Ilpo Järvinen [Sun, 21 Sep 2008 04:26:22 +0000 (21:26 -0700)]
tcp: back retransmit_high when it over-estimated
If lost skb is sacked, we might have nothing to retransmit
as high as the retransmit_high is pointing to, so place
it lower to avoid unnecessary walking.
This is mainly for the case where high L'ed skbs gets sacked.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Sun, 21 Sep 2008 04:25:52 +0000 (21:25 -0700)]
tcp: don't clear lost_skb_hint when not necessary
Most importantly avoid doing it with cumulative ACK. However,
since we have lost_cnt_hint in the picture as well needing
adjustments, it's not as trivial as dealing with
retransmit_skb_hint (and cannot be done in the all place we
could trivially leave retransmit_skb_hint untouched).
With the previous patch, this should mostly remove O(n^2)
behavior while cumulative ACKs start flowing once rexmit
after a lossy round-trip made it through.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Sun, 21 Sep 2008 04:24:49 +0000 (21:24 -0700)]
tcp: remove retransmit_skb_hint clearing from failure
This doesn't much sense here afaict, probably never has. Since
fragmenting and collapsing deal the hints by themselves, there
should be very little reason for the rexmit loop to do that.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Sun, 21 Sep 2008 04:21:16 +0000 (21:21 -0700)]
tcp: No need to clear retransmit_skb_hint when SACKing
Because lost counter no longer requires tuning, this is
trivial to remove (the tuning wouldn't have been too
hard either) because no "new" retransmittable skb appeared
below retransmit_skb_hint when SACKing for sure.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Sun, 21 Sep 2008 04:20:20 +0000 (21:20 -0700)]
tcp: convert retransmit_cnt_hint to seqno
Main benefit in this is that we can then freely point
the retransmit_skb_hint to anywhere we want to because
there's no longer need to know what would be the count
changes involve, and since this is really used only as a
terminator, unnecessary work is one time walk at most,
and if some retransmissions are necessary after that
point later on, the walk is not full waste of time
anyway.
Since retransmit_high must be kept valid, all lost
markers must ensure that.
Now I also have learned how those "holes" in the
rexmittable skbs can appear, mtu probe does them. So
I removed the misleading comment as well.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Brooks [Sun, 21 Sep 2008 03:06:16 +0000 (20:06 -0700)]
IB/mad: Don't discard BMA responses in kernel
This fixes the problem of incoming BMA responses being dropped due to
a bad "is response" check. Fix the test to use the ib_response_mad()
predicate, which correctly handles BMA MADs.
This fixes <https://bugs.openfabrics.org/show_bug.cgi?id=988>.
Signed-off-by: Michael Brooks <michael.brooks@qlogic.com> Acked-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
When a QP goes into error state, it is required that CQ entries with a
flush error status are delivered to the application for any
outstanding work requests. eHCA does not do this in hardware, so this
patch adds software flush CQE generation to the ehca driver.
Whenever a QP gets into error state, it is added to the QP error list
of its respective CQ. If the error QP list of a CQ is not empty,
poll_cq() generates flush CQEs before polling the actual CQ.
Signed-off-by: Alexander Schmidt <alexs@linux.vnet.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
Paul Mundt [Sun, 21 Sep 2008 03:00:23 +0000 (12:00 +0900)]
sh: Move lookup_exception_vector() out to asm/system_32.h.
There are other places where we want to have access to the trap/exception
number, so move out the lookup_exception_vector() helper. While we're at
it, refactor it slightly to return the vector instead.
SH has traditionally forced the thread order to be relative to the page
size, so there were never any situations where the same bug was
triggered by slub. Regardless, the usage of > 8kB stacks for the larger
page sizes is overkill, so we switch to using slab allocations there,
as per the powerpc change.
Akinobu Mita [Sat, 13 Sep 2008 10:03:32 +0000 (19:03 +0900)]
mmc_test: initialize mmc_test_lock statically
The mutex mmc_test_lock is initialized at every time mmc_test device
is probed. Probing another mmc_test device may break the mutex, if
the probe function is called while the mutex is locked.
This patch fixes it by statically initializing mmc_test_lock.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Pierre Ossman <drzeus@drzeus.cx>
We used to store a binary register snapshot in the "regs" file, so we
set the file size to be the size of this snapshot. This is no longer
valid since we switched to using seq_file.
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com> Signed-off-by: Pierre Ossman <drzeus@drzeus.cx>
The debugfs hook atmci_regs_show allocates a temporary buffer for
storing a register snapshot, but it doesn't free it before returning.
Plug this leak.
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com> Signed-off-by: Pierre Ossman <drzeus@drzeus.cx>
Andrew Paprocki [Sat, 20 Sep 2008 08:25:19 +0000 (10:25 +0200)]
hwmon: (it87) Fix fan tachometer reading in IT8712F rev 0x7 (I)
The IT8712F v0.9.1 datasheet applies to revisions >= 0x8 (J).
The driver was incorrectly attempting to enable 16-bit fan
readings on rev 0x7 (I) which led to incorrect RPM values.
Signed-off-by: Andrew Paprocki <andrew@ishiboo.com> Tested-by: John Gumb <john.gumb@tandberg.com> Signed-off-by: Jean Delvare <khali@linux-fr.org>
Commit 4611a77 ("[IA64] fix compile failure with non modular builds")
introduced struct fdesc into asm/elf.h, which duplicates KVM's definition.
Remove the latter to avoid the build error.
Signed-off-by: Jes Sorensen <jes@sgi.com> Acked-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Avi Kivity <avi@redhat.com>
* git://oss.sgi.com:8090/xfs/linux-2.6:
[XFS] Don't do I/O beyond eof when unreserving space
[XFS] Fix use-after-free with buffers
[XFS] Prevent lockdep false positives when locking two inodes.
[XFS] Fix barrier status change detection.
[XFS] Prevent direct I/O from mapping extents beyond eof
[XFS] Fix regression introduced by remount fixup
[XFS] Move memory allocations for log tracing out of the critical path
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
IPoIB: Fix deadlock on RTNL between bcast join comp and ipoib_stop()
RDMA/nes: Fix client side QP destroy
IB/mlx4: Fix up fast register page list format
mlx4_core: Set RAE and init mtt_sz field in FRMR MPT entries
Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched: fix deadlock in setting scheduler parameter to zero
sched: fix 2.6.27-rc5 couldn't boot on tulsa machine randomly
Merge branch 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
clockevents: make device shutdown robust
clocksource, acpi_pm.c: fix check for monotonicity
clockevents: remove WARN_ON which was used to gather information
David S. Miller [Fri, 19 Sep 2008 23:13:05 +0000 (16:13 -0700)]
qlge: Fix warnings in debugging code.
drivers/net/qlge/qlge_dbg.c: In function ‘ql_dump_qdev’:
drivers/net/qlge/qlge_dbg.c:369: warning: cast to pointer from integer of different size
drivers/net/qlge/qlge_dbg.c:373: warning: cast to pointer from integer of different size
drivers/net/qlge/qlge_dbg.c: In function ‘ql_dump_tx_ring’:
drivers/net/qlge/qlge_dbg.c:457: warning: format ‘%llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘long unsigned int’
drivers/net/qlge/qlge_dbg.c:461: warning: format ‘%llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘long unsigned int’
drivers/net/qlge/qlge_dbg.c: In function ‘ql_dump_rx_ring’:
drivers/net/qlge/qlge_dbg.c:557: warning: format ‘%llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘long unsigned int’
drivers/net/qlge/qlge_dbg.c:565: warning: format ‘%llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘long unsigned int’
drivers/net/qlge/qlge_dbg.c:575: warning: format ‘%llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘long unsigned int’
drivers/net/qlge/qlge_dbg.c:579: warning: format ‘%llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘long unsigned int’
drivers/net/qlge/qlge_dbg.c:598: warning: format ‘%llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘long unsigned int’
drivers/net/qlge/qlge_dbg.c:602: warning: format ‘%llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘long unsigned int’
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc:
Fix compile failure with non modular builds
powerpc: Holly board needs dtbImage target
powerpc: Fix interrupt values for DMA2 in MPC8610 HPCD device tree
* master.kernel.org:/home/rmk/linux-2.6-arm:
[ARM] 5255/1: Update jornada ssp to remove build errors/warnings
[ARM] omap: back out 'internal_clock' support
[ARM] 5249/1: davinci: remove redundant check in davinci_psc_config()
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-2.6:
sparc64: Fix SMP bootup with CONFIG_STACK_DEBUG or ftrace.
sparc64: Fix OOPS in psycho_pcierr_intr_other().
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
e100: Use pci_pme_active to clear PME_Status and disable PME#
e1000: prevent corruption of EEPROM/NVM
forcedeth: call restore mac addr in nv_shutdown path
bnx2: Promote vector field in bnx2_irq structure from u16 to unsigned int
sctp: Fix oops when INIT-ACK indicates that peer doesn't support AUTH
sctp: do not enable peer features if we can't do them.
sctp: set the skb->ip_summed correctly when sending over loopback.
udp: Fix rcv socket locking
Becky Bruce [Fri, 12 Sep 2008 15:42:56 +0000 (10:42 -0500)]
cpm_uart: Pass actual dev ptr to dma_* in ucc and cpm_uart serial
We're currently passing NULL, and really shouldn't be.
Signed-off-by: Becky Bruce <becky.bruce@freescale.com> Acked-By: Timur Tabi <timur@freescale.com> Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Manfred Spraul [Wed, 20 Aug 2008 13:39:59 +0000 (15:39 +0200)]
avr32: nmi_enter() without nmi_exit()
While updating the rcu code, I noticed that do_nmi() for AVR32 is odd:
There is an nmi_enter() call without an nmi_exit().
This can't be correct, it breaks rcu (at least the preempt version) and
lockdep.
[haavard.skinnemoen@atmel.com: fixed another case that returned directly] Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com>
Switch mv643xx_eth from using drivers/net/mii.c to using phylib.
Since the mv643xx_eth hardware does all the link state handling and
PHY polling, the driver will use phylib in the "Doing it all yourself"
mode described in the phylib documentation.
Signed-off-by: Lennert Buytenhek <buytenh@marvell.com> Acked-by: Andy Fleming <afleming@freescale.com>
On AVR32, all parameters beyond the 5th are passed on the stack. System
calls don't use the stack -- they borrow a callee-saved register
instead. This means that syscalls that take 6 parameters must be called
through a stub that pushes the last parameter on the stack.
This patch adds a stub for sync_file_range syscall on AVR32
architecture. Tested with uClibc snapshot.
Andrew Morton [Fri, 19 Sep 2008 11:16:23 +0000 (04:16 -0700)]
drivers/dma/dmatest.c: switch a GFP_ATOMIC to GFP_KERNEL
It was needlessly using the unreliable GFP_ATOMIC.
Cc: Timur Tabi <timur@freescale.com> Acked-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Timur Tabi [Fri, 19 Sep 2008 11:16:19 +0000 (04:16 -0700)]
dmatest: properly handle duplicate DMA channels
Update the the dmatest driver so that it handles duplicate DMA channels
properly.
When a DMA client is notified of an available DMA channel, it must check if it
has already allocated resources for that channel. If so, it should return
DMA_DUP. This can happen, for example, if a DMA driver calls
dma_async_device_register() more than once.
Acked-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com> Signed-off-by: Timur Tabi <timur@freescale.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
AMD IOMMU: use coherent_dma_mask in alloc_coherent
The alloc_coherent implementation for AMD IOMMU currently uses
*dev->dma_mask per default. This patch changes it to prefer
dev->coherent_dma_mask if it is set.
AMD IOMMU: use cmd_buf_size when freeing the command buffer
The command buffer release function uses the CMD_BUF_SIZE macro for
get_order. Replace this with iommu->cmd_buf_size which is more reliable
about the actual size of the buffer.
The current calculation of the IVHD entry size is hard to read. So move
this code to a seperate function to make it more clear what this
calculation does.
AMD IOMMU: free domain bitmap with its allocation order
The amd_iommu_pd_alloc_bitmap is allocated with a calculated order and
freed with order 1. This is not a bug since the calculated order always
evaluates to 1, but its unclean code. So replace the 1 with the
calculation in the release path.
AMD IOMMU: avoid unnecessary low zone allocation in alloc_coherent
x86's common alloc_coherent (dma_alloc_coherent in dma-mapping.h) sets
up the gfp flag according to the device dma_mask but AMD IOMMU doesn't
need it for devices that the IOMMU can do virtual mappings for. This
patch avoids unnecessary low zone allocation.
AMD IOMMU: don't assign preallocated protection domains to devices
In isolation mode the protection domains for the devices are
preallocated and preassigned. This is bad if a device should be passed
to a virtualization guest because the IOMMU code does not know if it is
in use by a driver. This patch changes the code to assign the device to
the preallocated domain only if there are dma mapping requests for it.
There is a bit in the device entry to suppress all IO page faults
generated by a device. This bit was set until now because there was no
event logging. Now that there is event logging this patch allows IO page
faults from devices to see them in the kernel log.
We need the pci_dev later anyways to enable MSI for the IOMMU hardware.
So remove the devid pointing to the BDF and replace it with the pci_dev
structure where the IOMMU is implemented.
This patch adds the allocation of a event buffer for each AMD IOMMU in
the system. The hardware will log events like device page faults or
other errors to this buffer once this is enabled.
The API definition for dma_alloc_coherent states that the bus address
has to be aligned to the next power of 2 boundary greater than the
allocation size. This is violated by AMD IOMMU so far and this patch
fixes it.
AMD IOMMU: add branch hints to completion wait checks
This patch adds branch hints to the cecks if a completion_wait is
necessary. The completion_waits in the mapping paths are unlikly because
they will only happen on software implementations of AMD IOMMU which
don't exists today or with lazy IO/TLB flushing when the allocator wraps
around the address space. With lazy IO/TLB flushing the completion_wait
in the unmapping path is unlikely too.
projects / linux-2.6-omap-h63xx.git / log