summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2013-08-30regulator: da9063: Optimize da9063_set_current_limit implementationAxel Lin
All the current limit tables have the values in ascend order. So we can slightly optimize the for loop iteration because the first match is the minimal value. Signed-off-by: Axel Lin <axel.lin@ingics.com> Signed-off-by: Mark Brown <broonie@linaro.org>
2013-08-30ARM: KVM: vgic: Bump VGIC_NR_IRQS to 256Christoffer Dall
The Versatile Express TC2 board, which we use as our main emulated platform in QEMU, defines 160+32 == 192 interrupts, so limiting the number of interrupts to 128 is not quite going to cut it for real board emulation. Note that this didn't use to be a problem because QEMU was buggy and only defined 128 interrupts until recently. Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Gleb Natapov <gleb@redhat.com>
2013-08-30ARM: KVM: Bugfix: vgic_bytemap_get_reg per cpu regsChristoffer Dall
For bytemaps each IRQ field is 1 byte wide, so we pack 4 irq fields in one word and since there are 32 private (per cpu) irqs, we have 8 private u32 fields on the vgic_bytemap struct. We shift the offset from the base of the register group right by 2, giving us the word index instead of the field index. But then there are 8 private words, not 4, which is also why we subtract 8 words from the offset of the shared words. Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Gleb Natapov <gleb@redhat.com>
2013-08-30ARM: KVM: vgic: fix GICD_ICFGRn accessMarc Zyngier
All the code in handle_mmio_cfg_reg() assumes the offset has been shifted right to accomodate for the 2:1 bit compression, but this is only done when getting the register address. Shift the offset early so the code works mostly unchanged. Reported-by: Zhaobo (Bob, ERC) <zhaobo@huawei.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Gleb Natapov <gleb@redhat.com>
2013-08-30ARM: KVM: vgic: simplify vgic_get_target_regMarc Zyngier
vgic_get_target_reg is quite complicated, for no good reason. Actually, it is fairly easy to write it in a much more efficient way by using the target CPU array instead of the bitmap. Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Gleb Natapov <gleb@redhat.com>
2013-08-30xen/evtchn: double free on errorDan Carpenter
The call to del_evtchn() frees "evtchn". Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-08-30Xen: Fix retry calls into PRIVCMD_MMAPBATCH*.Andres Lagar-Cavilla
When a foreign mapper attempts to map guest frames that are paged out, the mapper receives an ENOENT response and will have to try again while a helper process pages the target frame back in. Gating checks on PRIVCMD_MMAPBATCH* ioctl args were preventing retries of mapping calls. Permit subsequent calls to update a sub-range of the VMA, iff nothing is yet mapped in that range. Since it is now valid to call PRIVCMD_MMAPBATCH* multiple times, only set vma->vm_private_data if the parameters are valid and (if necessary) the pages for the auto_translated_physmap case have been allocated. This prevents subsequent calls from incorrectly entering the 'retry' path when there are no pages allocated etc. Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.org> Signed-off-by: David Vrabel <david.vrabel@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-08-30Merge branch 'kvm-ppc-next' of git://github.com/agraf/linux-2.6 into queueGleb Natapov
* 'kvm-ppc-next' of git://github.com/agraf/linux-2.6: KVM: PPC: Book3S PR: Rework kvmppc_mmu_book3s_64_xlate() KVM: PPC: Book3S PR: Make instruction fetch fallback work for system calls KVM: PPC: Book3S PR: Don't corrupt guest state when kernel uses VMX KVM: PPC: Book3S: Fix compile error in XICS emulation KVM: PPC: Book3S PR: return appropriate error when allocation fails arch: powerpc: kvm: add signed type cast for comparation powerpc/kvm: Copy the pvr value after memset KVM: PPC: Book3S PR: Load up SPRG3 register with guest value on guest entry kvm/ppc/booke: Don't call kvm_guest_enter twice kvm/ppc: Call trace_hardirqs_on before entry KVM: PPC: Book3S HV: Allow negative offsets to real-mode hcall handlers KVM: PPC: Book3S HV: Correct tlbie usage powerpc/kvm: Use 256K chunk to track both RMA and hash page table allocation. powerpc/kvm: Contiguous memory allocator based RMA allocation powerpc/kvm: Contiguous memory allocator based hash page table allocation KVM: PPC: Book3S: Ignore DABR register mm/cma: Move dma contiguous changes into a seperate config
2013-08-30Merge branch 'pm-cpufreq'Rafael J. Wysocki
* pm-cpufreq: cpufreq: Don't use smp_processor_id() in preemptible context cpufreq: governor: Fix typos in comments cpufreq: governors: Remove duplicate check of target freq in supported range cpufreq: Fix timer/workqueue corruption due to double queueing cpufreq: imx6q: Fix clock enable balance cpufreq: tegra: fix the wrong clock name
2013-08-30Merge branch 'pm-cpuidle'Rafael J. Wysocki
* pm-cpuidle: cpuidle: coupled: fix race condition between pokes and safe state cpuidle: coupled: abort idle if pokes are pending cpuidle: coupled: disable interrupts after entering safe state
2013-08-30Merge branch 'acpi-hotplug'Rafael J. Wysocki
* acpi-hotplug: ACPI / hotplug: Remove containers synchronously driver core / ACPI: Avoid device hot remove locking issues
2013-08-30Merge branch 'acpi-assorted'Rafael J. Wysocki
* acpi-assorted: ACPI / EC: Add ASUSTEK L4R to quirk list in order to validate ECDT ACPI / thermal: Add check of "_TZD" availability and evaluating result
2013-08-30video: da8xx-fb: fix the polarities of the hsync/vsync pulseDarren Etheridge
The polarities were being set to active low when fbdev was requesting active high. This patch reverses it so that what is set into the LCD controller is correct. Signed-off-by: Darren Etheridge <detheridge@ti.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30video: da8xx-fb: support lcdc v2 timing register expansionDarren Etheridge
TI LCD controller version 2 adds some extra bits in a register to increase the available size to represent horizontal timings. This patch allows the fbdev driver to utilize those extra bits. This will become important for driving an HDMI encoder from the lcd controller where some of the VESA/CEA modes require quite large porches. Signed-off-by: Darren Etheridge <detheridge@ti.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30video: da8xx-fb: fixing timing off by one errorsDarren Etheridge
The LCD controller represents some of the timing fields with a 0 in the register representing 1. This was not taken into account when these registers were being set. Interestingly enough not all of the LCDC controller timing registers implement this representation so carefully went through the technical reference manual to only "fix" the correct timings. Signed-off-by: Darren Etheridge <detheridge@ti.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30video: da8xx-fb fixing incorrect porch mappingsDarren Etheridge
The driver was mapping the wrong fbdev margins to the front porch / back porch for both vertical and horizontal timings. This patch corrects it so that: hfp = right margin hbp = left margin vbp = upper margin vfp = lower margin Signed-off-by: Darren Etheridge <detheridge@ti.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30Merge tag 'asoc-v3.12-2' of ↵Takashi Iwai
git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-next ASoC: Updates for v3.12 A few more updates for v3.12, mostly small cleanups plus the addition of the DT bindings for kirkwood and the new i.MX S/PDIF driver.
2013-08-30Merge remote-tracking branch 'asoc/topic/wm8904' into tmpMark Brown
2013-08-30Merge remote-tracking branch 'asoc/topic/samsung' into tmpMark Brown
2013-08-30Merge remote-tracking branch 'asoc/topic/kirkwood' into tmpMark Brown
2013-08-30Merge remote-tracking branch 'asoc/topic/fsl' into tmpMark Brown
2013-08-30Merge remote-tracking branch 'asoc/topic/fsi' into tmpMark Brown
2013-08-30Merge remote-tracking branch 'asoc/topic/ep93xx' into tmpMark Brown
2013-08-30Merge remote-tracking branch 'asoc/topic/designware' into tmpMark Brown
2013-08-30Merge remote-tracking branch 'asoc/topic/core' into tmpMark Brown
2013-08-30ASoC: fsl: Drop SND_SOC_FSL_UTILS from SND_SOC_IMX_SPDIFFabio Estevam
SND_SOC_FSL_UTILS is only used by PowerPC machines, so let's drop it in the i.mx case. Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com> Acked-by: Nicolin Chen <b42378@freescale.com> Signed-off-by: Mark Brown <broonie@linaro.org>
2013-08-30video: xilinxfb: replace devm_request_and_ioremap by devm_ioremap_resourceJulia Lawall
Use devm_ioremap_resource instead of devm_request_and_ioremap. This was done using the semantic patch scripts/coccinelle/api/devm_ioremap_resource.cocci The initialization of drvdata->regs_phys was manually moved lower, to take advantage of the NULL test on res performed by devm_ioremap_resource. Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30fbmem: move EXPORT_SYMBOL annotation next to symbol declarationsDaniel Mack
Just a cosmetic thing to bring that file in line with others in the tree. Signed-off-by: Daniel Mack <zonque@gmail.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30drivers: video: fbcmap: remove the redundency and incorrect checkingsChen Gang
fb_set_cmap() already checks the parameters, so need remove the redundancy checking. This redundancy checking is also incorrect, the related warning: drivers/video/fbcmap.c:288:2: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits] Signed-off-by: Chen Gang <gang.chen@asianux.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30pinctrl: sunxi: Fix off-by-one for valid offset range checkingAxel Lin
The valid offset range should be 0 ... chip->ngpio - 1. Signed-off-by: Axel Lin <axel.lin@ingics.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
2013-08-30pinctrl: sunxi: drop lock on error pathLinus Walleij
I forgot to drop the lock for the return inside the loop protected by the spinlock in the pin config routine when merging in -rc7 in commit 6ad30ce046aefbdc3848232c665a728860d7bb68 Reported-by: Sherman Yin <syin@broadcom.com> Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
2013-08-30video: mxsfb: simplify use of devm_ioremap_resourceJulia Lawall
Remove unneeded error handling on the result of a call to platform_get_resource when the value is passed to devm_ioremap_resource. Move the call to platform_get_resource adjacent to the call to devm_ioremap_resource to make the connection between them more clear. A simplified version of the semantic patch that makes this change is as follows: (http://coccinelle.lip6.fr/) // <smpl> @@ expression pdev,res,n,e,e1; expression ret != 0; identifier l; @@ - res = platform_get_resource(pdev, IORESOURCE_MEM, n); ... when != res - if (res == NULL) { ... \(goto l;\|return ret;\) } ... when != res + res = platform_get_resource(pdev, IORESOURCE_MEM, n); e = devm_ioremap_resource(e1, res); // </smpl> Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30Release efifb's colormap in efifb_destroy()Peter Jones
This was found by Alexandra Kossovsky, who noted this traceback from kmemleak: > unreferenced object 0xffff880216fcfe00 (size 512): > comm "swapper/0", pid 1, jiffies 4294895429 (age 1415.320s) > hex dump (first 32 bytes): > 00 00 00 00 00 00 00 00 aa aa aa aa aa aa aa aa ................ > 55 55 55 55 55 55 55 55 ff ff ff ff ff ff ff ff UUUUUUUU........ > backtrace: > [<ffffffff813e415c>] kmemleak_alloc+0x21/0x3e > [<ffffffff8111c17f>] > kmemleak_alloc_recursive.constprop.57+0x16/0x18 > [<ffffffff8111e63b>] __kmalloc+0xf9/0x144 > [<ffffffff8123d9cf>] fb_alloc_cmap_gfp+0x47/0xe1 > [<ffffffff8123da77>] fb_alloc_cmap+0xe/0x10 > [<ffffffff81aff40a>] efifb_probe+0x3e9/0x48f > [<ffffffff812c566f>] platform_drv_probe+0x34/0x5e > [<ffffffff812c3e6d>] driver_probe_device+0x98/0x1b4 > [<ffffffff812c3fd7>] __driver_attach+0x4e/0x6f > [<ffffffff812c25bf>] bus_for_each_dev+0x57/0x8a > [<ffffffff812c3984>] driver_attach+0x19/0x1b > [<ffffffff812c362b>] bus_add_driver+0xde/0x201 > [<ffffffff812c453f>] driver_register+0x8c/0x110 > [<ffffffff812c510d>] platform_driver_register+0x41/0x43 > [<ffffffff812c5127>] platform_driver_probe+0x18/0x8a > [<ffffffff81aff002>] efifb_init+0x276/0x295 Signed-off-by: Peter Jones <pjones@redhat.com> Reviewed-by: David Herrmann <dh.herrmann@gmail.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30at91/avr32/atmel_lcdfb: prepare clk before calling enableBoris BREZILLON
Replace clk_enable/disable with clk_prepare_enable/disable_unprepare to avoid common clk framework warnings. Signed-off-by: Boris BREZILLON <b.brezillon@overkiz.com> Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30video: exynos: Ensure definitions match prototypesMark Brown
Ensure that the definitions of functions match the prototypes used by other modules by including the header with the prototypes in the files with the definitions. Signed-off-by: Mark Brown <broonie@linaro.org> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
2013-08-30s390/pci: use virtual memory for iommu bitmapSebastian Ott
The bitmap used to mark dma mappings can be quite large on systems with huge amounts of memory. Use virtual memory for this bitmap. Suggested-by: Alexander Schmidt <alexschm@de.ibm.com> Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30s390/cio: fix unlocked access of global bitmapSebastian Ott
Access to the slow_subchannel_set has to be secured via the slow_subchannel_lock. Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30s390/pci: update function handle after resume from hibernateSebastian Ott
Function handles may change while the system was in hibernation use list pci functions and update the function handles. Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30s390/pci: try harder to modify a functionSebastian Ott
In rare situations a PCI function can report a busy condition when we issue the modify pci function command. A temporary busy condition can exceed 1 second but not 2 seconds. Increase the time until we report an error to 2 seconds. Also increase the time we sleep between the retries to reduce the load in this case. Suggested-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30s390/pci: split lpfSebastian Ott
List pci functions is used to query and iterate over pci functions. This function currently has 2 users - initial device discovery and rescan after a machine check. Instead of having a multipurpose function pass a callback which gets called for each pci function. Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30s390/hibernate: add early resume functionSebastian Ott
Some functions that do arch specific resume actions are called directly from swsusp_asm64.S . Before we add another function call provide a generic s390_early_resume function which can be used for this purpose. Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30s390/pci: add recover sysfs knobSebastian Ott
Add an arch specific attribute to recover a pci function from an error state or config space blockage. Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30s390/pci: use claim_resourceSebastian Ott
Use pci_claim_resource to find and request bus ressources in pcibios_add_device. Also move some (de)initialization stuff to pcibios_enable_device/pcibios_disable_device. Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30s390/pci/hotplug: convert to be builtin onlySebastian Ott
Convert s390' pci hotplug to be builtin only, with no module option. Suggested-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2013-08-30OMAPDSS: rename omap_dss_device's 'device' field to 'dst'Tomi Valkeinen
In the old panel device model we had omap_dss_output entities, representing the encoders in the DSS block. This entity had "device" field, which pointed to the panel that was using the omap_dss_output. With the new panel device model, the omap_dss_output is integrated into omap_dss_device, which now represents a "display entity". Thus the "device" field, now in omap_dss_device, points to the next entity in the display entity-chain. This patch renames the "device" field to "dst", which much better tells what the field points to. Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Reviewed-by: Archit Taneja <archit@ti.com>
2013-08-30OMAPDSS: rename omap_dss_device's 'output' to 'src'Tomi Valkeinen
In the old panel device model we had "outputs", which were the encoders inside OMAP DSS block, and panel devices (omap_dss_device). The panel devices had a reference to the source of the video data, i.e. reference to an "output", in a field named "output". That was somewhat confusing even in the old panel device model, but even more so with the panel device model where we can have longer chains of display entities. This patch renames the "output" field to "src", which much better tells what the field points to. Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Reviewed-by: Archit Taneja <archit@ti.com>
2013-08-30OMAPDSS: DSS: remove legacy dss bus supportTomi Valkeinen
With all the old panels removed and all the old panel model APIs removed from the DSS encoders, we can now remove the custom omapdss-bus which was used in the old panel model. Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Reviewed-by: Archit Taneja <archit@ti.com>
2013-08-29drivers:net: Convert dma_alloc_coherent(...__GFP_ZERO) to dma_zalloc_coherentJoe Perches
__GFP_ZERO is an uncommon flag and perhaps is better not used. static inline dma_zalloc_coherent exists so convert the uses of dma_alloc_coherent with __GFP_ZERO to the more common kernel style with zalloc. Remove memset from the static inline dma_zalloc_coherent and add just one use of __GFP_ZERO instead. Trivially reduces the size of the existing uses of dma_zalloc_coherent. Realign arguments as appropriate. Signed-off-by: Joe Perches <joe@perches.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-29pkt_sched: fq: Fair Queue packet schedulerEric Dumazet
- Uses perfect flow match (not stochastic hash like SFQ/FQ_codel) - Uses the new_flow/old_flow separation from FQ_codel - New flows get an initial credit allowing IW10 without added delay. - Special FIFO queue for high prio packets (no need for PRIO + FQ) - Uses a hash table of RB trees to locate the flows at enqueue() time - Smart on demand gc (at enqueue() time, RB tree lookup evicts old unused flows) - Dynamic memory allocations. - Designed to allow millions of concurrent flows per Qdisc. - Small memory footprint : ~8K per Qdisc, and 104 bytes per flow. - Single high resolution timer for throttled flows (if any). - One RB tree to link throttled flows. - Ability to have a max rate per flow. We might add a socket option to add per socket limitation. Attempts have been made to add TCP pacing in TCP stack, but this seems to add complex code to an already complex stack. TCP pacing is welcomed for flows having idle times, as the cwnd permits TCP stack to queue a possibly large number of packets. This removes the 'slow start after idle' choice, hitting badly large BDP flows, and applications delivering chunks of data as video streams. Nicely spaced packets : Here interface is 10Gbit, but flow bottleneck is ~20Mbit cwin is big, yet FQ avoids the typical bursts generated by TCP (as in netperf TCP_RR -- -r 100000,100000) 15:01:23.545279 IP A > B: . 78193:81089(2896) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.545394 IP B > A: . ack 81089 win 3668 <nop,nop,timestamp 11597985 1115> 15:01:23.546488 IP A > B: . 81089:83985(2896) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.546565 IP B > A: . ack 83985 win 3668 <nop,nop,timestamp 11597986 1115> 15:01:23.547713 IP A > B: . 83985:86881(2896) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.547778 IP B > A: . ack 86881 win 3668 <nop,nop,timestamp 11597987 1115> 15:01:23.548911 IP A > B: . 86881:89777(2896) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.548949 IP B > A: . ack 89777 win 3668 <nop,nop,timestamp 11597988 1115> 15:01:23.550116 IP A > B: . 89777:92673(2896) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.550182 IP B > A: . ack 92673 win 3668 <nop,nop,timestamp 11597989 1115> 15:01:23.551333 IP A > B: . 92673:95569(2896) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.551406 IP B > A: . ack 95569 win 3668 <nop,nop,timestamp 11597991 1115> 15:01:23.552539 IP A > B: . 95569:98465(2896) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.552576 IP B > A: . ack 98465 win 3668 <nop,nop,timestamp 11597992 1115> 15:01:23.553756 IP A > B: . 98465:99913(1448) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.554138 IP A > B: P 99913:100001(88) ack 65248 win 3125 <nop,nop,timestamp 1115 11597805> 15:01:23.554204 IP B > A: . ack 100001 win 3668 <nop,nop,timestamp 11597993 1115> 15:01:23.554234 IP B > A: . 65248:68144(2896) ack 100001 win 3668 <nop,nop,timestamp 11597993 1115> 15:01:23.555620 IP B > A: . 68144:71040(2896) ack 100001 win 3668 <nop,nop,timestamp 11597993 1115> 15:01:23.557005 IP B > A: . 71040:73936(2896) ack 100001 win 3668 <nop,nop,timestamp 11597993 1115> 15:01:23.558390 IP B > A: . 73936:76832(2896) ack 100001 win 3668 <nop,nop,timestamp 11597993 1115> 15:01:23.559773 IP B > A: . 76832:79728(2896) ack 100001 win 3668 <nop,nop,timestamp 11597993 1115> 15:01:23.561158 IP B > A: . 79728:82624(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.562543 IP B > A: . 82624:85520(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.563928 IP B > A: . 85520:88416(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.565313 IP B > A: . 88416:91312(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.566698 IP B > A: . 91312:94208(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.568083 IP B > A: . 94208:97104(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.569467 IP B > A: . 97104:100000(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.570852 IP B > A: . 100000:102896(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.572237 IP B > A: . 102896:105792(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.573639 IP B > A: . 105792:108688(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.575024 IP B > A: . 108688:111584(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.576408 IP B > A: . 111584:114480(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> 15:01:23.577793 IP B > A: . 114480:117376(2896) ack 100001 win 3668 <nop,nop,timestamp 11597994 1115> TCP timestamps show that most packets from B were queued in the same ms timeframe (TSval 1159799{3,4}), but FQ managed to send them right in time to avoid a big burst. In slow start or steady state, very few packets are throttled [1] FQ gets a bunch of tunables as : limit : max number of packets on whole Qdisc (default 10000) flow_limit : max number of packets per flow (default 100) quantum : the credit per RR round (default is 2 MTU) initial_quantum : initial credit for new flows (default is 10 MTU) maxrate : max per flow rate (default : unlimited) buckets : number of RB trees (default : 1024) in hash table. (consumes 8 bytes per bucket) [no]pacing : disable/enable pacing (default is enable) All of them can be changed on a live qdisc. $ tc qd add dev eth0 root fq help Usage: ... fq [ limit PACKETS ] [ flow_limit PACKETS ] [ quantum BYTES ] [ initial_quantum BYTES ] [ maxrate RATE ] [ buckets NUMBER ] [ [no]pacing ] $ tc -s -d qd qdisc fq 8002: dev eth0 root refcnt 32 limit 10000p flow_limit 100p buckets 256 quantum 3028 initial_quantum 15140 Sent 216532416 bytes 148395 pkt (dropped 0, overlimits 0 requeues 14) backlog 0b 0p requeues 14 511 flows, 511 inactive, 0 throttled 110 gc, 0 highprio, 0 retrans, 1143 throttled, 0 flows_plimit [1] Except if initial srtt is overestimated, as if using cached srtt in tcp metrics. We'll provide a fix for this issue. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-29Merge branch 'for-3.11-fixes' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup Pull cgroup fix from Tejun Heo: "During the percpu reference counting update which was merged during v3.11-rc1, the cgroup destruction path was updated so that a cgroup in the process of dying may linger on the children list, which was necessary as the cgroup should still be included in child/descendant iteration while percpu ref is being killed. Unfortunately, I forgot to update cgroup destruction path accordingly and cgroup destruction may fail spuriously with -EBUSY due to lingering dying children even when there's no live child left - e.g. "rmdir parent/child parent" will usually fail. This can be easily fixed by iterating through the children list to verify that there's no live child left. While this is very late in the release cycle, this bug is very visible to userland and I believe the fix is relatively safe. Thanks Hugh for spotting and providing fix for the issue" * 'for-3.11-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: cgroup: fix rmdir EBUSY regression in 3.11
generated by cgit (git 2.34.1) at 2025-09-14 08:32:19 +0000