diff --git a/CREDITS b/CREDITS
index 5b1edf3a38a2..7fb4c73e0228 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3642,11 +3642,9 @@ S: Beaverton, OR 97005
S: USA
N: Michal Wronski
-E: wrona@mat.uni.torun.pl
-W: http://www.mat.uni.torun.pl/~wrona
+E: Michal.Wronski@motorola.com
D: POSIX message queues fs (with K. Benedyczak)
-S: ul. Teczowa 23/12
-S: 80-680 Gdansk-Sobieszewo
+S: Krakow
S: Poland
N: Frank Xia
diff --git a/Documentation/Changes b/Documentation/Changes
index 783ddc3ce4e8..86b86399d61d 100644
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -139,9 +139,14 @@ You'll probably want to upgrade.
Ksymoops
--------
-If the unthinkable happens and your kernel oopses, you'll need a 2.4
-version of ksymoops to decode the report; see REPORTING-BUGS in the
-root of the Linux source for more information.
+If the unthinkable happens and your kernel oopses, you may need the
+ksymoops tool to decode it, but in most cases you don't.
+In the 2.6 kernel it is generally preferred to build the kernel with
+CONFIG_KALLSYMS so that it produces readable dumps that can be used as-is
+(this also produces better output than ksymoops).
+If for some reason your kernel is not build with CONFIG_KALLSYMS and
+you have no way to rebuild and reproduce the Oops with that option, then
+you can still decode that Oops with ksymoops.
Module-Init-Tools
-----------------
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index fa3e29ad8a46..7018f5c6a447 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -10,7 +10,7 @@ DOCBOOKS := wanbook.xml z8530book.xml mcabook.xml videobook.xml \
kernel-hacking.xml kernel-locking.xml deviceiobook.xml \
procfs-guide.xml writing_usb_driver.xml \
sis900.xml kernel-api.xml journal-api.xml lsm.xml usb.xml \
- gadget.xml libata.xml mtdnand.xml librs.xml
+ gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml
###
# The build process is as follows (targets):
diff --git a/Documentation/DocBook/journal-api.tmpl b/Documentation/DocBook/journal-api.tmpl
index 341aaa4ce481..2077f9a28c19 100644
--- a/Documentation/DocBook/journal-api.tmpl
+++ b/Documentation/DocBook/journal-api.tmpl
@@ -306,7 +306,7 @@ an example.
Journal Level
!Efs/jbd/journal.c
-!Efs/jbd/recovery.c
+!Ifs/jbd/recovery.c
Transasction Level
!Efs/jbd/transaction.c
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index ec474e5a25ed..a8316b1a3e3d 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -118,7 +118,7 @@ X!Ilib/string.c
User Space Memory Access
!Iinclude/asm-i386/uaccess.h
-!Iarch/i386/lib/usercopy.c
+!Earch/i386/lib/usercopy.c
More Memory Management Functions
!Iinclude/linux/rmap.h
@@ -174,7 +174,6 @@ X!Ilib/string.c
The Linux VFS
The Filesystem types
!Iinclude/linux/fs.h
-!Einclude/linux/fs.h
The Directory Cache
!Efs/dcache.c
@@ -266,7 +265,7 @@ X!Ekernel/module.c
Hardware Interfaces
Interrupt Handling
-!Ikernel/irq/manage.c
+!Ekernel/irq/manage.c
Resources Management
@@ -501,7 +500,7 @@ KAO -->
!Edrivers/video/modedb.c
Frame Buffer Macintosh Video Mode Database
-!Idrivers/video/macmodes.c
+!Edrivers/video/macmodes.c
Frame Buffer Fonts
diff --git a/Documentation/DocBook/rapidio.tmpl b/Documentation/DocBook/rapidio.tmpl
new file mode 100644
index 000000000000..1becf27ba27e
--- /dev/null
+++ b/Documentation/DocBook/rapidio.tmpl
@@ -0,0 +1,160 @@
+
+
+ ]>
+
+
+
+ RapidIO Subsystem Guide
+
+
+
+ Matt
+ Porter
+
+
+ mporter@kernel.crashing.org
+ mporter@mvista.com
+
+
+
+
+
+
+ 2005
+ MontaVista Software, Inc.
+
+
+
+
+ This documentation is free software; you can redistribute
+ it and/or modify it under the terms of the GNU General Public
+ License version 2 as published by the Free Software Foundation.
+
+
+
+ This program is distributed in the hope that it will be
+ useful, but WITHOUT ANY WARRANTY; without even the implied
+ warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ See the GNU General Public License for more details.
+
+
+
+ You should have received a copy of the GNU General Public
+ License along with this program; if not, write to the Free
+ Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ MA 02111-1307 USA
+
+
+
+ For more details see the file COPYING in the source
+ distribution of Linux.
+
+
+
+
+
+
+
+ Introduction
+
+ RapidIO is a high speed switched fabric interconnect with
+ features aimed at the embedded market. RapidIO provides
+ support for memory-mapped I/O as well as message-based
+ transactions over the switched fabric network. RapidIO has
+ a standardized discovery mechanism not unlike the PCI bus
+ standard that allows simple detection of devices in a
+ network.
+
+
+ This documentation is provided for developers intending
+ to support RapidIO on new architectures, write new drivers,
+ or to understand the subsystem internals.
+
+
+
+
+ Known Bugs and Limitations
+
+
+ Bugs
+ None. ;)
+
+
+ Limitations
+
+
+ Access/management of RapidIO memory regions is not supported
+ Multiple host enumeration is not supported
+
+
+
+
+
+
+ RapidIO driver interface
+
+ Drivers are provided a set of calls in order
+ to interface with the subsystem to gather info
+ on devices, request/map memory region resources,
+ and manage mailboxes/doorbells.
+
+
+ Functions
+!Iinclude/linux/rio_drv.h
+!Edrivers/rapidio/rio-driver.c
+!Edrivers/rapidio/rio.c
+
+
+
+
+ Internals
+
+
+ This chapter contains the autogenerated documentation of the RapidIO
+ subsystem.
+
+
+ Structures
+!Iinclude/linux/rio.h
+
+ Enumeration and Discovery
+!Idrivers/rapidio/rio-scan.c
+
+ Driver functionality
+!Idrivers/rapidio/rio.c
+!Idrivers/rapidio/rio-access.c
+
+ Device model support
+!Idrivers/rapidio/rio-driver.c
+
+ Sysfs support
+!Idrivers/rapidio/rio-sysfs.c
+
+ PPC32 support
+!Iarch/ppc/kernel/rio.c
+!Earch/ppc/syslib/ppc85xx_rio.c
+!Iarch/ppc/syslib/ppc85xx_rio.c
+
+
+
+
+ Credits
+
+ The following people have contributed to the RapidIO
+ subsystem directly or indirectly:
+
+ Matt Portermporter@kernel.crashing.org
+ Randy Vinsonrvinson@mvista.com
+ Dan Malekdan@embeddedalley.com
+
+
+
+ The following people have contributed to this document:
+
+ Matt Portermporter@kernel.crashing.org
+
+
+
+
diff --git a/Documentation/MSI-HOWTO.txt b/Documentation/MSI-HOWTO.txt
index 63edc5f847c4..3ec6c720b016 100644
--- a/Documentation/MSI-HOWTO.txt
+++ b/Documentation/MSI-HOWTO.txt
@@ -10,14 +10,22 @@
This guide describes the basics of Message Signaled Interrupts (MSI),
the advantages of using MSI over traditional interrupt mechanisms,
and how to enable your driver to use MSI or MSI-X. Also included is
-a Frequently Asked Questions.
+a Frequently Asked Questions (FAQ) section.
+
+1.1 Terminology
+
+PCI devices can be single-function or multi-function. In either case,
+when this text talks about enabling or disabling MSI on a "device
+function," it is referring to one specific PCI device and function and
+not to all functions on a PCI device (unless the PCI device has only
+one function).
2. Copyright 2003 Intel Corporation
3. What is MSI/MSI-X?
Message Signaled Interrupt (MSI), as described in the PCI Local Bus
-Specification Revision 2.3 or latest, is an optional feature, and a
+Specification Revision 2.3 or later, is an optional feature, and a
required feature for PCI Express devices. MSI enables a device function
to request service by sending an Inbound Memory Write on its PCI bus to
the FSB as a Message Signal Interrupt transaction. Because MSI is
@@ -27,7 +35,7 @@ supported.
A PCI device that supports MSI must also support pin IRQ assertion
interrupt mechanism to provide backward compatibility for systems that
-do not support MSI. In Systems, which support MSI, the bus driver is
+do not support MSI. In systems which support MSI, the bus driver is
responsible for initializing the message address and message data of
the device function's MSI/MSI-X capability structure during device
initial configuration.
@@ -61,17 +69,17 @@ over the MSI capability structure as described below.
- MSI and MSI-X both support per-vector masking. Per-vector
masking is an optional extension of MSI but a required
- feature for MSI-X. Per-vector masking provides the kernel
- the ability to mask/unmask MSI when servicing its software
- interrupt service routing handler. If per-vector masking is
+ feature for MSI-X. Per-vector masking provides the kernel the
+ ability to mask/unmask a single MSI while running its
+ interrupt service routine. If per-vector masking is
not supported, then the device driver should provide the
hardware/software synchronization to ensure that the device
generates MSI when the driver wants it to do so.
4. Why use MSI?
-As a benefit the simplification of board design, MSI allows board
-designers to remove out of band interrupt routing. MSI is another
+As a benefit to the simplification of board design, MSI allows board
+designers to remove out-of-band interrupt routing. MSI is another
step towards a legacy-free environment.
Due to increasing pressure on chipset and processor packages to
@@ -87,7 +95,7 @@ support. As a result, the PCI Express technology requires MSI
support for better interrupt performance.
Using MSI enables the device functions to support two or more
-vectors, which can be configured to target different CPU's to
+vectors, which can be configured to target different CPUs to
increase scalability.
5. Configuring a driver to use MSI/MSI-X
@@ -119,13 +127,13 @@ pci_enable_msi() explicitly.
int pci_enable_msi(struct pci_dev *dev)
-With this new API, any existing device driver, which like to have
-MSI enabled on its device function, must call this API to enable MSI
+With this new API, a device driver that wants to have MSI
+enabled on its device function must call this API to enable MSI.
A successful call will initialize the MSI capability structure
with ONE vector, regardless of whether a device function is
capable of supporting multiple messages. This vector replaces the
-pre-assigned dev->irq with a new MSI vector. To avoid the conflict
-of new assigned vector with existing pre-assigned vector requires
+pre-assigned dev->irq with a new MSI vector. To avoid a conflict
+of the new assigned vector with existing pre-assigned vector requires
a device driver to call this API before calling request_irq().
5.2.2 API pci_disable_msi
@@ -137,14 +145,14 @@ when a device driver is unloading. This API restores dev->irq with
the pre-assigned IOAPIC vector and switches a device's interrupt
mode to PCI pin-irq assertion/INTx emulation mode.
-Note that a device driver should always call free_irq() on MSI vector
-it has done request_irq() on before calling this API. Failure to do
-so results a BUG_ON() and a device will be left with MSI enabled and
+Note that a device driver should always call free_irq() on the MSI vector
+that it has done request_irq() on before calling this API. Failure to do
+so results in a BUG_ON() and a device will be left with MSI enabled and
leaks its vector.
5.2.3 MSI mode vs. legacy mode diagram
-The below diagram shows the events, which switches the interrupt
+The below diagram shows the events which switch the interrupt
mode on the MSI-capable device function between MSI mode and
PIN-IRQ assertion mode.
@@ -155,9 +163,9 @@ PIN-IRQ assertion mode.
------------ pci_disable_msi ------------------------
-Figure 1.0 MSI Mode vs. Legacy Mode
+Figure 1. MSI Mode vs. Legacy Mode
-In Figure 1.0, a device operates by default in legacy mode. Legacy
+In Figure 1, a device operates by default in legacy mode. Legacy
in this context means PCI pin-irq assertion or PCI-Express INTx
emulation. A successful MSI request (using pci_enable_msi()) switches
a device's interrupt mode to MSI mode. A pre-assigned IOAPIC vector
@@ -166,11 +174,11 @@ assigned MSI vector will replace dev->irq.
To return back to its default mode, a device driver should always call
pci_disable_msi() to undo the effect of pci_enable_msi(). Note that a
-device driver should always call free_irq() on MSI vector it has done
-request_irq() on before calling pci_disable_msi(). Failure to do so
-results a BUG_ON() and a device will be left with MSI enabled and
+device driver should always call free_irq() on the MSI vector it has
+done request_irq() on before calling pci_disable_msi(). Failure to do
+so results in a BUG_ON() and a device will be left with MSI enabled and
leaks its vector. Otherwise, the PCI subsystem restores a device's
-dev->irq with a pre-assigned IOAPIC vector and marks released
+dev->irq with a pre-assigned IOAPIC vector and marks the released
MSI vector as unused.
Once being marked as unused, there is no guarantee that the PCI
@@ -178,8 +186,8 @@ subsystem will reserve this MSI vector for a device. Depending on
the availability of current PCI vector resources and the number of
MSI/MSI-X requests from other drivers, this MSI may be re-assigned.
-For the case where the PCI subsystem re-assigned this MSI vector
-another driver, a request to switching back to MSI mode may result
+For the case where the PCI subsystem re-assigns this MSI vector to
+another driver, a request to switch back to MSI mode may result
in being assigned a different MSI vector or a failure if no more
vectors are available.
@@ -208,12 +216,12 @@ Unlike the function pci_enable_msi(), the function pci_enable_msix()
does not replace the pre-assigned IOAPIC dev->irq with a new MSI
vector because the PCI subsystem writes the 1:1 vector-to-entry mapping
into the field vector of each element contained in a second argument.
-Note that the pre-assigned IO-APIC dev->irq is valid only if the device
-operates in PIN-IRQ assertion mode. In MSI-X mode, any attempt of
+Note that the pre-assigned IOAPIC dev->irq is valid only if the device
+operates in PIN-IRQ assertion mode. In MSI-X mode, any attempt at
using dev->irq by the device driver to request for interrupt service
may result unpredictabe behavior.
-For each MSI-X vector granted, a device driver is responsible to call
+For each MSI-X vector granted, a device driver is responsible for calling
other functions like request_irq(), enable_irq(), etc. to enable
this vector with its corresponding interrupt service handler. It is
a device driver's choice to assign all vectors with the same
@@ -224,13 +232,13 @@ service handler.
The PCI 3.0 specification has implementation notes that MMIO address
space for a device's MSI-X structure should be isolated so that the
-software system can set different page for controlling accesses to
-the MSI-X structure. The implementation of MSI patch requires the PCI
+software system can set different pages for controlling accesses to the
+MSI-X structure. The implementation of MSI support requires the PCI
subsystem, not a device driver, to maintain full control of the MSI-X
-table/MSI-X PBA and MMIO address space of the MSI-X table/MSI-X PBA.
-A device driver is prohibited from requesting the MMIO address space
-of the MSI-X table/MSI-X PBA. Otherwise, the PCI subsystem will fail
-enabling MSI-X on its hardware device when it calls the function
+table/MSI-X PBA (Pending Bit Array) and MMIO address space of the MSI-X
+table/MSI-X PBA. A device driver is prohibited from requesting the MMIO
+address space of the MSI-X table/MSI-X PBA. Otherwise, the PCI subsystem
+will fail enabling MSI-X on its hardware device when it calls the function
pci_enable_msix().
5.3.2 Handling MSI-X allocation
@@ -274,9 +282,9 @@ For the case where fewer MSI-X vectors are allocated to a function
than requested, the function pci_enable_msix() will return the
maximum number of MSI-X vectors available to the caller. A device
driver may re-send its request with fewer or equal vectors indicated
-in a return. For example, if a device driver requests 5 vectors, but
-the number of available vectors is 3 vectors, a value of 3 will be a
-return as a result of pci_enable_msix() call. A function could be
+in the return. For example, if a device driver requests 5 vectors, but
+the number of available vectors is 3 vectors, a value of 3 will be
+returned as a result of pci_enable_msix() call. A function could be
designed for its driver to use only 3 MSI-X table entries as
different combinations as ABC--, A-B-C, A--CB, etc. Note that this
patch does not support multiple entries with the same vector. Such
@@ -285,49 +293,46 @@ as ABBCC, AABCC, BCCBA, etc will result as a failure by the function
pci_enable_msix(). Below are the reasons why supporting multiple
entries with the same vector is an undesirable solution.
- - The PCI subsystem can not determine which entry, which
- generated the message, to mask/unmask MSI while handling
+ - The PCI subsystem cannot determine the entry that
+ generated the message to mask/unmask MSI while handling
software driver ISR. Attempting to walk through all MSI-X
table entries (2048 max) to mask/unmask any match vector
is an undesirable solution.
- - Walk through all MSI-X table entries (2048 max) to handle
+ - Walking through all MSI-X table entries (2048 max) to handle
SMP affinity of any match vector is an undesirable solution.
5.3.4 API pci_enable_msix
-int pci_enable_msix(struct pci_dev *dev, u32 *entries, int nvec)
+int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
This API enables a device driver to request the PCI subsystem
-for enabling MSI-X messages on its hardware device. Depending on
+to enable MSI-X messages on its hardware device. Depending on
the availability of PCI vectors resources, the PCI subsystem enables
-either all or nothing.
+either all or none of the requested vectors.
-Argument dev points to the device (pci_dev) structure.
+Argument 'dev' points to the device (pci_dev) structure.
-Argument entries is a pointer of unsigned integer type. The number of
-elements is indicated in argument nvec. The content of each element
-will be mapped to the following struct defined in /driver/pci/msi.h.
+Argument 'entries' is a pointer to an array of msix_entry structs.
+The number of entries is indicated in argument 'nvec'.
+struct msix_entry is defined in /driver/pci/msi.h:
struct msix_entry {
u16 vector; /* kernel uses to write alloc vector */
u16 entry; /* driver uses to specify entry */
};
-A device driver is responsible for initializing the field entry of
-each element with unique entry supported by MSI-X table. Otherwise,
+A device driver is responsible for initializing the field 'entry' of
+each element with a unique entry supported by MSI-X table. Otherwise,
-EINVAL will be returned as a result. A successful return of zero
-indicates the PCI subsystem completes initializing each of requested
+indicates the PCI subsystem completed initializing each of the requested
entries of the MSI-X table with message address and message data.
Last but not least, the PCI subsystem will write the 1:1
-vector-to-entry mapping into the field vector of each element. A
-device driver is responsible of keeping track of allocated MSI-X
+vector-to-entry mapping into the field 'vector' of each element. A
+device driver is responsible for keeping track of allocated MSI-X
vectors in its internal data structure.
-Argument nvec is an integer indicating the number of messages
-requested.
-
-A return of zero indicates that the number of MSI-X vectors is
+A return of zero indicates that the number of MSI-X vectors was
successfully allocated. A return of greater than zero indicates
MSI-X vector shortage. Or a return of less than zero indicates
a failure. This failure may be a result of duplicate entries
@@ -341,12 +346,12 @@ void pci_disable_msix(struct pci_dev *dev)
This API should always be used to undo the effect of pci_enable_msix()
when a device driver is unloading. Note that a device driver should
always call free_irq() on all MSI-X vectors it has done request_irq()
-on before calling this API. Failure to do so results a BUG_ON() and
+on before calling this API. Failure to do so results in a BUG_ON() and
a device will be left with MSI-X enabled and leaks its vectors.
5.3.6 MSI-X mode vs. legacy mode diagram
-The below diagram shows the events, which switches the interrupt
+The below diagram shows the events which switch the interrupt
mode on the MSI-X capable device function between MSI-X mode and
PIN-IRQ assertion mode (legacy).
@@ -356,22 +361,22 @@ PIN-IRQ assertion mode (legacy).
| | ===============> | |
------------ pci_disable_msix ------------------------
-Figure 2.0 MSI-X Mode vs. Legacy Mode
+Figure 2. MSI-X Mode vs. Legacy Mode
-In Figure 2.0, a device operates by default in legacy mode. A
+In Figure 2, a device operates by default in legacy mode. A
successful MSI-X request (using pci_enable_msix()) switches a
device's interrupt mode to MSI-X mode. A pre-assigned IOAPIC vector
stored in dev->irq will be saved by the PCI subsystem; however,
unlike MSI mode, the PCI subsystem will not replace dev->irq with
assigned MSI-X vector because the PCI subsystem already writes the 1:1
-vector-to-entry mapping into the field vector of each element
+vector-to-entry mapping into the field 'vector' of each element
specified in second argument.
To return back to its default mode, a device driver should always call
pci_disable_msix() to undo the effect of pci_enable_msix(). Note that
a device driver should always call free_irq() on all MSI-X vectors it
has done request_irq() on before calling pci_disable_msix(). Failure
-to do so results a BUG_ON() and a device will be left with MSI-X
+to do so results in a BUG_ON() and a device will be left with MSI-X
enabled and leaks its vectors. Otherwise, the PCI subsystem switches a
device function's interrupt mode from MSI-X mode to legacy mode and
marks all allocated MSI-X vectors as unused.
@@ -383,53 +388,56 @@ MSI/MSI-X requests from other drivers, these MSI-X vectors may be
re-assigned.
For the case where the PCI subsystem re-assigned these MSI-X vectors
-to other driver, a request to switching back to MSI-X mode may result
+to other drivers, a request to switch back to MSI-X mode may result
being assigned with another set of MSI-X vectors or a failure if no
more vectors are available.
-5.4 Handling function implementng both MSI and MSI-X capabilities
+5.4 Handling function implementing both MSI and MSI-X capabilities
For the case where a function implements both MSI and MSI-X
capabilities, the PCI subsystem enables a device to run either in MSI
mode or MSI-X mode but not both. A device driver determines whether it
wants MSI or MSI-X enabled on its hardware device. Once a device
-driver requests for MSI, for example, it is prohibited to request for
+driver requests for MSI, for example, it is prohibited from requesting
MSI-X; in other words, a device driver is not permitted to ping-pong
between MSI mod MSI-X mode during a run-time.
5.5 Hardware requirements for MSI/MSI-X support
+
MSI/MSI-X support requires support from both system hardware and
individual hardware device functions.
5.5.1 System hardware support
+
Since the target of MSI address is the local APIC CPU, enabling
-MSI/MSI-X support in Linux kernel is dependent on whether existing
-system hardware supports local APIC. Users should verify their
-system whether it runs when CONFIG_X86_LOCAL_APIC=y.
+MSI/MSI-X support in the Linux kernel is dependent on whether existing
+system hardware supports local APIC. Users should verify that their
+system supports local APIC operation by testing that it runs when
+CONFIG_X86_LOCAL_APIC=y.
In SMP environment, CONFIG_X86_LOCAL_APIC is automatically set;
however, in UP environment, users must manually set
CONFIG_X86_LOCAL_APIC. Once CONFIG_X86_LOCAL_APIC=y, setting
-CONFIG_PCI_MSI enables the VECTOR based scheme and
-the option for MSI-capable device drivers to selectively enable
-MSI/MSI-X.
+CONFIG_PCI_MSI enables the VECTOR based scheme and the option for
+MSI-capable device drivers to selectively enable MSI/MSI-X.
Note that CONFIG_X86_IO_APIC setting is irrelevant because MSI/MSI-X
vector is allocated new during runtime and MSI/MSI-X support does not
depend on BIOS support. This key independency enables MSI/MSI-X
-support on future IOxAPIC free platform.
+support on future IOxAPIC free platforms.
5.5.2 Device hardware support
+
The hardware device function supports MSI by indicating the
MSI/MSI-X capability structure on its PCI capability list. By
default, this capability structure will not be initialized by
the kernel to enable MSI during the system boot. In other words,
the device function is running on its default pin assertion mode.
Note that in many cases the hardware supporting MSI have bugs,
-which may result in system hang. The software driver of specific
-MSI-capable hardware is responsible for whether calling
+which may result in system hangs. The software driver of specific
+MSI-capable hardware is responsible for deciding whether to call
pci_enable_msi or not. A return of zero indicates the kernel
-successfully initializes the MSI/MSI-X capability structure of the
+successfully initialized the MSI/MSI-X capability structure of the
device function. The device function is now running on MSI/MSI-X mode.
5.6 How to tell whether MSI/MSI-X is enabled on device function
@@ -439,10 +447,10 @@ pci_enable_msi()/pci_enable_msix() indicates to a device driver that
its device function is initialized successfully and ready to run in
MSI/MSI-X mode.
-At the user level, users can use command 'cat /proc/interrupts'
-to display the vector allocated for a device and its interrupt
-MSI/MSI-X mode ("PCI MSI"/"PCI MSIX"). Below shows below MSI mode is
-enabled on a SCSI Adaptec 39320D Ultra320.
+At the user level, users can use the command 'cat /proc/interrupts'
+to display the vectors allocated for devices and their interrupt
+MSI/MSI-X modes ("PCI-MSI"/"PCI-MSI-X"). Below shows MSI mode is
+enabled on a SCSI Adaptec 39320D Ultra320 controller.
CPU0 CPU1
0: 324639 0 IO-APIC-edge timer
@@ -453,8 +461,8 @@ enabled on a SCSI Adaptec 39320D Ultra320.
15: 1 0 IO-APIC-edge ide1
169: 0 0 IO-APIC-level uhci-hcd
185: 0 0 IO-APIC-level uhci-hcd
-193: 138 10 PCI MSI aic79xx
-201: 30 0 PCI MSI aic79xx
+193: 138 10 PCI-MSI aic79xx
+201: 30 0 PCI-MSI aic79xx
225: 30 0 IO-APIC-level aic7xxx
233: 30 0 IO-APIC-level aic7xxx
NMI: 0 0
@@ -490,8 +498,8 @@ target address set as 0xfeexxxxx, as conformed to PCI
specification 2.3 or latest, then it should work.
Q4. From the driver point of view, if the MSI is lost because
-of the errors occur during inbound memory write, then it may
-wait for ever. Is there a mechanism for it to recover?
+of errors occurring during inbound memory write, then it may
+wait forever. Is there a mechanism for it to recover?
A4. Since the target of the transaction is an inbound memory
write, all transaction termination conditions (Retry,
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 354d89c78377..15da16861fa3 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -772,8 +772,6 @@ RCU pointer/list traversal:
list_for_each_entry_rcu
list_for_each_continue_rcu (to be deprecated in favor of new
list_for_each_entry_continue_rcu)
- hlist_for_each_rcu (to be deprecated in favor of
- hlist_for_each_entry_rcu)
hlist_for_each_entry_rcu
RCU pointer update:
diff --git a/Documentation/device-mapper/snapshot.txt b/Documentation/device-mapper/snapshot.txt
index dca274ff4005..a5009c8300f3 100644
--- a/Documentation/device-mapper/snapshot.txt
+++ b/Documentation/device-mapper/snapshot.txt
@@ -19,7 +19,6 @@ There are two dm targets available: snapshot and snapshot-origin.
*) snapshot-origin
which will normally have one or more snapshots based on it.
-You must create the snapshot-origin device before you can create snapshots.
Reads will be mapped directly to the backing device. For each write, the
original data will be saved in the of each snapshot to keep
its visible content unchanged, at least until the fills up.
@@ -27,7 +26,7 @@ its visible content unchanged, at least until the fills up.
*) snapshot
-A snapshot is created of the block device. Changed chunks of
+A snapshot of the block device is created. Changed chunks of
sectors will be stored on the . Writes will
only go to the . Reads will come from the or
from for unchanged data. will often be
@@ -37,6 +36,8 @@ the amount of free space and expand the before it fills up.
is P (Persistent) or N (Not persistent - will not survive
after reboot).
+The difference is that for transient snapshots less metadata must be
+saved on disk - they can be kept in memory by the kernel.
How this is used by LVM2
diff --git a/Documentation/fb/vesafb.txt b/Documentation/fb/vesafb.txt
index 62db6758d1c1..ee277dd204b0 100644
--- a/Documentation/fb/vesafb.txt
+++ b/Documentation/fb/vesafb.txt
@@ -146,10 +146,10 @@ pmipal Use the protected mode interface for palette changes.
mtrr:n setup memory type range registers for the vesafb framebuffer
where n:
- 0 - disabled (equivalent to nomtrr)
+ 0 - disabled (equivalent to nomtrr) (default)
1 - uncachable
2 - write-back
- 3 - write-combining (default)
+ 3 - write-combining
4 - write-through
If you see the following in dmesg, choose the type that matches the
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index b67189a8d8d4..decdf9917e0d 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -69,6 +69,22 @@ Who: Grant Coady
---------------------------
+What: remove EXPORT_SYMBOL(panic_timeout)
+When: April 2006
+Files: kernel/panic.c
+Why: No modular usage in the kernel.
+Who: Adrian Bunk
+
+---------------------------
+
+What: remove EXPORT_SYMBOL(insert_resource)
+When: April 2006
+Files: kernel/resource.c
+Why: No modular usage in the kernel.
+Who: Adrian Bunk
+
+---------------------------
+
What: PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl])
When: November 2005
Files: drivers/pcmcia/: pcmcia_ioctl.c
diff --git a/Documentation/filesystems/dentry-locking.txt b/Documentation/filesystems/dentry-locking.txt
new file mode 100644
index 000000000000..4c0c575a4012
--- /dev/null
+++ b/Documentation/filesystems/dentry-locking.txt
@@ -0,0 +1,173 @@
+RCU-based dcache locking model
+==============================
+
+On many workloads, the most common operation on dcache is to look up a
+dentry, given a parent dentry and the name of the child. Typically,
+for every open(), stat() etc., the dentry corresponding to the
+pathname will be looked up by walking the tree starting with the first
+component of the pathname and using that dentry along with the next
+component to look up the next level and so on. Since it is a frequent
+operation for workloads like multiuser environments and web servers,
+it is important to optimize this path.
+
+Prior to 2.5.10, dcache_lock was acquired in d_lookup and thus in
+every component during path look-up. Since 2.5.10 onwards, fast-walk
+algorithm changed this by holding the dcache_lock at the beginning and
+walking as many cached path component dentries as possible. This
+significantly decreases the number of acquisition of
+dcache_lock. However it also increases the lock hold time
+significantly and affects performance in large SMP machines. Since
+2.5.62 kernel, dcache has been using a new locking model that uses RCU
+to make dcache look-up lock-free.
+
+The current dcache locking model is not very different from the
+existing dcache locking model. Prior to 2.5.62 kernel, dcache_lock
+protected the hash chain, d_child, d_alias, d_lru lists as well as
+d_inode and several other things like mount look-up. RCU-based changes
+affect only the way the hash chain is protected. For everything else
+the dcache_lock must be taken for both traversing as well as
+updating. The hash chain updates too take the dcache_lock. The
+significant change is the way d_lookup traverses the hash chain, it
+doesn't acquire the dcache_lock for this and rely on RCU to ensure
+that the dentry has not been *freed*.
+
+
+Dcache locking details
+======================
+
+For many multi-user workloads, open() and stat() on files are very
+frequently occurring operations. Both involve walking of path names to
+find the dentry corresponding to the concerned file. In 2.4 kernel,
+dcache_lock was held during look-up of each path component. Contention
+and cache-line bouncing of this global lock caused significant
+scalability problems. With the introduction of RCU in Linux kernel,
+this was worked around by making the look-up of path components during
+path walking lock-free.
+
+
+Safe lock-free look-up of dcache hash table
+===========================================
+
+Dcache is a complex data structure with the hash table entries also
+linked together in other lists. In 2.4 kernel, dcache_lock protected
+all the lists. We applied RCU only on hash chain walking. The rest of
+the lists are still protected by dcache_lock. Some of the important
+changes are :
+
+1. The deletion from hash chain is done using hlist_del_rcu() macro
+ which doesn't initialize next pointer of the deleted dentry and
+ this allows us to walk safely lock-free while a deletion is
+ happening.
+
+2. Insertion of a dentry into the hash table is done using
+ hlist_add_head_rcu() which take care of ordering the writes - the
+ writes to the dentry must be visible before the dentry is
+ inserted. This works in conjunction with hlist_for_each_rcu() while
+ walking the hash chain. The only requirement is that all
+ initialization to the dentry must be done before
+ hlist_add_head_rcu() since we don't have dcache_lock protection
+ while traversing the hash chain. This isn't different from the
+ existing code.
+
+3. The dentry looked up without holding dcache_lock by cannot be
+ returned for walking if it is unhashed. It then may have a NULL
+ d_inode or other bogosity since RCU doesn't protect the other
+ fields in the dentry. We therefore use a flag DCACHE_UNHASHED to
+ indicate unhashed dentries and use this in conjunction with a
+ per-dentry lock (d_lock). Once looked up without the dcache_lock,
+ we acquire the per-dentry lock (d_lock) and check if the dentry is
+ unhashed. If so, the look-up is failed. If not, the reference count
+ of the dentry is increased and the dentry is returned.
+
+4. Once a dentry is looked up, it must be ensured during the path walk
+ for that component it doesn't go away. In pre-2.5.10 code, this was
+ done holding a reference to the dentry. dcache_rcu does the same.
+ In some sense, dcache_rcu path walking looks like the pre-2.5.10
+ version.
+
+5. All dentry hash chain updates must take the dcache_lock as well as
+ the per-dentry lock in that order. dput() does this to ensure that
+ a dentry that has just been looked up in another CPU doesn't get
+ deleted before dget() can be done on it.
+
+6. There are several ways to do reference counting of RCU protected
+ objects. One such example is in ipv4 route cache where deferred
+ freeing (using call_rcu()) is done as soon as the reference count
+ goes to zero. This cannot be done in the case of dentries because
+ tearing down of dentries require blocking (dentry_iput()) which
+ isn't supported from RCU callbacks. Instead, tearing down of
+ dentries happen synchronously in dput(), but actual freeing happens
+ later when RCU grace period is over. This allows safe lock-free
+ walking of the hash chains, but a matched dentry may have been
+ partially torn down. The checking of DCACHE_UNHASHED flag with
+ d_lock held detects such dentries and prevents them from being
+ returned from look-up.
+
+
+Maintaining POSIX rename semantics
+==================================
+
+Since look-up of dentries is lock-free, it can race against a
+concurrent rename operation. For example, during rename of file A to
+B, look-up of either A or B must succeed. So, if look-up of B happens
+after A has been removed from the hash chain but not added to the new
+hash chain, it may fail. Also, a comparison while the name is being
+written concurrently by a rename may result in false positive matches
+violating rename semantics. Issues related to race with rename are
+handled as described below :
+
+1. Look-up can be done in two ways - d_lookup() which is safe from
+ simultaneous renames and __d_lookup() which is not. If
+ __d_lookup() fails, it must be followed up by a d_lookup() to
+ correctly determine whether a dentry is in the hash table or
+ not. d_lookup() protects look-ups using a sequence lock
+ (rename_lock).
+
+2. The name associated with a dentry (d_name) may be changed if a
+ rename is allowed to happen simultaneously. To avoid memcmp() in
+ __d_lookup() go out of bounds due to a rename and false positive
+ comparison, the name comparison is done while holding the
+ per-dentry lock. This prevents concurrent renames during this
+ operation.
+
+3. Hash table walking during look-up may move to a different bucket as
+ the current dentry is moved to a different bucket due to rename.
+ But we use hlists in dcache hash table and they are
+ null-terminated. So, even if a dentry moves to a different bucket,
+ hash chain walk will terminate. [with a list_head list, it may not
+ since termination is when the list_head in the original bucket is
+ reached]. Since we redo the d_parent check and compare name while
+ holding d_lock, lock-free look-up will not race against d_move().
+
+4. There can be a theoretical race when a dentry keeps coming back to
+ original bucket due to double moves. Due to this look-up may
+ consider that it has never moved and can end up in a infinite loop.
+ But this is not any worse that theoretical livelocks we already
+ have in the kernel.
+
+
+Important guidelines for filesystem developers related to dcache_rcu
+====================================================================
+
+1. Existing dcache interfaces (pre-2.5.62) exported to filesystem
+ don't change. Only dcache internal implementation changes. However
+ filesystems *must not* delete from the dentry hash chains directly
+ using the list macros like allowed earlier. They must use dcache
+ APIs like d_drop() or __d_drop() depending on the situation.
+
+2. d_flags is now protected by a per-dentry lock (d_lock). All access
+ to d_flags must be protected by it.
+
+3. For a hashed dentry, checking of d_count needs to be protected by
+ d_lock.
+
+
+Papers and other documentation on dcache locking
+================================================
+
+1. Scaling dcache with RCU (http://linuxjournal.com/article.php?sid=7124).
+
+2. http://lse.sourceforge.net/locking/dcache/dcache.html
+
+
+
diff --git a/Documentation/filesystems/devfs/README b/Documentation/filesystems/devfs/README
index 54366ecc241f..aabfba24bc2e 100644
--- a/Documentation/filesystems/devfs/README
+++ b/Documentation/filesystems/devfs/README
@@ -1812,11 +1812,6 @@ it may overflow the messages buffer, but try to get as much of it as
you can
-if you get an Oops, run ksymoops to decode it so that the
-names of the offending functions are provided. A non-decoded Oops is
-pretty useless
-
-
send a copy of your devfsd configuration file(s)
send the bug report to me first.
diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.txt b/Documentation/filesystems/ramfs-rootfs-initramfs.txt
new file mode 100644
index 000000000000..b3404a032596
--- /dev/null
+++ b/Documentation/filesystems/ramfs-rootfs-initramfs.txt
@@ -0,0 +1,195 @@
+ramfs, rootfs and initramfs
+October 17, 2005
+Rob Landley
+=============================
+
+What is ramfs?
+--------------
+
+Ramfs is a very simple filesystem that exports Linux's disk caching
+mechanisms (the page cache and dentry cache) as a dynamically resizable
+ram-based filesystem.
+
+Normally all files are cached in memory by Linux. Pages of data read from
+backing store (usually the block device the filesystem is mounted on) are kept
+around in case it's needed again, but marked as clean (freeable) in case the
+Virtual Memory system needs the memory for something else. Similarly, data
+written to files is marked clean as soon as it has been written to backing
+store, but kept around for caching purposes until the VM reallocates the
+memory. A similar mechanism (the dentry cache) greatly speeds up access to
+directories.
+
+With ramfs, there is no backing store. Files written into ramfs allocate
+dentries and page cache as usual, but there's nowhere to write them to.
+This means the pages are never marked clean, so they can't be freed by the
+VM when it's looking to recycle memory.
+
+The amount of code required to implement ramfs is tiny, because all the
+work is done by the existing Linux caching infrastructure. Basically,
+you're mounting the disk cache as a filesystem. Because of this, ramfs is not
+an optional component removable via menuconfig, since there would be negligible
+space savings.
+
+ramfs and ramdisk:
+------------------
+
+The older "ram disk" mechanism created a synthetic block device out of
+an area of ram and used it as backing store for a filesystem. This block
+device was of fixed size, so the filesystem mounted on it was of fixed
+size. Using a ram disk also required unnecessarily copying memory from the
+fake block device into the page cache (and copying changes back out), as well
+as creating and destroying dentries. Plus it needed a filesystem driver
+(such as ext2) to format and interpret this data.
+
+Compared to ramfs, this wastes memory (and memory bus bandwidth), creates
+unnecessary work for the CPU, and pollutes the CPU caches. (There are tricks
+to avoid this copying by playing with the page tables, but they're unpleasantly
+complicated and turn out to be about as expensive as the copying anyway.)
+More to the point, all the work ramfs is doing has to happen _anyway_,
+since all file access goes through the page and dentry caches. The ram
+disk is simply unnecessary, ramfs is internally much simpler.
+
+Another reason ramdisks are semi-obsolete is that the introduction of
+loopback devices offered a more flexible and convenient way to create
+synthetic block devices, now from files instead of from chunks of memory.
+See losetup (8) for details.
+
+ramfs and tmpfs:
+----------------
+
+One downside of ramfs is you can keep writing data into it until you fill
+up all memory, and the VM can't free it because the VM thinks that files
+should get written to backing store (rather than swap space), but ramfs hasn't
+got any backing store. Because of this, only root (or a trusted user) should
+be allowed write access to a ramfs mount.
+
+A ramfs derivative called tmpfs was created to add size limits, and the ability
+to write the data to swap space. Normal users can be allowed write access to
+tmpfs mounts. See Documentation/filesystems/tmpfs.txt for more information.
+
+What is rootfs?
+---------------
+
+Rootfs is a special instance of ramfs, which is always present in 2.6 systems.
+(It's used internally as the starting and stopping point for searches of the
+kernel's doubly-linked list of mount points.)
+
+Most systems just mount another filesystem over it and ignore it. The
+amount of space an empty instance of ramfs takes up is tiny.
+
+What is initramfs?
+------------------
+
+All 2.6 Linux kernels contain a gzipped "cpio" format archive, which is
+extracted into rootfs when the kernel boots up. After extracting, the kernel
+checks to see if rootfs contains a file "init", and if so it executes it as PID
+1. If found, this init process is responsible for bringing the system the
+rest of the way up, including locating and mounting the real root device (if
+any). If rootfs does not contain an init program after the embedded cpio
+archive is extracted into it, the kernel will fall through to the older code
+to locate and mount a root partition, then exec some variant of /sbin/init
+out of that.
+
+All this differs from the old initrd in several ways:
+
+ - The old initrd was a separate file, while the initramfs archive is linked
+ into the linux kernel image. (The directory linux-*/usr is devoted to
+ generating this archive during the build.)
+
+ - The old initrd file was a gzipped filesystem image (in some file format,
+ such as ext2, that had to be built into the kernel), while the new
+ initramfs archive is a gzipped cpio archive (like tar only simpler,
+ see cpio(1) and Documentation/early-userspace/buffer-format.txt).
+
+ - The program run by the old initrd (which was called /initrd, not /init) did
+ some setup and then returned to the kernel, while the init program from
+ initramfs is not expected to return to the kernel. (If /init needs to hand
+ off control it can overmount / with a new root device and exec another init
+ program. See the switch_root utility, below.)
+
+ - When switching another root device, initrd would pivot_root and then
+ umount the ramdisk. But initramfs is rootfs: you can neither pivot_root
+ rootfs, nor unmount it. Instead delete everything out of rootfs to
+ free up the space (find -xdev / -exec rm '{}' ';'), overmount rootfs
+ with the new root (cd /newmount; mount --move . /; chroot .), attach
+ stdin/stdout/stderr to the new /dev/console, and exec the new init.
+
+ Since this is a remarkably persnickity process (and involves deleting
+ commands before you can run them), the klibc package introduced a helper
+ program (utils/run_init.c) to do all this for you. Most other packages
+ (such as busybox) have named this command "switch_root".
+
+Populating initramfs:
+---------------------
+
+The 2.6 kernel build process always creates a gzipped cpio format initramfs
+archive and links it into the resulting kernel binary. By default, this
+archive is empty (consuming 134 bytes on x86). The config option
+CONFIG_INITRAMFS_SOURCE (for some reason buried under devices->block devices
+in menuconfig, and living in usr/Kconfig) can be used to specify a source for
+the initramfs archive, which will automatically be incorporated into the
+resulting binary. This option can point to an existing gzipped cpio archive, a
+directory containing files to be archived, or a text file specification such
+as the following example:
+
+ dir /dev 755 0 0
+ nod /dev/console 644 0 0 c 5 1
+ nod /dev/loop0 644 0 0 b 7 0
+ dir /bin 755 1000 1000
+ slink /bin/sh busybox 777 0 0
+ file /bin/busybox initramfs/busybox 755 0 0
+ dir /proc 755 0 0
+ dir /sys 755 0 0
+ dir /mnt 755 0 0
+ file /init initramfs/init.sh 755 0 0
+
+One advantage of the text file is that root access is not required to
+set permissions or create device nodes in the new archive. (Note that those
+two example "file" entries expect to find files named "init.sh" and "busybox" in
+a directory called "initramfs", under the linux-2.6.* directory. See
+Documentation/early-userspace/README for more details.)
+
+If you don't already understand what shared libraries, devices, and paths
+you need to get a minimal root filesystem up and running, here are some
+references:
+http://www.tldp.org/HOWTO/Bootdisk-HOWTO/
+http://www.tldp.org/HOWTO/From-PowerUp-To-Bash-Prompt-HOWTO.html
+http://www.linuxfromscratch.org/lfs/view/stable/
+
+The "klibc" package (http://www.kernel.org/pub/linux/libs/klibc) is
+designed to be a tiny C library to statically link early userspace
+code against, along with some related utilities. It is BSD licensed.
+
+I use uClibc (http://www.uclibc.org) and busybox (http://www.busybox.net)
+myself. These are LGPL and GPL, respectively.
+
+In theory you could use glibc, but that's not well suited for small embedded
+uses like this. (A "hello world" program statically linked against glibc is
+over 400k. With uClibc it's 7k. Also note that glibc dlopens libnss to do
+name lookups, even when otherwise statically linked.)
+
+Future directions:
+------------------
+
+Today (2.6.14), initramfs is always compiled in, but not always used. The
+kernel falls back to legacy boot code that is reached only if initramfs does
+not contain an /init program. The fallback is legacy code, there to ensure a
+smooth transition and allowing early boot functionality to gradually move to
+"early userspace" (I.E. initramfs).
+
+The move to early userspace is necessary because finding and mounting the real
+root device is complex. Root partitions can span multiple devices (raid or
+separate journal). They can be out on the network (requiring dhcp, setting a
+specific mac address, logging into a server, etc). They can live on removable
+media, with dynamically allocated major/minor numbers and persistent naming
+issues requiring a full udev implementation to sort out. They can be
+compressed, encrypted, copy-on-write, loopback mounted, strangely partitioned,
+and so on.
+
+This kind of complexity (which inevitably includes policy) is rightly handled
+in userspace. Both klibc and busybox/uClibc are working on simple initramfs
+packages to drop into a kernel build, and when standard solutions are ready
+and widely deployed, the kernel's legacy early boot code will become obsolete
+and a candidate for the feature removal schedule.
+
+But that's a while off yet.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index f042c12e0ed2..ee4c0a8b8db7 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -3,7 +3,7 @@
Original author: Richard Gooch
- Last updated on August 25, 2005
+ Last updated on October 28, 2005
Copyright (C) 1999 Richard Gooch
Copyright (C) 2005 Pekka Enberg
@@ -11,62 +11,61 @@
This file is released under the GPLv2.
-What is it?
-===========
+Introduction
+============
-The Virtual File System (otherwise known as the Virtual Filesystem
-Switch) is the software layer in the kernel that provides the
-filesystem interface to userspace programs. It also provides an
-abstraction within the kernel which allows different filesystem
-implementations to coexist.
+The Virtual File System (also known as the Virtual Filesystem Switch)
+is the software layer in the kernel that provides the filesystem
+interface to userspace programs. It also provides an abstraction
+within the kernel which allows different filesystem implementations to
+coexist.
+
+VFS system calls open(2), stat(2), read(2), write(2), chmod(2) and so
+on are called from a process context. Filesystem locking is described
+in the document Documentation/filesystems/Locking.
-A Quick Look At How It Works
-============================
+Directory Entry Cache (dcache)
+------------------------------
-In this section I'll briefly describe how things work, before
-launching into the details. I'll start with describing what happens
-when user programs open and manipulate files, and then look from the
-other view which is how a filesystem is supported and subsequently
-mounted.
+The VFS implements the open(2), stat(2), chmod(2), and similar system
+calls. The pathname argument that is passed to them is used by the VFS
+to search through the directory entry cache (also known as the dentry
+cache or dcache). This provides a very fast look-up mechanism to
+translate a pathname (filename) into a specific dentry. Dentries live
+in RAM and are never saved to disc: they exist only for performance.
+
+The dentry cache is meant to be a view into your entire filespace. As
+most computers cannot fit all dentries in the RAM at the same time,
+some bits of the cache are missing. In order to resolve your pathname
+into a dentry, the VFS may have to resort to creating dentries along
+the way, and then loading the inode. This is done by looking up the
+inode.
-Opening a File
---------------
+The Inode Object
+----------------
-The VFS implements the open(2), stat(2), chmod(2) and similar system
-calls. The pathname argument is used by the VFS to search through the
-directory entry cache (dentry cache or "dcache"). This provides a very
-fast look-up mechanism to translate a pathname (filename) into a
-specific dentry.
+An individual dentry usually has a pointer to an inode. Inodes are
+filesystem objects such as regular files, directories, FIFOs and other
+beasts. They live either on the disc (for block device filesystems)
+or in the memory (for pseudo filesystems). Inodes that live on the
+disc are copied into the memory when required and changes to the inode
+are written back to disc. A single inode can be pointed to by multiple
+dentries (hard links, for example, do this).
-An individual dentry usually has a pointer to an inode. Inodes are the
-things that live on disc drives, and can be regular files (you know:
-those things that you write data into), directories, FIFOs and other
-beasts. Dentries live in RAM and are never saved to disc: they exist
-only for performance. Inodes live on disc and are copied into memory
-when required. Later any changes are written back to disc. The inode
-that lives in RAM is a VFS inode, and it is this which the dentry
-points to. A single inode can be pointed to by multiple dentries
-(think about hardlinks).
+To look up an inode requires that the VFS calls the lookup() method of
+the parent directory inode. This method is installed by the specific
+filesystem implementation that the inode lives in. Once the VFS has
+the required dentry (and hence the inode), we can do all those boring
+things like open(2) the file, or stat(2) it to peek at the inode
+data. The stat(2) operation is fairly simple: once the VFS has the
+dentry, it peeks at the inode data and passes some of it back to
+userspace.
-The dcache is meant to be a view into your entire filespace. Unlike
-Linus, most of us losers can't fit enough dentries into RAM to cover
-all of our filespace, so the dcache has bits missing. In order to
-resolve your pathname into a dentry, the VFS may have to resort to
-creating dentries along the way, and then loading the inode. This is
-done by looking up the inode.
-To look up an inode (usually read from disc) requires that the VFS
-calls the lookup() method of the parent directory inode. This method
-is installed by the specific filesystem implementation that the inode
-lives in. There will be more on this later.
-
-Once the VFS has the required dentry (and hence the inode), we can do
-all those boring things like open(2) the file, or stat(2) it to peek
-at the inode data. The stat(2) operation is fairly simple: once the
-VFS has the dentry, it peeks at the inode data and passes some of it
-back to userspace.
+The File Object
+---------------
Opening a file requires another operation: allocation of a file
structure (this is the kernel-side implementation of file
@@ -74,51 +73,39 @@ descriptors). The freshly allocated file structure is initialized with
a pointer to the dentry and a set of file operation member functions.
These are taken from the inode data. The open() file method is then
called so the specific filesystem implementation can do it's work. You
-can see that this is another switch performed by the VFS.
-
-The file structure is placed into the file descriptor table for the
-process.
+can see that this is another switch performed by the VFS. The file
+structure is placed into the file descriptor table for the process.
Reading, writing and closing files (and other assorted VFS operations)
is done by using the userspace file descriptor to grab the appropriate
-file structure, and then calling the required file structure method
-function to do whatever is required.
-
-For as long as the file is open, it keeps the dentry "open" (in use),
-which in turn means that the VFS inode is still in use.
-
-All VFS system calls (i.e. open(2), stat(2), read(2), write(2),
-chmod(2) and so on) are called from a process context. You should
-assume that these calls are made without any kernel locks being
-held. This means that the processes may be executing the same piece of
-filesystem or driver code at the same time, on different
-processors. You should ensure that access to shared resources is
-protected by appropriate locks.
+file structure, and then calling the required file structure method to
+do whatever is required. For as long as the file is open, it keeps the
+dentry in use, which in turn means that the VFS inode is still in use.
Registering and Mounting a Filesystem
--------------------------------------
+=====================================
-If you want to support a new kind of filesystem in the kernel, all you
-need to do is call register_filesystem(). You pass a structure
-describing the filesystem implementation (struct file_system_type)
-which is then added to an internal table of supported filesystems. You
-can do:
+To register and unregister a filesystem, use the following API
+functions:
-% cat /proc/filesystems
+ #include
-to see what filesystems are currently available on your system.
+ extern int register_filesystem(struct file_system_type *);
+ extern int unregister_filesystem(struct file_system_type *);
-When a request is made to mount a block device onto a directory in
-your filespace the VFS will call the appropriate method for the
-specific filesystem. The dentry for the mount point will then be
-updated to point to the root inode for the new filesystem.
+The passed struct file_system_type describes your filesystem. When a
+request is made to mount a device onto a directory in your filespace,
+the VFS will call the appropriate get_sb() method for the specific
+filesystem. The dentry for the mount point will then be updated to
+point to the root inode for the new filesystem.
-It's now time to look at things in more detail.
+You can see all filesystems that are registered to the kernel in the
+file /proc/filesystems.
struct file_system_type
-=======================
+-----------------------
This describes the filesystem. As of kernel 2.6.13, the following
members are defined:
@@ -197,8 +184,14 @@ A fill_super() method implementation has the following arguments:
int silent: whether or not to be silent on error
+The Superblock Object
+=====================
+
+A superblock object represents a mounted filesystem.
+
+
struct super_operations
-=======================
+-----------------------
This describes how the VFS can manipulate the superblock of your
filesystem. As of kernel 2.6.13, the following members are defined:
@@ -286,9 +279,9 @@ or bottom half).
a superblock. The second parameter indicates whether the method
should wait until the write out has been completed. Optional.
- write_super_lockfs: called when VFS is locking a filesystem and forcing
- it into a consistent state. This function is currently used by the
- Logical Volume Manager (LVM).
+ write_super_lockfs: called when VFS is locking a filesystem and
+ forcing it into a consistent state. This method is currently
+ used by the Logical Volume Manager (LVM).
unlockfs: called when VFS is unlocking a filesystem and making it writable
again.
@@ -317,8 +310,14 @@ field. This is a pointer to a "struct inode_operations" which
describes the methods that can be performed on individual inodes.
+The Inode Object
+================
+
+An inode object represents an object within the filesystem.
+
+
struct inode_operations
-=======================
+-----------------------
This describes how the VFS can manipulate an inode in your
filesystem. As of kernel 2.6.13, the following members are defined:
@@ -394,51 +393,62 @@ otherwise noted.
will probably need to call d_instantiate() just as you would
in the create() method
+ rename: called by the rename(2) system call to rename the object to
+ have the parent and name given by the second inode and dentry.
+
readlink: called by the readlink(2) system call. Only required if
you want to support reading symbolic links
follow_link: called by the VFS to follow a symbolic link to the
inode it points to. Only required if you want to support
- symbolic links. This function returns a void pointer cookie
+ symbolic links. This method returns a void pointer cookie
that is passed to put_link().
put_link: called by the VFS to release resources allocated by
- follow_link(). The cookie returned by follow_link() is passed to
- to this function as the last parameter. It is used by filesystems
- such as NFS where page cache is not stable (i.e. page that was
- installed when the symbolic link walk started might not be in the
- page cache at the end of the walk).
+ follow_link(). The cookie returned by follow_link() is passed
+ to to this method as the last parameter. It is used by
+ filesystems such as NFS where page cache is not stable
+ (i.e. page that was installed when the symbolic link walk
+ started might not be in the page cache at the end of the
+ walk).
- truncate: called by the VFS to change the size of a file. The i_size
- field of the inode is set to the desired size by the VFS before
- this function is called. This function is called by the truncate(2)
- system call and related functionality.
+ truncate: called by the VFS to change the size of a file. The
+ i_size field of the inode is set to the desired size by the
+ VFS before this method is called. This method is called by
+ the truncate(2) system call and related functionality.
permission: called by the VFS to check for access rights on a POSIX-like
filesystem.
- setattr: called by the VFS to set attributes for a file. This function is
- called by chmod(2) and related system calls.
+ setattr: called by the VFS to set attributes for a file. This method
+ is called by chmod(2) and related system calls.
- getattr: called by the VFS to get attributes of a file. This function is
- called by stat(2) and related system calls.
+ getattr: called by the VFS to get attributes of a file. This method
+ is called by stat(2) and related system calls.
setxattr: called by the VFS to set an extended attribute for a file.
- Extended attribute is a name:value pair associated with an inode. This
- function is called by setxattr(2) system call.
+ Extended attribute is a name:value pair associated with an
+ inode. This method is called by setxattr(2) system call.
- getxattr: called by the VFS to retrieve the value of an extended attribute
- name. This function is called by getxattr(2) function call.
+ getxattr: called by the VFS to retrieve the value of an extended
+ attribute name. This method is called by getxattr(2) function
+ call.
- listxattr: called by the VFS to list all extended attributes for a given
- file. This function is called by listxattr(2) system call.
+ listxattr: called by the VFS to list all extended attributes for a
+ given file. This method is called by listxattr(2) system call.
- removexattr: called by the VFS to remove an extended attribute from a file.
- This function is called by removexattr(2) system call.
+ removexattr: called by the VFS to remove an extended attribute from
+ a file. This method is called by removexattr(2) system call.
+
+
+The Address Space Object
+========================
+
+The address space object is used to identify pages in the page cache.
struct address_space_operations
-===============================
+-------------------------------
This describes how the VFS can manipulate mapping of a file to page cache in
your filesystem. As of kernel 2.6.13, the following members are defined:
@@ -502,8 +512,14 @@ struct address_space_operations {
it. An example implementation can be found in fs/ext2/xip.c.
+The File Object
+===============
+
+A file object represents a file opened by a process.
+
+
struct file_operations
-======================
+----------------------
This describes how the VFS can manipulate an open file. As of kernel
2.6.13, the following members are defined:
@@ -661,7 +677,7 @@ of child dentries. Child dentries are basically like files in a
directory.
-Directory Entry Cache APIs
+Directory Entry Cache API
--------------------------
There are a number of functions defined which permit a filesystem to
@@ -705,178 +721,24 @@ manipulate dentries:
and the dentry is returned. The caller must use d_put()
to free the dentry when it finishes using it.
-
-RCU-based dcache locking model
-------------------------------
-
-On many workloads, the most common operation on dcache is
-to look up a dentry, given a parent dentry and the name
-of the child. Typically, for every open(), stat() etc.,
-the dentry corresponding to the pathname will be looked
-up by walking the tree starting with the first component
-of the pathname and using that dentry along with the next
-component to look up the next level and so on. Since it
-is a frequent operation for workloads like multiuser
-environments and web servers, it is important to optimize
-this path.
-
-Prior to 2.5.10, dcache_lock was acquired in d_lookup and thus
-in every component during path look-up. Since 2.5.10 onwards,
-fast-walk algorithm changed this by holding the dcache_lock
-at the beginning and walking as many cached path component
-dentries as possible. This significantly decreases the number
-of acquisition of dcache_lock. However it also increases the
-lock hold time significantly and affects performance in large
-SMP machines. Since 2.5.62 kernel, dcache has been using
-a new locking model that uses RCU to make dcache look-up
-lock-free.
-
-The current dcache locking model is not very different from the existing
-dcache locking model. Prior to 2.5.62 kernel, dcache_lock
-protected the hash chain, d_child, d_alias, d_lru lists as well
-as d_inode and several other things like mount look-up. RCU-based
-changes affect only the way the hash chain is protected. For everything
-else the dcache_lock must be taken for both traversing as well as
-updating. The hash chain updates too take the dcache_lock.
-The significant change is the way d_lookup traverses the hash chain,
-it doesn't acquire the dcache_lock for this and rely on RCU to
-ensure that the dentry has not been *freed*.
+For further information on dentry locking, please refer to the document
+Documentation/filesystems/dentry-locking.txt.
-Dcache locking details
-----------------------
+Resources
+=========
-For many multi-user workloads, open() and stat() on files are
-very frequently occurring operations. Both involve walking
-of path names to find the dentry corresponding to the
-concerned file. In 2.4 kernel, dcache_lock was held
-during look-up of each path component. Contention and
-cache-line bouncing of this global lock caused significant
-scalability problems. With the introduction of RCU
-in Linux kernel, this was worked around by making
-the look-up of path components during path walking lock-free.
+(Note some of these resources are not up-to-date with the latest kernel
+ version.)
+Creating Linux virtual filesystems. 2002
+
-Safe lock-free look-up of dcache hash table
-===========================================
+The Linux Virtual File-system Layer by Neil Brown. 1999
+
-Dcache is a complex data structure with the hash table entries
-also linked together in other lists. In 2.4 kernel, dcache_lock
-protected all the lists. We applied RCU only on hash chain
-walking. The rest of the lists are still protected by dcache_lock.
-Some of the important changes are :
+A tour of the Linux VFS by Michael K. Johnson. 1996
+
-1. The deletion from hash chain is done using hlist_del_rcu() macro which
- doesn't initialize next pointer of the deleted dentry and this
- allows us to walk safely lock-free while a deletion is happening.
-
-2. Insertion of a dentry into the hash table is done using
- hlist_add_head_rcu() which take care of ordering the writes -
- the writes to the dentry must be visible before the dentry
- is inserted. This works in conjunction with hlist_for_each_rcu()
- while walking the hash chain. The only requirement is that
- all initialization to the dentry must be done before hlist_add_head_rcu()
- since we don't have dcache_lock protection while traversing
- the hash chain. This isn't different from the existing code.
-
-3. The dentry looked up without holding dcache_lock by cannot be
- returned for walking if it is unhashed. It then may have a NULL
- d_inode or other bogosity since RCU doesn't protect the other
- fields in the dentry. We therefore use a flag DCACHE_UNHASHED to
- indicate unhashed dentries and use this in conjunction with a
- per-dentry lock (d_lock). Once looked up without the dcache_lock,
- we acquire the per-dentry lock (d_lock) and check if the
- dentry is unhashed. If so, the look-up is failed. If not, the
- reference count of the dentry is increased and the dentry is returned.
-
-4. Once a dentry is looked up, it must be ensured during the path
- walk for that component it doesn't go away. In pre-2.5.10 code,
- this was done holding a reference to the dentry. dcache_rcu does
- the same. In some sense, dcache_rcu path walking looks like
- the pre-2.5.10 version.
-
-5. All dentry hash chain updates must take the dcache_lock as well as
- the per-dentry lock in that order. dput() does this to ensure
- that a dentry that has just been looked up in another CPU
- doesn't get deleted before dget() can be done on it.
-
-6. There are several ways to do reference counting of RCU protected
- objects. One such example is in ipv4 route cache where
- deferred freeing (using call_rcu()) is done as soon as
- the reference count goes to zero. This cannot be done in
- the case of dentries because tearing down of dentries
- require blocking (dentry_iput()) which isn't supported from
- RCU callbacks. Instead, tearing down of dentries happen
- synchronously in dput(), but actual freeing happens later
- when RCU grace period is over. This allows safe lock-free
- walking of the hash chains, but a matched dentry may have
- been partially torn down. The checking of DCACHE_UNHASHED
- flag with d_lock held detects such dentries and prevents
- them from being returned from look-up.
-
-
-Maintaining POSIX rename semantics
-==================================
-
-Since look-up of dentries is lock-free, it can race against
-a concurrent rename operation. For example, during rename
-of file A to B, look-up of either A or B must succeed.
-So, if look-up of B happens after A has been removed from the
-hash chain but not added to the new hash chain, it may fail.
-Also, a comparison while the name is being written concurrently
-by a rename may result in false positive matches violating
-rename semantics. Issues related to race with rename are
-handled as described below :
-
-1. Look-up can be done in two ways - d_lookup() which is safe
- from simultaneous renames and __d_lookup() which is not.
- If __d_lookup() fails, it must be followed up by a d_lookup()
- to correctly determine whether a dentry is in the hash table
- or not. d_lookup() protects look-ups using a sequence
- lock (rename_lock).
-
-2. The name associated with a dentry (d_name) may be changed if
- a rename is allowed to happen simultaneously. To avoid memcmp()
- in __d_lookup() go out of bounds due to a rename and false
- positive comparison, the name comparison is done while holding the
- per-dentry lock. This prevents concurrent renames during this
- operation.
-
-3. Hash table walking during look-up may move to a different bucket as
- the current dentry is moved to a different bucket due to rename.
- But we use hlists in dcache hash table and they are null-terminated.
- So, even if a dentry moves to a different bucket, hash chain
- walk will terminate. [with a list_head list, it may not since
- termination is when the list_head in the original bucket is reached].
- Since we redo the d_parent check and compare name while holding
- d_lock, lock-free look-up will not race against d_move().
-
-4. There can be a theoretical race when a dentry keeps coming back
- to original bucket due to double moves. Due to this look-up may
- consider that it has never moved and can end up in a infinite loop.
- But this is not any worse that theoretical livelocks we already
- have in the kernel.
-
-
-Important guidelines for filesystem developers related to dcache_rcu
-====================================================================
-
-1. Existing dcache interfaces (pre-2.5.62) exported to filesystem
- don't change. Only dcache internal implementation changes. However
- filesystems *must not* delete from the dentry hash chains directly
- using the list macros like allowed earlier. They must use dcache
- APIs like d_drop() or __d_drop() depending on the situation.
-
-2. d_flags is now protected by a per-dentry lock (d_lock). All
- access to d_flags must be protected by it.
-
-3. For a hashed dentry, checking of d_count needs to be protected
- by d_lock.
-
-
-Papers and other documentation on dcache locking
-================================================
-
-1. Scaling dcache with RCU (http://linuxjournal.com/article.php?sid=7124).
-
-2. http://lse.sourceforge.net/locking/dcache/dcache.html
+A small trail through the Linux kernel by Andries Brouwer. 2001
+
diff --git a/Documentation/hpet.txt b/Documentation/hpet.txt
index 4e7cc8d3359b..e52457581f47 100644
--- a/Documentation/hpet.txt
+++ b/Documentation/hpet.txt
@@ -1,18 +1,21 @@
High Precision Event Timer Driver for Linux
-The High Precision Event Timer (HPET) hardware is the future replacement for the 8254 and Real
-Time Clock (RTC) periodic timer functionality. Each HPET can have up two 32 timers. It is possible
-to configure the first two timers as legacy replacements for 8254 and RTC periodic. A specification
-done by INTEL and Microsoft can be found at http://www.intel.com/labs/platcomp/hpet/hpetspec.htm.
+The High Precision Event Timer (HPET) hardware is the future replacement
+for the 8254 and Real Time Clock (RTC) periodic timer functionality.
+Each HPET can have up two 32 timers. It is possible to configure the
+first two timers as legacy replacements for 8254 and RTC periodic timers.
+A specification done by Intel and Microsoft can be found at
+.
-The driver supports detection of HPET driver allocation and initialization of the HPET before the
-driver module_init routine is called. This enables platform code which uses timer 0 or 1 as the
-main timer to intercept HPET initialization. An example of this initialization can be found in
+The driver supports detection of HPET driver allocation and initialization
+of the HPET before the driver module_init routine is called. This enables
+platform code which uses timer 0 or 1 as the main timer to intercept HPET
+initialization. An example of this initialization can be found in
arch/i386/kernel/time_hpet.c.
-The driver provides two APIs which are very similar to the API found in the rtc.c driver.
-There is a user space API and a kernel space API. An example user space program is provided
-below.
+The driver provides two APIs which are very similar to the API found in
+the rtc.c driver. There is a user space API and a kernel space API.
+An example user space program is provided below.
#include
#include
@@ -290,9 +293,8 @@ The kernel API has three interfaces exported from the driver:
hpet_unregister(struct hpet_task *tp)
hpet_control(struct hpet_task *tp, unsigned int cmd, unsigned long arg)
-The kernel module using this interface fills in the ht_func and ht_data members of the
-hpet_task structure before calling hpet_register. hpet_control simply vectors to the hpet_ioctl
-routine and has the same commands and respective arguments as the user API. hpet_unregister
+The kernel module using this interface fills in the ht_func and ht_data
+members of the hpet_task structure before calling hpet_register.
+hpet_control simply vectors to the hpet_ioctl routine and has the same
+commands and respective arguments as the user API. hpet_unregister
is used to terminate usage of the HPET timer reserved by hpet_register.
-
-
diff --git a/Documentation/ioctl-number.txt b/Documentation/ioctl-number.txt
index 769f925c8526..87f4d052e39c 100644
--- a/Documentation/ioctl-number.txt
+++ b/Documentation/ioctl-number.txt
@@ -130,8 +130,6 @@ Code Seq# Include File Comments
'i' 00-3F linux/i2o.h
'j' 00-3F linux/joystick.h
-'k' all asm-sparc/kbio.h
- asm-sparc64/kbio.h
'l' 00-3F linux/tcfs_fs.h transparent cryptographic file system
'l' 40-7F linux/udf_fs_i.h in development:
diff --git a/Documentation/magic-number.txt b/Documentation/magic-number.txt
index bd8eefa17587..af67faccf4de 100644
--- a/Documentation/magic-number.txt
+++ b/Documentation/magic-number.txt
@@ -120,7 +120,7 @@ ISDN_NET_MAGIC 0x49344C02 isdn_net_local_s drivers/isdn/i4l/isdn_net_li
SAVEKMSG_MAGIC2 0x4B4D5347 savekmsg arch/*/amiga/config.c
STLI_BOARDMAGIC 0x4bc6c825 stlibrd include/linux/istallion.h
CS_STATE_MAGIC 0x4c4f4749 cs_state sound/oss/cs46xx.c
-SLAB_C_MAGIC 0x4f17a36d kmem_cache_s mm/slab.c
+SLAB_C_MAGIC 0x4f17a36d kmem_cache mm/slab.c
COW_MAGIC 0x4f4f4f4d cow_header_v1 arch/um/drivers/ubd_user.c
I810_CARD_MAGIC 0x5072696E i810_card sound/oss/i810_audio.c
TRIDENT_CARD_MAGIC 0x5072696E trident_card sound/oss/trident.c
diff --git a/Documentation/networking/decnet.txt b/Documentation/networking/decnet.txt
index c6bd25f5d61d..e6c39c5831f5 100644
--- a/Documentation/networking/decnet.txt
+++ b/Documentation/networking/decnet.txt
@@ -176,8 +176,6 @@ information (_most_ of which _is_ _essential_) includes:
- Which client caused the problem ?
- How much data was being transferred ?
- Was the network congested ?
- - If there was a kernel panic, please run the output through ksymoops
- before sending it to me, otherwise its _useless_.
- How can the problem be reproduced ?
- Can you use tcpdump to get a trace ? (N.B. Most (all?) versions of
tcpdump don't understand how to dump DECnet properly, so including
diff --git a/Documentation/oops-tracing.txt b/Documentation/oops-tracing.txt
index 66eaaab7773d..c563842ed805 100644
--- a/Documentation/oops-tracing.txt
+++ b/Documentation/oops-tracing.txt
@@ -1,6 +1,6 @@
NOTE: ksymoops is useless on 2.6. Please use the Oops in its original format
(from dmesg, etc). Ignore any references in this or other docs to "decoding
-the Oops" or "running it through ksymoops". If you post an Oops fron 2.6 that
+the Oops" or "running it through ksymoops". If you post an Oops from 2.6 that
has been run through ksymoops, people will just tell you to repost it.
Quick Summary
diff --git a/Documentation/power/video.txt b/Documentation/power/video.txt
index 526d6dd267ea..912bed87c758 100644
--- a/Documentation/power/video.txt
+++ b/Documentation/power/video.txt
@@ -11,9 +11,9 @@ boot video card. (Kernel usually does not even contain video card
driver -- vesafb and vgacon are widely used).
This is not problem for swsusp, because during swsusp resume, BIOS is
-run normally so video card is normally initialized. S3 has absolutely
-no chance of working with SMP/HT. Be sure it to turn it off before
-testing (swsusp should work ok, OTOH).
+run normally so video card is normally initialized. It should not be
+problem for S1 standby, because hardware should retain its state over
+that.
There are a few types of systems where video works after S3 resume:
@@ -64,7 +64,7 @@ your video card (good luck getting docs :-(). Maybe suspending from X
(proper X, knowing your hardware, not XF68_FBcon) might have better
chance of working.
-Table of known working systems:
+Table of known working notebooks:
Model hack (or "how to do it")
------------------------------------------------------------------------------
@@ -73,7 +73,7 @@ Acer TM 242FX vbetool (6)
Acer TM C110 video_post (8)
Acer TM C300 vga=normal (only suspend on console, not in X), vbetool (6) or video_post (8)
Acer TM 4052LCi s3_bios (2)
-Acer TM 636Lci s3_bios vga=normal (2)
+Acer TM 636Lci s3_bios,s3_mode (4)
Acer TM 650 (Radeon M7) vga=normal plus boot-radeon (5) gets text console back
Acer TM 660 ??? (*)
Acer TM 800 vga=normal, X patches, see webpage (5) or vbetool (6)
@@ -137,6 +137,13 @@ Toshiba Satellite P10-554 s3_bios,s3_mode (4)(****)
Toshiba M30 (2) xor X with nvidia driver using internal AGP
Uniwill 244IIO ??? (*)
+Known working desktop systems
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Mainboard Graphics card hack (or "how to do it")
+------------------------------------------------------------------------------
+Asus A7V8X nVidia RIVA TNT2 model 64 s3_bios,s3_mode (4)
+
(*) from http://www.ubuntulinux.org/wiki/HoaryPMResults, not sure
which options to use. If you know, please tell me.
diff --git a/Documentation/s390/driver-model.txt b/Documentation/s390/driver-model.txt
index 19461958e2bd..df09758bf3fe 100644
--- a/Documentation/s390/driver-model.txt
+++ b/Documentation/s390/driver-model.txt
@@ -8,11 +8,10 @@ All devices which can be addressed by means of ccws are called 'CCW devices' -
even if they aren't actually driven by ccws.
All ccw devices are accessed via a subchannel, this is reflected in the
-structures under root/:
+structures under devices/:
-root/
- - sys
- - legacy
+devices/
+ - system/
- css0/
- 0.0.0000/0.0.0815/
- 0.0.0001/0.0.4711/
@@ -36,7 +35,7 @@ availability: Can be 'good' or 'boxed'; 'no path' or 'no device' for
online: An interface to set the device online and offline.
In the special case of the device being disconnected (see the
- notify function under 1.2), piping 0 to online will focibly delete
+ notify function under 1.2), piping 0 to online will forcibly delete
the device.
The device drivers can add entries to export per-device data and interfaces.
@@ -222,7 +221,7 @@ and are called 'chp0.'. They have no driver and do not belong to any bus.
Please note, that unlike /proc/chpids in 2.4, the channel path objects reflect
only the logical state and not the physical state, since we cannot track the
latter consistently due to lacking machine support (we don't need to be aware
-of anyway).
+of it anyway).
status - Can be 'online' or 'offline'.
Piping 'on' or 'off' sets the chpid logically online/offline.
@@ -235,12 +234,16 @@ status - Can be 'online' or 'offline'.
3. System devices
-----------------
-Note: cpus may yet be added here.
-
3.1 xpram
---------
-xpram shows up under sys/ as 'xpram'.
+xpram shows up under devices/system/ as 'xpram'.
+
+3.2 cpus
+--------
+
+For each cpu, a directory is created under devices/system/cpu/. Each cpu has an
+attribute 'online' which can be 0 or 1.
4. Other devices
diff --git a/Documentation/sharedsubtree.txt b/Documentation/sharedsubtree.txt
new file mode 100644
index 000000000000..2d8f403eb6eb
--- /dev/null
+++ b/Documentation/sharedsubtree.txt
@@ -0,0 +1,1060 @@
+Shared Subtrees
+---------------
+
+Contents:
+ 1) Overview
+ 2) Features
+ 3) smount command
+ 4) Use-case
+ 5) Detailed semantics
+ 6) Quiz
+ 7) FAQ
+ 8) Implementation
+
+
+1) Overview
+-----------
+
+Consider the following situation:
+
+A process wants to clone its own namespace, but still wants to access the CD
+that got mounted recently. Shared subtree semantics provide the necessary
+mechanism to accomplish the above.
+
+It provides the necessary building blocks for features like per-user-namespace
+and versioned filesystem.
+
+2) Features
+-----------
+
+Shared subtree provides four different flavors of mounts; struct vfsmount to be
+precise
+
+ a. shared mount
+ b. slave mount
+ c. private mount
+ d. unbindable mount
+
+
+2a) A shared mount can be replicated to as many mountpoints and all the
+replicas continue to be exactly same.
+
+ Here is an example:
+
+ Lets say /mnt has a mount that is shared.
+ mount --make-shared /mnt
+
+ note: mount command does not yet support the --make-shared flag.
+ I have included a small C program which does the same by executing
+ 'smount /mnt shared'
+
+ #mount --bind /mnt /tmp
+ The above command replicates the mount at /mnt to the mountpoint /tmp
+ and the contents of both the mounts remain identical.
+
+ #ls /mnt
+ a b c
+
+ #ls /tmp
+ a b c
+
+ Now lets say we mount a device at /tmp/a
+ #mount /dev/sd0 /tmp/a
+
+ #ls /tmp/a
+ t1 t2 t2
+
+ #ls /mnt/a
+ t1 t2 t2
+
+ Note that the mount has propagated to the mount at /mnt as well.
+
+ And the same is true even when /dev/sd0 is mounted on /mnt/a. The
+ contents will be visible under /tmp/a too.
+
+
+2b) A slave mount is like a shared mount except that mount and umount events
+ only propagate towards it.
+
+ All slave mounts have a master mount which is a shared.
+
+ Here is an example:
+
+ Lets say /mnt has a mount which is shared.
+ #mount --make-shared /mnt
+
+ Lets bind mount /mnt to /tmp
+ #mount --bind /mnt /tmp
+
+ the new mount at /tmp becomes a shared mount and it is a replica of
+ the mount at /mnt.
+
+ Now lets make the mount at /tmp; a slave of /mnt
+ #mount --make-slave /tmp
+ [or smount /tmp slave]
+
+ lets mount /dev/sd0 on /mnt/a
+ #mount /dev/sd0 /mnt/a
+
+ #ls /mnt/a
+ t1 t2 t3
+
+ #ls /tmp/a
+ t1 t2 t3
+
+ Note the mount event has propagated to the mount at /tmp
+
+ However lets see what happens if we mount something on the mount at /tmp
+
+ #mount /dev/sd1 /tmp/b
+
+ #ls /tmp/b
+ s1 s2 s3
+
+ #ls /mnt/b
+
+ Note how the mount event has not propagated to the mount at
+ /mnt
+
+
+2c) A private mount does not forward or receive propagation.
+
+ This is the mount we are familiar with. Its the default type.
+
+
+2d) A unbindable mount is a unbindable private mount
+
+ lets say we have a mount at /mnt and we make is unbindable
+
+ #mount --make-unbindable /mnt
+ [ smount /mnt unbindable ]
+
+ Lets try to bind mount this mount somewhere else.
+ # mount --bind /mnt /tmp
+ mount: wrong fs type, bad option, bad superblock on /mnt,
+ or too many mounted file systems
+
+ Binding a unbindable mount is a invalid operation.
+
+
+3) smount command
+
+ Currently the mount command is not aware of shared subtree features.
+ Work is in progress to add the support in mount ( util-linux package ).
+ Till then use the following program.
+
+ ------------------------------------------------------------------------
+ //
+ //this code was developed my Miklos Szeredi
+ //and modified by Ram Pai
+ // sample usage:
+ // smount /tmp shared
+ //
+ #include
+ #include
+ #include
+ #include
+ #include
+
+ #ifndef MS_REC
+ #define MS_REC 0x4000 /* 16384: Recursive loopback */
+ #endif
+
+ #ifndef MS_SHARED
+ #define MS_SHARED 1<<20 /* Shared */
+ #endif
+
+ #ifndef MS_PRIVATE
+ #define MS_PRIVATE 1<<18 /* Private */
+ #endif
+
+ #ifndef MS_SLAVE
+ #define MS_SLAVE 1<<19 /* Slave */
+ #endif
+
+ #ifndef MS_UNBINDABLE
+ #define MS_UNBINDABLE 1<<17 /* Unbindable */
+ #endif
+
+ int main(int argc, char *argv[])
+ {
+ int type;
+ if(argc != 3) {
+ fprintf(stderr, "usage: %s dir "
+ "\n" , argv[0]);
+ return 1;
+ }
+
+ fprintf(stdout, "%s %s %s\n", argv[0], argv[1], argv[2]);
+
+ if (strcmp(argv[2],"rshared")==0)
+ type=(MS_SHARED|MS_REC);
+ else if (strcmp(argv[2],"rslave")==0)
+ type=(MS_SLAVE|MS_REC);
+ else if (strcmp(argv[2],"rprivate")==0)
+ type=(MS_PRIVATE|MS_REC);
+ else if (strcmp(argv[2],"runbindable")==0)
+ type=(MS_UNBINDABLE|MS_REC);
+ else if (strcmp(argv[2],"shared")==0)
+ type=MS_SHARED;
+ else if (strcmp(argv[2],"slave")==0)
+ type=MS_SLAVE;
+ else if (strcmp(argv[2],"private")==0)
+ type=MS_PRIVATE;
+ else if (strcmp(argv[2],"unbindable")==0)
+ type=MS_UNBINDABLE;
+ else {
+ fprintf(stderr, "invalid operation: %s\n", argv[2]);
+ return 1;
+ }
+ setfsuid(getuid());
+
+ if(mount("", argv[1], "dontcare", type, "") == -1) {
+ perror("mount");
+ return 1;
+ }
+ return 0;
+ }
+ -----------------------------------------------------------------------
+
+ Copy the above code snippet into smount.c
+ gcc -o smount smount.c
+
+
+ (i) To mark all the mounts under /mnt as shared execute the following
+ command:
+
+ smount /mnt rshared
+ the corresponding syntax planned for mount command is
+ mount --make-rshared /mnt
+
+ just to mark a mount /mnt as shared, execute the following
+ command:
+ smount /mnt shared
+ the corresponding syntax planned for mount command is
+ mount --make-shared /mnt
+
+ (ii) To mark all the shared mounts under /mnt as slave execute the
+ following
+
+ command:
+ smount /mnt rslave
+ the corresponding syntax planned for mount command is
+ mount --make-rslave /mnt
+
+ just to mark a mount /mnt as slave, execute the following
+ command:
+ smount /mnt slave
+ the corresponding syntax planned for mount command is
+ mount --make-slave /mnt
+
+ (iii) To mark all the mounts under /mnt as private execute the
+ following command:
+
+ smount /mnt rprivate
+ the corresponding syntax planned for mount command is
+ mount --make-rprivate /mnt
+
+ just to mark a mount /mnt as private, execute the following
+ command:
+ smount /mnt private
+ the corresponding syntax planned for mount command is
+ mount --make-private /mnt
+
+ NOTE: by default all the mounts are created as private. But if
+ you want to change some shared/slave/unbindable mount as
+ private at a later point in time, this command can help.
+
+ (iv) To mark all the mounts under /mnt as unbindable execute the
+ following
+
+ command:
+ smount /mnt runbindable
+ the corresponding syntax planned for mount command is
+ mount --make-runbindable /mnt
+
+ just to mark a mount /mnt as unbindable, execute the following
+ command:
+ smount /mnt unbindable
+ the corresponding syntax planned for mount command is
+ mount --make-unbindable /mnt
+
+
+4) Use cases
+------------
+
+ A) A process wants to clone its own namespace, but still wants to
+ access the CD that got mounted recently.
+
+ Solution:
+
+ The system administrator can make the mount at /cdrom shared
+ mount --bind /cdrom /cdrom
+ mount --make-shared /cdrom
+
+ Now any process that clones off a new namespace will have a
+ mount at /cdrom which is a replica of the same mount in the
+ parent namespace.
+
+ So when a CD is inserted and mounted at /cdrom that mount gets
+ propagated to the other mount at /cdrom in all the other clone
+ namespaces.
+
+ B) A process wants its mounts invisible to any other process, but
+ still be able to see the other system mounts.
+
+ Solution:
+
+ To begin with, the administrator can mark the entire mount tree
+ as shareable.
+
+ mount --make-rshared /
+
+ A new process can clone off a new namespace. And mark some part
+ of its namespace as slave
+
+ mount --make-rslave /myprivatetree
+
+ Hence forth any mounts within the /myprivatetree done by the
+ process will not show up in any other namespace. However mounts
+ done in the parent namespace under /myprivatetree still shows
+ up in the process's namespace.
+
+
+ Apart from the above semantics this feature provides the
+ building blocks to solve the following problems:
+
+ C) Per-user namespace
+
+ The above semantics allows a way to share mounts across
+ namespaces. But namespaces are associated with processes. If
+ namespaces are made first class objects with user API to
+ associate/disassociate a namespace with userid, then each user
+ could have his/her own namespace and tailor it to his/her
+ requirements. Offcourse its needs support from PAM.
+
+ D) Versioned files
+
+ If the entire mount tree is visible at multiple locations, then
+ a underlying versioning file system can return different
+ version of the file depending on the path used to access that
+ file.
+
+ An example is:
+
+ mount --make-shared /
+ mount --rbind / /view/v1
+ mount --rbind / /view/v2
+ mount --rbind / /view/v3
+ mount --rbind / /view/v4
+
+ and if /usr has a versioning filesystem mounted, than that
+ mount appears at /view/v1/usr, /view/v2/usr, /view/v3/usr and
+ /view/v4/usr too
+
+ A user can request v3 version of the file /usr/fs/namespace.c
+ by accessing /view/v3/usr/fs/namespace.c . The underlying
+ versioning filesystem can then decipher that v3 version of the
+ filesystem is being requested and return the corresponding
+ inode.
+
+5) Detailed semantics:
+-------------------
+ The section below explains the detailed semantics of
+ bind, rbind, move, mount, umount and clone-namespace operations.
+
+ Note: the word 'vfsmount' and the noun 'mount' have been used
+ to mean the same thing, throughout this document.
+
+5a) Mount states
+
+ A given mount can be in one of the following states
+ 1) shared
+ 2) slave
+ 3) shared and slave
+ 4) private
+ 5) unbindable
+
+ A 'propagation event' is defined as event generated on a vfsmount
+ that leads to mount or unmount actions in other vfsmounts.
+
+ A 'peer group' is defined as a group of vfsmounts that propagate
+ events to each other.
+
+ (1) Shared mounts
+
+ A 'shared mount' is defined as a vfsmount that belongs to a
+ 'peer group'.
+
+ For example:
+ mount --make-shared /mnt
+ mount --bin /mnt /tmp
+
+ The mount at /mnt and that at /tmp are both shared and belong
+ to the same peer group. Anything mounted or unmounted under
+ /mnt or /tmp reflect in all the other mounts of its peer
+ group.
+
+
+ (2) Slave mounts
+
+ A 'slave mount' is defined as a vfsmount that receives
+ propagation events and does not forward propagation events.
+
+ A slave mount as the name implies has a master mount from which
+ mount/unmount events are received. Events do not propagate from
+ the slave mount to the master. Only a shared mount can be made
+ a slave by executing the following command
+
+ mount --make-slave mount
+
+ A shared mount that is made as a slave is no more shared unless
+ modified to become shared.
+
+ (3) Shared and Slave
+
+ A vfsmount can be both shared as well as slave. This state
+ indicates that the mount is a slave of some vfsmount, and
+ has its own peer group too. This vfsmount receives propagation
+ events from its master vfsmount, and also forwards propagation
+ events to its 'peer group' and to its slave vfsmounts.
+
+ Strictly speaking, the vfsmount is shared having its own
+ peer group, and this peer-group is a slave of some other
+ peer group.
+
+ Only a slave vfsmount can be made as 'shared and slave' by
+ either executing the following command
+ mount --make-shared mount
+ or by moving the slave vfsmount under a shared vfsmount.
+
+ (4) Private mount
+
+ A 'private mount' is defined as vfsmount that does not
+ receive or forward any propagation events.
+
+ (5) Unbindable mount
+
+ A 'unbindable mount' is defined as vfsmount that does not
+ receive or forward any propagation events and cannot
+ be bind mounted.
+
+
+ State diagram:
+ The state diagram below explains the state transition of a mount,
+ in response to various commands.
+ ------------------------------------------------------------------------
+ | |make-shared | make-slave | make-private |make-unbindab|
+ --------------|------------|--------------|--------------|-------------|
+ |shared |shared |*slave/private| private | unbindable |
+ | | | | | |
+ |-------------|------------|--------------|--------------|-------------|
+ |slave |shared | **slave | private | unbindable |
+ | |and slave | | | |
+ |-------------|------------|--------------|--------------|-------------|
+ |shared |shared | slave | private | unbindable |
+ |and slave |and slave | | | |
+ |-------------|------------|--------------|--------------|-------------|
+ |private |shared | **private | private | unbindable |
+ |-------------|------------|--------------|--------------|-------------|
+ |unbindable |shared |**unbindable | private | unbindable |
+ ------------------------------------------------------------------------
+
+ * if the shared mount is the only mount in its peer group, making it
+ slave, makes it private automatically. Note that there is no master to
+ which it can be slaved to.
+
+ ** slaving a non-shared mount has no effect on the mount.
+
+ Apart from the commands listed below, the 'move' operation also changes
+ the state of a mount depending on type of the destination mount. Its
+ explained in section 5d.
+
+5b) Bind semantics
+
+ Consider the following command
+
+ mount --bind A/a B/b
+
+ where 'A' is the source mount, 'a' is the dentry in the mount 'A', 'B'
+ is the destination mount and 'b' is the dentry in the destination mount.
+
+ The outcome depends on the type of mount of 'A' and 'B'. The table
+ below contains quick reference.
+ ---------------------------------------------------------------------------
+ | BIND MOUNT OPERATION |
+ |**************************************************************************
+ |source(A)->| shared | private | slave | unbindable |
+ | dest(B) | | | | |
+ | | | | | | |
+ | v | | | | |
+ |**************************************************************************
+ | shared | shared | shared | shared & slave | invalid |
+ | | | | | |
+ |non-shared| shared | private | slave | invalid |
+ ***************************************************************************
+
+ Details:
+
+ 1. 'A' is a shared mount and 'B' is a shared mount. A new mount 'C'
+ which is clone of 'A', is created. Its root dentry is 'a' . 'C' is
+ mounted on mount 'B' at dentry 'b'. Also new mount 'C1', 'C2', 'C3' ...
+ are created and mounted at the dentry 'b' on all mounts where 'B'
+ propagates to. A new propagation tree containing 'C1',..,'Cn' is
+ created. This propagation tree is identical to the propagation tree of
+ 'B'. And finally the peer-group of 'C' is merged with the peer group
+ of 'A'.
+
+ 2. 'A' is a private mount and 'B' is a shared mount. A new mount 'C'
+ which is clone of 'A', is created. Its root dentry is 'a'. 'C' is
+ mounted on mount 'B' at dentry 'b'. Also new mount 'C1', 'C2', 'C3' ...
+ are created and mounted at the dentry 'b' on all mounts where 'B'
+ propagates to. A new propagation tree is set containing all new mounts
+ 'C', 'C1', .., 'Cn' with exactly the same configuration as the
+ propagation tree for 'B'.
+
+ 3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. A new
+ mount 'C' which is clone of 'A', is created. Its root dentry is 'a' .
+ 'C' is mounted on mount 'B' at dentry 'b'. Also new mounts 'C1', 'C2',
+ 'C3' ... are created and mounted at the dentry 'b' on all mounts where
+ 'B' propagates to. A new propagation tree containing the new mounts
+ 'C','C1',.. 'Cn' is created. This propagation tree is identical to the
+ propagation tree for 'B'. And finally the mount 'C' and its peer group
+ is made the slave of mount 'Z'. In other words, mount 'C' is in the
+ state 'slave and shared'.
+
+ 4. 'A' is a unbindable mount and 'B' is a shared mount. This is a
+ invalid operation.
+
+ 5. 'A' is a private mount and 'B' is a non-shared(private or slave or
+ unbindable) mount. A new mount 'C' which is clone of 'A', is created.
+ Its root dentry is 'a'. 'C' is mounted on mount 'B' at dentry 'b'.
+
+ 6. 'A' is a shared mount and 'B' is a non-shared mount. A new mount 'C'
+ which is a clone of 'A' is created. Its root dentry is 'a'. 'C' is
+ mounted on mount 'B' at dentry 'b'. 'C' is made a member of the
+ peer-group of 'A'.
+
+ 7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount. A
+ new mount 'C' which is a clone of 'A' is created. Its root dentry is
+ 'a'. 'C' is mounted on mount 'B' at dentry 'b'. Also 'C' is set as a
+ slave mount of 'Z'. In other words 'A' and 'C' are both slave mounts of
+ 'Z'. All mount/unmount events on 'Z' propagates to 'A' and 'C'. But
+ mount/unmount on 'A' do not propagate anywhere else. Similarly
+ mount/unmount on 'C' do not propagate anywhere else.
+
+ 8. 'A' is a unbindable mount and 'B' is a non-shared mount. This is a
+ invalid operation. A unbindable mount cannot be bind mounted.
+
+5c) Rbind semantics
+
+ rbind is same as bind. Bind replicates the specified mount. Rbind
+ replicates all the mounts in the tree belonging to the specified mount.
+ Rbind mount is bind mount applied to all the mounts in the tree.
+
+ If the source tree that is rbind has some unbindable mounts,
+ then the subtree under the unbindable mount is pruned in the new
+ location.
+
+ eg: lets say we have the following mount tree.
+
+ A
+ / \
+ B C
+ / \ / \
+ D E F G
+
+ Lets say all the mount except the mount C in the tree are
+ of a type other than unbindable.
+
+ If this tree is rbound to say Z
+
+ We will have the following tree at the new location.
+
+ Z
+ |
+ A'
+ /
+ B' Note how the tree under C is pruned
+ / \ in the new location.
+ D' E'
+
+
+
+5d) Move semantics
+
+ Consider the following command
+
+ mount --move A B/b
+
+ where 'A' is the source mount, 'B' is the destination mount and 'b' is
+ the dentry in the destination mount.
+
+ The outcome depends on the type of the mount of 'A' and 'B'. The table
+ below is a quick reference.
+ ---------------------------------------------------------------------------
+ | MOVE MOUNT OPERATION |
+ |**************************************************************************
+ | source(A)->| shared | private | slave | unbindable |
+ | dest(B) | | | | |
+ | | | | | | |
+ | v | | | | |
+ |**************************************************************************
+ | shared | shared | shared |shared and slave| invalid |
+ | | | | | |
+ |non-shared| shared | private | slave | unbindable |
+ ***************************************************************************
+ NOTE: moving a mount residing under a shared mount is invalid.
+
+ Details follow:
+
+ 1. 'A' is a shared mount and 'B' is a shared mount. The mount 'A' is
+ mounted on mount 'B' at dentry 'b'. Also new mounts 'A1', 'A2'...'An'
+ are created and mounted at dentry 'b' on all mounts that receive
+ propagation from mount 'B'. A new propagation tree is created in the
+ exact same configuration as that of 'B'. This new propagation tree
+ contains all the new mounts 'A1', 'A2'... 'An'. And this new
+ propagation tree is appended to the already existing propagation tree
+ of 'A'.
+
+ 2. 'A' is a private mount and 'B' is a shared mount. The mount 'A' is
+ mounted on mount 'B' at dentry 'b'. Also new mount 'A1', 'A2'... 'An'
+ are created and mounted at dentry 'b' on all mounts that receive
+ propagation from mount 'B'. The mount 'A' becomes a shared mount and a
+ propagation tree is created which is identical to that of
+ 'B'. This new propagation tree contains all the new mounts 'A1',
+ 'A2'... 'An'.
+
+ 3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. The
+ mount 'A' is mounted on mount 'B' at dentry 'b'. Also new mounts 'A1',
+ 'A2'... 'An' are created and mounted at dentry 'b' on all mounts that
+ receive propagation from mount 'B'. A new propagation tree is created
+ in the exact same configuration as that of 'B'. This new propagation
+ tree contains all the new mounts 'A1', 'A2'... 'An'. And this new
+ propagation tree is appended to the already existing propagation tree of
+ 'A'. Mount 'A' continues to be the slave mount of 'Z' but it also
+ becomes 'shared'.
+
+ 4. 'A' is a unbindable mount and 'B' is a shared mount. The operation
+ is invalid. Because mounting anything on the shared mount 'B' can
+ create new mounts that get mounted on the mounts that receive
+ propagation from 'B'. And since the mount 'A' is unbindable, cloning
+ it to mount at other mountpoints is not possible.
+
+ 5. 'A' is a private mount and 'B' is a non-shared(private or slave or
+ unbindable) mount. The mount 'A' is mounted on mount 'B' at dentry 'b'.
+
+ 6. 'A' is a shared mount and 'B' is a non-shared mount. The mount 'A'
+ is mounted on mount 'B' at dentry 'b'. Mount 'A' continues to be a
+ shared mount.
+
+ 7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount.
+ The mount 'A' is mounted on mount 'B' at dentry 'b'. Mount 'A'
+ continues to be a slave mount of mount 'Z'.
+
+ 8. 'A' is a unbindable mount and 'B' is a non-shared mount. The mount
+ 'A' is mounted on mount 'B' at dentry 'b'. Mount 'A' continues to be a
+ unbindable mount.
+
+5e) Mount semantics
+
+ Consider the following command
+
+ mount device B/b
+
+ 'B' is the destination mount and 'b' is the dentry in the destination
+ mount.
+
+ The above operation is the same as bind operation with the exception
+ that the source mount is always a private mount.
+
+
+5f) Unmount semantics
+
+ Consider the following command
+
+ umount A
+
+ where 'A' is a mount mounted on mount 'B' at dentry 'b'.
+
+ If mount 'B' is shared, then all most-recently-mounted mounts at dentry
+ 'b' on mounts that receive propagation from mount 'B' and does not have
+ sub-mounts within them are unmounted.
+
+ Example: Lets say 'B1', 'B2', 'B3' are shared mounts that propagate to
+ each other.
+
+ lets say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount
+ 'B1', 'B2' and 'B3' respectively.
+
+ lets say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on
+ mount 'B1', 'B2' and 'B3' respectively.
+
+ if 'C1' is unmounted, all the mounts that are most-recently-mounted on
+ 'B1' and on the mounts that 'B1' propagates-to are unmounted.
+
+ 'B1' propagates to 'B2' and 'B3'. And the most recently mounted mount
+ on 'B2' at dentry 'b' is 'C2', and that of mount 'B3' is 'C3'.
+
+ So all 'C1', 'C2' and 'C3' should be unmounted.
+
+ If any of 'C2' or 'C3' has some child mounts, then that mount is not
+ unmounted, but all other mounts are unmounted. However if 'C1' is told
+ to be unmounted and 'C1' has some sub-mounts, the umount operation is
+ failed entirely.
+
+5g) Clone Namespace
+
+ A cloned namespace contains all the mounts as that of the parent
+ namespace.
+
+ Lets say 'A' and 'B' are the corresponding mounts in the parent and the
+ child namespace.
+
+ If 'A' is shared, then 'B' is also shared and 'A' and 'B' propagate to
+ each other.
+
+ If 'A' is a slave mount of 'Z', then 'B' is also the slave mount of
+ 'Z'.
+
+ If 'A' is a private mount, then 'B' is a private mount too.
+
+ If 'A' is unbindable mount, then 'B' is a unbindable mount too.
+
+
+6) Quiz
+
+ A. What is the result of the following command sequence?
+
+ mount --bind /mnt /mnt
+ mount --make-shared /mnt
+ mount --bind /mnt /tmp
+ mount --move /tmp /mnt/1
+
+ what should be the contents of /mnt /mnt/1 /mnt/1/1 should be?
+ Should they all be identical? or should /mnt and /mnt/1 be
+ identical only?
+
+
+ B. What is the result of the following command sequence?
+
+ mount --make-rshared /
+ mkdir -p /v/1
+ mount --rbind / /v/1
+
+ what should be the content of /v/1/v/1 be?
+
+
+ C. What is the result of the following command sequence?
+
+ mount --bind /mnt /mnt
+ mount --make-shared /mnt
+ mkdir -p /mnt/1/2/3 /mnt/1/test
+ mount --bind /mnt/1 /tmp
+ mount --make-slave /mnt
+ mount --make-shared /mnt
+ mount --bind /mnt/1/2 /tmp1
+ mount --make-slave /mnt
+
+ At this point we have the first mount at /tmp and
+ its root dentry is 1. Lets call this mount 'A'
+ And then we have a second mount at /tmp1 with root
+ dentry 2. Lets call this mount 'B'
+ Next we have a third mount at /mnt with root dentry
+ mnt. Lets call this mount 'C'
+
+ 'B' is the slave of 'A' and 'C' is a slave of 'B'
+ A -> B -> C
+
+ at this point if we execute the following command
+
+ mount --bind /bin /tmp/test
+
+ The mount is attempted on 'A'
+
+ will the mount propagate to 'B' and 'C' ?
+
+ what would be the contents of
+ /mnt/1/test be?
+
+7) FAQ
+
+ Q1. Why is bind mount needed? How is it different from symbolic links?
+ symbolic links can get stale if the destination mount gets
+ unmounted or moved. Bind mounts continue to exist even if the
+ other mount is unmounted or moved.
+
+ Q2. Why can't the shared subtree be implemented using exportfs?
+
+ exportfs is a heavyweight way of accomplishing part of what
+ shared subtree can do. I cannot imagine a way to implement the
+ semantics of slave mount using exportfs?
+
+ Q3 Why is unbindable mount needed?
+
+ Lets say we want to replicate the mount tree at multiple
+ locations within the same subtree.
+
+ if one rbind mounts a tree within the same subtree 'n' times
+ the number of mounts created is an exponential function of 'n'.
+ Having unbindable mount can help prune the unneeded bind
+ mounts. Here is a example.
+
+ step 1:
+ lets say the root tree has just two directories with
+ one vfsmount.
+ root
+ / \
+ tmp usr
+
+ And we want to replicate the tree at multiple
+ mountpoints under /root/tmp
+
+ step2:
+ mount --make-shared /root
+
+ mkdir -p /tmp/m1
+
+ mount --rbind /root /tmp/m1
+
+ the new tree now looks like this:
+
+ root
+ / \
+ tmp usr
+ /
+ m1
+ / \
+ tmp usr
+ /
+ m1
+
+ it has two vfsmounts
+
+ step3:
+ mkdir -p /tmp/m2
+ mount --rbind /root /tmp/m2
+
+ the new tree now looks like this:
+
+ root
+ / \
+ tmp usr
+ / \
+ m1 m2
+ / \ / \
+ tmp usr tmp usr
+ / \ /
+ m1 m2 m1
+ / \ / \
+ tmp usr tmp usr
+ / / \
+ m1 m1 m2
+ / \
+ tmp usr
+ / \
+ m1 m2
+
+ it has 6 vfsmounts
+
+ step 4:
+ mkdir -p /tmp/m3
+ mount --rbind /root /tmp/m3
+
+ I wont' draw the tree..but it has 24 vfsmounts
+
+
+ at step i the number of vfsmounts is V[i] = i*V[i-1].
+ This is an exponential function. And this tree has way more
+ mounts than what we really needed in the first place.
+
+ One could use a series of umount at each step to prune
+ out the unneeded mounts. But there is a better solution.
+ Unclonable mounts come in handy here.
+
+ step 1:
+ lets say the root tree has just two directories with
+ one vfsmount.
+ root
+ / \
+ tmp usr
+
+ How do we set up the same tree at multiple locations under
+ /root/tmp
+
+ step2:
+ mount --bind /root/tmp /root/tmp
+
+ mount --make-rshared /root
+ mount --make-unbindable /root/tmp
+
+ mkdir -p /tmp/m1
+
+ mount --rbind /root /tmp/m1
+
+ the new tree now looks like this:
+
+ root
+ / \
+ tmp usr
+ /
+ m1
+ / \
+ tmp usr
+
+ step3:
+ mkdir -p /tmp/m2
+ mount --rbind /root /tmp/m2
+
+ the new tree now looks like this:
+
+ root
+ / \
+ tmp usr
+ / \
+ m1 m2
+ / \ / \
+ tmp usr tmp usr
+
+ step4:
+
+ mkdir -p /tmp/m3
+ mount --rbind /root /tmp/m3
+
+ the new tree now looks like this:
+
+ root
+ / \
+ tmp usr
+ / \ \
+ m1 m2 m3
+ / \ / \ / \
+ tmp usr tmp usr tmp usr
+
+8) Implementation
+
+8A) Datastructure
+
+ 4 new fields are introduced to struct vfsmount
+ ->mnt_share
+ ->mnt_slave_list
+ ->mnt_slave
+ ->mnt_master
+
+ ->mnt_share links togather all the mount to/from which this vfsmount
+ send/receives propagation events.
+
+ ->mnt_slave_list links all the mounts to which this vfsmount propagates
+ to.
+
+ ->mnt_slave links togather all the slaves that its master vfsmount
+ propagates to.
+
+ ->mnt_master points to the master vfsmount from which this vfsmount
+ receives propagation.
+
+ ->mnt_flags takes two more flags to indicate the propagation status of
+ the vfsmount. MNT_SHARE indicates that the vfsmount is a shared
+ vfsmount. MNT_UNCLONABLE indicates that the vfsmount cannot be
+ replicated.
+
+ All the shared vfsmounts in a peer group form a cyclic list through
+ ->mnt_share.
+
+ All vfsmounts with the same ->mnt_master form on a cyclic list anchored
+ in ->mnt_master->mnt_slave_list and going through ->mnt_slave.
+
+ ->mnt_master can point to arbitrary (and possibly different) members
+ of master peer group. To find all immediate slaves of a peer group
+ you need to go through _all_ ->mnt_slave_list of its members.
+ Conceptually it's just a single set - distribution among the
+ individual lists does not affect propagation or the way propagation
+ tree is modified by operations.
+
+ A example propagation tree looks as shown in the figure below.
+ [ NOTE: Though it looks like a forest, if we consider all the shared
+ mounts as a conceptual entity called 'pnode', it becomes a tree]
+
+
+ A <--> B <--> C <---> D
+ /|\ /| |\
+ / F G J K H I
+ /
+ E<-->K
+ /|\
+ M L N
+
+ In the above figure A,B,C and D all are shared and propagate to each
+ other. 'A' has got 3 slave mounts 'E' 'F' and 'G' 'C' has got 2 slave
+ mounts 'J' and 'K' and 'D' has got two slave mounts 'H' and 'I'.
+ 'E' is also shared with 'K' and they propagate to each other. And
+ 'K' has 3 slaves 'M', 'L' and 'N'
+
+ A's ->mnt_share links with the ->mnt_share of 'B' 'C' and 'D'
+
+ A's ->mnt_slave_list links with ->mnt_slave of 'E', 'K', 'F' and 'G'
+
+ E's ->mnt_share links with ->mnt_share of K
+ 'E', 'K', 'F', 'G' have their ->mnt_master point to struct
+ vfsmount of 'A'
+ 'M', 'L', 'N' have their ->mnt_master point to struct vfsmount of 'K'
+ K's ->mnt_slave_list links with ->mnt_slave of 'M', 'L' and 'N'
+
+ C's ->mnt_slave_list links with ->mnt_slave of 'J' and 'K'
+ J and K's ->mnt_master points to struct vfsmount of C
+ and finally D's ->mnt_slave_list links with ->mnt_slave of 'H' and 'I'
+ 'H' and 'I' have their ->mnt_master pointing to struct vfsmount of 'D'.
+
+
+ NOTE: The propagation tree is orthogonal to the mount tree.
+
+
+8B Algorithm:
+
+ The crux of the implementation resides in rbind/move operation.
+
+ The overall algorithm breaks the operation into 3 phases: (look at
+ attach_recursive_mnt() and propagate_mnt())
+
+ 1. prepare phase.
+ 2. commit phases.
+ 3. abort phases.
+
+ Prepare phase:
+
+ for each mount in the source tree:
+ a) Create the necessary number of mount trees to
+ be attached to each of the mounts that receive
+ propagation from the destination mount.
+ b) Do not attach any of the trees to its destination.
+ However note down its ->mnt_parent and ->mnt_mountpoint
+ c) Link all the new mounts to form a propagation tree that
+ is identical to the propagation tree of the destination
+ mount.
+
+ If this phase is successful, there should be 'n' new
+ propagation trees; where 'n' is the number of mounts in the
+ source tree. Go to the commit phase
+
+ Also there should be 'm' new mount trees, where 'm' is
+ the number of mounts to which the destination mount
+ propagates to.
+
+ if any memory allocations fail, go to the abort phase.
+
+ Commit phase
+ attach each of the mount trees to their corresponding
+ destination mounts.
+
+ Abort phase
+ delete all the newly created trees.
+
+ NOTE: all the propagation related functionality resides in the file
+ pnode.c
+
+
+------------------------------------------------------------------------
+
+version 0.1 (created the initial document, Ram Pai linuxram@us.ibm.com)
+version 0.2 (Incorporated comments from Al Viro)
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 13cba955cb5a..2f27f391c7cc 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -167,7 +167,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
spdif - Support SPDIF I/O
- Default: disabled
- Module supports autoprobe and multiple chips (max 8).
+ This module supports one chip and autoprobe.
The power-management is supported.
@@ -206,7 +206,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
See "AC97 Quirk Option" section below.
spdif_aclink - S/PDIF transfer over AC-link (default = 1)
- This module supports up to 8 cards and autoprobe.
+ This module supports one card and autoprobe.
ATI IXP has two different methods to control SPDIF output. One is
over AC-link and another is over the "direct" SPDIF output. The
@@ -218,7 +218,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
Module for ATI IXP 150/200/250 AC97 modem controllers.
- Module supports up to 8 cards.
+ This module supports one card and autoprobe.
Note: The default index value of this module is -2, i.e. the first
slot is excluded.
@@ -637,7 +637,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
model - force the model name
position_fix - Fix DMA pointer (0 = auto, 1 = none, 2 = POSBUF, 3 = FIFO size)
- Module supports up to 8 cards.
+ This module supports one card and autoprobe.
Each codec may have a model table for different configurations.
If your machine isn't listed there, the default (usually minimal)
@@ -663,6 +663,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
adjusted. Appearing only when compiled with
$CONFIG_SND_DEBUG=y
+ ALC260
+ hp HP machines
+ fujitsu Fujitsu S7020
+
CMI9880
minimal 3-jack in back
min_fp 3-jack in back, 2-jack in front
@@ -811,7 +815,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
semaphores (e.g. on some ASUS laptops)
(default off)
- Module supports autoprobe and multiple bus-master chips (max 8).
+ This module supports one chip and autoprobe.
Note: the latest driver supports auto-detection of chip clock.
if you still encounter too fast playback, specify the clock
@@ -830,7 +834,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
ac97_clock - AC'97 codec clock base (0 = auto-detect)
- This module supports up to 8 cards and autoprobe.
+ This module supports one card and autoprobe.
Note: The default index value of this module is -2, i.e. the first
slot is excluded.
@@ -950,8 +954,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
use_cache - 0 or 1 (disabled by default)
vaio_hack - alias buffer_top=0x25a800
reset_workaround - enable AC97 RESET workaround for some laptops
+ reset_workaround2 - enable extended AC97 RESET workaround for some
+ other laptops
- Module supports autoprobe and multiple chips (max 8).
+ This module supports one chip and autoprobe.
The power-management is supported.
@@ -980,6 +986,11 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
workaround is enabled automatically. For other laptops with a
hard freeze, you can try reset_workaround=1 option.
+ Note: Dell Latitude CSx laptops have another problem regarding
+ AC97 RESET. On these laptops, reset_workaround2 option is
+ turned on as default. This option is worth to try if the
+ previous reset_workaround option doesn't help.
+
Note: This driver is really crappy. It's a porting from the
OSS driver, which is a result of black-magic reverse engineering.
The detection of codec will fail if the driver is loaded *after*
@@ -1310,7 +1321,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
ac97_quirk - AC'97 workaround for strange hardware
See "AC97 Quirk Option" section below.
- Module supports autoprobe and multiple bus-master chips (max 8).
+ This module supports one chip and autoprobe.
Note: on some SMP motherboards like MSI 694D the interrupts might
not be generated properly. In such a case, please try to
@@ -1352,7 +1363,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
ac97_clock - AC'97 codec clock base (default 48000Hz)
- Module supports up to 8 cards.
+ This module supports one card and autoprobe.
Note: The default index value of this module is -2, i.e. the first
slot is excluded.
diff --git a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
index 24e85520890b..260334c98d95 100644
--- a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
@@ -18,8 +18,8 @@
- March 6, 2005
- 0.3.4
+ October 6, 2005
+ 0.3.5
@@ -30,7 +30,7 @@
- Copyright (c) 2002-2004 Takashi Iwai tiwai@suse.de
+ Copyright (c) 2002-2005 Takashi Iwai tiwai@suse.de
@@ -1433,25 +1433,10 @@
res_port) {
- release_resource(chip->res_port);
- kfree_nocheck(chip->res_port);
- }
+ release_and_free_resource(chip->res_port);
]]>
-
- As you can see, the resource pointer is also to be freed
- via kfree_nocheck() after
- release_resource() is called. You
- cannot use kfree() here, because on ALSA,
- kfree() may be a wrapper to its own
- allocator with the memory debugging. Since the resource pointer
- is allocated externally outside the ALSA, it must be released
- via the native
- kfree().
- kfree_nocheck() is used for that; it calls
- the native kfree() without wrapper.
@@ -2190,8 +2175,7 @@ struct _snd_pcm_runtime {
unsigned int rate_den;
/* -- SW params -- */
- int tstamp_timespec; /* use timeval (0) or timespec (1) */
- snd_pcm_tstamp_t tstamp_mode; /* mmap timestamp is updated */
+ struct timespec tstamp_mode; /* mmap timestamp is updated */
unsigned int period_step;
unsigned int sleep_min; /* min ticks to sleep */
snd_pcm_uframes_t xfer_align; /* xfer size need to be a multiple */
@@ -3709,8 +3693,7 @@ struct _snd_pcm_runtime {
Here, the chip instance is retrieved via
snd_kcontrol_chip() macro. This macro
- converts from kcontrol->private_data to the type defined by
- chip_t. The
+ just accesses to kcontrol->private_data. The
kcontrol->private_data field is
given as the argument of snd_ctl_new()
(see the later subsection
@@ -5998,32 +5981,23 @@ struct _snd_pcm_runtime {
The first argument is the expression to evaluate, and the
second argument is the action if it fails. When
CONFIG_SND_DEBUG, is set, it will show an
- error message such as BUG? (xxx) (called from
- yyy). When no debug flag is set, this is
- ignored.
+ error message such as BUG? (xxx)
+ together with stack trace.
-
-
-
- <function>snd_runtime_check()</function>
- This macro is quite similar with
- snd_assert(). Unlike
- snd_assert(), the expression is always
- evaluated regardless of
- CONFIG_SND_DEBUG. When
- CONFIG_SND_DEBUG is set, the macro will
- show a message like ERROR (xx) (called from
- yyy).
+ When no debug flag is set, this macro is ignored.
<function>snd_BUG()</function>
- It calls snd_assert(0,) -- that is, just
- prints the error message at the point. It's useful to show that
- a fatal error happens there.
+ It shows BUG? message and
+ stack trace as well as snd_assert at the point.
+ It's useful to show that a fatal error happens there.
+
+
+ When no debug flag is set, this macro is ignored.
diff --git a/Documentation/sparse.txt b/Documentation/sparse.txt
index 1829009db771..3f1c5464b1c9 100644
--- a/Documentation/sparse.txt
+++ b/Documentation/sparse.txt
@@ -41,9 +41,9 @@ sure that bitwise types don't get mixed up (little-endian vs big-endian
vs cpu-endian vs whatever), and there the constant "0" really _is_
special.
-Modify top-level Makefile to say
+Use
-CHECK = sparse -Wbitwise
+ make C=[12] CF=-Wbitwise
or you don't get any checking at all.
diff --git a/Documentation/video4linux/bttv/README.freeze b/Documentation/video4linux/bttv/README.freeze
index 51f8d4379a94..4259dccc8287 100644
--- a/Documentation/video4linux/bttv/README.freeze
+++ b/Documentation/video4linux/bttv/README.freeze
@@ -27,9 +27,9 @@ information out of a register+stack dump printed by the kernel on
protection faults (so-called "kernel oops").
If you run into some kind of deadlock, you can try to dump a call trace
-for each process using sysrq-t (see Documentation/sysrq.txt). ksymoops
-will translate these dumps into kernel symbols too. This way it is
-possible to figure where *exactly* some process in "D" state is stuck.
+for each process using sysrq-t (see Documentation/sysrq.txt).
+This way it is possible to figure where *exactly* some process in "D"
+state is stuck.
I've seen reports that bttv 0.7.x crashes whereas 0.8.x works rock solid
for some people. Thus probably a small buglet left somewhere in bttv
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index 1b9bcd1fe98b..1ad9af1ca4d0 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -13,12 +13,13 @@ This optimization is more critical now as bigger and bigger physical memories
Users can use the huge page support in Linux kernel by either using the mmap
system call or standard SYSv shared memory system calls (shmget, shmat).
-First the Linux kernel needs to be built with CONFIG_HUGETLB_PAGE (present
-under Processor types and feature) and CONFIG_HUGETLBFS (present under file
-system option on config menu) config options.
+First the Linux kernel needs to be built with the CONFIG_HUGETLBFS
+(present under "File systems") and CONFIG_HUGETLB_PAGE (selected
+automatically when CONFIG_HUGETLBFS is selected) configuration
+options.
The kernel built with hugepage support should show the number of configured
-hugepages in the system by running the "cat /proc/meminfo" command.
+hugepages in the system by running the "cat /proc/meminfo" command.
/proc/meminfo also provides information about the total number of hugetlb
pages configured in the kernel. It also displays information about the
@@ -38,19 +39,19 @@ in the kernel.
/proc/sys/vm/nr_hugepages indicates the current number of configured hugetlb
pages in the kernel. Super user can dynamically request more (or free some
-pre-configured) hugepages.
-The allocation( or deallocation) of hugetlb pages is posible only if there are
+pre-configured) hugepages.
+The allocation (or deallocation) of hugetlb pages is possible only if there are
enough physically contiguous free pages in system (freeing of hugepages is
-possible only if there are enough hugetlb pages free that can be transfered
+possible only if there are enough hugetlb pages free that can be transfered
back to regular memory pool).
Pages that are used as hugetlb pages are reserved inside the kernel and can
-not be used for other purposes.
+not be used for other purposes.
Once the kernel with Hugetlb page support is built and running, a user can
use either the mmap system call or shared memory system calls to start using
the huge pages. It is required that the system administrator preallocate
-enough memory for huge page purposes.
+enough memory for huge page purposes.
Use the following command to dynamically allocate/deallocate hugepages:
@@ -80,9 +81,9 @@ memory (huge pages) allowed for that filesystem (/mnt/huge). The size is
rounded down to HPAGE_SIZE. The option nr_inode sets the maximum number of
inodes that /mnt/huge can use. If the size or nr_inode options are not
provided on command line then no limits are set. For size and nr_inodes
-options, you can use [G|g]/[M|m]/[K|k] to represent giga/mega/kilo. For
-example, size=2K has the same meaning as size=2048. An example is given at
-the end of this document.
+options, you can use [G|g]/[M|m]/[K|k] to represent giga/mega/kilo. For
+example, size=2K has the same meaning as size=2048. An example is given at
+the end of this document.
read and write system calls are not supported on files that reside on hugetlb
file systems.
diff --git a/MAINTAINERS b/MAINTAINERS
index d57c491212b1..995bfd8e6e7f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1077,6 +1077,26 @@ P: Jaroslav Kysela
M: perex@suse.cz
S: Maintained
+HPET: High Precision Event Timers driver (hpet.c)
+P: Clemens Ladisch
+M: clemens@ladisch.de
+S: Maintained
+
+HPET: i386
+P: Venkatesh Pallipadi (Venki)
+M: venkatesh.pallipadi@intel.com
+S: Maintained
+
+HPET: x86_64
+P: Andi Kleen and Vojtech Pavlik
+M: ak@muc.de and vojtech@suse.cz
+S: Maintained
+
+HPET: ACPI hpet.c
+P: Bob Picco
+M: bob.picco@hp.com
+S: Maintained
+
HPFS FILESYSTEM
P: Mikulas Patocka
M: mikulas@artax.karlin.mff.cuni.cz
@@ -2051,6 +2071,12 @@ P: Matt Mackall
M: mpm@selenic.com
S: Maintained
+RAPIDIO SUBSYSTEM
+P: Matt Porter
+M: mporter@kernel.crashing.org
+L: linux-kernel@vger.kernel.org
+S: Maintained
+
REAL TIME CLOCK DRIVER
P: Paul Gortmaker
M: p_gortmaker@yahoo.com
@@ -2455,10 +2481,10 @@ L: linux-kernel@vger.kernel.org
S: Maintained
TRIVIAL PATCHES
-P: Rusty Russell
-M: trivial@rustcorp.com.au
+P: Adrian Bunk
+M: trivial@kernel.org
L: linux-kernel@vger.kernel.org
-W: http://www.kernel.org/pub/linux/kernel/people/rusty/trivial/
+W: http://www.kernel.org/pub/linux/kernel/people/bunk/trivial/
S: Maintained
TMS380 TOKEN-RING NETWORK DRIVER
diff --git a/Makefile b/Makefile
index 2dac8010c142..ea96da1572d5 100644
--- a/Makefile
+++ b/Makefile
@@ -583,7 +583,7 @@ export MODLIB
ifeq ($(KBUILD_EXTMOD),)
-core-y += kernel/ mm/ fs/ ipc/ security/ crypto/
+core-y += kernel/ mm/ fs/ ipc/ security/ crypto/ block/
vmlinux-dirs := $(patsubst %/,%,$(filter %/, $(init-y) $(init-m) \
$(core-y) $(core-m) $(drivers-y) $(drivers-m) \
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 296bc03d1cf1..91d5ef3397be 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -324,7 +324,7 @@ menu "Kernel Features"
config SMP
bool "Symmetric Multi-Processing (EXPERIMENTAL)"
- depends on EXPERIMENTAL && BROKEN #&& n
+ depends on EXPERIMENTAL && REALVIEW_MPCORE
help
This enables support for systems with more than one CPU. If you have
a system with only one CPU, like most personal computers, say N. If
@@ -585,7 +585,7 @@ config FPE_NWFPE
config FPE_NWFPE_XP
bool "Support extended precision"
- depends on FPE_NWFPE && !CPU_BIG_ENDIAN
+ depends on FPE_NWFPE
help
Say Y to include 80-bit support in the kernel floating-point
emulator. Otherwise, only 32 and 64-bit support is compiled in.
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 9bd8609a2926..9a340e790da5 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -648,7 +648,7 @@ static int ptrace_setwmmxregs(struct task_struct *tsk, void __user *ufp)
#endif
-static int do_ptrace(int request, struct task_struct *child, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
unsigned long tmp;
int ret;
@@ -782,53 +782,6 @@ static int do_ptrace(int request, struct task_struct *child, long addr, long dat
return ret;
}
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
-{
- struct task_struct *child;
- int ret;
-
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- ret = security_ptrace(current->parent, current);
- if (ret)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret == 0)
- ret = do_ptrace(request, child, addr, data);
-
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
- return ret;
-}
-
asmlinkage void syscall_trace(int why, struct pt_regs *regs)
{
unsigned long ip;
diff --git a/arch/arm/mach-aaec2000/clock.c b/arch/arm/mach-aaec2000/clock.c
index 99e019169dda..0340ddc4824e 100644
--- a/arch/arm/mach-aaec2000/clock.c
+++ b/arch/arm/mach-aaec2000/clock.c
@@ -14,6 +14,7 @@
#include
#include
#include
+#include
#include
#include
diff --git a/arch/arm/mach-epxa10db/mm.c b/arch/arm/mach-epxa10db/mm.c
index e8832d0910ee..cfd0d2182d44 100644
--- a/arch/arm/mach-epxa10db/mm.c
+++ b/arch/arm/mach-epxa10db/mm.c
@@ -25,6 +25,7 @@
#include
#include
#include
+#include
#include
diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c
index a1b153d1626c..a4bafee77a06 100644
--- a/arch/arm/mach-integrator/impd1.c
+++ b/arch/arm/mach-integrator/impd1.c
@@ -420,8 +420,7 @@ static int impd1_probe(struct lm_device *dev)
free_impd1:
if (impd1 && impd1->base)
iounmap(impd1->base);
- if (impd1)
- kfree(impd1);
+ kfree(impd1);
release_lm:
release_mem_region(dev->resource.start, SZ_4K);
return ret;
diff --git a/arch/arm/mach-ixp2000/core.c b/arch/arm/mach-ixp2000/core.c
index df140962bb0f..6851abaf5524 100644
--- a/arch/arm/mach-ixp2000/core.c
+++ b/arch/arm/mach-ixp2000/core.c
@@ -84,63 +84,54 @@ static struct map_desc ixp2000_io_desc[] __initdata = {
.virtual = IXP2000_CAP_VIRT_BASE,
.pfn = __phys_to_pfn(IXP2000_CAP_PHYS_BASE),
.length = IXP2000_CAP_SIZE,
- .type = MT_DEVICE
+ .type = MT_IXP2000_DEVICE,
}, {
.virtual = IXP2000_INTCTL_VIRT_BASE,
.pfn = __phys_to_pfn(IXP2000_INTCTL_PHYS_BASE),
.length = IXP2000_INTCTL_SIZE,
- .type = MT_DEVICE
+ .type = MT_IXP2000_DEVICE,
}, {
.virtual = IXP2000_PCI_CREG_VIRT_BASE,
.pfn = __phys_to_pfn(IXP2000_PCI_CREG_PHYS_BASE),
.length = IXP2000_PCI_CREG_SIZE,
- .type = MT_DEVICE
+ .type = MT_IXP2000_DEVICE,
}, {
.virtual = IXP2000_PCI_CSR_VIRT_BASE,
.pfn = __phys_to_pfn(IXP2000_PCI_CSR_PHYS_BASE),
.length = IXP2000_PCI_CSR_SIZE,
- .type = MT_DEVICE
+ .type = MT_IXP2000_DEVICE,
}, {
.virtual = IXP2000_MSF_VIRT_BASE,
.pfn = __phys_to_pfn(IXP2000_MSF_PHYS_BASE),
.length = IXP2000_MSF_SIZE,
- .type = MT_DEVICE
+ .type = MT_IXP2000_DEVICE,
}, {
.virtual = IXP2000_PCI_IO_VIRT_BASE,
.pfn = __phys_to_pfn(IXP2000_PCI_IO_PHYS_BASE),
.length = IXP2000_PCI_IO_SIZE,
- .type = MT_DEVICE
+ .type = MT_IXP2000_DEVICE,
}, {
.virtual = IXP2000_PCI_CFG0_VIRT_BASE,
.pfn = __phys_to_pfn(IXP2000_PCI_CFG0_PHYS_BASE),
.length = IXP2000_PCI_CFG0_SIZE,
- .type = MT_DEVICE
+ .type = MT_IXP2000_DEVICE,
}, {
.virtual = IXP2000_PCI_CFG1_VIRT_BASE,
.pfn = __phys_to_pfn(IXP2000_PCI_CFG1_PHYS_BASE),
.length = IXP2000_PCI_CFG1_SIZE,
- .type = MT_DEVICE
+ .type = MT_IXP2000_DEVICE,
}
};
void __init ixp2000_map_io(void)
{
- extern unsigned int processor_id;
-
/*
- * On IXP2400 CPUs we need to use MT_IXP2000_DEVICE for
- * tweaking the PMDs so XCB=101. On IXP2800s we use the normal
- * PMD flags.
+ * On IXP2400 CPUs we need to use MT_IXP2000_DEVICE so that
+ * XCB=101 (to avoid triggering erratum #66), and given that
+ * this mode speeds up I/O accesses and we have write buffer
+ * flushes in the right places anyway, it doesn't hurt to use
+ * XCB=101 for all IXP2000s.
*/
- if ((processor_id & 0xfffffff0) == 0x69054190) {
- int i;
-
- printk(KERN_INFO "Enabling IXP2400 erratum #66 workaround\n");
-
- for(i=0;i
#include
#include
+#include
#include
#include
#include
diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig
index 4b63dc9eabfe..129976866d47 100644
--- a/arch/arm/mach-realview/Kconfig
+++ b/arch/arm/mach-realview/Kconfig
@@ -8,4 +8,13 @@ config MACH_REALVIEW_EB
help
Include support for the ARM(R) RealView Emulation Baseboard platform.
+config REALVIEW_MPCORE
+ bool "Support MPcore tile"
+ depends on MACH_REALVIEW_EB
+ help
+ Enable support for the MPCore tile on the Realview platform.
+ Since there are device address and interrupt differences, a
+ kernel built with this option enabled is not compatible with
+ other tiles.
+
endmenu
diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile
index 8d37ea1605fd..011a85c10627 100644
--- a/arch/arm/mach-realview/Makefile
+++ b/arch/arm/mach-realview/Makefile
@@ -4,3 +4,4 @@
obj-y := core.o clock.o
obj-$(CONFIG_MACH_REALVIEW_EB) += realview_eb.o
+obj-$(CONFIG_SMP) += platsmp.o headsmp.o
diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h
index 575599db74db..d83e8bad2038 100644
--- a/arch/arm/mach-realview/core.h
+++ b/arch/arm/mach-realview/core.h
@@ -23,6 +23,7 @@
#define __ASM_ARCH_REALVIEW_H
#include
+#include
#include
#define __io_address(n) __io(IO_ADDRESS(n))
diff --git a/arch/arm/mach-realview/headsmp.S b/arch/arm/mach-realview/headsmp.S
new file mode 100644
index 000000000000..4075473cf68a
--- /dev/null
+++ b/arch/arm/mach-realview/headsmp.S
@@ -0,0 +1,39 @@
+/*
+ * linux/arch/arm/mach-realview/headsmp.S
+ *
+ * Copyright (c) 2003 ARM Limited
+ * All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include
+#include
+
+ __INIT
+
+/*
+ * Realview specific entry point for secondary CPUs. This provides
+ * a "holding pen" into which all secondary cores are held until we're
+ * ready for them to initialise.
+ */
+ENTRY(realview_secondary_startup)
+ mrc p15, 0, r0, c0, c0, 5
+ and r0, r0, #15
+ adr r4, 1f
+ ldmia r4, {r5, r6}
+ sub r4, r4, r5
+ add r6, r6, r4
+pen: ldr r7, [r6]
+ cmp r7, r0
+ bne pen
+
+ /*
+ * we've been released from the holding pen: secondary_stack
+ * should now contain the SVC stack for this core
+ */
+ b secondary_startup
+
+1: .long .
+ .long pen_release
diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c
new file mode 100644
index 000000000000..9844644d0fb5
--- /dev/null
+++ b/arch/arm/mach-realview/platsmp.c
@@ -0,0 +1,195 @@
+/*
+ * linux/arch/arm/mach-realview/platsmp.c
+ *
+ * Copyright (C) 2002 ARM Ltd.
+ * All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+
+#include "core.h"
+
+extern void realview_secondary_startup(void);
+
+/*
+ * control for which core is the next to come out of the secondary
+ * boot "holding pen"
+ */
+volatile int __cpuinitdata pen_release = -1;
+
+static unsigned int __init get_core_count(void)
+{
+ unsigned int ncores;
+
+ ncores = __raw_readl(IO_ADDRESS(REALVIEW_MPCORE_SCU_BASE) + SCU_CONFIG);
+
+ return (ncores & 0x03) + 1;
+}
+
+static DEFINE_SPINLOCK(boot_lock);
+
+void __cpuinit platform_secondary_init(unsigned int cpu)
+{
+ /*
+ * the primary core may have used a "cross call" soft interrupt
+ * to get this processor out of WFI in the BootMonitor - make
+ * sure that we are no longer being sent this soft interrupt
+ */
+ smp_cross_call_done(cpumask_of_cpu(cpu));
+
+ /*
+ * if any interrupts are already enabled for the primary
+ * core (e.g. timer irq), then they will not have been enabled
+ * for us: do so
+ */
+ gic_cpu_init(__io_address(REALVIEW_GIC_CPU_BASE));
+
+ /*
+ * let the primary processor know we're out of the
+ * pen, then head off into the C entry point
+ */
+ pen_release = -1;
+
+ /*
+ * Synchronise with the boot thread.
+ */
+ spin_lock(&boot_lock);
+ spin_unlock(&boot_lock);
+}
+
+int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+ unsigned long timeout;
+
+ /*
+ * set synchronisation state between this boot processor
+ * and the secondary one
+ */
+ spin_lock(&boot_lock);
+
+ /*
+ * The secondary processor is waiting to be released from
+ * the holding pen - release it, then wait for it to flag
+ * that it has been released by resetting pen_release.
+ *
+ * Note that "pen_release" is the hardware CPU ID, whereas
+ * "cpu" is Linux's internal ID.
+ */
+ pen_release = cpu;
+ flush_cache_all();
+
+ /*
+ * XXX
+ *
+ * This is a later addition to the booting protocol: the
+ * bootMonitor now puts secondary cores into WFI, so
+ * poke_milo() no longer gets the cores moving; we need
+ * to send a soft interrupt to wake the secondary core.
+ * Use smp_cross_call() for this, since there's little
+ * point duplicating the code here
+ */
+ smp_cross_call(cpumask_of_cpu(cpu));
+
+ timeout = jiffies + (1 * HZ);
+ while (time_before(jiffies, timeout)) {
+ if (pen_release == -1)
+ break;
+
+ udelay(10);
+ }
+
+ /*
+ * now the secondary core is starting up let it run its
+ * calibrations, then wait for it to finish
+ */
+ spin_unlock(&boot_lock);
+
+ return pen_release != -1 ? -ENOSYS : 0;
+}
+
+static void __init poke_milo(void)
+{
+ extern void secondary_startup(void);
+
+ /* nobody is to be released from the pen yet */
+ pen_release = -1;
+
+ /*
+ * write the address of secondary startup into the system-wide
+ * flags register, then clear the bottom two bits, which is what
+ * BootMonitor is waiting for
+ */
+#if 1
+#define REALVIEW_SYS_FLAGSS_OFFSET 0x30
+ __raw_writel(virt_to_phys(realview_secondary_startup),
+ (IO_ADDRESS(REALVIEW_SYS_BASE) +
+ REALVIEW_SYS_FLAGSS_OFFSET));
+#define REALVIEW_SYS_FLAGSC_OFFSET 0x34
+ __raw_writel(3,
+ (IO_ADDRESS(REALVIEW_SYS_BASE) +
+ REALVIEW_SYS_FLAGSC_OFFSET));
+#endif
+
+ mb();
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+ unsigned int ncores = get_core_count();
+ unsigned int cpu = smp_processor_id();
+ int i;
+
+ /* sanity check */
+ if (ncores == 0) {
+ printk(KERN_ERR
+ "Realview: strange CM count of 0? Default to 1\n");
+
+ ncores = 1;
+ }
+
+ if (ncores > NR_CPUS) {
+ printk(KERN_WARNING
+ "Realview: no. of cores (%d) greater than configured "
+ "maximum of %d - clipping\n",
+ ncores, NR_CPUS);
+ ncores = NR_CPUS;
+ }
+
+ smp_store_cpu_info(cpu);
+
+ /*
+ * are we trying to boot more cores than exist?
+ */
+ if (max_cpus > ncores)
+ max_cpus = ncores;
+
+ /*
+ * Initialise the possible/present maps.
+ * cpu_possible_map describes the set of CPUs which may be present
+ * cpu_present_map describes the set of CPUs populated
+ */
+ for (i = 0; i < max_cpus; i++) {
+ cpu_set(i, cpu_possible_map);
+ cpu_set(i, cpu_present_map);
+ }
+
+ /*
+ * Do we need any more CPUs? If so, then let them know where
+ * to start. Note that, on modern versions of MILO, the "poke"
+ * doesn't actually do anything until each individual core is
+ * sent a soft interrupt to get it out of WFI
+ */
+ if (max_cpus > 1)
+ poke_milo();
+}
diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c
index 267bb07e39b7..7dc32503fdf2 100644
--- a/arch/arm/mach-realview/realview_eb.c
+++ b/arch/arm/mach-realview/realview_eb.c
@@ -136,6 +136,11 @@ static struct amba_device *amba_devs[] __initdata = {
static void __init gic_init_irq(void)
{
+#ifdef CONFIG_REALVIEW_MPCORE
+ writel(0x0000a05f, __io_address(REALVIEW_SYS_LOCK));
+ writel(0x008003c0, __io_address(REALVIEW_SYS_BASE) + 0xd8);
+ writel(0x00000000, __io_address(REALVIEW_SYS_LOCK));
+#endif
gic_dist_init(__io_address(REALVIEW_GIC_DIST_BASE));
gic_cpu_init(__io_address(REALVIEW_GIC_CPU_BASE));
}
diff --git a/arch/arm/mm/mm-armv.c b/arch/arm/mm/mm-armv.c
index fb5b40289de2..9e50127be635 100644
--- a/arch/arm/mm/mm-armv.c
+++ b/arch/arm/mm/mm-armv.c
@@ -354,7 +354,7 @@ void __init build_mem_type_table(void)
{
struct cachepolicy *cp;
unsigned int cr = get_cr();
- unsigned int user_pgprot;
+ unsigned int user_pgprot, kern_pgprot;
int cpu_arch = cpu_architecture();
int i;
@@ -381,7 +381,7 @@ void __init build_mem_type_table(void)
}
cp = &cache_policies[cachepolicy];
- user_pgprot = cp->pte;
+ kern_pgprot = user_pgprot = cp->pte;
/*
* ARMv6 and above have extended page tables.
@@ -393,6 +393,7 @@ void __init build_mem_type_table(void)
*/
mem_types[MT_MEMORY].prot_sect &= ~PMD_BIT4;
mem_types[MT_ROM].prot_sect &= ~PMD_BIT4;
+
/*
* Mark cache clean areas and XIP ROM read only
* from SVC mode and no access from userspace.
@@ -412,32 +413,47 @@ void __init build_mem_type_table(void)
* (iow, non-global)
*/
user_pgprot |= L_PTE_ASID;
+
+#ifdef CONFIG_SMP
+ /*
+ * Mark memory with the "shared" attribute for SMP systems
+ */
+ user_pgprot |= L_PTE_SHARED;
+ kern_pgprot |= L_PTE_SHARED;
+ mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+#endif
}
+ for (i = 0; i < 16; i++) {
+ unsigned long v = pgprot_val(protection_map[i]);
+ v = (v & ~(L_PTE_BUFFERABLE|L_PTE_CACHEABLE)) | user_pgprot;
+ protection_map[i] = __pgprot(v);
+ }
+
+ mem_types[MT_LOW_VECTORS].prot_pte |= kern_pgprot;
+ mem_types[MT_HIGH_VECTORS].prot_pte |= kern_pgprot;
+
if (cpu_arch >= CPU_ARCH_ARMv5) {
- mem_types[MT_LOW_VECTORS].prot_pte |= cp->pte & PTE_CACHEABLE;
- mem_types[MT_HIGH_VECTORS].prot_pte |= cp->pte & PTE_CACHEABLE;
+#ifndef CONFIG_SMP
+ /*
+ * Only use write-through for non-SMP systems
+ */
+ mem_types[MT_LOW_VECTORS].prot_pte &= ~L_PTE_BUFFERABLE;
+ mem_types[MT_HIGH_VECTORS].prot_pte &= ~L_PTE_BUFFERABLE;
+#endif
} else {
- mem_types[MT_LOW_VECTORS].prot_pte |= cp->pte;
- mem_types[MT_HIGH_VECTORS].prot_pte |= cp->pte;
mem_types[MT_MINICLEAN].prot_sect &= ~PMD_SECT_TEX(1);
}
+ pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG |
+ L_PTE_DIRTY | L_PTE_WRITE |
+ L_PTE_EXEC | kern_pgprot);
+
mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
mem_types[MT_ROM].prot_sect |= cp->pmd;
- for (i = 0; i < 16; i++) {
- unsigned long v = pgprot_val(protection_map[i]);
- v = (v & ~(PTE_BUFFERABLE|PTE_CACHEABLE)) | user_pgprot;
- protection_map[i] = __pgprot(v);
- }
-
- pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG |
- L_PTE_DIRTY | L_PTE_WRITE |
- L_PTE_EXEC | cp->pte);
-
switch (cp->pmd) {
case PMD_SECT_WT:
mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WT;
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 9bb5fff406fb..92f3ca31b7b9 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -12,6 +12,7 @@
#include
#include
#include
+#include
#include
#include
@@ -112,6 +113,9 @@ ENTRY(cpu_v6_dcache_clean_area)
ENTRY(cpu_v6_switch_mm)
mov r2, #0
ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id
+#ifdef CONFIG_SMP
+ orr r0, r0, #2 @ set shared pgtable
+#endif
mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB
mcr p15, 0, r2, c7, c10, 4 @ drain write buffer
mcr p15, 0, r0, c2, c0, 0 @ set TTB 0
@@ -140,7 +144,7 @@ ENTRY(cpu_v6_switch_mm)
ENTRY(cpu_v6_set_pte)
str r1, [r0], #-2048 @ linux version
- bic r2, r1, #0x000007f0
+ bic r2, r1, #0x000003f0
bic r2, r2, #0x00000003
orr r2, r2, #PTE_EXT_AP0 | 2
@@ -191,6 +195,23 @@ cpu_v6_name:
* - cache type register is implemented
*/
__v6_setup:
+#ifdef CONFIG_SMP
+ /* Set up the SCU on core 0 only */
+ mrc p15, 0, r0, c0, c0, 5 @ CPU core number
+ ands r0, r0, #15
+ moveq r0, #0x10000000 @ SCU_BASE
+ orreq r0, r0, #0x00100000
+ ldreq r5, [r0, #SCU_CTRL]
+ orreq r5, r5, #1
+ streq r5, [r0, #SCU_CTRL]
+
+#ifndef CONFIG_CPU_DCACHE_DISABLE
+ mrc p15, 0, r0, c1, c0, 1 @ Enable SMP/nAMP mode
+ orr r0, r0, #0x20
+ mcr p15, 0, r0, c1, c0, 1
+#endif
+#endif
+
mov r0, #0
mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
@@ -198,6 +219,9 @@ __v6_setup:
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs
mcr p15, 0, r0, c2, c0, 2 @ TTB control register
+#ifdef CONFIG_SMP
+ orr r4, r4, #2 @ set shared pgtable
+#endif
mcr p15, 0, r4, c2, c0, 1 @ load TTB1
#ifdef CONFIG_VFP
mrc p15, 0, r0, c1, c0, 2
diff --git a/arch/arm/nwfpe/fpa11.h b/arch/arm/nwfpe/fpa11.h
index 9677ae8448e8..da4c616b6c49 100644
--- a/arch/arm/nwfpe/fpa11.h
+++ b/arch/arm/nwfpe/fpa11.h
@@ -60,7 +60,7 @@ typedef union tagFPREG {
#ifdef CONFIG_FPE_NWFPE_XP
floatx80 fExtended;
#else
- int padding[3];
+ u32 padding[3];
#endif
} FPREG;
diff --git a/arch/arm/nwfpe/fpa11_cpdt.c b/arch/arm/nwfpe/fpa11_cpdt.c
index b0db5cbcc3b1..32859fa8dcfc 100644
--- a/arch/arm/nwfpe/fpa11_cpdt.c
+++ b/arch/arm/nwfpe/fpa11_cpdt.c
@@ -59,8 +59,13 @@ static inline void loadExtended(const unsigned int Fn, const unsigned int __user
p = (unsigned int *) &fpa11->fpreg[Fn].fExtended;
fpa11->fType[Fn] = typeExtended;
get_user(p[0], &pMem[0]); /* sign & exponent */
+#ifdef __ARMEB__
+ get_user(p[1], &pMem[1]); /* ms bits */
+ get_user(p[2], &pMem[2]); /* ls bits */
+#else
get_user(p[1], &pMem[2]); /* ls bits */
get_user(p[2], &pMem[1]); /* ms bits */
+#endif
}
#endif
@@ -177,8 +182,13 @@ static inline void storeExtended(const unsigned int Fn, unsigned int __user *pMe
}
put_user(val.i[0], &pMem[0]); /* sign & exp */
+#ifdef __ARMEB__
+ put_user(val.i[1], &pMem[1]); /* msw */
+ put_user(val.i[2], &pMem[2]);
+#else
put_user(val.i[1], &pMem[2]);
put_user(val.i[2], &pMem[1]); /* msw */
+#endif
}
#endif
diff --git a/arch/arm/nwfpe/fpopcode.c b/arch/arm/nwfpe/fpopcode.c
index 4c9f5703148c..67ff2ab08ea0 100644
--- a/arch/arm/nwfpe/fpopcode.c
+++ b/arch/arm/nwfpe/fpopcode.c
@@ -29,14 +29,14 @@
#ifdef CONFIG_FPE_NWFPE_XP
const floatx80 floatx80Constant[] = {
- {0x0000, 0x0000000000000000ULL}, /* extended 0.0 */
- {0x3fff, 0x8000000000000000ULL}, /* extended 1.0 */
- {0x4000, 0x8000000000000000ULL}, /* extended 2.0 */
- {0x4000, 0xc000000000000000ULL}, /* extended 3.0 */
- {0x4001, 0x8000000000000000ULL}, /* extended 4.0 */
- {0x4001, 0xa000000000000000ULL}, /* extended 5.0 */
- {0x3ffe, 0x8000000000000000ULL}, /* extended 0.5 */
- {0x4002, 0xa000000000000000ULL} /* extended 10.0 */
+ { .high = 0x0000, .low = 0x0000000000000000ULL},/* extended 0.0 */
+ { .high = 0x3fff, .low = 0x8000000000000000ULL},/* extended 1.0 */
+ { .high = 0x4000, .low = 0x8000000000000000ULL},/* extended 2.0 */
+ { .high = 0x4000, .low = 0xc000000000000000ULL},/* extended 3.0 */
+ { .high = 0x4001, .low = 0x8000000000000000ULL},/* extended 4.0 */
+ { .high = 0x4001, .low = 0xa000000000000000ULL},/* extended 5.0 */
+ { .high = 0x3ffe, .low = 0x8000000000000000ULL},/* extended 0.5 */
+ { .high = 0x4002, .low = 0xa000000000000000ULL},/* extended 10.0 */
};
#endif
diff --git a/arch/arm/nwfpe/softfloat-specialize b/arch/arm/nwfpe/softfloat-specialize
index acf409144763..d4a4c8e06635 100644
--- a/arch/arm/nwfpe/softfloat-specialize
+++ b/arch/arm/nwfpe/softfloat-specialize
@@ -332,6 +332,7 @@ static floatx80 commonNaNToFloatx80( commonNaNT a )
z.low = LIT64( 0xC000000000000000 ) | ( a.high>>1 );
z.high = ( ( (bits16) a.sign )<<15 ) | 0x7FFF;
+ z.__padding = 0;
return z;
}
diff --git a/arch/arm/nwfpe/softfloat.c b/arch/arm/nwfpe/softfloat.c
index f9f049132a17..0f9656e482ba 100644
--- a/arch/arm/nwfpe/softfloat.c
+++ b/arch/arm/nwfpe/softfloat.c
@@ -531,6 +531,7 @@ INLINE floatx80 packFloatx80( flag zSign, int32 zExp, bits64 zSig )
z.low = zSig;
z.high = ( ( (bits16) zSign )<<15 ) + zExp;
+ z.__padding = 0;
return z;
}
@@ -2831,6 +2832,7 @@ static floatx80 subFloatx80Sigs( struct roundingData *roundData, floatx80 a, flo
roundData->exception |= float_flag_invalid;
z.low = floatx80_default_nan_low;
z.high = floatx80_default_nan_high;
+ z.__padding = 0;
return z;
}
if ( aExp == 0 ) {
@@ -2950,6 +2952,7 @@ floatx80 floatx80_mul( struct roundingData *roundData, floatx80 a, floatx80 b )
roundData->exception |= float_flag_invalid;
z.low = floatx80_default_nan_low;
z.high = floatx80_default_nan_high;
+ z.__padding = 0;
return z;
}
return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) );
@@ -3015,6 +3018,7 @@ floatx80 floatx80_div( struct roundingData *roundData, floatx80 a, floatx80 b )
roundData->exception |= float_flag_invalid;
z.low = floatx80_default_nan_low;
z.high = floatx80_default_nan_high;
+ z.__padding = 0;
return z;
}
roundData->exception |= float_flag_divbyzero;
@@ -3093,6 +3097,7 @@ floatx80 floatx80_rem( struct roundingData *roundData, floatx80 a, floatx80 b )
roundData->exception |= float_flag_invalid;
z.low = floatx80_default_nan_low;
z.high = floatx80_default_nan_high;
+ z.__padding = 0;
return z;
}
normalizeFloatx80Subnormal( bSig, &bExp, &bSig );
@@ -3184,6 +3189,7 @@ floatx80 floatx80_sqrt( struct roundingData *roundData, floatx80 a )
roundData->exception |= float_flag_invalid;
z.low = floatx80_default_nan_low;
z.high = floatx80_default_nan_high;
+ z.__padding = 0;
return z;
}
if ( aExp == 0 ) {
diff --git a/arch/arm/nwfpe/softfloat.h b/arch/arm/nwfpe/softfloat.h
index 14151700b6b2..978c699673c6 100644
--- a/arch/arm/nwfpe/softfloat.h
+++ b/arch/arm/nwfpe/softfloat.h
@@ -51,11 +51,17 @@ input or output the `floatx80' type will be defined.
Software IEC/IEEE floating-point types.
-------------------------------------------------------------------------------
*/
-typedef unsigned long int float32;
-typedef unsigned long long float64;
+typedef u32 float32;
+typedef u64 float64;
typedef struct {
- unsigned short high;
- unsigned long long low;
+#ifdef __ARMEB__
+ u16 __padding;
+ u16 high;
+#else
+ u16 high;
+ u16 __padding;
+#endif
+ u64 low;
} floatx80;
/*
diff --git a/arch/arm26/kernel/ptrace.c b/arch/arm26/kernel/ptrace.c
index cf7e977d18c8..4e6b7356a722 100644
--- a/arch/arm26/kernel/ptrace.c
+++ b/arch/arm26/kernel/ptrace.c
@@ -546,7 +546,7 @@ static int ptrace_setfpregs(struct task_struct *tsk, void *ufp)
sizeof(struct user_fp)) ? -EFAULT : 0;
}
-static int do_ptrace(int request, struct task_struct *child, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
unsigned long tmp;
int ret;
@@ -665,53 +665,6 @@ static int do_ptrace(int request, struct task_struct *child, long addr, long dat
return ret;
}
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
-{
- struct task_struct *child;
- int ret;
-
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- ret = security_ptrace(current->parent, current);
- if (ret)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret == 0)
- ret = do_ptrace(request, child, addr, data);
-
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
- return ret;
-}
-
asmlinkage void syscall_trace(int why, struct pt_regs *regs)
{
unsigned long ip;
diff --git a/arch/cris/arch-v10/README.mm b/arch/cris/arch-v10/README.mm
index 6f08903f3139..517d1f027fe8 100644
--- a/arch/cris/arch-v10/README.mm
+++ b/arch/cris/arch-v10/README.mm
@@ -177,7 +177,7 @@ The example address is 0xd004000c; in binary this is:
Given the top-level Page Directory, the offset in that directory is calculated
using the upper 8 bits:
-extern inline pgd_t * pgd_offset(struct mm_struct * mm, unsigned long address)
+static inline pgd_t * pgd_offset(struct mm_struct * mm, unsigned long address)
{
return mm->pgd + (address >> PGDIR_SHIFT);
}
@@ -190,14 +190,14 @@ The pgd_t from our example will therefore be the 208'th (0xd0) entry in mm->pgd.
Since the Middle Directory does not exist, it is a unity mapping:
-extern inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
+static inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
{
return (pmd_t *) dir;
}
The Page Table provides the final lookup by using bits 13 to 23 as index:
-extern inline pte_t * pte_offset(pmd_t * dir, unsigned long address)
+static inline pte_t * pte_offset(pmd_t * dir, unsigned long address)
{
return (pte_t *) pmd_page(*dir) + ((address >> PAGE_SHIFT) &
(PTRS_PER_PTE - 1));
diff --git a/arch/cris/arch-v10/kernel/ptrace.c b/arch/cris/arch-v10/kernel/ptrace.c
index 130dd214e41d..6cbd34a27b90 100644
--- a/arch/cris/arch-v10/kernel/ptrace.c
+++ b/arch/cris/arch-v10/kernel/ptrace.c
@@ -76,55 +76,11 @@ ptrace_disable(struct task_struct *child)
* (in user space) where the result of the ptrace call is written (instead of
* being returned).
*/
-asmlinkage int
-sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
int ret;
unsigned long __user *datap = (unsigned long __user *)data;
- lock_kernel();
- ret = -EPERM;
-
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- ret = security_ptrace(current->parent, current);
- if (ret)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
-
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
-
- if (child)
- get_task_struct(child);
-
- read_unlock(&tasklist_lock);
-
- if (!child)
- goto out;
-
- ret = -EPERM;
-
- if (pid == 1) /* Leave the init process alone! */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
/* Read word at location address. */
case PTRACE_PEEKTEXT:
@@ -289,10 +245,7 @@ sys_ptrace(long request, long pid, long addr, long data)
ret = ptrace_request(child, request, addr, data);
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
+
return ret;
}
diff --git a/arch/cris/arch-v10/kernel/signal.c b/arch/cris/arch-v10/kernel/signal.c
index 693771961f85..19bcad05716f 100644
--- a/arch/cris/arch-v10/kernel/signal.c
+++ b/arch/cris/arch-v10/kernel/signal.c
@@ -476,7 +476,7 @@ give_sigsegv:
* OK, we're invoking a handler
*/
-extern inline void
+static inline void
handle_signal(int canrestart, unsigned long sig,
siginfo_t *info, struct k_sigaction *ka,
sigset_t *oldset, struct pt_regs * regs)
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index ca72076c630a..501fa52d8d3a 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -277,7 +277,7 @@ struct file_operations cryptocop_fops = {
static void free_cdesc(struct cryptocop_dma_desc *cdesc)
{
DEBUG(printk("free_cdesc: cdesc 0x%p, from_pool=%d\n", cdesc, cdesc->from_pool));
- if (cdesc->free_buf) kfree(cdesc->free_buf);
+ kfree(cdesc->free_buf);
if (cdesc->from_pool) {
unsigned long int flags;
@@ -2950,15 +2950,15 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
put_page(outpages[i]);
}
- if (digest_result) kfree(digest_result);
- if (inpages) kfree(inpages);
- if (outpages) kfree(outpages);
+ kfree(digest_result);
+ kfree(inpages);
+ kfree(outpages);
if (cop){
- if (cop->tfrm_op.indata) kfree(cop->tfrm_op.indata);
- if (cop->tfrm_op.outdata) kfree(cop->tfrm_op.outdata);
+ kfree(cop->tfrm_op.indata);
+ kfree(cop->tfrm_op.outdata);
kfree(cop);
}
- if (jc) kfree(jc);
+ kfree(jc);
DEBUG(print_lock_status());
diff --git a/arch/cris/arch-v32/kernel/ptrace.c b/arch/cris/arch-v32/kernel/ptrace.c
index 208489da2a87..5528b83a622b 100644
--- a/arch/cris/arch-v32/kernel/ptrace.c
+++ b/arch/cris/arch-v32/kernel/ptrace.c
@@ -99,55 +99,11 @@ ptrace_disable(struct task_struct *child)
}
-asmlinkage int
-sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
int ret;
unsigned long __user *datap = (unsigned long __user *)data;
- lock_kernel();
- ret = -EPERM;
-
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- ret = security_ptrace(current->parent, current);
- if (ret)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
-
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
-
- if (child)
- get_task_struct(child);
-
- read_unlock(&tasklist_lock);
-
- if (!child)
- goto out;
-
- ret = -EPERM;
-
- if (pid == 1) /* Leave the init process alone! */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
/* Read word at location address. */
case PTRACE_PEEKTEXT:
@@ -347,10 +303,7 @@ sys_ptrace(long request, long pid, long addr, long data)
ret = ptrace_request(child, request, addr, data);
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
+
return ret;
}
diff --git a/arch/cris/arch-v32/kernel/signal.c b/arch/cris/arch-v32/kernel/signal.c
index 0a3614dab887..99e59b3eacf8 100644
--- a/arch/cris/arch-v32/kernel/signal.c
+++ b/arch/cris/arch-v32/kernel/signal.c
@@ -513,7 +513,7 @@ give_sigsegv:
}
/* Invoke a singal handler to, well, handle the signal. */
-extern inline void
+static inline void
handle_signal(int canrestart, unsigned long sig,
siginfo_t *info, struct k_sigaction *ka,
sigset_t *oldset, struct pt_regs * regs)
diff --git a/arch/cris/mm/ioremap.c b/arch/cris/mm/ioremap.c
index a92ac9877582..1780df3ed9e5 100644
--- a/arch/cris/mm/ioremap.c
+++ b/arch/cris/mm/ioremap.c
@@ -16,7 +16,7 @@
#include
#include
-extern inline void remap_area_pte(pte_t * pte, unsigned long address, unsigned long size,
+static inline void remap_area_pte(pte_t * pte, unsigned long address, unsigned long size,
unsigned long phys_addr, pgprot_t prot)
{
unsigned long end;
diff --git a/arch/frv/kernel/ptrace.c b/arch/frv/kernel/ptrace.c
index cb335a14a315..f953484e7d59 100644
--- a/arch/frv/kernel/ptrace.c
+++ b/arch/frv/kernel/ptrace.c
@@ -106,48 +106,11 @@ void ptrace_enable(struct task_struct *child)
child->thread.frame0->__status |= REG__STATUS_STEP;
}
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
unsigned long tmp;
int ret;
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- ret = security_ptrace(current->parent, current);
- if (ret)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
@@ -351,10 +314,6 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
ret = -EIO;
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
return ret;
}
diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c
index a569fe4aa284..0ff6f79b0fed 100644
--- a/arch/h8300/kernel/ptrace.c
+++ b/arch/h8300/kernel/ptrace.c
@@ -57,43 +57,10 @@ void ptrace_disable(struct task_struct *child)
h8300_disable_trace(child);
}
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
int ret;
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA: {
@@ -251,10 +218,6 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
ret = -EIO;
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
return ret;
}
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index bac0da731ee3..dbf90ad6eac3 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -997,8 +997,21 @@ source "drivers/Kconfig"
source "fs/Kconfig"
+menu "Instrumentation Support"
+ depends on EXPERIMENTAL
+
source "arch/i386/oprofile/Kconfig"
+config KPROBES
+ bool "Kprobes (EXPERIMENTAL)"
+ help
+ Kprobes allows you to trap at almost any kernel address and
+ execute a callback function. register_kprobe() establishes
+ a probepoint and specifies the callback. Kprobes is useful
+ for kernel debugging, non-intrusive instrumentation and testing.
+ If in doubt, say "N".
+endmenu
+
source "arch/i386/Kconfig.debug"
source "security/Kconfig"
diff --git a/arch/i386/Kconfig.debug b/arch/i386/Kconfig.debug
index 5228c40a6fb2..c48b424dd640 100644
--- a/arch/i386/Kconfig.debug
+++ b/arch/i386/Kconfig.debug
@@ -22,16 +22,6 @@ config DEBUG_STACKOVERFLOW
This option will cause messages to be printed if free stack space
drops below a certain limit.
-config KPROBES
- bool "Kprobes"
- depends on DEBUG_KERNEL
- help
- Kprobes allows you to trap at almost any kernel address and
- execute a callback function. register_kprobe() establishes
- a probepoint and specifies the callback. Kprobes is useful
- for kernel debugging, non-intrusive instrumentation and testing.
- If in doubt, say "N".
-
config DEBUG_STACK_USAGE
bool "Stack utilization instrumentation"
depends on DEBUG_KERNEL
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index 7c724ffa08bb..496a2c9909fe 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -559,14 +559,20 @@ void __devinit setup_local_APIC(void)
* If Linux enabled the LAPIC against the BIOS default
* disable it down before re-entering the BIOS on shutdown.
* Otherwise the BIOS may get confused and not power-off.
+ * Additionally clear all LVT entries before disable_local_APIC
+ * for the case where Linux didn't enable the LAPIC.
*/
void lapic_shutdown(void)
{
- if (!cpu_has_apic || !enabled_via_apicbase)
+ if (!cpu_has_apic)
return;
local_irq_disable();
- disable_local_APIC();
+ clear_local_APIC();
+
+ if (enabled_via_apicbase)
+ disable_local_APIC();
+
local_irq_enable();
}
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index d2ef0c2aa93e..86e80c551478 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -447,8 +447,7 @@ static char * apm_event_name[] = {
"system standby resume",
"capabilities change"
};
-#define NR_APM_EVENT_NAME \
- (sizeof(apm_event_name) / sizeof(apm_event_name[0]))
+#define NR_APM_EVENT_NAME ARRAY_SIZE(apm_event_name)
typedef struct lookup_t {
int key;
@@ -479,7 +478,7 @@ static const lookup_t error_table[] = {
{ APM_NO_ERROR, "BIOS did not set a return code" },
{ APM_NOT_PRESENT, "No APM present" }
};
-#define ERROR_COUNT (sizeof(error_table)/sizeof(lookup_t))
+#define ERROR_COUNT ARRAY_SIZE(error_table)
/**
* apm_error - display an APM error
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 74145a33cb0f..c145fb30002e 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -30,8 +30,6 @@ static int disable_x86_serial_nr __devinitdata = 1;
struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {};
-extern void mcheck_init(struct cpuinfo_x86 *c);
-
extern int disable_pse;
static void default_init(struct cpuinfo_x86 * c)
@@ -429,9 +427,8 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c)
}
/* Init Machine Check Exception if available. */
-#ifdef CONFIG_X86_MCE
mcheck_init(c);
-#endif
+
if (c == &boot_cpu_data)
sysenter_setup();
enable_sep_cpu();
diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
index caa9f7711343..871366b83b3f 100644
--- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -377,10 +377,9 @@ acpi_cpufreq_cpu_init (
arg0.buffer.length = 12;
arg0.buffer.pointer = (u8 *) arg0_buf;
- data = kmalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL);
+ data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL);
if (!data)
return (-ENOMEM);
- memset(data, 0, sizeof(struct cpufreq_acpi_io));
acpi_io_data[cpu] = data;
diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k7.c b/arch/i386/kernel/cpu/cpufreq/powernow-k7.c
index 73a5dc5b26b8..edcd626001da 100644
--- a/arch/i386/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/i386/kernel/cpu/cpufreq/powernow-k7.c
@@ -171,10 +171,9 @@ static int get_ranges (unsigned char *pst)
unsigned int speed;
u8 fid, vid;
- powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table) * (number_scales + 1)), GFP_KERNEL);
+ powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * (number_scales + 1)), GFP_KERNEL);
if (!powernow_table)
return -ENOMEM;
- memset(powernow_table, 0, (sizeof(struct cpufreq_frequency_table) * (number_scales + 1)));
for (j=0 ; j < number_scales; j++) {
fid = *pst++;
@@ -305,16 +304,13 @@ static int powernow_acpi_init(void)
goto err0;
}
- acpi_processor_perf = kmalloc(sizeof(struct acpi_processor_performance),
+ acpi_processor_perf = kzalloc(sizeof(struct acpi_processor_performance),
GFP_KERNEL);
-
if (!acpi_processor_perf) {
retval = -ENOMEM;
goto err0;
}
- memset(acpi_processor_perf, 0, sizeof(struct acpi_processor_performance));
-
if (acpi_processor_register_performance(acpi_processor_perf, 0)) {
retval = -EIO;
goto err1;
@@ -337,14 +333,12 @@ static int powernow_acpi_init(void)
goto err2;
}
- powernow_table = kmalloc((number_scales + 1) * (sizeof(struct cpufreq_frequency_table)), GFP_KERNEL);
+ powernow_table = kzalloc((number_scales + 1) * (sizeof(struct cpufreq_frequency_table)), GFP_KERNEL);
if (!powernow_table) {
retval = -ENOMEM;
goto err2;
}
- memset(powernow_table, 0, ((number_scales + 1) * sizeof(struct cpufreq_frequency_table)));
-
pc.val = (unsigned long) acpi_processor_perf->states[0].control;
for (i = 0; i < number_scales; i++) {
u8 fid, vid;
diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
index 2d5c9adba0cd..68a1fc87f4ca 100644
--- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
@@ -462,7 +462,6 @@ static int check_supported_cpu(unsigned int cpu)
oldmask = current->cpus_allowed;
set_cpus_allowed(current, cpumask_of_cpu(cpu));
- schedule();
if (smp_processor_id() != cpu) {
printk(KERN_ERR "limiting to cpu %u failed\n", cpu);
@@ -497,9 +496,7 @@ static int check_supported_cpu(unsigned int cpu)
out:
set_cpus_allowed(current, oldmask);
- schedule();
return rc;
-
}
static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid)
@@ -913,7 +910,6 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
/* only run on specific CPU from here on */
oldmask = current->cpus_allowed;
set_cpus_allowed(current, cpumask_of_cpu(pol->cpu));
- schedule();
if (smp_processor_id() != pol->cpu) {
printk(KERN_ERR "limiting to cpu %u failed\n", pol->cpu);
@@ -968,8 +964,6 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
err_out:
set_cpus_allowed(current, oldmask);
- schedule();
-
return ret;
}
@@ -991,12 +985,11 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol)
if (!check_supported_cpu(pol->cpu))
return -ENODEV;
- data = kmalloc(sizeof(struct powernow_k8_data), GFP_KERNEL);
+ data = kzalloc(sizeof(struct powernow_k8_data), GFP_KERNEL);
if (!data) {
printk(KERN_ERR PFX "unable to alloc powernow_k8_data");
return -ENOMEM;
}
- memset(data,0,sizeof(struct powernow_k8_data));
data->cpu = pol->cpu;
@@ -1026,7 +1019,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol)
/* only run on specific CPU from here on */
oldmask = current->cpus_allowed;
set_cpus_allowed(current, cpumask_of_cpu(pol->cpu));
- schedule();
if (smp_processor_id() != pol->cpu) {
printk(KERN_ERR "limiting to cpu %u failed\n", pol->cpu);
@@ -1045,7 +1037,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol)
/* run on any CPU again */
set_cpus_allowed(current, oldmask);
- schedule();
pol->governor = CPUFREQ_DEFAULT_GOVERNOR;
pol->cpus = cpu_core_map[pol->cpu];
@@ -1080,7 +1071,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol)
err_out:
set_cpus_allowed(current, oldmask);
- schedule();
powernow_k8_cpu_exit_acpi(data);
kfree(data);
@@ -1116,17 +1106,14 @@ static unsigned int powernowk8_get (unsigned int cpu)
set_cpus_allowed(current, oldmask);
return 0;
}
- preempt_disable();
-
+
if (query_current_values_with_pending_wait(data))
goto out;
khz = find_khz_freq_from_fid(data->currfid);
- out:
- preempt_enable_no_resched();
+out:
set_cpus_allowed(current, oldmask);
-
return khz;
}
diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c
index 1465974256c9..edb9873e27e3 100644
--- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -67,7 +67,7 @@ static const struct cpu_id cpu_ids[] = {
[CPU_MP4HT_D0] = {15, 3, 4 },
[CPU_MP4HT_E0] = {15, 4, 1 },
};
-#define N_IDS (sizeof(cpu_ids)/sizeof(cpu_ids[0]))
+#define N_IDS ARRAY_SIZE(cpu_ids)
struct cpu_model
{
@@ -423,12 +423,11 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy)
}
}
- centrino_model[cpu] = kmalloc(sizeof(struct cpu_model), GFP_KERNEL);
+ centrino_model[cpu] = kzalloc(sizeof(struct cpu_model), GFP_KERNEL);
if (!centrino_model[cpu]) {
result = -ENOMEM;
goto err_unreg;
}
- memset(centrino_model[cpu], 0, sizeof(struct cpu_model));
centrino_model[cpu]->model_name=NULL;
centrino_model[cpu]->max_freq = p.states[0].core_frequency * 1000;
diff --git a/arch/i386/kernel/cpu/mcheck/k7.c b/arch/i386/kernel/cpu/mcheck/k7.c
index 7c6b9c73522f..fc5d5215e23d 100644
--- a/arch/i386/kernel/cpu/mcheck/k7.c
+++ b/arch/i386/kernel/cpu/mcheck/k7.c
@@ -68,7 +68,7 @@ static fastcall void k7_machine_check(struct pt_regs * regs, long error_code)
/* AMD K7 machine check is Intel like */
-void __devinit amd_mcheck_init(struct cpuinfo_x86 *c)
+void amd_mcheck_init(struct cpuinfo_x86 *c)
{
u32 l, h;
int i;
diff --git a/arch/i386/kernel/cpu/mcheck/mce.c b/arch/i386/kernel/cpu/mcheck/mce.c
index 2cf25d2ba0f1..6170af3c271a 100644
--- a/arch/i386/kernel/cpu/mcheck/mce.c
+++ b/arch/i386/kernel/cpu/mcheck/mce.c
@@ -16,7 +16,7 @@
#include "mce.h"
-int mce_disabled __devinitdata = 0;
+int mce_disabled = 0;
int nr_mce_banks;
EXPORT_SYMBOL_GPL(nr_mce_banks); /* non-fatal.o */
@@ -31,7 +31,7 @@ static fastcall void unexpected_machine_check(struct pt_regs * regs, long error_
void fastcall (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check;
/* This has to be run for each processor */
-void __devinit mcheck_init(struct cpuinfo_x86 *c)
+void mcheck_init(struct cpuinfo_x86 *c)
{
if (mce_disabled==1)
return;
diff --git a/arch/i386/kernel/cpu/mcheck/p4.c b/arch/i386/kernel/cpu/mcheck/p4.c
index 1d1e885f500a..fd2c459a31ef 100644
--- a/arch/i386/kernel/cpu/mcheck/p4.c
+++ b/arch/i386/kernel/cpu/mcheck/p4.c
@@ -77,7 +77,7 @@ fastcall void smp_thermal_interrupt(struct pt_regs *regs)
}
/* P4/Xeon Thermal regulation detect and init */
-static void __devinit intel_init_thermal(struct cpuinfo_x86 *c)
+static void intel_init_thermal(struct cpuinfo_x86 *c)
{
u32 l, h;
unsigned int cpu = smp_processor_id();
@@ -231,7 +231,7 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code)
}
-void __devinit intel_p4_mcheck_init(struct cpuinfo_x86 *c)
+void intel_p4_mcheck_init(struct cpuinfo_x86 *c)
{
u32 l, h;
int i;
diff --git a/arch/i386/kernel/cpu/mcheck/p5.c b/arch/i386/kernel/cpu/mcheck/p5.c
index 3a2e24baddc7..94bc43d950cf 100644
--- a/arch/i386/kernel/cpu/mcheck/p5.c
+++ b/arch/i386/kernel/cpu/mcheck/p5.c
@@ -28,7 +28,7 @@ static fastcall void pentium_machine_check(struct pt_regs * regs, long error_cod
}
/* Set up machine check reporting for processors with Intel style MCE */
-void __devinit intel_p5_mcheck_init(struct cpuinfo_x86 *c)
+void intel_p5_mcheck_init(struct cpuinfo_x86 *c)
{
u32 l, h;
diff --git a/arch/i386/kernel/cpu/mcheck/p6.c b/arch/i386/kernel/cpu/mcheck/p6.c
index 979b18bc95c1..deeae42ce199 100644
--- a/arch/i386/kernel/cpu/mcheck/p6.c
+++ b/arch/i386/kernel/cpu/mcheck/p6.c
@@ -79,7 +79,7 @@ static fastcall void intel_machine_check(struct pt_regs * regs, long error_code)
}
/* Set up machine check reporting for processors with Intel style MCE */
-void __devinit intel_p6_mcheck_init(struct cpuinfo_x86 *c)
+void intel_p6_mcheck_init(struct cpuinfo_x86 *c)
{
u32 l, h;
int i;
diff --git a/arch/i386/kernel/cpu/mcheck/winchip.c b/arch/i386/kernel/cpu/mcheck/winchip.c
index 5b9d2dd411d3..9e424b6c293d 100644
--- a/arch/i386/kernel/cpu/mcheck/winchip.c
+++ b/arch/i386/kernel/cpu/mcheck/winchip.c
@@ -22,7 +22,7 @@ static fastcall void winchip_machine_check(struct pt_regs * regs, long error_cod
}
/* Set up machine check reporting on the Winchip C6 series */
-void __devinit winchip_mcheck_init(struct cpuinfo_x86 *c)
+void winchip_mcheck_init(struct cpuinfo_x86 *c)
{
u32 lo, hi;
machine_check_vector = winchip_machine_check;
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 6345b430b105..32b0c24ab9a6 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -31,22 +31,16 @@
#include
#include
#include
-#include
#include
#include
#include
#include
-static struct kprobe *current_kprobe;
-static unsigned long kprobe_status, kprobe_old_eflags, kprobe_saved_eflags;
-static struct kprobe *kprobe_prev;
-static unsigned long kprobe_status_prev, kprobe_old_eflags_prev, kprobe_saved_eflags_prev;
-static struct pt_regs jprobe_saved_regs;
-static long *jprobe_saved_esp;
-/* copy of the kernel stack at the probe fire time */
-static kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
void jprobe_return_end(void);
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
/*
* returns non-zero if opcode modifies the interrupt flag.
*/
@@ -91,29 +85,30 @@ void __kprobes arch_remove_kprobe(struct kprobe *p)
{
}
-static inline void save_previous_kprobe(void)
+static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
- kprobe_prev = current_kprobe;
- kprobe_status_prev = kprobe_status;
- kprobe_old_eflags_prev = kprobe_old_eflags;
- kprobe_saved_eflags_prev = kprobe_saved_eflags;
+ kcb->prev_kprobe.kp = kprobe_running();
+ kcb->prev_kprobe.status = kcb->kprobe_status;
+ kcb->prev_kprobe.old_eflags = kcb->kprobe_old_eflags;
+ kcb->prev_kprobe.saved_eflags = kcb->kprobe_saved_eflags;
}
-static inline void restore_previous_kprobe(void)
+static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
- current_kprobe = kprobe_prev;
- kprobe_status = kprobe_status_prev;
- kprobe_old_eflags = kprobe_old_eflags_prev;
- kprobe_saved_eflags = kprobe_saved_eflags_prev;
+ __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+ kcb->kprobe_status = kcb->prev_kprobe.status;
+ kcb->kprobe_old_eflags = kcb->prev_kprobe.old_eflags;
+ kcb->kprobe_saved_eflags = kcb->prev_kprobe.saved_eflags;
}
-static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs)
+static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
{
- current_kprobe = p;
- kprobe_saved_eflags = kprobe_old_eflags
+ __get_cpu_var(current_kprobe) = p;
+ kcb->kprobe_saved_eflags = kcb->kprobe_old_eflags
= (regs->eflags & (TF_MASK | IF_MASK));
if (is_IF_modifier(p->opcode))
- kprobe_saved_eflags &= ~IF_MASK;
+ kcb->kprobe_saved_eflags &= ~IF_MASK;
}
static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
@@ -127,6 +122,7 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
regs->eip = (unsigned long)&p->ainsn.insn;
}
+/* Called with kretprobe_lock held */
void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
struct pt_regs *regs)
{
@@ -157,9 +153,15 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
int ret = 0;
kprobe_opcode_t *addr = NULL;
unsigned long *lp;
+ struct kprobe_ctlblk *kcb;
- /* We're in an interrupt, but this is clear and BUG()-safe. */
+ /*
+ * We don't want to be preempted for the entire
+ * duration of kprobe processing
+ */
preempt_disable();
+ kcb = get_kprobe_ctlblk();
+
/* Check if the application is using LDT entry for its code segment and
* calculate the address by reading the base address from the LDT entry.
*/
@@ -173,15 +175,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
}
/* Check we're not actually recursing */
if (kprobe_running()) {
- /* We *are* holding lock here, so this is safe.
- Disarm the probe we just hit, and ignore it. */
p = get_kprobe(addr);
if (p) {
- if (kprobe_status == KPROBE_HIT_SS &&
+ if (kcb->kprobe_status == KPROBE_HIT_SS &&
*p->ainsn.insn == BREAKPOINT_INSTRUCTION) {
regs->eflags &= ~TF_MASK;
- regs->eflags |= kprobe_saved_eflags;
- unlock_kprobes();
+ regs->eflags |= kcb->kprobe_saved_eflags;
goto no_kprobe;
}
/* We have reentered the kprobe_handler(), since
@@ -190,26 +189,23 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
* just single step on the instruction of the new probe
* without calling any user handlers.
*/
- save_previous_kprobe();
- set_current_kprobe(p, regs);
+ save_previous_kprobe(kcb);
+ set_current_kprobe(p, regs, kcb);
p->nmissed++;
prepare_singlestep(p, regs);
- kprobe_status = KPROBE_REENTER;
+ kcb->kprobe_status = KPROBE_REENTER;
return 1;
} else {
- p = current_kprobe;
+ p = __get_cpu_var(current_kprobe);
if (p->break_handler && p->break_handler(p, regs)) {
goto ss_probe;
}
}
- /* If it's not ours, can't be delete race, (we hold lock). */
goto no_kprobe;
}
- lock_kprobes();
p = get_kprobe(addr);
if (!p) {
- unlock_kprobes();
if (regs->eflags & VM_MASK) {
/* We are in virtual-8086 mode. Return 0 */
goto no_kprobe;
@@ -232,8 +228,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
goto no_kprobe;
}
- kprobe_status = KPROBE_HIT_ACTIVE;
- set_current_kprobe(p, regs);
+ set_current_kprobe(p, regs, kcb);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
if (p->pre_handler && p->pre_handler(p, regs))
/* handler has already set things up, so skip ss setup */
@@ -241,7 +237,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
ss_probe:
prepare_singlestep(p, regs);
- kprobe_status = KPROBE_HIT_SS;
+ kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
no_kprobe:
@@ -269,9 +265,10 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
struct kretprobe_instance *ri = NULL;
struct hlist_head *head;
struct hlist_node *node, *tmp;
- unsigned long orig_ret_address = 0;
+ unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
+ spin_lock_irqsave(&kretprobe_lock, flags);
head = kretprobe_inst_table_head(current);
/*
@@ -310,14 +307,15 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
regs->eip = orig_ret_address;
- unlock_kprobes();
+ reset_current_kprobe();
+ spin_unlock_irqrestore(&kretprobe_lock, flags);
preempt_enable_no_resched();
- /*
- * By returning a non-zero value, we are telling
- * kprobe_handler() that we have handled unlocking
- * and re-enabling preemption.
- */
+ /*
+ * By returning a non-zero value, we are telling
+ * kprobe_handler() that we don't want the post_handler
+ * to run (and have re-enabled preemption)
+ */
return 1;
}
@@ -343,7 +341,8 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
* that is atop the stack is the address following the copied instruction.
* We need to make it the address following the original instruction.
*/
-static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes resume_execution(struct kprobe *p,
+ struct pt_regs *regs, struct kprobe_ctlblk *kcb)
{
unsigned long *tos = (unsigned long *)®s->esp;
unsigned long next_eip = 0;
@@ -353,7 +352,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
switch (p->ainsn.insn[0]) {
case 0x9c: /* pushfl */
*tos &= ~(TF_MASK | IF_MASK);
- *tos |= kprobe_old_eflags;
+ *tos |= kcb->kprobe_old_eflags;
break;
case 0xc3: /* ret/lret */
case 0xcb:
@@ -394,27 +393,30 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
/*
* Interrupts are disabled on entry as trap1 is an interrupt gate and they
- * remain disabled thoroughout this function. And we hold kprobe lock.
+ * remain disabled thoroughout this function.
*/
static inline int post_kprobe_handler(struct pt_regs *regs)
{
- if (!kprobe_running())
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ if (!cur)
return 0;
- if ((kprobe_status != KPROBE_REENTER) && current_kprobe->post_handler) {
- kprobe_status = KPROBE_HIT_SSDONE;
- current_kprobe->post_handler(current_kprobe, regs, 0);
+ if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ cur->post_handler(cur, regs, 0);
}
- resume_execution(current_kprobe, regs);
- regs->eflags |= kprobe_saved_eflags;
+ resume_execution(cur, regs, kcb);
+ regs->eflags |= kcb->kprobe_saved_eflags;
/*Restore back the original saved kprobes variables and continue. */
- if (kprobe_status == KPROBE_REENTER) {
- restore_previous_kprobe();
+ if (kcb->kprobe_status == KPROBE_REENTER) {
+ restore_previous_kprobe(kcb);
goto out;
}
- unlock_kprobes();
+ reset_current_kprobe();
out:
preempt_enable_no_resched();
@@ -429,18 +431,19 @@ out:
return 1;
}
-/* Interrupts disabled, kprobe_lock held. */
static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
{
- if (current_kprobe->fault_handler
- && current_kprobe->fault_handler(current_kprobe, regs, trapnr))
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
- if (kprobe_status & KPROBE_HIT_SS) {
- resume_execution(current_kprobe, regs);
- regs->eflags |= kprobe_old_eflags;
+ if (kcb->kprobe_status & KPROBE_HIT_SS) {
+ resume_execution(cur, regs, kcb);
+ regs->eflags |= kcb->kprobe_old_eflags;
- unlock_kprobes();
+ reset_current_kprobe();
preempt_enable_no_resched();
}
return 0;
@@ -453,39 +456,41 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct die_args *args = (struct die_args *)data;
+ int ret = NOTIFY_DONE;
+
switch (val) {
case DIE_INT3:
if (kprobe_handler(args->regs))
- return NOTIFY_STOP;
+ ret = NOTIFY_STOP;
break;
case DIE_DEBUG:
if (post_kprobe_handler(args->regs))
- return NOTIFY_STOP;
+ ret = NOTIFY_STOP;
break;
case DIE_GPF:
- if (kprobe_running() &&
- kprobe_fault_handler(args->regs, args->trapnr))
- return NOTIFY_STOP;
- break;
case DIE_PAGE_FAULT:
+ /* kprobe_running() needs smp_processor_id() */
+ preempt_disable();
if (kprobe_running() &&
kprobe_fault_handler(args->regs, args->trapnr))
- return NOTIFY_STOP;
+ ret = NOTIFY_STOP;
+ preempt_enable();
break;
default:
break;
}
- return NOTIFY_DONE;
+ return ret;
}
int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
struct jprobe *jp = container_of(p, struct jprobe, kp);
unsigned long addr;
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- jprobe_saved_regs = *regs;
- jprobe_saved_esp = ®s->esp;
- addr = (unsigned long)jprobe_saved_esp;
+ kcb->jprobe_saved_regs = *regs;
+ kcb->jprobe_saved_esp = ®s->esp;
+ addr = (unsigned long)(kcb->jprobe_saved_esp);
/*
* TBD: As Linus pointed out, gcc assumes that the callee
@@ -494,7 +499,8 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
* we also save and restore enough stack bytes to cover
* the argument area.
*/
- memcpy(jprobes_stack, (kprobe_opcode_t *) addr, MIN_STACK_SIZE(addr));
+ memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr,
+ MIN_STACK_SIZE(addr));
regs->eflags &= ~IF_MASK;
regs->eip = (unsigned long)(jp->entry);
return 1;
@@ -502,36 +508,40 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
void __kprobes jprobe_return(void)
{
- preempt_enable_no_resched();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
asm volatile (" xchgl %%ebx,%%esp \n"
" int3 \n"
" .globl jprobe_return_end \n"
" jprobe_return_end: \n"
" nop \n"::"b"
- (jprobe_saved_esp):"memory");
+ (kcb->jprobe_saved_esp):"memory");
}
int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
u8 *addr = (u8 *) (regs->eip - 1);
- unsigned long stack_addr = (unsigned long)jprobe_saved_esp;
+ unsigned long stack_addr = (unsigned long)(kcb->jprobe_saved_esp);
struct jprobe *jp = container_of(p, struct jprobe, kp);
if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) {
- if (®s->esp != jprobe_saved_esp) {
+ if (®s->esp != kcb->jprobe_saved_esp) {
struct pt_regs *saved_regs =
- container_of(jprobe_saved_esp, struct pt_regs, esp);
+ container_of(kcb->jprobe_saved_esp,
+ struct pt_regs, esp);
printk("current esp %p does not match saved esp %p\n",
- ®s->esp, jprobe_saved_esp);
+ ®s->esp, kcb->jprobe_saved_esp);
printk("Saved registers for jprobe %p\n", jp);
show_registers(saved_regs);
printk("Current registers\n");
show_registers(regs);
BUG();
}
- *regs = jprobe_saved_regs;
- memcpy((kprobe_opcode_t *) stack_addr, jprobes_stack,
+ *regs = kcb->jprobe_saved_regs;
+ memcpy((kprobe_opcode_t *) stack_addr, kcb->jprobes_stack,
MIN_STACK_SIZE(stack_addr));
+ preempt_enable_no_resched();
return 1;
}
return 0;
diff --git a/arch/i386/kernel/ldt.c b/arch/i386/kernel/ldt.c
index fe1ffa55587d..983f95707e11 100644
--- a/arch/i386/kernel/ldt.c
+++ b/arch/i386/kernel/ldt.c
@@ -18,6 +18,7 @@
#include
#include
#include
+#include
#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */
static void flush_ldt(void *null)
diff --git a/arch/i386/kernel/mca.c b/arch/i386/kernel/mca.c
index 8600faeea29d..558bb207720f 100644
--- a/arch/i386/kernel/mca.c
+++ b/arch/i386/kernel/mca.c
@@ -132,7 +132,7 @@ static struct resource mca_standard_resources[] = {
{ .start = 0x100, .end = 0x107, .name = "POS (MCA)" }
};
-#define MCA_STANDARD_RESOURCES (sizeof(mca_standard_resources)/sizeof(struct resource))
+#define MCA_STANDARD_RESOURCES ARRAY_SIZE(mca_standard_resources)
/**
* mca_read_and_store_pos - read the POS registers into a memory buffer
diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c
index efd11f09c996..5ffbb4b7ad05 100644
--- a/arch/i386/kernel/ptrace.c
+++ b/arch/i386/kernel/ptrace.c
@@ -354,49 +354,12 @@ ptrace_set_thread_area(struct task_struct *child,
return 0;
}
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
struct user * dummy = NULL;
int i, ret;
unsigned long __user *datap = (unsigned long __user *)data;
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- ret = security_ptrace(current->parent, current);
- if (ret)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
@@ -663,10 +626,7 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
ret = ptrace_request(child, request, addr, data);
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
+ out_tsk:
return ret;
}
diff --git a/arch/i386/kernel/reboot_fixups.c b/arch/i386/kernel/reboot_fixups.c
index c9b87330aeea..10e21a4773dd 100644
--- a/arch/i386/kernel/reboot_fixups.c
+++ b/arch/i386/kernel/reboot_fixups.c
@@ -10,6 +10,7 @@
#include
#include
+#include
static void cs5530a_warm_reset(struct pci_dev *dev)
{
@@ -42,7 +43,7 @@ void mach_reboot_fixups(void)
struct pci_dev *dev;
int i;
- for (i=0; i < (sizeof(fixups_table)/sizeof(fixups_table[0])); i++) {
+ for (i=0; i < ARRAY_SIZE(fixups_table); i++) {
cur = &(fixups_table[i]);
dev = pci_get_device(cur->vendor, cur->device, NULL);
if (!dev)
diff --git a/arch/i386/kernel/scx200.c b/arch/i386/kernel/scx200.c
index 69e203a0d330..9c968ae67c43 100644
--- a/arch/i386/kernel/scx200.c
+++ b/arch/i386/kernel/scx200.c
@@ -12,6 +12,7 @@
#include
#include
+#include
/* Verify that the configuration block really is there */
#define scx200_cb_probe(base) (inw((base) + SCx200_CBA) == (base))
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 01b618e73ecd..47ec76794d02 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -68,11 +68,9 @@ EXPORT_SYMBOL(smp_num_siblings);
/* Package ID of each logical CPU */
int phys_proc_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID};
-EXPORT_SYMBOL(phys_proc_id);
/* Core ID of each logical CPU */
int cpu_core_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID};
-EXPORT_SYMBOL(cpu_core_id);
cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_sibling_map);
@@ -612,7 +610,7 @@ static inline void __inquire_remote_apic(int apicid)
printk("Inquiring remote APIC #%d...\n", apicid);
- for (i = 0; i < sizeof(regs) / sizeof(*regs); i++) {
+ for (i = 0; i < ARRAY_SIZE(regs); i++) {
printk("... APIC #%d %s: ", apicid, names[i]);
/*
diff --git a/arch/i386/oprofile/Kconfig b/arch/i386/oprofile/Kconfig
index 5ade19801b97..d8a84088471a 100644
--- a/arch/i386/oprofile/Kconfig
+++ b/arch/i386/oprofile/Kconfig
@@ -1,7 +1,3 @@
-
-menu "Profiling support"
- depends on EXPERIMENTAL
-
config PROFILING
bool "Profiling support (EXPERIMENTAL)"
help
@@ -19,5 +15,3 @@ config OPROFILE
If unsure, say N.
-endmenu
-
diff --git a/arch/i386/power/cpu.c b/arch/i386/power/cpu.c
index 1f1572692e0b..50a0bef8c85f 100644
--- a/arch/i386/power/cpu.c
+++ b/arch/i386/power/cpu.c
@@ -118,6 +118,7 @@ void __restore_processor_state(struct saved_context *ctxt)
fix_processor_context();
do_fpu_end();
mtrr_ap_init();
+ mcheck_init(&boot_cpu_data);
}
void restore_processor_state(void)
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 3b4248cff9a7..d4de8a4814be 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -191,6 +191,7 @@ config IOSAPIC
config IA64_SGI_SN_XP
tristate "Support communication between SGI SSIs"
+ depends on IA64_GENERIC || IA64_SGI_SN2
select IA64_UNCACHED_ALLOCATOR
help
An SGI machine can be divided into multiple Single System
@@ -426,8 +427,21 @@ config GENERIC_PENDING_IRQ
source "arch/ia64/hp/sim/Kconfig"
+menu "Instrumentation Support"
+ depends on EXPERIMENTAL
+
source "arch/ia64/oprofile/Kconfig"
+config KPROBES
+ bool "Kprobes (EXPERIMENTAL)"
+ help
+ Kprobes allows you to trap at almost any kernel address and
+ execute a callback function. register_kprobe() establishes
+ a probepoint and specifies the callback. Kprobes is useful
+ for kernel debugging, non-intrusive instrumentation and testing.
+ If in doubt, say "N".
+endmenu
+
source "arch/ia64/Kconfig.debug"
source "security/Kconfig"
diff --git a/arch/ia64/Kconfig.debug b/arch/ia64/Kconfig.debug
index fda67ac993d7..de9d507ba0fd 100644
--- a/arch/ia64/Kconfig.debug
+++ b/arch/ia64/Kconfig.debug
@@ -2,17 +2,6 @@ menu "Kernel hacking"
source "lib/Kconfig.debug"
-config KPROBES
- bool "Kprobes"
- depends on DEBUG_KERNEL
- help
- Kprobes allows you to trap at almost any kernel address and
- execute a callback function. register_kprobe() establishes
- a probepoint and specifies the callback. Kprobes is useful
- for kernel debugging, non-intrusive instrumentation and testing.
- If in doubt, say "N".
-
-
choice
prompt "Physical memory granularity"
default IA64_GRANULE_64MB
diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c
index b42ec37be51c..19ee635eeb70 100644
--- a/arch/ia64/hp/sim/simserial.c
+++ b/arch/ia64/hp/sim/simserial.c
@@ -642,10 +642,8 @@ static void rs_close(struct tty_struct *tty, struct file * filp)
info->event = 0;
info->tty = 0;
if (info->blocked_open) {
- if (info->close_delay) {
- current->state = TASK_INTERRUPTIBLE;
- schedule_timeout(info->close_delay);
- }
+ if (info->close_delay)
+ schedule_timeout_interruptible(info->close_delay);
wake_up_interruptible(&info->open_wait);
}
info->flags &= ~(ASYNC_NORMAL_ACTIVE|ASYNC_CLOSING);
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 471086b808a4..96736a119c91 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -26,7 +26,6 @@
#include
#include
#include
-#include
#include
#include
#include
@@ -38,13 +37,8 @@
extern void jprobe_inst_return(void);
-/* kprobe_status settings */
-#define KPROBE_HIT_ACTIVE 0x00000001
-#define KPROBE_HIT_SS 0x00000002
-
-static struct kprobe *current_kprobe, *kprobe_prev;
-static unsigned long kprobe_status, kprobe_status_prev;
-static struct pt_regs jprobe_saved_regs;
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
enum instruction_type {A, I, M, F, B, L, X, u};
static enum instruction_type bundle_encoding[32][3] = {
@@ -313,21 +307,22 @@ static int __kprobes valid_kprobe_addr(int template, int slot,
return 0;
}
-static inline void save_previous_kprobe(void)
+static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
- kprobe_prev = current_kprobe;
- kprobe_status_prev = kprobe_status;
+ kcb->prev_kprobe.kp = kprobe_running();
+ kcb->prev_kprobe.status = kcb->kprobe_status;
}
-static inline void restore_previous_kprobe(void)
+static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
- current_kprobe = kprobe_prev;
- kprobe_status = kprobe_status_prev;
+ __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+ kcb->kprobe_status = kcb->prev_kprobe.status;
}
-static inline void set_current_kprobe(struct kprobe *p)
+static inline void set_current_kprobe(struct kprobe *p,
+ struct kprobe_ctlblk *kcb)
{
- current_kprobe = p;
+ __get_cpu_var(current_kprobe) = p;
}
static void kretprobe_trampoline(void)
@@ -347,10 +342,11 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
struct kretprobe_instance *ri = NULL;
struct hlist_head *head;
struct hlist_node *node, *tmp;
- unsigned long orig_ret_address = 0;
+ unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address =
((struct fnptr *)kretprobe_trampoline)->ip;
+ spin_lock_irqsave(&kretprobe_lock, flags);
head = kretprobe_inst_table_head(current);
/*
@@ -389,17 +385,19 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
regs->cr_iip = orig_ret_address;
- unlock_kprobes();
+ reset_current_kprobe();
+ spin_unlock_irqrestore(&kretprobe_lock, flags);
preempt_enable_no_resched();
- /*
- * By returning a non-zero value, we are telling
- * kprobe_handler() that we have handled unlocking
- * and re-enabling preemption.
- */
+ /*
+ * By returning a non-zero value, we are telling
+ * kprobe_handler() that we don't want the post_handler
+ * to run (and have re-enabled preemption)
+ */
return 1;
}
+/* Called with kretprobe_lock held */
void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
struct pt_regs *regs)
{
@@ -606,17 +604,22 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
int ret = 0;
struct pt_regs *regs = args->regs;
kprobe_opcode_t *addr = (kprobe_opcode_t *)instruction_pointer(regs);
+ struct kprobe_ctlblk *kcb;
+ /*
+ * We don't want to be preempted for the entire
+ * duration of kprobe processing
+ */
preempt_disable();
+ kcb = get_kprobe_ctlblk();
/* Handle recursion cases */
if (kprobe_running()) {
p = get_kprobe(addr);
if (p) {
- if ( (kprobe_status == KPROBE_HIT_SS) &&
+ if ((kcb->kprobe_status == KPROBE_HIT_SS) &&
(p->ainsn.inst_flag == INST_FLAG_BREAK_INST)) {
ia64_psr(regs)->ss = 0;
- unlock_kprobes();
goto no_kprobe;
}
/* We have reentered the pre_kprobe_handler(), since
@@ -625,17 +628,17 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
* just single step on the instruction of the new probe
* without calling any user handlers.
*/
- save_previous_kprobe();
- set_current_kprobe(p);
+ save_previous_kprobe(kcb);
+ set_current_kprobe(p, kcb);
p->nmissed++;
prepare_ss(p, regs);
- kprobe_status = KPROBE_REENTER;
+ kcb->kprobe_status = KPROBE_REENTER;
return 1;
} else if (args->err == __IA64_BREAK_JPROBE) {
/*
* jprobe instrumented function just completed
*/
- p = current_kprobe;
+ p = __get_cpu_var(current_kprobe);
if (p->break_handler && p->break_handler(p, regs)) {
goto ss_probe;
}
@@ -645,10 +648,8 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
}
}
- lock_kprobes();
p = get_kprobe(addr);
if (!p) {
- unlock_kprobes();
if (!is_ia64_break_inst(regs)) {
/*
* The breakpoint instruction was removed right
@@ -665,8 +666,8 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
goto no_kprobe;
}
- kprobe_status = KPROBE_HIT_ACTIVE;
- set_current_kprobe(p);
+ set_current_kprobe(p, kcb);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
if (p->pre_handler && p->pre_handler(p, regs))
/*
@@ -678,7 +679,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
ss_probe:
prepare_ss(p, regs);
- kprobe_status = KPROBE_HIT_SS;
+ kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
no_kprobe:
@@ -688,23 +689,25 @@ no_kprobe:
static int __kprobes post_kprobes_handler(struct pt_regs *regs)
{
- if (!kprobe_running())
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ if (!cur)
return 0;
- if ((kprobe_status != KPROBE_REENTER) && current_kprobe->post_handler) {
- kprobe_status = KPROBE_HIT_SSDONE;
- current_kprobe->post_handler(current_kprobe, regs, 0);
+ if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ cur->post_handler(cur, regs, 0);
}
- resume_execution(current_kprobe, regs);
+ resume_execution(cur, regs);
/*Restore back the original saved kprobes variables and continue. */
- if (kprobe_status == KPROBE_REENTER) {
- restore_previous_kprobe();
+ if (kcb->kprobe_status == KPROBE_REENTER) {
+ restore_previous_kprobe(kcb);
goto out;
}
-
- unlock_kprobes();
+ reset_current_kprobe();
out:
preempt_enable_no_resched();
@@ -713,16 +716,15 @@ out:
static int __kprobes kprobes_fault_handler(struct pt_regs *regs, int trapnr)
{
- if (!kprobe_running())
- return 0;
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- if (current_kprobe->fault_handler &&
- current_kprobe->fault_handler(current_kprobe, regs, trapnr))
+ if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
- if (kprobe_status & KPROBE_HIT_SS) {
- resume_execution(current_kprobe, regs);
- unlock_kprobes();
+ if (kcb->kprobe_status & KPROBE_HIT_SS) {
+ resume_execution(cur, regs);
+ reset_current_kprobe();
preempt_enable_no_resched();
}
@@ -733,31 +735,38 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct die_args *args = (struct die_args *)data;
+ int ret = NOTIFY_DONE;
+
switch(val) {
case DIE_BREAK:
if (pre_kprobes_handler(args))
- return NOTIFY_STOP;
+ ret = NOTIFY_STOP;
break;
case DIE_SS:
if (post_kprobes_handler(args->regs))
- return NOTIFY_STOP;
+ ret = NOTIFY_STOP;
break;
case DIE_PAGE_FAULT:
- if (kprobes_fault_handler(args->regs, args->trapnr))
- return NOTIFY_STOP;
+ /* kprobe_running() needs smp_processor_id() */
+ preempt_disable();
+ if (kprobe_running() &&
+ kprobes_fault_handler(args->regs, args->trapnr))
+ ret = NOTIFY_STOP;
+ preempt_enable();
default:
break;
}
- return NOTIFY_DONE;
+ return ret;
}
int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
struct jprobe *jp = container_of(p, struct jprobe, kp);
unsigned long addr = ((struct fnptr *)(jp->entry))->ip;
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
/* save architectural state */
- jprobe_saved_regs = *regs;
+ kcb->jprobe_saved_regs = *regs;
/* after rfi, execute the jprobe instrumented function */
regs->cr_iip = addr & ~0xFULL;
@@ -775,7 +784,10 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
{
- *regs = jprobe_saved_regs;
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ *regs = kcb->jprobe_saved_regs;
+ preempt_enable_no_resched();
return 1;
}
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index f7dfc107cb7b..410d4804fa6e 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -4940,7 +4940,7 @@ abort_locked:
if (call_made && PFM_CMD_RW_ARG(cmd) && copy_to_user(arg, args_k, base_sz*count)) ret = -EFAULT;
error_args:
- if (args_k) kfree(args_k);
+ kfree(args_k);
DPRINT(("cmd=%s ret=%ld\n", PFM_CMD_NAME(cmd), ret));
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index fc56ca2da358..3af6de36a482 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -92,6 +92,13 @@ extern void efi_initialize_iomem_resources(struct resource *,
extern char _text[], _end[], _etext[];
unsigned long ia64_max_cacheline_size;
+
+int dma_get_cache_alignment(void)
+{
+ return ia64_max_cacheline_size;
+}
+EXPORT_SYMBOL(dma_get_cache_alignment);
+
unsigned long ia64_iobase; /* virtual address for I/O accesses */
EXPORT_SYMBOL(ia64_iobase);
struct io_space io_space[MAX_IO_SPACES];
diff --git a/arch/ia64/oprofile/Kconfig b/arch/ia64/oprofile/Kconfig
index 56e6f614b04a..97271ab484dc 100644
--- a/arch/ia64/oprofile/Kconfig
+++ b/arch/ia64/oprofile/Kconfig
@@ -1,7 +1,3 @@
-
-menu "Profiling support"
- depends on EXPERIMENTAL
-
config PROFILING
bool "Profiling support (EXPERIMENTAL)"
help
@@ -22,5 +18,3 @@ config OPROFILE
If unsure, say N.
-endmenu
-
diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c
index 6df7fb60dfea..e79bbc94216d 100644
--- a/arch/m68k/atari/time.c
+++ b/arch/m68k/atari/time.c
@@ -212,10 +212,8 @@ int atari_tt_hwclk( int op, struct rtc_time *t )
* additionally the RTC_SET bit is set to prevent an update cycle.
*/
- while( RTC_READ(RTC_FREQ_SELECT) & RTC_UIP ) {
- current->state = TASK_INTERRUPTIBLE;
- schedule_timeout(HWCLK_POLL_INTERVAL);
- }
+ while( RTC_READ(RTC_FREQ_SELECT) & RTC_UIP )
+ schedule_timeout_interruptible(HWCLK_POLL_INTERVAL);
local_irq_save(flags);
RTC_WRITE( RTC_CONTROL, ctrl | RTC_SET );
diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c
index f7f1d2e5b90b..7e54422685cf 100644
--- a/arch/m68k/kernel/ptrace.c
+++ b/arch/m68k/kernel/ptrace.c
@@ -121,48 +121,11 @@ void ptrace_disable(struct task_struct *child)
child->thread.work.syscall_trace = 0;
}
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
unsigned long tmp;
int i, ret = 0;
- lock_kernel();
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED) {
- ret = -EPERM;
- goto out;
- }
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- goto out;
- }
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (unlikely(!child)) {
- ret = -ESRCH;
- goto out;
- }
-
- /* you may not mess with init */
- if (unlikely(pid == 1)) {
- ret = -EPERM;
- goto out_tsk;
- }
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret)
- goto out_tsk;
-
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
@@ -317,14 +280,10 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
ret = ptrace_request(child, request, addr, data);
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
+
return ret;
out_eio:
- ret = -EIO;
- goto out_tsk;
+ return -EIO;
}
asmlinkage void syscall_trace(void)
diff --git a/arch/m68knommu/Kconfig b/arch/m68knommu/Kconfig
index 8520df9cee6d..b96498120fe9 100644
--- a/arch/m68knommu/Kconfig
+++ b/arch/m68knommu/Kconfig
@@ -71,6 +71,11 @@ config M5206e
help
Motorola ColdFire 5206e processor support.
+config M520x
+ bool "MCF520x"
+ help
+ Freescale Coldfire 5207/5208 processor support.
+
config M523x
bool "MCF523x"
help
@@ -120,7 +125,7 @@ config M527x
config COLDFIRE
bool
- depends on (M5206 || M5206e || M523x || M5249 || M527x || M5272 || M528x || M5307 || M5407)
+ depends on (M5206 || M5206e || M520x || M523x || M5249 || M527x || M5272 || M528x || M5307 || M5407)
default y
choice
@@ -322,6 +327,12 @@ config ELITE
help
Support for the Motorola M5206eLITE board.
+config M5208EVB
+ bool "Freescale M5208EVB board support"
+ depends on M520x
+ help
+ Support for the Freescale Coldfire M5208EVB.
+
config M5235EVB
bool "Freescale M5235EVB support"
depends on M523x
@@ -465,10 +476,10 @@ config ARNEWSH
default y
depends on (ARN5206 || ARN5307)
-config MOTOROLA
+config FREESCALE
bool
default y
- depends on (M5206eC3 || M5235EVB || M5249C3 || M5271EVB || M5272C3 || M5275EVB || M5282EVB || M5307C3 || M5407C3)
+ depends on (M5206eC3 || M5208EVB || M5235EVB || M5249C3 || M5271EVB || M5272C3 || M5275EVB || M5282EVB || M5307C3 || M5407C3)
config HW_FEITH
bool
diff --git a/arch/m68knommu/Makefile b/arch/m68knommu/Makefile
index b8fdf191b8f6..b6b5c14e55fd 100644
--- a/arch/m68knommu/Makefile
+++ b/arch/m68knommu/Makefile
@@ -14,6 +14,7 @@ platform-$(CONFIG_M68VZ328) := 68VZ328
platform-$(CONFIG_M68360) := 68360
platform-$(CONFIG_M5206) := 5206
platform-$(CONFIG_M5206e) := 5206e
+platform-$(CONFIG_M520x) := 520x
platform-$(CONFIG_M523x) := 523x
platform-$(CONFIG_M5249) := 5249
platform-$(CONFIG_M527x) := 527x
@@ -29,7 +30,7 @@ board-$(CONFIG_UCDIMM) := ucdimm
board-$(CONFIG_UCQUICC) := uCquicc
board-$(CONFIG_DRAGEN2) := de2
board-$(CONFIG_ARNEWSH) := ARNEWSH
-board-$(CONFIG_MOTOROLA) := MOTOROLA
+board-$(CONFIG_FREESCALE) := FREESCALE
board-$(CONFIG_M5235EVB) := M5235EVB
board-$(CONFIG_M5271EVB) := M5271EVB
board-$(CONFIG_M5275EVB) := M5275EVB
@@ -41,6 +42,7 @@ board-$(CONFIG_SECUREEDGEMP3) := MP3
board-$(CONFIG_CLEOPATRA) := CLEOPATRA
board-$(CONFIG_senTec) := senTec
board-$(CONFIG_SNEHA) := SNEHA
+board-$(CONFIG_M5208EVB) := M5208EVB
board-$(CONFIG_MOD5272) := MOD5272
BOARD := $(board-y)
@@ -56,6 +58,7 @@ MODEL := $(model-y)
#
cpuclass-$(CONFIG_M5206) := 5307
cpuclass-$(CONFIG_M5206e) := 5307
+cpuclass-$(CONFIG_M520x) := 5307
cpuclass-$(CONFIG_M523x) := 5307
cpuclass-$(CONFIG_M5249) := 5307
cpuclass-$(CONFIG_M527x) := 5307
@@ -80,6 +83,7 @@ export PLATFORM BOARD MODEL CPUCLASS
#
cflags-$(CONFIG_M5206) := -m5200 -Wa,-S -Wa,-m5200
cflags-$(CONFIG_M5206e) := -m5200 -Wa,-S -Wa,-m5200
+cflags-$(CONFIG_M520x) := -m5307 -Wa,-S -Wa,-m5307
cflags-$(CONFIG_M523x) := -m5307 -Wa,-S -Wa,-m5307
cflags-$(CONFIG_M5249) := -m5200 -Wa,-S -Wa,-m5200
cflags-$(CONFIG_M527x) := -m5307 -Wa,-S -Wa,-m5307
@@ -95,7 +99,6 @@ cflags-$(CONFIG_M68360) := -m68332
AFLAGS += $(cflags-y)
CFLAGS += $(cflags-y)
-CFLAGS += -fno-builtin
CFLAGS += -O1 -g
CFLAGS += -D__linux__
CFLAGS += -DUTS_SYSNAME=\"uClinux\"
diff --git a/arch/m68knommu/kernel/asm-offsets.c b/arch/m68knommu/kernel/asm-offsets.c
index cd3ffe12653e..b988c7bdc6e4 100644
--- a/arch/m68knommu/kernel/asm-offsets.c
+++ b/arch/m68knommu/kernel/asm-offsets.c
@@ -15,6 +15,7 @@
#include
#include
#include
+#include
#include
#define DEFINE(sym, val) \
diff --git a/arch/m68knommu/kernel/ptrace.c b/arch/m68knommu/kernel/ptrace.c
index 621d7b91ccfe..262ab8c72e5f 100644
--- a/arch/m68knommu/kernel/ptrace.c
+++ b/arch/m68knommu/kernel/ptrace.c
@@ -101,43 +101,10 @@ void ptrace_disable(struct task_struct *child)
put_reg(child, PT_SR, tmp);
}
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(truct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
int ret;
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
@@ -357,10 +324,6 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
ret = -EIO;
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
return ret;
}
diff --git a/arch/m68knommu/kernel/setup.c b/arch/m68knommu/kernel/setup.c
index a220345e9746..abb80fa2b940 100644
--- a/arch/m68knommu/kernel/setup.c
+++ b/arch/m68knommu/kernel/setup.c
@@ -107,6 +107,9 @@ void (*mach_power_off)( void ) = NULL;
#if defined(CONFIG_M5206e)
#define CPU "COLDFIRE(m5206e)"
#endif
+#if defined(CONFIG_M520x)
+ #define CPU "COLDFIRE(m520x)"
+#endif
#if defined(CONFIG_M523x)
#define CPU "COLDFIRE(m523x)"
#endif
@@ -132,7 +135,7 @@ void (*mach_power_off)( void ) = NULL;
#define CPU "COLDFIRE(m5407)"
#endif
#ifndef CPU
- #define CPU "UNKOWN"
+ #define CPU "UNKNOWN"
#endif
/* (es) */
diff --git a/arch/m68knommu/kernel/vmlinux.lds.S b/arch/m68knommu/kernel/vmlinux.lds.S
index 47f06787190d..0eab92ca4b97 100644
--- a/arch/m68knommu/kernel/vmlinux.lds.S
+++ b/arch/m68knommu/kernel/vmlinux.lds.S
@@ -124,6 +124,14 @@
#define RAM_LENGTH 0x3e0000
#endif
+/*
+ * The Freescale 5208EVB board has 32MB of RAM.
+ */
+#if defined(CONFIG_M5208EVB)
+#define RAM_START 0x40020000
+#define RAM_LENGTH 0x01e00000
+#endif
+
/*
* The senTec COBRA5272 board has nearly the same memory layout as
* the M5272C3. We assume 16MiB ram.
@@ -275,6 +283,7 @@ SECTIONS {
*(__ksymtab_strings)
/* Built-in module parameters */
+ . = ALIGN(4) ;
__start___param = .;
*(__param)
__stop___param = .;
diff --git a/arch/m68knommu/platform/520x/Makefile b/arch/m68knommu/platform/520x/Makefile
new file mode 100644
index 000000000000..e861b05106bc
--- /dev/null
+++ b/arch/m68knommu/platform/520x/Makefile
@@ -0,0 +1,19 @@
+#
+# Makefile for the M5208 specific file.
+#
+
+#
+# If you want to play with the HW breakpoints then you will
+# need to add define this, which will give you a stack backtrace
+# on the console port whenever a DBG interrupt occurs. You have to
+# set up you HW breakpoints to trigger a DBG interrupt:
+#
+# EXTRA_CFLAGS += -DTRAP_DBG_INTERRUPT
+# EXTRA_AFLAGS += -DTRAP_DBG_INTERRUPT
+#
+
+ifdef CONFIG_FULLDEBUG
+AFLAGS += -DDEBUGGER_COMPATIBLE_CACHE=1
+endif
+
+obj-y := config.o
diff --git a/arch/m68knommu/platform/520x/config.c b/arch/m68knommu/platform/520x/config.c
new file mode 100644
index 000000000000..71dea2e0f452
--- /dev/null
+++ b/arch/m68knommu/platform/520x/config.c
@@ -0,0 +1,65 @@
+/***************************************************************************/
+
+/*
+ * linux/arch/m68knommu/platform/520x/config.c
+ *
+ * Copyright (C) 2005, Freescale (www.freescale.com)
+ * Copyright (C) 2005, Intec Automation (mike@steroidmicros.com)
+ * Copyright (C) 1999-2003, Greg Ungerer (gerg@snapgear.com)
+ * Copyright (C) 2001-2003, SnapGear Inc. (www.snapgear.com)
+ */
+
+/***************************************************************************/
+
+#include
+#include
+#include
+#include
+#include
+
+/***************************************************************************/
+
+/*
+ * DMA channel base address table.
+ */
+unsigned int dma_base_addr[MAX_M68K_DMA_CHANNELS];
+unsigned int dma_device_address[MAX_M68K_DMA_CHANNELS];
+
+/***************************************************************************/
+
+void coldfire_pit_tick(void);
+void coldfire_pit_init(irqreturn_t (*handler)(int, void *, struct pt_regs *));
+unsigned long coldfire_pit_offset(void);
+void coldfire_trap_init(void);
+void coldfire_reset(void);
+
+/***************************************************************************/
+
+/*
+ * Program the vector to be an auto-vectored.
+ */
+
+void mcf_autovector(unsigned int vec)
+{
+ /* Everything is auto-vectored on the 520x devices */
+}
+
+/***************************************************************************/
+
+void config_BSP(char *commandp, int size)
+{
+#ifdef CONFIG_BOOTPARAM
+ strncpy(commandp, CONFIG_BOOTPARAM_STRING, size);
+ commandp[size-1] = 0;
+#else
+ memset(commandp, 0, size);
+#endif
+
+ mach_sched_init = coldfire_pit_init;
+ mach_tick = coldfire_pit_tick;
+ mach_gettimeoffset = coldfire_pit_offset;
+ mach_trap_init = coldfire_trap_init;
+ mach_reset = coldfire_reset;
+}
+
+/***************************************************************************/
diff --git a/arch/m68knommu/platform/5307/Makefile b/arch/m68knommu/platform/5307/Makefile
index 6fe5a2b8fb08..8d1619dc1ea6 100644
--- a/arch/m68knommu/platform/5307/Makefile
+++ b/arch/m68knommu/platform/5307/Makefile
@@ -19,6 +19,7 @@ endif
obj-$(CONFIG_COLDFIRE) += entry.o vectors.o ints.o
obj-$(CONFIG_M5206) += timers.o
obj-$(CONFIG_M5206e) += timers.o
+obj-$(CONFIG_M520x) += pit.o
obj-$(CONFIG_M523x) += pit.o
obj-$(CONFIG_M5249) += timers.o
obj-$(CONFIG_M527x) += pit.o
diff --git a/arch/m68knommu/platform/5307/head.S b/arch/m68knommu/platform/5307/head.S
index 7f4ba837901f..c30c462b99b1 100644
--- a/arch/m68knommu/platform/5307/head.S
+++ b/arch/m68knommu/platform/5307/head.S
@@ -113,6 +113,9 @@
#define MEM_BASE 0x02000000
#define VBR_BASE 0x20000000 /* vectors in SRAM */
#endif
+#if defined(CONFIG_M5208EVB)
+#define MEM_BASE 0x40000000
+#endif
#ifndef MEM_BASE
#define MEM_BASE 0x00000000 /* memory base at address 0 */
diff --git a/arch/m68knommu/platform/5307/ints.c b/arch/m68knommu/platform/5307/ints.c
index 0117754d44f3..a134fb2f0566 100644
--- a/arch/m68knommu/platform/5307/ints.c
+++ b/arch/m68knommu/platform/5307/ints.c
@@ -26,6 +26,7 @@
#include
#include
+#include
#include
#include
#include
diff --git a/arch/m68knommu/platform/5307/pit.c b/arch/m68knommu/platform/5307/pit.c
index a9b2c2e7e280..323f2677e49d 100644
--- a/arch/m68knommu/platform/5307/pit.c
+++ b/arch/m68knommu/platform/5307/pit.c
@@ -3,7 +3,7 @@
/*
* pit.c -- Motorola ColdFire PIT timer. Currently this type of
* hardware timer only exists in the Motorola ColdFire
- * 5270/5271 and 5282 CPUs.
+ * 5270/5271, 5282 and other CPUs.
*
* Copyright (C) 1999-2004, Greg Ungerer (gerg@snapgear.com)
* Copyright (C) 2001-2004, SnapGear Inc. (www.snapgear.com)
@@ -47,10 +47,10 @@ void coldfire_pit_init(irqreturn_t (*handler)(int, void *, struct pt_regs *))
icrp = (volatile unsigned char *) (MCF_IPSBAR + MCFICM_INTC0 +
MCFINTC_ICR0 + MCFINT_PIT1);
- *icrp = 0x2b; /* PIT1 with level 5, priority 3 */
+ *icrp = ICR_INTRCONF;
- imrp = (volatile unsigned long *) (MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH);
- *imrp &= ~(1 << (MCFINT_PIT1 - 32));
+ imrp = (volatile unsigned long *) (MCF_IPSBAR + MCFICM_INTC0 + MCFPIT_IMR);
+ *imrp &= ~MCFPIT_IMR_IBIT;
/* Set up PIT timer 1 as poll clock */
tp = (volatile struct mcfpit *) (MCF_IPSBAR + MCFPIT_BASE1);
@@ -70,7 +70,7 @@ unsigned long coldfire_pit_offset(void)
unsigned long pmr, pcntr, offset;
tp = (volatile struct mcfpit *) (MCF_IPSBAR + MCFPIT_BASE1);
- ipr = (volatile unsigned long *) (MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IPRH);
+ ipr = (volatile unsigned long *) (MCF_IPSBAR + MCFICM_INTC0 + MCFPIT_IMR);
pmr = *(&tp->pmr);
pcntr = *(&tp->pcntr);
@@ -80,7 +80,7 @@ unsigned long coldfire_pit_offset(void)
* timer interupt is pending, then add on a ticks worth of time.
*/
offset = ((pmr - pcntr) * (1000000 / HZ)) / pmr;
- if ((offset < (1000000 / HZ / 2)) && (*ipr & (1 << (MCFINT_PIT1 - 32))))
+ if ((offset < (1000000 / HZ / 2)) && (*ipr & MCFPIT_IMR_IBIT))
offset += 1000000 / HZ;
return offset;
}
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 0097a0d53b3b..e380a8322a94 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -958,7 +958,7 @@ config SOC_PNX8550
bool
select DMA_NONCOHERENT
select HW_HAS_PCI
- select SYS_HAS_CPU_R4X00
+ select SYS_HAS_CPU_MIPS32_R1
select SYS_SUPPORTS_32BIT_KERNEL
config SWAP_IO_SPACE
diff --git a/arch/mips/boot/.gitignore b/arch/mips/boot/.gitignore
new file mode 100644
index 000000000000..ba63401c6e10
--- /dev/null
+++ b/arch/mips/boot/.gitignore
@@ -0,0 +1,4 @@
+mkboot
+elf2ecoff
+zImage
+zImage.tmp
diff --git a/arch/mips/configs/pnx8550-jbs_defconfig b/arch/mips/configs/pnx8550-jbs_defconfig
index 95f84d711912..555837e4c06f 100644
--- a/arch/mips/configs/pnx8550-jbs_defconfig
+++ b/arch/mips/configs/pnx8550-jbs_defconfig
@@ -129,7 +129,7 @@ CONFIG_MIPS_L1_CACHE_SHIFT=5
#
# CPU selection
#
-# CONFIG_CPU_MIPS32_R1 is not set
+CONFIG_CPU_MIPS32_R1=y
# CONFIG_CPU_MIPS32_R2 is not set
# CONFIG_CPU_MIPS64_R1 is not set
# CONFIG_CPU_MIPS64_R2 is not set
@@ -137,7 +137,7 @@ CONFIG_MIPS_L1_CACHE_SHIFT=5
# CONFIG_CPU_TX39XX is not set
# CONFIG_CPU_VR41XX is not set
# CONFIG_CPU_R4300 is not set
-CONFIG_CPU_R4X00=y
+# CONFIG_CPU_R4X00 is not set
# CONFIG_CPU_TX49XX is not set
# CONFIG_CPU_R5000 is not set
# CONFIG_CPU_R5432 is not set
@@ -148,10 +148,11 @@ CONFIG_CPU_R4X00=y
# CONFIG_CPU_RM7000 is not set
# CONFIG_CPU_RM9000 is not set
# CONFIG_CPU_SB1 is not set
-CONFIG_SYS_HAS_CPU_R4X00=y
+CONFIG_SYS_HAS_CPU_MIPS32_R1=y
+CONFIG_CPU_MIPS32=y
+CONFIG_CPU_MIPSR1=y
CONFIG_SYS_SUPPORTS_32BIT_KERNEL=y
CONFIG_CPU_SUPPORTS_32BIT_KERNEL=y
-CONFIG_CPU_SUPPORTS_64BIT_KERNEL=y
#
# Kernel type
@@ -162,11 +163,11 @@ CONFIG_PAGE_SIZE_4KB=y
# CONFIG_PAGE_SIZE_8KB is not set
# CONFIG_PAGE_SIZE_16KB is not set
# CONFIG_PAGE_SIZE_64KB is not set
+CONFIG_CPU_HAS_PREFETCH=y
# CONFIG_MIPS_MT is not set
# CONFIG_64BIT_PHYS_ADDR is not set
# CONFIG_CPU_ADVANCED is not set
CONFIG_CPU_HAS_LLSC=y
-CONFIG_CPU_HAS_LLDSCD=y
CONFIG_CPU_HAS_SYNC=y
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
diff --git a/arch/mips/configs/pnx8550-v2pci_defconfig b/arch/mips/configs/pnx8550-v2pci_defconfig
index deb24c29ac0a..05e65206a7b4 100644
--- a/arch/mips/configs/pnx8550-v2pci_defconfig
+++ b/arch/mips/configs/pnx8550-v2pci_defconfig
@@ -128,7 +128,7 @@ CONFIG_MIPS_L1_CACHE_SHIFT=5
#
# CPU selection
#
-# CONFIG_CPU_MIPS32_R1 is not set
+CONFIG_CPU_MIPS32_R1=y
# CONFIG_CPU_MIPS32_R2 is not set
# CONFIG_CPU_MIPS64_R1 is not set
# CONFIG_CPU_MIPS64_R2 is not set
@@ -136,7 +136,7 @@ CONFIG_MIPS_L1_CACHE_SHIFT=5
# CONFIG_CPU_TX39XX is not set
# CONFIG_CPU_VR41XX is not set
# CONFIG_CPU_R4300 is not set
-CONFIG_CPU_R4X00=y
+# CONFIG_CPU_R4X00 is not set
# CONFIG_CPU_TX49XX is not set
# CONFIG_CPU_R5000 is not set
# CONFIG_CPU_R5432 is not set
@@ -147,10 +147,11 @@ CONFIG_CPU_R4X00=y
# CONFIG_CPU_RM7000 is not set
# CONFIG_CPU_RM9000 is not set
# CONFIG_CPU_SB1 is not set
-CONFIG_SYS_HAS_CPU_R4X00=y
+CONFIG_SYS_HAS_CPU_MIPS32_R1=y
+CONFIG_CPU_MIPS32=y
+CONFIG_CPU_MIPSR1=y
CONFIG_SYS_SUPPORTS_32BIT_KERNEL=y
CONFIG_CPU_SUPPORTS_32BIT_KERNEL=y
-CONFIG_CPU_SUPPORTS_64BIT_KERNEL=y
#
# Kernel type
@@ -161,6 +162,7 @@ CONFIG_PAGE_SIZE_4KB=y
# CONFIG_PAGE_SIZE_8KB is not set
# CONFIG_PAGE_SIZE_16KB is not set
# CONFIG_PAGE_SIZE_64KB is not set
+CONFIG_CPU_HAS_PREFETCH=y
# CONFIG_MIPS_MT is not set
# CONFIG_64BIT_PHYS_ADDR is not set
CONFIG_CPU_ADVANCED=y
diff --git a/arch/mips/ddb5xxx/common/rtc_ds1386.c b/arch/mips/ddb5xxx/common/rtc_ds1386.c
index f5b11508ff2f..995896ac0e39 100644
--- a/arch/mips/ddb5xxx/common/rtc_ds1386.c
+++ b/arch/mips/ddb5xxx/common/rtc_ds1386.c
@@ -41,7 +41,9 @@ rtc_ds1386_get_time(void)
u8 byte;
u8 temp;
unsigned int year, month, day, hour, minute, second;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
/* let us freeze external registers */
byte = READ_RTC(0xB);
byte &= 0x3f;
@@ -60,6 +62,7 @@ rtc_ds1386_get_time(void)
/* enable time transfer */
byte |= 0x80;
WRITE_RTC(0xB, byte);
+ spin_unlock_irqrestore(&rtc_lock, flags);
/* calc hour */
if (temp & 0x40) {
@@ -81,7 +84,9 @@ rtc_ds1386_set_time(unsigned long t)
u8 byte;
u8 temp;
u8 year, month, day, hour, minute, second;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
/* let us freeze external registers */
byte = READ_RTC(0xB);
byte &= 0x3f;
@@ -133,6 +138,7 @@ rtc_ds1386_set_time(unsigned long t)
if (second != READ_RTC(0x1)) {
WRITE_RTC(0x1, second);
}
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
diff --git a/arch/mips/dec/time.c b/arch/mips/dec/time.c
index dc7091caa7aa..174822344131 100644
--- a/arch/mips/dec/time.c
+++ b/arch/mips/dec/time.c
@@ -37,10 +37,25 @@
#include
+/*
+ * Returns true if a clock update is in progress
+ */
+static inline unsigned char dec_rtc_is_updating(void)
+{
+ unsigned char uip;
+ unsigned long flags;
+
+ spin_lock_irqsave(&rtc_lock, flags);
+ uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP);
+ spin_unlock_irqrestore(&rtc_lock, flags);
+ return uip;
+}
+
static unsigned long dec_rtc_get_time(void)
{
unsigned int year, mon, day, hour, min, sec, real_year;
int i;
+ unsigned long flags;
/* The Linux interpretation of the DS1287 clock register contents:
* When the Update-In-Progress (UIP) flag goes from 1 to 0, the
@@ -49,11 +64,12 @@ static unsigned long dec_rtc_get_time(void)
*/
/* read RTC exactly on falling edge of update flag */
for (i = 0; i < 1000000; i++) /* may take up to 1 second... */
- if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)
+ if (dec_rtc_is_updating())
break;
for (i = 0; i < 1000000; i++) /* must try at least 2.228 ms */
- if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP))
+ if (!dec_rtc_is_updating())
break;
+ spin_lock_irqsave(&rtc_lock, flags);
/* Isn't this overkill? UIP above should guarantee consistency */
do {
sec = CMOS_READ(RTC_SECONDS);
@@ -77,6 +93,7 @@ static unsigned long dec_rtc_get_time(void)
* of unused BBU RAM locations.
*/
real_year = CMOS_READ(RTC_DEC_YEAR);
+ spin_unlock_irqrestore(&rtc_lock, flags);
year += real_year - 72 + 2000;
return mktime(year, mon, day, hour, min, sec);
@@ -95,6 +112,8 @@ static int dec_rtc_set_mmss(unsigned long nowtime)
int real_seconds, real_minutes, cmos_minutes;
unsigned char save_control, save_freq_select;
+ /* irq are locally disabled here */
+ spin_lock(&rtc_lock);
/* tell the clock it's being set */
save_control = CMOS_READ(RTC_CONTROL);
CMOS_WRITE((save_control | RTC_SET), RTC_CONTROL);
@@ -141,6 +160,7 @@ static int dec_rtc_set_mmss(unsigned long nowtime)
*/
CMOS_WRITE(save_control, RTC_CONTROL);
CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
+ spin_unlock(&rtc_lock);
return retval;
}
diff --git a/arch/mips/jmr3927/common/rtc_ds1742.c b/arch/mips/jmr3927/common/rtc_ds1742.c
index 1ae4318e1358..8b407d7dc460 100644
--- a/arch/mips/jmr3927/common/rtc_ds1742.c
+++ b/arch/mips/jmr3927/common/rtc_ds1742.c
@@ -57,7 +57,9 @@ rtc_ds1742_get_time(void)
{
unsigned int year, month, day, hour, minute, second;
unsigned int century;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(RTC_READ, RTC_CONTROL);
second = BCD2BIN(CMOS_READ(RTC_SECONDS) & RTC_SECONDS_MASK);
minute = BCD2BIN(CMOS_READ(RTC_MINUTES));
@@ -67,6 +69,7 @@ rtc_ds1742_get_time(void)
year = BCD2BIN(CMOS_READ(RTC_YEAR));
century = BCD2BIN(CMOS_READ(RTC_CENTURY) & RTC_CENTURY_MASK);
CMOS_WRITE(0, RTC_CONTROL);
+ spin_unlock_irqrestore(&rtc_lock, flags);
year += century * 100;
@@ -81,7 +84,9 @@ rtc_ds1742_set_time(unsigned long t)
u8 year, month, day, hour, minute, second;
u8 cmos_year, cmos_month, cmos_day, cmos_hour, cmos_minute, cmos_second;
int cmos_century;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(RTC_READ, RTC_CONTROL);
cmos_second = (u8)(CMOS_READ(RTC_SECONDS) & RTC_SECONDS_MASK);
cmos_minute = (u8)CMOS_READ(RTC_MINUTES);
@@ -139,6 +144,7 @@ rtc_ds1742_set_time(unsigned long t)
/* RTC_CENTURY and RTC_CONTROL share same address... */
CMOS_WRITE(cmos_century, RTC_CONTROL);
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
diff --git a/arch/mips/kernel/irixsig.c b/arch/mips/kernel/irixsig.c
index 908e63684208..dd118c60bcd0 100644
--- a/arch/mips/kernel/irixsig.c
+++ b/arch/mips/kernel/irixsig.c
@@ -502,8 +502,7 @@ asmlinkage int irix_sigpoll_sys(unsigned long __user *set,
while(1) {
long tmp = 0;
- current->state = TASK_INTERRUPTIBLE;
- expire = schedule_timeout(expire);
+ expire = schedule_timeout_interruptible(expire);
for (i=0; i<=4; i++)
tmp |= (current->pending.signal.sig[i] & kset.sig[i]);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index f1b0f3e1f95b..510da5fda567 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -174,51 +174,10 @@ int ptrace_setfpregs (struct task_struct *child, __u32 __user *data)
return 0;
}
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
int ret;
-#if 0
- printk("ptrace(r=%d,pid=%d,addr=%08lx,data=%08lx)\n",
- (int) request, (int) pid, (unsigned long) addr,
- (unsigned long) data);
-#endif
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- if ((ret = security_ptrace(current->parent, current)))
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
@@ -319,7 +278,7 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
if (!cpu_has_dsp) {
tmp = 0;
ret = -EIO;
- goto out_tsk;
+ goto out;
}
if (child->thread.dsp.used_dsp) {
dregs = __get_dsp_regs(child);
@@ -333,14 +292,14 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
if (!cpu_has_dsp) {
tmp = 0;
ret = -EIO;
- goto out_tsk;
+ goto out;
}
tmp = child->thread.dsp.dspcontrol;
break;
default:
tmp = 0;
ret = -EIO;
- goto out_tsk;
+ goto out;
}
ret = put_user(tmp, (unsigned long __user *) data);
break;
@@ -495,11 +454,7 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
ret = ptrace_request(child, request, addr, data);
break;
}
-
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
+ out:
return ret;
}
diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index 8c81f3cb4e2d..1d855112bac2 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -20,42 +20,42 @@
#include
#include
#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
#include
#include
#include
#include
-#include
-#include
+#include
#include
#include
-#include
#include
+#include
-#define RTLX_MAJOR 64
#define RTLX_TARG_VPE 1
-struct rtlx_info *rtlx;
+static struct rtlx_info *rtlx;
static int major;
static char module_name[] = "rtlx";
-static inline int spacefree(int read, int write, int size);
+static struct irqaction irq;
+static int irq_num;
+
+static inline int spacefree(int read, int write, int size)
+{
+ if (read == write) {
+ /*
+ * never fill the buffer completely, so indexes are always
+ * equal if empty and only empty, or !equal if data available
+ */
+ return size - 1;
+ }
+
+ return ((read + size - write) % size) - 1;
+}
static struct chan_waitqueues {
wait_queue_head_t rt_queue;
wait_queue_head_t lx_queue;
} channel_wqs[RTLX_CHANNELS];
-static struct irqaction irq;
-static int irq_num;
-
extern void *vpe_get_shared(int index);
static void rtlx_dispatch(struct pt_regs *regs)
@@ -63,9 +63,8 @@ static void rtlx_dispatch(struct pt_regs *regs)
do_IRQ(MIPSCPU_INT_BASE + MIPS_CPU_RTLX_IRQ, regs);
}
-irqreturn_t rtlx_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t rtlx_interrupt(int irq, void *dev_id, struct pt_regs *regs)
{
- irqreturn_t r = IRQ_HANDLED;
int i;
for (i = 0; i < RTLX_CHANNELS; i++) {
@@ -75,30 +74,7 @@ irqreturn_t rtlx_interrupt(int irq, void *dev_id, struct pt_regs *regs)
wake_up_interruptible(&channel_wqs[i].lx_queue);
}
- return r;
-}
-
-void dump_rtlx(void)
-{
- int i;
-
- printk("id 0x%lx state %d\n", rtlx->id, rtlx->state);
-
- for (i = 0; i < RTLX_CHANNELS; i++) {
- struct rtlx_channel *chan = &rtlx->channel[i];
-
- printk(" rt_state %d lx_state %d buffer_size %d\n",
- chan->rt_state, chan->lx_state, chan->buffer_size);
-
- printk(" rt_read %d rt_write %d\n",
- chan->rt_read, chan->rt_write);
-
- printk(" lx_read %d lx_write %d\n",
- chan->lx_read, chan->lx_write);
-
- printk(" rt_buffer <%s>\n", chan->rt_buffer);
- printk(" lx_buffer <%s>\n", chan->lx_buffer);
- }
+ return IRQ_HANDLED;
}
/* call when we have the address of the shared structure from the SP side. */
@@ -108,7 +84,7 @@ static int rtlx_init(struct rtlx_info *rtlxi)
if (rtlxi->id != RTLX_ID) {
printk(KERN_WARNING "no valid RTLX id at 0x%p\n", rtlxi);
- return (-ENOEXEC);
+ return -ENOEXEC;
}
/* initialise the wait queues */
@@ -120,9 +96,8 @@ static int rtlx_init(struct rtlx_info *rtlxi)
/* set up for interrupt handling */
memset(&irq, 0, sizeof(struct irqaction));
- if (cpu_has_vint) {
+ if (cpu_has_vint)
set_vi_handler(MIPS_CPU_RTLX_IRQ, rtlx_dispatch);
- }
irq_num = MIPSCPU_INT_BASE + MIPS_CPU_RTLX_IRQ;
irq.handler = rtlx_interrupt;
@@ -132,7 +107,8 @@ static int rtlx_init(struct rtlx_info *rtlxi)
setup_irq(irq_num, &irq);
rtlx = rtlxi;
- return (0);
+
+ return 0;
}
/* only allow one open process at a time to open each channel */
@@ -147,36 +123,36 @@ static int rtlx_open(struct inode *inode, struct file *filp)
if (rtlx == NULL) {
struct rtlx_info **p;
if( (p = vpe_get_shared(RTLX_TARG_VPE)) == NULL) {
- printk(" vpe_get_shared is NULL. Has an SP program been loaded?\n");
- return (-EFAULT);
+ printk(KERN_ERR "vpe_get_shared is NULL. "
+ "Has an SP program been loaded?\n");
+ return -EFAULT;
}
if (*p == NULL) {
- printk(" vpe_shared %p %p\n", p, *p);
- return (-EFAULT);
+ printk(KERN_ERR "vpe_shared %p %p\n", p, *p);
+ return -EFAULT;
}
if ((ret = rtlx_init(*p)) < 0)
- return (ret);
+ return ret;
}
chan = &rtlx->channel[minor];
- /* already open? */
- if (chan->lx_state == RTLX_STATE_OPENED)
- return (-EBUSY);
+ if (test_and_set_bit(RTLX_STATE_OPENED, &chan->lx_state))
+ return -EBUSY;
- chan->lx_state = RTLX_STATE_OPENED;
- return (0);
+ return 0;
}
static int rtlx_release(struct inode *inode, struct file *filp)
{
- int minor;
+ int minor = MINOR(inode->i_rdev);
- minor = MINOR(inode->i_rdev);
- rtlx->channel[minor].lx_state = RTLX_STATE_UNUSED;
- return (0);
+ clear_bit(RTLX_STATE_OPENED, &rtlx->channel[minor].lx_state);
+ smp_mb__after_clear_bit();
+
+ return 0;
}
static unsigned int rtlx_poll(struct file *file, poll_table * wait)
@@ -199,12 +175,13 @@ static unsigned int rtlx_poll(struct file *file, poll_table * wait)
if (spacefree(chan->rt_read, chan->rt_write, chan->buffer_size))
mask |= POLLOUT | POLLWRNORM;
- return (mask);
+ return mask;
}
static ssize_t rtlx_read(struct file *file, char __user * buffer, size_t count,
loff_t * ppos)
{
+ unsigned long failed;
size_t fl = 0L;
int minor;
struct rtlx_channel *lx;
@@ -216,7 +193,7 @@ static ssize_t rtlx_read(struct file *file, char __user * buffer, size_t count,
/* data available? */
if (lx->lx_write == lx->lx_read) {
if (file->f_flags & O_NONBLOCK)
- return (0); // -EAGAIN makes cat whinge
+ return 0; /* -EAGAIN makes cat whinge */
/* go to sleep */
add_wait_queue(&channel_wqs[minor].lx_queue, &wait);
@@ -232,39 +209,39 @@ static ssize_t rtlx_read(struct file *file, char __user * buffer, size_t count,
}
/* find out how much in total */
- count = min( count,
- (size_t)(lx->lx_write + lx->buffer_size - lx->lx_read) % lx->buffer_size);
+ count = min(count,
+ (size_t)(lx->lx_write + lx->buffer_size - lx->lx_read) % lx->buffer_size);
/* then how much from the read pointer onwards */
- fl = min( count, (size_t)lx->buffer_size - lx->lx_read);
+ fl = min(count, (size_t)lx->buffer_size - lx->lx_read);
- copy_to_user (buffer, &lx->lx_buffer[lx->lx_read], fl);
+ failed = copy_to_user (buffer, &lx->lx_buffer[lx->lx_read], fl);
+ if (failed) {
+ count = fl - failed;
+ goto out;
+ }
/* and if there is anything left at the beginning of the buffer */
- if ( count - fl )
- copy_to_user (buffer + fl, lx->lx_buffer, count - fl);
+ if (count - fl) {
+ failed = copy_to_user (buffer + fl, lx->lx_buffer, count - fl);
+ if (failed) {
+ count -= failed;
+ goto out;
+ }
+ }
+out:
/* update the index */
lx->lx_read += count;
lx->lx_read %= lx->buffer_size;
- return (count);
-}
-
-static inline int spacefree(int read, int write, int size)
-{
- if (read == write) {
- /* never fill the buffer completely, so indexes are always equal if empty
- and only empty, or !equal if data available */
- return (size - 1);
- }
-
- return ((read + size - write) % size) - 1;
+ return count;
}
static ssize_t rtlx_write(struct file *file, const char __user * buffer,
size_t count, loff_t * ppos)
{
+ unsigned long failed;
int minor;
struct rtlx_channel *rt;
size_t fl;
@@ -277,7 +254,7 @@ static ssize_t rtlx_write(struct file *file, const char __user * buffer,
if (!spacefree(rt->rt_read, rt->rt_write, rt->buffer_size)) {
if (file->f_flags & O_NONBLOCK)
- return (-EAGAIN);
+ return -EAGAIN;
add_wait_queue(&channel_wqs[minor].rt_queue, &wait);
set_current_state(TASK_INTERRUPTIBLE);
@@ -290,52 +267,64 @@ static ssize_t rtlx_write(struct file *file, const char __user * buffer,
}
/* total number of bytes to copy */
- count = min( count, (size_t)spacefree(rt->rt_read, rt->rt_write, rt->buffer_size) );
+ count = min(count, (size_t)spacefree(rt->rt_read, rt->rt_write, rt->buffer_size) );
/* first bit from write pointer to the end of the buffer, or count */
fl = min(count, (size_t) rt->buffer_size - rt->rt_write);
- copy_from_user(&rt->rt_buffer[rt->rt_write], buffer, fl);
+ failed = copy_from_user(&rt->rt_buffer[rt->rt_write], buffer, fl);
+ if (failed) {
+ count = fl - failed;
+ goto out;
+ }
/* if there's any left copy to the beginning of the buffer */
- if( count - fl )
- copy_from_user(rt->rt_buffer, buffer + fl, count - fl);
+ if (count - fl) {
+ failed = copy_from_user(rt->rt_buffer, buffer + fl, count - fl);
+ if (failed) {
+ count -= failed;
+ goto out;
+ }
+ }
+out:
rt->rt_write += count;
rt->rt_write %= rt->buffer_size;
- return(count);
+ return count;
}
static struct file_operations rtlx_fops = {
- .owner = THIS_MODULE,
- .open = rtlx_open,
- .release = rtlx_release,
- .write = rtlx_write,
- .read = rtlx_read,
- .poll = rtlx_poll
+ .owner = THIS_MODULE,
+ .open = rtlx_open,
+ .release = rtlx_release,
+ .write = rtlx_write,
+ .read = rtlx_read,
+ .poll = rtlx_poll
};
-static int rtlx_module_init(void)
+static char register_chrdev_failed[] __initdata =
+ KERN_ERR "rtlx_module_init: unable to register device\n";
+
+static int __init rtlx_module_init(void)
{
- if ((major = register_chrdev(RTLX_MAJOR, module_name, &rtlx_fops)) < 0) {
- printk("rtlx_module_init: unable to register device\n");
- return (-EBUSY);
+ major = register_chrdev(0, module_name, &rtlx_fops);
+ if (major < 0) {
+ printk(register_chrdev_failed);
+ return major;
}
- if (major == 0)
- major = RTLX_MAJOR;
-
- return (0);
+ return 0;
}
-static void rtlx_module_exit(void)
+static void __exit rtlx_module_exit(void)
{
unregister_chrdev(major, module_name);
}
module_init(rtlx_module_init);
module_exit(rtlx_module_exit);
+
MODULE_DESCRIPTION("MIPS RTLX");
-MODULE_AUTHOR("Elizabeth Clarke, MIPS Technologies, Inc");
+MODULE_AUTHOR("Elizabeth Clarke, MIPS Technologies, Inc.");
MODULE_LICENSE("GPL");
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 9202a17db8f7..05e09eedabff 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -384,9 +384,6 @@ give_sigsegv:
return 0;
}
-extern void setup_rt_frame_n32(struct k_sigaction * ka,
- struct pt_regs *regs, int signr, sigset_t *set, siginfo_t *info);
-
static inline int handle_signal(unsigned long sig, siginfo_t *info,
struct k_sigaction *ka, sigset_t *oldset, struct pt_regs *regs)
{
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index dbe821303125..e315d3f6aa6e 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -647,8 +647,8 @@ static inline void *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
return (void *)((sp - frame_size) & ALMASK);
}
-void setup_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
- int signr, sigset_t *set)
+int setup_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
+ int signr, sigset_t *set)
{
struct sigframe *frame;
int err = 0;
@@ -694,13 +694,15 @@ void setup_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
current->comm, current->pid,
frame, regs->cp0_epc, frame->sf_code);
#endif
- return;
+ return 1;
give_sigsegv:
force_sigsegv(signr, current);
+ return 0;
}
-void setup_rt_frame_32(struct k_sigaction * ka, struct pt_regs *regs, int signr, sigset_t *set, siginfo_t *info)
+int setup_rt_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
+ int signr, sigset_t *set, siginfo_t *info)
{
struct rt_sigframe32 *frame;
int err = 0;
@@ -763,10 +765,11 @@ void setup_rt_frame_32(struct k_sigaction * ka, struct pt_regs *regs, int signr,
current->comm, current->pid,
frame, regs->cp0_epc, frame->rs_code);
#endif
- return;
+ return 1;
give_sigsegv:
force_sigsegv(signr, current);
+ return 0;
}
static inline int handle_signal(unsigned long sig, siginfo_t *info,
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index 97fefcc9dbe7..06be405be399 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -58,10 +58,6 @@
typedef void *vpe_handle;
-// defined here because the kernel module loader doesn't have
-// anything to do with it.
-#define SHN_MIPS_SCOMMON 0xff03
-
#ifndef ARCH_SHF_SMALL
#define ARCH_SHF_SMALL 0
#endif
@@ -69,11 +65,8 @@ typedef void *vpe_handle;
/* If this is set, the section belongs in the init part of the module */
#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1))
-// temp number,
-#define VPE_MAJOR 63
-
static char module_name[] = "vpe";
-static int major = 0;
+static int major;
/* grab the likely amount of memory we will need. */
#ifdef CONFIG_MIPS_VPE_LOADER_TOM
@@ -98,22 +91,7 @@ enum tc_state {
TC_STATE_DYNAMIC
};
-struct vpe;
-typedef struct tc {
- enum tc_state state;
- int index;
-
- /* parent VPE */
- struct vpe *pvpe;
-
- /* The list of TC's with this VPE */
- struct list_head tc;
-
- /* The global list of tc's */
- struct list_head list;
-} tc_t;
-
-typedef struct vpe {
+struct vpe {
enum vpe_state state;
/* (device) minor associated with this vpe */
@@ -135,7 +113,21 @@ typedef struct vpe {
/* shared symbol address */
void *shared_ptr;
-} vpe_t;
+};
+
+struct tc {
+ enum tc_state state;
+ int index;
+
+ /* parent VPE */
+ struct vpe *pvpe;
+
+ /* The list of TC's with this VPE */
+ struct list_head tc;
+
+ /* The global list of tc's */
+ struct list_head list;
+};
struct vpecontrol_ {
/* Virtual processing elements */
@@ -146,7 +138,7 @@ struct vpecontrol_ {
} vpecontrol;
static void release_progmem(void *ptr);
-static void dump_vpe(vpe_t * v);
+static void dump_vpe(struct vpe * v);
extern void save_gp_address(unsigned int secbase, unsigned int rel);
/* get the vpe associated with this minor */
@@ -197,13 +189,11 @@ struct vpe *alloc_vpe(int minor)
{
struct vpe *v;
- if ((v = kmalloc(sizeof(struct vpe), GFP_KERNEL)) == NULL) {
+ if ((v = kzalloc(sizeof(struct vpe), GFP_KERNEL)) == NULL) {
printk(KERN_WARNING "VPE: alloc_vpe no mem\n");
return NULL;
}
- memset(v, 0, sizeof(struct vpe));
-
INIT_LIST_HEAD(&v->tc);
list_add_tail(&v->list, &vpecontrol.vpe_list);
@@ -216,13 +206,11 @@ struct tc *alloc_tc(int index)
{
struct tc *t;
- if ((t = kmalloc(sizeof(struct tc), GFP_KERNEL)) == NULL) {
+ if ((t = kzalloc(sizeof(struct tc), GFP_KERNEL)) == NULL) {
printk(KERN_WARNING "VPE: alloc_tc no mem\n");
return NULL;
}
- memset(t, 0, sizeof(struct tc));
-
INIT_LIST_HEAD(&t->tc);
list_add_tail(&t->list, &vpecontrol.tc_list);
@@ -412,16 +400,17 @@ static int apply_r_mips_26(struct module *me, uint32_t *location,
return -ENOEXEC;
}
-/* Not desperately convinced this is a good check of an overflow condition
- anyway. But it gets in the way of handling undefined weak symbols which
- we want to set to zero.
- if ((v & 0xf0000000) != (((unsigned long)location + 4) & 0xf0000000)) {
- printk(KERN_ERR
- "module %s: relocation overflow\n",
- me->name);
- return -ENOEXEC;
- }
-*/
+/*
+ * Not desperately convinced this is a good check of an overflow condition
+ * anyway. But it gets in the way of handling undefined weak symbols which
+ * we want to set to zero.
+ * if ((v & 0xf0000000) != (((unsigned long)location + 4) & 0xf0000000)) {
+ * printk(KERN_ERR
+ * "module %s: relocation overflow\n",
+ * me->name);
+ * return -ENOEXEC;
+ * }
+ */
*location = (*location & ~0x03ffffff) |
((*location + (v >> 2)) & 0x03ffffff);
@@ -681,7 +670,7 @@ static void dump_tclist(void)
}
/* We are prepared so configure and start the VPE... */
-int vpe_run(vpe_t * v)
+int vpe_run(struct vpe * v)
{
unsigned long val;
struct tc *t;
@@ -772,7 +761,7 @@ int vpe_run(vpe_t * v)
return 0;
}
-static unsigned long find_vpe_symbols(vpe_t * v, Elf_Shdr * sechdrs,
+static unsigned long find_vpe_symbols(struct vpe * v, Elf_Shdr * sechdrs,
unsigned int symindex, const char *strtab,
struct module *mod)
{
@@ -792,10 +781,12 @@ static unsigned long find_vpe_symbols(vpe_t * v, Elf_Shdr * sechdrs,
return 0;
}
-/* Allocates a VPE with some program code space(the load address), copies the contents
- of the program (p)buffer performing relocatations/etc, free's it when finished.
+/*
+ * Allocates a VPE with some program code space(the load address), copies
+ * the contents of the program (p)buffer performing relocatations/etc,
+ * free's it when finished.
*/
-int vpe_elfload(vpe_t * v)
+int vpe_elfload(struct vpe * v)
{
Elf_Ehdr *hdr;
Elf_Shdr *sechdrs;
@@ -931,7 +922,7 @@ cleanup:
return err;
}
-static void dump_vpe(vpe_t * v)
+static void dump_vpe(struct vpe * v)
{
struct tc *t;
@@ -947,7 +938,7 @@ static void dump_vpe(vpe_t * v)
static int vpe_open(struct inode *inode, struct file *filp)
{
int minor;
- vpe_t *v;
+ struct vpe *v;
/* assume only 1 device at the mo. */
if ((minor = MINOR(inode->i_rdev)) != 1) {
@@ -1001,7 +992,7 @@ static int vpe_open(struct inode *inode, struct file *filp)
static int vpe_release(struct inode *inode, struct file *filp)
{
int minor, ret = 0;
- vpe_t *v;
+ struct vpe *v;
Elf_Ehdr *hdr;
minor = MINOR(inode->i_rdev);
@@ -1035,7 +1026,7 @@ static ssize_t vpe_write(struct file *file, const char __user * buffer,
{
int minor;
size_t ret = count;
- vpe_t *v;
+ struct vpe *v;
minor = MINOR(file->f_dentry->d_inode->i_rdev);
if ((v = get_vpe(minor)) == NULL)
@@ -1180,14 +1171,11 @@ static int __init vpe_module_init(void)
return -ENODEV;
}
- if ((major = register_chrdev(VPE_MAJOR, module_name, &vpe_fops) < 0)) {
+ if ((major = register_chrdev(0, module_name, &vpe_fops) < 0)) {
printk("VPE loader: unable to register character device\n");
- return -EBUSY;
+ return major;
}
- if (major == 0)
- major = VPE_MAJOR;
-
dmt();
dvpe();
diff --git a/arch/mips/lasat/ds1603.c b/arch/mips/lasat/ds1603.c
index 9d7812e03dcd..7dced67c55eb 100644
--- a/arch/mips/lasat/ds1603.c
+++ b/arch/mips/lasat/ds1603.c
@@ -8,6 +8,7 @@
#include
#include
#include
+#include
#include "ds1603.h"
@@ -138,19 +139,27 @@ static void rtc_end_op(void)
unsigned long ds1603_read(void)
{
unsigned long word;
+ unsigned long flags;
+
+ spin_lock_irqsave(&rtc_lock, flags);
rtc_init_op();
rtc_write_byte(READ_TIME_CMD);
word = rtc_read_word();
rtc_end_op();
+ spin_unlock_irqrestore(&rtc_lock, flags);
return word;
}
int ds1603_set(unsigned long time)
{
+ unsigned long flags;
+
+ spin_lock_irqsave(&rtc_lock, flags);
rtc_init_op();
rtc_write_byte(SET_TIME_CMD);
rtc_write_word(time);
rtc_end_op();
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
diff --git a/arch/mips/momentum/jaguar_atx/setup.c b/arch/mips/momentum/jaguar_atx/setup.c
index 768bf4406452..bab192ddc185 100644
--- a/arch/mips/momentum/jaguar_atx/setup.c
+++ b/arch/mips/momentum/jaguar_atx/setup.c
@@ -149,7 +149,9 @@ arch_initcall(per_cpu_mappings);
unsigned long m48t37y_get_time(void)
{
unsigned int year, month, day, hour, min, sec;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
/* stop the update */
rtc_base[0x7ff8] = 0x40;
@@ -166,6 +168,7 @@ unsigned long m48t37y_get_time(void)
/* start the update */
rtc_base[0x7ff8] = 0x00;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return mktime(year, month, day, hour, min, sec);
}
@@ -173,11 +176,13 @@ unsigned long m48t37y_get_time(void)
int m48t37y_set_time(unsigned long sec)
{
struct rtc_time tm;
+ unsigned long flags;
/* convert to a more useful format -- note months count from 0 */
to_tm(sec, &tm);
tm.tm_mon += 1;
+ spin_lock_irqsave(&rtc_lock, flags);
/* enable writing */
rtc_base[0x7ff8] = 0x80;
@@ -201,6 +206,7 @@ int m48t37y_set_time(unsigned long sec)
/* disable writing */
rtc_base[0x7ff8] = 0x00;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
diff --git a/arch/mips/momentum/ocelot_3/setup.c b/arch/mips/momentum/ocelot_3/setup.c
index a7803e08f9db..c9b7ff8148ec 100644
--- a/arch/mips/momentum/ocelot_3/setup.c
+++ b/arch/mips/momentum/ocelot_3/setup.c
@@ -135,7 +135,9 @@ void setup_wired_tlb_entries(void)
unsigned long m48t37y_get_time(void)
{
unsigned int year, month, day, hour, min, sec;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
/* stop the update */
rtc_base[0x7ff8] = 0x40;
@@ -152,6 +154,7 @@ unsigned long m48t37y_get_time(void)
/* start the update */
rtc_base[0x7ff8] = 0x00;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return mktime(year, month, day, hour, min, sec);
}
@@ -159,11 +162,13 @@ unsigned long m48t37y_get_time(void)
int m48t37y_set_time(unsigned long sec)
{
struct rtc_time tm;
+ unsigned long flags;
/* convert to a more useful format -- note months count from 0 */
to_tm(sec, &tm);
tm.tm_mon += 1;
+ spin_lock_irqsave(&rtc_lock, flags);
/* enable writing */
rtc_base[0x7ff8] = 0x80;
@@ -187,6 +192,7 @@ int m48t37y_set_time(unsigned long sec)
/* disable writing */
rtc_base[0x7ff8] = 0x00;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
diff --git a/arch/mips/momentum/ocelot_c/setup.c b/arch/mips/momentum/ocelot_c/setup.c
index ce70fc96f160..2755c1547473 100644
--- a/arch/mips/momentum/ocelot_c/setup.c
+++ b/arch/mips/momentum/ocelot_c/setup.c
@@ -140,7 +140,9 @@ unsigned long m48t37y_get_time(void)
unsigned char* rtc_base = (unsigned char*)0xfc800000;
#endif
unsigned int year, month, day, hour, min, sec;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
/* stop the update */
rtc_base[0x7ff8] = 0x40;
@@ -157,6 +159,7 @@ unsigned long m48t37y_get_time(void)
/* start the update */
rtc_base[0x7ff8] = 0x00;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return mktime(year, month, day, hour, min, sec);
}
@@ -169,11 +172,13 @@ int m48t37y_set_time(unsigned long sec)
unsigned char* rtc_base = (unsigned char*)0xfc800000;
#endif
struct rtc_time tm;
+ unsigned long flags;
/* convert to a more useful format -- note months count from 0 */
to_tm(sec, &tm);
tm.tm_mon += 1;
+ spin_lock_irqsave(&rtc_lock, flags);
/* enable writing */
rtc_base[0x7ff8] = 0x80;
@@ -197,6 +202,7 @@ int m48t37y_set_time(unsigned long sec)
/* disable writing */
rtc_base[0x7ff8] = 0x00;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
diff --git a/arch/mips/pmc-sierra/yosemite/setup.c b/arch/mips/pmc-sierra/yosemite/setup.c
index bdc2ab55bed6..059755b5ed57 100644
--- a/arch/mips/pmc-sierra/yosemite/setup.c
+++ b/arch/mips/pmc-sierra/yosemite/setup.c
@@ -73,7 +73,9 @@ void __init bus_error_init(void)
unsigned long m48t37y_get_time(void)
{
unsigned int year, month, day, hour, min, sec;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
/* Stop the update to the time */
m48t37_base->control = 0x40;
@@ -88,6 +90,7 @@ unsigned long m48t37y_get_time(void)
/* Start the update to the time again */
m48t37_base->control = 0x00;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return mktime(year, month, day, hour, min, sec);
}
@@ -95,11 +98,13 @@ unsigned long m48t37y_get_time(void)
int m48t37y_set_time(unsigned long sec)
{
struct rtc_time tm;
+ unsigned long flags;
/* convert to a more useful format -- note months count from 0 */
to_tm(sec, &tm);
tm.tm_mon += 1;
+ spin_lock_irqsave(&rtc_lock, flags);
/* enable writing */
m48t37_base->control = 0x80;
@@ -123,6 +128,7 @@ int m48t37y_set_time(unsigned long sec)
/* disable writing */
m48t37_base->control = 0x00;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c
index df9b5694328a..b7300cc5c5ad 100644
--- a/arch/mips/sgi-ip22/ip22-time.c
+++ b/arch/mips/sgi-ip22/ip22-time.c
@@ -35,7 +35,9 @@ static unsigned long indy_rtc_get_time(void)
{
unsigned int yrs, mon, day, hrs, min, sec;
unsigned int save_control;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
save_control = hpc3c0->rtcregs[RTC_CMD] & 0xff;
hpc3c0->rtcregs[RTC_CMD] = save_control | RTC_TE;
@@ -47,6 +49,7 @@ static unsigned long indy_rtc_get_time(void)
yrs = BCD2BIN(hpc3c0->rtcregs[RTC_YEAR] & 0xff);
hpc3c0->rtcregs[RTC_CMD] = save_control;
+ spin_unlock_irqrestore(&rtc_lock, flags);
if (yrs < 45)
yrs += 30;
@@ -60,6 +63,7 @@ static int indy_rtc_set_time(unsigned long tim)
{
struct rtc_time tm;
unsigned int save_control;
+ unsigned long flags;
to_tm(tim, &tm);
@@ -68,6 +72,7 @@ static int indy_rtc_set_time(unsigned long tim)
if (tm.tm_year >= 100)
tm.tm_year -= 100;
+ spin_lock_irqsave(&rtc_lock, flags);
save_control = hpc3c0->rtcregs[RTC_CMD] & 0xff;
hpc3c0->rtcregs[RTC_CMD] = save_control | RTC_TE;
@@ -80,6 +85,7 @@ static int indy_rtc_set_time(unsigned long tim)
hpc3c0->rtcregs[RTC_HUNDREDTH_SECOND] = 0;
hpc3c0->rtcregs[RTC_CMD] = save_control;
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
diff --git a/arch/mips/sibyte/swarm/rtc_m41t81.c b/arch/mips/sibyte/swarm/rtc_m41t81.c
index 5b4fc26c1b36..c13914bdda59 100644
--- a/arch/mips/sibyte/swarm/rtc_m41t81.c
+++ b/arch/mips/sibyte/swarm/rtc_m41t81.c
@@ -144,6 +144,7 @@ static int m41t81_write(uint8_t addr, int b)
int m41t81_set_time(unsigned long t)
{
struct rtc_time tm;
+ unsigned long flags;
to_tm(t, &tm);
@@ -153,6 +154,7 @@ int m41t81_set_time(unsigned long t)
* believe we should finish writing min within a second.
*/
+ spin_lock_irqsave(&rtc_lock, flags);
tm.tm_sec = BIN2BCD(tm.tm_sec);
m41t81_write(M41T81REG_SC, tm.tm_sec);
@@ -180,6 +182,7 @@ int m41t81_set_time(unsigned long t)
tm.tm_year %= 100;
tm.tm_year = BIN2BCD(tm.tm_year);
m41t81_write(M41T81REG_YR, tm.tm_year);
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
@@ -187,19 +190,23 @@ int m41t81_set_time(unsigned long t)
unsigned long m41t81_get_time(void)
{
unsigned int year, mon, day, hour, min, sec;
+ unsigned long flags;
/*
* min is valid if two reads of sec are the same.
*/
for (;;) {
+ spin_lock_irqsave(&rtc_lock, flags);
sec = m41t81_read(M41T81REG_SC);
min = m41t81_read(M41T81REG_MN);
if (sec == m41t81_read(M41T81REG_SC)) break;
+ spin_unlock_irqrestore(&rtc_lock, flags);
}
hour = m41t81_read(M41T81REG_HR) & 0x3f;
day = m41t81_read(M41T81REG_DT);
mon = m41t81_read(M41T81REG_MO);
year = m41t81_read(M41T81REG_YR);
+ spin_unlock_irqrestore(&rtc_lock, flags);
sec = BCD2BIN(sec);
min = BCD2BIN(min);
diff --git a/arch/mips/sibyte/swarm/rtc_xicor1241.c b/arch/mips/sibyte/swarm/rtc_xicor1241.c
index d9ff9323f24e..f4a178836415 100644
--- a/arch/mips/sibyte/swarm/rtc_xicor1241.c
+++ b/arch/mips/sibyte/swarm/rtc_xicor1241.c
@@ -113,9 +113,11 @@ int xicor_set_time(unsigned long t)
{
struct rtc_time tm;
int tmp;
+ unsigned long flags;
to_tm(t, &tm);
+ spin_lock_irqsave(&rtc_lock, flags);
/* unlock writes to the CCR */
xicor_write(X1241REG_SR, X1241REG_SR_WEL);
xicor_write(X1241REG_SR, X1241REG_SR_WEL | X1241REG_SR_RWEL);
@@ -160,6 +162,7 @@ int xicor_set_time(unsigned long t)
xicor_write(X1241REG_HR, tmp);
xicor_write(X1241REG_SR, 0);
+ spin_unlock_irqrestore(&rtc_lock, flags);
return 0;
}
@@ -167,7 +170,9 @@ int xicor_set_time(unsigned long t)
unsigned long xicor_get_time(void)
{
unsigned int year, mon, day, hour, min, sec, y2k;
+ unsigned long flags;
+ spin_lock_irqsave(&rtc_lock, flags);
sec = xicor_read(X1241REG_SC);
min = xicor_read(X1241REG_MN);
hour = xicor_read(X1241REG_HR);
@@ -183,6 +188,7 @@ unsigned long xicor_get_time(void)
mon = xicor_read(X1241REG_MO);
year = xicor_read(X1241REG_YR);
y2k = xicor_read(X1241REG_Y2K);
+ spin_unlock_irqrestore(&rtc_lock, flags);
sec = BCD2BIN(sec);
min = BCD2BIN(min);
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 18130c3748f3..b6fe202a620d 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -78,52 +78,13 @@ void ptrace_disable(struct task_struct *child)
pa_psw(child)->l = 0;
}
-long sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
long ret;
#ifdef DEBUG_PTRACE
long oaddr=addr, odata=data;
#endif
- lock_kernel();
- ret = -EPERM;
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
-
- ret = security_ptrace(current->parent, current);
- if (ret)
- goto out;
-
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
-
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
- ret = -EPERM;
- if (pid == 1) /* no messing around with init! */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA: {
@@ -383,11 +344,11 @@ long sys_ptrace(long request, long pid, long addr, long data)
case PTRACE_GETEVENTMSG:
ret = put_user(child->ptrace_message, (unsigned int __user *) data);
- goto out_tsk;
+ goto out;
default:
ret = ptrace_request(child, request, addr, data);
- goto out_tsk;
+ goto out;
}
out_wake_notrap:
@@ -396,10 +357,7 @@ out_wake:
wake_up_process(child);
ret = 0;
out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
- DBG("sys_ptrace(%ld, %d, %lx, %lx) returning %ld\n",
+ DBG("arch_ptrace(%ld, %d, %lx, %lx) returning %ld\n",
request, pid, oaddr, odata, ret);
return ret;
}
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ca7acb0c79f0..6ffae2d2b3fa 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -605,6 +605,7 @@ config NODES_SPAN_OTHER_NODES
config PPC_64K_PAGES
bool "64k page size"
+ depends on PPC64
help
This option changes the kernel logical page size to 64k. On machines
without processor support for 64k pages, the kernel will simulate
@@ -916,8 +917,21 @@ source "arch/powerpc/platforms/iseries/Kconfig"
source "lib/Kconfig"
+menu "Instrumentation Support"
+ depends on EXPERIMENTAL
+
source "arch/powerpc/oprofile/Kconfig"
+config KPROBES
+ bool "Kprobes (EXPERIMENTAL)"
+ help
+ Kprobes allows you to trap at almost any kernel address and
+ execute a callback function. register_kprobe() establishes
+ a probepoint and specifies the callback. Kprobes is useful
+ for kernel debugging, non-intrusive instrumentation and testing.
+ If in doubt, say "N".
+endmenu
+
source "arch/powerpc/Kconfig.debug"
source "security/Kconfig"
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 0baf64ec80d0..30a30bf559ea 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -9,16 +9,6 @@ config DEBUG_STACKOVERFLOW
This option will cause messages to be printed if free stack space
drops below a certain limit.
-config KPROBES
- bool "Kprobes"
- depends on DEBUG_KERNEL && PPC64
- help
- Kprobes allows you to trap at almost any kernel address and
- execute a callback function. register_kprobe() establishes
- a probepoint and specifies the callback. Kprobes is useful
- for kernel debugging, non-intrusive instrumentation and testing.
- If in doubt, say "N".
-
config DEBUG_STACK_USAGE
bool "Stack utilization instrumentation"
depends on DEBUG_KERNEL && PPC64
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 33c63bcf69f8..cc4e9eb1c13f 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -929,6 +929,16 @@ struct cpu_spec cpu_specs[] = {
.icache_bsize = 32,
.dcache_bsize = 32,
},
+ { /* 440SPe Rev. A */
+ .pvr_mask = 0xff000fff,
+ .pvr_value = 0x53000890,
+ .cpu_name = "440SPe Rev. A",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
#endif /* CONFIG_44x */
#ifdef CONFIG_FSL_BOOKE
{ /* e200z5 */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 568ea335d616..3d2abd95c7ae 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -248,46 +248,10 @@ void ptrace_disable(struct task_struct *child)
clear_single_step(child);
}
-long sys_ptrace(long request, long pid, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- struct task_struct *child;
int ret = -EPERM;
- lock_kernel();
- if (request == PTRACE_TRACEME) {
- /* are we already being traced? */
- if (current->ptrace & PT_PTRACED)
- goto out;
- ret = security_ptrace(current->parent, current);
- if (ret)
- goto out;
- /* set the ptrace bit in the process flags. */
- current->ptrace |= PT_PTRACED;
- ret = 0;
- goto out;
- }
- ret = -ESRCH;
- read_lock(&tasklist_lock);
- child = find_task_by_pid(pid);
- if (child)
- get_task_struct(child);
- read_unlock(&tasklist_lock);
- if (!child)
- goto out;
-
- ret = -EPERM;
- if (pid == 1) /* you may not mess with init */
- goto out_tsk;
-
- if (request == PTRACE_ATTACH) {
- ret = ptrace_attach(child);
- goto out_tsk;
- }
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out_tsk;
-
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
@@ -540,10 +504,7 @@ long sys_ptrace(long request, long pid, long addr, long data)
ret = ptrace_request(child, request, addr, data);
break;
}
-out_tsk:
- put_task_struct(child);
-out:
- unlock_kernel();
+
return ret;
}
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 6996a593dcb3..b1c89bc4bf90 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -69,6 +69,7 @@
#include
#include
#endif
+#include
/* keep track of when we need to update the rtc */
time_t last_rtc_update;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index b2f3dbca6952..f15dfb92dec0 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -329,12 +329,14 @@ static void __init htab_init_page_sizes(void)
*/
if (mmu_psize_defs[MMU_PAGE_16M].shift)
mmu_huge_psize = MMU_PAGE_16M;
+ /* With 4k/4level pagetables, we can't (for now) cope with a
+ * huge page size < PMD_SIZE */
else if (mmu_psize_defs[MMU_PAGE_1M].shift)
mmu_huge_psize = MMU_PAGE_1M;
/* Calculate HPAGE_SHIFT and sanity check it */
- if (mmu_psize_defs[mmu_huge_psize].shift > 16 &&
- mmu_psize_defs[mmu_huge_psize].shift < 28)
+ if (mmu_psize_defs[mmu_huge_psize].shift > MIN_HUGEPTE_SHIFT &&
+ mmu_psize_defs[mmu_huge_psize].shift < SID_SHIFT)
HPAGE_SHIFT = mmu_psize_defs[mmu_huge_psize].shift;
else
HPAGE_SHIFT = 0; /* No huge pages dude ! */
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0073a04047e4..426c269e552e 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -212,6 +212,12 @@ static int prepare_high_area_for_htlb(struct mm_struct *mm, unsigned long area)
BUG_ON(area >= NUM_HIGH_AREAS);
+ /* Hack, so that each addresses is controlled by exactly one
+ * of the high or low area bitmaps, the first high area starts
+ * at 4GB, not 0 */
+ if (start == 0)
+ start = 0x100000000UL;
+
/* Check no VMAs are in the region */
vma = find_vma(mm, start);
if (vma && (vma->vm_start < end))
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index d137abd241ff..ed7fcfe5fd37 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -188,9 +188,9 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
if (Hash == 0)
return;
- pmd = pmd_offset(pgd_offset(vma->vm_mm, address), address);
+ pmd = pmd_offset(pgd_offset(mm, ea), ea);
if (!pmd_none(*pmd))
- add_hash_page(vma->vm_mm->context, address, pmd_val(*pmd));
+ add_hash_page(mm->context, ea, pmd_val(*pmd));
}
/*
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 3e18241b6f35..950ffc5848c7 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -80,12 +80,17 @@ _GLOBAL(slb_miss_kernel_load_virtual)
BEGIN_FTR_SECTION
b 1f
END_FTR_SECTION_IFCLR(CPU_FTR_16M_PAGE)
+ cmpldi r10,16
+
+ lhz r9,PACALOWHTLBAREAS(r13)
+ mr r11,r10
+ blt 5f
+
lhz r9,PACAHIGHHTLBAREAS(r13)
srdi r11,r10,(HTLB_AREA_SHIFT-SID_SHIFT)
- srd r9,r9,r11
- lhz r11,PACALOWHTLBAREAS(r13)
- srd r11,r11,r10
- or. r9,r9,r11
+
+5: srd r9,r9,r11
+ andi. r9,r9,1
beq 1f
_GLOBAL(slb_miss_user_load_huge)
li r11,0
diff --git a/arch/powerpc/oprofile/Kconfig b/arch/powerpc/oprofile/Kconfig
index 19d37730b664..eb2dece76a54 100644
--- a/arch/powerpc/oprofile/Kconfig
+++ b/arch/powerpc/oprofile/Kconfig
@@ -1,7 +1,3 @@
-
-menu "Profiling support"
- depends on EXPERIMENTAL
-
config PROFILING
bool "Profiling support (EXPERIMENTAL)"
help
@@ -19,5 +15,3 @@ config OPROFILE
If unsure, say N.
-endmenu
-
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 58c61219d08e..d7d400339458 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -286,10 +286,8 @@ static struct property *new_property(const char *name, const int length,
return new;
cleanup:
- if (new->name)
- kfree(new->name);
- if (new->value)
- kfree(new->value);
+ kfree(new->name);
+ kfree(new->value);
kfree(new);
return NULL;
}
diff --git a/arch/ppc/4xx_io/serial_sicc.c b/arch/ppc/4xx_io/serial_sicc.c
index e95c48d57571..84d96b857e4a 100644
--- a/arch/ppc/4xx_io/serial_sicc.c
+++ b/arch/ppc/4xx_io/serial_sicc.c
@@ -1145,8 +1145,8 @@ static int set_serial_info(struct SICC_info *info,
info->flags = ((state->flags & ~ASYNC_INTERNAL_FLAGS) |
(info->flags & ASYNC_INTERNAL_FLAGS));
state->custom_divisor = new_serial.custom_divisor;
- state->close_delay = new_serial.close_delay * HZ / 100;
- state->closing_wait = new_serial.closing_wait * HZ / 100;
+ state->close_delay = msecs_to_jiffies(10 * new_serial.close_delay);
+ state->closing_wait = msecs_to_jiffies(10 * new_serial.closing_wait);
info->tty->low_latency = (info->flags & ASYNC_LOW_LATENCY) ? 1 : 0;
port->fifosize = new_serial.xmit_fifo_size;
@@ -1465,10 +1465,8 @@ static void siccuart_close(struct tty_struct *tty, struct file *filp)
info->event = 0;
info->tty = NULL;
if (info->blocked_open) {
- if (info->state->close_delay) {
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(info->state->close_delay);
- }
+ if (info->state->close_delay)
+ schedule_timeout_interruptible(info->state->close_delay);
wake_up_interruptible(&info->open_wait);
}
info->flags &= ~(ASYNC_NORMAL_ACTIVE|ASYNC_CLOSING);
@@ -1496,7 +1494,7 @@ static void siccuart_wait_until_sent(struct tty_struct *tty, int timeout)
* Note: we have to use pretty tight timings here to satisfy
* the NIST-PCTS.
*/
- char_time = (info->timeout - HZ/50) / info->port->fifosize;
+ char_time = (info->timeout - msecs_to_jiffies(20)) / info->port->fifosize;
char_time = char_time / 5;
if (char_time == 0)
char_time = 1;
@@ -1521,8 +1519,7 @@ static void siccuart_wait_until_sent(struct tty_struct *tty, int timeout)
tty->index, jiffies,
expire, char_time);
while ((readb(info->port->uart_base + BL_SICC_LSR) & _LSR_TX_ALL) != _LSR_TX_ALL) {
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(char_time);
+ schedule_timeout_interruptible(char_time);
if (signal_pending(current))
break;
if (timeout && time_after(jiffies, expire))
@@ -1773,7 +1770,7 @@ int __init siccuart_init(void)
for (i = 0; i < SERIAL_SICC_NR; i++) {
struct SICC_state *state = sicc_state + i;
state->line = i;
- state->close_delay = 5 * HZ / 10;
+ state->close_delay = msecs_to_jiffies(500);
state->closing_wait = 30 * HZ;
spin_lock_init(&state->sicc_lock);
}
diff --git a/arch/ppc/8260_io/fcc_enet.c b/arch/ppc/8260_io/fcc_enet.c
index 2086c6ad1147..4edeede9ccfd 100644
--- a/arch/ppc/8260_io/fcc_enet.c
+++ b/arch/ppc/8260_io/fcc_enet.c
@@ -1309,8 +1309,7 @@ static void mii_dm9161_wait(uint mii_reg, struct net_device *dev)
/* Davicom takes a bit to come up after a reset,
* so wait here for a bit */
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(timeout);
+ schedule_timeout_uninterruptible(timeout);
}
static phy_info_t phy_info_dm9161 = {
diff --git a/arch/ppc/8xx_io/cs4218_tdm.c b/arch/ppc/8xx_io/cs4218_tdm.c
index 532caa388dc2..49eb2a7e65c0 100644
--- a/arch/ppc/8xx_io/cs4218_tdm.c
+++ b/arch/ppc/8xx_io/cs4218_tdm.c
@@ -1013,8 +1013,7 @@ static void CS_IrqCleanup(void)
*/
cpm_free_handler(CPMVEC_SMC2);
- if (beep_buf)
- kfree(beep_buf);
+ kfree(beep_buf);
kd_mksound = orig_mksound;
}
#endif /* MODULE */
diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig
index 114b90fdea24..8fa51b0a32d2 100644
--- a/arch/ppc/Kconfig
+++ b/arch/ppc/Kconfig
@@ -746,6 +746,16 @@ config MPC834x
bool
default y if MPC834x_SYS
+config CPM1
+ bool
+ depends on 8xx
+ default y
+ help
+ The CPM1 (Communications Processor Module) is a coprocessor on
+ embedded CPUs made by Motorola. Selecting this option means that
+ you wish to build a kernel for a machine with a CPM1 coprocessor
+ on it (8xx, 827x, 8560).
+
config CPM2
bool
depends on 8260 || MPC8560 || MPC8555
@@ -1247,6 +1257,14 @@ source "drivers/pci/Kconfig"
source "drivers/pcmcia/Kconfig"
+config RAPIDIO
+ bool "RapidIO support" if MPC8540 || MPC8560
+ help
+ If you say Y here, the kernel will include drivers and
+ infrastructure code to support RapidIO interconnect devices.
+
+source "drivers/rapidio/Kconfig"
+
endmenu
menu "Advanced setup"
diff --git a/arch/ppc/boot/simple/Makefile b/arch/ppc/boot/simple/Makefile
index b7bd8f61a4ad..82df88b01bbe 100644
--- a/arch/ppc/boot/simple/Makefile
+++ b/arch/ppc/boot/simple/Makefile
@@ -67,6 +67,12 @@ zimageinitrd-$(CONFIG_BAMBOO) := zImage.initrd-TREE
entrypoint-$(CONFIG_BAMBOO) := 0x01000000
extra.o-$(CONFIG_BAMBOO) := pibs.o
+ zimage-$(CONFIG_BUBINGA) := zImage-TREE
+zimageinitrd-$(CONFIG_BUBINGA) := zImage.initrd-TREE
+ end-$(CONFIG_BUBINGA) := bubinga
+ entrypoint-$(CONFIG_BUBINGA) := 0x01000000
+ extra.o-$(CONFIG_BUBINGA) := openbios.o
+
zimage-$(CONFIG_EBONY) := zImage-TREE
zimageinitrd-$(CONFIG_EBONY) := zImage.initrd-TREE
end-$(CONFIG_EBONY) := ebony
@@ -79,12 +85,30 @@ zimageinitrd-$(CONFIG_LUAN) := zImage.initrd-TREE
entrypoint-$(CONFIG_LUAN) := 0x01000000
extra.o-$(CONFIG_LUAN) := pibs.o
+ zimage-$(CONFIG_YUCCA) := zImage-TREE
+zimageinitrd-$(CONFIG_YUCCA) := zImage.initrd-TREE
+ end-$(CONFIG_YUCCA) := yucca
+ entrypoint-$(CONFIG_YUCCA) := 0x01000000
+ extra.o-$(CONFIG_YUCCA) := pibs.o
+
zimage-$(CONFIG_OCOTEA) := zImage-TREE
zimageinitrd-$(CONFIG_OCOTEA) := zImage.initrd-TREE
end-$(CONFIG_OCOTEA) := ocotea
entrypoint-$(CONFIG_OCOTEA) := 0x01000000
extra.o-$(CONFIG_OCOTEA) := pibs.o
+ zimage-$(CONFIG_SYCAMORE) := zImage-TREE
+zimageinitrd-$(CONFIG_SYCAMORE) := zImage.initrd-TREE
+ end-$(CONFIG_SYCAMORE) := sycamore
+ entrypoint-$(CONFIG_SYCAMORE) := 0x01000000
+ extra.o-$(CONFIG_SYCAMORE) := openbios.o
+
+ zimage-$(CONFIG_WALNUT) := zImage-TREE
+zimageinitrd-$(CONFIG_WALNUT) := zImage.initrd-TREE
+ end-$(CONFIG_WALNUT) := walnut
+ entrypoint-$(CONFIG_WALNUT) := 0x01000000
+ extra.o-$(CONFIG_WALNUT) := openbios.o
+
extra.o-$(CONFIG_EV64260) := misc-ev64260.o
end-$(CONFIG_EV64260) := ev64260
cacheflag-$(CONFIG_EV64260) := -include $(clear_L2_L3)
@@ -162,7 +186,8 @@ OBJCOPY_ARGS := -O elf32-powerpc
# head.o and relocate.o must be at the start.
boot-y := head.o relocate.o $(extra.o-y) $(misc-y)
-boot-$(CONFIG_40x) += embed_config.o
+boot-$(CONFIG_REDWOOD_5) += embed_config.o
+boot-$(CONFIG_REDWOOD_6) += embed_config.o
boot-$(CONFIG_8xx) += embed_config.o
boot-$(CONFIG_8260) += embed_config.o
boot-$(CONFIG_BSEIP) += iic.o
diff --git a/arch/ppc/boot/simple/misc.c b/arch/ppc/boot/simple/misc.c
index e02de5b467a4..f415d6c62362 100644
--- a/arch/ppc/boot/simple/misc.c
+++ b/arch/ppc/boot/simple/misc.c
@@ -23,7 +23,7 @@
#include
#include
#include
-#ifdef CONFIG_44x
+#ifdef CONFIG_4xx
#include
#endif
#include
@@ -88,6 +88,14 @@ get_mem_size(void)
return 0;
}
+#if defined(CONFIG_40x)
+#define PPC4xx_EMAC0_MR0 EMAC0_BASE
+#endif
+
+#if defined(CONFIG_44x) && defined(PPC44x_EMAC0_MR0)
+#define PPC4xx_EMAC0_MR0 PPC44x_EMAC0_MR0
+#endif
+
struct bi_record *
decompress_kernel(unsigned long load_addr, int num_words, unsigned long cksum)
{
@@ -103,13 +111,13 @@ decompress_kernel(unsigned long load_addr, int num_words, unsigned long cksum)
com_port = serial_init(0, NULL);
#endif
-#if defined(CONFIG_44x) && defined(PPC44x_EMAC0_MR0)
+#if defined(PPC4xx_EMAC0_MR0)
/* Reset MAL */
mtdcr(DCRN_MALCR(DCRN_MAL_BASE), MALCR_MMSR);
/* Wait for reset */
while (mfdcr(DCRN_MALCR(DCRN_MAL_BASE)) & MALCR_MMSR) {};
/* Reset EMAC */
- *(volatile unsigned long *)PPC44x_EMAC0_MR0 = 0x20000000;
+ *(volatile unsigned long *)PPC4xx_EMAC0_MR0 = 0x20000000;
__asm__ __volatile__("eieio");
#endif
@@ -164,7 +172,9 @@ decompress_kernel(unsigned long load_addr, int num_words, unsigned long cksum)
puts(" "); puthex((unsigned long)(&__ramdisk_end));puts("\n");
}
+#ifndef CONFIG_40x /* don't overwrite the 40x image located at 0x00400000! */
avail_ram = (char *)0x00400000;
+#endif
end_avail = (char *)0x00800000;
puts("avail ram: "); puthex((unsigned long)avail_ram); puts(" ");
puthex((unsigned long)end_avail); puts("\n");
diff --git a/arch/ppc/boot/simple/openbios.c b/arch/ppc/boot/simple/openbios.c
index c732b6d70cfb..81f11d8b30a7 100644
--- a/arch/ppc/boot/simple/openbios.c
+++ b/arch/ppc/boot/simple/openbios.c
@@ -1,19 +1,43 @@
/*
* arch/ppc/boot/simple/openbios.c
*
- * 2005 (c) SYSGO AG - g.jaeger@sysgo.com
+ * Copyright (c) 2005 DENX Software Engineering
+ * Stefan Roese
+ *
+ * Based on original work by
+ * 2005 (c) SYSGO AG - g.jaeger@sysgo.com
+ *
* This file is licensed under the terms of the GNU General Public
* License version 2. This program is licensed "as is" without
* any warranty of any kind, whether express or implied.
*
- * Derived from arch/ppc/boot/simple/pibs.c (from MontaVista)
*/
#include
#include
#include
#include
-#include
+#include
+#include
+#ifdef CONFIG_40x
+#include
+#endif
+
+#if defined(CONFIG_BUBINGA)
+#define BOARD_INFO_VECTOR 0xFFF80B50 /* openbios 1.19 moved this vector down - armin */
+#else
+#define BOARD_INFO_VECTOR 0xFFFE0B50
+#endif
+
+#ifdef CONFIG_40x
+/* Supply a default Ethernet address for those eval boards that don't
+ * ship with one. This is an address from the MBX board I have, so
+ * it is unlikely you will find it on your network.
+ */
+static ushort def_enet_addr[] = { 0x0800, 0x3e26, 0x1559 };
+
+extern unsigned long timebase_period_ns;
+#endif /* CONFIG_40x */
extern unsigned long decompress_kernel(unsigned long load_addr, int num_words,
unsigned long cksum);
@@ -23,15 +47,85 @@ extern unsigned long decompress_kernel(unsigned long load_addr, int num_words,
bd_t hold_resid_buf __attribute__ ((__section__ (".data.boot")));
bd_t *hold_residual = &hold_resid_buf;
+typedef struct openbios_board_info {
+ unsigned char bi_s_version[4]; /* Version of this structure */
+ unsigned char bi_r_version[30]; /* Version of the IBM ROM */
+ unsigned int bi_memsize; /* DRAM installed, in bytes */
+#ifdef CONFIG_405EP
+ unsigned char bi_enetaddr[2][6]; /* Local Ethernet MAC address */
+#else /* CONFIG_405EP */
+ unsigned char bi_enetaddr[6]; /* Local Ethernet MAC address */
+#endif /* CONFIG_405EP */
+ unsigned char bi_pci_enetaddr[6]; /* PCI Ethernet MAC address */
+ unsigned int bi_intfreq; /* Processor speed, in Hz */
+ unsigned int bi_busfreq; /* PLB Bus speed, in Hz */
+ unsigned int bi_pci_busfreq; /* PCI Bus speed, in Hz */
+#ifdef CONFIG_405EP
+ unsigned int bi_opb_busfreq; /* OPB Bus speed, in Hz */
+ unsigned int bi_pllouta_freq; /* PLL OUTA speed, in Hz */
+#endif /* CONFIG_405EP */
+} openbios_bd_t;
+
void *
load_kernel(unsigned long load_addr, int num_words, unsigned long cksum,
void *ign1, void *ign2)
{
- decompress_kernel(load_addr, num_words, cksum);
+#ifdef CONFIG_40x
+ openbios_bd_t *openbios_bd = NULL;
+ openbios_bd_t *(*get_board_info)(void) =
+ (openbios_bd_t *(*)(void))(*(unsigned long *)BOARD_INFO_VECTOR);
+ /*
+ * On 40x platforms we not only need the MAC-addresses, but also the
+ * clocks and memsize. Now try to get all values using the OpenBIOS
+ * "get_board_info()" callback.
+ */
+ if ((openbios_bd = get_board_info()) != NULL) {
+ /*
+ * Copy bd_info from OpenBIOS struct into U-Boot struct
+ * used by kernel
+ */
+ hold_residual->bi_memsize = openbios_bd->bi_memsize;
+ hold_residual->bi_intfreq = openbios_bd->bi_intfreq;
+ hold_residual->bi_busfreq = openbios_bd->bi_busfreq;
+ hold_residual->bi_pci_busfreq = openbios_bd->bi_pci_busfreq;
+ memcpy(hold_residual->bi_pci_enetaddr, openbios_bd->bi_pci_enetaddr, 6);
+#ifdef CONFIG_405EP
+ memcpy(hold_residual->bi_enetaddr, openbios_bd->bi_enetaddr[0], 6);
+ memcpy(hold_residual->bi_enet1addr, openbios_bd->bi_enetaddr[1], 6);
+ hold_residual->bi_opbfreq = openbios_bd->bi_opb_busfreq;
+ hold_residual->bi_procfreq = openbios_bd->bi_pllouta_freq;
+#else /* CONFIG_405EP */
+ memcpy(hold_residual->bi_enetaddr, openbios_bd->bi_enetaddr, 6);
+#endif /* CONFIG_405EP */
+ } else {
+ /* Hmmm...better try to stuff some defaults.
+ */
+ hold_residual->bi_memsize = 16 * 1024 * 1024;
+ hold_residual->bi_intfreq = 200000000;
+ hold_residual->bi_busfreq = 100000000;
+ hold_residual->bi_pci_busfreq = 66666666;
+
+ /*
+ * Only supply one mac-address in this fallback
+ */
+ memcpy(hold_residual->bi_enetaddr, (void *)def_enet_addr, 6);
+#ifdef CONFIG_405EP
+ hold_residual->bi_opbfreq = 50000000;
+ hold_residual->bi_procfreq = 200000000;
+#endif /* CONFIG_405EP */
+ }
+
+ timebase_period_ns = 1000000000 / hold_residual->bi_intfreq;
+#endif /* CONFIG_40x */
+
+#ifdef CONFIG_440GP
/* simply copy the MAC addresses */
- memcpy(hold_residual->bi_enetaddr, (char *)EBONY_OPENBIOS_MAC_BASE, 6);
- memcpy(hold_residual->bi_enet1addr, (char *)(EBONY_OPENBIOS_MAC_BASE+EBONY_OPENBIOS_MAC_OFFSET), 6);
+ memcpy(hold_residual->bi_enetaddr, (char *)OPENBIOS_MAC_BASE, 6);
+ memcpy(hold_residual->bi_enet1addr, (char *)(OPENBIOS_MAC_BASE+OPENBIOS_MAC_OFFSET), 6);
+#endif /* CONFIG_440GP */
+
+ decompress_kernel(load_addr, num_words, cksum);
return (void *)hold_residual;
}
diff --git a/arch/ppc/configs/ev64360_defconfig b/arch/ppc/configs/ev64360_defconfig
index de9bbb791db9..d471e578dcb5 100644
--- a/arch/ppc/configs/ev64360_defconfig
+++ b/arch/ppc/configs/ev64360_defconfig
@@ -1,17 +1,17 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.13-rc5
-# Fri Aug 5 15:18:23 2005
+# Linux kernel version: 2.6.14
+# Fri Oct 28 19:15:34 2005
#
CONFIG_MMU=y
CONFIG_GENERIC_HARDIRQS=y
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_HAVE_DEC_LOCK=y
CONFIG_PPC=y
CONFIG_PPC32=y
CONFIG_GENERIC_NVRAM=y
CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
+CONFIG_ARCH_MAY_HAVE_PC_FDC=y
#
# Code maturity level options
@@ -26,6 +26,7 @@ CONFIG_INIT_ENV_ARG_LIMIT=32
# General setup
#
CONFIG_LOCALVERSION=""
+CONFIG_LOCALVERSION_AUTO=y
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
@@ -35,6 +36,7 @@ CONFIG_SYSCTL=y
CONFIG_HOTPLUG=y
CONFIG_KOBJECT_UEVENT=y
# CONFIG_IKCONFIG is not set
+CONFIG_INITRAMFS_SOURCE=""
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_EXTRA_PASS is not set
@@ -74,7 +76,7 @@ CONFIG_TAU=y
# CONFIG_TAU_AVERAGE is not set
# CONFIG_KEXEC is not set
# CONFIG_CPU_FREQ is not set
-# CONFIG_PM is not set
+# CONFIG_WANT_EARLY_SERIAL is not set
CONFIG_PPC_STD_MMU=y
CONFIG_NOT_COHERENT_CACHE=y
@@ -86,22 +88,18 @@ CONFIG_NOT_COHERENT_CACHE=y
# CONFIG_KATANA is not set
# CONFIG_WILLOW is not set
# CONFIG_CPCI690 is not set
-# CONFIG_PCORE is not set
# CONFIG_POWERPMC250 is not set
# CONFIG_CHESTNUT is not set
# CONFIG_SPRUCE is not set
# CONFIG_HDPU is not set
# CONFIG_EV64260 is not set
# CONFIG_LOPEC is not set
-# CONFIG_MCPN765 is not set
# CONFIG_MVME5100 is not set
# CONFIG_PPLUS is not set
# CONFIG_PRPMC750 is not set
# CONFIG_PRPMC800 is not set
# CONFIG_SANDPOINT is not set
# CONFIG_RADSTONE_PPC7D is not set
-# CONFIG_ADIR is not set
-# CONFIG_K2 is not set
# CONFIG_PAL4 is not set
# CONFIG_GEMINI is not set
# CONFIG_EST8260 is not set
@@ -138,10 +136,13 @@ CONFIG_FLATMEM_MANUAL=y
# CONFIG_SPARSEMEM_MANUAL is not set
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
+# CONFIG_SPARSEMEM_STATIC is not set
CONFIG_BINFMT_ELF=y
CONFIG_BINFMT_MISC=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="console=ttyMM0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2"
+# CONFIG_PM is not set
+# CONFIG_SOFTWARE_SUSPEND is not set
CONFIG_SECCOMP=y
CONFIG_ISA_DMA_API=y
@@ -152,7 +153,6 @@ CONFIG_GENERIC_ISA_DMA=y
CONFIG_PCI=y
CONFIG_PCI_DOMAINS=y
# CONFIG_PCI_LEGACY_PROC is not set
-# CONFIG_PCI_NAMES is not set
#
# PCCARD (PCMCIA/CardBus) support
@@ -206,13 +206,18 @@ CONFIG_SYN_COOKIES=y
# CONFIG_INET_ESP is not set
# CONFIG_INET_IPCOMP is not set
# CONFIG_INET_TUNNEL is not set
-CONFIG_IP_TCPDIAG=y
-# CONFIG_IP_TCPDIAG_IPV6 is not set
+CONFIG_INET_DIAG=y
+CONFIG_INET_TCP_DIAG=y
# CONFIG_TCP_CONG_ADVANCED is not set
CONFIG_TCP_CONG_BIC=y
# CONFIG_IPV6 is not set
# CONFIG_NETFILTER is not set
+#
+# DCCP Configuration (EXPERIMENTAL)
+#
+# CONFIG_IP_DCCP is not set
+
#
# SCTP Configuration (EXPERIMENTAL)
#
@@ -239,6 +244,7 @@ CONFIG_TCP_CONG_BIC=y
# CONFIG_HAMRADIO is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
+# CONFIG_IEEE80211 is not set
#
# Device Drivers
@@ -251,6 +257,11 @@ CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
# CONFIG_FW_LOADER is not set
+#
+# Connector - unified userspace <-> kernelspace linker
+#
+# CONFIG_CONNECTOR is not set
+
#
# Memory Technology Devices (MTD)
#
@@ -358,7 +369,6 @@ CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=32768
CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE=""
# CONFIG_LBD is not set
# CONFIG_CDROM_PKTCDVD is not set
@@ -379,6 +389,7 @@ CONFIG_IOSCHED_CFQ=y
#
# SCSI device support
#
+# CONFIG_RAID_ATTRS is not set
# CONFIG_SCSI is not set
#
@@ -419,6 +430,10 @@ CONFIG_NETDEVICES=y
#
# CONFIG_ARCNET is not set
+#
+# PHY device support
+#
+
#
# Ethernet (10 or 100Mbit)
#
@@ -434,6 +449,7 @@ CONFIG_NETDEVICES=y
# CONFIG_HAMACHI is not set
# CONFIG_YELLOWFIN is not set
# CONFIG_R8169 is not set
+# CONFIG_SIS190 is not set
# CONFIG_SKGE is not set
# CONFIG_SK98LIN is not set
# CONFIG_TIGON3 is not set
@@ -446,6 +462,7 @@ CONFIG_MV643XX_ETH_0=y
#
# Ethernet (10000 Mbit)
#
+# CONFIG_CHELSIO_T1 is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set
@@ -547,7 +564,20 @@ CONFIG_LEGACY_PTY_COUNT=256
#
# Watchdog Cards
#
-# CONFIG_WATCHDOG is not set
+CONFIG_WATCHDOG=y
+# CONFIG_WATCHDOG_NOWAYOUT is not set
+
+#
+# Watchdog Device Drivers
+#
+# CONFIG_SOFT_WATCHDOG is not set
+CONFIG_MV64X60_WDT=y
+
+#
+# PCI-based Watchdog Cards
+#
+# CONFIG_PCIPCWATCHDOG is not set
+# CONFIG_WDTPCI is not set
# CONFIG_NVRAM is not set
CONFIG_GEN_RTC=y
# CONFIG_GEN_RTC_X is not set
@@ -571,7 +601,6 @@ CONFIG_GEN_RTC=y
# I2C support
#
# CONFIG_I2C is not set
-# CONFIG_I2C_SENSOR is not set
#
# Dallas's 1-wire bus
@@ -582,12 +611,17 @@ CONFIG_GEN_RTC=y
# Hardware Monitoring support
#
CONFIG_HWMON=y
+# CONFIG_HWMON_VID is not set
# CONFIG_HWMON_DEBUG_CHIP is not set
#
# Misc devices
#
+#
+# Multimedia Capabilities Port drivers
+#
+
#
# Multimedia devices
#
@@ -651,10 +685,6 @@ CONFIG_EXT2_FS=y
# CONFIG_REISERFS_FS is not set
# CONFIG_JFS_FS is not set
# CONFIG_FS_POSIX_ACL is not set
-
-#
-# XFS support
-#
# CONFIG_XFS_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_ROMFS_FS is not set
@@ -663,6 +693,7 @@ CONFIG_INOTIFY=y
CONFIG_DNOTIFY=y
# CONFIG_AUTOFS_FS is not set
# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
#
# CD-ROM/DVD Filesystems
@@ -683,11 +714,10 @@ CONFIG_DNOTIFY=y
CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
CONFIG_SYSFS=y
-# CONFIG_DEVPTS_FS_XATTR is not set
CONFIG_TMPFS=y
-# CONFIG_TMPFS_XATTR is not set
# CONFIG_HUGETLB_PAGE is not set
CONFIG_RAMFS=y
+# CONFIG_RELAYFS_FS is not set
#
# Miscellaneous filesystems
@@ -735,6 +765,7 @@ CONFIG_SUNRPC=y
# CONFIG_NCP_FS is not set
# CONFIG_CODA_FS is not set
# CONFIG_AFS_FS is not set
+# CONFIG_9P_FS is not set
#
# Partition Types
@@ -751,6 +782,7 @@ CONFIG_MSDOS_PARTITION=y
# Library routines
#
# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
CONFIG_CRC32=y
# CONFIG_LIBCRC32C is not set
CONFIG_ZLIB_INFLATE=y
@@ -767,6 +799,7 @@ CONFIG_ZLIB_DEFLATE=y
# CONFIG_PRINTK_TIME is not set
# CONFIG_DEBUG_KERNEL is not set
CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_SERIAL_TEXT_DEBUG is not set
#
# Security options
diff --git a/arch/ppc/configs/stx_gp3_defconfig b/arch/ppc/configs/stx_gp3_defconfig
index 66dae8367659..3fedc43e44ad 100644
--- a/arch/ppc/configs/stx_gp3_defconfig
+++ b/arch/ppc/configs/stx_gp3_defconfig
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.11-rc2
-# Wed Jan 26 14:32:58 2005
+# Linux kernel version: 2.6.12-rc4
+# Tue May 24 18:11:04 2005
#
CONFIG_MMU=y
CONFIG_GENERIC_HARDIRQS=y
@@ -11,6 +11,7 @@ CONFIG_HAVE_DEC_LOCK=y
CONFIG_PPC=y
CONFIG_PPC32=y
CONFIG_GENERIC_NVRAM=y
+CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
#
# Code maturity level options
@@ -18,6 +19,7 @@ CONFIG_GENERIC_NVRAM=y
CONFIG_EXPERIMENTAL=y
CONFIG_CLEAN_COMPILE=y
CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
#
# General setup
@@ -29,7 +31,6 @@ CONFIG_SYSVIPC=y
# CONFIG_BSD_PROCESS_ACCT is not set
CONFIG_SYSCTL=y
# CONFIG_AUDIT is not set
-CONFIG_LOG_BUF_SHIFT=14
CONFIG_HOTPLUG=y
CONFIG_KOBJECT_UEVENT=y
# CONFIG_IKCONFIG is not set
@@ -37,6 +38,9 @@ CONFIG_EMBEDDED=y
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
@@ -46,6 +50,7 @@ CONFIG_CC_ALIGN_LABELS=0
CONFIG_CC_ALIGN_LOOPS=0
CONFIG_CC_ALIGN_JUMPS=0
# CONFIG_TINY_SHMEM is not set
+CONFIG_BASE_SMALL=0
#
# Loadable module support
@@ -69,9 +74,11 @@ CONFIG_KMOD=y
CONFIG_E500=y
CONFIG_BOOKE=y
CONFIG_FSL_BOOKE=y
+# CONFIG_PHYS_64BIT is not set
# CONFIG_SPE is not set
CONFIG_MATH_EMULATION=y
# CONFIG_CPU_FREQ is not set
+# CONFIG_PM is not set
CONFIG_85xx=y
CONFIG_PPC_INDIRECT_PCI_BE=y
@@ -96,6 +103,7 @@ CONFIG_HIGHMEM=y
CONFIG_BINFMT_ELF=y
CONFIG_BINFMT_MISC=m
# CONFIG_CMDLINE_BOOL is not set
+CONFIG_ISA_DMA_API=y
#
# Bus options
@@ -104,15 +112,15 @@ CONFIG_PCI=y
CONFIG_PCI_DOMAINS=y
# CONFIG_PCI_LEGACY_PROC is not set
# CONFIG_PCI_NAMES is not set
+# CONFIG_PCI_DEBUG is not set
#
# PCCARD (PCMCIA/CardBus) support
#
# CONFIG_PCCARD is not set
-
-#
-# PC-card bridges
-#
+CONFIG_RAPIDIO=y
+CONFIG_RAPIDIO_8_BIT_TRANSPORT=y
+CONFIG_RAPIDIO_DISC_TIMEOUT=30
#
# Advanced setup
@@ -152,7 +160,7 @@ CONFIG_PARPORT=m
CONFIG_PARPORT_PC=m
# CONFIG_PARPORT_PC_FIFO is not set
# CONFIG_PARPORT_PC_SUPERIO is not set
-# CONFIG_PARPORT_OTHER is not set
+# CONFIG_PARPORT_GSC is not set
# CONFIG_PARPORT_1284 is not set
#
@@ -264,7 +272,6 @@ CONFIG_SCSI_CONSTANTS=y
# CONFIG_SCSI_BUSLOGIC is not set
# CONFIG_SCSI_DMX3191D is not set
# CONFIG_SCSI_EATA is not set
-# CONFIG_SCSI_EATA_PIO is not set
# CONFIG_SCSI_FUTURE_DOMAIN is not set
# CONFIG_SCSI_GDTH is not set
# CONFIG_SCSI_IPS is not set
@@ -274,7 +281,6 @@ CONFIG_SCSI_CONSTANTS=y
# CONFIG_SCSI_IMM is not set
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
-# CONFIG_SCSI_QLOGIC_ISP is not set
# CONFIG_SCSI_QLOGIC_FC is not set
# CONFIG_SCSI_QLOGIC_1280 is not set
CONFIG_SCSI_QLA2XXX=m
@@ -283,6 +289,7 @@ CONFIG_SCSI_QLA2XXX=m
# CONFIG_SCSI_QLA2300 is not set
# CONFIG_SCSI_QLA2322 is not set
# CONFIG_SCSI_QLA6312 is not set
+# CONFIG_SCSI_LPFC is not set
# CONFIG_SCSI_DC395x is not set
# CONFIG_SCSI_DC390T is not set
# CONFIG_SCSI_NSP32 is not set
@@ -322,7 +329,6 @@ CONFIG_NET=y
#
CONFIG_PACKET=y
# CONFIG_PACKET_MMAP is not set
-# CONFIG_NETLINK_DEV is not set
CONFIG_UNIX=y
# CONFIG_NET_KEY is not set
CONFIG_INET=y
@@ -431,7 +437,7 @@ CONFIG_IP_NF_NAT_FTP=m
#
# Network testing
#
-# CONFIG_NET_PKTGEN is not set
+CONFIG_NET_PKTGEN=y
# CONFIG_NETPOLL is not set
# CONFIG_NET_POLL_CONTROLLER is not set
# CONFIG_HAMRADIO is not set
@@ -499,6 +505,7 @@ CONFIG_GFAR_NAPI=y
# Wan interfaces
#
# CONFIG_WAN is not set
+CONFIG_RIONET=y
# CONFIG_FDDI is not set
# CONFIG_HIPPI is not set
# CONFIG_PLIP is not set
@@ -535,20 +542,6 @@ CONFIG_INPUT_JOYDEV=m
CONFIG_INPUT_EVDEV=m
# CONFIG_INPUT_EVBUG is not set
-#
-# Input I/O drivers
-#
-# CONFIG_GAMEPORT is not set
-CONFIG_SOUND_GAMEPORT=y
-CONFIG_SERIO=y
-CONFIG_SERIO_I8042=y
-CONFIG_SERIO_SERPORT=y
-# CONFIG_SERIO_CT82C710 is not set
-# CONFIG_SERIO_PARKBD is not set
-# CONFIG_SERIO_PCIPS2 is not set
-CONFIG_SERIO_LIBPS2=y
-# CONFIG_SERIO_RAW is not set
-
#
# Input Device Drivers
#
@@ -566,6 +559,19 @@ CONFIG_MOUSE_PS2=y
# CONFIG_INPUT_TOUCHSCREEN is not set
# CONFIG_INPUT_MISC is not set
+#
+# Hardware I/O ports
+#
+CONFIG_SERIO=y
+CONFIG_SERIO_I8042=y
+CONFIG_SERIO_SERPORT=y
+# CONFIG_SERIO_PARKBD is not set
+# CONFIG_SERIO_PCIPS2 is not set
+CONFIG_SERIO_LIBPS2=y
+# CONFIG_SERIO_RAW is not set
+# CONFIG_GAMEPORT is not set
+CONFIG_SOUND_GAMEPORT=y
+
#
# Character devices
#
@@ -590,6 +596,7 @@ CONFIG_SERIAL_CPM_SCC2=y
# CONFIG_SERIAL_CPM_SCC4 is not set
# CONFIG_SERIAL_CPM_SMC1 is not set
# CONFIG_SERIAL_CPM_SMC2 is not set
+# CONFIG_SERIAL_JSM is not set
CONFIG_UNIX98_PTYS=y
CONFIG_LEGACY_PTYS=y
CONFIG_LEGACY_PTY_COUNT=256
@@ -625,6 +632,11 @@ CONFIG_DRM=m
# CONFIG_DRM_SIS is not set
# CONFIG_RAW_DRIVER is not set
+#
+# TPM devices
+#
+# CONFIG_TCG_TPM is not set
+
#
# I2C support
#
@@ -648,12 +660,12 @@ CONFIG_I2C_ALGOBIT=m
# CONFIG_I2C_AMD8111 is not set
# CONFIG_I2C_I801 is not set
# CONFIG_I2C_I810 is not set
+# CONFIG_I2C_PIIX4 is not set
# CONFIG_I2C_ISA is not set
# CONFIG_I2C_MPC is not set
# CONFIG_I2C_NFORCE2 is not set
# CONFIG_I2C_PARPORT is not set
# CONFIG_I2C_PARPORT_LIGHT is not set
-# CONFIG_I2C_PIIX4 is not set
# CONFIG_I2C_PROSAVAGE is not set
# CONFIG_I2C_SAVAGE4 is not set
# CONFIG_SCx200_ACB is not set
@@ -677,7 +689,9 @@ CONFIG_I2C_ALGOBIT=m
# CONFIG_SENSORS_ASB100 is not set
# CONFIG_SENSORS_DS1621 is not set
# CONFIG_SENSORS_FSCHER is not set
+# CONFIG_SENSORS_FSCPOS is not set
# CONFIG_SENSORS_GL518SM is not set
+# CONFIG_SENSORS_GL520SM is not set
# CONFIG_SENSORS_IT87 is not set
# CONFIG_SENSORS_LM63 is not set
# CONFIG_SENSORS_LM75 is not set
@@ -688,9 +702,11 @@ CONFIG_I2C_ALGOBIT=m
# CONFIG_SENSORS_LM85 is not set
# CONFIG_SENSORS_LM87 is not set
# CONFIG_SENSORS_LM90 is not set
+# CONFIG_SENSORS_LM92 is not set
# CONFIG_SENSORS_MAX1619 is not set
# CONFIG_SENSORS_PC87360 is not set
# CONFIG_SENSORS_SMSC47B397 is not set
+# CONFIG_SENSORS_SIS5595 is not set
# CONFIG_SENSORS_SMSC47M1 is not set
# CONFIG_SENSORS_VIA686A is not set
# CONFIG_SENSORS_W83781D is not set
@@ -700,10 +716,12 @@ CONFIG_I2C_ALGOBIT=m
#
# Other I2C Chip support
#
+# CONFIG_SENSORS_DS1337 is not set
# CONFIG_SENSORS_EEPROM is not set
# CONFIG_SENSORS_PCF8574 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_RTC8564 is not set
+# CONFIG_SENSORS_M41T00 is not set
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
@@ -732,7 +750,6 @@ CONFIG_I2C_ALGOBIT=m
# Graphics support
#
# CONFIG_FB is not set
-# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
#
# Sound
@@ -752,13 +769,9 @@ CONFIG_SOUND=m
#
# USB support
#
-# CONFIG_USB is not set
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB_ARCH_HAS_OHCI=y
-
-#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information
-#
+# CONFIG_USB is not set
#
# USB Gadget Support
@@ -789,6 +802,10 @@ CONFIG_JBD_DEBUG=y
CONFIG_FS_MBCACHE=y
# CONFIG_REISERFS_FS is not set
# CONFIG_JFS_FS is not set
+
+#
+# XFS support
+#
# CONFIG_XFS_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_ROMFS_FS is not set
@@ -859,7 +876,6 @@ CONFIG_NFS_V3=y
CONFIG_ROOT_NFS=y
CONFIG_LOCKD=y
CONFIG_LOCKD_V4=y
-# CONFIG_EXPORTFS is not set
CONFIG_SUNRPC=y
# CONFIG_RPCSEC_GSS_KRB5 is not set
# CONFIG_RPCSEC_GSS_SPKM3 is not set
@@ -942,8 +958,10 @@ CONFIG_ZLIB_INFLATE=m
#
# Kernel hacking
#
+# CONFIG_PRINTK_TIME is not set
CONFIG_DEBUG_KERNEL=y
# CONFIG_MAGIC_SYSRQ is not set
+CONFIG_LOG_BUF_SHIFT=14
# CONFIG_SCHEDSTATS is not set
# CONFIG_DEBUG_SLAB is not set
# CONFIG_DEBUG_SPINLOCK is not set
diff --git a/arch/ppc/kernel/Makefile b/arch/ppc/kernel/Makefile
index c610ca933a25..76a55a438f23 100644
--- a/arch/ppc/kernel/Makefile
+++ b/arch/ppc/kernel/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_POWER4) += cpu_setup_power4.o
obj-$(CONFIG_MODULES) += module.o ppc_ksyms.o
obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-mapping.o
obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_RAPIDIO) += rio.o
obj-$(CONFIG_KGDB) += ppc-stub.o
obj-$(CONFIG_SMP) += smp.o smp-tbsync.o
obj-$(CONFIG_TAU) += temp.o
diff --git a/arch/ppc/kernel/head_44x.S b/arch/ppc/kernel/head_44x.S
index 8b49679fad54..677c571aa276 100644
--- a/arch/ppc/kernel/head_44x.S
+++ b/arch/ppc/kernel/head_44x.S
@@ -190,8 +190,8 @@ skpinv: addi r4,r4,1 /* Increment */
/* xlat fields */
lis r4,UART0_PHYS_IO_BASE@h /* RPN depends on SoC */
-#ifndef CONFIG_440EP
- ori r4,r4,0x0001 /* ERPN is 1 for second 4GB page */
+#ifdef UART0_PHYS_ERPN
+ ori r4,r4,UART0_PHYS_ERPN /* Add ERPN if above 4GB */
#endif
/* attrib fields */
diff --git a/arch/ppc/kernel/rio.c b/arch/ppc/kernel/rio.c
new file mode 100644
index 000000000000..29487fedfc76
--- /dev/null
+++ b/arch/ppc/kernel/rio.c
@@ -0,0 +1,52 @@
+/*
+ * RapidIO PPC32 support
+ *
+ * Copyright 2005 MontaVista Software, Inc.
+ * Matt Porter
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include
+#include
+#include
+
+#include
+
+/**
+ * platform_rio_init - Do platform specific RIO init
+ *
+ * Any platform specific initialization of RapdIO
+ * hardware is done here as well as registration
+ * of any active master ports in the system.
+ */
+void __attribute__ ((weak))
+ platform_rio_init(void)
+{
+ printk(KERN_WARNING "RIO: No platform_rio_init() present\n");
+}
+
+/**
+ * ppc_rio_init - Do PPC32 RIO init
+ *
+ * Calls platform-specific RIO init code and then calls
+ * rio_init_mports() to initialize any master ports that
+ * have been registered with the RIO subsystem.
+ */
+static int __init ppc_rio_init(void)
+{
+ printk(KERN_INFO "RIO: RapidIO init\n");
+
+ /* Platform specific initialization */
+ platform_rio_init();
+
+ /* Enumerate all registered ports */
+ rio_init_mports();
+
+ return 0;
+}
+
+subsys_initcall(ppc_rio_init);
diff --git a/arch/ppc/platforms/4xx/Kconfig b/arch/ppc/platforms/4xx/Kconfig
index 76f4476cab44..d8837911bbc6 100644
--- a/arch/ppc/platforms/4xx/Kconfig
+++ b/arch/ppc/platforms/4xx/Kconfig
@@ -82,6 +82,12 @@ config LUAN
help
This option enables support for the IBM PPC440SP evaluation board.
+config YUCCA
+ bool "Yucca"
+ select WANT_EARLY_SERIAL
+ help
+ This option enables support for the AMCC PPC440SPe evaluation board.
+
config OCOTEA
bool "Ocotea"
select WANT_EARLY_SERIAL
@@ -124,9 +130,14 @@ config 440SP
depends on LUAN
default y
+config 440SPE
+ bool
+ depends on YUCCA
+ default y
+
config 440
bool
- depends on 440GP || 440SP || 440EP
+ depends on 440GP || 440SP || 440SPE || 440EP
default y
config 440A
@@ -158,7 +169,7 @@ config BOOKE
config IBM_OCP
bool
- depends on ASH || BAMBOO || BUBINGA || CPCI405 || EBONY || EP405 || LUAN || OCOTEA || REDWOOD_5 || REDWOOD_6 || SYCAMORE || WALNUT
+ depends on ASH || BAMBOO || BUBINGA || CPCI405 || EBONY || EP405 || LUAN || YUCCA || OCOTEA || REDWOOD_5 || REDWOOD_6 || SYCAMORE || WALNUT
default y
config XILINX_OCP
@@ -168,7 +179,7 @@ config XILINX_OCP
config IBM_EMAC4
bool
- depends on 440GX || 440SP
+ depends on 440GX || 440SP || 440SPE
default y
config BIOS_FIXUP
@@ -214,7 +225,7 @@ config EMBEDDEDBOOT
config IBM_OPENBIOS
bool
- depends on ASH || BUBINGA || REDWOOD_5 || REDWOOD_6 || SYCAMORE || WALNUT
+ depends on ASH || REDWOOD_5 || REDWOOD_6
default y
config PPC4xx_DMA
diff --git a/arch/ppc/platforms/4xx/Makefile b/arch/ppc/platforms/4xx/Makefile
index 1dd6d7fd6a9a..c9bb61170954 100644
--- a/arch/ppc/platforms/4xx/Makefile
+++ b/arch/ppc/platforms/4xx/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_EBONY) += ebony.o
obj-$(CONFIG_EP405) += ep405.o
obj-$(CONFIG_BUBINGA) += bubinga.o
obj-$(CONFIG_LUAN) += luan.o
+obj-$(CONFIG_YUCCA) += yucca.o
obj-$(CONFIG_OCOTEA) += ocotea.o
obj-$(CONFIG_REDWOOD_5) += redwood5.o
obj-$(CONFIG_REDWOOD_6) += redwood6.o
@@ -22,6 +23,7 @@ obj-$(CONFIG_440EP) += ibm440ep.o
obj-$(CONFIG_440GP) += ibm440gp.o
obj-$(CONFIG_440GX) += ibm440gx.o
obj-$(CONFIG_440SP) += ibm440sp.o
+obj-$(CONFIG_440SPE) += ppc440spe.o
obj-$(CONFIG_405EP) += ibm405ep.o
obj-$(CONFIG_405GPR) += ibm405gpr.o
obj-$(CONFIG_VIRTEX_II_PRO) += virtex-ii_pro.o
diff --git a/arch/ppc/platforms/4xx/bubinga.c b/arch/ppc/platforms/4xx/bubinga.c
index 3678abf86313..8110f55668c5 100644
--- a/arch/ppc/platforms/4xx/bubinga.c
+++ b/arch/ppc/platforms/4xx/bubinga.c
@@ -89,7 +89,7 @@ bubinga_early_serial_map(void)
* by 16.
*/
uart_div = (mfdcr(DCRN_CPC0_UCR_BASE) & DCRN_CPC0_UCR_U0DIV);
- uart_clock = __res.bi_pllouta_freq / uart_div;
+ uart_clock = __res.bi_procfreq / uart_div;
/* Setup serial port access */
memset(&port, 0, sizeof(port));
diff --git a/arch/ppc/platforms/4xx/bubinga.h b/arch/ppc/platforms/4xx/bubinga.h
index b1df856f8e22..b5380cfaf5c0 100644
--- a/arch/ppc/platforms/4xx/bubinga.h
+++ b/arch/ppc/platforms/4xx/bubinga.h
@@ -1,52 +1,34 @@
/*
- * Support for IBM PPC 405EP evaluation board (Bubinga).
+ * arch/ppc/platforms/4xx/bubinga.h
*
- * Author: SAW (IBM), derived from walnut.h.
- * Maintained by MontaVista Software
+ * Bubinga board definitions
+ *
+ * Copyright (c) 2005 DENX Software Engineering
+ * Stefan Roese
+ *
+ * Based on original work by
+ * SAW (IBM)
+ * 2003 (c) MontaVista Softare Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
*
- * 2003 (c) MontaVista Softare Inc. This file is licensed under the
- * terms of the GNU General Public License version 2. This program is
- * licensed "as is" without any warranty of any kind, whether express
- * or implied.
*/
#ifdef __KERNEL__
#ifndef __BUBINGA_H__
#define __BUBINGA_H__
-/* 405EP */
+#include
#include
-
-#ifndef __ASSEMBLY__
-/*
- * Data structure defining board information maintained by the boot
- * ROM on IBM's evaluation board. An effort has been made to
- * keep the field names consistent with the 8xx 'bd_t' board info
- * structures.
- */
-
-typedef struct board_info {
- unsigned char bi_s_version[4]; /* Version of this structure */
- unsigned char bi_r_version[30]; /* Version of the IBM ROM */
- unsigned int bi_memsize; /* DRAM installed, in bytes */
- unsigned char bi_enetaddr[2][6]; /* Local Ethernet MAC address */ unsigned char bi_pci_enetaddr[6]; /* PCI Ethernet MAC address */
- unsigned int bi_intfreq; /* Processor speed, in Hz */
- unsigned int bi_busfreq; /* PLB Bus speed, in Hz */
- unsigned int bi_pci_busfreq; /* PCI Bus speed, in Hz */
- unsigned int bi_opb_busfreq; /* OPB Bus speed, in Hz */
- unsigned int bi_pllouta_freq; /* PLL OUTA speed, in Hz */
-} bd_t;
-
-/* Some 4xx parts use a different timebase frequency from the internal clock.
-*/
-#define bi_tbfreq bi_intfreq
-
+#include
/* Memory map for the Bubinga board.
* Generic 4xx plus RTC.
*/
-extern void *bubinga_rtc_base;
#define BUBINGA_RTC_PADDR ((uint)0xf0000000)
#define BUBINGA_RTC_VADDR BUBINGA_RTC_PADDR
#define BUBINGA_RTC_SIZE ((uint)8*1024)
@@ -58,12 +40,18 @@ extern void *bubinga_rtc_base;
* for typical configurations at various CPU speeds.
* The base baud is calculated as (FWDA / EXT UART DIV / 16)
*/
-#define BASE_BAUD 0
+#define BASE_BAUD 0
-#define BUBINGA_FPGA_BASE 0xF0300000
+/* Flash */
+#define PPC40x_FPGA_BASE 0xF0300000
+#define PPC40x_FPGA_REG_OFFS 1 /* offset to flash map reg */
+#define PPC40x_FLASH_ONBD_N(x) (x & 0x02)
+#define PPC40x_FLASH_SRAM_SEL(x) (x & 0x01)
+#define PPC40x_FLASH_LOW 0xFFF00000
+#define PPC40x_FLASH_HIGH 0xFFF80000
+#define PPC40x_FLASH_SIZE 0x80000
-#define PPC4xx_MACHINE_NAME "IBM Bubinga"
+#define PPC4xx_MACHINE_NAME "IBM Bubinga"
-#endif /* !__ASSEMBLY__ */
#endif /* __BUBINGA_H__ */
#endif /* __KERNEL__ */
diff --git a/arch/ppc/platforms/4xx/ebony.h b/arch/ppc/platforms/4xx/ebony.h
index d08faa46a0ae..b91ad4272dfe 100644
--- a/arch/ppc/platforms/4xx/ebony.h
+++ b/arch/ppc/platforms/4xx/ebony.h
@@ -24,8 +24,8 @@
#define PPC44x_EMAC0_MR0 0xE0000800
/* Where to find the MAC info */
-#define EBONY_OPENBIOS_MAC_BASE 0xfffffe0c
-#define EBONY_OPENBIOS_MAC_OFFSET 0x0c
+#define OPENBIOS_MAC_BASE 0xfffffe0c
+#define OPENBIOS_MAC_OFFSET 0x0c
/* Default clock rates for Rev. B and Rev. C silicon */
#define EBONY_440GP_RB_SYSCLK 33000000
diff --git a/arch/ppc/platforms/4xx/ppc440spe.c b/arch/ppc/platforms/4xx/ppc440spe.c
new file mode 100644
index 000000000000..6139a0b3393e
--- /dev/null
+++ b/arch/ppc/platforms/4xx/ppc440spe.c
@@ -0,0 +1,148 @@
+/*
+ * arch/ppc/platforms/4xx/ppc440spe.c
+ *
+ * PPC440SPe I/O descriptions
+ *
+ * Roland Dreier
+ * Copyright (c) 2005 Cisco Systems. All rights reserved.
+ *
+ * Matt Porter
+ * Copyright 2002-2005 MontaVista Software Inc.
+ *
+ * Eugene Surovegin or
+ * Copyright (c) 2003, 2004 Zultys Technologies
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ */
+#include
+#include
+#include
+#include
+#include
+
+static struct ocp_func_emac_data ppc440spe_emac0_def = {
+ .rgmii_idx = -1, /* No RGMII */
+ .rgmii_mux = -1, /* No RGMII */
+ .zmii_idx = -1, /* No ZMII */
+ .zmii_mux = -1, /* No ZMII */
+ .mal_idx = 0, /* MAL device index */
+ .mal_rx_chan = 0, /* MAL rx channel number */
+ .mal_tx_chan = 0, /* MAL tx channel number */
+ .wol_irq = 61, /* WOL interrupt number */
+ .mdio_idx = -1, /* No shared MDIO */
+ .tah_idx = -1, /* No TAH */
+};
+OCP_SYSFS_EMAC_DATA()
+
+static struct ocp_func_mal_data ppc440spe_mal0_def = {
+ .num_tx_chans = 1, /* Number of TX channels */
+ .num_rx_chans = 1, /* Number of RX channels */
+ .txeob_irq = 38, /* TX End Of Buffer IRQ */
+ .rxeob_irq = 39, /* RX End Of Buffer IRQ */
+ .txde_irq = 34, /* TX Descriptor Error IRQ */
+ .rxde_irq = 35, /* RX Descriptor Error IRQ */
+ .serr_irq = 33, /* MAL System Error IRQ */
+ .dcr_base = DCRN_MAL_BASE /* MAL0_CFG DCR number */
+};
+OCP_SYSFS_MAL_DATA()
+
+static struct ocp_func_iic_data ppc440spe_iic0_def = {
+ .fast_mode = 0, /* Use standad mode (100Khz) */
+};
+
+static struct ocp_func_iic_data ppc440spe_iic1_def = {
+ .fast_mode = 0, /* Use standad mode (100Khz) */
+};
+OCP_SYSFS_IIC_DATA()
+
+struct ocp_def core_ocp[] = {
+ { .vendor = OCP_VENDOR_IBM,
+ .function = OCP_FUNC_16550,
+ .index = 0,
+ .paddr = PPC440SPE_UART0_ADDR,
+ .irq = UART0_INT,
+ .pm = IBM_CPM_UART0,
+ },
+ { .vendor = OCP_VENDOR_IBM,
+ .function = OCP_FUNC_16550,
+ .index = 1,
+ .paddr = PPC440SPE_UART1_ADDR,
+ .irq = UART1_INT,
+ .pm = IBM_CPM_UART1,
+ },
+ { .vendor = OCP_VENDOR_IBM,
+ .function = OCP_FUNC_16550,
+ .index = 2,
+ .paddr = PPC440SPE_UART2_ADDR,
+ .irq = UART2_INT,
+ .pm = IBM_CPM_UART2,
+ },
+ { .vendor = OCP_VENDOR_IBM,
+ .function = OCP_FUNC_IIC,
+ .index = 0,
+ .paddr = 0x00000004f0000400ULL,
+ .irq = 2,
+ .pm = IBM_CPM_IIC0,
+ .additions = &ppc440spe_iic0_def,
+ .show = &ocp_show_iic_data
+ },
+ { .vendor = OCP_VENDOR_IBM,
+ .function = OCP_FUNC_IIC,
+ .index = 1,
+ .paddr = 0x00000004f0000500ULL,
+ .irq = 3,
+ .pm = IBM_CPM_IIC1,
+ .additions = &ppc440spe_iic1_def,
+ .show = &ocp_show_iic_data
+ },
+ { .vendor = OCP_VENDOR_IBM,
+ .function = OCP_FUNC_GPIO,
+ .index = 0,
+ .paddr = 0x00000004f0000700ULL,
+ .irq = OCP_IRQ_NA,
+ .pm = IBM_CPM_GPIO0,
+ },
+ { .vendor = OCP_VENDOR_IBM,
+ .function = OCP_FUNC_MAL,
+ .paddr = OCP_PADDR_NA,
+ .irq = OCP_IRQ_NA,
+ .pm = OCP_CPM_NA,
+ .additions = &ppc440spe_mal0_def,
+ .show = &ocp_show_mal_data,
+ },
+ { .vendor = OCP_VENDOR_IBM,
+ .function = OCP_FUNC_EMAC,
+ .index = 0,
+ .paddr = 0x00000004f0000800ULL,
+ .irq = 60,
+ .pm = OCP_CPM_NA,
+ .additions = &ppc440spe_emac0_def,
+ .show = &ocp_show_emac_data,
+ },
+ { .vendor = OCP_VENDOR_INVALID
+ }
+};
+
+/* Polarity and triggering settings for internal interrupt sources */
+struct ppc4xx_uic_settings ppc4xx_core_uic_cfg[] __initdata = {
+ { .polarity = 0xffffffff,
+ .triggering = 0x010f0004,
+ .ext_irq_mask = 0x00000000,
+ },
+ { .polarity = 0xffffffff,
+ .triggering = 0x001f8040,
+ .ext_irq_mask = 0x00007c30, /* IRQ6 - IRQ7, IRQ8 - IRQ12 */
+ },
+ { .polarity = 0xffffffff,
+ .triggering = 0x00000000,
+ .ext_irq_mask = 0x000000fc, /* IRQ0 - IRQ5 */
+ },
+ { .polarity = 0xffffffff,
+ .triggering = 0x00000000,
+ .ext_irq_mask = 0x00000000,
+ },
+};
diff --git a/arch/ppc/platforms/4xx/ppc440spe.h b/arch/ppc/platforms/4xx/ppc440spe.h
new file mode 100644
index 000000000000..2216846973b8
--- /dev/null
+++ b/arch/ppc/platforms/4xx/ppc440spe.h
@@ -0,0 +1,66 @@
+/*
+ * arch/ppc/platforms/4xx/ibm440spe.h
+ *
+ * PPC440SPe definitions
+ *
+ * Roland Dreier
+ * Copyright (c) 2005 Cisco Systems. All rights reserved.
+ *
+ * Matt Porter
+ * Copyright 2004-2005 MontaVista Software, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifdef __KERNEL__
+#ifndef __PPC_PLATFORMS_PPC440SPE_H
+#define __PPC_PLATFORMS_PPC440SPE_H
+
+#include
+
+#include
+
+/* UART */
+#define PPC440SPE_UART0_ADDR 0x00000004f0000200ULL
+#define PPC440SPE_UART1_ADDR 0x00000004f0000300ULL
+#define PPC440SPE_UART2_ADDR 0x00000004f0000600ULL
+#define UART0_INT 0
+#define UART1_INT 1
+#define UART2_INT 37
+
+/* Clock and Power Management */
+#define IBM_CPM_IIC0 0x80000000 /* IIC interface */
+#define IBM_CPM_IIC1 0x40000000 /* IIC interface */
+#define IBM_CPM_PCI 0x20000000 /* PCI bridge */
+#define IBM_CPM_CPU 0x02000000 /* processor core */
+#define IBM_CPM_DMA 0x01000000 /* DMA controller */
+#define IBM_CPM_BGO 0x00800000 /* PLB to OPB bus arbiter */
+#define IBM_CPM_BGI 0x00400000 /* OPB to PLB bridge */
+#define IBM_CPM_EBC 0x00200000 /* External Bux Controller */
+#define IBM_CPM_EBM 0x00100000 /* Ext Bus Master Interface */
+#define IBM_CPM_DMC 0x00080000 /* SDRAM peripheral controller */
+#define IBM_CPM_PLB 0x00040000 /* PLB bus arbiter */
+#define IBM_CPM_SRAM 0x00020000 /* SRAM memory controller */
+#define IBM_CPM_PPM 0x00002000 /* PLB Performance Monitor */
+#define IBM_CPM_UIC1 0x00001000 /* Universal Interrupt Controller */
+#define IBM_CPM_GPIO0 0x00000800 /* General Purpose IO (??) */
+#define IBM_CPM_GPT 0x00000400 /* General Purpose Timers */
+#define IBM_CPM_UART0 0x00000200 /* serial port 0 */
+#define IBM_CPM_UART1 0x00000100 /* serial port 1 */
+#define IBM_CPM_UART2 0x00000100 /* serial port 1 */
+#define IBM_CPM_UIC0 0x00000080 /* Universal Interrupt Controller */
+#define IBM_CPM_TMRCLK 0x00000040 /* CPU timers */
+#define IBM_CPM_EMAC0 0x00000020 /* EMAC 0 */
+
+#define DFLT_IBM4xx_PM ~(IBM_CPM_UIC | IBM_CPM_UIC1 | IBM_CPM_CPU \
+ | IBM_CPM_EBC | IBM_CPM_SRAM | IBM_CPM_BGO \
+ | IBM_CPM_EBM | IBM_CPM_PLB | IBM_CPM_OPB \
+ | IBM_CPM_TMRCLK | IBM_CPM_DMA | IBM_CPM_PCI \
+ | IBM_CPM_TAHOE0 | IBM_CPM_TAHOE1 \
+ | IBM_CPM_EMAC0 | IBM_CPM_EMAC1 \
+ | IBM_CPM_EMAC2 | IBM_CPM_EMAC3 )
+#endif /* __PPC_PLATFORMS_PPC440SP_H */
+#endif /* __KERNEL__ */
diff --git a/arch/ppc/platforms/4xx/sycamore.c b/arch/ppc/platforms/4xx/sycamore.c
index d8019eec4704..281b4a2ffb96 100644
--- a/arch/ppc/platforms/4xx/sycamore.c
+++ b/arch/ppc/platforms/4xx/sycamore.c
@@ -88,9 +88,6 @@ ppc405_map_irq(struct pci_dev *dev, unsigned char idsel, unsigned char pin)
void __init
sycamore_setup_arch(void)
{
-#define SYCAMORE_PS2_BASE 0xF0100000
-#define SYCAMORE_FPGA_BASE 0xF0300000
-
void *fpga_brdc;
unsigned char fpga_brdc_data;
void *fpga_enable;
@@ -100,7 +97,7 @@ sycamore_setup_arch(void)
ppc4xx_setup_arch();
- ibm_ocp_set_emac(0, 1);
+ ibm_ocp_set_emac(0, 0);
kb_data = ioremap(SYCAMORE_PS2_BASE, 8);
if (!kb_data) {
@@ -111,7 +108,7 @@ sycamore_setup_arch(void)
kb_cs = kb_data + 1;
- fpga_status = ioremap(SYCAMORE_FPGA_BASE, 8);
+ fpga_status = ioremap(PPC40x_FPGA_BASE, 8);
if (!fpga_status) {
printk(KERN_CRIT
"sycamore_setup_arch() fpga_status ioremap failed\n");
diff --git a/arch/ppc/platforms/4xx/sycamore.h b/arch/ppc/platforms/4xx/sycamore.h
index 3e7b4e2c8c57..1cd6c824fd62 100644
--- a/arch/ppc/platforms/4xx/sycamore.h
+++ b/arch/ppc/platforms/4xx/sycamore.h
@@ -1,67 +1,52 @@
/*
* arch/ppc/platforms/4xx/sycamore.h
*
- * Macros, definitions, and data structures specific to the IBM PowerPC
- * 405GPr "Sycamore" evaluation board.
+ * Sycamore board definitions
*
- * Author: Armin Kuster
+ * Copyright (c) 2005 DENX Software Engineering
+ * Stefan Roese
+ *
+ * Based on original work by
+ * Armin Kuster
+ * 2000 (c) MontaVista, Software, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
*
- * 2000 (c) MontaVista, Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
*/
#ifdef __KERNEL__
#ifndef __ASM_SYCAMORE_H__
#define __ASM_SYCAMORE_H__
+#include
#include
+#include
-#ifndef __ASSEMBLY__
-/*
- * Data structure defining board information maintained by the boot
- * ROM on IBM's "Sycamore" evaluation board. An effort has been made to
- * keep the field names consistent with the 8xx 'bd_t' board info
- * structures.
- */
-
-typedef struct board_info {
- unsigned char bi_s_version[4]; /* Version of this structure */
- unsigned char bi_r_version[30]; /* Version of the IBM ROM */
- unsigned int bi_memsize; /* DRAM installed, in bytes */
- unsigned char bi_enetaddr[6]; /* Local Ethernet MAC address */
- unsigned char bi_pci_enetaddr[6]; /* PCI Ethernet MAC address */
- unsigned int bi_intfreq; /* Processor speed, in Hz */
- unsigned int bi_busfreq; /* PLB Bus speed, in Hz */
- unsigned int bi_pci_busfreq; /* PCI Bus speed, in Hz */
-} bd_t;
-
-/* Some 4xx parts use a different timebase frequency from the internal clock.
-*/
-#define bi_tbfreq bi_intfreq
-
-
-/* Memory map for the IBM "Sycamore" 405GP evaluation board.
+/* Memory map for the IBM "Sycamore" 405GPr evaluation board.
* Generic 4xx plus RTC.
*/
-extern void *sycamore_rtc_base;
#define SYCAMORE_RTC_PADDR ((uint)0xf0000000)
#define SYCAMORE_RTC_VADDR SYCAMORE_RTC_PADDR
-#define SYCAMORE_RTC_SIZE ((uint)8*1024)
+#define SYCAMORE_RTC_SIZE ((uint)8*1024)
-#ifdef CONFIG_PPC405GP_INTERNAL_CLOCK
-#define BASE_BAUD 201600
-#else
#define BASE_BAUD 691200
-#endif
-#define SYCAMORE_PS2_BASE 0xF0100000
-#define SYCAMORE_FPGA_BASE 0xF0300000
+#define SYCAMORE_PS2_BASE 0xF0100000
+
+/* Flash */
+#define PPC40x_FPGA_BASE 0xF0300000
+#define PPC40x_FPGA_REG_OFFS 5 /* offset to flash map reg */
+#define PPC40x_FLASH_ONBD_N(x) (x & 0x02)
+#define PPC40x_FLASH_SRAM_SEL(x) (x & 0x01)
+#define PPC40x_FLASH_LOW 0xFFF00000
+#define PPC40x_FLASH_HIGH 0xFFF80000
+#define PPC40x_FLASH_SIZE 0x80000
#define PPC4xx_MACHINE_NAME "IBM Sycamore"
-#endif /* !__ASSEMBLY__ */
#endif /* __ASM_SYCAMORE_H__ */
#endif /* __KERNEL__ */
diff --git a/arch/ppc/platforms/4xx/walnut.c b/arch/ppc/platforms/4xx/walnut.c
index a33eda4b7489..74cb33182d9f 100644
--- a/arch/ppc/platforms/4xx/walnut.c
+++ b/arch/ppc/platforms/4xx/walnut.c
@@ -90,7 +90,7 @@ walnut_setup_arch(void)
kb_cs = kb_data + 1;
- fpga_status = ioremap(WALNUT_FPGA_BASE, 8);
+ fpga_status = ioremap(PPC40x_FPGA_BASE, 8);
if (!fpga_status) {
printk(KERN_CRIT
"walnut_setup_arch() fpga_status ioremap failed\n");
diff --git a/arch/ppc/platforms/4xx/walnut.h b/arch/ppc/platforms/4xx/walnut.h
index 04cfbf3696b9..dcf2691698c0 100644
--- a/arch/ppc/platforms/4xx/walnut.h
+++ b/arch/ppc/platforms/4xx/walnut.h
@@ -1,72 +1,55 @@
/*
* arch/ppc/platforms/4xx/walnut.h
*
- * Macros, definitions, and data structures specific to the IBM PowerPC
- * 405GP "Walnut" evaluation board.
+ * Walnut board definitions
*
- * Authors: Grant Erickson , Frank Rowand
- * , Debbie Chu or
- * source@mvista.com
+ * Copyright (c) 2005 DENX Software Engineering
+ * Stefan Roese
*
- * Copyright (c) 1999 Grant Erickson
+ * Based on original work by
+ * Copyright (c) 1999 Grant Erickson
+ * Frank Rowand
+ * Debbie Chu
+ * 2000 (c) MontaVista, Software, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
*
- * 2000 (c) MontaVista, Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
*/
#ifdef __KERNEL__
#ifndef __ASM_WALNUT_H__
#define __ASM_WALNUT_H__
-/* We have a 405GP core */
+#include
#include
-
-#ifndef __ASSEMBLY__
-/*
- * Data structure defining board information maintained by the boot
- * ROM on IBM's "Walnut" evaluation board. An effort has been made to
- * keep the field names consistent with the 8xx 'bd_t' board info
- * structures.
- */
-
-typedef struct board_info {
- unsigned char bi_s_version[4]; /* Version of this structure */
- unsigned char bi_r_version[30]; /* Version of the IBM ROM */
- unsigned int bi_memsize; /* DRAM installed, in bytes */
- unsigned char bi_enetaddr[6]; /* Local Ethernet MAC address */
- unsigned char bi_pci_enetaddr[6]; /* PCI Ethernet MAC address */
- unsigned int bi_intfreq; /* Processor speed, in Hz */
- unsigned int bi_busfreq; /* PLB Bus speed, in Hz */
- unsigned int bi_pci_busfreq; /* PCI Bus speed, in Hz */
-} bd_t;
-
-/* Some 4xx parts use a different timebase frequency from the internal clock.
-*/
-#define bi_tbfreq bi_intfreq
-
+#include
/* Memory map for the IBM "Walnut" 405GP evaluation board.
* Generic 4xx plus RTC.
*/
-extern void *walnut_rtc_base;
#define WALNUT_RTC_PADDR ((uint)0xf0000000)
#define WALNUT_RTC_VADDR WALNUT_RTC_PADDR
#define WALNUT_RTC_SIZE ((uint)8*1024)
-#ifdef CONFIG_PPC405GP_INTERNAL_CLOCK
-#define BASE_BAUD 201600
-#else
#define BASE_BAUD 691200
-#endif
#define WALNUT_PS2_BASE 0xF0100000
-#define WALNUT_FPGA_BASE 0xF0300000
+
+/* Flash */
+#define PPC40x_FPGA_BASE 0xF0300000
+#define PPC40x_FPGA_REG_OFFS 5 /* offset to flash map reg */
+#define PPC40x_FLASH_ONBD_N(x) (x & 0x02)
+#define PPC40x_FLASH_SRAM_SEL(x) (x & 0x01)
+#define PPC40x_FLASH_LOW 0xFFF00000
+#define PPC40x_FLASH_HIGH 0xFFF80000
+#define PPC40x_FLASH_SIZE 0x80000
+#define WALNUT_FPGA_BASE PPC40x_FPGA_BASE
#define PPC4xx_MACHINE_NAME "IBM Walnut"
-#endif /* !__ASSEMBLY__ */
#endif /* __ASM_WALNUT_H__ */
#endif /* __KERNEL__ */
diff --git a/arch/ppc/platforms/4xx/yucca.c b/arch/ppc/platforms/4xx/yucca.c
new file mode 100644
index 000000000000..e60f4bd437ec
--- /dev/null
+++ b/arch/ppc/platforms/4xx/yucca.c
@@ -0,0 +1,395 @@
+/*
+ * arch/ppc/platforms/4xx/yucca.c
+ *
+ * Yucca board specific routines
+ *
+ * Roland Dreier (based on luan.c by Matt Porter)
+ *
+ * Copyright 2004-2005 MontaVista Software Inc.
+ * Copyright (c) 2005 Cisco Systems. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+#include
+
+extern bd_t __res;
+
+static struct ibm44x_clocks clocks __initdata;
+
+static void __init
+yucca_calibrate_decr(void)
+{
+ unsigned int freq;
+
+ if (mfspr(SPRN_CCR1) & CCR1_TCS)
+ freq = YUCCA_TMR_CLK;
+ else
+ freq = clocks.cpu;
+
+ ibm44x_calibrate_decr(freq);
+}
+
+static int
+yucca_show_cpuinfo(struct seq_file *m)
+{
+ seq_printf(m, "vendor\t\t: AMCC\n");
+ seq_printf(m, "machine\t\t: PPC440SPe EVB (Yucca)\n");
+
+ return 0;
+}
+
+static enum {
+ HOSE_UNKNOWN,
+ HOSE_PCIX,
+ HOSE_PCIE0,
+ HOSE_PCIE1,
+ HOSE_PCIE2
+} hose_type[4];
+
+static inline int
+yucca_map_irq(struct pci_dev *dev, unsigned char idsel, unsigned char pin)
+{
+ struct pci_controller *hose = pci_bus_to_hose(dev->bus->number);
+
+ if (hose_type[hose->index] == HOSE_PCIX) {
+ static char pci_irq_table[][4] =
+ /*
+ * PCI IDSEL/INTPIN->INTLINE
+ * A B C D
+ */
+ {
+ { 81, -1, -1, -1 }, /* IDSEL 1 - PCIX0 Slot 0 */
+ };
+ const long min_idsel = 1, max_idsel = 1, irqs_per_slot = 4;
+ return PCI_IRQ_TABLE_LOOKUP;
+ } else if (hose_type[hose->index] == HOSE_PCIE0) {
+ static char pci_irq_table[][4] =
+ /*
+ * PCI IDSEL/INTPIN->INTLINE
+ * A B C D
+ */
+ {
+ { 96, 97, 98, 99 },
+ };
+ const long min_idsel = 1, max_idsel = 1, irqs_per_slot = 4;
+ return PCI_IRQ_TABLE_LOOKUP;
+ } else if (hose_type[hose->index] == HOSE_PCIE1) {
+ static char pci_irq_table[][4] =
+ /*
+ * PCI IDSEL/INTPIN->INTLINE
+ * A B C D
+ */
+ {
+ { 100, 101, 102, 103 },
+ };
+ const long min_idsel = 1, max_idsel = 1, irqs_per_slot = 4;
+ return PCI_IRQ_TABLE_LOOKUP;
+ } else if (hose_type[hose->index] == HOSE_PCIE2) {
+ static char pci_irq_table[][4] =
+ /*
+ * PCI IDSEL/INTPIN->INTLINE
+ * A B C D
+ */
+ {
+ { 104, 105, 106, 107 },
+ };
+ const long min_idsel = 1, max_idsel = 1, irqs_per_slot = 4;
+ return PCI_IRQ_TABLE_LOOKUP;
+ }
+ return -1;
+}
+
+static void __init yucca_set_emacdata(void)
+{
+ struct ocp_def *def;
+ struct ocp_func_emac_data *emacdata;
+
+ /* Set phy_map, phy_mode, and mac_addr for the EMAC */
+ def = ocp_get_one_device(OCP_VENDOR_IBM, OCP_FUNC_EMAC, 0);
+ emacdata = def->additions;
+ emacdata->phy_map = 0x00000001; /* Skip 0x00 */
+ emacdata->phy_mode = PHY_MODE_GMII;
+ memcpy(emacdata->mac_addr, __res.bi_enetaddr, 6);
+}
+
+static int __init yucca_pcie_card_present(int port)
+{
+ void __iomem *pcie_fpga_base;
+ u16 reg;
+
+ pcie_fpga_base = ioremap64(YUCCA_FPGA_REG_BASE, YUCCA_FPGA_REG_SIZE);
+ reg = in_be16(pcie_fpga_base + FPGA_REG1C);
+ iounmap(pcie_fpga_base);
+
+ switch(port) {
+ case 0: return !(reg & FPGA_REG1C_PE0_PRSNT);
+ case 1: return !(reg & FPGA_REG1C_PE1_PRSNT);
+ case 2: return !(reg & FPGA_REG1C_PE2_PRSNT);
+ default: return 0;
+ }
+}
+
+/*
+ * For the given slot, set rootpoint mode, send power to the slot,
+ * turn on the green LED and turn off the yellow LED, enable the clock
+ * and turn off reset.
+ */
+static void __init yucca_setup_pcie_fpga_rootpoint(int port)
+{
+ void __iomem *pcie_reg_fpga_base;
+ u16 power, clock, green_led, yellow_led, reset_off, rootpoint, endpoint;
+
+ pcie_reg_fpga_base = ioremap64(YUCCA_FPGA_REG_BASE, YUCCA_FPGA_REG_SIZE);
+
+ switch(port) {
+ case 0:
+ rootpoint = FPGA_REG1C_PE0_ROOTPOINT;
+ endpoint = 0;
+ power = FPGA_REG1A_PE0_PWRON;
+ green_led = FPGA_REG1A_PE0_GLED;
+ clock = FPGA_REG1A_PE0_REFCLK_ENABLE;
+ yellow_led = FPGA_REG1A_PE0_YLED;
+ reset_off = FPGA_REG1C_PE0_PERST;
+ break;
+ case 1:
+ rootpoint = 0;
+ endpoint = FPGA_REG1C_PE1_ENDPOINT;
+ power = FPGA_REG1A_PE1_PWRON;
+ green_led = FPGA_REG1A_PE1_GLED;
+ clock = FPGA_REG1A_PE1_REFCLK_ENABLE;
+ yellow_led = FPGA_REG1A_PE1_YLED;
+ reset_off = FPGA_REG1C_PE1_PERST;
+ break;
+ case 2:
+ rootpoint = 0;
+ endpoint = FPGA_REG1C_PE2_ENDPOINT;
+ power = FPGA_REG1A_PE2_PWRON;
+ green_led = FPGA_REG1A_PE2_GLED;
+ clock = FPGA_REG1A_PE2_REFCLK_ENABLE;
+ yellow_led = FPGA_REG1A_PE2_YLED;
+ reset_off = FPGA_REG1C_PE2_PERST;
+ break;
+
+ default:
+ return;
+ }
+
+ out_be16(pcie_reg_fpga_base + FPGA_REG1A,
+ ~(power | clock | green_led) &
+ (yellow_led | in_be16(pcie_reg_fpga_base + FPGA_REG1A)));
+ out_be16(pcie_reg_fpga_base + FPGA_REG1C,
+ ~(endpoint | reset_off) &
+ (rootpoint | in_be16(pcie_reg_fpga_base + FPGA_REG1C)));
+
+ /*
+ * Leave device in reset for a while after powering on the
+ * slot to give it a chance to initialize.
+ */
+ mdelay(250);
+
+ out_be16(pcie_reg_fpga_base + FPGA_REG1C,
+ reset_off | in_be16(pcie_reg_fpga_base + FPGA_REG1C));
+
+ iounmap(pcie_reg_fpga_base);
+}
+
+static void __init
+yucca_setup_hoses(void)
+{
+ struct pci_controller *hose;
+ char name[20];
+ int i;
+
+ if (0 && ppc440spe_init_pcie()) {
+ printk(KERN_WARNING "PPC440SPe PCI Express initialization failed\n");
+ return;
+ }
+
+ for (i = 0; i <= 2; ++i) {
+ if (!yucca_pcie_card_present(i))
+ continue;
+
+ printk(KERN_INFO "PCIE%d: card present\n", i);
+ yucca_setup_pcie_fpga_rootpoint(i);
+ if (ppc440spe_init_pcie_rootport(i)) {
+ printk(KERN_WARNING "PCIE%d: initialization failed\n", i);
+ continue;
+ }
+
+ hose = pcibios_alloc_controller();
+ if (!hose)
+ return;
+
+ sprintf(name, "PCIE%d host bridge", i);
+ pci_init_resource(&hose->io_resource,
+ YUCCA_PCIX_LOWER_IO,
+ YUCCA_PCIX_UPPER_IO,
+ IORESOURCE_IO,
+ name);
+
+ hose->mem_space.start = YUCCA_PCIE_LOWER_MEM +
+ i * YUCCA_PCIE_MEM_SIZE;
+ hose->mem_space.end = hose->mem_space.start +
+ YUCCA_PCIE_MEM_SIZE - 1;
+
+ pci_init_resource(&hose->mem_resources[0],
+ hose->mem_space.start,
+ hose->mem_space.end,
+ IORESOURCE_MEM,
+ name);
+
+ hose->first_busno = 0;
+ hose->last_busno = 15;
+ hose_type[hose->index] = HOSE_PCIE0 + i;
+
+ ppc440spe_setup_pcie(hose, i);
+ hose->last_busno = pciauto_bus_scan(hose, hose->first_busno);
+ }
+
+ ppc_md.pci_swizzle = common_swizzle;
+ ppc_md.pci_map_irq = yucca_map_irq;
+}
+
+TODC_ALLOC();
+
+static void __init
+yucca_early_serial_map(void)
+{
+ struct uart_port port;
+
+ /* Setup ioremapped serial port access */
+ memset(&port, 0, sizeof(port));
+ port.membase = ioremap64(PPC440SPE_UART0_ADDR, 8);
+ port.irq = UART0_INT;
+ port.uartclk = clocks.uart0;
+ port.regshift = 0;
+ port.iotype = SERIAL_IO_MEM;
+ port.flags = ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST;
+ port.line = 0;
+
+ if (early_serial_setup(&port) != 0) {
+ printk("Early serial init of port 0 failed\n");
+ }
+
+ port.membase = ioremap64(PPC440SPE_UART1_ADDR, 8);
+ port.irq = UART1_INT;
+ port.uartclk = clocks.uart1;
+ port.line = 1;
+
+ if (early_serial_setup(&port) != 0) {
+ printk("Early serial init of port 1 failed\n");
+ }
+
+ port.membase = ioremap64(PPC440SPE_UART2_ADDR, 8);
+ port.irq = UART2_INT;
+ port.uartclk = BASE_BAUD;
+ port.line = 2;
+
+ if (early_serial_setup(&port) != 0) {
+ printk("Early serial init of port 2 failed\n");
+ }
+}
+
+static void __init
+yucca_setup_arch(void)
+{
+ yucca_set_emacdata();
+
+#if !defined(CONFIG_BDI_SWITCH)
+ /*
+ * The Abatron BDI JTAG debugger does not tolerate others
+ * mucking with the debug registers.
+ */
+ mtspr(SPRN_DBCR0, (DBCR0_TDE | DBCR0_IDM));
+#endif
+
+ /*
+ * Determine various clocks.
+ * To be completely correct we should get SysClk
+ * from FPGA, because it can be changed by on-board switches
+ * --ebs
+ */
+ /* 440GX and 440SPe clocking is the same - rd */
+ ibm440gx_get_clocks(&clocks, 33333333, 6 * 1843200);
+ ocp_sys_info.opb_bus_freq = clocks.opb;
+
+ /* init to some ~sane value until calibrate_delay() runs */
+ loops_per_jiffy = 50000000/HZ;
+
+ /* Setup PCIXn host bridges */
+ yucca_setup_hoses();
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (initrd_start)
+ ROOT_DEV = Root_RAM0;
+ else
+#endif
+#ifdef CONFIG_ROOT_NFS
+ ROOT_DEV = Root_NFS;
+#else
+ ROOT_DEV = Root_HDA1;
+#endif
+
+ yucca_early_serial_map();
+
+ /* Identify the system */
+ printk("Yucca port (Roland Dreier )\n");
+}
+
+void __init platform_init(unsigned long r3, unsigned long r4,
+ unsigned long r5, unsigned long r6, unsigned long r7)
+{
+ ibm44x_platform_init(r3, r4, r5, r6, r7);
+
+ ppc_md.setup_arch = yucca_setup_arch;
+ ppc_md.show_cpuinfo = yucca_show_cpuinfo;
+ ppc_md.find_end_of_memory = ibm440sp_find_end_of_memory;
+ ppc_md.get_irq = NULL; /* Set in ppc4xx_pic_init() */
+
+ ppc_md.calibrate_decr = yucca_calibrate_decr;
+#ifdef CONFIG_KGDB
+ ppc_md.early_serial_map = yucca_early_serial_map;
+#endif
+}
diff --git a/arch/ppc/platforms/4xx/yucca.h b/arch/ppc/platforms/4xx/yucca.h
new file mode 100644
index 000000000000..01a4afea1514
--- /dev/null
+++ b/arch/ppc/platforms/4xx/yucca.h
@@ -0,0 +1,111 @@
+/*
+ * arch/ppc/platforms/4xx/yucca.h
+ *
+ * Yucca board definitions
+ *
+ * Roland Dreier (based on luan.h by Matt Porter)
+ *
+ * Copyright 2004-2005 MontaVista Software Inc.
+ * Copyright (c) 2005 Cisco Systems. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ */
+
+#ifdef __KERNEL__
+#ifndef __ASM_YUCCA_H__
+#define __ASM_YUCCA_H__
+
+#include
+#include
+
+/* F/W TLB mapping used in bootloader glue to reset EMAC */
+#define PPC44x_EMAC0_MR0 0xa0000800
+
+/* Location of MAC addresses in PIBS image */
+#define PIBS_FLASH_BASE 0xffe00000
+#define PIBS_MAC_BASE (PIBS_FLASH_BASE+0x1b0400)
+
+/* External timer clock frequency */
+#define YUCCA_TMR_CLK 25000000
+
+/*
+ * FPGA registers
+ */
+#define YUCCA_FPGA_REG_BASE 0x00000004e2000000ULL
+#define YUCCA_FPGA_REG_SIZE 0x24
+
+#define FPGA_REG1A 0x1a
+
+#define FPGA_REG1A_PE0_GLED 0x8000
+#define FPGA_REG1A_PE1_GLED 0x4000
+#define FPGA_REG1A_PE2_GLED 0x2000
+#define FPGA_REG1A_PE0_YLED 0x1000
+#define FPGA_REG1A_PE1_YLED 0x0800
+#define FPGA_REG1A_PE2_YLED 0x0400
+#define FPGA_REG1A_PE0_PWRON 0x0200
+#define FPGA_REG1A_PE1_PWRON 0x0100
+#define FPGA_REG1A_PE2_PWRON 0x0080
+#define FPGA_REG1A_PE0_REFCLK_ENABLE 0x0040
+#define FPGA_REG1A_PE1_REFCLK_ENABLE 0x0020
+#define FPGA_REG1A_PE2_REFCLK_ENABLE 0x0010
+#define FPGA_REG1A_PE_SPREAD0 0x0008
+#define FPGA_REG1A_PE_SPREAD1 0x0004
+#define FPGA_REG1A_PE_SELSOURCE_0 0x0002
+#define FPGA_REG1A_PE_SELSOURCE_1 0x0001
+
+#define FPGA_REG1C 0x1c
+
+#define FPGA_REG1C_PE0_ROOTPOINT 0x8000
+#define FPGA_REG1C_PE1_ENDPOINT 0x4000
+#define FPGA_REG1C_PE2_ENDPOINT 0x2000
+#define FPGA_REG1C_PE0_PRSNT 0x1000
+#define FPGA_REG1C_PE1_PRSNT 0x0800
+#define FPGA_REG1C_PE2_PRSNT 0x0400
+#define FPGA_REG1C_PE0_WAKE 0x0080
+#define FPGA_REG1C_PE1_WAKE 0x0040
+#define FPGA_REG1C_PE2_WAKE 0x0020
+#define FPGA_REG1C_PE0_PERST 0x0010
+#define FPGA_REG1C_PE1_PERST 0x0008
+#define FPGA_REG1C_PE2_PERST 0x0004
+
+/*
+ * Serial port defines
+ */
+#define RS_TABLE_SIZE 3
+
+/* PIBS defined UART mappings, used before early_serial_setup */
+#define UART0_IO_BASE 0xa0000200
+#define UART1_IO_BASE 0xa0000300
+#define UART2_IO_BASE 0xa0000600
+
+#define BASE_BAUD 11059200
+#define STD_UART_OP(num) \
+ { 0, BASE_BAUD, 0, UART##num##_INT, \
+ (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST), \
+ iomem_base: (void*)UART##num##_IO_BASE, \
+ io_type: SERIAL_IO_MEM},
+
+#define SERIAL_PORT_DFNS \
+ STD_UART_OP(0) \
+ STD_UART_OP(1) \
+ STD_UART_OP(2)
+
+/* PCI support */
+#define YUCCA_PCIX_LOWER_IO 0x00000000
+#define YUCCA_PCIX_UPPER_IO 0x0000ffff
+#define YUCCA_PCIX_LOWER_MEM 0x80000000
+#define YUCCA_PCIX_UPPER_MEM 0x8fffffff
+#define YUCCA_PCIE_LOWER_MEM 0x90000000
+#define YUCCA_PCIE_MEM_SIZE 0x10000000
+
+#define YUCCA_PCIX_MEM_SIZE 0x10000000
+#define YUCCA_PCIX_MEM_OFFSET 0x00000000
+#define YUCCA_PCIE_MEM_SIZE 0x10000000
+#define YUCCA_PCIE_MEM_OFFSET 0x00000000
+
+#endif /* __ASM_YUCCA_H__ */
+#endif /* __KERNEL__ */
diff --git a/arch/ppc/platforms/85xx/mpc85xx_ads_common.c b/arch/ppc/platforms/85xx/mpc85xx_ads_common.c
index bd3ac0136756..16ad092d8a06 100644
--- a/arch/ppc/platforms/85xx/mpc85xx_ads_common.c
+++ b/arch/ppc/platforms/85xx/mpc85xx_ads_common.c
@@ -45,6 +45,8 @@
#include
+#include
+
#include
#ifndef CONFIG_PCI
@@ -189,3 +191,11 @@ mpc85xx_exclude_device(u_char bus, u_char devfn)
}
#endif /* CONFIG_PCI */
+
+#ifdef CONFIG_RAPIDIO
+void platform_rio_init(void)
+{
+ /* 512MB RIO LAW at 0xc0000000 */
+ mpc85xx_rio_setup(0xc0000000, 0x20000000);
+}
+#endif /* CONFIG_RAPIDIO */
diff --git a/arch/ppc/platforms/85xx/stx_gp3.c b/arch/ppc/platforms/85xx/stx_gp3.c
index 1e1b85f8193a..15ce9d070634 100644
--- a/arch/ppc/platforms/85xx/stx_gp3.c
+++ b/arch/ppc/platforms/85xx/stx_gp3.c
@@ -37,6 +37,7 @@
#include
#include
#include
+#include
#include
#include
@@ -57,6 +58,7 @@
#include
#include
+#include
unsigned char __res[sizeof(bd_t)];
@@ -273,6 +275,18 @@ int mpc85xx_exclude_device(u_char bus, u_char devfn)
}
#endif /* CONFIG_PCI */
+#ifdef CONFIG_RAPIDIO
+void
+platform_rio_init(void)
+{
+ /*
+ * The STx firmware configures the RapidIO Local Access Window
+ * at 0xc0000000 with a size of 512MB.
+ */
+ mpc85xx_rio_setup(0xc0000000, 0x20000000);
+}
+#endif /* CONFIG_RAPIDIO */
+
void __init
platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
unsigned long r6, unsigned long r7)
diff --git a/arch/ppc/platforms/ev64360.c b/arch/ppc/platforms/ev64360.c
index b1324564456e..b9d844f88c2b 100644
--- a/arch/ppc/platforms/ev64360.c
+++ b/arch/ppc/platforms/ev64360.c
@@ -52,6 +52,8 @@ static u32 ev64360_bus_frequency;
unsigned char __res[sizeof(bd_t)];
+TODC_ALLOC();
+
static int __init
ev64360_map_irq(struct pci_dev *dev, unsigned char idsel, unsigned char pin)
{
@@ -182,6 +184,9 @@ ev64360_setup_peripherals(void)
EV64360_RTC_WINDOW_BASE, EV64360_RTC_WINDOW_SIZE, 0);
bh.ci->enable_window_32bit(&bh, MV64x60_CPU2DEV_1_WIN);
+ TODC_INIT(TODC_TYPE_DS1501, 0, 0,
+ ioremap(EV64360_RTC_WINDOW_BASE, EV64360_RTC_WINDOW_SIZE), 8);
+
mv64x60_set_32bit_window(&bh, MV64x60_CPU2SRAM_WIN,
EV64360_INTERNAL_SRAM_BASE, MV64360_SRAM_SIZE, 0);
bh.ci->enable_window_32bit(&bh, MV64x60_CPU2SRAM_WIN);
@@ -496,6 +501,13 @@ platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
ppc_md.power_off = ev64360_power_off;
ppc_md.halt = ev64360_halt;
ppc_md.find_end_of_memory = ev64360_find_end_of_memory;
+ ppc_md.init = NULL;
+
+ ppc_md.time_init = todc_time_init;
+ ppc_md.set_rtc_time = todc_set_rtc_time;
+ ppc_md.get_rtc_time = todc_get_rtc_time;
+ ppc_md.nvram_read_val = todc_direct_read_val;
+ ppc_md.nvram_write_val = todc_direct_write_val;
ppc_md.calibrate_decr = ev64360_calibrate_decr;
#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(CONFIG_SERIAL_MPSC_CONSOLE)
diff --git a/arch/ppc/syslib/Makefile b/arch/ppc/syslib/Makefile
index b4ef15b45c4a..5bd33baac243 100644
--- a/arch/ppc/syslib/Makefile
+++ b/arch/ppc/syslib/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_440EP) += ibm440gx_common.o
obj-$(CONFIG_440GP) += ibm440gp_common.o
obj-$(CONFIG_440GX) += ibm440gx_common.o
obj-$(CONFIG_440SP) += ibm440gx_common.o ibm440sp_common.o
+obj-$(CONFIG_440SPE) += ibm440gx_common.o ibm440sp_common.o ppc440spe_pcie.o
ifeq ($(CONFIG_4xx),y)
ifeq ($(CONFIG_VIRTEX_II_PRO),y)
obj-$(CONFIG_40x) += xilinx_pic.o
@@ -32,6 +33,7 @@ obj-$(CONFIG_PPC4xx_DMA) += ppc4xx_dma.o
obj-$(CONFIG_PPC4xx_EDMA) += ppc4xx_sgdma.o
ifeq ($(CONFIG_40x),y)
obj-$(CONFIG_PCI) += pci_auto.o ppc405_pci.o
+obj-$(CONFIG_RAPIDIO) += ppc85xx_rio.o
endif
endif
obj-$(CONFIG_8xx) += m8xx_setup.o ppc8xx_pic.o $(wdt-mpc8xx-y) \
@@ -46,12 +48,14 @@ obj-$(CONFIG_BAMBOO) += pci_auto.o todc_time.o
obj-$(CONFIG_CPCI690) += todc_time.o pci_auto.o
obj-$(CONFIG_EBONY) += pci_auto.o todc_time.o
obj-$(CONFIG_EV64260) += todc_time.o pci_auto.o
+obj-$(CONFIG_EV64360) += todc_time.o
obj-$(CONFIG_CHESTNUT) += mv64360_pic.o pci_auto.o
obj-$(CONFIG_GEMINI) += open_pic.o
obj-$(CONFIG_GT64260) += gt64260_pic.o
obj-$(CONFIG_LOPEC) += pci_auto.o todc_time.o
obj-$(CONFIG_HDPU) += pci_auto.o
obj-$(CONFIG_LUAN) += pci_auto.o todc_time.o
+obj-$(CONFIG_YUCCA) += pci_auto.o todc_time.o
obj-$(CONFIG_KATANA) += pci_auto.o
obj-$(CONFIG_MV64360) += mv64360_pic.o
obj-$(CONFIG_MV64X60) += mv64x60.o mv64x60_win.o
diff --git a/arch/ppc/syslib/ibm440sp_common.c b/arch/ppc/syslib/ibm440sp_common.c
index 417d4cff77a0..cdafda127d81 100644
--- a/arch/ppc/syslib/ibm440sp_common.c
+++ b/arch/ppc/syslib/ibm440sp_common.c
@@ -1,7 +1,7 @@
/*
* arch/ppc/syslib/ibm440sp_common.c
*
- * PPC440SP system library
+ * PPC440SP/PPC440SPe system library
*
* Matt Porter
* Copyright 2002-2005 MontaVista Software Inc.
@@ -35,7 +35,7 @@ unsigned long __init ibm440sp_find_end_of_memory(void)
u32 mem_size = 0;
/* Read two bank sizes and sum */
- for (i=0; i<2; i++)
+ for (i=0; i< MQ0_NUM_BANKS; i++)
switch (mfdcr(DCRN_MQ0_BS0BAS + i) & MQ0_CONFIG_SIZE_MASK) {
case MQ0_CONFIG_SIZE_8M:
mem_size += PPC44x_MEM_SIZE_8M;
diff --git a/arch/ppc/syslib/ibm44x_common.c b/arch/ppc/syslib/ibm44x_common.c
index 5152c8e41340..71db11d22158 100644
--- a/arch/ppc/syslib/ibm44x_common.c
+++ b/arch/ppc/syslib/ibm44x_common.c
@@ -20,6 +20,7 @@
#include
#include
#include
+#include
#include
#include
@@ -214,9 +215,20 @@ void __init ibm44x_platform_init(unsigned long r3, unsigned long r4, unsigned lo
/* Called from machine_check_exception */
void platform_machine_check(struct pt_regs *regs)
{
+#if defined(CONFIG_440SP) || defined(CONFIG_440SPE)
+ printk("PLB0: BEAR=0x%08x%08x ACR= 0x%08x BESR= 0x%08x%08x\n",
+ mfdcr(DCRN_PLB0_BEARH), mfdcr(DCRN_PLB0_BEARL),
+ mfdcr(DCRN_PLB0_ACR), mfdcr(DCRN_PLB0_BESRH),
+ mfdcr(DCRN_PLB0_BESRL));
+ printk("PLB1: BEAR=0x%08x%08x ACR= 0x%08x BESR= 0x%08x%08x\n",
+ mfdcr(DCRN_PLB1_BEARH), mfdcr(DCRN_PLB1_BEARL),
+ mfdcr(DCRN_PLB1_ACR), mfdcr(DCRN_PLB1_BESRH),
+ mfdcr(DCRN_PLB1_BESRL));
+#else
printk("PLB0: BEAR=0x%08x%08x ACR= 0x%08x BESR= 0x%08x\n",
mfdcr(DCRN_PLB0_BEARH), mfdcr(DCRN_PLB0_BEARL),
mfdcr(DCRN_PLB0_ACR), mfdcr(DCRN_PLB0_BESR));
+#endif
printk("POB0: BEAR=0x%08x%08x BESR0=0x%08x BESR1=0x%08x\n",
mfdcr(DCRN_POB0_BEARH), mfdcr(DCRN_POB0_BEARL),
mfdcr(DCRN_POB0_BESR0), mfdcr(DCRN_POB0_BESR1));
diff --git a/arch/ppc/syslib/ppc405_pci.c b/arch/ppc/syslib/ppc405_pci.c
index 81c83bf98df4..d6d838b16dac 100644
--- a/arch/ppc/syslib/ppc405_pci.c
+++ b/arch/ppc/syslib/ppc405_pci.c
@@ -89,13 +89,6 @@ ppc4xx_find_bridges(void)
isa_mem_base = 0;
pci_dram_offset = 0;
-#if (PSR_PCI_ARBIT_EN > 1)
- /* Check if running in slave mode */
- if ((mfdcr(DCRN_CHPSR) & PSR_PCI_ARBIT_EN) == 0) {
- printk("Running as PCI slave, kernel PCI disabled !\n");
- return;
- }
-#endif
/* Setup PCI32 hose */
hose_a = pcibios_alloc_controller();
if (!hose_a)
diff --git a/arch/ppc/syslib/ppc440spe_pcie.c b/arch/ppc/syslib/ppc440spe_pcie.c
new file mode 100644
index 000000000000..1509fc1ddfb6
--- /dev/null
+++ b/arch/ppc/syslib/ppc440spe_pcie.c
@@ -0,0 +1,442 @@
+/*
+ * Copyright (c) 2005 Cisco Systems. All rights reserved.
+ * Roland Dreier
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+#include
+
+#include "ppc440spe_pcie.h"
+
+static int
+pcie_read_config(struct pci_bus *bus, unsigned int devfn, int offset,
+ int len, u32 *val)
+{
+ struct pci_controller *hose = bus->sysdata;
+
+ if (PCI_SLOT(devfn) != 1)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ offset += devfn << 12;
+
+ /*
+ * Note: the caller has already checked that offset is
+ * suitably aligned and that len is 1, 2 or 4.
+ */
+ switch (len) {
+ case 1:
+ *val = in_8(hose->cfg_data + offset);
+ break;
+ case 2:
+ *val = in_le16(hose->cfg_data + offset);
+ break;
+ default:
+ *val = in_le32(hose->cfg_data + offset);
+ break;
+ }
+
+ if (0) printk("%s: read %x(%d) @ %x\n", __func__, *val, len, offset);
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static int
+pcie_write_config(struct pci_bus *bus, unsigned int devfn, int offset,
+ int len, u32 val)
+{
+ struct pci_controller *hose = bus->sysdata;
+
+ if (PCI_SLOT(devfn) != 1)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ offset += devfn << 12;
+
+ switch (len) {
+ case 1:
+ out_8(hose->cfg_data + offset, val);
+ break;
+ case 2:
+ out_le16(hose->cfg_data + offset, val);
+ break;
+ default:
+ out_le32(hose->cfg_data + offset, val);
+ break;
+ }
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops pcie_pci_ops =
+{
+ .read = pcie_read_config,
+ .write = pcie_write_config
+};
+
+enum {
+ PTYPE_ENDPOINT = 0x0,
+ PTYPE_LEGACY_ENDPOINT = 0x1,
+ PTYPE_ROOT_PORT = 0x4,
+
+ LNKW_X1 = 0x1,
+ LNKW_X4 = 0x4,
+ LNKW_X8 = 0x8
+};
+
+static void check_error(void)
+{
+ u32 valPE0, valPE1, valPE2;
+
+ /* SDR0_PEGPLLLCT1 reset */
+ if (!(valPE0 = SDR_READ(PESDR0_PLLLCT1) & 0x01000000)) {
+ printk(KERN_INFO "PCIE: SDR0_PEGPLLLCT1 reset error 0x%8x\n", valPE0);
+ }
+
+ valPE0 = SDR_READ(PESDR0_RCSSET);
+ valPE1 = SDR_READ(PESDR1_RCSSET);
+ valPE2 = SDR_READ(PESDR2_RCSSET);
+
+ /* SDR0_PExRCSSET rstgu */
+ if ( !(valPE0 & 0x01000000) ||
+ !(valPE1 & 0x01000000) ||
+ !(valPE2 & 0x01000000)) {
+ printk(KERN_INFO "PCIE: SDR0_PExRCSSET rstgu error\n");
+ }
+
+ /* SDR0_PExRCSSET rstdl */
+ if ( !(valPE0 & 0x00010000) ||
+ !(valPE1 & 0x00010000) ||
+ !(valPE2 & 0x00010000)) {
+ printk(KERN_INFO "PCIE: SDR0_PExRCSSET rstdl error\n");
+ }
+
+ /* SDR0_PExRCSSET rstpyn */
+ if ( (valPE0 & 0x00001000) ||
+ (valPE1 & 0x00001000) ||
+ (valPE2 & 0x00001000)) {
+ printk(KERN_INFO "PCIE: SDR0_PExRCSSET rstpyn error\n");
+ }
+
+ /* SDR0_PExRCSSET hldplb */
+ if ( (valPE0 & 0x10000000) ||
+ (valPE1 & 0x10000000) ||
+ (valPE2 & 0x10000000)) {
+ printk(KERN_INFO "PCIE: SDR0_PExRCSSET hldplb error\n");
+ }
+
+ /* SDR0_PExRCSSET rdy */
+ if ( (valPE0 & 0x00100000) ||
+ (valPE1 & 0x00100000) ||
+ (valPE2 & 0x00100000)) {
+ printk(KERN_INFO "PCIE: SDR0_PExRCSSET rdy error\n");
+ }
+
+ /* SDR0_PExRCSSET shutdown */
+ if ( (valPE0 & 0x00000100) ||
+ (valPE1 & 0x00000100) ||
+ (valPE2 & 0x00000100)) {
+ printk(KERN_INFO "PCIE: SDR0_PExRCSSET shutdown error\n");
+ }
+}
+
+/*
+ * Initialize PCI Express core as described in User Manual section 27.12.1
+ */
+int ppc440spe_init_pcie(void)
+{
+ /* Set PLL clock receiver to LVPECL */
+ SDR_WRITE(PESDR0_PLLLCT1, SDR_READ(PESDR0_PLLLCT1) | 1 << 28);
+
+ check_error();
+
+ printk(KERN_INFO "PCIE initialization OK\n");
+
+ if (!(SDR_READ(PESDR0_PLLLCT2) & 0x10000))
+ printk(KERN_INFO "PESDR_PLLCT2 resistance calibration failed (0x%08x)\n",
+ SDR_READ(PESDR0_PLLLCT2));
+
+ /* De-assert reset of PCIe PLL, wait for lock */
+ SDR_WRITE(PESDR0_PLLLCT1, SDR_READ(PESDR0_PLLLCT1) & ~(1 << 24));
+ udelay(3);
+
+ return 0;
+}
+
+int ppc440spe_init_pcie_rootport(int port)
+{
+ static int core_init;
+ void __iomem *utl_base;
+ u32 val = 0;
+ int i;
+
+ if (!core_init) {
+ ++core_init;
+ i = ppc440spe_init_pcie();
+ if (i)
+ return i;
+ }
+
+ /*
+ * Initialize various parts of the PCI Express core for our port:
+ *
+ * - Set as a root port and enable max width
+ * (PXIE0 -> X8, PCIE1 and PCIE2 -> X4).
+ * - Set up UTL configuration.
+ * - Increase SERDES drive strength to levels suggested by AMCC.
+ * - De-assert RSTPYN, RSTDL and RSTGU.
+ */
+ switch (port) {
+ case 0:
+ SDR_WRITE(PESDR0_DLPSET, PTYPE_ROOT_PORT << 20 | LNKW_X8 << 12);
+
+ SDR_WRITE(PESDR0_UTLSET1, 0x21222222);
+ SDR_WRITE(PESDR0_UTLSET2, 0x11000000);
+
+ SDR_WRITE(PESDR0_HSSL0SET1, 0x35000000);
+ SDR_WRITE(PESDR0_HSSL1SET1, 0x35000000);
+ SDR_WRITE(PESDR0_HSSL2SET1, 0x35000000);
+ SDR_WRITE(PESDR0_HSSL3SET1, 0x35000000);
+ SDR_WRITE(PESDR0_HSSL4SET1, 0x35000000);
+ SDR_WRITE(PESDR0_HSSL5SET1, 0x35000000);
+ SDR_WRITE(PESDR0_HSSL6SET1, 0x35000000);
+ SDR_WRITE(PESDR0_HSSL7SET1, 0x35000000);
+
+ SDR_WRITE(PESDR0_RCSSET,
+ (SDR_READ(PESDR0_RCSSET) & ~(1 << 24 | 1 << 16)) | 1 << 12);
+ break;
+
+ case 1:
+ SDR_WRITE(PESDR1_DLPSET, PTYPE_ROOT_PORT << 20 | LNKW_X4 << 12);
+
+ SDR_WRITE(PESDR1_UTLSET1, 0x21222222);
+ SDR_WRITE(PESDR1_UTLSET2, 0x11000000);
+
+ SDR_WRITE(PESDR1_HSSL0SET1, 0x35000000);
+ SDR_WRITE(PESDR1_HSSL1SET1, 0x35000000);
+ SDR_WRITE(PESDR1_HSSL2SET1, 0x35000000);
+ SDR_WRITE(PESDR1_HSSL3SET1, 0x35000000);
+
+ SDR_WRITE(PESDR1_RCSSET,
+ (SDR_READ(PESDR1_RCSSET) & ~(1 << 24 | 1 << 16)) | 1 << 12);
+ break;
+
+ case 2:
+ SDR_WRITE(PESDR2_DLPSET, PTYPE_ROOT_PORT << 20 | LNKW_X4 << 12);
+
+ SDR_WRITE(PESDR2_UTLSET1, 0x21222222);
+ SDR_WRITE(PESDR2_UTLSET2, 0x11000000);
+
+ SDR_WRITE(PESDR2_HSSL0SET1, 0x35000000);
+ SDR_WRITE(PESDR2_HSSL1SET1, 0x35000000);
+ SDR_WRITE(PESDR2_HSSL2SET1, 0x35000000);
+ SDR_WRITE(PESDR2_HSSL3SET1, 0x35000000);
+
+ SDR_WRITE(PESDR2_RCSSET,
+ (SDR_READ(PESDR2_RCSSET) & ~(1 << 24 | 1 << 16)) | 1 << 12);
+ break;
+ }
+
+ mdelay(1000);
+
+ switch (port) {
+ case 0: val = SDR_READ(PESDR0_RCSSTS); break;
+ case 1: val = SDR_READ(PESDR1_RCSSTS); break;
+ case 2: val = SDR_READ(PESDR2_RCSSTS); break;
+ }
+
+ if (!(val & (1 << 20)))
+ printk(KERN_INFO "PCIE%d: PGRST inactive\n", port);
+ else
+ printk(KERN_WARNING "PGRST for PCIE%d failed %08x\n", port, val);
+
+ switch (port) {
+ case 0: printk(KERN_INFO "PCIE0: LOOP %08x\n", SDR_READ(PESDR0_LOOP)); break;
+ case 1: printk(KERN_INFO "PCIE1: LOOP %08x\n", SDR_READ(PESDR1_LOOP)); break;
+ case 2: printk(KERN_INFO "PCIE2: LOOP %08x\n", SDR_READ(PESDR2_LOOP)); break;
+ }
+
+ /*
+ * Map UTL registers at 0xc_1000_0n00
+ */
+ switch (port) {
+ case 0:
+ mtdcr(DCRN_PEGPL_REGBAH(PCIE0), 0x0000000c);
+ mtdcr(DCRN_PEGPL_REGBAL(PCIE0), 0x10000000);
+ mtdcr(DCRN_PEGPL_REGMSK(PCIE0), 0x00007001);
+ mtdcr(DCRN_PEGPL_SPECIAL(PCIE0), 0x68782800);
+ break;
+
+ case 1:
+ mtdcr(DCRN_PEGPL_REGBAH(PCIE1), 0x0000000c);
+ mtdcr(DCRN_PEGPL_REGBAL(PCIE1), 0x10001000);
+ mtdcr(DCRN_PEGPL_REGMSK(PCIE1), 0x00007001);
+ mtdcr(DCRN_PEGPL_SPECIAL(PCIE1), 0x68782800);
+ break;
+
+ case 2:
+ mtdcr(DCRN_PEGPL_REGBAH(PCIE2), 0x0000000c);
+ mtdcr(DCRN_PEGPL_REGBAL(PCIE2), 0x10002000);
+ mtdcr(DCRN_PEGPL_REGMSK(PCIE2), 0x00007001);
+ mtdcr(DCRN_PEGPL_SPECIAL(PCIE2), 0x68782800);
+ }
+
+ utl_base = ioremap64(0xc10000000ull + 0x1000 * port, 0x100);
+
+ /*
+ * Set buffer allocations and then assert VRB and TXE.
+ */
+ out_be32(utl_base + PEUTL_OUTTR, 0x08000000);
+ out_be32(utl_base + PEUTL_INTR, 0x02000000);
+ out_be32(utl_base + PEUTL_OPDBSZ, 0x10000000);
+ out_be32(utl_base + PEUTL_PBBSZ, 0x53000000);
+ out_be32(utl_base + PEUTL_IPHBSZ, 0x08000000);
+ out_be32(utl_base + PEUTL_IPDBSZ, 0x10000000);
+ out_be32(utl_base + PEUTL_RCIRQEN, 0x00f00000);
+ out_be32(utl_base + PEUTL_PCTL, 0x80800066);
+
+ iounmap(utl_base);
+
+ /*
+ * We map PCI Express configuration access into the 512MB regions
+ * PCIE0: 0xc_4000_0000
+ * PCIE1: 0xc_8000_0000
+ * PCIE2: 0xc_c000_0000
+ */
+ switch (port) {
+ case 0:
+ mtdcr(DCRN_PEGPL_CFGBAH(PCIE0), 0x0000000c);
+ mtdcr(DCRN_PEGPL_CFGBAL(PCIE0), 0x40000000);
+ mtdcr(DCRN_PEGPL_CFGMSK(PCIE0), 0xe0000001); /* 512MB region, valid */
+ break;
+
+ case 1:
+ mtdcr(DCRN_PEGPL_CFGBAH(PCIE1), 0x0000000c);
+ mtdcr(DCRN_PEGPL_CFGBAL(PCIE1), 0x80000000);
+ mtdcr(DCRN_PEGPL_CFGMSK(PCIE1), 0xe0000001); /* 512MB region, valid */
+ break;
+
+ case 2:
+ mtdcr(DCRN_PEGPL_CFGBAH(PCIE2), 0x0000000c);
+ mtdcr(DCRN_PEGPL_CFGBAL(PCIE2), 0xc0000000);
+ mtdcr(DCRN_PEGPL_CFGMSK(PCIE2), 0xe0000001); /* 512MB region, valid */
+ break;
+ }
+
+ /*
+ * Check for VC0 active and assert RDY.
+ */
+ switch (port) {
+ case 0:
+ if (!(SDR_READ(PESDR0_RCSSTS) & (1 << 16)))
+ printk(KERN_WARNING "PCIE0: VC0 not active\n");
+ SDR_WRITE(PESDR0_RCSSET, SDR_READ(PESDR0_RCSSET) | 1 << 20);
+ break;
+ case 1:
+ if (!(SDR_READ(PESDR1_RCSSTS) & (1 << 16)))
+ printk(KERN_WARNING "PCIE0: VC0 not active\n");
+ SDR_WRITE(PESDR1_RCSSET, SDR_READ(PESDR1_RCSSET) | 1 << 20);
+ break;
+ case 2:
+ if (!(SDR_READ(PESDR2_RCSSTS) & (1 << 16)))
+ printk(KERN_WARNING "PCIE0: VC0 not active\n");
+ SDR_WRITE(PESDR2_RCSSET, SDR_READ(PESDR2_RCSSET) | 1 << 20);
+ break;
+ }
+
+#if 0
+ /* Dump all config regs */
+ for (i = 0x300; i <= 0x320; ++i)
+ printk("[%04x] 0x%08x\n", i, SDR_READ(i));
+ for (i = 0x340; i <= 0x353; ++i)
+ printk("[%04x] 0x%08x\n", i, SDR_READ(i));
+ for (i = 0x370; i <= 0x383; ++i)
+ printk("[%04x] 0x%08x\n", i, SDR_READ(i));
+ for (i = 0x3a0; i <= 0x3a2; ++i)
+ printk("[%04x] 0x%08x\n", i, SDR_READ(i));
+ for (i = 0x3c0; i <= 0x3c3; ++i)
+ printk("[%04x] 0x%08x\n", i, SDR_READ(i));
+#endif
+
+ mdelay(100);
+
+ return 0;
+}
+
+void ppc440spe_setup_pcie(struct pci_controller *hose, int port)
+{
+ void __iomem *mbase;
+
+ /*
+ * Map 16MB, which is enough for 4 bits of bus #
+ */
+ hose->cfg_data = ioremap64(0xc40000000ull + port * 0x40000000,
+ 1 << 24);
+ hose->ops = &pcie_pci_ops;
+
+ /*
+ * Set bus numbers on our root port
+ */
+ mbase = ioremap64(0xc50000000ull + port * 0x40000000, 4096);
+ out_8(mbase + PCI_PRIMARY_BUS, 0);
+ out_8(mbase + PCI_SECONDARY_BUS, 0);
+
+ /*
+ * Set up outbound translation to hose->mem_space from PLB
+ * addresses at an offset of 0xd_0000_0000. We set the low
+ * bits of the mask to 11 to turn off splitting into 8
+ * subregions and to enable the outbound translation.
+ */
+ out_le32(mbase + PECFG_POM0LAH, 0);
+ out_le32(mbase + PECFG_POM0LAL, hose->mem_space.start);
+
+ switch (port) {
+ case 0:
+ mtdcr(DCRN_PEGPL_OMR1BAH(PCIE0), 0x0000000d);
+ mtdcr(DCRN_PEGPL_OMR1BAL(PCIE0), hose->mem_space.start);
+ mtdcr(DCRN_PEGPL_OMR1MSKH(PCIE0), 0x7fffffff);
+ mtdcr(DCRN_PEGPL_OMR1MSKL(PCIE0),
+ ~(hose->mem_space.end - hose->mem_space.start) | 3);
+ break;
+ case 1:
+ mtdcr(DCRN_PEGPL_OMR1BAH(PCIE1), 0x0000000d);
+ mtdcr(DCRN_PEGPL_OMR1BAL(PCIE1), hose->mem_space.start);
+ mtdcr(DCRN_PEGPL_OMR1MSKH(PCIE1), 0x7fffffff);
+ mtdcr(DCRN_PEGPL_OMR1MSKL(PCIE1),
+ ~(hose->mem_space.end - hose->mem_space.start) | 3);
+
+ break;
+ case 2:
+ mtdcr(DCRN_PEGPL_OMR1BAH(PCIE2), 0x0000000d);
+ mtdcr(DCRN_PEGPL_OMR1BAL(PCIE2), hose->mem_space.start);
+ mtdcr(DCRN_PEGPL_OMR1MSKH(PCIE2), 0x7fffffff);
+ mtdcr(DCRN_PEGPL_OMR1MSKL(PCIE2),
+ ~(hose->mem_space.end - hose->mem_space.start) | 3);
+ break;
+ }
+
+ /* Set up 16GB inbound memory window at 0 */
+ out_le32(mbase + PCI_BASE_ADDRESS_0, 0);
+ out_le32(mbase + PCI_BASE_ADDRESS_1, 0);
+ out_le32(mbase + PECFG_BAR0HMPA, 0x7fffffc);
+ out_le32(mbase + PECFG_BAR0LMPA, 0);
+ out_le32(mbase + PECFG_PIM0LAL, 0);
+ out_le32(mbase + PECFG_PIM0LAH, 0);
+ out_le32(mbase + PECFG_PIMEN, 0x1);
+
+ /* Enable I/O, Mem, and Busmaster cycles */
+ out_le16(mbase + PCI_COMMAND,
+ in_le16(mbase + PCI_COMMAND) |
+ PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
+
+ iounmap(mbase);
+}
diff --git a/arch/ppc/syslib/ppc440spe_pcie.h b/arch/ppc/syslib/ppc440spe_pcie.h
new file mode 100644
index 000000000000..55b765ad3272
--- /dev/null
+++ b/arch/ppc/syslib/ppc440spe_pcie.h
@@ -0,0 +1,149 @@
+/*
+ * Copyright (c) 2005 Cisco Systems. All rights reserved.
+ * Roland Dreier
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __PPC_SYSLIB_PPC440SPE_PCIE_H
+#define __PPC_SYSLIB_PPC440SPE_PCIE_H
+
+#define DCRN_SDR0_CFGADDR 0x00e
+#define DCRN_SDR0_CFGDATA 0x00f
+
+#define DCRN_PCIE0_BASE 0x100
+#define DCRN_PCIE1_BASE 0x120
+#define DCRN_PCIE2_BASE 0x140
+#define PCIE0 DCRN_PCIE0_BASE
+#define PCIE1 DCRN_PCIE1_BASE
+#define PCIE2 DCRN_PCIE2_BASE
+
+#define DCRN_PEGPL_CFGBAH(base) (base + 0x00)
+#define DCRN_PEGPL_CFGBAL(base) (base + 0x01)
+#define DCRN_PEGPL_CFGMSK(base) (base + 0x02)
+#define DCRN_PEGPL_MSGBAH(base) (base + 0x03)
+#define DCRN_PEGPL_MSGBAL(base) (base + 0x04)
+#define DCRN_PEGPL_MSGMSK(base) (base + 0x05)
+#define DCRN_PEGPL_OMR1BAH(base) (base + 0x06)
+#define DCRN_PEGPL_OMR1BAL(base) (base + 0x07)
+#define DCRN_PEGPL_OMR1MSKH(base) (base + 0x08)
+#define DCRN_PEGPL_OMR1MSKL(base) (base + 0x09)
+#define DCRN_PEGPL_REGBAH(base) (base + 0x12)
+#define DCRN_PEGPL_REGBAL(base) (base + 0x13)
+#define DCRN_PEGPL_REGMSK(base) (base + 0x14)
+#define DCRN_PEGPL_SPECIAL(base) (base + 0x15)
+
+/*
+ * System DCRs (SDRs)
+ */
+#define PESDR0_PLLLCT1 0x03a0
+#define PESDR0_PLLLCT2 0x03a1
+#define PESDR0_PLLLCT3 0x03a2
+
+#define PESDR0_UTLSET1 0x0300
+#define PESDR0_UTLSET2 0x0301
+#define PESDR0_DLPSET 0x0302
+#define PESDR0_LOOP 0x0303
+#define PESDR0_RCSSET 0x0304
+#define PESDR0_RCSSTS 0x0305
+#define PESDR0_HSSL0SET1 0x0306
+#define PESDR0_HSSL0SET2 0x0307
+#define PESDR0_HSSL0STS 0x0308
+#define PESDR0_HSSL1SET1 0x0309
+#define PESDR0_HSSL1SET2 0x030a
+#define PESDR0_HSSL1STS 0x030b
+#define PESDR0_HSSL2SET1 0x030c
+#define PESDR0_HSSL2SET2 0x030d
+#define PESDR0_HSSL2STS 0x030e
+#define PESDR0_HSSL3SET1 0x030f
+#define PESDR0_HSSL3SET2 0x0310
+#define PESDR0_HSSL3STS 0x0311
+#define PESDR0_HSSL4SET1 0x0312
+#define PESDR0_HSSL4SET2 0x0313
+#define PESDR0_HSSL4STS 0x0314
+#define PESDR0_HSSL5SET1 0x0315
+#define PESDR0_HSSL5SET2 0x0316
+#define PESDR0_HSSL5STS 0x0317
+#define PESDR0_HSSL6SET1 0x0318
+#define PESDR0_HSSL6SET2 0x0319
+#define PESDR0_HSSL6STS 0x031a
+#define PESDR0_HSSL7SET1 0x031b
+#define PESDR0_HSSL7SET2 0x031c
+#define PESDR0_HSSL7STS 0x031d
+#define PESDR0_HSSCTLSET 0x031e
+#define PESDR0_LANE_ABCD 0x031f
+#define PESDR0_LANE_EFGH 0x0320
+
+#define PESDR1_UTLSET1 0x0340
+#define PESDR1_UTLSET2 0x0341
+#define PESDR1_DLPSET 0x0342
+#define PESDR1_LOOP 0x0343
+#define PESDR1_RCSSET 0x0344
+#define PESDR1_RCSSTS 0x0345
+#define PESDR1_HSSL0SET1 0x0346
+#define PESDR1_HSSL0SET2 0x0347
+#define PESDR1_HSSL0STS 0x0348
+#define PESDR1_HSSL1SET1 0x0349
+#define PESDR1_HSSL1SET2 0x034a
+#define PESDR1_HSSL1STS 0x034b
+#define PESDR1_HSSL2SET1 0x034c
+#define PESDR1_HSSL2SET2 0x034d
+#define PESDR1_HSSL2STS 0x034e
+#define PESDR1_HSSL3SET1 0x034f
+#define PESDR1_HSSL3SET2 0x0350
+#define PESDR1_HSSL3STS 0x0351
+#define PESDR1_HSSCTLSET 0x0352
+#define PESDR1_LANE_ABCD 0x0353
+
+#define PESDR2_UTLSET1 0x0370
+#define PESDR2_UTLSET2 0x0371
+#define PESDR2_DLPSET 0x0372
+#define PESDR2_LOOP 0x0373
+#define PESDR2_RCSSET 0x0374
+#define PESDR2_RCSSTS 0x0375
+#define PESDR2_HSSL0SET1 0x0376
+#define PESDR2_HSSL0SET2 0x0377
+#define PESDR2_HSSL0STS 0x0378
+#define PESDR2_HSSL1SET1 0x0379
+#define PESDR2_HSSL1SET2 0x037a
+#define PESDR2_HSSL1STS 0x037b
+#define PESDR2_HSSL2SET1 0x037c
+#define PESDR2_HSSL2SET2 0x037d
+#define PESDR2_HSSL2STS 0x037e
+#define PESDR2_HSSL3SET1 0x037f
+#define PESDR2_HSSL3SET2 0x0380
+#define PESDR2_HSSL3STS 0x0381
+#define PESDR2_HSSCTLSET 0x0382
+#define PESDR2_LANE_ABCD 0x0383
+
+/*
+ * UTL register offsets
+ */
+#define PEUTL_PBBSZ 0x20
+#define PEUTL_OPDBSZ 0x68
+#define PEUTL_IPHBSZ 0x70
+#define PEUTL_IPDBSZ 0x78
+#define PEUTL_OUTTR 0x90
+#define PEUTL_INTR 0x98
+#define PEUTL_PCTL 0xa0
+#define PEUTL_RCIRQEN 0xb8
+
+/*
+ * Config space register offsets
+ */
+#define PECFG_BAR0LMPA 0x210
+#define PECFG_BAR0HMPA 0x214
+#define PECFG_PIMEN 0x33c
+#define PECFG_PIM0LAL 0x340
+#define PECFG_PIM0LAH 0x344
+#define PECFG_POM0LAL 0x380
+#define PECFG_POM0LAH 0x384
+
+int ppc440spe_init_pcie(void);
+int ppc440spe_init_pcie_rootport(int port);
+void ppc440spe_setup_pcie(struct pci_controller *hose, int port);
+
+#endif /* __PPC_SYSLIB_PPC440SPE_PCIE_H */
diff --git a/arch/ppc/syslib/ppc4xx_pic.c b/arch/ppc/syslib/ppc4xx_pic.c
index 0b435633a0d1..aa4165144ec2 100644
--- a/arch/ppc/syslib/ppc4xx_pic.c
+++ b/arch/ppc/syslib/ppc4xx_pic.c
@@ -38,6 +38,7 @@ extern unsigned char ppc4xx_uic_ext_irq_cfg[] __attribute__ ((weak));
#define IRQ_MASK_UICx(irq) (1 << (31 - ((irq) & 0x1f)))
#define IRQ_MASK_UIC1(irq) IRQ_MASK_UICx(irq)
#define IRQ_MASK_UIC2(irq) IRQ_MASK_UICx(irq)
+#define IRQ_MASK_UIC3(irq) IRQ_MASK_UICx(irq)
#define UIC_HANDLERS(n) \
static void ppc4xx_uic##n##_enable(unsigned int irq) \
@@ -88,7 +89,38 @@ static void ppc4xx_uic##n##_end(unsigned int irq) \
.end = ppc4xx_uic##n##_end, \
} \
-#if NR_UICS == 3
+#if NR_UICS == 4
+#define ACK_UIC0_PARENT
+#define ACK_UIC1_PARENT mtdcr(DCRN_UIC_SR(UIC0), UIC0_UIC1NC);
+#define ACK_UIC2_PARENT mtdcr(DCRN_UIC_SR(UIC0), UIC0_UIC2NC);
+#define ACK_UIC3_PARENT mtdcr(DCRN_UIC_SR(UIC0), UIC0_UIC3NC);
+UIC_HANDLERS(0);
+UIC_HANDLERS(1);
+UIC_HANDLERS(2);
+UIC_HANDLERS(3);
+
+static int ppc4xx_pic_get_irq(struct pt_regs *regs)
+{
+ u32 uic0 = mfdcr(DCRN_UIC_MSR(UIC0));
+ if (uic0 & UIC0_UIC1NC)
+ return 64 - ffs(mfdcr(DCRN_UIC_MSR(UIC1)));
+ else if (uic0 & UIC0_UIC2NC)
+ return 96 - ffs(mfdcr(DCRN_UIC_MSR(UIC2)));
+ else if (uic0 & UIC0_UIC3NC)
+ return 128 - ffs(mfdcr(DCRN_UIC_MSR(UIC3)));
+ else
+ return uic0 ? 32 - ffs(uic0) : -1;
+}
+
+static void __init ppc4xx_pic_impl_init(void)
+{
+ /* Enable cascade interrupts in UIC0 */
+ ppc_cached_irq_mask[0] |= UIC0_UIC1NC | UIC0_UIC2NC | UIC0_UIC3NC;
+ mtdcr(DCRN_UIC_SR(UIC0), UIC0_UIC1NC | UIC0_UIC2NC | UIC0_UIC3NC);
+ mtdcr(DCRN_UIC_ER(UIC0), ppc_cached_irq_mask[0]);
+}
+
+#elif NR_UICS == 3
#define ACK_UIC0_PARENT mtdcr(DCRN_UIC_SR(UICB), UICB_UIC0NC);
#define ACK_UIC1_PARENT mtdcr(DCRN_UIC_SR(UICB), UICB_UIC1NC);
#define ACK_UIC2_PARENT mtdcr(DCRN_UIC_SR(UICB), UICB_UIC2NC);
@@ -170,6 +202,9 @@ static struct ppc4xx_uic_impl {
{ .decl = DECLARE_UIC(1), .base = UIC1 },
#if NR_UICS > 2
{ .decl = DECLARE_UIC(2), .base = UIC2 },
+#if NR_UICS > 3
+ { .decl = DECLARE_UIC(3), .base = UIC3 },
+#endif
#endif
#endif
};
diff --git a/arch/ppc/syslib/ppc85xx_rio.c b/arch/ppc/syslib/ppc85xx_rio.c
new file mode 100644
index 000000000000..297f3b549177
--- /dev/null
+++ b/arch/ppc/syslib/ppc85xx_rio.c
@@ -0,0 +1,938 @@
+/*
+ * MPC85xx RapidIO support
+ *
+ * Copyright 2005 MontaVista Software, Inc.
+ * Matt Porter
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+
+#define RIO_REGS_BASE (CCSRBAR + 0xc0000)
+#define RIO_ATMU_REGS_OFFSET 0x10c00
+#define RIO_MSG_REGS_OFFSET 0x11000
+#define RIO_MAINT_WIN_SIZE 0x400000
+#define RIO_DBELL_WIN_SIZE 0x1000
+
+#define RIO_MSG_OMR_MUI 0x00000002
+#define RIO_MSG_OSR_TE 0x00000080
+#define RIO_MSG_OSR_QOI 0x00000020
+#define RIO_MSG_OSR_QFI 0x00000010
+#define RIO_MSG_OSR_MUB 0x00000004
+#define RIO_MSG_OSR_EOMI 0x00000002
+#define RIO_MSG_OSR_QEI 0x00000001
+
+#define RIO_MSG_IMR_MI 0x00000002
+#define RIO_MSG_ISR_TE 0x00000080
+#define RIO_MSG_ISR_QFI 0x00000010
+#define RIO_MSG_ISR_DIQI 0x00000001
+
+#define RIO_MSG_DESC_SIZE 32
+#define RIO_MSG_BUFFER_SIZE 4096
+#define RIO_MIN_TX_RING_SIZE 2
+#define RIO_MAX_TX_RING_SIZE 2048
+#define RIO_MIN_RX_RING_SIZE 2
+#define RIO_MAX_RX_RING_SIZE 2048
+
+#define DOORBELL_DMR_DI 0x00000002
+#define DOORBELL_DSR_TE 0x00000080
+#define DOORBELL_DSR_QFI 0x00000010
+#define DOORBELL_DSR_DIQI 0x00000001
+#define DOORBELL_TID_OFFSET 0x03
+#define DOORBELL_SID_OFFSET 0x05
+#define DOORBELL_INFO_OFFSET 0x06
+
+#define DOORBELL_MESSAGE_SIZE 0x08
+#define DBELL_SID(x) (*(u8 *)(x + DOORBELL_SID_OFFSET))
+#define DBELL_TID(x) (*(u8 *)(x + DOORBELL_TID_OFFSET))
+#define DBELL_INF(x) (*(u16 *)(x + DOORBELL_INFO_OFFSET))
+
+#define is_power_of_2(x) (((x) & ((x) - 1)) == 0)
+
+struct rio_atmu_regs {
+ u32 rowtar;
+ u32 pad1;
+ u32 rowbar;
+ u32 pad2;
+ u32 rowar;
+ u32 pad3[3];
+};
+
+struct rio_msg_regs {
+ u32 omr;
+ u32 osr;
+ u32 pad1;
+ u32 odqdpar;
+ u32 pad2;
+ u32 osar;
+ u32 odpr;
+ u32 odatr;
+ u32 odcr;
+ u32 pad3;
+ u32 odqepar;
+ u32 pad4[13];
+ u32 imr;
+ u32 isr;
+ u32 pad5;
+ u32 ifqdpar;
+ u32 pad6;
+ u32 ifqepar;
+ u32 pad7[250];
+ u32 dmr;
+ u32 dsr;
+ u32 pad8;
+ u32 dqdpar;
+ u32 pad9;
+ u32 dqepar;
+ u32 pad10[26];
+ u32 pwmr;
+ u32 pwsr;
+ u32 pad11;
+ u32 pwqbar;
+};
+
+struct rio_tx_desc {
+ u32 res1;
+ u32 saddr;
+ u32 dport;
+ u32 dattr;
+ u32 res2;
+ u32 res3;
+ u32 dwcnt;
+ u32 res4;
+};
+
+static u32 regs_win;
+static struct rio_atmu_regs *atmu_regs;
+static struct rio_atmu_regs *maint_atmu_regs;
+static struct rio_atmu_regs *dbell_atmu_regs;
+static u32 dbell_win;
+static u32 maint_win;
+static struct rio_msg_regs *msg_regs;
+
+static struct rio_dbell_ring {
+ void *virt;
+ dma_addr_t phys;
+} dbell_ring;
+
+static struct rio_msg_tx_ring {
+ void *virt;
+ dma_addr_t phys;
+ void *virt_buffer[RIO_MAX_TX_RING_SIZE];
+ dma_addr_t phys_buffer[RIO_MAX_TX_RING_SIZE];
+ int tx_slot;
+ int size;
+ void *dev_id;
+} msg_tx_ring;
+
+static struct rio_msg_rx_ring {
+ void *virt;
+ dma_addr_t phys;
+ void *virt_buffer[RIO_MAX_RX_RING_SIZE];
+ int rx_slot;
+ int size;
+ void *dev_id;
+} msg_rx_ring;
+
+/**
+ * mpc85xx_rio_doorbell_send - Send a MPC85xx doorbell message
+ * @index: ID of RapidIO interface
+ * @destid: Destination ID of target device
+ * @data: 16-bit info field of RapidIO doorbell message
+ *
+ * Sends a MPC85xx doorbell message. Returns %0 on success or
+ * %-EINVAL on failure.
+ */
+static int mpc85xx_rio_doorbell_send(int index, u16 destid, u16 data)
+{
+ pr_debug("mpc85xx_doorbell_send: index %d destid %4.4x data %4.4x\n",
+ index, destid, data);
+ out_be32((void *)&dbell_atmu_regs->rowtar, destid << 22);
+ out_be16((void *)(dbell_win), data);
+
+ return 0;
+}
+
+/**
+ * mpc85xx_local_config_read - Generate a MPC85xx local config space read
+ * @index: ID of RapdiIO interface
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @data: Value to be read into
+ *
+ * Generates a MPC85xx local configuration space read. Returns %0 on
+ * success or %-EINVAL on failure.
+ */
+static int mpc85xx_local_config_read(int index, u32 offset, int len, u32 * data)
+{
+ pr_debug("mpc85xx_local_config_read: index %d offset %8.8x\n", index,
+ offset);
+ *data = in_be32((void *)(regs_win + offset));
+
+ return 0;
+}
+
+/**
+ * mpc85xx_local_config_write - Generate a MPC85xx local config space write
+ * @index: ID of RapdiIO interface
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @data: Value to be written
+ *
+ * Generates a MPC85xx local configuration space write. Returns %0 on
+ * success or %-EINVAL on failure.
+ */
+static int mpc85xx_local_config_write(int index, u32 offset, int len, u32 data)
+{
+ pr_debug
+ ("mpc85xx_local_config_write: index %d offset %8.8x data %8.8x\n",
+ index, offset, data);
+ out_be32((void *)(regs_win + offset), data);
+
+ return 0;
+}
+
+/**
+ * mpc85xx_rio_config_read - Generate a MPC85xx read maintenance transaction
+ * @index: ID of RapdiIO interface
+ * @destid: Destination ID of transaction
+ * @hopcount: Number of hops to target device
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @val: Location to be read into
+ *
+ * Generates a MPC85xx read maintenance transaction. Returns %0 on
+ * success or %-EINVAL on failure.
+ */
+static int
+mpc85xx_rio_config_read(int index, u16 destid, u8 hopcount, u32 offset, int len,
+ u32 * val)
+{
+ u8 *data;
+
+ pr_debug
+ ("mpc85xx_rio_config_read: index %d destid %d hopcount %d offset %8.8x len %d\n",
+ index, destid, hopcount, offset, len);
+ out_be32((void *)&maint_atmu_regs->rowtar,
+ (destid << 22) | (hopcount << 12) | ((offset & ~0x3) >> 9));
+
+ data = (u8 *) maint_win + offset;
+ switch (len) {
+ case 1:
+ *val = in_8((u8 *) data);
+ break;
+ case 2:
+ *val = in_be16((u16 *) data);
+ break;
+ default:
+ *val = in_be32((u32 *) data);
+ break;
+ }
+
+ return 0;
+}
+
+/**
+ * mpc85xx_rio_config_write - Generate a MPC85xx write maintenance transaction
+ * @index: ID of RapdiIO interface
+ * @destid: Destination ID of transaction
+ * @hopcount: Number of hops to target device
+ * @offset: Offset into configuration space
+ * @len: Length (in bytes) of the maintenance transaction
+ * @val: Value to be written
+ *
+ * Generates an MPC85xx write maintenance transaction. Returns %0 on
+ * success or %-EINVAL on failure.
+ */
+static int
+mpc85xx_rio_config_write(int index, u16 destid, u8 hopcount, u32 offset,
+ int len, u32 val)
+{
+ u8 *data;
+ pr_debug
+ ("mpc85xx_rio_config_write: index %d destid %d hopcount %d offset %8.8x len %d val %8.8x\n",
+ index, destid, hopcount, offset, len, val);
+ out_be32((void *)&maint_atmu_regs->rowtar,
+ (destid << 22) | (hopcount << 12) | ((offset & ~0x3) >> 9));
+
+ data = (u8 *) maint_win + offset;
+ switch (len) {
+ case 1:
+ out_8((u8 *) data, val);
+ break;
+ case 2:
+ out_be16((u16 *) data, val);
+ break;
+ default:
+ out_be32((u32 *) data, val);
+ break;
+ }
+
+ return 0;
+}
+
+/**
+ * rio_hw_add_outb_message - Add message to the MPC85xx outbound message queue
+ * @mport: Master port with outbound message queue
+ * @rdev: Target of outbound message
+ * @mbox: Outbound mailbox
+ * @buffer: Message to add to outbound queue
+ * @len: Length of message
+ *
+ * Adds the @buffer message to the MPC85xx outbound message queue. Returns
+ * %0 on success or %-EINVAL on failure.
+ */
+int
+rio_hw_add_outb_message(struct rio_mport *mport, struct rio_dev *rdev, int mbox,
+ void *buffer, size_t len)
+{
+ u32 omr;
+ struct rio_tx_desc *desc =
+ (struct rio_tx_desc *)msg_tx_ring.virt + msg_tx_ring.tx_slot;
+ int ret = 0;
+
+ pr_debug
+ ("RIO: rio_hw_add_outb_message(): destid %4.4x mbox %d buffer %8.8x len %8.8x\n",
+ rdev->destid, mbox, (int)buffer, len);
+
+ if ((len < 8) || (len > RIO_MAX_MSG_SIZE)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* Copy and clear rest of buffer */
+ memcpy(msg_tx_ring.virt_buffer[msg_tx_ring.tx_slot], buffer, len);
+ if (len < (RIO_MAX_MSG_SIZE - 4))
+ memset((void *)((u32) msg_tx_ring.
+ virt_buffer[msg_tx_ring.tx_slot] + len), 0,
+ RIO_MAX_MSG_SIZE - len);
+
+ /* Set mbox field for message */
+ desc->dport = mbox & 0x3;
+
+ /* Enable EOMI interrupt, set priority, and set destid */
+ desc->dattr = 0x28000000 | (rdev->destid << 2);
+
+ /* Set transfer size aligned to next power of 2 (in double words) */
+ desc->dwcnt = is_power_of_2(len) ? len : 1 << get_bitmask_order(len);
+
+ /* Set snooping and source buffer address */
+ desc->saddr = 0x00000004 | msg_tx_ring.phys_buffer[msg_tx_ring.tx_slot];
+
+ /* Increment enqueue pointer */
+ omr = in_be32((void *)&msg_regs->omr);
+ out_be32((void *)&msg_regs->omr, omr | RIO_MSG_OMR_MUI);
+
+ /* Go to next descriptor */
+ if (++msg_tx_ring.tx_slot == msg_tx_ring.size)
+ msg_tx_ring.tx_slot = 0;
+
+ out:
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(rio_hw_add_outb_message);
+
+/**
+ * mpc85xx_rio_tx_handler - MPC85xx outbound message interrupt handler
+ * @irq: Linux interrupt number
+ * @dev_instance: Pointer to interrupt-specific data
+ * @regs: Register context
+ *
+ * Handles outbound message interrupts. Executes a register outbound
+ * mailbox event handler and acks the interrupt occurence.
+ */
+static irqreturn_t
+mpc85xx_rio_tx_handler(int irq, void *dev_instance, struct pt_regs *regs)
+{
+ int osr;
+ struct rio_mport *port = (struct rio_mport *)dev_instance;
+
+ osr = in_be32((void *)&msg_regs->osr);
+
+ if (osr & RIO_MSG_OSR_TE) {
+ pr_info("RIO: outbound message transmission error\n");
+ out_be32((void *)&msg_regs->osr, RIO_MSG_OSR_TE);
+ goto out;
+ }
+
+ if (osr & RIO_MSG_OSR_QOI) {
+ pr_info("RIO: outbound message queue overflow\n");
+ out_be32((void *)&msg_regs->osr, RIO_MSG_OSR_QOI);
+ goto out;
+ }
+
+ if (osr & RIO_MSG_OSR_EOMI) {
+ u32 dqp = in_be32((void *)&msg_regs->odqdpar);
+ int slot = (dqp - msg_tx_ring.phys) >> 5;
+ port->outb_msg[0].mcback(port, msg_tx_ring.dev_id, -1, slot);
+
+ /* Ack the end-of-message interrupt */
+ out_be32((void *)&msg_regs->osr, RIO_MSG_OSR_EOMI);
+ }
+
+ out:
+ return IRQ_HANDLED;
+}
+
+/**
+ * rio_open_outb_mbox - Initialize MPC85xx outbound mailbox
+ * @mport: Master port implementing the outbound message unit
+ * @dev_id: Device specific pointer to pass on event
+ * @mbox: Mailbox to open
+ * @entries: Number of entries in the outbound mailbox ring
+ *
+ * Initializes buffer ring, request the outbound message interrupt,
+ * and enables the outbound message unit. Returns %0 on success and
+ * %-EINVAL or %-ENOMEM on failure.
+ */
+int rio_open_outb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entries)
+{
+ int i, j, rc = 0;
+
+ if ((entries < RIO_MIN_TX_RING_SIZE) ||
+ (entries > RIO_MAX_TX_RING_SIZE) || (!is_power_of_2(entries))) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ /* Initialize shadow copy ring */
+ msg_tx_ring.dev_id = dev_id;
+ msg_tx_ring.size = entries;
+
+ for (i = 0; i < msg_tx_ring.size; i++) {
+ if (!
+ (msg_tx_ring.virt_buffer[i] =
+ dma_alloc_coherent(NULL, RIO_MSG_BUFFER_SIZE,
+ &msg_tx_ring.phys_buffer[i],
+ GFP_KERNEL))) {
+ rc = -ENOMEM;
+ for (j = 0; j < msg_tx_ring.size; j++)
+ if (msg_tx_ring.virt_buffer[j])
+ dma_free_coherent(NULL,
+ RIO_MSG_BUFFER_SIZE,
+ msg_tx_ring.
+ virt_buffer[j],
+ msg_tx_ring.
+ phys_buffer[j]);
+ goto out;
+ }
+ }
+
+ /* Initialize outbound message descriptor ring */
+ if (!(msg_tx_ring.virt = dma_alloc_coherent(NULL,
+ msg_tx_ring.size *
+ RIO_MSG_DESC_SIZE,
+ &msg_tx_ring.phys,
+ GFP_KERNEL))) {
+ rc = -ENOMEM;
+ goto out_dma;
+ }
+ memset(msg_tx_ring.virt, 0, msg_tx_ring.size * RIO_MSG_DESC_SIZE);
+ msg_tx_ring.tx_slot = 0;
+
+ /* Point dequeue/enqueue pointers at first entry in ring */
+ out_be32((void *)&msg_regs->odqdpar, msg_tx_ring.phys);
+ out_be32((void *)&msg_regs->odqepar, msg_tx_ring.phys);
+
+ /* Configure for snooping */
+ out_be32((void *)&msg_regs->osar, 0x00000004);
+
+ /* Clear interrupt status */
+ out_be32((void *)&msg_regs->osr, 0x000000b3);
+
+ /* Hook up outbound message handler */
+ if ((rc =
+ request_irq(MPC85xx_IRQ_RIO_TX, mpc85xx_rio_tx_handler, 0,
+ "msg_tx", (void *)mport)) < 0)
+ goto out_irq;
+
+ /*
+ * Configure outbound message unit
+ * Snooping
+ * Interrupts (all enabled, except QEIE)
+ * Chaining mode
+ * Disable
+ */
+ out_be32((void *)&msg_regs->omr, 0x00100220);
+
+ /* Set number of entries */
+ out_be32((void *)&msg_regs->omr,
+ in_be32((void *)&msg_regs->omr) |
+ ((get_bitmask_order(entries) - 2) << 12));
+
+ /* Now enable the unit */
+ out_be32((void *)&msg_regs->omr, in_be32((void *)&msg_regs->omr) | 0x1);
+
+ out:
+ return rc;
+
+ out_irq:
+ dma_free_coherent(NULL, msg_tx_ring.size * RIO_MSG_DESC_SIZE,
+ msg_tx_ring.virt, msg_tx_ring.phys);
+
+ out_dma:
+ for (i = 0; i < msg_tx_ring.size; i++)
+ dma_free_coherent(NULL, RIO_MSG_BUFFER_SIZE,
+ msg_tx_ring.virt_buffer[i],
+ msg_tx_ring.phys_buffer[i]);
+
+ return rc;
+}
+
+/**
+ * rio_close_outb_mbox - Shut down MPC85xx outbound mailbox
+ * @mport: Master port implementing the outbound message unit
+ * @mbox: Mailbox to close
+ *
+ * Disables the outbound message unit, free all buffers, and
+ * frees the outbound message interrupt.
+ */
+void rio_close_outb_mbox(struct rio_mport *mport, int mbox)
+{
+ /* Disable inbound message unit */
+ out_be32((void *)&msg_regs->omr, 0);
+
+ /* Free ring */
+ dma_free_coherent(NULL, msg_tx_ring.size * RIO_MSG_DESC_SIZE,
+ msg_tx_ring.virt, msg_tx_ring.phys);
+
+ /* Free interrupt */
+ free_irq(MPC85xx_IRQ_RIO_TX, (void *)mport);
+}
+
+/**
+ * mpc85xx_rio_rx_handler - MPC85xx inbound message interrupt handler
+ * @irq: Linux interrupt number
+ * @dev_instance: Pointer to interrupt-specific data
+ * @regs: Register context
+ *
+ * Handles inbound message interrupts. Executes a registered inbound
+ * mailbox event handler and acks the interrupt occurence.
+ */
+static irqreturn_t
+mpc85xx_rio_rx_handler(int irq, void *dev_instance, struct pt_regs *regs)
+{
+ int isr;
+ struct rio_mport *port = (struct rio_mport *)dev_instance;
+
+ isr = in_be32((void *)&msg_regs->isr);
+
+ if (isr & RIO_MSG_ISR_TE) {
+ pr_info("RIO: inbound message reception error\n");
+ out_be32((void *)&msg_regs->isr, RIO_MSG_ISR_TE);
+ goto out;
+ }
+
+ /* XXX Need to check/dispatch until queue empty */
+ if (isr & RIO_MSG_ISR_DIQI) {
+ /*
+ * We implement *only* mailbox 0, but can receive messages
+ * for any mailbox/letter to that mailbox destination. So,
+ * make the callback with an unknown/invalid mailbox number
+ * argument.
+ */
+ port->inb_msg[0].mcback(port, msg_rx_ring.dev_id, -1, -1);
+
+ /* Ack the queueing interrupt */
+ out_be32((void *)&msg_regs->isr, RIO_MSG_ISR_DIQI);
+ }
+
+ out:
+ return IRQ_HANDLED;
+}
+
+/**
+ * rio_open_inb_mbox - Initialize MPC85xx inbound mailbox
+ * @mport: Master port implementing the inbound message unit
+ * @dev_id: Device specific pointer to pass on event
+ * @mbox: Mailbox to open
+ * @entries: Number of entries in the inbound mailbox ring
+ *
+ * Initializes buffer ring, request the inbound message interrupt,
+ * and enables the inbound message unit. Returns %0 on success
+ * and %-EINVAL or %-ENOMEM on failure.
+ */
+int rio_open_inb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entries)
+{
+ int i, rc = 0;
+
+ if ((entries < RIO_MIN_RX_RING_SIZE) ||
+ (entries > RIO_MAX_RX_RING_SIZE) || (!is_power_of_2(entries))) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ /* Initialize client buffer ring */
+ msg_rx_ring.dev_id = dev_id;
+ msg_rx_ring.size = entries;
+ msg_rx_ring.rx_slot = 0;
+ for (i = 0; i < msg_rx_ring.size; i++)
+ msg_rx_ring.virt_buffer[i] = NULL;
+
+ /* Initialize inbound message ring */
+ if (!(msg_rx_ring.virt = dma_alloc_coherent(NULL,
+ msg_rx_ring.size *
+ RIO_MAX_MSG_SIZE,
+ &msg_rx_ring.phys,
+ GFP_KERNEL))) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ /* Point dequeue/enqueue pointers at first entry in ring */
+ out_be32((void *)&msg_regs->ifqdpar, (u32) msg_rx_ring.phys);
+ out_be32((void *)&msg_regs->ifqepar, (u32) msg_rx_ring.phys);
+
+ /* Clear interrupt status */
+ out_be32((void *)&msg_regs->isr, 0x00000091);
+
+ /* Hook up inbound message handler */
+ if ((rc =
+ request_irq(MPC85xx_IRQ_RIO_RX, mpc85xx_rio_rx_handler, 0,
+ "msg_rx", (void *)mport)) < 0) {
+ dma_free_coherent(NULL, RIO_MSG_BUFFER_SIZE,
+ msg_tx_ring.virt_buffer[i],
+ msg_tx_ring.phys_buffer[i]);
+ goto out;
+ }
+
+ /*
+ * Configure inbound message unit:
+ * Snooping
+ * 4KB max message size
+ * Unmask all interrupt sources
+ * Disable
+ */
+ out_be32((void *)&msg_regs->imr, 0x001b0060);
+
+ /* Set number of queue entries */
+ out_be32((void *)&msg_regs->imr,
+ in_be32((void *)&msg_regs->imr) |
+ ((get_bitmask_order(entries) - 2) << 12));
+
+ /* Now enable the unit */
+ out_be32((void *)&msg_regs->imr, in_be32((void *)&msg_regs->imr) | 0x1);
+
+ out:
+ return rc;
+}
+
+/**
+ * rio_close_inb_mbox - Shut down MPC85xx inbound mailbox
+ * @mport: Master port implementing the inbound message unit
+ * @mbox: Mailbox to close
+ *
+ * Disables the inbound message unit, free all buffers, and
+ * frees the inbound message interrupt.
+ */
+void rio_close_inb_mbox(struct rio_mport *mport, int mbox)
+{
+ /* Disable inbound message unit */
+ out_be32((void *)&msg_regs->imr, 0);
+
+ /* Free ring */
+ dma_free_coherent(NULL, msg_rx_ring.size * RIO_MAX_MSG_SIZE,
+ msg_rx_ring.virt, msg_rx_ring.phys);
+
+ /* Free interrupt */
+ free_irq(MPC85xx_IRQ_RIO_RX, (void *)mport);
+}
+
+/**
+ * rio_hw_add_inb_buffer - Add buffer to the MPC85xx inbound message queue
+ * @mport: Master port implementing the inbound message unit
+ * @mbox: Inbound mailbox number
+ * @buf: Buffer to add to inbound queue
+ *
+ * Adds the @buf buffer to the MPC85xx inbound message queue. Returns
+ * %0 on success or %-EINVAL on failure.
+ */
+int rio_hw_add_inb_buffer(struct rio_mport *mport, int mbox, void *buf)
+{
+ int rc = 0;
+
+ pr_debug("RIO: rio_hw_add_inb_buffer(), msg_rx_ring.rx_slot %d\n",
+ msg_rx_ring.rx_slot);
+
+ if (msg_rx_ring.virt_buffer[msg_rx_ring.rx_slot]) {
+ printk(KERN_ERR
+ "RIO: error adding inbound buffer %d, buffer exists\n",
+ msg_rx_ring.rx_slot);
+ rc = -EINVAL;
+ goto out;
+ }
+
+ msg_rx_ring.virt_buffer[msg_rx_ring.rx_slot] = buf;
+ if (++msg_rx_ring.rx_slot == msg_rx_ring.size)
+ msg_rx_ring.rx_slot = 0;
+
+ out:
+ return rc;
+}
+
+EXPORT_SYMBOL_GPL(rio_hw_add_inb_buffer);
+
+/**
+ * rio_hw_get_inb_message - Fetch inbound message from the MPC85xx message unit
+ * @mport: Master port implementing the inbound message unit
+ * @mbox: Inbound mailbox number
+ *
+ * Gets the next available inbound message from the inbound message queue.
+ * A pointer to the message is returned on success or NULL on failure.
+ */
+void *rio_hw_get_inb_message(struct rio_mport *mport, int mbox)
+{
+ u32 imr;
+ u32 phys_buf, virt_buf;
+ void *buf = NULL;
+ int buf_idx;
+
+ phys_buf = in_be32((void *)&msg_regs->ifqdpar);
+
+ /* If no more messages, then bail out */
+ if (phys_buf == in_be32((void *)&msg_regs->ifqepar))
+ goto out2;
+
+ virt_buf = (u32) msg_rx_ring.virt + (phys_buf - msg_rx_ring.phys);
+ buf_idx = (phys_buf - msg_rx_ring.phys) / RIO_MAX_MSG_SIZE;
+ buf = msg_rx_ring.virt_buffer[buf_idx];
+
+ if (!buf) {
+ printk(KERN_ERR
+ "RIO: inbound message copy failed, no buffers\n");
+ goto out1;
+ }
+
+ /* Copy max message size, caller is expected to allocate that big */
+ memcpy(buf, (void *)virt_buf, RIO_MAX_MSG_SIZE);
+
+ /* Clear the available buffer */
+ msg_rx_ring.virt_buffer[buf_idx] = NULL;
+
+ out1:
+ imr = in_be32((void *)&msg_regs->imr);
+ out_be32((void *)&msg_regs->imr, imr | RIO_MSG_IMR_MI);
+
+ out2:
+ return buf;
+}
+
+EXPORT_SYMBOL_GPL(rio_hw_get_inb_message);
+
+/**
+ * mpc85xx_rio_dbell_handler - MPC85xx doorbell interrupt handler
+ * @irq: Linux interrupt number
+ * @dev_instance: Pointer to interrupt-specific data
+ * @regs: Register context
+ *
+ * Handles doorbell interrupts. Parses a list of registered
+ * doorbell event handlers and executes a matching event handler.
+ */
+static irqreturn_t
+mpc85xx_rio_dbell_handler(int irq, void *dev_instance, struct pt_regs *regs)
+{
+ int dsr;
+ struct rio_mport *port = (struct rio_mport *)dev_instance;
+
+ dsr = in_be32((void *)&msg_regs->dsr);
+
+ if (dsr & DOORBELL_DSR_TE) {
+ pr_info("RIO: doorbell reception error\n");
+ out_be32((void *)&msg_regs->dsr, DOORBELL_DSR_TE);
+ goto out;
+ }
+
+ if (dsr & DOORBELL_DSR_QFI) {
+ pr_info("RIO: doorbell queue full\n");
+ out_be32((void *)&msg_regs->dsr, DOORBELL_DSR_QFI);
+ goto out;
+ }
+
+ /* XXX Need to check/dispatch until queue empty */
+ if (dsr & DOORBELL_DSR_DIQI) {
+ u32 dmsg =
+ (u32) dbell_ring.virt +
+ (in_be32((void *)&msg_regs->dqdpar) & 0xfff);
+ u32 dmr;
+ struct rio_dbell *dbell;
+ int found = 0;
+
+ pr_debug
+ ("RIO: processing doorbell, sid %2.2x tid %2.2x info %4.4x\n",
+ DBELL_SID(dmsg), DBELL_TID(dmsg), DBELL_INF(dmsg));
+
+ list_for_each_entry(dbell, &port->dbells, node) {
+ if ((dbell->res->start <= DBELL_INF(dmsg)) &&
+ (dbell->res->end >= DBELL_INF(dmsg))) {
+ found = 1;
+ break;
+ }
+ }
+ if (found) {
+ dbell->dinb(port, dbell->dev_id, DBELL_SID(dmsg), DBELL_TID(dmsg),
+ DBELL_INF(dmsg));
+ } else {
+ pr_debug
+ ("RIO: spurious doorbell, sid %2.2x tid %2.2x info %4.4x\n",
+ DBELL_SID(dmsg), DBELL_TID(dmsg), DBELL_INF(dmsg));
+ }
+ dmr = in_be32((void *)&msg_regs->dmr);
+ out_be32((void *)&msg_regs->dmr, dmr | DOORBELL_DMR_DI);
+ out_be32((void *)&msg_regs->dsr, DOORBELL_DSR_DIQI);
+ }
+
+ out:
+ return IRQ_HANDLED;
+}
+
+/**
+ * mpc85xx_rio_doorbell_init - MPC85xx doorbell interface init
+ * @mport: Master port implementing the inbound doorbell unit
+ *
+ * Initializes doorbell unit hardware and inbound DMA buffer
+ * ring. Called from mpc85xx_rio_setup(). Returns %0 on success
+ * or %-ENOMEM on failure.
+ */
+static int mpc85xx_rio_doorbell_init(struct rio_mport *mport)
+{
+ int rc = 0;
+
+ /* Map outbound doorbell window immediately after maintenance window */
+ if (!(dbell_win =
+ (u32) ioremap(mport->iores.start + RIO_MAINT_WIN_SIZE,
+ RIO_DBELL_WIN_SIZE))) {
+ printk(KERN_ERR
+ "RIO: unable to map outbound doorbell window\n");
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ /* Initialize inbound doorbells */
+ if (!(dbell_ring.virt = dma_alloc_coherent(NULL,
+ 512 * DOORBELL_MESSAGE_SIZE,
+ &dbell_ring.phys,
+ GFP_KERNEL))) {
+ printk(KERN_ERR "RIO: unable allocate inbound doorbell ring\n");
+ rc = -ENOMEM;
+ iounmap((void *)dbell_win);
+ goto out;
+ }
+
+ /* Point dequeue/enqueue pointers at first entry in ring */
+ out_be32((void *)&msg_regs->dqdpar, (u32) dbell_ring.phys);
+ out_be32((void *)&msg_regs->dqepar, (u32) dbell_ring.phys);
+
+ /* Clear interrupt status */
+ out_be32((void *)&msg_regs->dsr, 0x00000091);
+
+ /* Hook up doorbell handler */
+ if ((rc =
+ request_irq(MPC85xx_IRQ_RIO_BELL, mpc85xx_rio_dbell_handler, 0,
+ "dbell_rx", (void *)mport) < 0)) {
+ iounmap((void *)dbell_win);
+ dma_free_coherent(NULL, 512 * DOORBELL_MESSAGE_SIZE,
+ dbell_ring.virt, dbell_ring.phys);
+ printk(KERN_ERR
+ "MPC85xx RIO: unable to request inbound doorbell irq");
+ goto out;
+ }
+
+ /* Configure doorbells for snooping, 512 entries, and enable */
+ out_be32((void *)&msg_regs->dmr, 0x00108161);
+
+ out:
+ return rc;
+}
+
+static char *cmdline = NULL;
+
+static int mpc85xx_rio_get_hdid(int index)
+{
+ /* XXX Need to parse multiple entries in some format */
+ if (!cmdline)
+ return -1;
+
+ return simple_strtol(cmdline, NULL, 0);
+}
+
+static int mpc85xx_rio_get_cmdline(char *s)
+{
+ if (!s)
+ return 0;
+
+ cmdline = s;
+ return 1;
+}
+
+__setup("riohdid=", mpc85xx_rio_get_cmdline);
+
+/**
+ * mpc85xx_rio_setup - Setup MPC85xx RapidIO interface
+ * @law_start: Starting physical address of RapidIO LAW
+ * @law_size: Size of RapidIO LAW
+ *
+ * Initializes MPC85xx RapidIO hardware interface, configures
+ * master port with system-specific info, and registers the
+ * master port with the RapidIO subsystem.
+ */
+void mpc85xx_rio_setup(int law_start, int law_size)
+{
+ struct rio_ops *ops;
+ struct rio_mport *port;
+
+ ops = kmalloc(sizeof(struct rio_ops), GFP_KERNEL);
+ ops->lcread = mpc85xx_local_config_read;
+ ops->lcwrite = mpc85xx_local_config_write;
+ ops->cread = mpc85xx_rio_config_read;
+ ops->cwrite = mpc85xx_rio_config_write;
+ ops->dsend = mpc85xx_rio_doorbell_send;
+
+ port = kmalloc(sizeof(struct rio_mport), GFP_KERNEL);
+ port->id = 0;
+ port->index = 0;
+ INIT_LIST_HEAD(&port->dbells);
+ port->iores.start = law_start;
+ port->iores.end = law_start + law_size;
+ port->iores.flags = IORESOURCE_MEM;
+
+ rio_init_dbell_res(&port->riores[RIO_DOORBELL_RESOURCE], 0, 0xffff);
+ rio_init_mbox_res(&port->riores[RIO_INB_MBOX_RESOURCE], 0, 0);
+ rio_init_mbox_res(&port->riores[RIO_OUTB_MBOX_RESOURCE], 0, 0);
+ strcpy(port->name, "RIO0 mport");
+
+ port->ops = ops;
+ port->host_deviceid = mpc85xx_rio_get_hdid(port->id);
+
+ rio_register_mport(port);
+
+ regs_win = (u32) ioremap(RIO_REGS_BASE, 0x20000);
+ atmu_regs = (struct rio_atmu_regs *)(regs_win + RIO_ATMU_REGS_OFFSET);
+ maint_atmu_regs = atmu_regs + 1;
+ dbell_atmu_regs = atmu_regs + 2;
+ msg_regs = (struct rio_msg_regs *)(regs_win + RIO_MSG_REGS_OFFSET);
+
+ /* Configure maintenance transaction window */
+ out_be32((void *)&maint_atmu_regs->rowbar, 0x000c0000);
+ out_be32((void *)&maint_atmu_regs->rowar, 0x80077015);
+
+ maint_win = (u32) ioremap(law_start, RIO_MAINT_WIN_SIZE);
+
+ /* Configure outbound doorbell window */
+ out_be32((void *)&dbell_atmu_regs->rowbar, 0x000c0400);
+ out_be32((void *)&dbell_atmu_regs->rowar, 0x8004200b);
+ mpc85xx_rio_doorbell_init(port);
+}
diff --git a/arch/ppc/syslib/ppc85xx_rio.h b/arch/ppc/syslib/ppc85xx_rio.h
new file mode 100644
index 000000000000..c0827a2c3eec
--- /dev/null
+++ b/arch/ppc/syslib/ppc85xx_rio.h
@@ -0,0 +1,21 @@
+/*
+ * MPC85xx RapidIO definitions
+ *
+ * Copyright 2005 MontaVista Software, Inc.
+ * Matt Porter
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __PPC_SYSLIB_PPC85XX_RIO_H
+#define __PPC_SYSLIB_PPC85XX_RIO_H
+
+#include
+#include
+
+extern void mpc85xx_rio_setup(int law_start, int law_size);
+
+#endif /* __PPC_SYSLIB_PPC85XX_RIO_H */
diff --git a/arch/ppc/syslib/ppc_sys.c b/arch/ppc/syslib/ppc_sys.c
index 62ee86e80711..603f01190816 100644
--- a/arch/ppc/syslib/ppc_sys.c
+++ b/arch/ppc/syslib/ppc_sys.c
@@ -14,6 +14,7 @@
* option) any later version.
*/
+#include
#include