc2e56784d061dc6a1d98e8", "a16a1647fa6b6783c2e91623e72e86f0c2adac5e" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 17 19:22:24 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 17 19:22:24 2012 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net\n\nPull networking changes from David Miller:\n \"1) icmp6_dst_alloc() returns NULL instead of ERR_PTR() leading to\n crashes, particularly during shutdown. Reported by Dave Jones and\n fixed by Eric Dumazet.\n\n 2) hyperv and wimax/i2400m return NETDEV_TX_BUSY when they have\n already freed the SKB, which causes crashes as to the caller this\n means requeue the packet. Fixes from Eric Dumazet.\n\n 3) usbnet driver doesn\u0027t allocate the right amount of headroom on\n fresh RX SKBs, fix from Eric Dumazet.\n\n 4) Fix regression in ip6_mc_find_dev_rcu(), as an RCU lookup it\n abolutely should not take a reference to \u0027dev\u0027, this leads to\n leaks. Fix from RonQing Li.\n\n 5) Fix netfilter ctnetlink race between delete and timeout expiration.\n From Pablo Neira Ayuso.\n\n 6) Revert SFQ change which causes regressions, specifically queueing\n to tail can lead to unavoidable flow starvation. From Eric\n Dumazet.\n\n 7) Fix a memory leak and a crash on corrupt firmware files in bnx2x,\n from Michal Schmidt.\"\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:\n netfilter: ctnetlink: fix race between delete and timeout expiration\n ipv6: Don\u0027t dev_hold(dev) in ip6_mc_find_dev_rcu.\n wimax/i2400m: fix erroneous NETDEV_TX_BUSY use\n net/hyperv: fix erroneous NETDEV_TX_BUSY use\n net/usbnet: reserve headroom on rx skbs\n bnx2x: fix memory leak in bnx2x_init_firmware()\n bnx2x: fix a crash on corrupt firmware file\n sch_sfq: revert dont put new flow at the end of flows\n ipv6: fix icmp6_dst_alloc()\n" }, { "commit": "96ee0499c59810736dc2e56784d061dc6a1d98e8", "tree": "ee558fa2917f7331ba9bed30ee49977418d6e141", "parents": [ "cb1ecf25a84aec8c9d1fc6ad0c78adf4fd8335de", "89c5bd08df5841326abbf167d136bcf14cf759ed" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 17 09:54:16 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 17 09:54:16 2012 -0700" }, "message": "Merge branch \u0027perf-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip\n\nPull perf fixes from Ingo Molnar.\n\n* \u0027perf-urgent-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:\n perf tools, x86: Build perf on older user-space as well\n perf tools: Use scnprintf where applicable\n perf tools: Incorrect use of snprintf results in SEGV\n" }, { "commit": "81a430ac1b88b0702c57d2513e247317e810e04d", "tree": "5d4b825c9b568b569833ec72cc5cbf43e1e6031c", "parents": [ "c2ec3ff6b8712f5d951927d7774c805fe3270caa", "729739b754affa482e92fa7836e4066096089d11" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Mar 17 02:02:26 2012 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Mar 17 02:02:26 2012 -0700" }, "message": "Merge branch \u0027master\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next\n" }, { "commit": "a16a1647fa6b6783c2e91623e72e86f0c2adac5e", "tree": "949b73345b860aec586d67243eab4a9944a158ad", "parents": [ "c577923756b7fe9071f28a76b66b83b306d1d001" ], "author": { "name": "Pablo Neira Ayuso", "email": "pablo@netfilter.org", "time": "Fri Mar 16 02:00:34 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Mar 17 01:47:08 2012 -0700" }, "message": "netfilter: ctnetlink: fix race between delete and timeout expiration\n\nKerin Millar reported hardlockups while running `conntrackd -c\u0027\nin a busy firewall. That system (with several processors) was\nacting as backup in a primary-backup setup.\n\nAfter several tries, I found a race condition between the deletion\noperation of ctnetlink and timeout expiration. This patch fixes\nthis problem.\n\nTested-by: Kerin Millar \u003ckerframil@gmail.com\u003e\nReported-by: Kerin Millar \u003ckerframil@gmail.com\u003e\nSigned-off-by: Pablo Neira Ayuso \u003cpablo@netfilter.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "729739b754affa482e92fa7836e4066096089d11", "tree": "878a830a30731a5c64559ecb95caa115a524b799", "parents": [ "091a6246869cec2ac66e897b436f7fd59ec4d316" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:06 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:41:49 2012 -0700" }, "message": "ixgbe: always write DMA for single_mapped value with skb\n\nThis change makes it so that we always write the DMA address for the skb\nitself on the same tx_buffer struct that the skb is written on. This way\nwe don\u0027t need the MAPPED_AS_PAGE flag and we always know it will be the\nfirst DMA value that we will have to unmap.\n\nIn addition I have found an issue in which we were leaking a DMA mapping if\nthe value happened to be 0 which is possible on some platforms. In order\nto resolve that I have updated the transmit path to use the length instead\nof the DMA mapping in order to determine if a mapping is actually present.\n\nOne other tweak in this patch is that it only writes the olinfo information\non the first descriptor. As it turns out it isn\u0027t necessary to write it\nfor anything but the first descriptor so there is no need to carry it\nforward.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "c2ec3ff6b8712f5d951927d7774c805fe3270caa", "tree": "99245281ae8c686cf6ee5b63dd6e387d2748c7a5", "parents": [ "126a3fd251b244eabd9ab9dcb32b8b6f999c1b91" ], "author": { "name": "Richard Cochran", "email": "richardcochran@gmail.com", "time": "Fri Mar 16 22:39:29 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Mar 17 01:41:43 2012 -0700" }, "message": "phc: Update author\u0027s email address.\n\nThis commit brings the author email address macros up to date for four\nmodules in the PTP Hardware Clock subsystem.\n\nSigned-off-by: Richard Cochran \u003crichardcochran@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "091a6246869cec2ac66e897b436f7fd59ec4d316", "tree": "11bfc09e746e5bbe953e81410071e291c718a991", "parents": [ "fd0db0ed02a6abce5427e90d1e8522322107d62b" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:51:01 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:08:29 2012 -0700" }, "message": "ixgbe: Write gso_segs and bytcount to the ring sooner\n\nThis change makes it so that gso_segs and bytecount are written to the ring\nsooner. This helps to simplify the logic for the two since segmentation\noffloads can now update them within their own function.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "fd0db0ed02a6abce5427e90d1e8522322107d62b", "tree": "0fa1df643c68e44d7c0a77e67a67d6e72526e57a", "parents": [ "7d7ce682f8437ff91c964c478b8845ed98a3207d" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:50:56 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:08:23 2012 -0700" }, "message": "ixgbe: Place skb on first buffer_info structure to avoid using stack space\n\nInstead of keeping a local copy of the skb on the stack for as long as long\nas we do it makes sense to instead just place it on the first tx_buffer\nstructure so that we can save space on the stack and avoid unnecessary\nread/write operations copying the pointer out of the stack and onto the\nring later.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "7d7ce682f8437ff91c964c478b8845ed98a3207d", "tree": "573e92106b0372a9cf7c9dcc79de5ff1f6908f79", "parents": [ "93f5b3c1f148f2cca247a2c5afdd3ba7a123a6f1" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:50:51 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:06:59 2012 -0700" }, "message": "ixgbe: Use packets to track Tx completions instead of a seperate value\n\nA separate value was added to track Tx completions in order to determine if\nthe Tx unit was hung. However we can do the same thing using the number of\npackets completed without having to add another stat to the Tx ring.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "93f5b3c1f148f2cca247a2c5afdd3ba7a123a6f1", "tree": "e611dafd4a29f99596630b771069ce39509cc5db", "parents": [ "a50c29dd09ed14f8489677813a4b1c8b62dcf19d" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:50:45 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:06:53 2012 -0700" }, "message": "ixgbe: Modify setup of descriptor flags to avoid conditional jumps\n\nThis change makes it more likely that the descriptor flags setup will use\ncmov instructions instead of conditional jumps when setting up the flags.\nThe advantage to this is that the code should just flow a bit more\nsmoothly.\n\nTo do this it is necessary to set the TX_FLAGS_CSUM bit in tx_flags when\ndoing TSO so that we also do the checksum in addition to the segmentation\noffload.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "a50c29dd09ed14f8489677813a4b1c8b62dcf19d", "tree": "45d28e67b4fd04ce6df4c9c974d51d14a28f92d3", "parents": [ "655309e944fd482e59850d55186571c1b2a91e55" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:50:40 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:06:47 2012 -0700" }, "message": "ixgbe: Make certain that all frames fit minimum size requirements\n\nThis change makes certain that any packet we attempt to transmit will meet\nminimum size requirements for the hardware.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "655309e944fd482e59850d55186571c1b2a91e55", "tree": "80c5bb8a37188aebe3378b10a8b9059045aaee43", "parents": [ "f800326dca7bc158f4c886aa92f222de37993c80" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Feb 08 07:50:35 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:04:33 2012 -0700" }, "message": "ixgbe: cleanup logic in ixgbe_change_mtu\n\nThis change is meant to just cleanup the logic in ixgbe_change_mtu since we\nare making it unnecessarily complex due to a workaround required for 82599\nwhen SR-IOV is enabled.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "f800326dca7bc158f4c886aa92f222de37993c80", "tree": "25bd55b82e32633dd24af9166a1e255d1899606d", "parents": [ "3f2d1c0f57c6bfad7aacc249fca3514e98a94137" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Sat Mar 03 02:35:52 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:04:27 2012 -0700" }, "message": "ixgbe: Replace standard receive path with a page based receive\n\nThis patch replaces the existing Rx hot-path in the ixgbe driver with a new\nimplementation that is based on performing a double buffered receive. The\nixgbe driver already had something similar in place for its\u0027 packet split\npath, however in that case we were still receiving the header for the\npacket into the sk_buff. The big change here is the entire receive path\nwill receive into pages only, and then pull the header out of the page and\ncopy it into the sk_buff data. There are several motivations behind this\napproach.\n\nFirst, this allows us to avoid several cache misses as we were taking a\nset of cache misses for allocating the sk_buff and then another set for\nreceiving data into the sk_buff. We are able to avoid these misses on\nreceive now as we allocate the sk_buff when data is available.\n\nSecond we are able to see a considerable performance gain when an IOMMU is\nenabled because we are no longer unmapping every buffer on receive.\nInstead we can delay the unmap until we are unable to use the page, and\ninstead we can simply call sync_single_range on the half of the page that\ncontains new data.\n\nFinally we are able to drop a considerable amount of code from the driver\nas we no longer have to support 2 different receive modes, packet split and\none buffer. This allows us to optimize the Rx path further since less\nbranching is required.\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nTested-by: Ross Brattain \u003cross.b.brattain@intel.com\u003e\nTested-by: Stephen Ko \u003cstephen.s.ko@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "3f2d1c0f57c6bfad7aacc249fca3514e98a94137", "tree": "b58b949e48170ede6bad45272ea5c786dd42c9ca", "parents": [ "f43f313eb7c5f189ff4e27da6cc96ad2e613e333" ], "author": { "name": "Ben Greear", "email": "greearb@candelatech.com", "time": "Thu Mar 08 08:28:41 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:03:22 2012 -0700" }, "message": "ixgbe: Support RX-ALL feature flag.\n\nThis allows the NIC to receive all frames available, including\nthose with bad FCS, ethernet control frames, and more.\n\nTested by sending frames with bad FCS.\n\nSigned-off-by: Ben Greear \u003cgreearb@candelatech.com\u003e\nTested-by: Jeff Pieper \u003cjeffrey.e.pieper@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "f43f313eb7c5f189ff4e27da6cc96ad2e613e333", "tree": "f7d73bc23abb91af9c19fc125cf779c91b4e732e", "parents": [ "89eaefb61dc9170237d95b844dd357338fc7225d" ], "author": { "name": "Ben Greear", "email": "greearb@candelatech.com", "time": "Tue Mar 06 09:42:04 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:03:16 2012 -0700" }, "message": "ixgbe: Support sending custom Ethernet FCS.\n\nIncluding bad FCS, used generate frames with bad FCS\nto test other system\u0027s handling of RX of bad packets.\n\nSigned-off-by: Ben Greear \u003cgreearb@candelatech.com\u003e\nTested-by: Jeff Pieper \u003cjeffrey.e.pieper@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "89eaefb61dc9170237d95b844dd357338fc7225d", "tree": "6c921a7344a7bcf7dd26975c978ff4626ebd8e01", "parents": [ "6b8f092284672c6504ed215052bfee6b7171411e" ], "author": { "name": "Ben Greear", "email": "greearb@candelatech.com", "time": "Tue Mar 06 09:41:58 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:02:26 2012 -0700" }, "message": "igb: Support RX-ALL feature flag.\n\nThis allows the NIC to receive all frames available, including\nthose with bad FCS, un-matched vlans, ethernet control frames,\nand more.\n\nTested by sending frames with bad FCS.\n\nSigned-off-by: Ben Greear \u003cgreearb@candelatech.com\u003e\nTested-by: Jeff Pieper \u003cjeffrey.e.pieper@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "6b8f092284672c6504ed215052bfee6b7171411e", "tree": "b7013b75a77dfd1670986960bb2e019d0ed7a40f", "parents": [ "126a3fd251b244eabd9ab9dcb32b8b6f999c1b91" ], "author": { "name": "Ben Greear", "email": "greearb@candelatech.com", "time": "Tue Mar 06 09:41:53 2012 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sat Mar 17 01:02:20 2012 -0700" }, "message": "igb: Support sending custom Ethernet FCS.\n\nIncluding bad FCS, used generate frames with bad FCS\nto test other system\u0027s handling of RX of bad packets.\n\nSigned-off-by: Ben Greear \u003cgreearb@candelatech.com\u003e\nTested-by: Jeff Pieper \u003cjeffrey.e.pieper@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "126a3fd251b244eabd9ab9dcb32b8b6f999c1b91", "tree": "db496f9ba4536215e9be58745565a426c090aebb", "parents": [ "4823cd388dd68015e254d1449bd63ffe47d83fa7" ], "author": { "name": "françois romieu", "email": "romieu@fr.zoreil.com", "time": "Fri Mar 16 01:52:04 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Mar 16 23:13:20 2012 -0700" }, "message": "eni: fix driver remove function and driver probe error path.\n\n- add eni_do_release() to balance eni_do_init\n- turn the zeroes DMA area into a per device data\n\nSigned-off-by: Francois Romieu \u003cromieu@fr.zoreil.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4823cd388dd68015e254d1449bd63ffe47d83fa7", "tree": "6e027801b3dab713afd5fa8cd76374436e91347c", "parents": [ "124d37e9f088a8f56494b0264d63d22555f53fef" ], "author": { "name": "Philipp Zabel", "email": "philipp.zabel@gmail.com", "time": "Thu Mar 15 08:19:29 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Mar 16 23:11:14 2012 -0700" }, "message": "net/irda: add clk_prepare/clk_unprepare to pxaficp_ir\n\nThis patch adds clk_prepare/clk_unprepare calls to the pxaficp_ir\ndriver by using the helper functions clk_prepare_enable and\nclk_disable_unprepare.\n\nSigned-off-by: Philipp Zabel \u003cphilipp.zabel@gmail.com\u003e\nCc: Eric Miao \u003ceric.y.miao@gmail.com\u003e\nCc: Haojian Zhuang \u003chaojian.zhuang@marvell.com\u003e\nCc: Samuel Ortiz \u003csamuel@sortiz.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "124d37e9f088a8f56494b0264d63d22555f53fef", "tree": "372cf065963b109c0df78964ec196488a570eba5", "parents": [ "1aa9bc5b2f4cf8c48944fb9a607bf1dd674e2c10" ], "author": { "name": "Neil Horman", "email": "nhorman@tuxdriver.com", "time": "Thu Mar 15 05:25:58 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Mar 16 23:00:20 2012 -0700" }, "message": "arp: allow arp processing to honor per interface arp_accept sysctl\n\nI found recently that the arp_process function which handles all of our received\narp frames, is using IPV4_DEVCONF_ALL macro to check the state of the arp_process\nflag. This seems wrong, as it implies that either none or all of the network\ninterfaces accept gratuitous arps. This patch corrects that, allowing\nper-interface arp_accept configuration to deviate from the all setting. Note\nthis also brings us into line with the way the arp_filter setting is handled\nduring arp_process execution.\n\nTested this myself on my home network, and confirmed it works as expected.\n\nSigned-off-by: Neil Horman \u003cnhorman@tuxdriver.com\u003e\nCC: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1aa9bc5b2f4cf8c48944fb9a607bf1dd674e2c10", "tree": "8ccaee8f80b2db29d52554333af82711bf1a5f0b", "parents": [ "6a228452d11eaf1f1577261540ec0903a2af7f61" ], "author": { "name": "Alexey Orishko", "email": "alexey.orishko@gmail.com", "time": "Wed Mar 14 04:00:24 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Mar 16 22:50:19 2012 -0700" }, "message": "usbnet: use netif_tx_wake_queue instead of netif_start_queue\n\nIf host is going to autosuspend function with two interfaces and\nif IP packet has arrived in-between of two usbnet_suspend() callbacks,\ni.e usbnet_resume() is called in-between, tx data flow is stopped.\nWhen autosuspend timer expires and device is put to autosuspend\nagain, tx queue is waked up and data can be sent again.\nThis behavior might be repeated several times in a row.\n\nTested on Intel/ARM.\n\nReviewed-by: Sjur Brændeland \u003csjur.brandeland@stericsson.com\u003e\nTested-by: Dmitry Tarnyagin \u003cdmitry.tarnyagin@stericsson.com\u003e\nSigned-off-by: Alexey Orishko \u003calexey.orishko@stericsson.com\u003e\nAcked-by: Oliver Neukum \u003coneukum@suse.de\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6a228452d11eaf1f1577261540ec0903a2af7f61", "tree": "9e08f1ba22948df7f09c0f2f6d4d6c7fa3d55871", "parents": [ "06d6c1087605b38342eb20e74b0cacb8b71f5086" ], "author": { "name": "Stefan Roese", "email": "sr@denx.de", "time": "Tue Mar 13 04:56:37 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Mar 16 22:48:53 2012 -0700" }, "message": "stmmac: Add device-tree support\n\nThis patch adds support to configure the STMMAC ethernet driver via\ndevice-tree instead of platform_data.\n\nCurrently, only the properties needed on SPEAr600 are provided. All\nother properties should be added once needed on other platforms.\n\nSigned-off-by: Stefan Roese \u003csr@denx.de\u003e\nCc: Giuseppe Cavallaro \u003cpeppe.cavallaro@st.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "06d6c1087605b38342eb20e74b0cacb8b71f5086", "tree": "57533b01a509a7d79c264400ceac83aaba80e5b7", "parents": [ "50cdc8fc4007cf773cad710186d253612b83cc72" ], "author": { "name": "Santosh Nayak", "email": "santoshprasadnayak@gmail.com", "time": "Mon Mar 12 22:58:24 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Mar 16 22:20:44 2012 -0700" }, "message": "netxen: qlogic ethernet : Fix endian bug.\n\nChange the datatype of \"ip_addr\" to __be32 as \u0027ip\u0027 should be in\nbig endian format.\n\nAdapter needs \"ip address\" in big endian format stored at lower 32bit\nof req.word[1]. netxen_config_ipaddr() now receives \u0027ip\u0027 in big endian\nformat. To satisfy adapter\u0027s need, use memcpy() to copy byte by byte\nof \u0027ip\u0027 into lower 32bit of req.word[1].\n\nMac address and serial number of adapter need to be in little endian format.\nChange the data type of the related variables to __le32 / __le64 or cast it\nexplicitly to __le32 / __le64 depending upon the requirement.\n\nSigned-off-by: Santosh Nayak \u003csantoshprasadnayak@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c577923756b7fe9071f28a76b66b83b306d1d001", "tree": "3cdb24e829bf58f5a319c9e9dca491ce295276e1", "parents": [ "b8fbaef586176f6abe0eb7887ddae66e99898b79" ], "author": { "name": "RongQing.Li", "email": "roy.qing.li@gmail.com", "time": "Thu Mar 15 22:54:14 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Mar 16 21:56:42 2012 -0700" }, "message": "ipv6: Don\u0027t dev_hold(dev) in ip6_mc_find_dev_rcu.\n\nip6_mc_find_dev_rcu() is called with rcu_read_lock(), so don\u0027t\nneed to dev_hold().\nWith dev_hold(), not corresponding dev_put(), will lead to leak.\n\n[ bug introduced in 96b52e61be1 (ipv6: mcast: RCU conversions) ]\n\nSigned-off-by: RongQing.Li \u003croy.qing.li@gmail.com\u003e\nAcked-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "50cdc8fc4007cf773cad710186d253612b83cc72", "tree": "30742451e8b1129e516435c8555a76a80147fd92", "parents": [ "01a282980937f9ca55a3cb06b9c6ff1cc49ea396" ], "author": { "name": "Rami Rosen", "email": "ramirose@gmail.com", "time": "Fri Mar 16 05:19:36 2012 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Mar 16 21:54:44 2012 -0700" }, "message": "pxa168: remove unused stats member.\n\nThe patch removes unused stats member in pxa168 network driver.\n\nSigned-off-by: Rami Rosen \u003cramirose@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cb1ecf25a84aec8c9d1fc6ad0c78adf4fd8335de", "tree": "8c466871a54837c7b64c0a10bf6afe498bdafddc", "parents": [ "33e9ee8dbd0c564533e9ac0e1a0c00e073d5b5c0", "d7178c79d9b7c5518f9943188091a75fc6ce0675" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Mar 16 17:14:55 2012 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Mar 16 17:14:55 2012 -0700" }, "message": "Merge branch \u0027akpm\u0027 (more patches from Andrew)\n\nMerge some more email patches from Andrew Morton:\n \"A couple of nilfs fixes\"\n\n* emailed from Andrew Morton \u003cakpm@linux-foundation.org\u003e:\n nilfs2: fix NULL pointer dereference in nilfs_load_super_block()\n nilfs2: clamp ns_r_segments_percentage to [1, 99]\n" } ], "next": "d7178c79d9b7c5518f9943188091a75fc6ce0675" }