After seeing, at best, "guesses" as to the following kind
of information in several drivers, I decided that we really
need a way for platforms to specifically give advice in this
area for what works best with their PCI controller implementation.
Basically, this new interface gives DMA bursting advice on
PCI. There are three forms of the advice:
1) Burst as much as possible, it is not necessary to end bursts
on some particular boundary for best performance.
2) Burst on some byte count multiple. A DMA burst to some multiple of
number of bytes may be done, but it is important to end the burst
on an exact multiple for best performance.
The best example of this I am aware of are the PPC64 PCI
controllers, where if you end a burst mid-cacheline then
chip has to refetch the data and the IOMMU translations
which hurts performance a lot.
3) Burst on a single byte count multiple. Bursts shall end
exactly on the next multiple boundary for best performance.
Sparc64 and Alpha's PCI controllers operate this way. They
disconnect any device which tries to burst across a cacheline
boundary.
Actually, newer sparc64 PCI controllers do not have this behavior.
That is why the "pdev" is passed into the interface, so I can
add code later to check which PCI controller the system is using
and give advice accordingly.
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This is an updated version of Ben's fix-pci-mmap-on-ppc-and-ppc64.patch
which is in 2.6.12-rc4-mm1.
It fixes the patch to work on PPC iSeries, removes some debug printks
at Ben's request, and incorporates your
fix-pci-mmap-on-ppc-and-ppc64-fix.patch also.
Originally from Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch was discussed at length on linux-pci and so far, the last
iteration of it didn't raise any comment. It's effect is a nop on
architecture that don't define the new pci_resource_to_user() callback
anyway. It allows architecture like ppc who put weird things inside of
PCI resource structures to convert to some different value for user
visible ones. It also fixes mmap'ing of IO space on those archs.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch adds PCI based I/O xAPIC hot-add support to ACPIPHP
driver. When PCI root bridge is hot-added, all PCI based I/O xAPICs
under the root bridge are hot-added by this patch. Hot-remove support
is TBD.
Signed-off-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This is an ia64 implementation of acpi_register_ioapic() and
acpi_unregister_ioapic() interfaces.
Signed-off-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch adds the following new interfaces for I/O xAPIC
hotplug. The implementation of these interfaces depends on each
architecture.
o int acpi_register_ioapic(acpi_handle handle, u64 phys_addr,
u32 gsi_base);
This new interface is to add a new I/O xAPIC specified by
phys_addr and gsi_base pair. phys_addr is the physical address
to which the I/O xAPIC is mapped and gsi_base is global system
interrupt base of the I/O xAPIC. acpi_register_ioapic returns
0 on success, or negative value on error.
o int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base);
This new interface is to remove a I/O xAPIC specified by
gsi_base. acpi_unregister_ioapic returns 0 on success, or
negative value on error.
Signed-off-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Current acpiphp code does not distinguish between the physical presence and
power state of a device/slot. That is, if a device has to be disabled, it
also tries to physically ejects the device. This patch decouples power state
from physical presence. You can now echo to the corresponding sysfs power
control file to repeatedly enable and disable a device without having to
physically re-insert it.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
acpiphp changes to support acpi based root bridge hot-add.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Earlier I reported that Matthew's acpiphp rewrite had problem in powering down
slot on my i386 system. The following patch is needed to get the acpiphp
rewrite properly powering down the slot.
Signed-off-by: Dely Sy <dely.l.sy@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
A root bridge may not have directly attached hotpluggable slots under it.
Instead, it may have p2p bridges with slots under it. In this case, we need
to clean up the p2p bridges and slots properly too. Patch below applies on
top of the original patch, and fixes this problem. Without this, acpiphp
leaves behind notify handlers on module unload, and subsequent module load
attempts don't work properly too. Patch was tested on an ia64 Tiger4 box.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch converts acpiphp to use the generic PCI resource assignment code.
It's quite large, but most of it is deleting the acpiphp_pci and acpiphp_res
files. It's tested on an hp Integrity rx8620 (which won't work without this
patch). Testers with other hardware welcomed.
Signed-off-by: Matthew Wilcox <matthew@wil.cx>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Export an acpi interface to get PCI domain/bus/devfn information from the
corresponding namespace handle. Used by acpiphp code to transpate the device
handle of the hot-plugged root bridge to the corresponding pci location
information.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Create new interfaces to recursively add an acpi namespace object to the acpi
device list, and recursively start the namespace object. This is needed for
ACPI based hotplug of a root bridge hierarchy where the add operation must be
performed first and the start operation must be performed separately after the
hot-plugged devices have been properly configured.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Read bridge io/mem/pfmem ranges when fixing up the bus so that bus resources
are tracked. This is required to properly support pci end device and bridge
hotplug.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
When hot-plugging an I/O hierarchy that contains many bridges and leaf
devices, it's possible that there are not enough resources to start all the
device present. If we fail to assign a resource, clear the corresponding
value in the pci_dev structure, so other code can take corrective action.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
When a root bridge hierarchy is hot-plugged, resource requirements for the new
devices may be greater than what the root bridge is decoding. In this case,
we want to remove devices that did not get needed resources. These devices
have been scanned into bus specific lists but not yet added to the global
device list. Make sure the pci remove functions can handle this case.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
When a pci child bus is created, add it to the parent's children list
immediately rather than waiting till pci_bus_add_devices(). For hot-plug
bridges/devices, pci_bus_add_devices() may be called much later, after they
have been properly configured. In the meantime, this allows us to use the
normal pci bus search functions for the hot-plug bridges/buses.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
With root bridge and pci bridge hot-plug, new buses and devices can be added
or removed at run time. Protect the pci bus and device lists with the pci
lock when doing so.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
When hot-plugging a root bridge, as we try to assign bus numbers we may find
that the hotplugged hieratchy has more PCI to PCI bridges (i.e. bus
requirements) than available. Make sure we don't step over an existing bus
when that happens.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
PCI scan code calls the arch specific pcibios_fixup_bus() each time it scans a
new bridge. For root bridge hot-plug, the bridge and it's attached devices
may not have been configured properly yet, so it's not safe to claim those
resources at this time.
This code goes away when we clean up the way pci resources are claimed (in
pci_enable_device()), so this is only a stopgap fix.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
When checking if a PCI to PCI bridge should be enabled to decode memory and/or
IO resources, we need to look at all device resources not just the first 6.
This is needed to allow PCI bridges to pass down memory and IO accesses to
child devices even when the bridge itself does not consume resources in its
PCI BARs.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
When you hot-plug a (root) bridge hierarchy, it may have p2p bridges and
devices attached to it that have not been configured by firmware. In this
case, we need to configure the devices before starting them. This patch
separates device start from device scan so that we can introduce the
configuration step in the middle.
I kept the existing semantics for pci_scan_bus() since there are a huge number
of callers to that function.
Also, I have no way of testing the changes I made to the parisc files, so this
needs review by those folks. Sorry for the massive cross-post, this touches
files in many different places.
Signed-off-by: Rajesh Shah <rajesh.shah@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
I updated this to remove unnecessary variable initialization, make
check_routing be inline only and not __init, switch to strtoul, and
formatting fixes as per Randy Dunlap's recommendations.
I updated this to change pirq_table_addr to a long, and to add a warning
msg if the PIRQ table wasn't found at the specified address, as per thread
with Matthew Wilcox.
In our hardware situation, the BIOS is unable to store or generate it's PIRQ
table in the F0000h-100000h standard range. This patch adds a pci kernel
parameter, pirqaddr to allow the bootloader (or BIOS based loader) to inform
the kernel where the PIRQ table got stored. A beneficial side-effect is that,
if one's BIOS uses a static address each time for it's PIRQ table, then
pirqaddr can be used to avoid the $pirq search through that address block each
time at boot for normal PIRQ BIOSes.
Signed-off-by: Jaya Kumar <jayalk@intworks.biz>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
From: <pageexec@freemail.hu>
$subject was fixed in 2.4 already, 2.6 needs it as well.
The impact of the bugs is a kernel stack overflow and privilege escalation
from CAP_NET_ADMIN via the IP_VS_SO_SET_STARTDAEMON/IP_VS_SO_GET_DAEMON
ioctls. People running with 'root=all caps' (i.e., most users) are not
really affected (there's nothing to escalate), but SELinux and similar
users should take it seriously if they grant CAP_NET_ADMIN to other users.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes two bugs in the dm9000 network driver:
- Don't read one byte too much in 8bit mode.
- release correct resource
Signed-off-by: Jochen Karrer <j.karrer@lightmaze.com>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Cc: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Patch indents dmfe.txt to look like other docs. It adds a tip about CNET
cards using Davicom chipsets. Also it removes parts where it refers to how
to build driver out-of-kernel which seems to be cruft from times where the
driver was out of the kernel.
Signed-off-by: Ismail Donmez <ismail@kde.org.tr>
Signed-off-by: Domen Puncer <domen@coderock.org>
Cc: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Fix int vs. pm_message_t confusion in airo. Should change no code.
Signed-off-by: Pavel Machek <pavel@suse.cz>
Cc: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
This is a fix for the interrupt handler in the defxx driver to use
irqreturn_t. Beside the obvious fix of returning a proper status at all,
it actually checks board registers as appropriate for determining if an
interrupt has been recorded in the bus-specific interface logic.
The patch also includes an obvious one-line fix for SET_NETDEV_DEV needed
for the EISA variation, for which I've decided there is no point in sending
separately.
Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org>
Cc: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
drivers/net/tulip/dmfe.c: In function `dmfe_parse_srom':
drivers/net/tulip/dmfe.c:1805: warning: passing arg 1 of `__le16_to_cpup' from incompatible pointer type
drivers/net/tulip/dmfe.c:1817: warning: passing arg 1 of `__le32_to_cpup' from incompatible pointer type
drivers/net/tulip/dmfe.c:1817: warning: passing arg 1 of `__le32_to_cpup' from incompatible pointer type
This is basically a guess:
Cc: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
The 8129/8130 support is a sub-option that is not visible if the user
hasn't enabled the 8139 support.
Let's make it a bit easier for users to find the driver for their nic.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
1) netlink_release() should only decrement the hash entry
count if the socket was actually hashed.
This was causing hash->entries to underflow, which
resulting in all kinds of troubles.
On 64-bit systems, this would cause the following
conditional to erroneously trigger:
err = -ENOMEM;
if (BITS_PER_LONG > 32 && unlikely(hash->entries >= UINT_MAX))
goto err;
2) netlink_autobind() needs to propagate the error return from
netlink_insert(). Otherwise, callers will not see the error
as they should and thus try to operate on a socket with a zero pid,
which is very bad.
However, it should not propagate -EBUSY. If two threads race
to autobind the socket, that is fine. This is consistent with the
autobind behavior in other protocols.
So bug #1 above, combined with this one, resulted in hangs
on netlink_sendmsg() calls to the rtnetlink socket. We'd try
to do the user sendmsg() with the socket's pid set to zero,
later we do a socket lookup using that pid (via the value we
stashed away in NETLINK_CB(skb).pid), but that won't give us the
user socket, it will give us the rtnetlink socket. So when we
try to wake up the receive queue, we dive back into rtnetlink_rcv()
which tries to recursively take the rtnetlink semaphore.
Thanks to Jakub Jelink for providing backtraces. Also, thanks to
Herbert Xu for supplying debugging patches to help track this down,
and also finding a mistake in an earlier version of this fix.
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch contains the follwing cleanups:
- make needlessly global code static
- remove obsolete Emacs settings
Signed-off-by: Adrian Bunk <bunk@stusta.de>
We're using __be16 in userland visible types, so we
have to include asm/byteorder.h so that works.
Signed-off-by: David S. Miller <davem@davemloft.net>
During some performance diagnostics I stumbled on this slightly wasteful
code in pcnet_cs.c which I made the patch included at the bottom for (two
minor comment fixes included).
Improvement:
instead of *always* calculating
lea 0x2c0(%edx),%ebx
and then additionally doing the
mov %edx,0xc0(%ebx)
addition *if we need it*,
we now do the *whole* calculation of
mov %edx,0x380(%ebx)
*only* if we need it.
This even manages to save us a whole 16-byte alignment buffer loss
in this compilation case.
Result: slightly improves IRQ handler performance in both shared and
non-shared IRQ case, which should make my rusty P3/700 a slight bit happier.
Thank you for your support,
Andreas Mohr
old asm result (using gcc 3.3.5):
000015a0 <ei_irq_wrapper>:
15a0: 55 push %ebp
15a1: 89 e5 mov %esp,%ebp
15a3: 53 push %ebx
15a4: 8d 9a c0 02 00 00 lea 0x2c0(%edx),%ebx
15aa: e8 fc ff ff ff call 15ab <ei_irq_wrapper+0xb>
15af: 83 f8 01 cmp $0x1,%eax
15b2: 74 03 je 15b7 <ei_irq_wrapper+0x17>
15b4: 5b pop %ebx
15b5: 5d pop %ebp
15b6: c3 ret
15b7: 31 d2 xor %edx,%edx
15b9: 89 93 c0 00 00 00 mov %edx,0xc0(%ebx)
15bf: eb f3 jmp 15b4 <ei_irq_wrapper+0x14>
15c1: eb 0d jmp 15d0 <ei_watchdog>
15c3: 90 nop
15c4: 90 nop
15c5: 90 nop
15c6: 90 nop
15c7: 90 nop
15c8: 90 nop
15c9: 90 nop
15ca: 90 nop
15cb: 90 nop
15cc: 90 nop
15cd: 90 nop
15ce: 90 nop
15cf: 90 nop
000015d0 <ei_watchdog>:
new asm result:
000015a0 <ei_irq_wrapper>:
15a0: 55 push %ebp
15a1: 89 e5 mov %esp,%ebp
15a3: 53 push %ebx
15a4: 89 d3 mov %edx,%ebx
15a6: e8 fc ff ff ff call 15a7 <ei_irq_wrapper+0x7>
15ab: 83 f8 01 cmp $0x1,%eax
15ae: 74 03 je 15b3 <ei_irq_wrapper+0x13>
15b0: 5b pop %ebx
15b1: 5d pop %ebp
15b2: c3 ret
15b3: 31 d2 xor %edx,%edx
15b5: 89 93 80 03 00 00 mov %edx,0x380(%ebx)
15bb: eb f3 jmp 15b0 <ei_irq_wrapper+0x10>
15bd: 8d 76 00 lea 0x0(%esi),%esi
000015c0 <ei_watchdog>:
Signed-off-by: Andrew Morton <akpm@osdl.org>
Use the DMA_{64,32}BIT_MASK constants from dma-mapping.h when calling
pci_set_dma_mask() or pci_set_consistent_dma_mask()
This patch includes dma-mapping.h explicitly because it caused errors
on some architectures otherwise.
See http://marc.theaimsgroup.com/?t=108001993000001&r=1&w=2 for details
Signed-off-by: Tobias Klauser <tklauser@nuerscht.ch>
Signed-off-by: Domen Puncer <domen@coderock.org>
It doesn't seem to make much sense to let an "If unsure, say N." option
default to y.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since it is tristate when we offer it as a choice, we should
definte it also as tristate when forcing it as the default.
Otherwise kconfig warns.
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure the code compiles with and without ARLAN_ENTRY_EXIT_DEBUGGING.
Only provide parameter descriptions when parameters are defined.
Remove "arlan_"-prefix to shape up built-in parameter names:
arlan.arlan_debug -> arlan.debug
arlan.arlan_EEPROM_bad -> arlan.EEPROM_bad
arlan.arlan_entry_and_exit_debug -> arlan.entry_and_exit_debug
arlan.arlan_entry_debug -> arlan.entry_debug
arlan.arlan_exit_debug -> arlan.exit_debug
Signed-off-by: Magnus Damm <damm@opensource.se>
Use the DMA_32BIT_MASK constant from dma-mapping.h when calling
pci_set_dma_mask() or pci_set_consistent_dma_mask() instead of custom
macros.
This patch includes dma-mapping.h explicitly because it caused errors
on some architectures otherwise.
See http://marc.theaimsgroup.com/?t=108001993000001&r=1&w=2 for details
Signed-off-by: Tobias Klauser <tklauser@nuerscht.ch>
The spin loop in 8139cp is limited to 100 iterations when pulling hardware
stats. There is no allowance for processor speed so on a fast machine, the
stats may not be available that fast. Also, if the board doesn't return
soon enough make sure turn the address back off to prevent later updates
when memory has gone away.
David S. Miller