diff --git a/CREDITS b/CREDITS index 8e577ce4abeb..6957ef4efab3 100644 --- a/CREDITS +++ b/CREDITS @@ -3101,7 +3101,7 @@ S: Minto, NSW, 2566 S: Australia N: Stephen Smalley -E: sds@epoch.ncsc.mil +E: sds@tycho.nsa.gov D: portions of the Linux Security Module (LSM) framework and security modules N: Chris Smith diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt index fcbcbc35b122..6221464d1a7e 100644 --- a/Documentation/RCU/RTFP.txt +++ b/Documentation/RCU/RTFP.txt @@ -90,16 +90,20 @@ at OLS. The resulting abundance of RCU patches was presented the following year [McKenney02a], and use of RCU in dcache was first described that same year [Linder02a]. -Also in 2002, Michael [Michael02b,Michael02a] presented techniques -that defer the destruction of data structures to simplify non-blocking -synchronization (wait-free synchronization, lock-free synchronization, -and obstruction-free synchronization are all examples of non-blocking -synchronization). In particular, this technique eliminates locking, -reduces contention, reduces memory latency for readers, and parallelizes -pipeline stalls and memory latency for writers. However, these -techniques still impose significant read-side overhead in the form of -memory barriers. Researchers at Sun worked along similar lines in the -same timeframe [HerlihyLM02,HerlihyLMS03]. +Also in 2002, Michael [Michael02b,Michael02a] presented "hazard-pointer" +techniques that defer the destruction of data structures to simplify +non-blocking synchronization (wait-free synchronization, lock-free +synchronization, and obstruction-free synchronization are all examples of +non-blocking synchronization). In particular, this technique eliminates +locking, reduces contention, reduces memory latency for readers, and +parallelizes pipeline stalls and memory latency for writers. However, +these techniques still impose significant read-side overhead in the +form of memory barriers. Researchers at Sun worked along similar lines +in the same timeframe [HerlihyLM02,HerlihyLMS03]. These techniques +can be thought of as inside-out reference counts, where the count is +represented by the number of hazard pointers referencing a given data +structure (rather than the more conventional counter field within the +data structure itself). In 2003, the K42 group described how RCU could be used to create hot-pluggable implementations of operating-system functions. Later that @@ -113,7 +117,6 @@ number of operating-system kernels [PaulEdwardMcKenneyPhD], a paper describing how to make RCU safe for soft-realtime applications [Sarma04c], and a paper describing SELinux performance with RCU [JamesMorris04b]. - 2005 has seen further adaptation of RCU to realtime use, permitting preemption of RCU realtime critical sections [PaulMcKenney05a, PaulMcKenney05b]. diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index e118a7c1a092..49e27cc19385 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -177,3 +177,9 @@ over a rather long period of time, but improvements are always welcome! If you want to wait for some of these other things, you might instead need to use synchronize_irq() or synchronize_sched(). + +12. Any lock acquired by an RCU callback must be acquired elsewhere + with irq disabled, e.g., via spin_lock_irqsave(). Failing to + disable irq on a given acquisition of that lock will result in + deadlock as soon as the RCU callback happens to interrupt that + acquisition's critical section. diff --git a/Documentation/RCU/listRCU.txt b/Documentation/RCU/listRCU.txt index f8a54fa0d8ab..1fd175368a87 100644 --- a/Documentation/RCU/listRCU.txt +++ b/Documentation/RCU/listRCU.txt @@ -232,7 +232,7 @@ entry does not exist. For this to be helpful, the search function must return holding the per-entry spinlock, as ipc_lock() does in fact do. Quick Quiz: Why does the search function need to return holding the -per-entry lock for this deleted-flag technique to be helpful? + per-entry lock for this deleted-flag technique to be helpful? If the system-call audit module were to ever need to reject stale data, one way to accomplish this would be to add a "deleted" flag and a "lock" @@ -275,8 +275,8 @@ flag under the spinlock as follows: { struct audit_entry *e; - /* Do not use the _rcu iterator here, since this is the only - * deletion routine. */ + /* Do not need to use the _rcu iterator here, since this + * is the only deletion routine. */ list_for_each_entry(e, list, list) { if (!audit_compare_rule(rule, &e->rule)) { spin_lock(&e->lock); @@ -304,9 +304,12 @@ function to reject newly deleted data. Answer to Quick Quiz + Why does the search function need to return holding the per-entry + lock for this deleted-flag technique to be helpful? -If the search function drops the per-entry lock before returning, then -the caller will be processing stale data in any case. If it is really -OK to be processing stale data, then you don't need a "deleted" flag. -If processing stale data really is a problem, then you need to hold the -per-entry lock across all of the code that uses the value looked up. + If the search function drops the per-entry lock before returning, + then the caller will be processing stale data in any case. If it + is really OK to be processing stale data, then you don't need a + "deleted" flag. If processing stale data really is a problem, + then you need to hold the per-entry lock across all of the code + that uses the value that was returned. diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt index 6fa092251586..02e27bf1d365 100644 --- a/Documentation/RCU/rcu.txt +++ b/Documentation/RCU/rcu.txt @@ -111,6 +111,11 @@ o What are all these files in this directory? You are reading it! + rcuref.txt + + Describes how to combine use of reference counts + with RCU. + whatisRCU.txt Overview of how the RCU implementation works. Along diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.txt index 3f60db41b2f0..451de2ad8329 100644 --- a/Documentation/RCU/rcuref.txt +++ b/Documentation/RCU/rcuref.txt @@ -1,7 +1,7 @@ -Refcounter design for elements of lists/arrays protected by RCU. +Reference-count design for elements of lists/arrays protected by RCU. -Refcounting on elements of lists which are protected by traditional -reader/writer spinlocks or semaphores are straight forward as in: +Reference counting on elements of lists which are protected by traditional +reader/writer spinlocks or semaphores are straightforward: 1. 2. add() search_and_reference() @@ -28,12 +28,12 @@ release_referenced() delete() ... } -If this list/array is made lock free using rcu as in changing the -write_lock in add() and delete() to spin_lock and changing read_lock +If this list/array is made lock free using RCU as in changing the +write_lock() in add() and delete() to spin_lock and changing read_lock in search_and_reference to rcu_read_lock(), the atomic_get in search_and_reference could potentially hold reference to an element which -has already been deleted from the list/array. atomic_inc_not_zero takes -care of this scenario. search_and_reference should look as; +has already been deleted from the list/array. Use atomic_inc_not_zero() +in this scenario as follows: 1. 2. add() search_and_reference() @@ -51,17 +51,16 @@ add() search_and_reference() release_referenced() delete() { { ... write_lock(&list_lock); - atomic_dec(&el->rc, relfunc) ... - ... delete_element -} write_unlock(&list_lock); - ... + if (atomic_dec_and_test(&el->rc)) ... + call_rcu(&el->head, el_free); delete_element + ... write_unlock(&list_lock); +} ... if (atomic_dec_and_test(&el->rc)) call_rcu(&el->head, el_free); ... } -Sometimes, reference to the element need to be obtained in the -update (write) stream. In such cases, atomic_inc_not_zero might be an -overkill since the spinlock serialising list updates are held. atomic_inc -is to be used in such cases. - +Sometimes, a reference to the element needs to be obtained in the +update (write) stream. In such cases, atomic_inc_not_zero() might be +overkill, since we hold the update-side spinlock. One might instead +use atomic_inc() in such cases. diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 15da16861fa3..5ed85af88789 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -200,10 +200,11 @@ rcu_assign_pointer() the new value, and also executes any memory-barrier instructions required for a given CPU architecture. - Perhaps more important, it serves to document which pointers - are protected by RCU. That said, rcu_assign_pointer() is most - frequently used indirectly, via the _rcu list-manipulation - primitives such as list_add_rcu(). + Perhaps just as important, it serves to document (1) which + pointers are protected by RCU and (2) the point at which a + given structure becomes accessible to other CPUs. That said, + rcu_assign_pointer() is most frequently used indirectly, via + the _rcu list-manipulation primitives such as list_add_rcu(). rcu_dereference() @@ -258,9 +259,11 @@ rcu_dereference() locking. As with rcu_assign_pointer(), an important function of - rcu_dereference() is to document which pointers are protected - by RCU. And, again like rcu_assign_pointer(), rcu_dereference() - is typically used indirectly, via the _rcu list-manipulation + rcu_dereference() is to document which pointers are protected by + RCU, in particular, flagging a pointer that is subject to changing + at any time, including immediately after the rcu_dereference(). + And, again like rcu_assign_pointer(), rcu_dereference() is + typically used indirectly, via the _rcu list-manipulation primitives, such as list_for_each_entry_rcu(). The following diagram shows how each API communicates among the @@ -327,7 +330,7 @@ for specialized uses, but are relatively uncommon. 3. WHAT ARE SOME EXAMPLE USES OF CORE RCU API? This section shows a simple use of the core RCU API to protect a -global pointer to a dynamically allocated structure. More typical +global pointer to a dynamically allocated structure. More-typical uses of RCU may be found in listRCU.txt, arrayRCU.txt, and NMI-RCU.txt. struct foo { @@ -410,6 +413,8 @@ o Use synchronize_rcu() -after- removing a data element from an data item. See checklist.txt for additional rules to follow when using RCU. +And again, more-typical uses of RCU may be found in listRCU.txt, +arrayRCU.txt, and NMI-RCU.txt. 4. WHAT IF MY UPDATING THREAD CANNOT BLOCK? @@ -513,7 +518,7 @@ production-quality implementation, and see: for papers describing the Linux kernel RCU implementation. The OLS'01 and OLS'02 papers are a good introduction, and the dissertation provides -more details on the current implementation. +more details on the current implementation as of early 2004. 5A. "TOY" IMPLEMENTATION #1: LOCKING @@ -768,7 +773,6 @@ RCU pointer/list traversal: rcu_dereference list_for_each_rcu (to be deprecated in favor of list_for_each_entry_rcu) - list_for_each_safe_rcu (deprecated, not used) list_for_each_entry_rcu list_for_each_continue_rcu (to be deprecated in favor of new list_for_each_entry_continue_rcu) @@ -807,7 +811,8 @@ Quick Quiz #1: Why is this argument naive? How could a deadlock Answer: Consider the following sequence of events: 1. CPU 0 acquires some unrelated lock, call it - "problematic_lock". + "problematic_lock", disabling irq via + spin_lock_irqsave(). 2. CPU 1 enters synchronize_rcu(), write-acquiring rcu_gp_mutex. @@ -894,7 +899,7 @@ Answer: Just as PREEMPT_RT permits preemption of spinlock ACKNOWLEDGEMENTS My thanks to the people who helped make this human-readable, including -Jon Walpole, Josh Triplett, Serge Hallyn, and Suzanne Wood. +Jon Walpole, Josh Triplett, Serge Hallyn, Suzanne Wood, and Alan Stern. For more information, see http://www.rdrop.com/users/paulmck/RCU. diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt new file mode 100644 index 000000000000..ff280e2e1613 --- /dev/null +++ b/Documentation/cputopology.txt @@ -0,0 +1,41 @@ + +Export cpu topology info by sysfs. Items (attributes) are similar +to /proc/cpuinfo. + +1) /sys/devices/system/cpu/cpuX/topology/physical_package_id: +represent the physical package id of cpu X; +2) /sys/devices/system/cpu/cpuX/topology/core_id: +represent the cpu core id to cpu X; +3) /sys/devices/system/cpu/cpuX/topology/thread_siblings: +represent the thread siblings to cpu X in the same core; +4) /sys/devices/system/cpu/cpuX/topology/core_siblings: +represent the thread siblings to cpu X in the same physical package; + +To implement it in an architecture-neutral way, a new source file, +driver/base/topology.c, is to export the 5 attributes. + +If one architecture wants to support this feature, it just needs to +implement 4 defines, typically in file include/asm-XXX/topology.h. +The 4 defines are: +#define topology_physical_package_id(cpu) +#define topology_core_id(cpu) +#define topology_thread_siblings(cpu) +#define topology_core_siblings(cpu) + +The type of **_id is int. +The type of siblings is cpumask_t. + +To be consistent on all architectures, the 4 attributes should have +deafult values if their values are unavailable. Below is the rule. +1) physical_package_id: If cpu has no physical package id, -1 is the +default value. +2) core_id: If cpu doesn't support multi-core, its core id is 0. +3) thread_siblings: Just include itself, if the cpu doesn't support +HT/multi-thread. +4) core_siblings: Just include itself, if the cpu doesn't support +multi-core and HT/Multi-thread. + +So be careful when declaring the 4 defines in include/asm-XXX/topology.h. + +If an attribute isn't defined on an architecture, it won't be exported. + diff --git a/Documentation/driver-model/overview.txt b/Documentation/driver-model/overview.txt index 44662735cf81..ac4a7a737e43 100644 --- a/Documentation/driver-model/overview.txt +++ b/Documentation/driver-model/overview.txt @@ -1,50 +1,43 @@ The Linux Kernel Device Model -Patrick Mochel +Patrick Mochel -26 August 2002 +Drafted 26 August 2002 +Updated 31 January 2006 Overview ~~~~~~~~ -This driver model is a unification of all the current, disparate driver models -that are currently in the kernel. It is intended to augment the +The Linux Kernel Driver Model is a unification of all the disparate driver +models that were previously used in the kernel. It is intended to augment the bus-specific drivers for bridges and devices by consolidating a set of data and operations into globally accessible data structures. -Current driver models implement some sort of tree-like structure (sometimes -just a list) for the devices they control. But, there is no linkage between -the different bus types. +Traditional driver models implemented some sort of tree-like structure +(sometimes just a list) for the devices they control. There wasn't any +uniformity across the different bus types. -A common data structure can provide this linkage with little overhead: when a -bus driver discovers a particular device, it can insert it into the global -tree as well as its local tree. In fact, the local tree becomes just a subset -of the global tree. - -Common data fields can also be moved out of the local bus models into the -global model. Some of the manipulations of these fields can also be -consolidated. Most likely, manipulation functions will become a set -of helper functions, which the bus drivers wrap around to include any -bus-specific items. - -The common device and bridge interface currently reflects the goals of the -modern PC: namely the ability to do seamless Plug and Play, power management, -and hot plug. (The model dictated by Intel and Microsoft (read: ACPI) ensures -us that any device in the system may fit any of these criteria.) - -In reality, not every bus will be able to support such operations. But, most -buses will support a majority of those operations, and all future buses will. -In other words, a bus that doesn't support an operation is the exception, -instead of the other way around. +The current driver model provides a comon, uniform data model for describing +a bus and the devices that can appear under the bus. The unified bus +model includes a set of common attributes which all busses carry, and a set +of common callbacks, such as device discovery during bus probing, bus +shutdown, bus power management, etc. +The common device and bridge interface reflects the goals of the modern +computer: namely the ability to do seamless device "plug and play", power +management, and hot plug. In particular, the model dictated by Intel and +Microsoft (namely ACPI) ensures that almost every device on almost any bus +on an x86-compatible system can work within this paradigm. Of course, +not every bus is able to support all such operations, although most +buses support a most of those operations. Downstream Access ~~~~~~~~~~~~~~~~~ Common data fields have been moved out of individual bus layers into a common -data structure. But, these fields must still be accessed by the bus layers, +data structure. These fields must still be accessed by the bus layers, and sometimes by the device-specific drivers. Other bus layers are encouraged to do what has been done for the PCI layer. @@ -53,7 +46,7 @@ struct pci_dev now looks like this: struct pci_dev { ... - struct device device; + struct device dev; }; Note first that it is statically allocated. This means only one allocation on @@ -64,9 +57,9 @@ the two. The PCI bus layer freely accesses the fields of struct device. It knows about the structure of struct pci_dev, and it should know the structure of struct -device. PCI devices that have been converted generally do not touch the fields -of struct device. More precisely, device-specific drivers should not touch -fields of struct device unless there is a strong compelling reason to do so. +device. Individual PCI device drivers that have been converted the the current +driver model generally do not and should not touch the fields of struct device, +unless there is a strong compelling reason to do so. This abstraction is prevention of unnecessary pain during transitional phases. If the name of the field changes or is removed, then every downstream driver diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index b4a1ea762698..4d4897c8ef96 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -148,3 +148,17 @@ Why: The 8250 serial driver now has the ability to deal with the differences brother on Alchemy SOCs. The loss of features is not considered an issue. Who: Ralf Baechle + +--------------------------- + +What: Legacy /proc/pci interface (PCI_LEGACY_PROC) +When: March 2006 +Why: deprecated since 2.5.53 in favor of lspci(8) +Who: Adrian Bunk + +--------------------------- + +What: pci_module_init(driver) +When: January 2007 +Why: Is replaced by pci_register_driver(pci_driver). +Who: Richard Knutsson and Greg Kroah-Hartman diff --git a/Documentation/filesystems/configfs/configfs_example.c b/Documentation/filesystems/configfs/configfs_example.c index f3c6e4946f98..3d4713a6c207 100644 --- a/Documentation/filesystems/configfs/configfs_example.c +++ b/Documentation/filesystems/configfs/configfs_example.c @@ -320,6 +320,7 @@ static struct config_item_type simple_children_type = { .ct_item_ops = &simple_children_item_ops, .ct_group_ops = &simple_children_group_ops, .ct_attrs = simple_children_attrs, + .ct_owner = THIS_MODULE, }; static struct configfs_subsystem simple_children_subsys = { @@ -403,6 +404,7 @@ static struct config_item_type group_children_type = { .ct_item_ops = &group_children_item_ops, .ct_group_ops = &group_children_group_ops, .ct_attrs = group_children_attrs, + .ct_owner = THIS_MODULE, }; static struct configfs_subsystem group_children_subsys = { diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt index f2595caf052e..4389c684a80a 100644 --- a/Documentation/filesystems/ocfs2.txt +++ b/Documentation/filesystems/ocfs2.txt @@ -35,6 +35,7 @@ Features which OCFS2 does not support yet: be cluster coherent. - quotas - cluster aware flock + - cluster aware lockf - Directory change notification (F_NOTIFY) - Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease) - POSIX ACLs diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt index c406ce67edd0..c65233d430f0 100644 --- a/Documentation/kernel-doc-nano-HOWTO.txt +++ b/Documentation/kernel-doc-nano-HOWTO.txt @@ -45,10 +45,10 @@ How to extract the documentation If you just want to read the ready-made books on the various subsystems (see Documentation/DocBook/*.tmpl), just type 'make -psdocs', or 'make pdfdocs', or 'make htmldocs', depending on your -preference. If you would rather read a different format, you can type -'make sgmldocs' and then use DocBook tools to convert -Documentation/DocBook/*.sgml to a format of your choice (for example, +psdocs', or 'make pdfdocs', or 'make htmldocs', depending on your +preference. If you would rather read a different format, you can type +'make sgmldocs' and then use DocBook tools to convert +Documentation/DocBook/*.sgml to a format of your choice (for example, 'db2html ...' if 'make htmldocs' was not defined). If you want to see man pages instead, you can do this: @@ -124,6 +124,36 @@ patterns, which are highlighted appropriately. Take a look around the source tree for examples. +kernel-doc for structs, unions, enums, and typedefs +--------------------------------------------------- + +Beside functions you can also write documentation for structs, unions, +enums and typedefs. Instead of the function name you must write the name +of the declaration; the struct/union/enum/typedef must always precede +the name. Nesting of declarations is not supported. +Use the argument mechanism to document members or constants. + +Inside a struct description, you can use the "private:" and "public:" +comment tags. Structure fields that are inside a "private:" area +are not listed in the generated output documentation. + +Example: + +/** + * struct my_struct - short description + * @a: first member + * @b: second member + * + * Longer description + */ +struct my_struct { + int a; + int b; +/* private: */ + int c; +}; + + How to make new SGML template files ----------------------------------- @@ -147,4 +177,3 @@ documentation, in , for the functions listed. Tim. */ - diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 1cbcf65b764b..84370363da80 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -452,6 +452,11 @@ running once the system is up. eata= [HW,SCSI] + ec_intr= [HW,ACPI] ACPI Embedded Controller interrupt mode + Format: + 0: polling mode + non-0: interrupt mode (default) + eda= [HW,PS2] edb= [HW,PS2] diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 2b7cf19a06ad..26364d06ae92 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -427,6 +427,23 @@ icmp_ignore_bogus_error_responses - BOOLEAN will avoid log file clutter. Default: FALSE +icmp_errors_use_inbound_ifaddr - BOOLEAN + + If zero, icmp error messages are sent with the primary address of + the exiting interface. + + If non-zero, the message will be sent with the primary address of + the interface that received the packet that caused the icmp error. + This is the behaviour network many administrators will expect from + a router. And it can make debugging complicated network layouts + much easier. + + Note that if no primary address exists for the interface selected, + then the primary address of the first non-loopback interface that + has one will be used regarldess of this setting. + + Default: 0 + igmp_max_memberships - INTEGER Change the maximum number of multicast groups we can subscribe to. Default: 20 diff --git a/Documentation/parport-lowlevel.txt b/Documentation/parport-lowlevel.txt index 1d40008a1926..8f2302415eff 100644 --- a/Documentation/parport-lowlevel.txt +++ b/Documentation/parport-lowlevel.txt @@ -1068,7 +1068,7 @@ SYNOPSIS struct parport_operations { ... - void (*write_status) (struct parport *port, unsigned char s); + void (*write_control) (struct parport *port, unsigned char s); ... }; @@ -1097,9 +1097,9 @@ SYNOPSIS struct parport_operations { ... - void (*frob_control) (struct parport *port, - unsigned char mask, - unsigned char val); + unsigned char (*frob_control) (struct parport *port, + unsigned char mask, + unsigned char val); ... }; diff --git a/Documentation/pci-error-recovery.txt b/Documentation/pci-error-recovery.txt index d089967e4948..634d3e5b5756 100644 --- a/Documentation/pci-error-recovery.txt +++ b/Documentation/pci-error-recovery.txt @@ -1,246 +1,396 @@ PCI Error Recovery ------------------ - May 31, 2005 + February 2, 2006 - Current document maintainer: - Linas Vepstas + Current document maintainer: + Linas Vepstas -Some PCI bus controllers are able to detect certain "hard" PCI errors -on the bus, such as parity errors on the data and address busses, as -well as SERR and PERR errors. These chipsets are then able to disable -I/O to/from the affected device, so that, for example, a bad DMA -address doesn't end up corrupting system memory. These same chipsets -are also able to reset the affected PCI device, and return it to -working condition. This document describes a generic API form -performing error recovery. +Many PCI bus controllers are able to detect a variety of hardware +PCI errors on the bus, such as parity errors on the data and address +busses, as well as SERR and PERR errors. Some of the more advanced +chipsets are able to deal with these errors; these include PCI-E chipsets, +and the PCI-host bridges found on IBM Power4 and Power5-based pSeries +boxes. A typical action taken is to disconnect the affected device, +halting all I/O to it. The goal of a disconnection is to avoid system +corruption; for example, to halt system memory corruption due to DMA's +to "wild" addresses. Typically, a reconnection mechanism is also +offered, so that the affected PCI device(s) are reset and put back +into working condition. The reset phase requires coordination +between the affected device drivers and the PCI controller chip. +This document describes a generic API for notifying device drivers +of a bus disconnection, and then performing error recovery. +This API is currently implemented in the 2.6.16 and later kernels. -The core idea is that after a PCI error has been detected, there must -be a way for the kernel to coordinate with all affected device drivers -so that the pci card can be made operational again, possibly after -performing a full electrical #RST of the PCI card. The API below -provides a generic API for device drivers to be notified of PCI -errors, and to be notified of, and respond to, a reset sequence. +Reporting and recovery is performed in several steps. First, when +a PCI hardware error has resulted in a bus disconnect, that event +is reported as soon as possible to all affected device drivers, +including multiple instances of a device driver on multi-function +cards. This allows device drivers to avoid deadlocking in spinloops, +waiting for some i/o-space register to change, when it never will. +It also gives the drivers a chance to defer incoming I/O as +needed. -Preliminary sketch of API, cut-n-pasted-n-modified email from -Ben Herrenschmidt, circa 5 april 2005 +Next, recovery is performed in several stages. Most of the complexity +is forced by the need to handle multi-function devices, that is, +devices that have multiple device drivers associated with them. +In the first stage, each driver is allowed to indicate what type +of reset it desires, the choices being a simple re-enabling of I/O +or requesting a hard reset (a full electrical #RST of the PCI card). +If any driver requests a full reset, that is what will be done. + +After a full reset and/or a re-enabling of I/O, all drivers are +again notified, so that they may then perform any device setup/config +that may be required. After these have all completed, a final +"resume normal operations" event is sent out. + +The biggest reason for choosing a kernel-based implementation rather +than a user-space implementation was the need to deal with bus +disconnects of PCI devices attached to storage media, and, in particular, +disconnects from devices holding the root file system. If the root +file system is disconnected, a user-space mechanism would have to go +through a large number of contortions to complete recovery. Almost all +of the current Linux file systems are not tolerant of disconnection +from/reconnection to their underlying block device. By contrast, +bus errors are easy to manage in the device driver. Indeed, most +device drivers already handle very similar recovery procedures; +for example, the SCSI-generic layer already provides significant +mechanisms for dealing with SCSI bus errors and SCSI bus resets. + + +Detailed Design +--------------- +Design and implementation details below, based on a chain of +public email discussions with Ben Herrenschmidt, circa 5 April 2005. The error recovery API support is exposed to the driver in the form of a structure of function pointers pointed to by a new field in struct -pci_driver. The absence of this pointer in pci_driver denotes an -"non-aware" driver, behaviour on these is platform dependant. -Platforms like ppc64 can try to simulate pci hotplug remove/add. - -The definition of "pci_error_token" is not covered here. It is based on -Seto's work on the synchronous error detection. We still need to define -functions for extracting infos out of an opaque error token. This is -separate from this API. +pci_driver. A driver that fails to provide the structure is "non-aware", +and the actual recovery steps taken are platform dependent. The +arch/powerpc implementation will simulate a PCI hotplug remove/add. This structure has the form: - struct pci_error_handlers { - int (*error_detected)(struct pci_dev *dev, pci_error_token error); + int (*error_detected)(struct pci_dev *dev, enum pci_channel_state); int (*mmio_enabled)(struct pci_dev *dev); - int (*resume)(struct pci_dev *dev); int (*link_reset)(struct pci_dev *dev); int (*slot_reset)(struct pci_dev *dev); + void (*resume)(struct pci_dev *dev); }; -A driver doesn't have to implement all of these callbacks. The -only mandatory one is error_detected(). If a callback is not -implemented, the corresponding feature is considered unsupported. -For example, if mmio_enabled() and resume() aren't there, then the -driver is assumed as not doing any direct recovery and requires +The possible channel states are: +enum pci_channel_state { + pci_channel_io_normal, /* I/O channel is in normal state */ + pci_channel_io_frozen, /* I/O to channel is blocked */ + pci_channel_io_perm_failure, /* PCI card is dead */ +}; + +Possible return values are: +enum pci_ers_result { + PCI_ERS_RESULT_NONE, /* no result/none/not supported in device driver */ + PCI_ERS_RESULT_CAN_RECOVER, /* Device driver can recover without slot reset */ + PCI_ERS_RESULT_NEED_RESET, /* Device driver wants slot to be reset. */ + PCI_ERS_RESULT_DISCONNECT, /* Device has completely failed, is unrecoverable */ + PCI_ERS_RESULT_RECOVERED, /* Device driver is fully recovered and operational */ +}; + +A driver does not have to implement all of these callbacks; however, +if it implements any, it must implement error_detected(). If a callback +is not implemented, the corresponding feature is considered unsupported. +For example, if mmio_enabled() and resume() aren't there, then it +is assumed that the driver is not doing any direct recovery and requires a reset. If link_reset() is not implemented, the card is assumed as -not caring about link resets, in which case, if recover is supported, -the core can try recover (but not slot_reset() unless it really did -reset the slot). If slot_reset() is not supported, link_reset() can -be called instead on a slot reset. +not care about link resets. Typically a driver will want to know about +a slot_reset(). -At first, the call will always be : +The actual steps taken by a platform to recover from a PCI error +event will be platform-dependent, but will follow the general +sequence described below. - 1) error_detected() +STEP 0: Error Event +------------------- +PCI bus error is detect by the PCI hardware. On powerpc, the slot +is isolated, in that all I/O is blocked: all reads return 0xffffffff, +all writes are ignored. - Error detected. This is sent once after an error has been detected. At -this point, the device might not be accessible anymore depending on the -platform (the slot will be isolated on ppc64). The driver may already -have "noticed" the error because of a failing IO, but this is the proper -"synchronisation point", that is, it gives a chance to the driver to -cleanup, waiting for pending stuff (timers, whatever, etc...) to -complete; it can take semaphores, schedule, etc... everything but touch -the device. Within this function and after it returns, the driver + +STEP 1: Notification +-------------------- +Platform calls the error_detected() callback on every instance of +every driver affected by the error. + +At this point, the device might not be accessible anymore, depending on +the platform (the slot will be isolated on powerpc). The driver may +already have "noticed" the error because of a failing I/O, but this +is the proper "synchronization point", that is, it gives the driver +a chance to cleanup, waiting for pending stuff (timers, whatever, etc...) +to complete; it can take semaphores, schedule, etc... everything but +touch the device. Within this function and after it returns, the driver shouldn't do any new IOs. Called in task context. This is sort of a "quiesce" point. See note about interrupts at the end of this doc. - Result codes: - - PCIERR_RESULT_CAN_RECOVER: - Driever returns this if it thinks it might be able to recover +All drivers participating in this system must implement this call. +The driver must return one of the following result codes: + - PCI_ERS_RESULT_CAN_RECOVER: + Driver returns this if it thinks it might be able to recover the HW by just banging IOs or if it wants to be given - a chance to extract some diagnostic informations (see - below). - - PCIERR_RESULT_NEED_RESET: - Driver returns this if it thinks it can't recover unless the - slot is reset. - - PCIERR_RESULT_DISCONNECT: - Return this if driver thinks it won't recover at all, - (this will detach the driver ? or just leave it - dangling ? to be decided) + a chance to extract some diagnostic information (see + mmio_enable, below). + - PCI_ERS_RESULT_NEED_RESET: + Driver returns this if it can't recover without a hard + slot reset. + - PCI_ERS_RESULT_DISCONNECT: + Driver returns this if it doesn't want to recover at all. -So at this point, we have called error_detected() for all drivers -on the segment that had the error. On ppc64, the slot is isolated. What -happens now typically depends on the result from the drivers. If all -drivers on the segment/slot return PCIERR_RESULT_CAN_RECOVER, we would -re-enable IOs on the slot (or do nothing special if the platform doesn't -isolate slots) and call 2). If not and we can reset slots, we go to 4), -if neither, we have a dead slot. If it's an hotplug slot, we might -"simulate" reset by triggering HW unplug/replug though. +The next step taken will depend on the result codes returned by the +drivers. ->>> Current ppc64 implementation assumes that a device driver will ->>> *not* schedule or semaphore in this routine; the current ppc64 +If all drivers on the segment/slot return PCI_ERS_RESULT_CAN_RECOVER, +then the platform should re-enable IOs on the slot (or do nothing in +particular, if the platform doesn't isolate slots), and recovery +proceeds to STEP 2 (MMIO Enable). + +If any driver requested a slot reset (by returning PCI_ERS_RESULT_NEED_RESET), +then recovery proceeds to STEP 4 (Slot Reset). + +If the platform is unable to recover the slot, the next step +is STEP 6 (Permanent Failure). + +>>> The current powerpc implementation assumes that a device driver will +>>> *not* schedule or semaphore in this routine; the current powerpc >>> implementation uses one kernel thread to notify all devices; ->>> thus, of one device sleeps/schedules, all devices are affected. +>>> thus, if one device sleeps/schedules, all devices are affected. >>> Doing better requires complex multi-threaded logic in the error >>> recovery implementation (e.g. waiting for all notification threads >>> to "join" before proceeding with recovery.) This seems excessively >>> complex and not worth implementing. ->>> The current ppc64 implementation doesn't much care if the device ->>> attempts i/o at this point, or not. I/O's will fail, returning +>>> The current powerpc implementation doesn't much care if the device +>>> attempts I/O at this point, or not. I/O's will fail, returning >>> a value of 0xff on read, and writes will be dropped. If the device >>> driver attempts more than 10K I/O's to a frozen adapter, it will >>> assume that the device driver has gone into an infinite loop, and ->>> it will panic the the kernel. +>>> it will panic the the kernel. There doesn't seem to be any other +>>> way of stopping a device driver that insists on spinning on I/O. - 2) mmio_enabled() +STEP 2: MMIO Enabled +------------------- +The platform re-enables MMIO to the device (but typically not the +DMA), and then calls the mmio_enabled() callback on all affected +device drivers. - This is the "early recovery" call. IOs are allowed again, but DMA is +This is the "early recovery" call. IOs are allowed again, but DMA is not (hrm... to be discussed, I prefer not), with some restrictions. This is NOT a callback for the driver to start operations again, only to peek/poke at the device, extract diagnostic information, if any, and eventually do things like trigger a device local reset or some such, -but not restart operations. This is sent if all drivers on a segment -agree that they can try to recover and no automatic link reset was -performed by the HW. If the platform can't just re-enable IOs without -a slot reset or a link reset, it doesn't call this callback and goes -directly to 3) or 4). All IOs should be done _synchronously_ from -within this callback, errors triggered by them will be returned via -the normal pci_check_whatever() api, no new error_detected() callback -will be issued due to an error happening here. However, such an error -might cause IOs to be re-blocked for the whole segment, and thus -invalidate the recovery that other devices on the same segment might -have done, forcing the whole segment into one of the next states, -that is link reset or slot reset. +but not restart operations. This is callback is made if all drivers on +a segment agree that they can try to recover and if no automatic link reset +was performed by the HW. If the platform can't just re-enable IOs without +a slot reset or a link reset, it wont call this callback, and instead +will have gone directly to STEP 3 (Link Reset) or STEP 4 (Slot Reset) - Result codes: - - PCIERR_RESULT_RECOVERED +>>> The following is proposed; no platform implements this yet: +>>> Proposal: All I/O's should be done _synchronously_ from within +>>> this callback, errors triggered by them will be returned via +>>> the normal pci_check_whatever() API, no new error_detected() +>>> callback will be issued due to an error happening here. However, +>>> such an error might cause IOs to be re-blocked for the whole +>>> segment, and thus invalidate the recovery that other devices +>>> on the same segment might have done, forcing the whole segment +>>> into one of the next states, that is, link reset or slot reset. + +The driver should return one of the following result codes: + - PCI_ERS_RESULT_RECOVERED Driver returns this if it thinks the device is fully - functionnal and thinks it is ready to start + functional and thinks it is ready to start normal driver operations again. There is no guarantee that the driver will actually be allowed to proceed, as another driver on the same segment might have failed and thus triggered a slot reset on platforms that support it. - - PCIERR_RESULT_NEED_RESET + - PCI_ERS_RESULT_NEED_RESET Driver returns this if it thinks the device is not recoverable in it's current state and it needs a slot reset to proceed. - - PCIERR_RESULT_DISCONNECT + - PCI_ERS_RESULT_DISCONNECT Same as above. Total failure, no recovery even after reset driver dead. (To be defined more precisely) ->>> The current ppc64 implementation does not implement this callback. +The next step taken depends on the results returned by the drivers. +If all drivers returned PCI_ERS_RESULT_RECOVERED, then the platform +proceeds to either STEP3 (Link Reset) or to STEP 5 (Resume Operations). - 3) link_reset() +If any driver returned PCI_ERS_RESULT_NEED_RESET, then the platform +proceeds to STEP 4 (Slot Reset) - This is called after the link has been reset. This is typically -a PCI Express specific state at this point and is done whenever a -non-fatal error has been detected that can be "solved" by resetting -the link. This call informs the driver of the reset and the driver -should check if the device appears to be in working condition. -This function acts a bit like 2) mmio_enabled(), in that the driver -is not supposed to restart normal driver I/O operations right away. -Instead, it should just "probe" the device to check it's recoverability -status. If all is right, then the core will call resume() once all -drivers have ack'd link_reset(). +>>> The current powerpc implementation does not implement this callback. + + +STEP 3: Link Reset +------------------ +The platform resets the link, and then calls the link_reset() callback +on all affected device drivers. This is a PCI-Express specific state +and is done whenever a non-fatal error has been detected that can be +"solved" by resetting the link. This call informs the driver of the +reset and the driver should check to see if the device appears to be +in working condition. + +The driver is not supposed to restart normal driver I/O operations +at this point. It should limit itself to "probing" the device to +check it's recoverability status. If all is right, then the platform +will call resume() once all drivers have ack'd link_reset(). Result codes: - (identical to mmio_enabled) + (identical to STEP 3 (MMIO Enabled) ->>> The current ppc64 implementation does not implement this callback. +The platform then proceeds to either STEP 4 (Slot Reset) or STEP 5 +(Resume Operations). - 4) slot_reset() +>>> The current powerpc implementation does not implement this callback. - This is called after the slot has been soft or hard reset by the -platform. A soft reset consists of asserting the adapter #RST line -and then restoring the PCI BARs and PCI configuration header. If the -platform supports PCI hotplug, then it might instead perform a hard -reset by toggling power on the slot off/on. This call gives drivers -the chance to re-initialize the hardware (re-download firmware, etc.), -but drivers shouldn't restart normal I/O processing operations at -this point. (See note about interrupts; interrupts aren't guaranteed -to be delivered until the resume() callback has been called). If all -device drivers report success on this callback, the patform will call -resume() to complete the error handling and let the driver restart -normal I/O processing. + +STEP 4: Slot Reset +------------------ +The platform performs a soft or hard reset of the device, and then +calls the slot_reset() callback. + +A soft reset consists of asserting the adapter #RST line and then +restoring the PCI BAR's and PCI configuration header to a state +that is equivalent to what it would be after a fresh system +power-on followed by power-on BIOS/system firmware initialization. +If the platform supports PCI hotplug, then the reset might be +performed by toggling the slot electrical power off/on. + +It is important for the platform to restore the PCI config space +to the "fresh poweron" state, rather than the "last state". After +a slot reset, the device driver will almost always use its standard +device initialization routines, and an unusual config space setup +may result in hung devices, kernel panics, or silent data corruption. + +This call gives drivers the chance to re-initialize the hardware +(re-download firmware, etc.). At this point, the driver may assume +that he card is in a fresh state and is fully functional. In +particular, interrupt generation should work normally. + +Drivers should not yet restart normal I/O processing operations +at this point. If all device drivers report success on this +callback, the platform will call resume() to complete the sequence, +and let the driver restart normal I/O processing. A driver can still return a critical failure for this function if it can't get the device operational after reset. If the platform -previously tried a soft reset, it migh now try a hard reset (power +previously tried a soft reset, it might now try a hard reset (power cycle) and then call slot_reset() again. It the device still can't be recovered, there is nothing more that can be done; the platform will typically report a "permanent failure" in such a case. The device will be considered "dead" in this case. +Drivers for multi-function cards will need to coordinate among +themselves as to which driver instance will perform any "one-shot" +or global device initialization. For example, the Symbios sym53cxx2 +driver performs device init only from PCI function 0: + ++ if (PCI_FUNC(pdev->devfn) == 0) ++ sym_reset_scsi_bus(np, 0); + Result codes: - - PCIERR_RESULT_DISCONNECT + - PCI_ERS_RESULT_DISCONNECT Same as above. ->>> The current ppc64 implementation does not try a power-cycle reset ->>> if the driver returned PCIERR_RESULT_DISCONNECT. However, it should. +Platform proceeds either to STEP 5 (Resume Operations) or STEP 6 (Permanent +Failure). - 5) resume() +>>> The current powerpc implementation does not currently try a +>>> power-cycle reset if the driver returned PCI_ERS_RESULT_DISCONNECT. +>>> However, it probably should. - This is called if all drivers on the segment have returned -PCIERR_RESULT_RECOVERED from one of the 3 prevous callbacks. -That basically tells the driver to restart activity, tht everything -is back and running. No result code is taken into account here. If -a new error happens, it will restart a new error handling process. -That's it. I think this covers all the possibilities. The way those -callbacks are called is platform policy. A platform with no slot reset -capability for example may want to just "ignore" drivers that can't +STEP 5: Resume Operations +------------------------- +The platform will call the resume() callback on all affected device +drivers if all drivers on the segment have returned +PCI_ERS_RESULT_RECOVERED from one of the 3 previous callbacks. +The goal of this callback is to tell the driver to restart activity, +that everything is back and running. This callback does not return +a result code. + +At this point, if a new error happens, the platform will restart +a new error recovery sequence. + +STEP 6: Permanent Failure +------------------------- +A "permanent failure" has occurred, and the platform cannot recover +the device. The platform will call error_detected() with a +pci_channel_state value of pci_channel_io_perm_failure. + +The device driver should, at this point, assume the worst. It should +cancel all pending I/O, refuse all new I/O, returning -EIO to +higher layers. The device driver should then clean up all of its +memory and remove itself from kernel operations, much as it would +during system shutdown. + +The platform will typically notify the system operator of the +permanent failure in some way. If the device is hotplug-capable, +the operator will probably want to remove and replace the device. +Note, however, not all failures are truly "permanent". Some are +caused by over-heating, some by a poorly seated card. Many +PCI error events are caused by software bugs, e.g. DMA's to +wild addresses or bogus split transactions due to programming +errors. See the discussion in powerpc/eeh-pci-error-recovery.txt +for additional detail on real-life experience of the causes of +software errors. + + +Conclusion; General Remarks +--------------------------- +The way those callbacks are called is platform policy. A platform with +no slot reset capability may want to just "ignore" drivers that can't recover (disconnect them) and try to let other cards on the same segment recover. Keep in mind that in most real life cases, though, there will be only one driver per segment. -Now, there is a note about interrupts. If you get an interrupt and your +Now, a note about interrupts. If you get an interrupt and your device is dead or has been isolated, there is a problem :) - -After much thinking, I decided to leave that to the platform. That is, -the recovery API only precies that: +The current policy is to turn this into a platform policy. +That is, the recovery API only requires that: - There is no guarantee that interrupt delivery can proceed from any device on the segment starting from the error detection and until the -restart callback is sent, at which point interrupts are expected to be +resume callback is sent, at which point interrupts are expected to be fully operational. - - There is no guarantee that interrupt delivery is stopped, that is, ad -river that gets an interrupts after detecting an error, or that detects -and error within the interrupt handler such that it prevents proper + - There is no guarantee that interrupt delivery is stopped, that is, +a driver that gets an interrupt after detecting an error, or that detects +an error within the interrupt handler such that it prevents proper ack'ing of the interrupt (and thus removal of the source) should just -return IRQ_NOTHANDLED. It's up to the platform to deal with taht -condition, typically by masking the irq source during the duration of +return IRQ_NOTHANDLED. It's up to the platform to deal with that +condition, typically by masking the IRQ source during the duration of the error handling. It is expected that the platform "knows" which interrupts are routed to error-management capable slots and can deal -with temporarily disabling that irq number during error processing (this +with temporarily disabling that IRQ number during error processing (this isn't terribly complex). That means some IRQ latency for other devices sharing the interrupt, but there is simply no other way. High end platforms aren't supposed to share interrupts between many devices anyway :) +>>> Implementation details for the powerpc platform are discussed in +>>> the file Documentation/powerpc/eeh-pci-error-recovery.txt -Revised: 31 May 2005 Linas Vepstas +>>> As of this writing, there are six device drivers with patches +>>> implementing error recovery. Not all of these patches are in +>>> mainline yet. These may be used as "examples": +>>> +>>> drivers/scsi/ipr.c +>>> drivers/scsi/sym53cxx_2 +>>> drivers/next/e100.c +>>> drivers/net/e1000 +>>> drivers/net/ixgb +>>> drivers/net/s2io.c + +The End +------- diff --git a/Documentation/power/interface.txt b/Documentation/power/interface.txt index bd4ffb5bd49a..4117802af0f8 100644 --- a/Documentation/power/interface.txt +++ b/Documentation/power/interface.txt @@ -44,7 +44,7 @@ it. /sys/power/image_size controls the size of the image created by the suspend-to-disk mechanism. It can be written a string representing a non-negative integer that will be used as an upper -limit of the image size, in megabytes. The suspend-to-disk mechanism will +limit of the image size, in bytes. The suspend-to-disk mechanism will do its best to ensure the image size will not exceed that number. However, if this turns out to be impossible, it will try to suspend anyway using the smallest image possible. In particular, if "0" is written to this file, the diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt index 08c79d4dc540..b28b7f04abb8 100644 --- a/Documentation/power/swsusp.txt +++ b/Documentation/power/swsusp.txt @@ -27,7 +27,7 @@ echo shutdown > /sys/power/disk; echo disk > /sys/power/state echo platform > /sys/power/disk; echo disk > /sys/power/state -If you want to limit the suspend image size to N megabytes, do +If you want to limit the suspend image size to N bytes, do echo N > /sys/power/image_size diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt new file mode 100644 index 000000000000..1284498e847c --- /dev/null +++ b/Documentation/powerpc/booting-without-of.txt @@ -0,0 +1,1420 @@ + Booting the Linux/ppc kernel without Open Firmware + -------------------------------------------------- + + +(c) 2005 Benjamin Herrenschmidt , + IBM Corp. +(c) 2005 Becky Bruce , + Freescale Semiconductor, FSL SOC and 32-bit additions + + May 18, 2005: Rev 0.1 - Initial draft, no chapter III yet. + + May 19, 2005: Rev 0.2 - Add chapter III and bits & pieces here or + clarifies the fact that a lot of things are + optional, the kernel only requires a very + small device tree, though it is encouraged + to provide an as complete one as possible. + + May 24, 2005: Rev 0.3 - Precise that DT block has to be in RAM + - Misc fixes + - Define version 3 and new format version 16 + for the DT block (version 16 needs kernel + patches, will be fwd separately). + String block now has a size, and full path + is replaced by unit name for more + compactness. + linux,phandle is made optional, only nodes + that are referenced by other nodes need it. + "name" property is now automatically + deduced from the unit name + + June 1, 2005: Rev 0.4 - Correct confusion between OF_DT_END and + OF_DT_END_NODE in structure definition. + - Change version 16 format to always align + property data to 4 bytes. Since tokens are + already aligned, that means no specific + required alignement between property size + and property data. The old style variable + alignment would make it impossible to do + "simple" insertion of properties using + memove (thanks Milton for + noticing). Updated kernel patch as well + - Correct a few more alignement constraints + - Add a chapter about the device-tree + compiler and the textural representation of + the tree that can be "compiled" by dtc. + + + November 21, 2005: Rev 0.5 + - Additions/generalizations for 32-bit + - Changed to reflect the new arch/powerpc + structure + - Added chapter VI + + + ToDo: + - Add some definitions of interrupt tree (simple/complex) + - Add some definitions for pci host bridges + - Add some common address format examples + - Add definitions for standard properties and "compatible" + names for cells that are not already defined by the existing + OF spec. + - Compare FSL SOC use of PCI to standard and make sure no new + node definition required. + - Add more information about node definitions for SOC devices + that currently have no standard, like the FSL CPM. + + +I - Introduction +================ + +During the recent development of the Linux/ppc64 kernel, and more +specifically, the addition of new platform types outside of the old +IBM pSeries/iSeries pair, it was decided to enforce some strict rules +regarding the kernel entry and bootloader <-> kernel interfaces, in +order to avoid the degeneration that had become the ppc32 kernel entry +point and the way a new platform should be added to the kernel. The +legacy iSeries platform breaks those rules as it predates this scheme, +but no new board support will be accepted in the main tree that +doesn't follows them properly. In addition, since the advent of the +arch/powerpc merged architecture for ppc32 and ppc64, new 32-bit +platforms and 32-bit platforms which move into arch/powerpc will be +required to use these rules as well. + +The main requirement that will be defined in more detail below is +the presence of a device-tree whose format is defined after Open +Firmware specification. However, in order to make life easier +to embedded board vendors, the kernel doesn't require the device-tree +to represent every device in the system and only requires some nodes +and properties to be present. This will be described in detail in +section III, but, for example, the kernel does not require you to +create a node for every PCI device in the system. It is a requirement +to have a node for PCI host bridges in order to provide interrupt +routing informations and memory/IO ranges, among others. It is also +recommended to define nodes for on chip devices and other busses that +don't specifically fit in an existing OF specification. This creates a +great flexibility in the way the kernel can then probe those and match +drivers to device, without having to hard code all sorts of tables. It +also makes it more flexible for board vendors to do minor hardware +upgrades without significantly impacting the kernel code or cluttering +it with special cases. + + +1) Entry point for arch/powerpc +------------------------------- + + There is one and one single entry point to the kernel, at the start + of the kernel image. That entry point supports two calling + conventions: + + a) Boot from Open Firmware. If your firmware is compatible + with Open Firmware (IEEE 1275) or provides an OF compatible + client interface API (support for "interpret" callback of + forth words isn't required), you can enter the kernel with: + + r5 : OF callback pointer as defined by IEEE 1275 + bindings to powerpc. Only the 32 bit client interface + is currently supported + + r3, r4 : address & length of an initrd if any or 0 + + The MMU is either on or off; the kernel will run the + trampoline located in arch/powerpc/kernel/prom_init.c to + extract the device-tree and other information from open + firmware and build a flattened device-tree as described + in b). prom_init() will then re-enter the kernel using + the second method. This trampoline code runs in the + context of the firmware, which is supposed to handle all + exceptions during that time. + + b) Direct entry with a flattened device-tree block. This entry + point is called by a) after the OF trampoline and can also be + called directly by a bootloader that does not support the Open + Firmware client interface. It is also used by "kexec" to + implement "hot" booting of a new kernel from a previous + running one. This method is what I will describe in more + details in this document, as method a) is simply standard Open + Firmware, and thus should be implemented according to the + various standard documents defining it and its binding to the + PowerPC platform. The entry point definition then becomes: + + r3 : physical pointer to the device-tree block + (defined in chapter II) in RAM + + r4 : physical pointer to the kernel itself. This is + used by the assembly code to properly disable the MMU + in case you are entering the kernel with MMU enabled + and a non-1:1 mapping. + + r5 : NULL (as to differenciate with method a) + + Note about SMP entry: Either your firmware puts your other + CPUs in some sleep loop or spin loop in ROM where you can get + them out via a soft reset or some other means, in which case + you don't need to care, or you'll have to enter the kernel + with all CPUs. The way to do that with method b) will be + described in a later revision of this document. + + +2) Board support +---------------- + +64-bit kernels: + + Board supports (platforms) are not exclusive config options. An + arbitrary set of board supports can be built in a single kernel + image. The kernel will "know" what set of functions to use for a + given platform based on the content of the device-tree. Thus, you + should: + + a) add your platform support as a _boolean_ option in + arch/powerpc/Kconfig, following the example of PPC_PSERIES, + PPC_PMAC and PPC_MAPLE. The later is probably a good + example of a board support to start from. + + b) create your main platform file as + "arch/powerpc/platforms/myplatform/myboard_setup.c" and add it + to the Makefile under the condition of your CONFIG_ + option. This file will define a structure of type "ppc_md" + containing the various callbacks that the generic code will + use to get to your platform specific code + + c) Add a reference to your "ppc_md" structure in the + "machines" table in arch/powerpc/kernel/setup_64.c if you are + a 64-bit platform. + + d) request and get assigned a platform number (see PLATFORM_* + constants in include/asm-powerpc/processor.h + +32-bit embedded kernels: + + Currently, board support is essentially an exclusive config option. + The kernel is configured for a single platform. Part of the reason + for this is to keep kernels on embedded systems small and efficient; + part of this is due to the fact the code is already that way. In the + future, a kernel may support multiple platforms, but only if the + platforms feature the same core architectire. A single kernel build + cannot support both configurations with Book E and configurations + with classic Powerpc architectures. + + 32-bit embedded platforms that are moved into arch/powerpc using a + flattened device tree should adopt the merged tree practice of + setting ppc_md up dynamically, even though the kernel is currently + built with support for only a single platform at a time. This allows + unification of the setup code, and will make it easier to go to a + multiple-platform-support model in the future. + +NOTE: I believe the above will be true once Ben's done with the merge +of the boot sequences.... someone speak up if this is wrong! + + To add a 32-bit embedded platform support, follow the instructions + for 64-bit platforms above, with the exception that the Kconfig + option should be set up such that the kernel builds exclusively for + the platform selected. The processor type for the platform should + enable another config option to select the specific board + supported. + +NOTE: If ben doesn't merge the setup files, may need to change this to +point to setup_32.c + + + I will describe later the boot process and various callbacks that + your platform should implement. + + +II - The DT block format +======================== + + +This chapter defines the actual format of the flattened device-tree +passed to the kernel. The actual content of it and kernel requirements +are described later. You can find example of code manipulating that +format in various places, including arch/powerpc/kernel/prom_init.c +which will generate a flattened device-tree from the Open Firmware +representation, or the fs2dt utility which is part of the kexec tools +which will generate one from a filesystem representation. It is +expected that a bootloader like uboot provides a bit more support, +that will be discussed later as well. + +Note: The block has to be in main memory. It has to be accessible in +both real mode and virtual mode with no mapping other than main +memory. If you are writing a simple flash bootloader, it should copy +the block to RAM before passing it to the kernel. + + +1) Header +--------- + + The kernel is entered with r3 pointing to an area of memory that is + roughtly described in include/asm-powerpc/prom.h by the structure + boot_param_header: + +struct boot_param_header { + u32 magic; /* magic word OF_DT_HEADER */ + u32 totalsize; /* total size of DT block */ + u32 off_dt_struct; /* offset to structure */ + u32 off_dt_strings; /* offset to strings */ + u32 off_mem_rsvmap; /* offset to memory reserve map +*/ + u32 version; /* format version */ + u32 last_comp_version; /* last compatible version */ + + /* version 2 fields below */ + u32 boot_cpuid_phys; /* Which physical CPU id we're + booting on */ + /* version 3 fields below */ + u32 size_dt_strings; /* size of the strings block */ +}; + + Along with the constants: + +/* Definitions used by the flattened device tree */ +#define OF_DT_HEADER 0xd00dfeed /* 4: version, + 4: total size */ +#define OF_DT_BEGIN_NODE 0x1 /* Start node: full name +*/ +#define OF_DT_END_NODE 0x2 /* End node */ +#define OF_DT_PROP 0x3 /* Property: name off, + size, content */ +#define OF_DT_END 0x9 + + All values in this header are in big endian format, the various + fields in this header are defined more precisely below. All + "offset" values are in bytes from the start of the header; that is + from the value of r3. + + - magic + + This is a magic value that "marks" the beginning of the + device-tree block header. It contains the value 0xd00dfeed and is + defined by the constant OF_DT_HEADER + + - totalsize + + This is the total size of the DT block including the header. The + "DT" block should enclose all data structures defined in this + chapter (who are pointed to by offsets in this header). That is, + the device-tree structure, strings, and the memory reserve map. + + - off_dt_struct + + This is an offset from the beginning of the header to the start + of the "structure" part the device tree. (see 2) device tree) + + - off_dt_strings + + This is an offset from the beginning of the header to the start + of the "strings" part of the device-tree + + - off_mem_rsvmap + + This is an offset from the beginning of the header to the start + of the reserved memory map. This map is a list of pairs of 64 + bit integers. Each pair is a physical address and a size. The + + list is terminated by an entry of size 0. This map provides the + kernel with a list of physical memory areas that are "reserved" + and thus not to be used for memory allocations, especially during + early initialization. The kernel needs to allocate memory during + boot for things like un-flattening the device-tree, allocating an + MMU hash table, etc... Those allocations must be done in such a + way to avoid overriding critical things like, on Open Firmware + capable machines, the RTAS instance, or on some pSeries, the TCE + tables used for the iommu. Typically, the reserve map should + contain _at least_ this DT block itself (header,total_size). If + you are passing an initrd to the kernel, you should reserve it as + well. You do not need to reserve the kernel image itself. The map + should be 64 bit aligned. + + - version + + This is the version of this structure. Version 1 stops + here. Version 2 adds an additional field boot_cpuid_phys. + Version 3 adds the size of the strings block, allowing the kernel + to reallocate it easily at boot and free up the unused flattened + structure after expansion. Version 16 introduces a new more + "compact" format for the tree itself that is however not backward + compatible. You should always generate a structure of the highest + version defined at the time of your implementation. Currently + that is version 16, unless you explicitely aim at being backward + compatible. + + - last_comp_version + + Last compatible version. This indicates down to what version of + the DT block you are backward compatible. For example, version 2 + is backward compatible with version 1 (that is, a kernel build + for version 1 will be able to boot with a version 2 format). You + should put a 1 in this field if you generate a device tree of + version 1 to 3, or 0x10 if you generate a tree of version 0x10 + using the new unit name format. + + - boot_cpuid_phys + + This field only exist on version 2 headers. It indicate which + physical CPU ID is calling the kernel entry point. This is used, + among others, by kexec. If you are on an SMP system, this value + should match the content of the "reg" property of the CPU node in + the device-tree corresponding to the CPU calling the kernel entry + point (see further chapters for more informations on the required + device-tree contents) + + + So the typical layout of a DT block (though the various parts don't + need to be in that order) looks like this (addresses go from top to + bottom): + + + ------------------------------ + r3 -> | struct boot_param_header | + ------------------------------ + | (alignment gap) (*) | + ------------------------------ + | memory reserve map | + ------------------------------ + | (alignment gap) | + ------------------------------ + | | + | device-tree structure | + | | + ------------------------------ + | (alignment gap) | + ------------------------------ + | | + | device-tree strings | + | | + -----> ------------------------------ + | + | + --- (r3 + totalsize) + + (*) The alignment gaps are not necessarily present; their presence + and size are dependent on the various alignment requirements of + the individual data blocks. + + +2) Device tree generalities +--------------------------- + +This device-tree itself is separated in two different blocks, a +structure block and a strings block. Both need to be aligned to a 4 +byte boundary. + +First, let's quickly describe the device-tree concept before detailing +the storage format. This chapter does _not_ describe the detail of the +required types of nodes & properties for the kernel, this is done +later in chapter III. + +The device-tree layout is strongly inherited from the definition of +the Open Firmware IEEE 1275 device-tree. It's basically a tree of +nodes, each node having two or more named properties. A property can +have a value or not. + +It is a tree, so each node has one and only one parent except for the +root node who has no parent. + +A node has 2 names. The actual node name is generally contained in a +property of type "name" in the node property list whose value is a +zero terminated string and is mandatory for version 1 to 3 of the +format definition (as it is in Open Firmware). Version 0x10 makes it +optional as it can generate it from the unit name defined below. + +There is also a "unit name" that is used to differenciate nodes with +the same name at the same level, it is usually made of the node +name's, the "@" sign, and a "unit address", which definition is +specific to the bus type the node sits on. + +The unit name doesn't exist as a property per-se but is included in +the device-tree structure. It is typically used to represent "path" in +the device-tree. More details about the actual format of these will be +below. + +The kernel powerpc generic code does not make any formal use of the +unit address (though some board support code may do) so the only real +requirement here for the unit address is to ensure uniqueness of +the node unit name at a given level of the tree. Nodes with no notion +of address and no possible sibling of the same name (like /memory or +/cpus) may omit the unit address in the context of this specification, +or use the "@0" default unit address. The unit name is used to define +a node "full path", which is the concatenation of all parent node +unit names separated with "/". + +The root node doesn't have a defined name, and isn't required to have +a name property either if you are using version 3 or earlier of the +format. It also has no unit address (no @ symbol followed by a unit +address). The root node unit name is thus an empty string. The full +path to the root node is "/". + +Every node which actually represents an actual device (that is, a node +which isn't only a virtual "container" for more nodes, like "/cpus" +is) is also required to have a "device_type" property indicating the +type of node . + +Finally, every node that can be referenced from a property in another +node is required to have a "linux,phandle" property. Real open +firmware implementations provide a unique "phandle" value for every +node that the "prom_init()" trampoline code turns into +"linux,phandle" properties. However, this is made optional if the +flattened device tree is used directly. An example of a node +referencing another node via "phandle" is when laying out the +interrupt tree which will be described in a further version of this +document. + +This "linux, phandle" property is a 32 bit value that uniquely +identifies a node. You are free to use whatever values or system of +values, internal pointers, or whatever to generate these, the only +requirement is that every node for which you provide that property has +a unique value for it. + +Here is an example of a simple device-tree. In this example, an "o" +designates a node followed by the node unit name. Properties are +presented with their name followed by their content. "content" +represents an ASCII string (zero terminated) value, while +represents a 32 bit hexadecimal value. The various nodes in this +example will be discussed in a later chapter. At this point, it is +only meant to give you a idea of what a device-tree looks like. I have +purposefully kept the "name" and "linux,phandle" properties which +aren't necessary in order to give you a better idea of what the tree +looks like in practice. + + / o device-tree + |- name = "device-tree" + |- model = "MyBoardName" + |- compatible = "MyBoardFamilyName" + |- #address-cells = <2> + |- #size-cells = <2> + |- linux,phandle = <0> + | + o cpus + | | - name = "cpus" + | | - linux,phandle = <1> + | | - #address-cells = <1> + | | - #size-cells = <0> + | | + | o PowerPC,970@0 + | |- name = "PowerPC,970" + | |- device_type = "cpu" + | |- reg = <0> + | |- clock-frequency = <5f5e1000> + | |- linux,boot-cpu + | |- linux,phandle = <2> + | + o memory@0 + | |- name = "memory" + | |- device_type = "memory" + | |- reg = <00000000 00000000 00000000 20000000> + | |- linux,phandle = <3> + | + o chosen + |- name = "chosen" + |- bootargs = "root=/dev/sda2" + |- linux,platform = <00000600> + |- linux,phandle = <4> + +This tree is almost a minimal tree. It pretty much contains the +minimal set of required nodes and properties to boot a linux kernel; +that is, some basic model informations at the root, the CPUs, and the +physical memory layout. It also includes misc information passed +through /chosen, like in this example, the platform type (mandatory) +and the kernel command line arguments (optional). + +The /cpus/PowerPC,970@0/linux,boot-cpu property is an example of a +property without a value. All other properties have a value. The +significance of the #address-cells and #size-cells properties will be +explained in chapter IV which defines precisely the required nodes and +properties and their content. + + +3) Device tree "structure" block + +The structure of the device tree is a linearized tree structure. The +"OF_DT_BEGIN_NODE" token starts a new node, and the "OF_DT_END_NODE" +ends that node definition. Child nodes are simply defined before +"OF_DT_END_NODE" (that is nodes within the node). A 'token' is a 32 +bit value. The tree has to be "finished" with a OF_DT_END token + +Here's the basic structure of a single node: + + * token OF_DT_BEGIN_NODE (that is 0x00000001) + * for version 1 to 3, this is the node full path as a zero + terminated string, starting with "/". For version 16 and later, + this is the node unit name only (or an empty string for the + root node) + * [align gap to next 4 bytes boundary] + * for each property: + * token OF_DT_PROP (that is 0x00000003) + * 32 bit value of property value size in bytes (or 0 of no + * value) + * 32 bit value of offset in string block of property name + * property value data if any + * [align gap to next 4 bytes boundary] + * [child nodes if any] + * token OF_DT_END_NODE (that is 0x00000002) + +So the node content can be summmarised as a start token, a full path, +a list of properties, a list of child node and an end token. Every +child node is a full node structure itself as defined above. + +4) Device tree 'strings" block + +In order to save space, property names, which are generally redundant, +are stored separately in the "strings" block. This block is simply the +whole bunch of zero terminated strings for all property names +concatenated together. The device-tree property definitions in the +structure block will contain offset values from the beginning of the +strings block. + + +III - Required content of the device tree +========================================= + +WARNING: All "linux,*" properties defined in this document apply only +to a flattened device-tree. If your platform uses a real +implementation of Open Firmware or an implementation compatible with +the Open Firmware client interface, those properties will be created +by the trampoline code in the kernel's prom_init() file. For example, +that's where you'll have to add code to detect your board model and +set the platform number. However, when using the flatenned device-tree +entry point, there is no prom_init() pass, and thus you have to +provide those properties yourself. + + +1) Note about cells and address representation +---------------------------------------------- + +The general rule is documented in the various Open Firmware +documentations. If you chose to describe a bus with the device-tree +and there exist an OF bus binding, then you should follow the +specification. However, the kernel does not require every single +device or bus to be described by the device tree. + +In general, the format of an address for a device is defined by the +parent bus type, based on the #address-cells and #size-cells +property. In the absence of such a property, the parent's parent +values are used, etc... The kernel requires the root node to have +those properties defining addresses format for devices directly mapped +on the processor bus. + +Those 2 properties define 'cells' for representing an address and a +size. A "cell" is a 32 bit number. For example, if both contain 2 +like the example tree given above, then an address and a size are both +composed of 2 cells, and each is a 64 bit number (cells are +concatenated and expected to be in big endian format). Another example +is the way Apple firmware defines them, with 2 cells for an address +and one cell for a size. Most 32-bit implementations should define +#address-cells and #size-cells to 1, which represents a 32-bit value. +Some 32-bit processors allow for physical addresses greater than 32 +bits; these processors should define #address-cells as 2. + +"reg" properties are always a tuple of the type "address size" where +the number of cells of address and size is specified by the bus +#address-cells and #size-cells. When a bus supports various address +spaces and other flags relative to a given address allocation (like +prefetchable, etc...) those flags are usually added to the top level +bits of the physical address. For example, a PCI physical address is +made of 3 cells, the bottom two containing the actual address itself +while the top cell contains address space indication, flags, and pci +bus & device numbers. + +For busses that support dynamic allocation, it's the accepted practice +to then not provide the address in "reg" (keep it 0) though while +providing a flag indicating the address is dynamically allocated, and +then, to provide a separate "assigned-addresses" property that +contains the fully allocated addresses. See the PCI OF bindings for +details. + +In general, a simple bus with no address space bits and no dynamic +allocation is preferred if it reflects your hardware, as the existing +kernel address parsing functions will work out of the box. If you +define a bus type with a more complex address format, including things +like address space bits, you'll have to add a bus translator to the +prom_parse.c file of the recent kernels for your bus type. + +The "reg" property only defines addresses and sizes (if #size-cells +is +non-0) within a given bus. In order to translate addresses upward +(that is into parent bus addresses, and possibly into cpu physical +addresses), all busses must contain a "ranges" property. If the +"ranges" property is missing at a given level, it's assumed that +translation isn't possible. The format of the "ranges" proprety for a +bus is a list of: + + bus address, parent bus address, size + +"bus address" is in the format of the bus this bus node is defining, +that is, for a PCI bridge, it would be a PCI address. Thus, (bus +address, size) defines a range of addresses for child devices. "parent +bus address" is in the format of the parent bus of this bus. For +example, for a PCI host controller, that would be a CPU address. For a +PCI<->ISA bridge, that would be a PCI address. It defines the base +address in the parent bus where the beginning of that range is mapped. + +For a new 64 bit powerpc board, I recommend either the 2/2 format or +Apple's 2/1 format which is slightly more compact since sizes usually +fit in a single 32 bit word. New 32 bit powerpc boards should use a +1/1 format, unless the processor supports physical addresses greater +than 32-bits, in which case a 2/1 format is recommended. + + +2) Note about "compatible" properties +------------------------------------- + +These properties are optional, but recommended in devices and the root +node. The format of a "compatible" property is a list of concatenated +zero terminated strings. They allow a device to express its +compatibility with a family of similar devices, in some cases, +allowing a single driver to match against several devices regardless +of their actual names. + +3) Note about "name" properties +------------------------------- + +While earlier users of Open Firmware like OldWorld macintoshes tended +to use the actual device name for the "name" property, it's nowadays +considered a good practice to use a name that is closer to the device +class (often equal to device_type). For example, nowadays, ethernet +controllers are named "ethernet", an additional "model" property +defining precisely the chip type/model, and "compatible" property +defining the family in case a single driver can driver more than one +of these chips. However, the kernel doesn't generally put any +restriction on the "name" property; it is simply considered good +practice to follow the standard and its evolutions as closely as +possible. + +Note also that the new format version 16 makes the "name" property +optional. If it's absent for a node, then the node's unit name is then +used to reconstruct the name. That is, the part of the unit name +before the "@" sign is used (or the entire unit name if no "@" sign +is present). + +4) Note about node and property names and character set +------------------------------------------------------- + +While open firmware provides more flexibe usage of 8859-1, this +specification enforces more strict rules. Nodes and properties should +be comprised only of ASCII characters 'a' to 'z', '0' to +'9', ',', '.', '_', '+', '#', '?', and '-'. Node names additionally +allow uppercase characters 'A' to 'Z' (property names should be +lowercase. The fact that vendors like Apple don't respect this rule is +irrelevant here). Additionally, node and property names should always +begin with a character in the range 'a' to 'z' (or 'A' to 'Z' for node +names). + +The maximum number of characters for both nodes and property names +is 31. In the case of node names, this is only the leftmost part of +a unit name (the pure "name" property), it doesn't include the unit +address which can extend beyond that limit. + + +5) Required nodes and properties +-------------------------------- + These are all that are currently required. However, it is strongly + recommended that you expose PCI host bridges as documented in the + PCI binding to open firmware, and your interrupt tree as documented + in OF interrupt tree specification. + + a) The root node + + The root node requires some properties to be present: + + - model : this is your board name/model + - #address-cells : address representation for "root" devices + - #size-cells: the size representation for "root" devices + + Additionally, some recommended properties are: + + - compatible : the board "family" generally finds its way here, + for example, if you have 2 board models with a similar layout, + that typically get driven by the same platform code in the + kernel, you would use a different "model" property but put a + value in "compatible". The kernel doesn't directly use that + value (see /chosen/linux,platform for how the kernel choses a + platform type) but it is generally useful. + + The root node is also generally where you add additional properties + specific to your board like the serial number if any, that sort of + thing. it is recommended that if you add any "custom" property whose + name may clash with standard defined ones, you prefix them with your + vendor name and a comma. + + b) The /cpus node + + This node is the parent of all individual CPU nodes. It doesn't + have any specific requirements, though it's generally good practice + to have at least: + + #address-cells = <00000001> + #size-cells = <00000000> + + This defines that the "address" for a CPU is a single cell, and has + no meaningful size. This is not necessary but the kernel will assume + that format when reading the "reg" properties of a CPU node, see + below + + c) The /cpus/* nodes + + So under /cpus, you are supposed to create a node for every CPU on + the machine. There is no specific restriction on the name of the + CPU, though It's common practice to call it PowerPC,. For + example, Apple uses PowerPC,G5 while IBM uses PowerPC,970FX. + + Required properties: + + - device_type : has to be "cpu" + - reg : This is the physical cpu number, it's a single 32 bit cell + and is also used as-is as the unit number for constructing the + unit name in the full path. For example, with 2 CPUs, you would + have the full path: + /cpus/PowerPC,970FX@0 + /cpus/PowerPC,970FX@1 + (unit addresses do not require leading zeroes) + - d-cache-line-size : one cell, L1 data cache line size in bytes + - i-cache-line-size : one cell, L1 instruction cache line size in + bytes + - d-cache-size : one cell, size of L1 data cache in bytes + - i-cache-size : one cell, size of L1 instruction cache in bytes + - linux, boot-cpu : Should be defined if this cpu is the boot cpu. + + Recommended properties: + + - timebase-frequency : a cell indicating the frequency of the + timebase in Hz. This is not directly used by the generic code, + but you are welcome to copy/paste the pSeries code for setting + the kernel timebase/decrementer calibration based on this + value. + - clock-frequency : a cell indicating the CPU core clock frequency + in Hz. A new property will be defined for 64 bit values, but if + your frequency is < 4Ghz, one cell is enough. Here as well as + for the above, the common code doesn't use that property, but + you are welcome to re-use the pSeries or Maple one. A future + kernel version might provide a common function for this. + + You are welcome to add any property you find relevant to your board, + like some information about the mechanism used to soft-reset the + CPUs. For example, Apple puts the GPIO number for CPU soft reset + lines in there as a "soft-reset" property since they start secondary + CPUs by soft-resetting them. + + + d) the /memory node(s) + + To define the physical memory layout of your board, you should + create one or more memory node(s). You can either create a single + node with all memory ranges in its reg property, or you can create + several nodes, as you wish. The unit address (@ part) used for the + full path is the address of the first range of memory defined by a + given node. If you use a single memory node, this will typically be + @0. + + Required properties: + + - device_type : has to be "memory" + - reg : This property contains all the physical memory ranges of + your board. It's a list of addresses/sizes concatenated + together, with the number of cells of each defined by the + #address-cells and #size-cells of the root node. For example, + with both of these properties beeing 2 like in the example given + earlier, a 970 based machine with 6Gb of RAM could typically + have a "reg" property here that looks like: + + 00000000 00000000 00000000 80000000 + 00000001 00000000 00000001 00000000 + + That is a range starting at 0 of 0x80000000 bytes and a range + starting at 0x100000000 and of 0x100000000 bytes. You can see + that there is no memory covering the IO hole between 2Gb and + 4Gb. Some vendors prefer splitting those ranges into smaller + segments, but the kernel doesn't care. + + e) The /chosen node + + This node is a bit "special". Normally, that's where open firmware + puts some variable environment information, like the arguments, or + phandle pointers to nodes like the main interrupt controller, or the + default input/output devices. + + This specification makes a few of these mandatory, but also defines + some linux-specific properties that would be normally constructed by + the prom_init() trampoline when booting with an OF client interface, + but that you have to provide yourself when using the flattened format. + + Required properties: + + - linux,platform : This is your platform number as assigned by the + architecture maintainers + + Recommended properties: + + - bootargs : This zero-terminated string is passed as the kernel + command line + - linux,stdout-path : This is the full path to your standard + console device if any. Typically, if you have serial devices on + your board, you may want to put the full path to the one set as + the default console in the firmware here, for the kernel to pick + it up as it's own default console. If you look at the funciton + set_preferred_console() in arch/ppc64/kernel/setup.c, you'll see + that the kernel tries to find out the default console and has + knowledge of various types like 8250 serial ports. You may want + to extend this function to add your own. + - interrupt-controller : This is one cell containing a phandle + value that matches the "linux,phandle" property of your main + interrupt controller node. May be used for interrupt routing. + + + Note that u-boot creates and fills in the chosen node for platforms + that use it. + + f) the /soc node + + This node is used to represent a system-on-a-chip (SOC) and must be + present if the processor is a SOC. The top-level soc node contains + information that is global to all devices on the SOC. The node name + should contain a unit address for the SOC, which is the base address + of the memory-mapped register set for the SOC. The name of an soc + node should start with "soc", and the remainder of the name should + represent the part number for the soc. For example, the MPC8540's + soc node would be called "soc8540". + + Required properties: + + - device_type : Should be "soc" + - ranges : Should be defined as specified in 1) to describe the + translation of SOC addresses for memory mapped SOC registers. + + Recommended properties: + + - reg : This property defines the address and size of the + memory-mapped registers that are used for the SOC node itself. + It does not include the child device registers - these will be + defined inside each child node. The address specified in the + "reg" property should match the unit address of the SOC node. + - #address-cells : Address representation for "soc" devices. The + format of this field may vary depending on whether or not the + device registers are memory mapped. For memory mapped + registers, this field represents the number of cells needed to + represent the address of the registers. For SOCs that do not + use MMIO, a special address format should be defined that + contains enough cells to represent the required information. + See 1) above for more details on defining #address-cells. + - #size-cells : Size representation for "soc" devices + - #interrupt-cells : Defines the width of cells used to represent + interrupts. Typically this value is <2>, which includes a + 32-bit number that represents the interrupt number, and a + 32-bit number that represents the interrupt sense and level. + This field is only needed if the SOC contains an interrupt + controller. + + The SOC node may contain child nodes for each SOC device that the + platform uses. Nodes should not be created for devices which exist + on the SOC but are not used by a particular platform. See chapter VI + for more information on how to specify devices that are part of an +SOC. + + Example SOC node for the MPC8540: + + soc8540@e0000000 { + #address-cells = <1>; + #size-cells = <1>; + #interrupt-cells = <2>; + device_type = "soc"; + ranges = <00000000 e0000000 00100000> + reg = ; + } + + + +IV - "dtc", the device tree compiler +==================================== + + +dtc source code can be found at + + +WARNING: This version is still in early development stage; the +resulting device-tree "blobs" have not yet been validated with the +kernel. The current generated bloc lacks a useful reserve map (it will +be fixed to generate an empty one, it's up to the bootloader to fill +it up) among others. The error handling needs work, bugs are lurking, +etc... + +dtc basically takes a device-tree in a given format and outputs a +device-tree in another format. The currently supported formats are: + + Input formats: + ------------- + + - "dtb": "blob" format, that is a flattened device-tree block + with + header all in a binary blob. + - "dts": "source" format. This is a text file containing a + "source" for a device-tree. The format is defined later in this + chapter. + - "fs" format. This is a representation equivalent to the + output of /proc/device-tree, that is nodes are directories and + properties are files + + Output formats: + --------------- + + - "dtb": "blob" format + - "dts": "source" format + - "asm": assembly language file. This is a file that can be + sourced by gas to generate a device-tree "blob". That file can + then simply be added to your Makefile. Additionally, the + assembly file exports some symbols that can be use + + +The syntax of the dtc tool is + + dtc [-I ] [-O ] + [-o output-filename] [-V output_version] input_filename + + +The "output_version" defines what versio of the "blob" format will be +generated. Supported versions are 1,2,3 and 16. The default is +currently version 3 but that may change in the future to version 16. + +Additionally, dtc performs various sanity checks on the tree, like the +uniqueness of linux,phandle properties, validity of strings, etc... + +The format of the .dts "source" file is "C" like, supports C and C++ +style commments. + +/ { +} + +The above is the "device-tree" definition. It's the only statement +supported currently at the toplevel. + +/ { + property1 = "string_value"; /* define a property containing a 0 + * terminated string + */ + + property2 = <1234abcd>; /* define a property containing a + * numerical 32 bits value (hexadecimal) + */ + + property3 = <12345678 12345678 deadbeef>; + /* define a property containing 3 + * numerical 32 bits values (cells) in + * hexadecimal + */ + property4 = [0a 0b 0c 0d de ea ad be ef]; + /* define a property whose content is + * an arbitrary array of bytes + */ + + childnode@addresss { /* define a child node named "childnode" + * whose unit name is "childnode at + * address" + */ + + childprop = "hello\n"; /* define a property "childprop" of + * childnode (in this case, a string) + */ + }; +}; + +Nodes can contain other nodes etc... thus defining the hierarchical +structure of the tree. + +Strings support common escape sequences from C: "\n", "\t", "\r", +"\(octal value)", "\x(hex value)". + +It is also suggested that you pipe your source file through cpp (gcc +preprocessor) so you can use #include's, #define for constants, etc... + +Finally, various options are planned but not yet implemented, like +automatic generation of phandles, labels (exported to the asm file so +you can point to a property content and change it easily from whatever +you link the device-tree with), label or path instead of numeric value +in some cells to "point" to a node (replaced by a phandle at compile +time), export of reserve map address to the asm file, ability to +specify reserve map content at compile time, etc... + +We may provide a .h include file with common definitions of that +proves useful for some properties (like building PCI properties or +interrupt maps) though it may be better to add a notion of struct +definitions to the compiler... + + +V - Recommendations for a bootloader +==================================== + + +Here are some various ideas/recommendations that have been proposed +while all this has been defined and implemented. + + - The bootloader may want to be able to use the device-tree itself + and may want to manipulate it (to add/edit some properties, + like physical memory size or kernel arguments). At this point, 2 + choices can be made. Either the bootloader works directly on the + flattened format, or the bootloader has its own internal tree + representation with pointers (similar to the kernel one) and + re-flattens the tree when booting the kernel. The former is a bit + more difficult to edit/modify, the later requires probably a bit + more code to handle the tree structure. Note that the structure + format has been designed so it's relatively easy to "insert" + properties or nodes or delete them by just memmoving things + around. It contains no internal offsets or pointers for this + purpose. + + - An example of code for iterating nodes & retreiving properties + directly from the flattened tree format can be found in the kernel + file arch/ppc64/kernel/prom.c, look at scan_flat_dt() function, + it's usage in early_init_devtree(), and the corresponding various + early_init_dt_scan_*() callbacks. That code can be re-used in a + GPL bootloader, and as the author of that code, I would be happy + do discuss possible free licencing to any vendor who wishes to + integrate all or part of this code into a non-GPL bootloader. + + + +VI - System-on-a-chip devices and nodes +======================================= + +Many companies are now starting to develop system-on-a-chip +processors, where the processor core (cpu) and many peripheral devices +exist on a single piece of silicon. For these SOCs, an SOC node +should be used that defines child nodes for the devices that make +up the SOC. While platforms are not required to use this model in +order to boot the kernel, it is highly encouraged that all SOC +implementations define as complete a flat-device-tree as possible to +describe the devices on the SOC. This will allow for the +genericization of much of the kernel code. + + +1) Defining child nodes of an SOC +--------------------------------- + +Each device that is part of an SOC may have its own node entry inside +the SOC node. For each device that is included in the SOC, the unit +address property represents the address offset for this device's +memory-mapped registers in the parent's address space. The parent's +address space is defined by the "ranges" property in the top-level soc +node. The "reg" property for each node that exists directly under the +SOC node should contain the address mapping from the child address space +to the parent SOC address space and the size of the device's +memory-mapped register file. + +For many devices that may exist inside an SOC, there are predefined +specifications for the format of the device tree node. All SOC child +nodes should follow these specifications, except where noted in this +document. + +See appendix A for an example partial SOC node definition for the +MPC8540. + + +2) Specifying interrupt information for SOC devices +--------------------------------------------------- + +Each device that is part of an SOC and which generates interrupts +should have the following properties: + + - interrupt-parent : contains the phandle of the interrupt + controller which handles interrupts for this device + - interrupts : a list of tuples representing the interrupt + number and the interrupt sense and level for each interupt + for this device. + +This information is used by the kernel to build the interrupt table +for the interrupt controllers in the system. + +Sense and level information should be encoded as follows: + + Devices connected to openPIC-compatible controllers should encode + sense and polarity as follows: + + 0 = high to low edge sensitive type enabled + 1 = active low level sensitive type enabled + 2 = low to high edge sensitive type enabled + 3 = active high level sensitive type enabled + + ISA PIC interrupt controllers should adhere to the ISA PIC + encodings listed below: + + 0 = active low level sensitive type enabled + 1 = active high level sensitive type enabled + 2 = high to low edge sensitive type enabled + 3 = low to high edge sensitive type enabled + + + +3) Representing devices without a current OF specification +---------------------------------------------------------- + +Currently, there are many devices on SOCs that do not have a standard +representation pre-defined as part of the open firmware +specifications, mainly because the boards that contain these SOCs are +not currently booted using open firmware. This section contains +descriptions for the SOC devices for which new nodes have been +defined; this list will expand as more and more SOC-containing +platforms are moved over to use the flattened-device-tree model. + + a) MDIO IO device + + The MDIO is a bus to which the PHY devices are connected. For each + device that exists on this bus, a child node should be created. See + the definition of the PHY node below for an example of how to define + a PHY. + + Required properties: + - reg : Offset and length of the register set for the device + - device_type : Should be "mdio" + - compatible : Should define the compatible device type for the + mdio. Currently, this is most likely to be "gianfar" + + Example: + + mdio@24520 { + reg = <24520 20>; + + ethernet-phy@0 { + ...... + }; + }; + + + b) Gianfar-compatible ethernet nodes + + Required properties: + + - device_type : Should be "network" + - model : Model of the device. Can be "TSEC", "eTSEC", or "FEC" + - compatible : Should be "gianfar" + - reg : Offset and length of the register set for the device + - address : List of bytes representing the ethernet address of + this controller + - interrupts : where a is the interrupt number and b is a + field that represents an encoding of the sense and level + information for the interrupt. This should be encoded based on + the information in section 2) depending on the type of interrupt + controller you have. + - interrupt-parent : the phandle for the interrupt controller that + services interrupts for this device. + - phy-handle : The phandle for the PHY connected to this ethernet + controller. + + Example: + + ethernet@24000 { + #size-cells = <0>; + device_type = "network"; + model = "TSEC"; + compatible = "gianfar"; + reg = <24000 1000>; + address = [ 00 E0 0C 00 73 00 ]; + interrupts = ; + interrupt-parent = <40000>; + phy-handle = <2452000> + }; + + + + c) PHY nodes + + Required properties: + + - device_type : Should be "ethernet-phy" + - interrupts : where a is the interrupt number and b is a + field that represents an encoding of the sense and level + information for the interrupt. This should be encoded based on + the information in section 2) depending on the type of interrupt + controller you have. + - interrupt-parent : the phandle for the interrupt controller that + services interrupts for this device. + - reg : The ID number for the phy, usually a small integer + - linux,phandle : phandle for this node; likely referenced by an + ethernet controller node. + + + Example: + + ethernet-phy@0 { + linux,phandle = <2452000> + interrupt-parent = <40000>; + interrupts = <35 1>; + reg = <0>; + device_type = "ethernet-phy"; + }; + + + d) Interrupt controllers + + Some SOC devices contain interrupt controllers that are different + from the standard Open PIC specification. The SOC device nodes for + these types of controllers should be specified just like a standard + OpenPIC controller. Sense and level information should be encoded + as specified in section 2) of this chapter for each device that + specifies an interrupt. + + Example : + + pic@40000 { + linux,phandle = <40000>; + clock-frequency = <0>; + interrupt-controller; + #address-cells = <0>; + reg = <40000 40000>; + built-in; + compatible = "chrp,open-pic"; + device_type = "open-pic"; + big-endian; + }; + + + e) I2C + + Required properties : + + - device_type : Should be "i2c" + - reg : Offset and length of the register set for the device + + Recommended properties : + + - compatible : Should be "fsl-i2c" for parts compatible with + Freescale I2C specifications. + - interrupts : where a is the interrupt number and b is a + field that represents an encoding of the sense and level + information for the interrupt. This should be encoded based on + the information in section 2) depending on the type of interrupt + controller you have. + - interrupt-parent : the phandle for the interrupt controller that + services interrupts for this device. + - dfsrr : boolean; if defined, indicates that this I2C device has + a digital filter sampling rate register + - fsl5200-clocking : boolean; if defined, indicated that this device + uses the FSL 5200 clocking mechanism. + + Example : + + i2c@3000 { + interrupt-parent = <40000>; + interrupts = <1b 3>; + reg = <3000 18>; + device_type = "i2c"; + compatible = "fsl-i2c"; + dfsrr; + }; + + + More devices will be defined as this spec matures. + + +Appendix A - Sample SOC node for MPC8540 +======================================== + +Note that the #address-cells and #size-cells for the SoC node +in this example have been explicitly listed; these are likely +not necessary as they are usually the same as the root node. + + soc8540@e0000000 { + #address-cells = <1>; + #size-cells = <1>; + #interrupt-cells = <2>; + device_type = "soc"; + ranges = <00000000 e0000000 00100000> + reg = ; + + mdio@24520 { + reg = <24520 20>; + device_type = "mdio"; + compatible = "gianfar"; + + ethernet-phy@0 { + linux,phandle = <2452000> + interrupt-parent = <40000>; + interrupts = <35 1>; + reg = <0>; + device_type = "ethernet-phy"; + }; + + ethernet-phy@1 { + linux,phandle = <2452001> + interrupt-parent = <40000>; + interrupts = <35 1>; + reg = <1>; + device_type = "ethernet-phy"; + }; + + ethernet-phy@3 { + linux,phandle = <2452002> + interrupt-parent = <40000>; + interrupts = <35 1>; + reg = <3>; + device_type = "ethernet-phy"; + }; + + }; + + ethernet@24000 { + #size-cells = <0>; + device_type = "network"; + model = "TSEC"; + compatible = "gianfar"; + reg = <24000 1000>; + address = [ 00 E0 0C 00 73 00 ]; + interrupts = ; + interrupt-parent = <40000>; + phy-handle = <2452000>; + }; + + ethernet@25000 { + #address-cells = <1>; + #size-cells = <0>; + device_type = "network"; + model = "TSEC"; + compatible = "gianfar"; + reg = <25000 1000>; + address = [ 00 E0 0C 00 73 01 ]; + interrupts = <13 3 14 3 18 3>; + interrupt-parent = <40000>; + phy-handle = <2452001>; + }; + + ethernet@26000 { + #address-cells = <1>; + #size-cells = <0>; + device_type = "network"; + model = "FEC"; + compatible = "gianfar"; + reg = <26000 1000>; + address = [ 00 E0 0C 00 73 02 ]; + interrupts = <19 3>; + interrupt-parent = <40000>; + phy-handle = <2452002>; + }; + + serial@4500 { + device_type = "serial"; + compatible = "ns16550"; + reg = <4500 100>; + clock-frequency = <0>; + interrupts = <1a 3>; + interrupt-parent = <40000>; + }; + + pic@40000 { + linux,phandle = <40000>; + clock-frequency = <0>; + interrupt-controller; + #address-cells = <0>; + reg = <40000 40000>; + built-in; + compatible = "chrp,open-pic"; + device_type = "open-pic"; + big-endian; + }; + + i2c@3000 { + interrupt-parent = <40000>; + interrupts = <1b 3>; + reg = <3000 18>; + device_type = "i2c"; + compatible = "fsl-i2c"; + dfsrr; + }; + + }; diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas new file mode 100644 index 000000000000..f8c16cbf56ba --- /dev/null +++ b/Documentation/scsi/ChangeLog.megaraid_sas @@ -0,0 +1,24 @@ +1 Release Date : Mon Jan 23 14:09:01 PST 2006 - Sumant Patro +2 Current Version : 00.00.02.02 +3 Older Version : 00.00.02.01 + +i. New template defined to represent each family of controllers (identified by processor used). + The template will have defintions that will be initialised to appropritae values for a specific family of controllers. The template definition has four function pointers. During driver initialisation the function pointers will be set based on the controller family type. This change is done to support new controllers that has different processors and thus different register set. + + -Sumant Patro + +1 Release Date : Mon Dec 19 14:36:26 PST 2005 - Sumant Patro +2 Current Version : 00.00.02.00-rc4 +3 Older Version : 00.00.02.01 + +i. Code reorganized to remove code duplication in megasas_build_cmd. + + "There's a lot of duplicate code megasas_build_cmd. Move that out of the different codepathes and merge the reminder of megasas_build_cmd into megasas_queue_command" + + - Christoph Hellwig + +ii. Defined MEGASAS_IOC_FIRMWARE32 for code paths that handles 32 bit applications in 64 bit systems. + + "MEGASAS_IOC_FIRMWARE can't be redefined if CONFIG_COMPAT is set, we need to define a MEGASAS_IOC_FIRMWARE32 define so native binaries continue to work" + + - Christoph Hellwig diff --git a/Documentation/scsi/aic79xx.txt b/Documentation/scsi/aic79xx.txt index 0aeef740a95a..382b439b439e 100644 --- a/Documentation/scsi/aic79xx.txt +++ b/Documentation/scsi/aic79xx.txt @@ -1,5 +1,5 @@ ==================================================================== -= Adaptec Ultra320 Family Manager Set v1.3.11 = += Adaptec Ultra320 Family Manager Set = = = = README for = = The Linux Operating System = @@ -63,6 +63,11 @@ The following information is available in this file: 68-pin) 2. Version History + 3.0 (December 1st, 2005) + - Updated driver to use SCSI transport class infrastructure + - Upported sequencer and core fixes from adaptec released + version 2.0.15 of the driver. + 1.3.11 (July 11, 2003) - Fix several deadlock issues. - Add 29320ALP and 39320B Id's. @@ -194,7 +199,7 @@ The following information is available in this file: supported) - Support for the PCI-X standard up to 133MHz - Support for the PCI v2.2 standard - - Domain Validation + - Domain Validation 2.2. Operating System Support: - Redhat Linux 7.2, 7.3, 8.0, Advanced Server 2.1 @@ -411,77 +416,53 @@ The following information is available in this file: http://www.adaptec.com. -5. Contacting Adaptec +5. Adaptec Customer Support A Technical Support Identification (TSID) Number is required for Adaptec technical support. - The 12-digit TSID can be found on the white barcode-type label - included inside the box with your product. The TSID helps us + included inside the box with your product. The TSID helps us provide more efficient service by accurately identifying your product and support status. + Support Options - Search the Adaptec Support Knowledgebase (ASK) at http://ask.adaptec.com for articles, troubleshooting tips, and - frequently asked questions for your product. + frequently asked questions about your product. - For support via Email, submit your question to Adaptec's - Technical Support Specialists at http://ask.adaptec.com. + Technical Support Specialists at http://ask.adaptec.com/. North America - - Visit our Web site at http://www.adaptec.com. - - To speak with a Fibre Channel/RAID/External Storage Technical - Support Specialist, call 1-321-207-2000, - Hours: Monday-Friday, 3:00 A.M. to 5:00 P.M., PST. - (Not open on holidays) - - For Technical Support in all other technologies including - SCSI, call 1-408-934-7274, - Hours: Monday-Friday, 6:00 A.M. to 5:00 P.M., PST. - (Not open on holidays) - - For after hours support, call 1-800-416-8066 ($99/call, - $149/call on holidays) - - To order Adaptec products including software and cables, call - 1-800-442-7274 or 1-408-957-7274. You can also visit our - online store at http://www.adaptecstore.com + - Visit our Web site at http://www.adaptec.com/. + - For information about Adaptec's support options, call + 408-957-2550, 24 hours a day, 7 days a week. + - To speak with a Technical Support Specialist, + * For hardware products, call 408-934-7274, + Monday to Friday, 3:00 am to 5:00 pm, PDT. + * For RAID and Fibre Channel products, call 321-207-2000, + Monday to Friday, 3:00 am to 5:00 pm, PDT. + To expedite your service, have your computer with you. + - To order Adaptec products, including accessories and cables, + call 408-957-7274. To order cables online go to + http://www.adaptec.com/buy-cables/. Europe - - Visit our Web site at http://www.adaptec-europe.com. - - English and French: To speak with a Technical Support - Specialist, call one of the following numbers: - - English: +32-2-352-3470 - - French: +32-2-352-3460 - Hours: Monday-Thursday, 10:00 to 12:30, 13:30 to 17:30 CET - Friday, 10:00 to 12:30, 13:30 to 16:30 CET - - German: To speak with a Technical Support Specialist, - call +49-89-456-40660 - Hours: Monday-Thursday, 09:30 to 12:30, 13:30 to 16:30 CET - Friday, 09:30 to 12:30, 13:30 to 15:00 CET - - To order Adaptec products, including accessories and cables: - - UK: +0800-96-65-26 or fax +0800-731-02-95 - - Other European countries: +32-11-300-379 - - Australia and New Zealand - - Visit our Web site at http://www.adaptec.com.au. - - To speak with a Technical Support Specialist, call - +612-9416-0698 - Hours: Monday-Friday, 10:00 A.M. to 4:30 P.M., EAT - (Not open on holidays) + - Visit our Web site at http://www.adaptec-europe.com/. + - To speak with a Technical Support Specialist, call, or email, + * German: +49 89 4366 5522, Monday-Friday, 9:00-17:00 CET, + http://ask-de.adaptec.com/. + * French: +49 89 4366 5533, Monday-Friday, 9:00-17:00 CET, + http://ask-fr.adaptec.com/. + * English: +49 89 4366 5544, Monday-Friday, 9:00-17:00 GMT, + http://ask.adaptec.com/. + - You can order Adaptec cables online at + http://www.adaptec.com/buy-cables/. Japan + - Visit our web site at http://www.adaptec.co.jp/. - To speak with a Technical Support Specialist, call - +81-3-5308-6120 - Hours: Monday-Friday, 9:00 a.m. to 12:00 p.m., 1:00 p.m. to - 6:00 p.m. TSC - - Hong Kong and China - - To speak with a Technical Support Specialist, call - +852-2869-7200 - Hours: Monday-Friday, 10:00 to 17:00. - - Fax Technical Support at +852-2869-7100. - - Singapore - - To speak with a Technical Support Specialist, call - +65-245-7470 - Hours: Monday-Friday, 10:00 to 17:00. - - Fax Technical Support at +852-2869-7100 + +81 3 5308 6120, Monday-Friday, 9:00 a.m. to 12:00 p.m., + 1:00 p.m. to 6:00 p.m. ------------------------------------------------------------------- /* diff --git a/Documentation/scsi/aic7xxx.txt b/Documentation/scsi/aic7xxx.txt index 47e74ddc4bc9..3481fcded4c2 100644 --- a/Documentation/scsi/aic7xxx.txt +++ b/Documentation/scsi/aic7xxx.txt @@ -309,81 +309,57 @@ The following information is available in this file: ----------------------------------------------------------------- Example: - 'options aic7xxx aic7xxx=verbose,no_probe,tag_info:{{},{,,10}},seltime:1" + 'options aic7xxx aic7xxx=verbose,no_probe,tag_info:{{},{,,10}},seltime:1' enables verbose logging, Disable EISA/VLB probing, and set tag depth on Controller 1/Target 2 to 10 tags. -3. Contacting Adaptec +4. Adaptec Customer Support A Technical Support Identification (TSID) Number is required for Adaptec technical support. - The 12-digit TSID can be found on the white barcode-type label - included inside the box with your product. The TSID helps us + included inside the box with your product. The TSID helps us provide more efficient service by accurately identifying your product and support status. + Support Options - Search the Adaptec Support Knowledgebase (ASK) at http://ask.adaptec.com for articles, troubleshooting tips, and - frequently asked questions for your product. + frequently asked questions about your product. - For support via Email, submit your question to Adaptec's - Technical Support Specialists at http://ask.adaptec.com. + Technical Support Specialists at http://ask.adaptec.com/. North America - - Visit our Web site at http://www.adaptec.com. - - To speak with a Fibre Channel/RAID/External Storage Technical - Support Specialist, call 1-321-207-2000, - Hours: Monday-Friday, 3:00 A.M. to 5:00 P.M., PST. - (Not open on holidays) - - For Technical Support in all other technologies including - SCSI, call 1-408-934-7274, - Hours: Monday-Friday, 6:00 A.M. to 5:00 P.M., PST. - (Not open on holidays) - - For after hours support, call 1-800-416-8066 ($99/call, - $149/call on holidays) - - To order Adaptec products including software and cables, call - 1-800-442-7274 or 1-408-957-7274. You can also visit our - online store at http://www.adaptecstore.com + - Visit our Web site at http://www.adaptec.com/. + - For information about Adaptec's support options, call + 408-957-2550, 24 hours a day, 7 days a week. + - To speak with a Technical Support Specialist, + * For hardware products, call 408-934-7274, + Monday to Friday, 3:00 am to 5:00 pm, PDT. + * For RAID and Fibre Channel products, call 321-207-2000, + Monday to Friday, 3:00 am to 5:00 pm, PDT. + To expedite your service, have your computer with you. + - To order Adaptec products, including accessories and cables, + call 408-957-7274. To order cables online go to + http://www.adaptec.com/buy-cables/. Europe - - Visit our Web site at http://www.adaptec-europe.com. - - English and French: To speak with a Technical Support - Specialist, call one of the following numbers: - - English: +32-2-352-3470 - - French: +32-2-352-3460 - Hours: Monday-Thursday, 10:00 to 12:30, 13:30 to 17:30 CET - Friday, 10:00 to 12:30, 13:30 to 16:30 CET - - German: To speak with a Technical Support Specialist, - call +49-89-456-40660 - Hours: Monday-Thursday, 09:30 to 12:30, 13:30 to 16:30 CET - Friday, 09:30 to 12:30, 13:30 to 15:00 CET - - To order Adaptec products, including accessories and cables: - - UK: +0800-96-65-26 or fax +0800-731-02-95 - - Other European countries: +32-11-300-379 - - Australia and New Zealand - - Visit our Web site at http://www.adaptec.com.au. - - To speak with a Technical Support Specialist, call - +612-9416-0698 - Hours: Monday-Friday, 10:00 A.M. to 4:30 P.M., EAT - (Not open on holidays) + - Visit our Web site at http://www.adaptec-europe.com/. + - To speak with a Technical Support Specialist, call, or email, + * German: +49 89 4366 5522, Monday-Friday, 9:00-17:00 CET, + http://ask-de.adaptec.com/. + * French: +49 89 4366 5533, Monday-Friday, 9:00-17:00 CET, + http://ask-fr.adaptec.com/. + * English: +49 89 4366 5544, Monday-Friday, 9:00-17:00 GMT, + http://ask.adaptec.com/. + - You can order Adaptec cables online at + http://www.adaptec.com/buy-cables/. Japan + - Visit our web site at http://www.adaptec.co.jp/. - To speak with a Technical Support Specialist, call - +81-3-5308-6120 - Hours: Monday-Friday, 9:00 a.m. to 12:00 p.m., 1:00 p.m. to - 6:00 p.m. TSC - - Hong Kong and China - - To speak with a Technical Support Specialist, call - +852-2869-7200 - Hours: Monday-Friday, 10:00 to 17:00. - - Fax Technical Support at +852-2869-7100. - - Singapore - - To speak with a Technical Support Specialist, call - +65-245-7470 - Hours: Monday-Friday, 10:00 to 17:00. - - Fax Technical Support at +852-2869-7100 + +81 3 5308 6120, Monday-Friday, 9:00 a.m. to 12:00 p.m., + 1:00 p.m. to 6:00 p.m. ------------------------------------------------------------------- /* diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt index d2578013e829..36b511c7cade 100644 --- a/Documentation/sound/alsa/ALSA-Configuration.txt +++ b/Documentation/sound/alsa/ALSA-Configuration.txt @@ -837,8 +837,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. Module for AC'97 motherboards from Intel and compatibles. * Intel i810/810E, i815, i820, i830, i84x, MX440 + ICH5, ICH6, ICH7, ESB2 * SiS 7012 (SiS 735) - * NVidia NForce, NForce2 + * NVidia NForce, NForce2, NForce3, MCP04, CK804 + CK8, CK8S, MCP501 * AMD AMD768, AMD8111 * ALi m5455 @@ -868,6 +870,12 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. -------------------- Module for Intel ICH (i8x0) chipset MC97 modems. + * Intel i810/810E, i815, i820, i830, i84x, MX440 + ICH5, ICH6, ICH7 + * SiS 7013 (SiS 735) + * NVidia NForce, NForce2, NForce2s, NForce3 + * AMD AMD8111 + * ALi m5455 ac97_clock - AC'97 codec clock base (0 = auto-detect) diff --git a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl index e651ed8d1e6f..4251085d38d3 100644 --- a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl +++ b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl @@ -5206,14 +5206,14 @@ struct _snd_pcm_runtime { You need to pass the snd_dma_pci_data(pci), where pci is the struct pci_dev pointer of the chip as well. - The snd_sg_buf_t instance is created as + The struct snd_sg_buf instance is created as substream->dma_private. You can cast the pointer like: dma_private; + struct snd_sg_buf *sgbuf = (struct snd_sg_buf *)substream->dma_private; ]]> diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 391dd64363e7..a46c10fcddfc 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -28,6 +28,7 @@ Currently, these files are in /proc/sys/vm: - block_dump - drop-caches - zone_reclaim_mode +- zone_reclaim_interval ============================================================== @@ -126,15 +127,54 @@ the high water marks for each per cpu page list. zone_reclaim_mode: -This is set during bootup to 1 if it is determined that pages from -remote zones will cause a significant performance reduction. The +Zone_reclaim_mode allows to set more or less agressive approaches to +reclaim memory when a zone runs out of memory. If it is set to zero then no +zone reclaim occurs. Allocations will be satisfied from other zones / nodes +in the system. + +This is value ORed together of + +1 = Zone reclaim on +2 = Zone reclaim writes dirty pages out +4 = Zone reclaim swaps pages +8 = Also do a global slab reclaim pass + +zone_reclaim_mode is set during bootup to 1 if it is determined that pages +from remote zones will cause a measurable performance reduction. The page allocator will then reclaim easily reusable pages (those page -cache pages that are currently not used) before going off node. +cache pages that are currently not used) before allocating off node pages. -The user can override this setting. It may be beneficial to switch -off zone reclaim if the system is used for a file server and all -of memory should be used for caching files from disk. +It may be beneficial to switch off zone reclaim if the system is +used for a file server and all of memory should be used for caching files +from disk. In that case the caching effect is more important than +data locality. -It may be beneficial to switch this on if one wants to do zone -reclaim regardless of the numa distances in the system. +Allowing zone reclaim to write out pages stops processes that are +writing large amounts of data from dirtying pages on other nodes. Zone +reclaim will write out dirty pages if a zone fills up and so effectively +throttle the process. This may decrease the performance of a single process +since it cannot use all of system memory to buffer the outgoing writes +anymore but it preserve the memory on other nodes so that the performance +of other processes running on other nodes will not be affected. + +Allowing regular swap effectively restricts allocations to the local +node unless explicitly overridden by memory policies or cpuset +configurations. + +It may be advisable to allow slab reclaim if the system makes heavy +use of files and builds up large slab caches. However, the slab +shrink operation is global, may take a long time and free slabs +in all nodes of the system. + +================================================================ + +zone_reclaim_interval: + +The time allowed for off node allocations after zone reclaim +has failed to reclaim enough pages to allow a local allocation. + +Time is set in seconds and set by default to 30 seconds. + +Reduce the interval if undesired off node allocations occur. However, too +frequent scans will have a negative impact onoff node allocation performance. diff --git a/Documentation/usb/et61x251.txt b/Documentation/usb/et61x251.txt new file mode 100644 index 000000000000..b44dda407ce2 --- /dev/null +++ b/Documentation/usb/et61x251.txt @@ -0,0 +1,306 @@ + + ET61X[12]51 PC Camera Controllers + Driver for Linux + ================================= + + - Documentation - + + +Index +===== +1. Copyright +2. Disclaimer +3. License +4. Overview and features +5. Module dependencies +6. Module loading +7. Module parameters +8. Optional device control through "sysfs" +9. Supported devices +10. Notes for V4L2 application developers +11. Contact information + + +1. Copyright +============ +Copyright (C) 2006 by Luca Risolia + + +2. Disclaimer +============= +Etoms is a trademark of Etoms Electronics Corp. +This software is not developed or sponsored by Etoms Electronics. + + +3. License +========== +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. + +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., 675 Mass Ave, Cambridge, MA 02139, USA. + + +4. Overview and features +======================== +This driver supports the video interface of the devices mounting the ET61X151 +or ET61X251 PC Camera Controllers. + +It's worth to note that Etoms Electronics has never collaborated with the +author during the development of this project; despite several requests, +Etoms Electronics also refused to release enough detailed specifications of +the video compression engine. + +The driver relies on the Video4Linux2 and USB core modules. It has been +designed to run properly on SMP systems as well. + +The latest version of the ET61X[12]51 driver can be found at the following URL: +http://www.linux-projects.org/ + +Some of the features of the driver are: + +- full compliance with the Video4Linux2 API (see also "Notes for V4L2 + application developers" paragraph); +- available mmap or read/poll methods for video streaming through isochronous + data transfers; +- automatic detection of image sensor; +- support for any window resolutions and optional panning within the maximum + pixel area of image sensor; +- image downscaling with arbitrary scaling factors from 1 and 2 in both + directions (see "Notes for V4L2 application developers" paragraph); +- two different video formats for uncompressed or compressed data in low or + high compression quality (see also "Notes for V4L2 application developers" + paragraph); +- full support for the capabilities of every possible image sensors that can + be connected to the ET61X[12]51 bridges, including, for istance, red, green, + blue and global gain adjustments and exposure control (see "Supported + devices" paragraph for details); +- use of default color settings for sunlight conditions; +- dynamic I/O interface for both ET61X[12]51 and image sensor control (see + "Optional device control through 'sysfs'" paragraph); +- dynamic driver control thanks to various module parameters (see "Module + parameters" paragraph); +- up to 64 cameras can be handled at the same time; they can be connected and + disconnected from the host many times without turning off the computer, if + the system supports hotplugging; +- no known bugs. + + +5. Module dependencies +====================== +For it to work properly, the driver needs kernel support for Video4Linux and +USB. + +The following options of the kernel configuration file must be enabled and +corresponding modules must be compiled: + + # Multimedia devices + # + CONFIG_VIDEO_DEV=m + +To enable advanced debugging functionality on the device through /sysfs: + + # Multimedia devices + # + CONFIG_VIDEO_ADV_DEBUG=y + + # USB support + # + CONFIG_USB=m + +In addition, depending on the hardware being used, the modules below are +necessary: + + # USB Host Controller Drivers + # + CONFIG_USB_EHCI_HCD=m + CONFIG_USB_UHCI_HCD=m + CONFIG_USB_OHCI_HCD=m + +And finally: + + # USB Multimedia devices + # + CONFIG_USB_ET61X251=m + + +6. Module loading +================= +To use the driver, it is necessary to load the "et61x251" module into memory +after every other module required: "videodev", "usbcore" and, depending on +the USB host controller you have, "ehci-hcd", "uhci-hcd" or "ohci-hcd". + +Loading can be done as shown below: + + [root@localhost home]# modprobe et61x251 + +At this point the devices should be recognized. You can invoke "dmesg" to +analyze kernel messages and verify that the loading process has gone well: + + [user@localhost home]$ dmesg + + +7. Module parameters +==================== +Module parameters are listed below: +------------------------------------------------------------------------------- +Name: video_nr +Type: short array (min = 0, max = 64) +Syntax: <-1|n[,...]> +Description: Specify V4L2 minor mode number: + -1 = use next available + n = use minor number n + You can specify up to 64 cameras this way. + For example: + video_nr=-1,2,-1 would assign minor number 2 to the second + registered camera and use auto for the first one and for every + other camera. +Default: -1 +------------------------------------------------------------------------------- +Name: force_munmap +Type: bool array (min = 0, max = 64) +Syntax: <0|1[,...]> +Description: Force the application to unmap previously mapped buffer memory + before calling any VIDIOC_S_CROP or VIDIOC_S_FMT ioctl's. Not + all the applications support this feature. This parameter is + specific for each detected camera. + 0 = do not force memory unmapping + 1 = force memory unmapping (save memory) +Default: 0 +------------------------------------------------------------------------------- +Name: debug +Type: ushort +Syntax: +Description: Debugging information level, from 0 to 3: + 0 = none (use carefully) + 1 = critical errors + 2 = significant informations + 3 = more verbose messages + Level 3 is useful for testing only, when only one device + is used at the same time. It also shows some more informations + about the hardware being detected. This module parameter can be + changed at runtime thanks to the /sys filesystem interface. +Default: 2 +------------------------------------------------------------------------------- + + +8. Optional device control through "sysfs" +========================================== +If the kernel has been compiled with the CONFIG_VIDEO_ADV_DEBUG option enabled, +it is possible to read and write both the ET61X[12]51 and the image sensor +registers by using the "sysfs" filesystem interface. + +There are four files in the /sys/class/video4linux/videoX directory for each +registered camera: "reg", "val", "i2c_reg" and "i2c_val". The first two files +control the ET61X[12]51 bridge, while the other two control the sensor chip. +"reg" and "i2c_reg" hold the values of the current register index where the +following reading/writing operations are addressed at through "val" and +"i2c_val". Their use is not intended for end-users, unless you know what you +are doing. Remember that you must be logged in as root before writing to them. + +As an example, suppose we were to want to read the value contained in the +register number 1 of the sensor register table - which is usually the product +identifier - of the camera registered as "/dev/video0": + + [root@localhost #] cd /sys/class/video4linux/video0 + [root@localhost #] echo 1 > i2c_reg + [root@localhost #] cat i2c_val + +Note that if the sensor registers can not be read, "cat" will fail. +To avoid race conditions, all the I/O accesses to the files are serialized. + + +9. Supported devices +==================== +None of the names of the companies as well as their products will be mentioned +here. They have never collaborated with the author, so no advertising. + +From the point of view of a driver, what unambiguously identify a device are +its vendor and product USB identifiers. Below is a list of known identifiers of +devices mounting the ET61X[12]51 PC camera controllers: + +Vendor ID Product ID +--------- ---------- +0x102c 0x6151 +0x102c 0x6251 +0x102c 0x6253 +0x102c 0x6254 +0x102c 0x6255 +0x102c 0x6256 +0x102c 0x6257 +0x102c 0x6258 +0x102c 0x6259 +0x102c 0x625a +0x102c 0x625b +0x102c 0x625c +0x102c 0x625d +0x102c 0x625e +0x102c 0x625f +0x102c 0x6260 +0x102c 0x6261 +0x102c 0x6262 +0x102c 0x6263 +0x102c 0x6264 +0x102c 0x6265 +0x102c 0x6266 +0x102c 0x6267 +0x102c 0x6268 +0x102c 0x6269 + +The following image sensors are supported: + +Model Manufacturer +----- ------------ +TAS5130D1B Taiwan Advanced Sensor Corporation + +All the available control settings of each image sensor are supported through +the V4L2 interface. + + +10. Notes for V4L2 application developers +======================================== +This driver follows the V4L2 API specifications. In particular, it enforces two +rules: + +- exactly one I/O method, either "mmap" or "read", is associated with each +file descriptor. Once it is selected, the application must close and reopen the +device to switch to the other I/O method; + +- although it is not mandatory, previously mapped buffer memory should always +be unmapped before calling any "VIDIOC_S_CROP" or "VIDIOC_S_FMT" ioctl's. +The same number of buffers as before will be allocated again to match the size +of the new video frames, so you have to map the buffers again before any I/O +attempts on them. + +Consistently with the hardware limits, this driver also supports image +downscaling with arbitrary scaling factors from 1 and 2 in both directions. +However, the V4L2 API specifications don't correctly define how the scaling +factor can be chosen arbitrarily by the "negotiation" of the "source" and +"target" rectangles. To work around this flaw, we have added the convention +that, during the negotiation, whenever the "VIDIOC_S_CROP" ioctl is issued, the +scaling factor is restored to 1. + +This driver supports two different video formats: the first one is the "8-bit +Sequential Bayer" format and can be used to obtain uncompressed video data +from the device through the current I/O method, while the second one provides +"raw" compressed video data (without frame headers not related to the +compressed data). The current compression quality may vary from 0 to 1 and can +be selected or queried thanks to the VIDIOC_S_JPEGCOMP and VIDIOC_G_JPEGCOMP +V4L2 ioctl's. + + +11. Contact information +======================= +The author may be contacted by e-mail at . + +GPG/PGP encrypted e-mail's are accepted. The GPG key ID of the author is +'FCE635A4'; the public 1024-bit key should be available at any keyserver; +the fingerprint is: '88E8 F32F 7244 68BA 3958 5D40 99DA 5D2A FCE6 35A4'. diff --git a/Documentation/usb/sn9c102.txt b/Documentation/usb/sn9c102.txt index 3f8a119db31b..c6b76414172c 100644 --- a/Documentation/usb/sn9c102.txt +++ b/Documentation/usb/sn9c102.txt @@ -17,16 +17,15 @@ Index 7. Module parameters 8. Optional device control through "sysfs" 9. Supported devices -10. How to add plug-in's for new image sensors -11. Notes for V4L2 application developers -12. Video frame formats -13. Contact information -14. Credits +10. Notes for V4L2 application developers +11. Video frame formats +12. Contact information +13. Credits 1. Copyright ============ -Copyright (C) 2004-2005 by Luca Risolia +Copyright (C) 2004-2006 by Luca Risolia 2. Disclaimer @@ -54,9 +53,8 @@ Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. 4. Overview and features ======================== -This driver attempts to support the video and audio streaming capabilities of -the devices mounting the SONiX SN9C101, SN9C102 and SN9C103 PC Camera -Controllers. +This driver attempts to support the video interface of the devices mounting the +SONiX SN9C101, SN9C102 and SN9C103 PC Camera Controllers. It's worth to note that SONiX has never collaborated with the author during the development of this project, despite several requests for enough detailed @@ -78,6 +76,7 @@ Some of the features of the driver are: - available mmap or read/poll methods for video streaming through isochronous data transfers; - automatic detection of image sensor; +- support for built-in microphone interface; - support for any window resolutions and optional panning within the maximum pixel area of image sensor; - image downscaling with arbitrary scaling factors from 1, 2 and 4 in both @@ -96,7 +95,7 @@ Some of the features of the driver are: parameters" paragraph); - up to 64 cameras can be handled at the same time; they can be connected and disconnected from the host many times without turning off the computer, if - your system supports hotplugging; + the system supports hotplugging; - no known bugs. @@ -112,6 +111,12 @@ corresponding modules must be compiled: # CONFIG_VIDEO_DEV=m +To enable advanced debugging functionality on the device through /sysfs: + + # Multimedia devices + # + CONFIG_VIDEO_ADV_DEBUG=y + # USB support # CONFIG_USB=m @@ -125,6 +130,21 @@ necessary: CONFIG_USB_UHCI_HCD=m CONFIG_USB_OHCI_HCD=m +The SN9C103 controller also provides a built-in microphone interface. It is +supported by the USB Audio driver thanks to the ALSA API: + + # Sound + # + CONFIG_SOUND=y + + # Advanced Linux Sound Architecture + # + CONFIG_SND=m + + # USB devices + # + CONFIG_SND_USB_AUDIO=m + And finally: # USB Multimedia devices @@ -153,7 +173,7 @@ analyze kernel messages and verify that the loading process has gone well: Module parameters are listed below: ------------------------------------------------------------------------------- Name: video_nr -Type: int array (min = 0, max = 64) +Type: short array (min = 0, max = 64) Syntax: <-1|n[,...]> Description: Specify V4L2 minor mode number: -1 = use next available @@ -165,19 +185,19 @@ Description: Specify V4L2 minor mode number: other camera. Default: -1 ------------------------------------------------------------------------------- -Name: force_munmap; +Name: force_munmap Type: bool array (min = 0, max = 64) Syntax: <0|1[,...]> Description: Force the application to unmap previously mapped buffer memory before calling any VIDIOC_S_CROP or VIDIOC_S_FMT ioctl's. Not all the applications support this feature. This parameter is specific for each detected camera. - 0 = do not force memory unmapping" - 1 = force memory unmapping (save memory)" + 0 = do not force memory unmapping + 1 = force memory unmapping (save memory) Default: 0 ------------------------------------------------------------------------------- Name: debug -Type: int +Type: ushort Syntax: Description: Debugging information level, from 0 to 3: 0 = none (use carefully) @@ -187,14 +207,15 @@ Description: Debugging information level, from 0 to 3: Level 3 is useful for testing only, when only one device is used. It also shows some more informations about the hardware being detected. This parameter can be changed at - runtime thanks to the /sys filesystem. + runtime thanks to the /sys filesystem interface. Default: 2 ------------------------------------------------------------------------------- 8. Optional device control through "sysfs" [1] ========================================== -It is possible to read and write both the SN9C10x and the image sensor +If the kernel has been compiled with the CONFIG_VIDEO_ADV_DEBUG option enabled, +it is possible to read and write both the SN9C10x and the image sensor registers by using the "sysfs" filesystem interface. Every time a supported device is recognized, a write-only file named "green" is @@ -236,7 +257,7 @@ serialized. The sysfs interface also provides the "frame_header" entry, which exports the frame header of the most recent requested and captured video frame. The header -is 12-bytes long and is appended to every video frame by the SN9C10x +is always 18-bytes long and is appended to every video frame by the SN9C10x controllers. As an example, this additional information can be used by the user application for implementing auto-exposure features via software. @@ -250,7 +271,8 @@ Byte # Value Description 0x03 0xC4 Frame synchronisation pattern. 0x04 0xC4 Frame synchronisation pattern. 0x05 0x96 Frame synchronisation pattern. -0x06 0x00 or 0x01 Unknown meaning. The exact value depends on the chip. +0x06 0xXX Unknown meaning. The exact value depends on the chip; + possible values are 0x00, 0x01 and 0x20. 0x07 0xXX Variable value, whose bits are ff00uzzc, where ff is a frame counter, u is unknown, zz is a size indicator (00 = VGA, 01 = SIF, 10 = QSIF) and c stands for @@ -267,12 +289,23 @@ Byte # Value Description times the area outside of the specified AE area. For images that are not pure white, the value scales down according to relative whiteness. + according to relative whiteness. + +The following bytes are used by the SN9C103 bridge only: + +0x0C 0xXX Unknown meaning +0x0D 0xXX Unknown meaning +0x0E 0xXX Unknown meaning +0x0F 0xXX Unknown meaning +0x10 0xXX Unknown meaning +0x11 0xXX Unknown meaning The AE area (sx, sy, ex, ey) in the active window can be set by programming the registers 0x1c, 0x1d, 0x1e and 0x1f of the SN9C10x controllers, where one unit corresponds to 32 pixels. -[1] The frame header has been documented by Bertrik Sikken. +[1] Part of the meaning of the frame header has been documented by Bertrik + Sikken. 9. Supported devices @@ -298,6 +331,7 @@ Vendor ID Product ID 0x0c45 0x602b 0x0c45 0x602c 0x0c45 0x602d +0x0c45 0x602e 0x0c45 0x6030 0x0c45 0x6080 0x0c45 0x6082 @@ -348,18 +382,7 @@ appreciated. Non-available hardware will not be supported by the author of this driver. -10. How to add plug-in's for new image sensors -============================================== -It should be easy to write plug-in's for new sensors by using the small API -that has been created for this purpose, which is present in "sn9c102_sensor.h" -(documentation is included there). As an example, have a look at the code in -"sn9c102_pas106b.c", which uses the mentioned interface. - -At the moment, possible unsupported image sensors are: CIS-VF10 (VGA), -OV7620 (VGA), OV7630 (VGA). - - -11. Notes for V4L2 application developers +10. Notes for V4L2 application developers ========================================= This driver follows the V4L2 API specifications. In particular, it enforces two rules: @@ -394,7 +417,7 @@ initialized (as described in the documentation of the API for the image sensors supplied by this driver). -12. Video frame formats [1] +11. Video frame formats [1] ======================= The SN9C10x PC Camera Controllers can send images in two possible video formats over the USB: either native "Sequential RGB Bayer" or Huffman @@ -455,7 +478,7 @@ The following Huffman codes have been found: documented by Bertrik Sikken. -13. Contact information +12. Contact information ======================= The author may be contacted by e-mail at . @@ -464,7 +487,7 @@ GPG/PGP encrypted e-mail's are accepted. The GPG key ID of the author is the fingerprint is: '88E8 F32F 7244 68BA 3958 5D40 99DA 5D2A FCE6 35A4'. -14. Credits +13. Credits =========== Many thanks to following persons for their contribute (listed in alphabetical order): @@ -480,5 +503,5 @@ order): - Bertrik Sikken, who reverse-engineered and documented the Huffman compression algorithm used in the SN9C10x controllers and implemented the first decoder; - Mizuno Takafumi for the donation of a webcam; -- An "anonymous" donator (who didn't want his name to be revealed) for the +- an "anonymous" donator (who didn't want his name to be revealed) for the donation of a webcam. diff --git a/Documentation/usb/w9968cf.txt b/Documentation/usb/w9968cf.txt index 18a47738d56c..9d46cd0b19e3 100644 --- a/Documentation/usb/w9968cf.txt +++ b/Documentation/usb/w9968cf.txt @@ -57,16 +57,12 @@ based cameras should be supported as well. The driver is divided into two modules: the basic one, "w9968cf", is needed for the supported devices to work; the second one, "w9968cf-vpp", is an optional module, which provides some useful video post-processing functions like video -decoding, up-scaling and colour conversions. Once the driver is installed, -every time an application tries to open a recognized device, "w9968cf" checks -the presence of the "w9968cf-vpp" module and loads it automatically by default. +decoding, up-scaling and colour conversions. -Please keep in mind that official kernels do not include the second module for -performance purposes. However it is always recommended to download and install -the latest and complete release of the driver, replacing the existing one, if -present: it will be still even possible not to load the "w9968cf-vpp" module at -all, if you ever want to. Another important missing feature of the version in -the official Linux 2.4 kernels is the writeable /proc filesystem interface. +Note that the official kernels do neither include nor support the second +module for performance purposes. Therefore, it is always recommended to +download and install the latest and complete release of the driver, +replacing the existing one, if present. The latest and full-featured version of the W996[87]CF driver can be found at: http://www.linux-projects.org. Please refer to the documentation included in @@ -201,22 +197,6 @@ Note: The kernel must be compiled with the CONFIG_KMOD option enabled for the 'ovcamchip' module to be loaded and for this parameter to be present. ------------------------------------------------------------------------------- -Name: vppmod_load -Type: bool -Syntax: <0|1> -Description: Automatic 'w9968cf-vpp' module loading: 0 disabled, 1 enabled. - If enabled, every time an application attempts to open a - camera, 'insmod' searches for the video post-processing module - in the system and loads it automatically (if present). - The optional 'w9968cf-vpp' module adds extra image manipulation - capabilities to the 'w9968cf' module,like software up-scaling, - colour conversions and video decompression for very high frame - rates. -Default: 1 -Note: The kernel must be compiled with the CONFIG_KMOD option - enabled for the 'w9968cf-vpp' module to be loaded and for - this parameter to be present. -------------------------------------------------------------------------------- Name: simcams Type: int Syntax: diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration new file mode 100644 index 000000000000..c52820fcf500 --- /dev/null +++ b/Documentation/vm/page_migration @@ -0,0 +1,129 @@ +Page migration +-------------- + +Page migration allows the moving of the physical location of pages between +nodes in a numa system while the process is running. This means that the +virtual addresses that the process sees do not change. However, the +system rearranges the physical location of those pages. + +The main intend of page migration is to reduce the latency of memory access +by moving pages near to the processor where the process accessing that memory +is running. + +Page migration allows a process to manually relocate the node on which its +pages are located through the MF_MOVE and MF_MOVE_ALL options while setting +a new memory policy. The pages of process can also be relocated +from another process using the sys_migrate_pages() function call. The +migrate_pages function call takes two sets of nodes and moves pages of a +process that are located on the from nodes to the destination nodes. + +Manual migration is very useful if for example the scheduler has relocated +a process to a processor on a distant node. A batch scheduler or an +administrator may detect the situation and move the pages of the process +nearer to the new processor. At some point in the future we may have +some mechanism in the scheduler that will automatically move the pages. + +Larger installations usually partition the system using cpusets into +sections of nodes. Paul Jackson has equipped cpusets with the ability to +move pages when a task is moved to another cpuset. This allows automatic +control over locality of a process. If a task is moved to a new cpuset +then also all its pages are moved with it so that the performance of the +process does not sink dramatically (as is the case today). + +Page migration allows the preservation of the relative location of pages +within a group of nodes for all migration techniques which will preserve a +particular memory allocation pattern generated even after migrating a +process. This is necessary in order to preserve the memory latencies. +Processes will run with similar performance after migration. + +Page migration occurs in several steps. First a high level +description for those trying to use migrate_pages() and then +a low level description of how the low level details work. + +A. Use of migrate_pages() +------------------------- + +1. Remove pages from the LRU. + + Lists of pages to be migrated are generated by scanning over + pages and moving them into lists. This is done by + calling isolate_lru_page() or __isolate_lru_page(). + Calling isolate_lru_page increases the references to the page + so that it cannot vanish under us. + +2. Generate a list of newly allocates page to move the contents + of the first list to. + +3. The migrate_pages() function is called which attempts + to do the migration. It returns the moved pages in the + list specified as the third parameter and the failed + migrations in the fourth parameter. The first parameter + will contain the pages that could still be retried. + +4. The leftover pages of various types are returned + to the LRU using putback_to_lru_pages() or otherwise + disposed of. The pages will still have the refcount as + increased by isolate_lru_pages()! + +B. Operation of migrate_pages() +-------------------------------- + +migrate_pages does several passes over its list of pages. A page is moved +if all references to a page are removable at the time. + +Steps: + +1. Lock the page to be migrated + +2. Insure that writeback is complete. + +3. Make sure that the page has assigned swap cache entry if + it is an anonyous page. The swap cache reference is necessary + to preserve the information contain in the page table maps. + +4. Prep the new page that we want to move to. It is locked + and set to not being uptodate so that all accesses to the new + page immediately lock while we are moving references. + +5. All the page table references to the page are either dropped (file backed) + or converted to swap references (anonymous pages). This should decrease the + reference count. + +6. The radix tree lock is taken + +7. The refcount of the page is examined and we back out if references remain + otherwise we know that we are the only one referencing this page. + +8. The radix tree is checked and if it does not contain the pointer to this + page then we back out. + +9. The mapping is checked. If the mapping is gone then a truncate action may + be in progress and we back out. + +10. The new page is prepped with some settings from the old page so that accesses + to the new page will be discovered to have the correct settings. + +11. The radix tree is changed to point to the new page. + +12. The reference count of the old page is dropped because the reference has now + been removed. + +13. The radix tree lock is dropped. + +14. The page contents are copied to the new page. + +15. The remaining page flags are copied to the new page. + +16. The old page flags are cleared to indicate that the page does + not use any information anymore. + +17. Queued up writeback on the new page is triggered. + +18. If swap pte's were generated for the page then remove them again. + +19. The locks are dropped from the old and new page. + +20. The new page is moved to the LRU. + +Christoph Lameter, December 19, 2005. + diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86_64/boot-options.txt index 9c5fc15d03d1..153740f460a6 100644 --- a/Documentation/x86_64/boot-options.txt +++ b/Documentation/x86_64/boot-options.txt @@ -40,6 +40,18 @@ APICs no_timer_check Don't check the IO-APIC timer. This can work around problems with incorrect timer initialization on some boards. + apicmaintimer Run time keeping from the local APIC timer instead + of using the PIT/HPET interrupt for this. This is useful + when the PIT/HPET interrupts are unreliable. + + noapicmaintimer Don't do time keeping using the APIC timer. + Useful when this option was auto selected, but doesn't work. + + apicpmtimer + Do APIC timer calibration using the pmtimer. Implies + apicmaintimer. Useful when your PIT timer is totally + broken. + Early Console syntax: earlyprintk=vga diff --git a/MAINTAINERS b/MAINTAINERS index 3f8a90ac47d7..11d44daa6025 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -557,7 +557,8 @@ S: Supported CONFIGFS P: Joel Becker -M: Joel Becker +M: joel.becker@oracle.com +L: linux-kernel@vger.kernel.org S: Supported CIRRUS LOGIC GENERIC FBDEV DRIVER @@ -1176,8 +1177,8 @@ T: git kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git S: Maintained SN-IA64 (Itanium) SUB-PLATFORM -P: Greg Edwards -M: edwardsg@sgi.com +P: Jes Sorensen +M: jes@sgi.com L: linux-altix@sgi.com L: linux-ia64@vger.kernel.org W: http://www.sgi.com/altix @@ -1984,7 +1985,6 @@ M: philb@gnu.org P: Tim Waugh M: tim@cyberelk.net P: David Campbell -M: campbell@torque.net P: Andrea Arcangeli M: andrea@suse.de L: linux-parport@lists.infradead.org @@ -2298,7 +2298,7 @@ S: Supported SELINUX SECURITY MODULE P: Stephen Smalley -M: sds@epoch.ncsc.mil +M: sds@tycho.nsa.gov P: James Morris M: jmorris@namei.org L: linux-kernel@vger.kernel.org (kernel issues) @@ -2673,6 +2673,14 @@ M: dbrownell@users.sourceforge.net L: linux-usb-devel@lists.sourceforge.net S: Maintained +USB ET61X[12]51 DRIVER +P: Luca Risolia +M: luca.risolia@studio.unibo.it +L: linux-usb-devel@lists.sourceforge.net +L: video4linux-list@redhat.com +W: http://www.linux-projects.org +S: Maintained + USB HID/HIDBP DRIVERS P: Vojtech Pavlik M: vojtech@suse.cz @@ -2836,6 +2844,7 @@ USB SN9C10x DRIVER P: Luca Risolia M: luca.risolia@studio.unibo.it L: linux-usb-devel@lists.sourceforge.net +L: video4linux-list@redhat.com W: http://www.linux-projects.org S: Maintained @@ -2865,6 +2874,7 @@ USB W996[87]CF DRIVER P: Luca Risolia M: luca.risolia@studio.unibo.it L: linux-usb-devel@lists.sourceforge.net +L: video4linux-list@redhat.com W: http://www.linux-projects.org S: Maintained diff --git a/Makefile b/Makefile index 252a659896f3..cd5b619db9d8 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 16 -EXTRAVERSION =-rc1 +EXTRAVERSION =-rc2 NAME=Sliding Snow Leopard # *DOCUMENTATION* diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c index 8f2e5c718b50..6c56c754a0b5 100644 --- a/arch/alpha/kernel/asm-offsets.c +++ b/arch/alpha/kernel/asm-offsets.c @@ -28,6 +28,7 @@ void foo(void) DEFINE(TASK_GID, offsetof(struct task_struct, gid)); DEFINE(TASK_EGID, offsetof(struct task_struct, egid)); DEFINE(TASK_REAL_PARENT, offsetof(struct task_struct, real_parent)); + DEFINE(TASK_GROUP_LEADER, offsetof(struct task_struct, group_leader)); DEFINE(TASK_TGID, offsetof(struct task_struct, tgid)); BLANK(); diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index e38671c922bc..7af15bf7e5ab 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -879,17 +879,19 @@ sys_getxpid: /* See linux/kernel/timer.c sys_getppid for discussion about this loop. */ - ldq $3, TASK_REAL_PARENT($2) -1: ldl $1, TASK_TGID($3) + ldq $3, TASK_GROUP_LEADER($2) + ldq $4, TASK_REAL_PARENT($3) + ldl $0, TASK_TGID($2) +1: ldl $1, TASK_TGID($4) #ifdef CONFIG_SMP - mov $3, $4 + mov $4, $5 mb - ldq $3, TASK_REAL_PARENT($2) - cmpeq $3, $4, $4 - beq $4, 1b + ldq $3, TASK_GROUP_LEADER($2) + ldq $4, TASK_REAL_PARENT($3) + cmpeq $4, $5, $5 + beq $5, 1b #endif stq $1, 80($sp) - ldl $0, TASK_TGID($2) ret .end sys_getxpid diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 76be5cf0de13..9006063e7369 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -68,34 +68,32 @@ show_interrupts(struct seq_file *p, void *v) #ifdef CONFIG_SMP int j; #endif - int i = *(loff_t *) v; + int irq = *(loff_t *) v; struct irqaction * action; unsigned long flags; #ifdef CONFIG_SMP - if (i == 0) { + if (irq == 0) { seq_puts(p, " "); - for (i = 0; i < NR_CPUS; i++) - if (cpu_online(i)) - seq_printf(p, "CPU%d ", i); + for_each_online_cpu(j) + seq_printf(p, "CPU%d ", j); seq_putc(p, '\n'); } #endif - if (i < ACTUAL_NR_IRQS) { - spin_lock_irqsave(&irq_desc[i].lock, flags); - action = irq_desc[i].action; + if (irq < ACTUAL_NR_IRQS) { + spin_lock_irqsave(&irq_desc[irq].lock, flags); + action = irq_desc[irq].action; if (!action) goto unlock; - seq_printf(p, "%3d: ",i); + seq_printf(p, "%3d: ", irq); #ifndef CONFIG_SMP - seq_printf(p, "%10u ", kstat_irqs(i)); + seq_printf(p, "%10u ", kstat_irqs(irq)); #else - for (j = 0; j < NR_CPUS; j++) - if (cpu_online(j)) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + for_each_online_cpu(j) + seq_printf(p, "%10u ", kstat_cpu(j).irqs[irq]); #endif - seq_printf(p, " %14s", irq_desc[i].handler->typename); + seq_printf(p, " %14s", irq_desc[irq].handler->typename); seq_printf(p, " %c%s", (action->flags & SA_INTERRUPT)?'+':' ', action->name); @@ -108,13 +106,12 @@ show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); unlock: - spin_unlock_irqrestore(&irq_desc[i].lock, flags); - } else if (i == ACTUAL_NR_IRQS) { + spin_unlock_irqrestore(&irq_desc[irq].lock, flags); + } else if (irq == ACTUAL_NR_IRQS) { #ifdef CONFIG_SMP seq_puts(p, "IPI: "); - for (i = 0; i < NR_CPUS; i++) - if (cpu_online(i)) - seq_printf(p, "%10lu ", cpu_data[i].ipi_count); + for_each_online_cpu(j) + seq_printf(p, "%10lu ", cpu_data[j].ipi_count); seq_putc(p, '\n'); #endif seq_printf(p, "ERR: %10lu\n", irq_err_count); @@ -122,7 +119,6 @@ show_interrupts(struct seq_file *p, void *v) return 0; } - /* * handle_irq handles all normal device IRQ's (the special * SMP cross-CPU interrupts have their own specific diff --git a/arch/arm/configs/at91rm9200dk_defconfig b/arch/arm/configs/at91rm9200dk_defconfig index 5cdd13acf8ff..1fe73d198888 100644 --- a/arch/arm/configs/at91rm9200dk_defconfig +++ b/arch/arm/configs/at91rm9200dk_defconfig @@ -85,7 +85,6 @@ CONFIG_DEFAULT_IOSCHED="anticipatory" # CONFIG_ARCH_CLPS711X is not set # CONFIG_ARCH_CO285 is not set # CONFIG_ARCH_EBSA110 is not set -# CONFIG_ARCH_CAMELOT is not set # CONFIG_ARCH_FOOTBRIDGE is not set # CONFIG_ARCH_INTEGRATOR is not set # CONFIG_ARCH_IOP3XX is not set diff --git a/arch/arm/configs/at91rm9200ek_defconfig b/arch/arm/configs/at91rm9200ek_defconfig index 20838ccf1da7..b7d934cdb1b7 100644 --- a/arch/arm/configs/at91rm9200ek_defconfig +++ b/arch/arm/configs/at91rm9200ek_defconfig @@ -85,7 +85,6 @@ CONFIG_DEFAULT_IOSCHED="anticipatory" # CONFIG_ARCH_CLPS711X is not set # CONFIG_ARCH_CO285 is not set # CONFIG_ARCH_EBSA110 is not set -# CONFIG_ARCH_CAMELOT is not set # CONFIG_ARCH_FOOTBRIDGE is not set # CONFIG_ARCH_INTEGRATOR is not set # CONFIG_ARCH_IOP3XX is not set diff --git a/arch/arm/configs/bast_defconfig b/arch/arm/configs/bast_defconfig index 6886001b5366..4a8564f386af 100644 --- a/arch/arm/configs/bast_defconfig +++ b/arch/arm/configs/bast_defconfig @@ -14,8 +14,7 @@ CONFIG_GENERIC_IOMAP=y # Code maturity level options # CONFIG_EXPERIMENTAL=y -# CONFIG_CLEAN_COMPILE is not set -CONFIG_BROKEN=y +CONFIG_CLEAN_COMPILE=y CONFIG_BROKEN_ON_SMP=y # @@ -360,7 +359,6 @@ CONFIG_BLK_DEV_IDE_BAST=y # # IEEE 1394 (FireWire) support # -# CONFIG_IEEE1394 is not set # # I2O device support @@ -781,7 +779,6 @@ CONFIG_SYSFS=y # CONFIG_DEVFS_FS is not set # CONFIG_DEVPTS_FS_XATTR is not set # CONFIG_TMPFS is not set -# CONFIG_HUGETLBFS is not set # CONFIG_HUGETLB_PAGE is not set CONFIG_RAMFS=y diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig index 15468a0cf70e..c9aa878e610a 100644 --- a/arch/arm/configs/collie_defconfig +++ b/arch/arm/configs/collie_defconfig @@ -13,8 +13,7 @@ CONFIG_GENERIC_CALIBRATE_DELAY=y # Code maturity level options # CONFIG_EXPERIMENTAL=y -# CONFIG_CLEAN_COMPILE is not set -CONFIG_BROKEN=y +CONFIG_CLEAN_COMPILE=y CONFIG_BROKEN_ON_SMP=y CONFIG_LOCK_KERNEL=y CONFIG_INIT_ENV_ARG_LIMIT=32 @@ -308,9 +307,7 @@ CONFIG_MTD_CFI_I2=y # CONFIG_MTD_ROM is not set # CONFIG_MTD_ABSENT is not set CONFIG_MTD_OBSOLETE_CHIPS=y -# CONFIG_MTD_AMDSTD is not set CONFIG_MTD_SHARP=y -# CONFIG_MTD_JEDEC is not set # # Mapping drivers for chip access @@ -396,7 +393,6 @@ CONFIG_ATA_OVER_ETH=m # # IEEE 1394 (FireWire) support # -# CONFIG_IEEE1394 is not set # # I2O device support @@ -741,7 +737,6 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" CONFIG_PROC_FS=y CONFIG_SYSFS=y CONFIG_TMPFS=y -# CONFIG_HUGETLBFS is not set # CONFIG_HUGETLB_PAGE is not set CONFIG_RAMFS=y # CONFIG_RELAYFS_FS is not set diff --git a/arch/arm/configs/csb337_defconfig b/arch/arm/configs/csb337_defconfig index 885a3184830a..94bd9932a402 100644 --- a/arch/arm/configs/csb337_defconfig +++ b/arch/arm/configs/csb337_defconfig @@ -85,7 +85,6 @@ CONFIG_DEFAULT_IOSCHED="anticipatory" # CONFIG_ARCH_CLPS711X is not set # CONFIG_ARCH_CO285 is not set # CONFIG_ARCH_EBSA110 is not set -# CONFIG_ARCH_CAMELOT is not set # CONFIG_ARCH_FOOTBRIDGE is not set # CONFIG_ARCH_INTEGRATOR is not set # CONFIG_ARCH_IOP3XX is not set diff --git a/arch/arm/configs/csb637_defconfig b/arch/arm/configs/csb637_defconfig index 95a96a5462a0..1519124c5501 100644 --- a/arch/arm/configs/csb637_defconfig +++ b/arch/arm/configs/csb637_defconfig @@ -85,7 +85,6 @@ CONFIG_DEFAULT_IOSCHED="anticipatory" # CONFIG_ARCH_CLPS711X is not set # CONFIG_ARCH_CO285 is not set # CONFIG_ARCH_EBSA110 is not set -# CONFIG_ARCH_CAMELOT is not set # CONFIG_ARCH_FOOTBRIDGE is not set # CONFIG_ARCH_INTEGRATOR is not set # CONFIG_ARCH_IOP3XX is not set diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig index 33f31080a98c..1964ccd8a71f 100644 --- a/arch/arm/configs/s3c2410_defconfig +++ b/arch/arm/configs/s3c2410_defconfig @@ -13,8 +13,7 @@ CONFIG_GENERIC_CALIBRATE_DELAY=y # Code maturity level options # CONFIG_EXPERIMENTAL=y -# CONFIG_CLEAN_COMPILE is not set -CONFIG_BROKEN=y +CONFIG_CLEAN_COMPILE=y CONFIG_BROKEN_ON_SMP=y CONFIG_INIT_ENV_ARG_LIMIT=32 @@ -473,7 +472,6 @@ CONFIG_BLK_DEV_IDE_BAST=y # # IEEE 1394 (FireWire) support # -# CONFIG_IEEE1394 is not set # # I2O device support @@ -896,7 +894,6 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" CONFIG_PROC_FS=y CONFIG_SYSFS=y # CONFIG_TMPFS is not set -# CONFIG_HUGETLBFS is not set # CONFIG_HUGETLB_PAGE is not set CONFIG_RAMFS=y # CONFIG_RELAYFS_FS is not set diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index 75e6f9a94713..d058e7c12568 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -7,337 +7,334 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. * - * This file is included twice in entry-common.S + * This file is included thrice in entry-common.S */ -#ifndef NR_syscalls -#define NR_syscalls 328 -#else - -100: -/* 0 */ .long sys_restart_syscall - .long sys_exit - .long sys_fork_wrapper - .long sys_read - .long sys_write -/* 5 */ .long sys_open - .long sys_close - .long sys_ni_syscall /* was sys_waitpid */ - .long sys_creat - .long sys_link -/* 10 */ .long sys_unlink - .long sys_execve_wrapper - .long sys_chdir - .long OBSOLETE(sys_time) /* used by libc4 */ - .long sys_mknod -/* 15 */ .long sys_chmod - .long sys_lchown16 - .long sys_ni_syscall /* was sys_break */ - .long sys_ni_syscall /* was sys_stat */ - .long sys_lseek -/* 20 */ .long sys_getpid - .long sys_mount - .long OBSOLETE(sys_oldumount) /* used by libc4 */ - .long sys_setuid16 - .long sys_getuid16 -/* 25 */ .long OBSOLETE(sys_stime) - .long sys_ptrace - .long OBSOLETE(sys_alarm) /* used by libc4 */ - .long sys_ni_syscall /* was sys_fstat */ - .long sys_pause -/* 30 */ .long OBSOLETE(sys_utime) /* used by libc4 */ - .long sys_ni_syscall /* was sys_stty */ - .long sys_ni_syscall /* was sys_getty */ - .long sys_access - .long sys_nice -/* 35 */ .long sys_ni_syscall /* was sys_ftime */ - .long sys_sync - .long sys_kill - .long sys_rename - .long sys_mkdir -/* 40 */ .long sys_rmdir - .long sys_dup - .long sys_pipe - .long sys_times - .long sys_ni_syscall /* was sys_prof */ -/* 45 */ .long sys_brk - .long sys_setgid16 - .long sys_getgid16 - .long sys_ni_syscall /* was sys_signal */ - .long sys_geteuid16 -/* 50 */ .long sys_getegid16 - .long sys_acct - .long sys_umount - .long sys_ni_syscall /* was sys_lock */ - .long sys_ioctl -/* 55 */ .long sys_fcntl - .long sys_ni_syscall /* was sys_mpx */ - .long sys_setpgid - .long sys_ni_syscall /* was sys_ulimit */ - .long sys_ni_syscall /* was sys_olduname */ -/* 60 */ .long sys_umask - .long sys_chroot - .long sys_ustat - .long sys_dup2 - .long sys_getppid -/* 65 */ .long sys_getpgrp - .long sys_setsid - .long sys_sigaction - .long sys_ni_syscall /* was sys_sgetmask */ - .long sys_ni_syscall /* was sys_ssetmask */ -/* 70 */ .long sys_setreuid16 - .long sys_setregid16 - .long sys_sigsuspend_wrapper - .long sys_sigpending - .long sys_sethostname -/* 75 */ .long sys_setrlimit - .long OBSOLETE(sys_old_getrlimit) /* used by libc4 */ - .long sys_getrusage - .long sys_gettimeofday - .long sys_settimeofday -/* 80 */ .long sys_getgroups16 - .long sys_setgroups16 - .long OBSOLETE(old_select) /* used by libc4 */ - .long sys_symlink - .long sys_ni_syscall /* was sys_lstat */ -/* 85 */ .long sys_readlink - .long sys_uselib - .long sys_swapon - .long sys_reboot - .long OBSOLETE(old_readdir) /* used by libc4 */ -/* 90 */ .long OBSOLETE(old_mmap) /* used by libc4 */ - .long sys_munmap - .long sys_truncate - .long sys_ftruncate - .long sys_fchmod -/* 95 */ .long sys_fchown16 - .long sys_getpriority - .long sys_setpriority - .long sys_ni_syscall /* was sys_profil */ - .long sys_statfs -/* 100 */ .long sys_fstatfs - .long sys_ni_syscall - .long OBSOLETE(sys_socketcall) - .long sys_syslog - .long sys_setitimer -/* 105 */ .long sys_getitimer - .long sys_newstat - .long sys_newlstat - .long sys_newfstat - .long sys_ni_syscall /* was sys_uname */ -/* 110 */ .long sys_ni_syscall /* was sys_iopl */ - .long sys_vhangup - .long sys_ni_syscall - .long OBSOLETE(sys_syscall) /* call a syscall */ - .long sys_wait4 -/* 115 */ .long sys_swapoff - .long sys_sysinfo - .long OBSOLETE(ABI(sys_ipc, sys_oabi_ipc)) - .long sys_fsync - .long sys_sigreturn_wrapper -/* 120 */ .long sys_clone_wrapper - .long sys_setdomainname - .long sys_newuname - .long sys_ni_syscall - .long sys_adjtimex -/* 125 */ .long sys_mprotect - .long sys_sigprocmask - .long sys_ni_syscall /* was sys_create_module */ - .long sys_init_module - .long sys_delete_module -/* 130 */ .long sys_ni_syscall /* was sys_get_kernel_syms */ - .long sys_quotactl - .long sys_getpgid - .long sys_fchdir - .long sys_bdflush -/* 135 */ .long sys_sysfs - .long sys_personality - .long sys_ni_syscall /* .long _sys_afs_syscall */ - .long sys_setfsuid16 - .long sys_setfsgid16 -/* 140 */ .long sys_llseek - .long sys_getdents - .long sys_select - .long sys_flock - .long sys_msync -/* 145 */ .long sys_readv - .long sys_writev - .long sys_getsid - .long sys_fdatasync - .long sys_sysctl -/* 150 */ .long sys_mlock - .long sys_munlock - .long sys_mlockall - .long sys_munlockall - .long sys_sched_setparam -/* 155 */ .long sys_sched_getparam - .long sys_sched_setscheduler - .long sys_sched_getscheduler - .long sys_sched_yield - .long sys_sched_get_priority_max -/* 160 */ .long sys_sched_get_priority_min - .long sys_sched_rr_get_interval - .long sys_nanosleep - .long sys_arm_mremap - .long sys_setresuid16 -/* 165 */ .long sys_getresuid16 - .long sys_ni_syscall - .long sys_ni_syscall /* was sys_query_module */ - .long sys_poll - .long sys_nfsservctl -/* 170 */ .long sys_setresgid16 - .long sys_getresgid16 - .long sys_prctl - .long sys_rt_sigreturn_wrapper - .long sys_rt_sigaction -/* 175 */ .long sys_rt_sigprocmask - .long sys_rt_sigpending - .long sys_rt_sigtimedwait - .long sys_rt_sigqueueinfo - .long sys_rt_sigsuspend_wrapper -/* 180 */ .long ABI(sys_pread64, sys_oabi_pread64) - .long ABI(sys_pwrite64, sys_oabi_pwrite64) - .long sys_chown16 - .long sys_getcwd - .long sys_capget -/* 185 */ .long sys_capset - .long sys_sigaltstack_wrapper - .long sys_sendfile - .long sys_ni_syscall - .long sys_ni_syscall -/* 190 */ .long sys_vfork_wrapper - .long sys_getrlimit - .long sys_mmap2 - .long ABI(sys_truncate64, sys_oabi_truncate64) - .long ABI(sys_ftruncate64, sys_oabi_ftruncate64) -/* 195 */ .long ABI(sys_stat64, sys_oabi_stat64) - .long ABI(sys_lstat64, sys_oabi_lstat64) - .long ABI(sys_fstat64, sys_oabi_fstat64) - .long sys_lchown - .long sys_getuid -/* 200 */ .long sys_getgid - .long sys_geteuid - .long sys_getegid - .long sys_setreuid - .long sys_setregid -/* 205 */ .long sys_getgroups - .long sys_setgroups - .long sys_fchown - .long sys_setresuid - .long sys_getresuid -/* 210 */ .long sys_setresgid - .long sys_getresgid - .long sys_chown - .long sys_setuid - .long sys_setgid -/* 215 */ .long sys_setfsuid - .long sys_setfsgid - .long sys_getdents64 - .long sys_pivot_root - .long sys_mincore -/* 220 */ .long sys_madvise - .long ABI(sys_fcntl64, sys_oabi_fcntl64) - .long sys_ni_syscall /* TUX */ - .long sys_ni_syscall - .long sys_gettid -/* 225 */ .long ABI(sys_readahead, sys_oabi_readahead) - .long sys_setxattr - .long sys_lsetxattr - .long sys_fsetxattr - .long sys_getxattr -/* 230 */ .long sys_lgetxattr - .long sys_fgetxattr - .long sys_listxattr - .long sys_llistxattr - .long sys_flistxattr -/* 235 */ .long sys_removexattr - .long sys_lremovexattr - .long sys_fremovexattr - .long sys_tkill - .long sys_sendfile64 -/* 240 */ .long sys_futex - .long sys_sched_setaffinity - .long sys_sched_getaffinity - .long sys_io_setup - .long sys_io_destroy -/* 245 */ .long sys_io_getevents - .long sys_io_submit - .long sys_io_cancel - .long sys_exit_group - .long sys_lookup_dcookie -/* 250 */ .long sys_epoll_create - .long ABI(sys_epoll_ctl, sys_oabi_epoll_ctl) - .long ABI(sys_epoll_wait, sys_oabi_epoll_wait) - .long sys_remap_file_pages - .long sys_ni_syscall /* sys_set_thread_area */ -/* 255 */ .long sys_ni_syscall /* sys_get_thread_area */ - .long sys_set_tid_address - .long sys_timer_create - .long sys_timer_settime - .long sys_timer_gettime -/* 260 */ .long sys_timer_getoverrun - .long sys_timer_delete - .long sys_clock_settime - .long sys_clock_gettime - .long sys_clock_getres -/* 265 */ .long sys_clock_nanosleep - .long sys_statfs64_wrapper - .long sys_fstatfs64_wrapper - .long sys_tgkill - .long sys_utimes -/* 270 */ .long sys_arm_fadvise64_64 - .long sys_pciconfig_iobase - .long sys_pciconfig_read - .long sys_pciconfig_write - .long sys_mq_open -/* 275 */ .long sys_mq_unlink - .long sys_mq_timedsend - .long sys_mq_timedreceive - .long sys_mq_notify - .long sys_mq_getsetattr -/* 280 */ .long sys_waitid - .long sys_socket - .long sys_bind - .long sys_connect - .long sys_listen -/* 285 */ .long sys_accept - .long sys_getsockname - .long sys_getpeername - .long sys_socketpair - .long sys_send -/* 290 */ .long sys_sendto - .long sys_recv - .long sys_recvfrom - .long sys_shutdown - .long sys_setsockopt -/* 295 */ .long sys_getsockopt - .long sys_sendmsg - .long sys_recvmsg - .long ABI(sys_semop, sys_oabi_semop) - .long sys_semget -/* 300 */ .long sys_semctl - .long sys_msgsnd - .long sys_msgrcv - .long sys_msgget - .long sys_msgctl -/* 305 */ .long sys_shmat - .long sys_shmdt - .long sys_shmget - .long sys_shmctl - .long sys_add_key -/* 310 */ .long sys_request_key - .long sys_keyctl - .long ABI(sys_semtimedop, sys_oabi_semtimedop) -/* vserver */ .long sys_ni_syscall - .long sys_ioprio_set -/* 315 */ .long sys_ioprio_get - .long sys_inotify_init - .long sys_inotify_add_watch - .long sys_inotify_rm_watch - .long sys_mbind -/* 320 */ .long sys_get_mempolicy - .long sys_set_mempolicy - - .rept NR_syscalls - (. - 100b) / 4 - .long sys_ni_syscall - .endr +/* 0 */ CALL(sys_restart_syscall) + CALL(sys_exit) + CALL(sys_fork_wrapper) + CALL(sys_read) + CALL(sys_write) +/* 5 */ CALL(sys_open) + CALL(sys_close) + CALL(sys_ni_syscall) /* was sys_waitpid */ + CALL(sys_creat) + CALL(sys_link) +/* 10 */ CALL(sys_unlink) + CALL(sys_execve_wrapper) + CALL(sys_chdir) + CALL(OBSOLETE(sys_time)) /* used by libc4 */ + CALL(sys_mknod) +/* 15 */ CALL(sys_chmod) + CALL(sys_lchown16) + CALL(sys_ni_syscall) /* was sys_break */ + CALL(sys_ni_syscall) /* was sys_stat */ + CALL(sys_lseek) +/* 20 */ CALL(sys_getpid) + CALL(sys_mount) + CALL(OBSOLETE(sys_oldumount)) /* used by libc4 */ + CALL(sys_setuid16) + CALL(sys_getuid16) +/* 25 */ CALL(OBSOLETE(sys_stime)) + CALL(sys_ptrace) + CALL(OBSOLETE(sys_alarm)) /* used by libc4 */ + CALL(sys_ni_syscall) /* was sys_fstat */ + CALL(sys_pause) +/* 30 */ CALL(OBSOLETE(sys_utime)) /* used by libc4 */ + CALL(sys_ni_syscall) /* was sys_stty */ + CALL(sys_ni_syscall) /* was sys_getty */ + CALL(sys_access) + CALL(sys_nice) +/* 35 */ CALL(sys_ni_syscall) /* was sys_ftime */ + CALL(sys_sync) + CALL(sys_kill) + CALL(sys_rename) + CALL(sys_mkdir) +/* 40 */ CALL(sys_rmdir) + CALL(sys_dup) + CALL(sys_pipe) + CALL(sys_times) + CALL(sys_ni_syscall) /* was sys_prof */ +/* 45 */ CALL(sys_brk) + CALL(sys_setgid16) + CALL(sys_getgid16) + CALL(sys_ni_syscall) /* was sys_signal */ + CALL(sys_geteuid16) +/* 50 */ CALL(sys_getegid16) + CALL(sys_acct) + CALL(sys_umount) + CALL(sys_ni_syscall) /* was sys_lock */ + CALL(sys_ioctl) +/* 55 */ CALL(sys_fcntl) + CALL(sys_ni_syscall) /* was sys_mpx */ + CALL(sys_setpgid) + CALL(sys_ni_syscall) /* was sys_ulimit */ + CALL(sys_ni_syscall) /* was sys_olduname */ +/* 60 */ CALL(sys_umask) + CALL(sys_chroot) + CALL(sys_ustat) + CALL(sys_dup2) + CALL(sys_getppid) +/* 65 */ CALL(sys_getpgrp) + CALL(sys_setsid) + CALL(sys_sigaction) + CALL(sys_ni_syscall) /* was sys_sgetmask */ + CALL(sys_ni_syscall) /* was sys_ssetmask */ +/* 70 */ CALL(sys_setreuid16) + CALL(sys_setregid16) + CALL(sys_sigsuspend_wrapper) + CALL(sys_sigpending) + CALL(sys_sethostname) +/* 75 */ CALL(sys_setrlimit) + CALL(OBSOLETE(sys_old_getrlimit)) /* used by libc4 */ + CALL(sys_getrusage) + CALL(sys_gettimeofday) + CALL(sys_settimeofday) +/* 80 */ CALL(sys_getgroups16) + CALL(sys_setgroups16) + CALL(OBSOLETE(old_select)) /* used by libc4 */ + CALL(sys_symlink) + CALL(sys_ni_syscall) /* was sys_lstat */ +/* 85 */ CALL(sys_readlink) + CALL(sys_uselib) + CALL(sys_swapon) + CALL(sys_reboot) + CALL(OBSOLETE(old_readdir)) /* used by libc4 */ +/* 90 */ CALL(OBSOLETE(old_mmap)) /* used by libc4 */ + CALL(sys_munmap) + CALL(sys_truncate) + CALL(sys_ftruncate) + CALL(sys_fchmod) +/* 95 */ CALL(sys_fchown16) + CALL(sys_getpriority) + CALL(sys_setpriority) + CALL(sys_ni_syscall) /* was sys_profil */ + CALL(sys_statfs) +/* 100 */ CALL(sys_fstatfs) + CALL(sys_ni_syscall) + CALL(OBSOLETE(sys_socketcall)) + CALL(sys_syslog) + CALL(sys_setitimer) +/* 105 */ CALL(sys_getitimer) + CALL(sys_newstat) + CALL(sys_newlstat) + CALL(sys_newfstat) + CALL(sys_ni_syscall) /* was sys_uname */ +/* 110 */ CALL(sys_ni_syscall) /* was sys_iopl */ + CALL(sys_vhangup) + CALL(sys_ni_syscall) + CALL(OBSOLETE(sys_syscall)) /* call a syscall */ + CALL(sys_wait4) +/* 115 */ CALL(sys_swapoff) + CALL(sys_sysinfo) + CALL(OBSOLETE(ABI(sys_ipc, sys_oabi_ipc))) + CALL(sys_fsync) + CALL(sys_sigreturn_wrapper) +/* 120 */ CALL(sys_clone_wrapper) + CALL(sys_setdomainname) + CALL(sys_newuname) + CALL(sys_ni_syscall) + CALL(sys_adjtimex) +/* 125 */ CALL(sys_mprotect) + CALL(sys_sigprocmask) + CALL(sys_ni_syscall) /* was sys_create_module */ + CALL(sys_init_module) + CALL(sys_delete_module) +/* 130 */ CALL(sys_ni_syscall) /* was sys_get_kernel_syms */ + CALL(sys_quotactl) + CALL(sys_getpgid) + CALL(sys_fchdir) + CALL(sys_bdflush) +/* 135 */ CALL(sys_sysfs) + CALL(sys_personality) + CALL(sys_ni_syscall) /* CALL(_sys_afs_syscall) */ + CALL(sys_setfsuid16) + CALL(sys_setfsgid16) +/* 140 */ CALL(sys_llseek) + CALL(sys_getdents) + CALL(sys_select) + CALL(sys_flock) + CALL(sys_msync) +/* 145 */ CALL(sys_readv) + CALL(sys_writev) + CALL(sys_getsid) + CALL(sys_fdatasync) + CALL(sys_sysctl) +/* 150 */ CALL(sys_mlock) + CALL(sys_munlock) + CALL(sys_mlockall) + CALL(sys_munlockall) + CALL(sys_sched_setparam) +/* 155 */ CALL(sys_sched_getparam) + CALL(sys_sched_setscheduler) + CALL(sys_sched_getscheduler) + CALL(sys_sched_yield) + CALL(sys_sched_get_priority_max) +/* 160 */ CALL(sys_sched_get_priority_min) + CALL(sys_sched_rr_get_interval) + CALL(sys_nanosleep) + CALL(sys_arm_mremap) + CALL(sys_setresuid16) +/* 165 */ CALL(sys_getresuid16) + CALL(sys_ni_syscall) + CALL(sys_ni_syscall) /* was sys_query_module */ + CALL(sys_poll) + CALL(sys_nfsservctl) +/* 170 */ CALL(sys_setresgid16) + CALL(sys_getresgid16) + CALL(sys_prctl) + CALL(sys_rt_sigreturn_wrapper) + CALL(sys_rt_sigaction) +/* 175 */ CALL(sys_rt_sigprocmask) + CALL(sys_rt_sigpending) + CALL(sys_rt_sigtimedwait) + CALL(sys_rt_sigqueueinfo) + CALL(sys_rt_sigsuspend_wrapper) +/* 180 */ CALL(ABI(sys_pread64, sys_oabi_pread64)) + CALL(ABI(sys_pwrite64, sys_oabi_pwrite64)) + CALL(sys_chown16) + CALL(sys_getcwd) + CALL(sys_capget) +/* 185 */ CALL(sys_capset) + CALL(sys_sigaltstack_wrapper) + CALL(sys_sendfile) + CALL(sys_ni_syscall) + CALL(sys_ni_syscall) +/* 190 */ CALL(sys_vfork_wrapper) + CALL(sys_getrlimit) + CALL(sys_mmap2) + CALL(ABI(sys_truncate64, sys_oabi_truncate64)) + CALL(ABI(sys_ftruncate64, sys_oabi_ftruncate64)) +/* 195 */ CALL(ABI(sys_stat64, sys_oabi_stat64)) + CALL(ABI(sys_lstat64, sys_oabi_lstat64)) + CALL(ABI(sys_fstat64, sys_oabi_fstat64)) + CALL(sys_lchown) + CALL(sys_getuid) +/* 200 */ CALL(sys_getgid) + CALL(sys_geteuid) + CALL(sys_getegid) + CALL(sys_setreuid) + CALL(sys_setregid) +/* 205 */ CALL(sys_getgroups) + CALL(sys_setgroups) + CALL(sys_fchown) + CALL(sys_setresuid) + CALL(sys_getresuid) +/* 210 */ CALL(sys_setresgid) + CALL(sys_getresgid) + CALL(sys_chown) + CALL(sys_setuid) + CALL(sys_setgid) +/* 215 */ CALL(sys_setfsuid) + CALL(sys_setfsgid) + CALL(sys_getdents64) + CALL(sys_pivot_root) + CALL(sys_mincore) +/* 220 */ CALL(sys_madvise) + CALL(ABI(sys_fcntl64, sys_oabi_fcntl64)) + CALL(sys_ni_syscall) /* TUX */ + CALL(sys_ni_syscall) + CALL(sys_gettid) +/* 225 */ CALL(ABI(sys_readahead, sys_oabi_readahead)) + CALL(sys_setxattr) + CALL(sys_lsetxattr) + CALL(sys_fsetxattr) + CALL(sys_getxattr) +/* 230 */ CALL(sys_lgetxattr) + CALL(sys_fgetxattr) + CALL(sys_listxattr) + CALL(sys_llistxattr) + CALL(sys_flistxattr) +/* 235 */ CALL(sys_removexattr) + CALL(sys_lremovexattr) + CALL(sys_fremovexattr) + CALL(sys_tkill) + CALL(sys_sendfile64) +/* 240 */ CALL(sys_futex) + CALL(sys_sched_setaffinity) + CALL(sys_sched_getaffinity) + CALL(sys_io_setup) + CALL(sys_io_destroy) +/* 245 */ CALL(sys_io_getevents) + CALL(sys_io_submit) + CALL(sys_io_cancel) + CALL(sys_exit_group) + CALL(sys_lookup_dcookie) +/* 250 */ CALL(sys_epoll_create) + CALL(ABI(sys_epoll_ctl, sys_oabi_epoll_ctl)) + CALL(ABI(sys_epoll_wait, sys_oabi_epoll_wait)) + CALL(sys_remap_file_pages) + CALL(sys_ni_syscall) /* sys_set_thread_area */ +/* 255 */ CALL(sys_ni_syscall) /* sys_get_thread_area */ + CALL(sys_set_tid_address) + CALL(sys_timer_create) + CALL(sys_timer_settime) + CALL(sys_timer_gettime) +/* 260 */ CALL(sys_timer_getoverrun) + CALL(sys_timer_delete) + CALL(sys_clock_settime) + CALL(sys_clock_gettime) + CALL(sys_clock_getres) +/* 265 */ CALL(sys_clock_nanosleep) + CALL(sys_statfs64_wrapper) + CALL(sys_fstatfs64_wrapper) + CALL(sys_tgkill) + CALL(sys_utimes) +/* 270 */ CALL(sys_arm_fadvise64_64) + CALL(sys_pciconfig_iobase) + CALL(sys_pciconfig_read) + CALL(sys_pciconfig_write) + CALL(sys_mq_open) +/* 275 */ CALL(sys_mq_unlink) + CALL(sys_mq_timedsend) + CALL(sys_mq_timedreceive) + CALL(sys_mq_notify) + CALL(sys_mq_getsetattr) +/* 280 */ CALL(sys_waitid) + CALL(sys_socket) + CALL(sys_bind) + CALL(sys_connect) + CALL(sys_listen) +/* 285 */ CALL(sys_accept) + CALL(sys_getsockname) + CALL(sys_getpeername) + CALL(sys_socketpair) + CALL(sys_send) +/* 290 */ CALL(sys_sendto) + CALL(sys_recv) + CALL(sys_recvfrom) + CALL(sys_shutdown) + CALL(sys_setsockopt) +/* 295 */ CALL(sys_getsockopt) + CALL(sys_sendmsg) + CALL(sys_recvmsg) + CALL(ABI(sys_semop, sys_oabi_semop)) + CALL(sys_semget) +/* 300 */ CALL(sys_semctl) + CALL(sys_msgsnd) + CALL(sys_msgrcv) + CALL(sys_msgget) + CALL(sys_msgctl) +/* 305 */ CALL(sys_shmat) + CALL(sys_shmdt) + CALL(sys_shmget) + CALL(sys_shmctl) + CALL(sys_add_key) +/* 310 */ CALL(sys_request_key) + CALL(sys_keyctl) + CALL(ABI(sys_semtimedop, sys_oabi_semtimedop)) +/* vserver */ CALL(sys_ni_syscall) + CALL(sys_ioprio_set) +/* 315 */ CALL(sys_ioprio_get) + CALL(sys_inotify_init) + CALL(sys_inotify_add_watch) + CALL(sys_inotify_rm_watch) + CALL(sys_mbind) +/* 320 */ CALL(sys_get_mempolicy) + CALL(sys_set_mempolicy) +#ifndef syscalls_counted +.equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls +#define syscalls_counted #endif +.rept syscalls_padding + CALL(sys_ni_syscall) +.endr diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 2b92ce85f97f..dbcb11a31f78 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -87,7 +87,11 @@ ENTRY(ret_from_fork) b ret_slow_syscall + .equ NR_syscalls,0 +#define CALL(x) .equ NR_syscalls,NR_syscalls+1 #include "calls.S" +#undef CALL +#define CALL(x) .long x /*============================================================================= * SWI handler diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c index 31820170f306..a0724f2b24ce 100644 --- a/arch/arm/mach-integrator/integrator_cp.c +++ b/arch/arm/mach-integrator/integrator_cp.c @@ -469,7 +469,9 @@ static void cp_clcd_enable(struct clcd_fb *fb) if (fb->fb.var.bits_per_pixel <= 8) val = CM_CTRL_LCDMUXSEL_VGA_8421BPP; else if (fb->fb.var.bits_per_pixel <= 16) - val = CM_CTRL_LCDMUXSEL_VGA_16BPP; + val = CM_CTRL_LCDMUXSEL_VGA_16BPP + | CM_CTRL_LCDEN0 | CM_CTRL_LCDEN1 + | CM_CTRL_STATIC1 | CM_CTRL_STATIC2; else val = 0; /* no idea for this, don't trust the docs */ diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c index b41b1efaa2cf..3baa70819f24 100644 --- a/arch/arm/mach-pxa/pxa27x.c +++ b/arch/arm/mach-pxa/pxa27x.c @@ -44,7 +44,7 @@ unsigned int get_clk_frequency_khz( int info) /* Read clkcfg register: it has turbo, b, half-turbo (and f) */ asm( "mrc\tp14, 0, %0, c6, c0, 0" : "=r" (clkcfg) ); - t = clkcfg & (1 << 1); + t = clkcfg & (1 << 0); ht = clkcfg & (1 << 2); b = clkcfg & (1 << 3); diff --git a/arch/arm/mach-s3c2410/Makefile b/arch/arm/mach-s3c2410/Makefile index b4f1e051c768..1217bf00309c 100644 --- a/arch/arm/mach-s3c2410/Makefile +++ b/arch/arm/mach-s3c2410/Makefile @@ -10,9 +10,13 @@ obj-m := obj-n := obj- := +# S3C2400 support files +obj-$(CONFIG_CPU_S3C2400) += s3c2400-gpio.o + # S3C2410 support files obj-$(CONFIG_CPU_S3C2410) += s3c2410.o +obj-$(CONFIG_CPU_S3C2410) += s3c2410-gpio.o obj-$(CONFIG_S3C2410_DMA) += dma.o # Power Management support @@ -25,6 +29,7 @@ obj-$(CONFIG_PM_SIMTEC) += pm-simtec.o obj-$(CONFIG_CPU_S3C2440) += s3c2440.o s3c2440-dsc.o obj-$(CONFIG_CPU_S3C2440) += s3c2440-irq.o obj-$(CONFIG_CPU_S3C2440) += s3c2440-clock.o +obj-$(CONFIG_CPU_S3C2440) += s3c2410-gpio.o # bast extras diff --git a/arch/arm/mach-s3c2410/cpu.c b/arch/arm/mach-s3c2410/cpu.c index 687fe371369d..00a379334b60 100644 --- a/arch/arm/mach-s3c2410/cpu.c +++ b/arch/arm/mach-s3c2410/cpu.c @@ -40,6 +40,7 @@ #include "cpu.h" #include "clock.h" +#include "s3c2400.h" #include "s3c2410.h" #include "s3c2440.h" @@ -55,6 +56,7 @@ struct cpu_table { /* table of supported CPUs */ +static const char name_s3c2400[] = "S3C2400"; static const char name_s3c2410[] = "S3C2410"; static const char name_s3c2440[] = "S3C2440"; static const char name_s3c2410a[] = "S3C2410A"; @@ -96,7 +98,16 @@ static struct cpu_table cpu_ids[] __initdata = { .init_uarts = s3c2440_init_uarts, .init = s3c2440_init, .name = name_s3c2440a - } + }, + { + .idcode = 0x0, /* S3C2400 doesn't have an idcode */ + .idmask = 0xffffffff, + .map_io = s3c2400_map_io, + .init_clocks = s3c2400_init_clocks, + .init_uarts = s3c2400_init_uarts, + .init = s3c2400_init, + .name = name_s3c2400 + }, }; /* minimal IO mapping */ @@ -148,12 +159,15 @@ static struct cpu_table *cpu; void __init s3c24xx_init_io(struct map_desc *mach_desc, int size) { - unsigned long idcode; + unsigned long idcode = 0x0; /* initialise the io descriptors we need for initialisation */ iotable_init(s3c_iodesc, ARRAY_SIZE(s3c_iodesc)); +#ifndef CONFIG_CPU_S3C2400 idcode = __raw_readl(S3C2410_GSTATUS1); +#endif + cpu = s3c_lookup_cpu(idcode); if (cpu == NULL) { diff --git a/arch/arm/mach-s3c2410/cpu.h b/arch/arm/mach-s3c2410/cpu.h index 9cbe5eef492b..fc1067783f6d 100644 --- a/arch/arm/mach-s3c2410/cpu.h +++ b/arch/arm/mach-s3c2410/cpu.h @@ -17,11 +17,12 @@ * 14-Jan-2005 BJD Added s3c24xx_init_clocks() call * 10-Mar-2005 LCVR Changed S3C2410_{VA,SZ} to S3C24XX_{VA,SZ} & IODESC_ENT * 14-Mar-2005 BJD Updated for __iomem + * 15-Jan-2006 LCVR Updated S3C2410_PA_##x to new S3C24XX_PA_##x macro */ /* todo - fix when rmk changes iodescs to use `void __iomem *` */ -#define IODESC_ENT(x) { (unsigned long)S3C24XX_VA_##x, __phys_to_pfn(S3C2410_PA_##x), S3C24XX_SZ_##x, MT_DEVICE } +#define IODESC_ENT(x) { (unsigned long)S3C24XX_VA_##x, __phys_to_pfn(S3C24XX_PA_##x), S3C24XX_SZ_##x, MT_DEVICE } #ifndef MHZ #define MHZ (1000*1000) diff --git a/arch/arm/mach-s3c2410/devs.c b/arch/arm/mach-s3c2410/devs.c index f58406e6ef5a..b8d994a24d1c 100644 --- a/arch/arm/mach-s3c2410/devs.c +++ b/arch/arm/mach-s3c2410/devs.c @@ -10,6 +10,7 @@ * published by the Free Software Foundation. * * Modifications: + * 15-Jan-2006 LCVR Using S3C24XX_PA_##x macro for common S3C24XX devices * 10-Mar-2005 LCVR Changed S3C2410_{VA,SZ} to S3C24XX_{VA,SZ} * 10-Feb-2005 BJD Added camera from guillaume.gourat@nexvision.tv * 29-Aug-2004 BJD Added timers 0 through 3 @@ -46,8 +47,8 @@ struct platform_device *s3c24xx_uart_devs[3]; static struct resource s3c_usb_resource[] = { [0] = { - .start = S3C2410_PA_USBHOST, - .end = S3C2410_PA_USBHOST + S3C24XX_SZ_USBHOST - 1, + .start = S3C24XX_PA_USBHOST, + .end = S3C24XX_PA_USBHOST + S3C24XX_SZ_USBHOST - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -76,8 +77,8 @@ EXPORT_SYMBOL(s3c_device_usb); static struct resource s3c_lcd_resource[] = { [0] = { - .start = S3C2410_PA_LCD, - .end = S3C2410_PA_LCD + S3C24XX_SZ_LCD - 1, + .start = S3C24XX_PA_LCD, + .end = S3C24XX_PA_LCD + S3C24XX_SZ_LCD - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -139,8 +140,8 @@ EXPORT_SYMBOL(s3c_device_nand); static struct resource s3c_usbgadget_resource[] = { [0] = { - .start = S3C2410_PA_USBDEV, - .end = S3C2410_PA_USBDEV + S3C24XX_SZ_USBDEV - 1, + .start = S3C24XX_PA_USBDEV, + .end = S3C24XX_PA_USBDEV + S3C24XX_SZ_USBDEV - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -164,8 +165,8 @@ EXPORT_SYMBOL(s3c_device_usbgadget); static struct resource s3c_wdt_resource[] = { [0] = { - .start = S3C2410_PA_WATCHDOG, - .end = S3C2410_PA_WATCHDOG + S3C24XX_SZ_WATCHDOG - 1, + .start = S3C24XX_PA_WATCHDOG, + .end = S3C24XX_PA_WATCHDOG + S3C24XX_SZ_WATCHDOG - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -189,8 +190,8 @@ EXPORT_SYMBOL(s3c_device_wdt); static struct resource s3c_i2c_resource[] = { [0] = { - .start = S3C2410_PA_IIC, - .end = S3C2410_PA_IIC + S3C24XX_SZ_IIC - 1, + .start = S3C24XX_PA_IIC, + .end = S3C24XX_PA_IIC + S3C24XX_SZ_IIC - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -214,8 +215,8 @@ EXPORT_SYMBOL(s3c_device_i2c); static struct resource s3c_iis_resource[] = { [0] = { - .start = S3C2410_PA_IIS, - .end = S3C2410_PA_IIS + S3C24XX_SZ_IIS -1, + .start = S3C24XX_PA_IIS, + .end = S3C24XX_PA_IIS + S3C24XX_SZ_IIS -1, .flags = IORESOURCE_MEM, } }; @@ -239,8 +240,8 @@ EXPORT_SYMBOL(s3c_device_iis); static struct resource s3c_rtc_resource[] = { [0] = { - .start = S3C2410_PA_RTC, - .end = S3C2410_PA_RTC + 0xff, + .start = S3C24XX_PA_RTC, + .end = S3C24XX_PA_RTC + 0xff, .flags = IORESOURCE_MEM, }, [1] = { @@ -268,8 +269,8 @@ EXPORT_SYMBOL(s3c_device_rtc); static struct resource s3c_adc_resource[] = { [0] = { - .start = S3C2410_PA_ADC, - .end = S3C2410_PA_ADC + S3C24XX_SZ_ADC - 1, + .start = S3C24XX_PA_ADC, + .end = S3C24XX_PA_ADC + S3C24XX_SZ_ADC - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -316,8 +317,8 @@ EXPORT_SYMBOL(s3c_device_sdi); static struct resource s3c_spi0_resource[] = { [0] = { - .start = S3C2410_PA_SPI, - .end = S3C2410_PA_SPI + 0x1f, + .start = S3C24XX_PA_SPI, + .end = S3C24XX_PA_SPI + 0x1f, .flags = IORESOURCE_MEM, }, [1] = { @@ -341,8 +342,8 @@ EXPORT_SYMBOL(s3c_device_spi0); static struct resource s3c_spi1_resource[] = { [0] = { - .start = S3C2410_PA_SPI + 0x20, - .end = S3C2410_PA_SPI + 0x20 + 0x1f, + .start = S3C24XX_PA_SPI + 0x20, + .end = S3C24XX_PA_SPI + 0x20 + 0x1f, .flags = IORESOURCE_MEM, }, [1] = { @@ -366,8 +367,8 @@ EXPORT_SYMBOL(s3c_device_spi1); static struct resource s3c_timer0_resource[] = { [0] = { - .start = S3C2410_PA_TIMER + 0x0C, - .end = S3C2410_PA_TIMER + 0x0C + 0xB, + .start = S3C24XX_PA_TIMER + 0x0C, + .end = S3C24XX_PA_TIMER + 0x0C + 0xB, .flags = IORESOURCE_MEM, }, [1] = { @@ -391,8 +392,8 @@ EXPORT_SYMBOL(s3c_device_timer0); static struct resource s3c_timer1_resource[] = { [0] = { - .start = S3C2410_PA_TIMER + 0x18, - .end = S3C2410_PA_TIMER + 0x23, + .start = S3C24XX_PA_TIMER + 0x18, + .end = S3C24XX_PA_TIMER + 0x23, .flags = IORESOURCE_MEM, }, [1] = { @@ -416,8 +417,8 @@ EXPORT_SYMBOL(s3c_device_timer1); static struct resource s3c_timer2_resource[] = { [0] = { - .start = S3C2410_PA_TIMER + 0x24, - .end = S3C2410_PA_TIMER + 0x2F, + .start = S3C24XX_PA_TIMER + 0x24, + .end = S3C24XX_PA_TIMER + 0x2F, .flags = IORESOURCE_MEM, }, [1] = { @@ -441,8 +442,8 @@ EXPORT_SYMBOL(s3c_device_timer2); static struct resource s3c_timer3_resource[] = { [0] = { - .start = S3C2410_PA_TIMER + 0x30, - .end = S3C2410_PA_TIMER + 0x3B, + .start = S3C24XX_PA_TIMER + 0x30, + .end = S3C24XX_PA_TIMER + 0x3B, .flags = IORESOURCE_MEM, }, [1] = { diff --git a/arch/arm/mach-s3c2410/dma.c b/arch/arm/mach-s3c2410/dma.c index 65feaf20d23e..4dbd8e758ea6 100644 --- a/arch/arm/mach-s3c2410/dma.c +++ b/arch/arm/mach-s3c2410/dma.c @@ -1152,7 +1152,7 @@ static int __init s3c2410_init_dma(void) printk("S3C2410 DMA Driver, (c) 2003-2004 Simtec Electronics\n"); - dma_base = ioremap(S3C2410_PA_DMA, 0x200); + dma_base = ioremap(S3C24XX_PA_DMA, 0x200); if (dma_base == NULL) { printk(KERN_ERR "dma failed to remap register block\n"); return -ENOMEM; diff --git a/arch/arm/mach-s3c2410/gpio.c b/arch/arm/mach-s3c2410/gpio.c index 23ea3d5fa09c..cd39e8684584 100644 --- a/arch/arm/mach-s3c2410/gpio.c +++ b/arch/arm/mach-s3c2410/gpio.c @@ -31,6 +31,7 @@ * 05-Nov-2004 BJD EXPORT_SYMBOL() added for all code * 13-Mar-2005 BJD Updates for __iomem * 26-Oct-2005 BJD Added generic configuration types + * 15-Jan-2006 LCVR Added support for the S3C2400 */ @@ -48,7 +49,7 @@ void s3c2410_gpio_cfgpin(unsigned int pin, unsigned int function) { - void __iomem *base = S3C2410_GPIO_BASE(pin); + void __iomem *base = S3C24XX_GPIO_BASE(pin); unsigned long mask; unsigned long con; unsigned long flags; @@ -95,7 +96,7 @@ EXPORT_SYMBOL(s3c2410_gpio_cfgpin); unsigned int s3c2410_gpio_getcfg(unsigned int pin) { - void __iomem *base = S3C2410_GPIO_BASE(pin); + void __iomem *base = S3C24XX_GPIO_BASE(pin); unsigned long mask; if (pin < S3C2410_GPIO_BANKB) { @@ -111,7 +112,7 @@ EXPORT_SYMBOL(s3c2410_gpio_getcfg); void s3c2410_gpio_pullup(unsigned int pin, unsigned int to) { - void __iomem *base = S3C2410_GPIO_BASE(pin); + void __iomem *base = S3C24XX_GPIO_BASE(pin); unsigned long offs = S3C2410_GPIO_OFFSET(pin); unsigned long flags; unsigned long up; @@ -133,7 +134,7 @@ EXPORT_SYMBOL(s3c2410_gpio_pullup); void s3c2410_gpio_setpin(unsigned int pin, unsigned int to) { - void __iomem *base = S3C2410_GPIO_BASE(pin); + void __iomem *base = S3C24XX_GPIO_BASE(pin); unsigned long offs = S3C2410_GPIO_OFFSET(pin); unsigned long flags; unsigned long dat; @@ -152,7 +153,7 @@ EXPORT_SYMBOL(s3c2410_gpio_setpin); unsigned int s3c2410_gpio_getpin(unsigned int pin) { - void __iomem *base = S3C2410_GPIO_BASE(pin); + void __iomem *base = S3C24XX_GPIO_BASE(pin); unsigned long offs = S3C2410_GPIO_OFFSET(pin); return __raw_readl(base + 0x04) & (1<< offs); @@ -166,70 +167,13 @@ unsigned int s3c2410_modify_misccr(unsigned int clear, unsigned int change) unsigned long misccr; local_irq_save(flags); - misccr = __raw_readl(S3C2410_MISCCR); + misccr = __raw_readl(S3C24XX_MISCCR); misccr &= ~clear; misccr ^= change; - __raw_writel(misccr, S3C2410_MISCCR); + __raw_writel(misccr, S3C24XX_MISCCR); local_irq_restore(flags); return misccr; } EXPORT_SYMBOL(s3c2410_modify_misccr); - -int s3c2410_gpio_getirq(unsigned int pin) -{ - if (pin < S3C2410_GPF0 || pin > S3C2410_GPG15_EINT23) - return -1; /* not valid interrupts */ - - if (pin < S3C2410_GPG0 && pin > S3C2410_GPF7) - return -1; /* not valid pin */ - - if (pin < S3C2410_GPF4) - return (pin - S3C2410_GPF0) + IRQ_EINT0; - - if (pin < S3C2410_GPG0) - return (pin - S3C2410_GPF4) + IRQ_EINT4; - - return (pin - S3C2410_GPG0) + IRQ_EINT8; -} - -EXPORT_SYMBOL(s3c2410_gpio_getirq); - -int s3c2410_gpio_irqfilter(unsigned int pin, unsigned int on, - unsigned int config) -{ - void __iomem *reg = S3C2410_EINFLT0; - unsigned long flags; - unsigned long val; - - if (pin < S3C2410_GPG8 || pin > S3C2410_GPG15) - return -1; - - config &= 0xff; - - pin -= S3C2410_GPG8_EINT16; - reg += pin & ~3; - - local_irq_save(flags); - - /* update filter width and clock source */ - - val = __raw_readl(reg); - val &= ~(0xff << ((pin & 3) * 8)); - val |= config << ((pin & 3) * 8); - __raw_writel(val, reg); - - /* update filter enable */ - - val = __raw_readl(S3C2410_EXTINT2); - val &= ~(1 << ((pin * 4) + 3)); - val |= on << ((pin * 4) + 3); - __raw_writel(val, S3C2410_EXTINT2); - - local_irq_restore(flags); - - return 0; -} - -EXPORT_SYMBOL(s3c2410_gpio_irqfilter); diff --git a/arch/arm/mach-s3c2410/s3c2400-gpio.c b/arch/arm/mach-s3c2410/s3c2400-gpio.c new file mode 100644 index 000000000000..5127f39fa9bf --- /dev/null +++ b/arch/arm/mach-s3c2410/s3c2400-gpio.c @@ -0,0 +1,45 @@ +/* linux/arch/arm/mach-s3c2410/gpio.c + * + * Copyright (c) 2006 Lucas Correia Villa Real + * + * S3C2400 GPIO support + * + * 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. + * + * 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 + * + * Changelog + * 15-Jan-2006 LCVR Splitted from gpio.c, adding support for the S3C2400 + */ + +#include +#include +#include +#include +#include + +#include +#include +#include + +#include + +int s3c2400_gpio_getirq(unsigned int pin) +{ + if (pin < S3C2410_GPE0 || pin > S3C2400_GPE7_EINT7) + return -1; /* not valid interrupts */ + + return (pin - S3C2410_GPE0) + IRQ_EINT0; +} + +EXPORT_SYMBOL(s3c2400_gpio_getirq); diff --git a/arch/arm/mach-s3c2410/s3c2410-gpio.c b/arch/arm/mach-s3c2410/s3c2410-gpio.c new file mode 100644 index 000000000000..d5e1caea1d23 --- /dev/null +++ b/arch/arm/mach-s3c2410/s3c2410-gpio.c @@ -0,0 +1,93 @@ +/* linux/arch/arm/mach-s3c2410/gpio.c + * + * Copyright (c) 2004-2006 Simtec Electronics + * Ben Dooks + * + * S3C2410 GPIO support + * + * 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. + * + * 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 + * + * Changelog + * 15-Jan-2006 LCVR Splitted from gpio.c + */ + +#include +#include +#include +#include +#include + +#include +#include +#include + +#include + +int s3c2410_gpio_irqfilter(unsigned int pin, unsigned int on, + unsigned int config) +{ + void __iomem *reg = S3C2410_EINFLT0; + unsigned long flags; + unsigned long val; + + if (pin < S3C2410_GPG8 || pin > S3C2410_GPG15) + return -1; + + config &= 0xff; + + pin -= S3C2410_GPG8_EINT16; + reg += pin & ~3; + + local_irq_save(flags); + + /* update filter width and clock source */ + + val = __raw_readl(reg); + val &= ~(0xff << ((pin & 3) * 8)); + val |= config << ((pin & 3) * 8); + __raw_writel(val, reg); + + /* update filter enable */ + + val = __raw_readl(S3C2410_EXTINT2); + val &= ~(1 << ((pin * 4) + 3)); + val |= on << ((pin * 4) + 3); + __raw_writel(val, S3C2410_EXTINT2); + + local_irq_restore(flags); + + return 0; +} + +EXPORT_SYMBOL(s3c2410_gpio_irqfilter); + +int s3c2410_gpio_getirq(unsigned int pin) +{ + if (pin < S3C2410_GPF0 || pin > S3C2410_GPG15_EINT23) + return -1; /* not valid interrupts */ + + if (pin < S3C2410_GPG0 && pin > S3C2410_GPF7) + return -1; /* not valid pin */ + + if (pin < S3C2410_GPF4) + return (pin - S3C2410_GPF0) + IRQ_EINT0; + + if (pin < S3C2410_GPG0) + return (pin - S3C2410_GPF4) + IRQ_EINT4; + + return (pin - S3C2410_GPG0) + IRQ_EINT8; +} + +EXPORT_SYMBOL(s3c2410_gpio_getirq); diff --git a/arch/arm/mach-s3c2410/sleep.S b/arch/arm/mach-s3c2410/sleep.S index 61768dac7fee..832fb86a03b4 100644 --- a/arch/arm/mach-s3c2410/sleep.S +++ b/arch/arm/mach-s3c2410/sleep.S @@ -72,7 +72,7 @@ ENTRY(s3c2410_cpu_suspend) @@ prepare cpu to sleep ldr r4, =S3C2410_REFRESH - ldr r5, =S3C2410_MISCCR + ldr r5, =S3C24XX_MISCCR ldr r6, =S3C2410_CLKCON ldr r7, [ r4 ] @ get REFRESH (and ensure in TLB) ldr r8, [ r5 ] @ get MISCCR (and ensure in TLB) @@ -133,12 +133,12 @@ ENTRY(s3c2410_cpu_resume) @@ load UART to allow us to print the two characters for @@ resume debug - mov r2, #S3C2410_PA_UART & 0xff000000 - orr r2, r2, #S3C2410_PA_UART & 0xff000 + mov r2, #S3C24XX_PA_UART & 0xff000000 + orr r2, r2, #S3C24XX_PA_UART & 0xff000 #if 0 /* SMDK2440 LED set */ - mov r14, #S3C2410_PA_GPIO + mov r14, #S3C24XX_PA_GPIO ldr r12, [ r14, #0x54 ] bic r12, r12, #3<<4 orr r12, r12, #1<<7 diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S index 72966d90e956..d921c1024ae0 100644 --- a/arch/arm/mm/cache-v6.S +++ b/arch/arm/mm/cache-v6.S @@ -92,22 +92,16 @@ ENTRY(v6_coherent_kern_range) * - the Icache does not read data from the write buffer */ ENTRY(v6_coherent_user_range) - bic r0, r0, #CACHE_LINE_SIZE - 1 -1: + #ifdef HARVARD_CACHE - mcr p15, 0, r0, c7, c10, 1 @ clean D line + bic r0, r0, #CACHE_LINE_SIZE - 1 +1: mcr p15, 0, r0, c7, c10, 1 @ clean D line mcr p15, 0, r0, c7, c5, 1 @ invalidate I line -#endif - mcr p15, 0, r0, c7, c5, 7 @ invalidate BTB entry - add r0, r0, #BTB_FLUSH_SIZE - mcr p15, 0, r0, c7, c5, 7 @ invalidate BTB entry - add r0, r0, #BTB_FLUSH_SIZE - mcr p15, 0, r0, c7, c5, 7 @ invalidate BTB entry - add r0, r0, #BTB_FLUSH_SIZE - mcr p15, 0, r0, c7, c5, 7 @ invalidate BTB entry - add r0, r0, #BTB_FLUSH_SIZE + add r0, r0, #CACHE_LINE_SIZE cmp r0, r1 blo 1b +#endif + mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB #ifdef HARVARD_CACHE mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index de3ce1eec2ec..da9b35974118 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -142,7 +142,7 @@ __ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size, return NULL; addr = (unsigned long)area->addr; if (remap_area_pages(addr, pfn, size, flags)) { - vfree(addr); + vfree((void *)addr); return NULL; } return (void __iomem *) (offset + (char *)addr); diff --git a/arch/arm/mm/mm-armv.c b/arch/arm/mm/mm-armv.c index d0245a31d4dd..ef8d30a185a9 100644 --- a/arch/arm/mm/mm-armv.c +++ b/arch/arm/mm/mm-armv.c @@ -343,6 +343,12 @@ static struct mem_types mem_types[] __initdata = { PMD_SECT_AP_WRITE | PMD_SECT_BUFFERABLE | PMD_SECT_TEX(1), .domain = DOMAIN_IO, + }, + [MT_NONSHARED_DEVICE] = { + .prot_l1 = PMD_TYPE_TABLE, + .prot_sect = PMD_TYPE_SECT | PMD_SECT_NONSHARED_DEV | + PMD_SECT_AP_WRITE, + .domain = DOMAIN_IO, } }; diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 861b35947280..2d3823ec3153 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -241,7 +241,15 @@ ENTRY(xscale_flush_user_cache_range) * it also trashes the mini I-cache used by JTAG debuggers. */ ENTRY(xscale_coherent_kern_range) - /* FALLTHROUGH */ + bic r0, r0, #CACHELINESIZE - 1 +1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry + add r0, r0, #CACHELINESIZE + cmp r0, r1 + blo 1b + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ Invalidate I cache & BTB + mcr p15, 0, r0, c7, c10, 4 @ Drain Write (& Fill) Buffer + mov pc, lr /* * coherent_user_range(start, end) @@ -252,18 +260,16 @@ ENTRY(xscale_coherent_kern_range) * * - start - virtual start address * - end - virtual end address - * - * Note: single I-cache line invalidation isn't used here since - * it also trashes the mini I-cache used by JTAG debuggers. */ ENTRY(xscale_coherent_user_range) bic r0, r0, #CACHELINESIZE - 1 1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry + mcr p15, 0, r0, c7, c5, 1 @ Invalidate I cache entry add r0, r0, #CACHELINESIZE cmp r0, r1 blo 1b mov r0, #0 - mcr p15, 0, r0, c7, c5, 0 @ Invalidate I cache & BTB + mcr p15, 0, r0, c7, c5, 6 @ Invalidate BTB mcr p15, 0, r0, c7, c10, 4 @ Drain Write (& Fill) Buffer mov pc, lr diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 1415930ceee1..6f8bc1f0e6a1 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -137,8 +137,9 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) if (spec) { init_MUTEX(&op_arm_sem); - if (spec->init() < 0) - return -ENODEV; + ret = spec->init(); + if (ret < 0) + return ret; op_arm_model = spec; init_driverfs(); diff --git a/arch/arm26/Kconfig b/arch/arm26/Kconfig index 274e07019b46..dee23d87fc5a 100644 --- a/arch/arm26/Kconfig +++ b/arch/arm26/Kconfig @@ -53,14 +53,14 @@ config GENERIC_ISA_DMA config ARCH_MAY_HAVE_PC_FDC bool - default y source "init/Kconfig" menu "System Type" -comment "Archimedes/A5000 Implementations (select only ONE)" +choice + prompt "Archimedes/A5000 Implementations" config ARCH_ARC bool "Archimedes" @@ -73,6 +73,7 @@ config ARCH_ARC config ARCH_A5K bool "A5000" + select ARCH_MAY_HAVE_PC_FDC help Say Y here to to support the Acorn A5000. @@ -87,6 +88,7 @@ config PAGESIZE_16 Say Y here if your Archimedes or A5000 system has only 2MB of memory, otherwise say N. The resulting kernel will not run on a machine with 4MB of memory. +endchoice endmenu config ISA_DMA_API diff --git a/arch/arm26/kernel/fiq.c b/arch/arm26/kernel/fiq.c index 08a97c9498ff..a24272b61f30 100644 --- a/arch/arm26/kernel/fiq.c +++ b/arch/arm26/kernel/fiq.c @@ -104,14 +104,14 @@ void set_fiq_regs(struct pt_regs *regs) { register unsigned long tmp, tmp2; __asm__ volatile ( - "mov %0, pc - bic %1, %0, #0x3 - orr %1, %1, %3 - teqp %1, #0 @ select FIQ mode - mov r0, r0 - ldmia %2, {r8 - r14} - teqp %0, #0 @ return to SVC mode - mov r0, r0" + "mov %0, pc \n" + "bic %1, %0, #0x3 \n" + "orr %1, %1, %3 \n" + "teqp %1, #0 @ select FIQ mode \n" + "mov r0, r0 \n" + "ldmia %2, {r8 - r14} \n" + "teqp %0, #0 @ return to SVC mode \n" + "mov r0, r0 " : "=&r" (tmp), "=&r" (tmp2) : "r" (®s->ARM_r8), "I" (PSR_I_BIT | PSR_F_BIT | MODE_FIQ26) /* These registers aren't modified by the above code in a way @@ -125,14 +125,14 @@ void get_fiq_regs(struct pt_regs *regs) { register unsigned long tmp, tmp2; __asm__ volatile ( - "mov %0, pc - bic %1, %0, #0x3 - orr %1, %1, %3 - teqp %1, #0 @ select FIQ mode - mov r0, r0 - stmia %2, {r8 - r14} - teqp %0, #0 @ return to SVC mode - mov r0, r0" + "mov %0, pc \n" + "bic %1, %0, #0x3 \n" + "orr %1, %1, %3 \n" + "teqp %1, #0 @ select FIQ mode \n" + "mov r0, r0 \n" + "stmia %2, {r8 - r14} \n" + "teqp %0, #0 @ return to SVC mode \n" + "mov r0, r0 " : "=&r" (tmp), "=&r" (tmp2) : "r" (®s->ARM_r8), "I" (PSR_I_BIT | PSR_F_BIT | MODE_FIQ26) /* These registers aren't modified by the above code in a way diff --git a/arch/arm26/kernel/signal.c b/arch/arm26/kernel/signal.c index ce2055bdc9ee..2a48c12100c0 100644 --- a/arch/arm26/kernel/signal.c +++ b/arch/arm26/kernel/signal.c @@ -480,6 +480,7 @@ static int do_signal(sigset_t *oldset, struct pt_regs *regs, int syscall) { siginfo_t info; int signr; + struct k_sigaction ka; /* * We want the common case to go fast, which @@ -493,7 +494,7 @@ static int do_signal(sigset_t *oldset, struct pt_regs *regs, int syscall) if (current->ptrace & PT_SINGLESTEP) ptrace_cancel_bpt(current); - signr = get_signal_to_deliver(&info, regs, NULL); + signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { handle_signal(signr, &info, oldset, regs, syscall); if (current->ptrace & PT_SINGLESTEP) diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index cbde675bc95c..0afec8566e7b 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -47,15 +47,6 @@ config DMI source "init/Kconfig" -config DOUBLEFAULT - default y - bool "Enable doublefault exception handler" if EMBEDDED - help - This option allows trapping of rare doublefault exceptions that - would otherwise cause a system to silently reboot. Disabling this - option saves about 4k and might cause you much additional grey - hair. - menu "Processor type and features" choice @@ -451,12 +442,50 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" + depends on X86_CMPXCHG64 help Select this if you have a 32-bit processor and more than 4 gigabytes of physical RAM. endchoice +choice + depends on EXPERIMENTAL && !X86_PAE + prompt "Memory split" + default VMSPLIT_3G + help + Select the desired split between kernel and user memory. + + If the address range available to the kernel is less than the + physical memory installed, the remaining memory will be available + as "high memory". Accessing high memory is a little more costly + than low memory, as it needs to be mapped into the kernel first. + Note that increasing the kernel address space limits the range + available to user programs, making the address space there + tighter. Selecting anything other than the default 3G/1G split + will also likely make your kernel incompatible with binary-only + kernel modules. + + If you are not absolutely sure what you are doing, leave this + option alone! + + config VMSPLIT_3G + bool "3G/1G user/kernel split" + config VMSPLIT_3G_OPT + bool "3G/1G user/kernel split (for full 1G low memory)" + config VMSPLIT_2G + bool "2G/2G user/kernel split" + config VMSPLIT_1G + bool "1G/3G user/kernel split" +endchoice + +config PAGE_OFFSET + hex + default 0xB0000000 if VMSPLIT_3G_OPT + default 0x78000000 if VMSPLIT_2G + default 0x40000000 if VMSPLIT_1G + default 0xC0000000 + config HIGHMEM bool depends on HIGHMEM64G || HIGHMEM4G @@ -711,6 +740,15 @@ config HOTPLUG_CPU Say N. +config DOUBLEFAULT + default y + bool "Enable doublefault exception handler" if EMBEDDED + help + This option allows trapping of rare doublefault exceptions that + would otherwise cause a system to silently reboot. Disabling this + option saves about 4k and might cause you much additional grey + hair. + endmenu diff --git a/arch/i386/kernel/acpi/Makefile b/arch/i386/kernel/acpi/Makefile index 267ca48e1b6c..d51c7313cae8 100644 --- a/arch/i386/kernel/acpi/Makefile +++ b/arch/i386/kernel/acpi/Makefile @@ -3,6 +3,6 @@ obj-$(CONFIG_X86_IO_APIC) += earlyquirk.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o ifneq ($(CONFIG_ACPI_PROCESSOR),) -obj-y += cstate.o +obj-y += cstate.o processor.o endif diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 2111529dea77..79577f0ace98 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -248,10 +248,17 @@ acpi_parse_lapic(acpi_table_entry_header * header, const unsigned long end) acpi_table_print_madt_entry(header); - /* Register even disabled CPUs for cpu hotplug */ - - x86_acpiid_to_apicid[processor->acpi_id] = processor->id; + /* Record local apic id only when enabled */ + if (processor->flags.enabled) + x86_acpiid_to_apicid[processor->acpi_id] = processor->id; + /* + * We need to register disabled CPU as well to permit + * counting disabled CPUs. This allows us to size + * cpus_possible_map more accurately, to permit + * to not preallocating memory for all NR_CPUS + * when we use CPU hotplug. + */ mp_register_lapic(processor->id, /* APIC ID */ processor->flags.enabled); /* Enabled? */ @@ -464,7 +471,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) * success: return IRQ number (>=0) * failure: return < 0 */ -int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low) +int acpi_register_gsi(u32 gsi, int triggering, int polarity) { unsigned int irq; unsigned int plat_gsi = gsi; @@ -476,14 +483,14 @@ int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low) if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) { extern void eisa_set_level_irq(unsigned int irq); - if (edge_level == ACPI_LEVEL_SENSITIVE) + if (triggering == ACPI_LEVEL_SENSITIVE) eisa_set_level_irq(gsi); } #endif #ifdef CONFIG_X86_IO_APIC if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) { - plat_gsi = mp_register_gsi(gsi, edge_level, active_high_low); + plat_gsi = mp_register_gsi(gsi, triggering, polarity); } #endif acpi_gsi_to_irq(plat_gsi, &irq); diff --git a/arch/i386/kernel/acpi/cstate.c b/arch/i386/kernel/acpi/cstate.c index 4c3036ba65df..25db49ef1770 100644 --- a/arch/i386/kernel/acpi/cstate.c +++ b/arch/i386/kernel/acpi/cstate.c @@ -14,64 +14,6 @@ #include #include -static void acpi_processor_power_init_intel_pdc(struct acpi_processor_power - *pow) -{ - struct acpi_object_list *obj_list; - union acpi_object *obj; - u32 *buf; - - /* allocate and initialize pdc. It will be used later. */ - obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL); - if (!obj_list) { - printk(KERN_ERR "Memory allocation error\n"); - return; - } - - obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL); - if (!obj) { - printk(KERN_ERR "Memory allocation error\n"); - kfree(obj_list); - return; - } - - buf = kmalloc(12, GFP_KERNEL); - if (!buf) { - printk(KERN_ERR "Memory allocation error\n"); - kfree(obj); - kfree(obj_list); - return; - } - - buf[0] = ACPI_PDC_REVISION_ID; - buf[1] = 1; - buf[2] = ACPI_PDC_C_CAPABILITY_SMP; - - obj->type = ACPI_TYPE_BUFFER; - obj->buffer.length = 12; - obj->buffer.pointer = (u8 *) buf; - obj_list->count = 1; - obj_list->pointer = obj; - pow->pdc = obj_list; - - return; -} - -/* Initialize _PDC data based on the CPU vendor */ -void acpi_processor_power_init_pdc(struct acpi_processor_power *pow, - unsigned int cpu) -{ - struct cpuinfo_x86 *c = cpu_data + cpu; - - pow->pdc = NULL; - if (c->x86_vendor == X86_VENDOR_INTEL) - acpi_processor_power_init_intel_pdc(pow); - - return; -} - -EXPORT_SYMBOL(acpi_processor_power_init_pdc); - /* * Initialize bm_flags based on the CPU cache properties * On SMP it depends on cache configuration diff --git a/arch/i386/kernel/acpi/processor.c b/arch/i386/kernel/acpi/processor.c new file mode 100644 index 000000000000..9f4cc02717ec --- /dev/null +++ b/arch/i386/kernel/acpi/processor.c @@ -0,0 +1,75 @@ +/* + * arch/i386/kernel/acpi/processor.c + * + * Copyright (C) 2005 Intel Corporation + * Venkatesh Pallipadi + * - Added _PDC for platforms with Intel CPUs + */ + +#include +#include +#include +#include + +#include +#include + +static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c) +{ + struct acpi_object_list *obj_list; + union acpi_object *obj; + u32 *buf; + + /* allocate and initialize pdc. It will be used later. */ + obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL); + if (!obj_list) { + printk(KERN_ERR "Memory allocation error\n"); + return; + } + + obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL); + if (!obj) { + printk(KERN_ERR "Memory allocation error\n"); + kfree(obj_list); + return; + } + + buf = kmalloc(12, GFP_KERNEL); + if (!buf) { + printk(KERN_ERR "Memory allocation error\n"); + kfree(obj); + kfree(obj_list); + return; + } + + buf[0] = ACPI_PDC_REVISION_ID; + buf[1] = 1; + buf[2] = ACPI_PDC_C_CAPABILITY_SMP; + + if (cpu_has(c, X86_FEATURE_EST)) + buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP; + + obj->type = ACPI_TYPE_BUFFER; + obj->buffer.length = 12; + obj->buffer.pointer = (u8 *) buf; + obj_list->count = 1; + obj_list->pointer = obj; + pr->pdc = obj_list; + + return; +} + +/* Initialize _PDC data based on the CPU vendor */ +void arch_acpi_processor_init_pdc(struct acpi_processor *pr) +{ + unsigned int cpu = pr->id; + struct cpuinfo_x86 *c = cpu_data + cpu; + + pr->pdc = NULL; + if (c->x86_vendor == X86_VENDOR_INTEL) + init_intel_pdc(pr, c); + + return; +} + +EXPORT_SYMBOL(arch_acpi_processor_init_pdc); diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index acd3f1e34ca6..98a5c23cf3df 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -75,8 +75,10 @@ void ack_bad_irq(unsigned int irq) * holds up an irq slot - in excessive cases (when multiple * unexpected vectors occur) that might lock up the APIC * completely. + * But only ack when the APIC is enabled -AK */ - ack_APIC_irq(); + if (!cpu_has_apic) + ack_APIC_irq(); } void __init apic_intr_init(void) @@ -1303,6 +1305,7 @@ int __init APIC_init_uniprocessor (void) if (!cpu_has_apic && APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); + clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability); return -1; } diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index 333578a4e91a..0810f81f2a05 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -282,3 +282,11 @@ int __init amd_init_cpu(void) } //early_arch_initcall(amd_init_cpu); + +static int __init amd_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_AMD] = NULL; + return 0; +} + +late_initcall(amd_exit_cpu); diff --git a/arch/i386/kernel/cpu/centaur.c b/arch/i386/kernel/cpu/centaur.c index 394814e57672..f52669ecb93f 100644 --- a/arch/i386/kernel/cpu/centaur.c +++ b/arch/i386/kernel/cpu/centaur.c @@ -405,10 +405,6 @@ static void __init init_centaur(struct cpuinfo_x86 *c) winchip2_protect_mcr(); #endif break; - case 10: - name="4"; - /* no info on the WC4 yet */ - break; default: name="??"; } @@ -474,3 +470,11 @@ int __init centaur_init_cpu(void) } //early_arch_initcall(centaur_init_cpu); + +static int __init centaur_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_CENTAUR] = NULL; + return 0; +} + +late_initcall(centaur_exit_cpu); diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 15aee26ec2b6..7eb9213734a3 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -44,6 +44,7 @@ static void default_init(struct cpuinfo_x86 * c) static struct cpu_dev default_cpu = { .c_init = default_init, + .c_vendor = "Unknown", }; static struct cpu_dev * this_cpu = &default_cpu; @@ -150,6 +151,7 @@ static void __devinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) { char *v = c->x86_vendor_id; int i; + static int printed; for (i = 0; i < X86_VENDOR_NUM; i++) { if (cpu_devs[i]) { @@ -159,10 +161,17 @@ static void __devinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) c->x86_vendor = i; if (!early) this_cpu = cpu_devs[i]; - break; + return; } } } + if (!printed) { + printed++; + printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n"); + printk(KERN_ERR "CPU: Your system may be unstable.\n"); + } + c->x86_vendor = X86_VENDOR_UNKNOWN; + this_cpu = &default_cpu; } diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig index 0f1eb507233b..26892d2099b0 100644 --- a/arch/i386/kernel/cpu/cpufreq/Kconfig +++ b/arch/i386/kernel/cpu/cpufreq/Kconfig @@ -96,6 +96,7 @@ config X86_POWERNOW_K8_ACPI config X86_GX_SUSPMOD tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation" + depends on PCI help This add the CPUFreq driver for NatSemi Geode processors which support suspend modulation. diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index 7975e79d5fa4..3852d0a4c1b5 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -295,68 +295,6 @@ acpi_cpufreq_guess_freq ( } -/* - * acpi_processor_cpu_init_pdc_est - let BIOS know about the SMP capabilities - * of this driver - * @perf: processor-specific acpi_io_data struct - * @cpu: CPU being initialized - * - * To avoid issues with legacy OSes, some BIOSes require to be informed of - * the SMP capabilities of OS P-state driver. Here we set the bits in _PDC - * accordingly, for Enhanced Speedstep. Actual call to _PDC is done in - * driver/acpi/processor.c - */ -static void -acpi_processor_cpu_init_pdc_est( - struct acpi_processor_performance *perf, - unsigned int cpu, - struct acpi_object_list *obj_list - ) -{ - union acpi_object *obj; - u32 *buf; - struct cpuinfo_x86 *c = cpu_data + cpu; - dprintk("acpi_processor_cpu_init_pdc_est\n"); - - if (!cpu_has(c, X86_FEATURE_EST)) - return; - - /* Initialize pdc. It will be used later. */ - if (!obj_list) - return; - - if (!(obj_list->count && obj_list->pointer)) - return; - - obj = obj_list->pointer; - if ((obj->buffer.length == 12) && obj->buffer.pointer) { - buf = (u32 *)obj->buffer.pointer; - buf[0] = ACPI_PDC_REVISION_ID; - buf[1] = 1; - buf[2] = ACPI_PDC_EST_CAPABILITY_SMP; - perf->pdc = obj_list; - } - return; -} - - -/* CPU specific PDC initialization */ -static void -acpi_processor_cpu_init_pdc( - struct acpi_processor_performance *perf, - unsigned int cpu, - struct acpi_object_list *obj_list - ) -{ - struct cpuinfo_x86 *c = cpu_data + cpu; - dprintk("acpi_processor_cpu_init_pdc\n"); - perf->pdc = NULL; - if (cpu_has(c, X86_FEATURE_EST)) - acpi_processor_cpu_init_pdc_est(perf, cpu, obj_list); - return; -} - - static int acpi_cpufreq_cpu_init ( struct cpufreq_policy *policy) @@ -367,14 +305,7 @@ acpi_cpufreq_cpu_init ( unsigned int result = 0; struct cpuinfo_x86 *c = &cpu_data[policy->cpu]; - union acpi_object arg0 = {ACPI_TYPE_BUFFER}; - u32 arg0_buf[3]; - struct acpi_object_list arg_list = {1, &arg0}; - dprintk("acpi_cpufreq_cpu_init\n"); - /* setup arg_list for _PDC settings */ - arg0.buffer.length = 12; - arg0.buffer.pointer = (u8 *) arg0_buf; data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); if (!data) @@ -382,9 +313,7 @@ acpi_cpufreq_cpu_init ( acpi_io_data[cpu] = data; - acpi_processor_cpu_init_pdc(&data->acpi_data, cpu, &arg_list); result = acpi_processor_register_performance(&data->acpi_data, cpu); - data->acpi_data.pdc = NULL; if (result) goto err_free; diff --git a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c index 270f2188d68b..cc73a7ae34bc 100644 --- a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c @@ -52,6 +52,7 @@ enum { static int has_N44_O17_errata[NR_CPUS]; +static int has_N60_errata[NR_CPUS]; static unsigned int stock_freq; static struct cpufreq_driver p4clockmod_driver; static unsigned int cpufreq_p4_get(unsigned int cpu); @@ -226,6 +227,12 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) case 0x0f12: has_N44_O17_errata[policy->cpu] = 1; dprintk("has errata -- disabling low frequencies\n"); + break; + + case 0x0f29: + has_N60_errata[policy->cpu] = 1; + dprintk("has errata -- disabling frequencies lower than 2ghz\n"); + break; } /* get max frequency */ @@ -237,6 +244,8 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) for (i=1; (p4clockmod_table[i].frequency != CPUFREQ_TABLE_END); i++) { if ((i<2) && (has_N44_O17_errata[policy->cpu])) p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID; + else if (has_N60_errata[policy->cpu] && p4clockmod_table[i].frequency < 2000000) + p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID; else p4clockmod_table[i].frequency = (stock_freq * i)/8; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index 9a826cde4fd1..c173c0fa117a 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -362,22 +362,10 @@ static struct acpi_processor_performance p; */ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) { - union acpi_object arg0 = {ACPI_TYPE_BUFFER}; - u32 arg0_buf[3]; - struct acpi_object_list arg_list = {1, &arg0}; unsigned long cur_freq; int result = 0, i; unsigned int cpu = policy->cpu; - /* _PDC settings */ - arg0.buffer.length = 12; - arg0.buffer.pointer = (u8 *) arg0_buf; - arg0_buf[0] = ACPI_PDC_REVISION_ID; - arg0_buf[1] = 1; - arg0_buf[2] = ACPI_PDC_EST_CAPABILITY_SMP_MSR; - - p.pdc = &arg_list; - /* register with ACPI core */ if (acpi_processor_register_performance(&p, cpu)) { dprintk(KERN_INFO PFX "obtaining ACPI data failed\n"); diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c index 75015975d038..00f2e058797c 100644 --- a/arch/i386/kernel/cpu/cyrix.c +++ b/arch/i386/kernel/cpu/cyrix.c @@ -345,7 +345,7 @@ static void __init init_cyrix(struct cpuinfo_x86 *c) /* * Handle National Semiconductor branded processors */ -static void __devinit init_nsc(struct cpuinfo_x86 *c) +static void __init init_nsc(struct cpuinfo_x86 *c) { /* There may be GX1 processors in the wild that are branded * NSC and not Cyrix. @@ -444,6 +444,14 @@ int __init cyrix_init_cpu(void) //early_arch_initcall(cyrix_init_cpu); +static int __init cyrix_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_CYRIX] = NULL; + return 0; +} + +late_initcall(cyrix_exit_cpu); + static struct cpu_dev nsc_cpu_dev __initdata = { .c_vendor = "NSC", .c_ident = { "Geode by NSC" }, @@ -458,3 +466,11 @@ int __init nsc_init_cpu(void) } //early_arch_initcall(nsc_init_cpu); + +static int __init nsc_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_NSC] = NULL; + return 0; +} + +late_initcall(nsc_exit_cpu); diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index fbfd374aa336..ffe58cee0c48 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -43,13 +43,23 @@ static struct _cache_table cache_table[] __cpuinitdata = { 0x2c, LVL_1_DATA, 32 }, /* 8-way set assoc, 64 byte line size */ { 0x30, LVL_1_INST, 32 }, /* 8-way set assoc, 64 byte line size */ { 0x39, LVL_2, 128 }, /* 4-way set assoc, sectored cache, 64 byte line size */ + { 0x3a, LVL_2, 192 }, /* 6-way set assoc, sectored cache, 64 byte line size */ { 0x3b, LVL_2, 128 }, /* 2-way set assoc, sectored cache, 64 byte line size */ { 0x3c, LVL_2, 256 }, /* 4-way set assoc, sectored cache, 64 byte line size */ + { 0x3d, LVL_2, 384 }, /* 6-way set assoc, sectored cache, 64 byte line size */ + { 0x3e, LVL_2, 512 }, /* 4-way set assoc, sectored cache, 64 byte line size */ { 0x41, LVL_2, 128 }, /* 4-way set assoc, 32 byte line size */ { 0x42, LVL_2, 256 }, /* 4-way set assoc, 32 byte line size */ { 0x43, LVL_2, 512 }, /* 4-way set assoc, 32 byte line size */ { 0x44, LVL_2, 1024 }, /* 4-way set assoc, 32 byte line size */ { 0x45, LVL_2, 2048 }, /* 4-way set assoc, 32 byte line size */ + { 0x46, LVL_3, 4096 }, /* 4-way set assoc, 64 byte line size */ + { 0x47, LVL_3, 8192 }, /* 8-way set assoc, 64 byte line size */ + { 0x49, LVL_3, 4096 }, /* 16-way set assoc, 64 byte line size */ + { 0x4a, LVL_3, 6144 }, /* 12-way set assoc, 64 byte line size */ + { 0x4b, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */ + { 0x4c, LVL_3, 12288 }, /* 12-way set assoc, 64 byte line size */ + { 0x4d, LVL_3, 16384 }, /* 16-way set assoc, 64 byte line size */ { 0x60, LVL_1_DATA, 16 }, /* 8-way set assoc, sectored cache, 64 byte line size */ { 0x66, LVL_1_DATA, 8 }, /* 4-way set assoc, sectored cache, 64 byte line size */ { 0x67, LVL_1_DATA, 16 }, /* 4-way set assoc, sectored cache, 64 byte line size */ @@ -57,6 +67,7 @@ static struct _cache_table cache_table[] __cpuinitdata = { 0x70, LVL_TRACE, 12 }, /* 8-way set assoc */ { 0x71, LVL_TRACE, 16 }, /* 8-way set assoc */ { 0x72, LVL_TRACE, 32 }, /* 8-way set assoc */ + { 0x73, LVL_TRACE, 64 }, /* 8-way set assoc */ { 0x78, LVL_2, 1024 }, /* 4-way set assoc, 64 byte line size */ { 0x79, LVL_2, 128 }, /* 8-way set assoc, sectored cache, 64 byte line size */ { 0x7a, LVL_2, 256 }, /* 8-way set assoc, sectored cache, 64 byte line size */ @@ -141,6 +152,7 @@ static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_le return 0; } +/* will only be called once; __init is safe here */ static int __init find_num_cache_leaves(void) { unsigned int eax, ebx, ecx, edx; diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c index 1e9db198c440..3b4618bed70d 100644 --- a/arch/i386/kernel/cpu/mtrr/main.c +++ b/arch/i386/kernel/cpu/mtrr/main.c @@ -44,12 +44,10 @@ #include #include "mtrr.h" -#define MTRR_VERSION "2.0 (20020519)" - u32 num_var_ranges = 0; unsigned int *usage_table; -static DECLARE_MUTEX(main_lock); +static DECLARE_MUTEX(mtrr_sem); u32 size_or_mask, size_and_mask; @@ -335,7 +333,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); /* Search for existing MTRR */ - down(&main_lock); + down(&mtrr_sem); for (i = 0; i < num_var_ranges; ++i) { mtrr_if->get(i, &lbase, &lsize, <ype); if (base >= lbase + lsize) @@ -373,7 +371,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, printk(KERN_INFO "mtrr: no more MTRRs available\n"); error = i; out: - up(&main_lock); + up(&mtrr_sem); unlock_cpu_hotplug(); return error; } @@ -466,7 +464,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) max = num_var_ranges; /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); - down(&main_lock); + down(&mtrr_sem); if (reg < 0) { /* Search for existing MTRR */ for (i = 0; i < max; ++i) { @@ -505,7 +503,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) set_mtrr(reg, 0, 0, 0); error = reg; out: - up(&main_lock); + up(&mtrr_sem); unlock_cpu_hotplug(); return error; } @@ -671,7 +669,6 @@ void __init mtrr_bp_init(void) break; } } - printk(KERN_INFO "mtrr: v%s\n",MTRR_VERSION); if (mtrr_if) { set_num_var_ranges(); @@ -688,7 +685,7 @@ void mtrr_ap_init(void) if (!mtrr_if || !use_intel()) return; /* - * Ideally we should hold main_lock here to avoid mtrr entries changed, + * Ideally we should hold mtrr_sem here to avoid mtrr entries changed, * but this routine will be called in cpu boot time, holding the lock * breaks it. This routine is called in two cases: 1.very earily time * of software resume, when there absolutely isn't mtrr entry changes; diff --git a/arch/i386/kernel/cpu/nexgen.c b/arch/i386/kernel/cpu/nexgen.c index 30898a260a5c..ad87fa58058d 100644 --- a/arch/i386/kernel/cpu/nexgen.c +++ b/arch/i386/kernel/cpu/nexgen.c @@ -61,3 +61,11 @@ int __init nexgen_init_cpu(void) } //early_arch_initcall(nexgen_init_cpu); + +static int __init nexgen_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_NEXGEN] = NULL; + return 0; +} + +late_initcall(nexgen_exit_cpu); diff --git a/arch/i386/kernel/cpu/rise.c b/arch/i386/kernel/cpu/rise.c index 8602425628ca..d08d5a2811c8 100644 --- a/arch/i386/kernel/cpu/rise.c +++ b/arch/i386/kernel/cpu/rise.c @@ -51,3 +51,11 @@ int __init rise_init_cpu(void) } //early_arch_initcall(rise_init_cpu); + +static int __init rise_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_RISE] = NULL; + return 0; +} + +late_initcall(rise_exit_cpu); diff --git a/arch/i386/kernel/cpu/transmeta.c b/arch/i386/kernel/cpu/transmeta.c index fc426380366b..bdbeb77f4e22 100644 --- a/arch/i386/kernel/cpu/transmeta.c +++ b/arch/i386/kernel/cpu/transmeta.c @@ -84,7 +84,7 @@ static void __init init_transmeta(struct cpuinfo_x86 *c) #endif } -static void transmeta_identify(struct cpuinfo_x86 * c) +static void __init transmeta_identify(struct cpuinfo_x86 * c) { u32 xlvl; generic_identify(c); @@ -111,3 +111,11 @@ int __init transmeta_init_cpu(void) } //early_arch_initcall(transmeta_init_cpu); + +static int __init transmeta_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_TRANSMETA] = NULL; + return 0; +} + +late_initcall(transmeta_exit_cpu); diff --git a/arch/i386/kernel/cpu/umc.c b/arch/i386/kernel/cpu/umc.c index 264fcad559d5..2cd988f6dc55 100644 --- a/arch/i386/kernel/cpu/umc.c +++ b/arch/i386/kernel/cpu/umc.c @@ -31,3 +31,11 @@ int __init umc_init_cpu(void) } //early_arch_initcall(umc_init_cpu); + +static int __init umc_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_UMC] = NULL; + return 0; +} + +late_initcall(umc_exit_cpu); diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c index 91a64016956e..0102f3d50e57 100644 --- a/arch/i386/kernel/mpparse.c +++ b/arch/i386/kernel/mpparse.c @@ -1080,7 +1080,7 @@ void __init mp_config_acpi_legacy_irqs (void) #define MAX_GSI_NUM 4096 -int mp_register_gsi (u32 gsi, int edge_level, int active_high_low) +int mp_register_gsi (u32 gsi, int triggering, int polarity) { int ioapic = -1; int ioapic_pin = 0; @@ -1129,7 +1129,7 @@ int mp_register_gsi (u32 gsi, int edge_level, int active_high_low) mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<xss,regs->esp); - printk(" EFLAGS: %08lx %s (%s)\n", - regs->eflags, print_tainted(), system_utsname.release); + printk(" EFLAGS: %08lx %s (%s %.*s)\n", + regs->eflags, print_tainted(), system_utsname.release, + (int)strcspn(system_utsname.version, " "), + system_utsname.version); printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->eax,regs->ebx,regs->ecx,regs->edx); printk("ESI: %08lx EDI: %08lx EBP: %08lx", diff --git a/arch/i386/kernel/timers/timer_tsc.c b/arch/i386/kernel/timers/timer_tsc.c index 47675bbbb316..7c86e3c5f1c1 100644 --- a/arch/i386/kernel/timers/timer_tsc.c +++ b/arch/i386/kernel/timers/timer_tsc.c @@ -45,6 +45,15 @@ static unsigned long last_tsc_high; /* msb 32 bits of Time Stamp Counter */ static unsigned long long monotonic_base; static seqlock_t monotonic_lock = SEQLOCK_UNLOCKED; +/* Avoid compensating for lost ticks before TSCs are synched */ +static int detect_lost_ticks; +static int __init start_lost_tick_compensation(void) +{ + detect_lost_ticks = 1; + return 0; +} +late_initcall(start_lost_tick_compensation); + /* convert from cycles(64bits) => nanoseconds (64bits) * basic equation: * ns = cycles / (freq / ns_per_sec) @@ -196,7 +205,8 @@ static void mark_offset_tsc_hpet(void) /* lost tick compensation */ offset = hpet_readl(HPET_T0_CMP) - hpet_tick; - if (unlikely(((offset - hpet_last) > hpet_tick) && (hpet_last != 0))) { + if (unlikely(((offset - hpet_last) > hpet_tick) && (hpet_last != 0)) + && detect_lost_ticks) { int lost_ticks = (offset - hpet_last) / hpet_tick; jiffies_64 += lost_ticks; } @@ -421,7 +431,7 @@ static void mark_offset_tsc(void) delta += delay_at_last_interrupt; lost = delta/(1000000/HZ); delay = delta%(1000000/HZ); - if (lost >= 2) { + if (lost >= 2 && detect_lost_ticks) { jiffies_64 += lost-1; /* sanity check to ensure we're not always losing ticks */ diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 0aaebf3e1cfa..b814dbdcc91e 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -166,7 +166,8 @@ static void show_trace_log_lvl(struct task_struct *task, stack = (unsigned long*)context->previous_esp; if (!stack) break; - printk(KERN_EMERG " =======================\n"); + printk(log_lvl); + printk(" =======================\n"); } } @@ -239,9 +240,11 @@ void show_registers(struct pt_regs *regs) } print_modules(); printk(KERN_EMERG "CPU: %d\nEIP: %04x:[<%08lx>] %s VLI\n" - "EFLAGS: %08lx (%s) \n", + "EFLAGS: %08lx (%s %.*s) \n", smp_processor_id(), 0xffff & regs->xcs, regs->eip, - print_tainted(), regs->eflags, system_utsname.release); + print_tainted(), regs->eflags, system_utsname.release, + (int)strcspn(system_utsname.version, " "), + system_utsname.version); print_symbol(KERN_EMERG "EIP is at %s\n", regs->eip); printk(KERN_EMERG "eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", regs->eax, regs->ebx, regs->ecx, regs->edx); diff --git a/arch/i386/oprofile/backtrace.c b/arch/i386/oprofile/backtrace.c index 21654be3f73f..acc18138fb22 100644 --- a/arch/i386/oprofile/backtrace.c +++ b/arch/i386/oprofile/backtrace.c @@ -49,7 +49,9 @@ dump_backtrace(struct frame_head * head) * | stack | * --------------- saved regs->ebp value if valid (frame_head address) * . . - * --------------- struct pt_regs stored on stack (struct pt_regs *) + * --------------- saved regs->rsp value if x86_64 + * | | + * --------------- struct pt_regs * stored on stack if 32-bit * | | * . . * | | @@ -57,13 +59,26 @@ dump_backtrace(struct frame_head * head) * | | * | | \/ Lower addresses * - * Thus, &pt_regs <-> stack base restricts the valid(ish) ebp values + * Thus, regs (or regs->rsp for x86_64) <-> stack base restricts the + * valid(ish) ebp values. Note: (1) for x86_64, NMI and several other + * exceptions use special stacks, maintained by the interrupt stack table + * (IST). These stacks are set up in trap_init() in + * arch/x86_64/kernel/traps.c. Thus, for x86_64, regs now does not point + * to the kernel stack; instead, it points to some location on the NMI + * stack. On the other hand, regs->rsp is the stack pointer saved when the + * NMI occurred. (2) For 32-bit, regs->esp is not valid because the + * processor does not save %esp on the kernel stack when interrupts occur + * in the kernel mode. */ #ifdef CONFIG_FRAME_POINTER static int valid_kernel_stack(struct frame_head * head, struct pt_regs * regs) { unsigned long headaddr = (unsigned long)head; +#ifdef CONFIG_X86_64 + unsigned long stack = (unsigned long)regs->rsp; +#else unsigned long stack = (unsigned long)regs; +#endif unsigned long stack_base = (stack & ~(THREAD_SIZE - 1)) + THREAD_SIZE; return headaddr > stack && headaddr < stack_base; diff --git a/arch/i386/pci/irq.c b/arch/i386/pci/irq.c index e715aa930036..3ca59cad05f3 100644 --- a/arch/i386/pci/irq.c +++ b/arch/i386/pci/irq.c @@ -539,6 +539,11 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route case PCI_DEVICE_ID_INTEL_ICH7_30: case PCI_DEVICE_ID_INTEL_ICH7_31: case PCI_DEVICE_ID_INTEL_ESB2_0: + case PCI_DEVICE_ID_INTEL_ICH8_0: + case PCI_DEVICE_ID_INTEL_ICH8_1: + case PCI_DEVICE_ID_INTEL_ICH8_2: + case PCI_DEVICE_ID_INTEL_ICH8_3: + case PCI_DEVICE_ID_INTEL_ICH8_4: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index 4bb4d4b0f73a..0ee8a983708c 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -36,8 +36,7 @@ static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn) while (1) { ++cfg_num; if (cfg_num >= pci_mmcfg_config_num) { - /* Not found - fallback to type 1 */ - return 0; + break; } cfg = &pci_mmcfg_config[cfg_num]; if (cfg->pci_segment_group_number != seg) @@ -46,6 +45,18 @@ static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn) (cfg->end_bus_number >= bus)) return cfg->base_address; } + + /* Handle more broken MCFG tables on Asus etc. + They only contain a single entry for bus 0-0. Assume + this applies to all busses. */ + cfg = &pci_mmcfg_config[0]; + if (pci_mmcfg_config_num == 1 && + cfg->pci_segment_group_number == 0 && + (cfg->start_bus_number | cfg->end_bus_number) == 0) + return cfg->base_address; + + /* Fall back to type 0 */ + return 0; } static inline void pci_exp_set_dev_base(unsigned int base, int bus, int devfn) diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 3945d378bd7e..70dba1f0e2ee 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -52,9 +52,9 @@ #include #include #include +#include #include -#include #include #include #include @@ -86,7 +86,7 @@ * while doing so. */ /* XXX make per-mm: */ -static DECLARE_MUTEX(ia32_mmap_sem); +static DEFINE_MUTEX(ia32_mmap_mutex); asmlinkage long sys32_execve (char __user *name, compat_uptr_t __user *argv, compat_uptr_t __user *envp, @@ -895,11 +895,11 @@ ia32_do_mmap (struct file *file, unsigned long addr, unsigned long len, int prot prot = get_prot32(prot); #if PAGE_SHIFT > IA32_PAGE_SHIFT - down(&ia32_mmap_sem); + mutex_lock(&ia32_mmap_mutex); { addr = emulate_mmap(file, addr, len, prot, flags, offset); } - up(&ia32_mmap_sem); + mutex_unlock(&ia32_mmap_mutex); #else down_write(¤t->mm->mmap_sem); { @@ -1000,11 +1000,9 @@ sys32_munmap (unsigned int start, unsigned int len) if (start >= end) return 0; - down(&ia32_mmap_sem); - { - ret = sys_munmap(start, end - start); - } - up(&ia32_mmap_sem); + mutex_lock(&ia32_mmap_mutex); + ret = sys_munmap(start, end - start); + mutex_unlock(&ia32_mmap_mutex); #endif return ret; } @@ -1056,7 +1054,7 @@ sys32_mprotect (unsigned int start, unsigned int len, int prot) if (retval < 0) return retval; - down(&ia32_mmap_sem); + mutex_lock(&ia32_mmap_mutex); { if (offset_in_page(start)) { /* start address is 4KB aligned but not page aligned. */ @@ -1080,7 +1078,7 @@ sys32_mprotect (unsigned int start, unsigned int len, int prot) retval = sys_mprotect(start, end - start, prot); } out: - up(&ia32_mmap_sem); + mutex_unlock(&ia32_mmap_mutex); return retval; #endif } @@ -1124,11 +1122,9 @@ sys32_mremap (unsigned int addr, unsigned int old_len, unsigned int new_len, old_len = PAGE_ALIGN(old_end) - addr; new_len = PAGE_ALIGN(new_end) - addr; - down(&ia32_mmap_sem); - { - ret = sys_mremap(addr, old_len, new_len, flags, new_addr); - } - up(&ia32_mmap_sem); + mutex_lock(&ia32_mmap_mutex); + ret = sys_mremap(addr, old_len, new_len, flags, new_addr); + mutex_unlock(&ia32_mmap_mutex); if ((ret >= 0) && (old_len < new_len)) { /* mremap expanded successfully */ diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 307514f7a282..09a0dbc17fb6 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -13,6 +13,11 @@ obj-$(CONFIG_IA64_BRL_EMU) += brl_emu.o obj-$(CONFIG_IA64_GENERIC) += acpi-ext.o obj-$(CONFIG_IA64_HP_ZX1) += acpi-ext.o obj-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += acpi-ext.o + +ifneq ($(CONFIG_ACPI_PROCESSOR),) +obj-y += acpi-processor.o +endif + obj-$(CONFIG_IA64_PALINFO) += palinfo.o obj-$(CONFIG_IOSAPIC) += iosapic.o obj-$(CONFIG_MODULES) += module.o diff --git a/arch/ia64/kernel/acpi-ext.c b/arch/ia64/kernel/acpi-ext.c index 13a5b3b49bf8..4a5574ff007b 100644 --- a/arch/ia64/kernel/acpi-ext.c +++ b/arch/ia64/kernel/acpi-ext.c @@ -33,33 +33,33 @@ acpi_vendor_resource_match(struct acpi_resource *resource, void *context) struct acpi_vendor_info *info = (struct acpi_vendor_info *)context; struct acpi_resource_vendor *vendor; struct acpi_vendor_descriptor *descriptor; - u32 length; + u32 byte_length; - if (resource->id != ACPI_RSTYPE_VENDOR) + if (resource->type != ACPI_RESOURCE_TYPE_VENDOR) return AE_OK; vendor = (struct acpi_resource_vendor *)&resource->data; - descriptor = (struct acpi_vendor_descriptor *)vendor->reserved; - if (vendor->length <= sizeof(*info->descriptor) || + descriptor = (struct acpi_vendor_descriptor *)vendor->byte_data; + if (vendor->byte_length <= sizeof(*info->descriptor) || descriptor->guid_id != info->descriptor->guid_id || efi_guidcmp(descriptor->guid, info->descriptor->guid)) return AE_OK; - length = vendor->length - sizeof(struct acpi_vendor_descriptor); - info->data = acpi_os_allocate(length); + byte_length = vendor->byte_length - sizeof(struct acpi_vendor_descriptor); + info->data = acpi_os_allocate(byte_length); if (!info->data) return AE_NO_MEMORY; memcpy(info->data, - vendor->reserved + sizeof(struct acpi_vendor_descriptor), - length); - info->length = length; + vendor->byte_data + sizeof(struct acpi_vendor_descriptor), + byte_length); + info->length = byte_length; return AE_CTRL_TERMINATE; } acpi_status acpi_find_vendor_resource(acpi_handle obj, struct acpi_vendor_descriptor * id, - u8 ** data, u32 * length) + u8 ** data, u32 * byte_length) { struct acpi_vendor_info info; @@ -72,7 +72,7 @@ acpi_find_vendor_resource(acpi_handle obj, struct acpi_vendor_descriptor * id, return AE_NOT_FOUND; *data = info.data; - *length = info.length; + *byte_length = info.length; return AE_OK; } diff --git a/arch/ia64/kernel/acpi-processor.c b/arch/ia64/kernel/acpi-processor.c new file mode 100644 index 000000000000..e683630c8ce2 --- /dev/null +++ b/arch/ia64/kernel/acpi-processor.c @@ -0,0 +1,67 @@ +/* + * arch/ia64/kernel/cpufreq/processor.c + * + * Copyright (C) 2005 Intel Corporation + * Venkatesh Pallipadi + * - Added _PDC for platforms with Intel CPUs + */ + +#include +#include +#include +#include + +#include +#include + +static void init_intel_pdc(struct acpi_processor *pr) +{ + struct acpi_object_list *obj_list; + union acpi_object *obj; + u32 *buf; + + /* allocate and initialize pdc. It will be used later. */ + obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL); + if (!obj_list) { + printk(KERN_ERR "Memory allocation error\n"); + return; + } + + obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL); + if (!obj) { + printk(KERN_ERR "Memory allocation error\n"); + kfree(obj_list); + return; + } + + buf = kmalloc(12, GFP_KERNEL); + if (!buf) { + printk(KERN_ERR "Memory allocation error\n"); + kfree(obj); + kfree(obj_list); + return; + } + + buf[0] = ACPI_PDC_REVISION_ID; + buf[1] = 1; + buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP; + + obj->type = ACPI_TYPE_BUFFER; + obj->buffer.length = 12; + obj->buffer.pointer = (u8 *) buf; + obj_list->count = 1; + obj_list->pointer = obj; + pr->pdc = obj_list; + + return; +} + +/* Initialize _PDC data based on the CPU vendor */ +void arch_acpi_processor_init_pdc(struct acpi_processor *pr) +{ + pr->pdc = NULL; + init_intel_pdc(pr); + return; +} + +EXPORT_SYMBOL(arch_acpi_processor_init_pdc); diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 9ad94ddf6687..d2702c419cf8 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -567,16 +567,16 @@ void __init acpi_numa_arch_fixup(void) * success: return IRQ number (>=0) * failure: return < 0 */ -int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low) +int acpi_register_gsi(u32 gsi, int triggering, int polarity) { if (has_8259 && gsi < 16) return isa_irq_to_vector(gsi); return iosapic_register_intr(gsi, - (active_high_low == + (polarity == ACPI_ACTIVE_HIGH) ? IOSAPIC_POL_HIGH : IOSAPIC_POL_LOW, - (edge_level == + (triggering == ACPI_EDGE_SENSITIVE) ? IOSAPIC_EDGE : IOSAPIC_LEVEL); } diff --git a/arch/ia64/kernel/cpufreq/Makefile b/arch/ia64/kernel/cpufreq/Makefile index f748d34c02f0..4838f2a57c7a 100644 --- a/arch/ia64/kernel/cpufreq/Makefile +++ b/arch/ia64/kernel/cpufreq/Makefile @@ -1 +1,2 @@ obj-$(CONFIG_IA64_ACPI_CPUFREQ) += acpi-cpufreq.o + diff --git a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c index da4d5cf80a48..5a1bf815282d 100644 --- a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c +++ b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c @@ -269,48 +269,6 @@ acpi_cpufreq_verify ( } -/* - * processor_init_pdc - let BIOS know about the SMP capabilities - * of this driver - * @perf: processor-specific acpi_io_data struct - * @cpu: CPU being initialized - * - * To avoid issues with legacy OSes, some BIOSes require to be informed of - * the SMP capabilities of OS P-state driver. Here we set the bits in _PDC - * accordingly. Actual call to _PDC is done in driver/acpi/processor.c - */ -static void -processor_init_pdc ( - struct acpi_processor_performance *perf, - unsigned int cpu, - struct acpi_object_list *obj_list - ) -{ - union acpi_object *obj; - u32 *buf; - - dprintk("processor_init_pdc\n"); - - perf->pdc = NULL; - /* Initialize pdc. It will be used later. */ - if (!obj_list) - return; - - if (!(obj_list->count && obj_list->pointer)) - return; - - obj = obj_list->pointer; - if ((obj->buffer.length == 12) && obj->buffer.pointer) { - buf = (u32 *)obj->buffer.pointer; - buf[0] = ACPI_PDC_REVISION_ID; - buf[1] = 1; - buf[2] = ACPI_PDC_EST_CAPABILITY_SMP; - perf->pdc = obj_list; - } - return; -} - - static int acpi_cpufreq_cpu_init ( struct cpufreq_policy *policy) @@ -320,14 +278,7 @@ acpi_cpufreq_cpu_init ( struct cpufreq_acpi_io *data; unsigned int result = 0; - union acpi_object arg0 = {ACPI_TYPE_BUFFER}; - u32 arg0_buf[3]; - struct acpi_object_list arg_list = {1, &arg0}; - dprintk("acpi_cpufreq_cpu_init\n"); - /* setup arg_list for _PDC settings */ - arg0.buffer.length = 12; - arg0.buffer.pointer = (u8 *) arg0_buf; data = kmalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); if (!data) @@ -337,9 +288,7 @@ acpi_cpufreq_cpu_init ( acpi_io_data[cpu] = data; - processor_init_pdc(&data->acpi_data, cpu, &arg_list); result = acpi_processor_register_performance(&data->acpi_data, cpu); - data->acpi_data.pdc = NULL; if (result) goto err_free; diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S index 403a80a58c13..60a464bfd9e2 100644 --- a/arch/ia64/kernel/mca_asm.S +++ b/arch/ia64/kernel/mca_asm.S @@ -512,7 +512,7 @@ ia64_state_save: st8 [temp1]=r12 // os_status, default is cold boot mov r6=IA64_MCA_SAME_CONTEXT ;; - st8 [temp1]=r6 // context, default is same context + st8 [temp2]=r6 // context, default is same context // Save the pt_regs data that is not in minstate. The previous code // left regs at sos. diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 2ea4b39efffa..9c5194b385da 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -286,7 +287,7 @@ typedef struct pfm_context { unsigned long ctx_ovfl_regs[4]; /* which registers overflowed (notification) */ - struct semaphore ctx_restart_sem; /* use for blocking notification mode */ + struct completion ctx_restart_done; /* use for blocking notification mode */ unsigned long ctx_used_pmds[4]; /* bitmask of PMD used */ unsigned long ctx_all_pmds[4]; /* bitmask of all accessible PMDs */ @@ -1991,7 +1992,7 @@ pfm_close(struct inode *inode, struct file *filp) /* * force task to wake up from MASKED state */ - up(&ctx->ctx_restart_sem); + complete(&ctx->ctx_restart_done); DPRINT(("waking up ctx_state=%d\n", state)); @@ -2706,7 +2707,7 @@ pfm_context_create(pfm_context_t *ctx, void *arg, int count, struct pt_regs *reg /* * init restart semaphore to locked */ - sema_init(&ctx->ctx_restart_sem, 0); + init_completion(&ctx->ctx_restart_done); /* * activation is used in SMP only @@ -3687,7 +3688,7 @@ pfm_restart(pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs) */ if (CTX_OVFL_NOBLOCK(ctx) == 0 && state == PFM_CTX_MASKED) { DPRINT(("unblocking [%d] \n", task->pid)); - up(&ctx->ctx_restart_sem); + complete(&ctx->ctx_restart_done); } else { DPRINT(("[%d] armed exit trap\n", task->pid)); @@ -5089,7 +5090,7 @@ pfm_handle_work(void) * may go through without blocking on SMP systems * if restart has been received already by the time we call down() */ - ret = down_interruptible(&ctx->ctx_restart_sem); + ret = wait_for_completion_interruptible(&ctx->ctx_restart_done); DPRINT(("after block sleeping ret=%d\n", ret)); diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 706b7734e191..6e5eea19fa67 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -71,31 +71,33 @@ static int __init topology_init(void) int i, err = 0; #ifdef CONFIG_NUMA - sysfs_nodes = kmalloc(sizeof(struct node) * MAX_NUMNODES, GFP_KERNEL); + sysfs_nodes = kzalloc(sizeof(struct node) * MAX_NUMNODES, GFP_KERNEL); if (!sysfs_nodes) { err = -ENOMEM; goto out; } - memset(sysfs_nodes, 0, sizeof(struct node) * MAX_NUMNODES); - /* MCD - Do we want to register all ONLINE nodes, or all POSSIBLE nodes? */ - for_each_online_node(i) + /* + * MCD - Do we want to register all ONLINE nodes, or all POSSIBLE nodes? + */ + for_each_online_node(i) { if ((err = register_node(&sysfs_nodes[i], i, 0))) goto out; + } #endif - sysfs_cpus = kmalloc(sizeof(struct ia64_cpu) * NR_CPUS, GFP_KERNEL); + sysfs_cpus = kzalloc(sizeof(struct ia64_cpu) * NR_CPUS, GFP_KERNEL); if (!sysfs_cpus) { err = -ENOMEM; goto out; } - memset(sysfs_cpus, 0, sizeof(struct ia64_cpu) * NR_CPUS); - for_each_present_cpu(i) + for_each_present_cpu(i) { if((err = arch_register_cpu(i))) goto out; + } out: return err; } -__initcall(topology_init); +subsys_initcall(topology_init); diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c index 43b45b65ee5a..f9e0ae936d1a 100644 --- a/arch/ia64/kernel/unaligned.c +++ b/arch/ia64/kernel/unaligned.c @@ -1283,8 +1283,9 @@ within_logging_rate_limit (void) if (jiffies - last_time > 5*HZ) count = 0; - if (++count < 5) { + if (count < 5) { last_time = jiffies; + count++; return 1; } return 0; diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c index b631cf86ed44..fcd2bad0286f 100644 --- a/arch/ia64/kernel/uncached.c +++ b/arch/ia64/kernel/uncached.c @@ -210,6 +210,7 @@ uncached_build_memmap(unsigned long start, unsigned long end, void *arg) dprintk(KERN_ERR "uncached_build_memmap(%lx %lx)\n", start, end); + touch_softlockup_watchdog(); memset((char *)start, 0, length); node = paddr_to_nid(start - __IA64_UNCACHED_OFFSET); diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index d27ecdcb6fca..0b30ca006286 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -193,12 +193,12 @@ add_io_space (struct pci_root_info *info, struct acpi_resource_address64 *addr) goto free_resource; } - min = addr->min_address_range; + min = addr->minimum; max = min + addr->address_length - 1; - if (addr->attribute.io.translation_attribute == ACPI_SPARSE_TRANSLATION) + if (addr->info.io.translation_type == ACPI_SPARSE_TRANSLATION) sparse = 1; - space_nr = new_space(addr->address_translation_offset, sparse); + space_nr = new_space(addr->translation_offset, sparse); if (space_nr == ~0) goto free_name; @@ -285,7 +285,7 @@ static __devinit acpi_status add_window(struct acpi_resource *res, void *data) if (addr.resource_type == ACPI_MEMORY_RANGE) { flags = IORESOURCE_MEM; root = &iomem_resource; - offset = addr.address_translation_offset; + offset = addr.translation_offset; } else if (addr.resource_type == ACPI_IO_RANGE) { flags = IORESOURCE_IO; root = &ioport_resource; @@ -298,7 +298,7 @@ static __devinit acpi_status add_window(struct acpi_resource *res, void *data) window = &info->controller->window[info->controller->windows++]; window->resource.name = info->name; window->resource.flags = flags; - window->resource.start = addr.min_address_range + offset; + window->resource.start = addr.minimum + offset; window->resource.end = window->resource.start + addr.address_length - 1; window->resource.child = NULL; window->offset = offset; diff --git a/arch/ia64/sn/include/xtalk/hubdev.h b/arch/ia64/sn/include/xtalk/hubdev.h index 7c88e9a58516..8182583c762c 100644 --- a/arch/ia64/sn/include/xtalk/hubdev.h +++ b/arch/ia64/sn/include/xtalk/hubdev.h @@ -51,6 +51,15 @@ struct sn_flush_device_kernel { struct sn_flush_device_common *common; }; +/* 01/16/06 This struct is the old PROM/kernel struct and needs to be included + * for older official PROMs to function on the new kernel base. This struct + * will be removed when the next official PROM release occurs. */ + +struct sn_flush_device_war { + struct sn_flush_device_common common; + u32 filler; /* older PROMs expect the default size of a spinlock_t */ +}; + /* * **widget_p - Used as an array[wid_num][device] of sn_flush_device_kernel. */ diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c index 233d55115d33..a4c78152b336 100644 --- a/arch/ia64/sn/kernel/io_init.c +++ b/arch/ia64/sn/kernel/io_init.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -165,8 +166,46 @@ sn_pcidev_info_get(struct pci_dev *dev) return NULL; } +/* Older PROM flush WAR + * + * 01/16/06 -- This war will be in place until a new official PROM is released. + * Additionally note that the struct sn_flush_device_war also has to be + * removed from arch/ia64/sn/include/xtalk/hubdev.h + */ +static u8 war_implemented = 0; + +static s64 sn_device_fixup_war(u64 nasid, u64 widget, int device, + struct sn_flush_device_common *common) +{ + struct sn_flush_device_war *war_list; + struct sn_flush_device_war *dev_entry; + struct ia64_sal_retval isrv = {0,0,0,0}; + + if (!war_implemented) { + printk(KERN_WARNING "PROM version < 4.50 -- implementing old " + "PROM flush WAR\n"); + war_implemented = 1; + } + + war_list = kzalloc(DEV_PER_WIDGET * sizeof(*war_list), GFP_KERNEL); + if (!war_list) + BUG(); + + SAL_CALL_NOLOCK(isrv, SN_SAL_IOIF_GET_WIDGET_DMAFLUSH_LIST, + nasid, widget, __pa(war_list), 0, 0, 0 ,0); + if (isrv.status) + panic("sn_device_fixup_war failed: %s\n", + ia64_sal_strerror(isrv.status)); + + dev_entry = war_list + device; + memcpy(common,dev_entry, sizeof(*common)); + kfree(war_list); + + return isrv.status; +} + /* - * sn_fixup_ionodes() - This routine initializes the HUB data strcuture for + * sn_fixup_ionodes() - This routine initializes the HUB data strcuture for * each node in the system. */ static void sn_fixup_ionodes(void) @@ -242,12 +281,21 @@ static void sn_fixup_ionodes(void) memset(dev_entry->common, 0x0, sizeof(struct sn_flush_device_common)); - status = sal_get_device_dmaflush_list(nasid, - widget, - device, + if (sn_prom_feature_available( + PRF_DEVICE_FLUSH_LIST)) + status = sal_get_device_dmaflush_list( + nasid, + widget, + device, (u64)(dev_entry->common)); - if (status) - BUG(); + else + status = sn_device_fixup_war(nasid, + widget, + device, + dev_entry->common); + if (status != SALRET_OK) + panic("SAL call failed: %s\n", + ia64_sal_strerror(status)); spin_lock_init(&dev_entry->sfdl_flush_lock); } diff --git a/arch/ia64/sn/kernel/mca.c b/arch/ia64/sn/kernel/mca.c index 6546db6abdba..9ab684d1bb55 100644 --- a/arch/ia64/sn/kernel/mca.c +++ b/arch/ia64/sn/kernel/mca.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -27,7 +28,7 @@ void sn_init_cpei_timer(void); /* Printing oemdata from mca uses data that is not passed through SAL, it is * global. Only one user at a time. */ -static DECLARE_MUTEX(sn_oemdata_mutex); +static DEFINE_MUTEX(sn_oemdata_mutex); static u8 **sn_oemdata; static u64 *sn_oemdata_size, sn_oemdata_bufsize; @@ -89,7 +90,7 @@ static int sn_platform_plat_specific_err_print(const u8 * sect_header, u8 ** oemdata, u64 * oemdata_size) { - down(&sn_oemdata_mutex); + mutex_lock(&sn_oemdata_mutex); sn_oemdata = oemdata; sn_oemdata_size = oemdata_size; sn_oemdata_bufsize = 0; @@ -107,7 +108,7 @@ sn_platform_plat_specific_err_print(const u8 * sect_header, u8 ** oemdata, *sn_oemdata_size = 0; ia64_sn_plat_specific_err_print(print_hook, (char *)sect_header); } - up(&sn_oemdata_mutex); + mutex_unlock(&sn_oemdata_mutex); return 0; } diff --git a/arch/ia64/sn/kernel/xp_main.c b/arch/ia64/sn/kernel/xp_main.c index 3be52a34c80f..b7ea46645e12 100644 --- a/arch/ia64/sn/kernel/xp_main.c +++ b/arch/ia64/sn/kernel/xp_main.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -136,13 +137,13 @@ xpc_connect(int ch_number, xpc_channel_func func, void *key, u16 payload_size, registration = &xpc_registrations[ch_number]; - if (down_interruptible(®istration->sema) != 0) { + if (mutex_lock_interruptible(®istration->mutex) != 0) { return xpcInterrupted; } /* if XPC_CHANNEL_REGISTERED(ch_number) */ if (registration->func != NULL) { - up(®istration->sema); + mutex_unlock(®istration->mutex); return xpcAlreadyRegistered; } @@ -154,7 +155,7 @@ xpc_connect(int ch_number, xpc_channel_func func, void *key, u16 payload_size, registration->key = key; registration->func = func; - up(®istration->sema); + mutex_unlock(®istration->mutex); xpc_interface.connect(ch_number); @@ -190,11 +191,11 @@ xpc_disconnect(int ch_number) * figured XPC's users will just turn around and call xpc_disconnect() * again anyways, so we might as well wait, if need be. */ - down(®istration->sema); + mutex_lock(®istration->mutex); /* if !XPC_CHANNEL_REGISTERED(ch_number) */ if (registration->func == NULL) { - up(®istration->sema); + mutex_unlock(®istration->mutex); return; } @@ -208,7 +209,7 @@ xpc_disconnect(int ch_number) xpc_interface.disconnect(ch_number); - up(®istration->sema); + mutex_unlock(®istration->mutex); return; } @@ -250,9 +251,9 @@ xp_init(void) xp_nofault_PIOR_target = SH1_IPI_ACCESS; } - /* initialize the connection registration semaphores */ + /* initialize the connection registration mutex */ for (ch_number = 0; ch_number < XPC_NCHANNELS; ch_number++) { - sema_init(&xpc_registrations[ch_number].sema, 1); /* mutex */ + mutex_init(&xpc_registrations[ch_number].mutex); } return 0; diff --git a/arch/ia64/sn/kernel/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c index 0c0a68902409..36e5437a0fb6 100644 --- a/arch/ia64/sn/kernel/xpc_channel.c +++ b/arch/ia64/sn/kernel/xpc_channel.c @@ -22,6 +22,8 @@ #include #include #include +#include +#include #include #include #include @@ -56,8 +58,8 @@ xpc_initialize_channels(struct xpc_partition *part, partid_t partid) atomic_set(&ch->n_to_notify, 0); spin_lock_init(&ch->lock); - sema_init(&ch->msg_to_pull_sema, 1); /* mutex */ - sema_init(&ch->wdisconnect_sema, 0); /* event wait */ + mutex_init(&ch->msg_to_pull_mutex); + init_completion(&ch->wdisconnect_wait); atomic_set(&ch->n_on_msg_allocate_wq, 0); init_waitqueue_head(&ch->msg_allocate_wq); @@ -445,7 +447,7 @@ xpc_allocate_local_msgqueue(struct xpc_channel *ch) nbytes = nentries * ch->msg_size; ch->local_msgqueue = xpc_kmalloc_cacheline_aligned(nbytes, - (GFP_KERNEL | GFP_DMA), + GFP_KERNEL, &ch->local_msgqueue_base); if (ch->local_msgqueue == NULL) { continue; @@ -453,7 +455,7 @@ xpc_allocate_local_msgqueue(struct xpc_channel *ch) memset(ch->local_msgqueue, 0, nbytes); nbytes = nentries * sizeof(struct xpc_notify); - ch->notify_queue = kmalloc(nbytes, (GFP_KERNEL | GFP_DMA)); + ch->notify_queue = kmalloc(nbytes, GFP_KERNEL); if (ch->notify_queue == NULL) { kfree(ch->local_msgqueue_base); ch->local_msgqueue = NULL; @@ -500,7 +502,7 @@ xpc_allocate_remote_msgqueue(struct xpc_channel *ch) nbytes = nentries * ch->msg_size; ch->remote_msgqueue = xpc_kmalloc_cacheline_aligned(nbytes, - (GFP_KERNEL | GFP_DMA), + GFP_KERNEL, &ch->remote_msgqueue_base); if (ch->remote_msgqueue == NULL) { continue; @@ -534,7 +536,6 @@ static enum xpc_retval xpc_allocate_msgqueues(struct xpc_channel *ch) { unsigned long irq_flags; - int i; enum xpc_retval ret; @@ -552,11 +553,6 @@ xpc_allocate_msgqueues(struct xpc_channel *ch) return ret; } - for (i = 0; i < ch->local_nentries; i++) { - /* use a semaphore as an event wait queue */ - sema_init(&ch->notify_queue[i].sema, 0); - } - spin_lock_irqsave(&ch->lock, irq_flags); ch->flags |= XPC_C_SETUP; spin_unlock_irqrestore(&ch->lock, irq_flags); @@ -799,10 +795,8 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) } if (ch->flags & XPC_C_WDISCONNECT) { - spin_unlock_irqrestore(&ch->lock, *irq_flags); - up(&ch->wdisconnect_sema); - spin_lock_irqsave(&ch->lock, *irq_flags); - + /* we won't lose the CPU since we're holding ch->lock */ + complete(&ch->wdisconnect_wait); } else if (ch->delayed_IPI_flags) { if (part->act_state != XPC_P_DEACTIVATING) { /* time to take action on any delayed IPI flags */ @@ -1092,12 +1086,12 @@ xpc_connect_channel(struct xpc_channel *ch) struct xpc_registration *registration = &xpc_registrations[ch->number]; - if (down_trylock(®istration->sema) != 0) { + if (mutex_trylock(®istration->mutex) == 0) { return xpcRetry; } if (!XPC_CHANNEL_REGISTERED(ch->number)) { - up(®istration->sema); + mutex_unlock(®istration->mutex); return xpcUnregistered; } @@ -1108,7 +1102,7 @@ xpc_connect_channel(struct xpc_channel *ch) if (ch->flags & XPC_C_DISCONNECTING) { spin_unlock_irqrestore(&ch->lock, irq_flags); - up(®istration->sema); + mutex_unlock(®istration->mutex); return ch->reason; } @@ -1140,7 +1134,7 @@ xpc_connect_channel(struct xpc_channel *ch) * channel lock be locked and will unlock and relock * the channel lock as needed. */ - up(®istration->sema); + mutex_unlock(®istration->mutex); XPC_DISCONNECT_CHANNEL(ch, xpcUnequalMsgSizes, &irq_flags); spin_unlock_irqrestore(&ch->lock, irq_flags); @@ -1155,7 +1149,7 @@ xpc_connect_channel(struct xpc_channel *ch) atomic_inc(&xpc_partitions[ch->partid].nchannels_active); } - up(®istration->sema); + mutex_unlock(®istration->mutex); /* initiate the connection */ @@ -2089,7 +2083,7 @@ xpc_pull_remote_msg(struct xpc_channel *ch, s64 get) enum xpc_retval ret; - if (down_interruptible(&ch->msg_to_pull_sema) != 0) { + if (mutex_lock_interruptible(&ch->msg_to_pull_mutex) != 0) { /* we were interrupted by a signal */ return NULL; } @@ -2125,7 +2119,7 @@ xpc_pull_remote_msg(struct xpc_channel *ch, s64 get) XPC_DEACTIVATE_PARTITION(part, ret); - up(&ch->msg_to_pull_sema); + mutex_unlock(&ch->msg_to_pull_mutex); return NULL; } @@ -2134,7 +2128,7 @@ xpc_pull_remote_msg(struct xpc_channel *ch, s64 get) ch->next_msg_to_pull += nmsgs; } - up(&ch->msg_to_pull_sema); + mutex_unlock(&ch->msg_to_pull_mutex); /* return the message we were looking for */ msg_offset = (get % ch->remote_nentries) * ch->msg_size; diff --git a/arch/ia64/sn/kernel/xpc_main.c b/arch/ia64/sn/kernel/xpc_main.c index 8930586e0eb4..c75f8aeefc2b 100644 --- a/arch/ia64/sn/kernel/xpc_main.c +++ b/arch/ia64/sn/kernel/xpc_main.c @@ -55,6 +55,7 @@ #include #include #include +#include #include #include #include @@ -177,10 +178,10 @@ static DECLARE_WAIT_QUEUE_HEAD(xpc_act_IRQ_wq); static unsigned long xpc_hb_check_timeout; /* notification that the xpc_hb_checker thread has exited */ -static DECLARE_MUTEX_LOCKED(xpc_hb_checker_exited); +static DECLARE_COMPLETION(xpc_hb_checker_exited); /* notification that the xpc_discovery thread has exited */ -static DECLARE_MUTEX_LOCKED(xpc_discovery_exited); +static DECLARE_COMPLETION(xpc_discovery_exited); static struct timer_list xpc_hb_timer; @@ -321,7 +322,7 @@ xpc_hb_checker(void *ignore) /* mark this thread as having exited */ - up(&xpc_hb_checker_exited); + complete(&xpc_hb_checker_exited); return 0; } @@ -341,7 +342,7 @@ xpc_initiate_discovery(void *ignore) dev_dbg(xpc_part, "discovery thread is exiting\n"); /* mark this thread as having exited */ - up(&xpc_discovery_exited); + complete(&xpc_discovery_exited); return 0; } @@ -893,7 +894,7 @@ xpc_disconnect_wait(int ch_number) continue; } - (void) down(&ch->wdisconnect_sema); + wait_for_completion(&ch->wdisconnect_wait); spin_lock_irqsave(&ch->lock, irq_flags); DBUG_ON(!(ch->flags & XPC_C_DISCONNECTED)); @@ -946,10 +947,10 @@ xpc_do_exit(enum xpc_retval reason) free_irq(SGI_XPC_ACTIVATE, NULL); /* wait for the discovery thread to exit */ - down(&xpc_discovery_exited); + wait_for_completion(&xpc_discovery_exited); /* wait for the heartbeat checker thread to exit */ - down(&xpc_hb_checker_exited); + wait_for_completion(&xpc_hb_checker_exited); /* sleep for a 1/3 of a second or so */ @@ -1367,7 +1368,7 @@ xpc_init(void) dev_err(xpc_part, "failed while forking discovery thread\n"); /* mark this new thread as a non-starter */ - up(&xpc_discovery_exited); + complete(&xpc_discovery_exited); xpc_do_exit(xpcUnloading); return -EBUSY; diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index 9bf9f23b9a1f..5a36292388eb 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -90,14 +90,14 @@ void *sn_dma_alloc_coherent(struct device *dev, size_t size, */ node = pcibus_to_node(pdev->bus); if (likely(node >=0)) { - struct page *p = alloc_pages_node(node, GFP_ATOMIC, get_order(size)); + struct page *p = alloc_pages_node(node, flags, get_order(size)); if (likely(p)) cpuaddr = page_address(p); else return NULL; } else - cpuaddr = (void *)__get_free_pages(GFP_ATOMIC, get_order(size)); + cpuaddr = (void *)__get_free_pages(flags, get_order(size)); if (unlikely(!cpuaddr)) return NULL; diff --git a/arch/ia64/sn/pci/pcibr/pcibr_provider.c b/arch/ia64/sn/pci/pcibr/pcibr_provider.c index 77a1262751d3..2fac27049bf6 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_provider.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_provider.c @@ -24,13 +24,15 @@ sal_pcibr_slot_enable(struct pcibus_info *soft, int device, void *resp) { struct ia64_sal_retval ret_stuff; u64 busnum; + u64 segment; ret_stuff.status = 0; ret_stuff.v0 = 0; + segment = soft->pbi_buscommon.bs_persist_segment; busnum = soft->pbi_buscommon.bs_persist_busnum; - SAL_CALL_NOLOCK(ret_stuff, (u64) SN_SAL_IOIF_SLOT_ENABLE, (u64) busnum, - (u64) device, (u64) resp, 0, 0, 0, 0); + SAL_CALL_NOLOCK(ret_stuff, (u64) SN_SAL_IOIF_SLOT_ENABLE, segment, + busnum, (u64) device, (u64) resp, 0, 0, 0); return (int)ret_stuff.v0; } @@ -41,14 +43,16 @@ sal_pcibr_slot_disable(struct pcibus_info *soft, int device, int action, { struct ia64_sal_retval ret_stuff; u64 busnum; + u64 segment; ret_stuff.status = 0; ret_stuff.v0 = 0; + segment = soft->pbi_buscommon.bs_persist_segment; busnum = soft->pbi_buscommon.bs_persist_busnum; SAL_CALL_NOLOCK(ret_stuff, (u64) SN_SAL_IOIF_SLOT_DISABLE, - (u64) busnum, (u64) device, (u64) action, - (u64) resp, 0, 0, 0); + segment, busnum, (u64) device, (u64) action, + (u64) resp, 0, 0); return (int)ret_stuff.v0; } diff --git a/arch/mips/kernel/gdb-stub.c b/arch/mips/kernel/gdb-stub.c index 96d18c43dca0..d4f88e0af24c 100644 --- a/arch/mips/kernel/gdb-stub.c +++ b/arch/mips/kernel/gdb-stub.c @@ -178,7 +178,7 @@ int kgdb_enabled; */ static DEFINE_SPINLOCK(kgdb_lock); static raw_spinlock_t kgdb_cpulock[NR_CPUS] = { - [0 ... NR_CPUS-1] = __RAW_SPIN_LOCK_UNLOCKED; + [0 ... NR_CPUS-1] = __RAW_SPIN_LOCK_UNLOCKED, }; /* diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index e77a06e9621e..7c914a4c67c3 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -149,14 +149,20 @@ config HOTPLUG_CPU default y if SMP select HOTPLUG +config ARCH_SELECT_MEMORY_MODEL + def_bool y + depends on 64BIT + config ARCH_DISCONTIGMEM_ENABLE - bool "Discontiguous memory support (EXPERIMENTAL)" - depends on 64BIT && EXPERIMENTAL - help - Say Y to support efficient handling of discontiguous physical memory, - for architectures which are either NUMA (Non-Uniform Memory Access) - or have huge holes in the physical address space for other reasons. - See for more. + def_bool y + depends on 64BIT + +config ARCH_FLATMEM_ENABLE + def_bool y + +config ARCH_DISCONTIGMEM_DEFAULT + def_bool y + depends on ARCH_DISCONTIGMEM_ENABLE source "kernel/Kconfig.hz" source "mm/Kconfig" diff --git a/arch/parisc/Kconfig.debug b/arch/parisc/Kconfig.debug index 8caaed187a1f..9166bd117267 100644 --- a/arch/parisc/Kconfig.debug +++ b/arch/parisc/Kconfig.debug @@ -11,4 +11,14 @@ config DEBUG_RWLOCK too many attempts. If you suspect a rwlock problem or a kernel hacker asks for this option then say Y. Otherwise say N. +config DEBUG_RODATA + bool "Write protect kernel read-only data structures" + depends on DEBUG_KERNEL + help + Mark the kernel read-only data as write-protected in the pagetables, + in order to catch accidental (and incorrect) writes to such const + data. This option may have a slight performance impact because a + portion of the kernel code won't be covered by a TLB anymore. + If in doubt, say "N". + endmenu diff --git a/arch/parisc/configs/b180_defconfig b/arch/parisc/configs/b180_defconfig index 8819e7e6ae3f..37e98241ce4b 100644 --- a/arch/parisc/configs/b180_defconfig +++ b/arch/parisc/configs/b180_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.14-rc5-pa1 -# Fri Oct 21 23:06:10 2005 +# Linux kernel version: 2.6.16-rc1-pa0 +# Tue Jan 17 08:21:01 2006 # CONFIG_PARISC=y CONFIG_MMU=y @@ -29,8 +29,6 @@ CONFIG_SYSVIPC=y # CONFIG_BSD_PROCESS_ACCT is not set CONFIG_SYSCTL=y # CONFIG_AUDIT is not set -# CONFIG_HOTPLUG is not set -CONFIG_KOBJECT_UEVENT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_INITRAMFS_SOURCE="" @@ -38,8 +36,10 @@ CONFIG_INITRAMFS_SOURCE="" CONFIG_KALLSYMS=y # CONFIG_KALLSYMS_ALL is not set # CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y +CONFIG_ELF_CORE=y CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y @@ -48,8 +48,10 @@ CONFIG_CC_ALIGN_FUNCTIONS=0 CONFIG_CC_ALIGN_LABELS=0 CONFIG_CC_ALIGN_LOOPS=0 CONFIG_CC_ALIGN_JUMPS=0 +CONFIG_SLAB=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 +# CONFIG_SLOB is not set # # Loadable module support @@ -57,9 +59,27 @@ CONFIG_BASE_SMALL=0 CONFIG_MODULES=y # CONFIG_MODULE_UNLOAD is not set CONFIG_OBSOLETE_MODPARM=y +CONFIG_MODVERSIONS=y # CONFIG_MODULE_SRCVERSION_ALL is not set # CONFIG_KMOD is not set +# +# Block layer +# + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +# CONFIG_DEFAULT_AS is not set +# CONFIG_DEFAULT_DEADLINE is not set +CONFIG_DEFAULT_CFQ=y +# CONFIG_DEFAULT_NOOP is not set +CONFIG_DEFAULT_IOSCHED="cfq" + # # Processor type and features # @@ -77,6 +97,7 @@ CONFIG_HZ=250 CONFIG_FLATMEM=y CONFIG_FLAT_NODE_MEM_MAP=y # CONFIG_SPARSEMEM_STATIC is not set +CONFIG_SPLIT_PTLOCK_CPUS=4096 # CONFIG_PREEMPT is not set # CONFIG_HPUX is not set @@ -84,8 +105,8 @@ CONFIG_FLAT_NODE_MEM_MAP=y # Bus options (PCI, PCMCIA, EISA, GSC, ISA) # CONFIG_GSC=y -# CONFIG_HPPB is not set -# CONFIG_IOMMU_CCIO is not set +CONFIG_HPPB=y +CONFIG_IOMMU_CCIO=y CONFIG_GSC_LASI=y CONFIG_GSC_WAX=y CONFIG_EISA=y @@ -165,8 +186,11 @@ CONFIG_IPV6=y # CONFIG_LLC2 is not set # CONFIG_IPX is not set # CONFIG_ATALK is not set + +# +# QoS and/or fair queueing +# # CONFIG_NET_SCHED is not set -# CONFIG_NET_CLS_ROUTE is not set # # Network testing @@ -205,6 +229,7 @@ CONFIG_STANDALONE=y CONFIG_PARPORT=y CONFIG_PARPORT_PC=y # CONFIG_PARPORT_SERIAL is not set +CONFIG_PARPORT_NOT_PC=y CONFIG_PARPORT_GSC=y # CONFIG_PARPORT_1284 is not set @@ -230,14 +255,6 @@ CONFIG_BLK_DEV_RAM_COUNT=16 CONFIG_CDROM_PKTCDVD=m CONFIG_CDROM_PKTCDVD_BUFFERS=8 # CONFIG_CDROM_PKTCDVD_WCACHE is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y CONFIG_ATA_OVER_ETH=y # @@ -281,6 +298,7 @@ CONFIG_SCSI_SPI_ATTRS=y # # SCSI low-level drivers # +# CONFIG_ISCSI_TCP is not set # CONFIG_BLK_DEV_3W_XXXX_RAID is not set # CONFIG_SCSI_3W_9XXX is not set # CONFIG_SCSI_ACARD is not set @@ -313,21 +331,19 @@ CONFIG_SCSI_SYM53C8XX_2=y CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16 CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64 -# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set +CONFIG_SCSI_SYM53C8XX_MMIO=y # CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_ZALON is not set +CONFIG_SCSI_ZALON=y +CONFIG_SCSI_NCR53C8XX_DEFAULT_TAGS=8 +CONFIG_SCSI_NCR53C8XX_MAX_TAGS=32 +CONFIG_SCSI_NCR53C8XX_SYNC=40 +# CONFIG_SCSI_NCR53C8XX_PROFILE is not set # CONFIG_SCSI_PAS16 is not set # CONFIG_SCSI_PSI240I is not set # CONFIG_SCSI_QLOGIC_FAS is not set # CONFIG_SCSI_QLOGIC_FC is not set # CONFIG_SCSI_QLOGIC_1280 is not set -CONFIG_SCSI_QLA2XXX=y -# CONFIG_SCSI_QLA21XX is not set -# CONFIG_SCSI_QLA22XX is not set -# CONFIG_SCSI_QLA2300 is not set -# CONFIG_SCSI_QLA2322 is not set -# CONFIG_SCSI_QLA6312 is not set -# CONFIG_SCSI_QLA24XX is not set +# CONFIG_SCSI_QLA_FC is not set # CONFIG_SCSI_LPFC is not set # CONFIG_SCSI_SIM710 is not set # CONFIG_SCSI_SYM53C416 is not set @@ -397,7 +413,7 @@ CONFIG_NETDEVICES=y # CONFIG_NET_ETHERNET=y # CONFIG_MII is not set -# CONFIG_LASI_82596 is not set +CONFIG_LASI_82596=y # CONFIG_HAPPYMEAL is not set # CONFIG_SUNGEM is not set # CONFIG_CASSINI is not set @@ -464,6 +480,7 @@ CONFIG_NET_RADIO=y # Wireless 802.11b ISA/PCI cards support # # CONFIG_HERMES is not set +# CONFIG_ATMEL is not set # # Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support @@ -527,7 +544,7 @@ CONFIG_KEYBOARD_ATKBD_HP_KEYCODES=y # CONFIG_KEYBOARD_XTKBD is not set # CONFIG_KEYBOARD_NEWTON is not set # CONFIG_KEYBOARD_HIL_OLD is not set -# CONFIG_KEYBOARD_HIL is not set +CONFIG_KEYBOARD_HIL=y CONFIG_INPUT_MOUSE=y CONFIG_MOUSE_PS2=y # CONFIG_MOUSE_SERIAL is not set @@ -535,7 +552,7 @@ CONFIG_MOUSE_PS2=y # CONFIG_MOUSE_LOGIBM is not set # CONFIG_MOUSE_PC110PAD is not set # CONFIG_MOUSE_VSXXXAA is not set -# CONFIG_MOUSE_HIL is not set +CONFIG_MOUSE_HIL=y # CONFIG_INPUT_JOYSTICK is not set # CONFIG_INPUT_TOUCHSCREEN is not set CONFIG_INPUT_MISC=y @@ -549,7 +566,8 @@ CONFIG_SERIO=y # CONFIG_SERIO_SERPORT is not set # CONFIG_SERIO_PARKBD is not set CONFIG_SERIO_GSCPS2=y -# CONFIG_HP_SDC is not set +CONFIG_HP_SDC=y +CONFIG_HIL_MLC=y # CONFIG_SERIO_PCIPS2 is not set CONFIG_SERIO_LIBPS2=y # CONFIG_SERIO_RAW is not set @@ -569,6 +587,7 @@ CONFIG_HW_CONSOLE=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=13 +CONFIG_SERIAL_8250_RUNTIME_UARTS=4 CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_SHARE_IRQ=y @@ -582,11 +601,10 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y # # Non-8250 serial port support # -# CONFIG_SERIAL_MUX is not set -# CONFIG_PDC_CONSOLE is not set +CONFIG_SERIAL_MUX=y +CONFIG_SERIAL_MUX_CONSOLE=y CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y -# CONFIG_SERIAL_JSM is not set CONFIG_UNIX98_PTYS=y CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 @@ -625,6 +643,12 @@ CONFIG_GEN_RTC=y # # CONFIG_I2C is not set +# +# SPI support +# +# CONFIG_SPI is not set +# CONFIG_SPI_MASTER is not set + # # Dallas's 1-wire bus # @@ -661,7 +685,6 @@ CONFIG_FB=y CONFIG_FB_CFB_FILLRECT=y CONFIG_FB_CFB_COPYAREA=y CONFIG_FB_CFB_IMAGEBLIT=y -CONFIG_FB_SOFT_CURSOR=y # CONFIG_FB_MACMODES is not set # CONFIG_FB_MODE_HELPERS is not set # CONFIG_FB_TILEBLITTING is not set @@ -671,6 +694,7 @@ CONFIG_FB_SOFT_CURSOR=y # CONFIG_FB_ASILIANT is not set # CONFIG_FB_IMSTT is not set CONFIG_FB_STI=y +# CONFIG_FB_S1D13XXX is not set # CONFIG_FB_NVIDIA is not set # CONFIG_FB_RIVA is not set # CONFIG_FB_MATROX is not set @@ -683,9 +707,7 @@ CONFIG_FB_STI=y # CONFIG_FB_KYRO is not set # CONFIG_FB_3DFX is not set # CONFIG_FB_VOODOO1 is not set -# CONFIG_FB_CYBLA is not set # CONFIG_FB_TRIDENT is not set -# CONFIG_FB_S1D13XXX is not set # CONFIG_FB_VIRTUAL is not set # @@ -695,6 +717,7 @@ CONFIG_DUMMY_CONSOLE=y CONFIG_DUMMY_CONSOLE_COLUMNS=160 CONFIG_DUMMY_CONSOLE_ROWS=64 CONFIG_FRAMEBUFFER_CONSOLE=y +# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set CONFIG_STI_CONSOLE=y # CONFIG_FONTS is not set CONFIG_FONT_8x8=y @@ -713,7 +736,85 @@ CONFIG_LOGO_PARISC_CLUT224=y # # Sound # -# CONFIG_SOUND is not set +CONFIG_SOUND=y + +# +# Advanced Linux Sound Architecture +# +CONFIG_SND=y +CONFIG_SND_TIMER=y +CONFIG_SND_PCM=y +CONFIG_SND_SEQUENCER=y +# CONFIG_SND_SEQ_DUMMY is not set +CONFIG_SND_OSSEMUL=y +CONFIG_SND_MIXER_OSS=y +CONFIG_SND_PCM_OSS=y +CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_SUPPORT_OLD_API=y +# CONFIG_SND_VERBOSE_PRINTK is not set +# CONFIG_SND_DEBUG is not set + +# +# Generic devices +# +# CONFIG_SND_DUMMY is not set +# CONFIG_SND_VIRMIDI is not set +# CONFIG_SND_MTPAV is not set +# CONFIG_SND_SERIAL_U16550 is not set +# CONFIG_SND_MPU401 is not set + +# +# PCI devices +# +# CONFIG_SND_AD1889 is not set +# CONFIG_SND_ALI5451 is not set +# CONFIG_SND_ATIIXP is not set +# CONFIG_SND_ATIIXP_MODEM is not set +# CONFIG_SND_AU8810 is not set +# CONFIG_SND_AU8820 is not set +# CONFIG_SND_AU8830 is not set +# CONFIG_SND_BT87X is not set +# CONFIG_SND_CA0106 is not set +# CONFIG_SND_CMIPCI is not set +# CONFIG_SND_CS4281 is not set +# CONFIG_SND_CS46XX is not set +# CONFIG_SND_EMU10K1 is not set +# CONFIG_SND_EMU10K1X is not set +# CONFIG_SND_ENS1370 is not set +# CONFIG_SND_ENS1371 is not set +# CONFIG_SND_ES1938 is not set +# CONFIG_SND_ES1968 is not set +# CONFIG_SND_FM801 is not set +# CONFIG_SND_HDA_INTEL is not set +# CONFIG_SND_HDSP is not set +# CONFIG_SND_HDSPM is not set +# CONFIG_SND_ICE1712 is not set +# CONFIG_SND_ICE1724 is not set +# CONFIG_SND_INTEL8X0 is not set +# CONFIG_SND_KORG1212 is not set +# CONFIG_SND_MAESTRO3 is not set +# CONFIG_SND_MIXART is not set +# CONFIG_SND_NM256 is not set +# CONFIG_SND_PCXHR is not set +# CONFIG_SND_RME32 is not set +# CONFIG_SND_RME96 is not set +# CONFIG_SND_RME9652 is not set +# CONFIG_SND_SONICVIBES is not set +# CONFIG_SND_TRIDENT is not set +# CONFIG_SND_VIA82XX is not set +# CONFIG_SND_VIA82XX_MODEM is not set +# CONFIG_SND_VX222 is not set +# CONFIG_SND_YMFPCI is not set + +# +# GSC devices +# +CONFIG_SND_HARMONY=y + +# +# Open Sound System +# +# CONFIG_SOUND_PRIME is not set # # USB support @@ -722,6 +823,10 @@ CONFIG_USB_ARCH_HAS_HCD=y CONFIG_USB_ARCH_HAS_OHCI=y # CONFIG_USB is not set +# +# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' +# + # # USB Gadget Support # @@ -877,18 +982,23 @@ CONFIG_NLS_DEFAULT="iso8859-1" # Kernel hacking # # CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y CONFIG_LOG_BUF_SHIFT=16 CONFIG_DETECT_SOFTLOCKUP=y # CONFIG_SCHEDSTATS is not set # CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_MUTEXES is not set # CONFIG_DEBUG_SPINLOCK is not set # CONFIG_DEBUG_SPINLOCK_SLEEP is not set # CONFIG_DEBUG_KOBJECT is not set # CONFIG_DEBUG_INFO is not set # CONFIG_DEBUG_IOREMAP is not set # CONFIG_DEBUG_FS is not set +# CONFIG_DEBUG_VM is not set +CONFIG_FORCED_INLINING=y +# CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_DEBUG_RODATA is not set # # Security options diff --git a/arch/parisc/hpux/entry_hpux.S b/arch/parisc/hpux/entry_hpux.S index fa9bf38787e7..31c8cccfba31 100644 --- a/arch/parisc/hpux/entry_hpux.S +++ b/arch/parisc/hpux/entry_hpux.S @@ -22,10 +22,9 @@ #include #include - .text - #define ENTRY_NAME(_name_) .word _name_ + .section .rodata,"a" .align 4 .export hpux_call_table .import hpux_unimplemented_wrapper diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 2d804e2d16d1..3d569a485a1a 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -408,11 +408,10 @@ static void setup_bus_id(struct parisc_device *padev) struct parisc_device * create_tree_node(char id, struct device *parent) { - struct parisc_device *dev = kmalloc(sizeof(*dev), GFP_KERNEL); + struct parisc_device *dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return NULL; - memset(dev, 0, sizeof(*dev)); dev->hw_path = id; dev->id.hw_type = HPHW_FAULTY; diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index f40a777dd388..1d00c365f2b1 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -48,9 +48,6 @@ EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(strpbrk); -#include -EXPORT_SYMBOL(pm_power_off); - #include EXPORT_SYMBOL(__xchg8); EXPORT_SYMBOL(__xchg32); diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c index 88cba49c5301..79c7db2705fd 100644 --- a/arch/parisc/kernel/pci.c +++ b/arch/parisc/kernel/pci.c @@ -47,18 +47,17 @@ * this makes the boot time much longer than necessary. * 20ms seems to work for all the HP PCI implementations to date. * - * XXX: turn into a #defined constant in ? + * #define pci_post_reset_delay 50 */ -int pci_post_reset_delay = 50; -struct pci_port_ops *pci_port; -struct pci_bios_ops *pci_bios; +struct pci_port_ops *pci_port __read_mostly; +struct pci_bios_ops *pci_bios __read_mostly; -int pci_hba_count = 0; +static int pci_hba_count __read_mostly; /* parisc_pci_hba used by pci_port->in/out() ops to lookup bus data. */ #define PCI_HBA_MAX 32 -struct pci_hba_data *parisc_pci_hba[PCI_HBA_MAX]; +static struct pci_hba_data *parisc_pci_hba[PCI_HBA_MAX] __read_mostly; /******************************************************************** @@ -259,8 +258,10 @@ void __devinit pcibios_resource_to_bus(struct pci_dev *dev, void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, struct pci_bus_region *region) { +#ifdef CONFIG_64BIT struct pci_bus *bus = dev->bus; struct pci_hba_data *hba = HBA_DATA(bus->bridge->platform_data); +#endif if (res->flags & IORESOURCE_MEM) { res->start = PCI_HOST_ADDR(hba, region->start); diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c index 11d406cd0b3e..53f861c82f93 100644 --- a/arch/parisc/kernel/perf.c +++ b/arch/parisc/kernel/perf.c @@ -68,20 +68,20 @@ struct rdr_tbl_ent { }; static int perf_processor_interface __read_mostly = UNKNOWN_INTF; -static int perf_enabled __read_mostly = 0; +static int perf_enabled __read_mostly; static spinlock_t perf_lock; -struct parisc_device *cpu_device __read_mostly = NULL; +struct parisc_device *cpu_device __read_mostly; /* RDRs to write for PCX-W */ -static int perf_rdrs_W[] = +static const int perf_rdrs_W[] = { 0, 1, 4, 5, 6, 15, 16, 17, 18, 20, 21, 22, 23, 24, 25, -1 }; /* RDRs to write for PCX-U */ -static int perf_rdrs_U[] = +static const int perf_rdrs_U[] = { 0, 1, 4, 5, 6, 7, 16, 17, 18, 20, 21, 22, 23, 24, 25, -1 }; /* RDR register descriptions for PCX-W */ -static struct rdr_tbl_ent perf_rdr_tbl_W[] = { +static const struct rdr_tbl_ent perf_rdr_tbl_W[] = { { 19, 1, 8 }, /* RDR 0 */ { 16, 1, 16 }, /* RDR 1 */ { 72, 2, 0 }, /* RDR 2 */ @@ -117,7 +117,7 @@ static struct rdr_tbl_ent perf_rdr_tbl_W[] = { }; /* RDR register descriptions for PCX-U */ -static struct rdr_tbl_ent perf_rdr_tbl_U[] = { +static const struct rdr_tbl_ent perf_rdr_tbl_U[] = { { 19, 1, 8 }, /* RDR 0 */ { 32, 1, 16 }, /* RDR 1 */ { 20, 1, 0 }, /* RDR 2 */ @@ -156,7 +156,7 @@ static struct rdr_tbl_ent perf_rdr_tbl_U[] = { * A non-zero write_control in the above tables is a byte offset into * this array. */ -static uint64_t perf_bitmasks[] = { +static const uint64_t perf_bitmasks[] = { 0x0000000000000000ul, /* first dbl word must be zero */ 0xfdffe00000000000ul, /* RDR0 bitmask */ 0x003f000000000000ul, /* RDR1 bitmask */ @@ -173,7 +173,7 @@ static uint64_t perf_bitmasks[] = { * Write control bitmasks for Pa-8700 processor given * somethings have changed slightly. */ -static uint64_t perf_bitmasks_piranha[] = { +static const uint64_t perf_bitmasks_piranha[] = { 0x0000000000000000ul, /* first dbl word must be zero */ 0xfdffe00000000000ul, /* RDR0 bitmask */ 0x003f000000000000ul, /* RDR1 bitmask */ @@ -186,7 +186,7 @@ static uint64_t perf_bitmasks_piranha[] = { 0xfffc000000000000ul }; -static uint64_t *bitmask_array; /* array of bitmasks to use */ +static const uint64_t *bitmask_array; /* array of bitmasks to use */ /****************************************************************************** * Function Prototypes @@ -200,7 +200,7 @@ static ssize_t perf_write(struct file *file, const char __user *buf, size_t coun static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg); static void perf_start_counters(void); static int perf_stop_counters(uint32_t *raddr); -static struct rdr_tbl_ent * perf_rdr_get_entry(uint32_t rdr_num); +static const struct rdr_tbl_ent * perf_rdr_get_entry(uint32_t rdr_num); static int perf_rdr_read_ubuf(uint32_t rdr_num, uint64_t *buffer); static int perf_rdr_clear(uint32_t rdr_num); static int perf_write_image(uint64_t *memaddr); @@ -444,7 +444,6 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) uint32_t raddr[4]; int error = 0; - lock_kernel(); switch (cmd) { case PA_PERF_ON: @@ -477,8 +476,6 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) error = -ENOTTY; } - unlock_kernel(); - return error; } @@ -655,7 +652,7 @@ static int perf_stop_counters(uint32_t *raddr) * Retrieve a pointer to the description of what this * RDR contains. */ -static struct rdr_tbl_ent * perf_rdr_get_entry(uint32_t rdr_num) +static const struct rdr_tbl_ent * perf_rdr_get_entry(uint32_t rdr_num) { if (perf_processor_interface == ONYX_INTF) { return &perf_rdr_tbl_U[rdr_num]; @@ -673,7 +670,7 @@ static int perf_rdr_read_ubuf(uint32_t rdr_num, uint64_t *buffer) { uint64_t data, data_mask = 0; uint32_t width, xbits, i; - struct rdr_tbl_ent *tentry; + const struct rdr_tbl_ent *tentry; tentry = perf_rdr_get_entry(rdr_num); if ((width = tentry->width) == 0) @@ -721,7 +718,7 @@ static int perf_rdr_read_ubuf(uint32_t rdr_num, uint64_t *buffer) */ static int perf_rdr_clear(uint32_t rdr_num) { - struct rdr_tbl_ent *tentry; + const struct rdr_tbl_ent *tentry; int32_t i; tentry = perf_rdr_get_entry(rdr_num); @@ -753,10 +750,11 @@ static int perf_write_image(uint64_t *memaddr) uint64_t buffer[MAX_RDR_WORDS]; uint64_t *bptr; uint32_t dwords; - uint32_t *intrigue_rdr; - uint64_t *intrigue_bitmask, tmp64; + const uint32_t *intrigue_rdr; + const uint64_t *intrigue_bitmask; + uint64_t tmp64; void __iomem *runway; - struct rdr_tbl_ent *tentry; + const struct rdr_tbl_ent *tentry; int i; /* Clear out counters */ @@ -830,7 +828,7 @@ static int perf_write_image(uint64_t *memaddr) */ static void perf_rdr_write(uint32_t rdr_num, uint64_t *buffer) { - struct rdr_tbl_ent *tentry; + const struct rdr_tbl_ent *tentry; int32_t i; printk("perf_rdr_write\n"); diff --git a/arch/parisc/kernel/perf_images.h b/arch/parisc/kernel/perf_images.h index d9562fe3f75c..7fef9644df47 100644 --- a/arch/parisc/kernel/perf_images.h +++ b/arch/parisc/kernel/perf_images.h @@ -25,7 +25,7 @@ #define PCXU_IMAGE_SIZE 584 -static uint32_t onyx_images[][PCXU_IMAGE_SIZE/sizeof(uint32_t)] = { +static uint32_t onyx_images[][PCXU_IMAGE_SIZE/sizeof(uint32_t)] __read_mostly = { /* * CPI: * @@ -2093,7 +2093,7 @@ static uint32_t onyx_images[][PCXU_IMAGE_SIZE/sizeof(uint32_t)] = { }; #define PCXW_IMAGE_SIZE 576 -static uint32_t cuda_images[][PCXW_IMAGE_SIZE/sizeof(uint32_t)] = { +static uint32_t cuda_images[][PCXW_IMAGE_SIZE/sizeof(uint32_t)] __read_mostly = { /* * CPI: FROM CPI.IDF (Image 0) * diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 5da41677e70b..e8dea4177113 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -54,27 +54,6 @@ #include #include -static int hlt_counter __read_mostly; - -/* - * Power off function, if any - */ -void (*pm_power_off)(void); - -void disable_hlt(void) -{ - hlt_counter++; -} - -EXPORT_SYMBOL(disable_hlt); - -void enable_hlt(void) -{ - hlt_counter--; -} - -EXPORT_SYMBOL(enable_hlt); - void default_idle(void) { barrier(); @@ -102,12 +81,7 @@ void cpu_idle(void) } -#ifdef __LP64__ -#define COMMAND_GLOBAL 0xfffffffffffe0030UL -#else -#define COMMAND_GLOBAL 0xfffe0030 -#endif - +#define COMMAND_GLOBAL F_EXTEND(0xfffe0030) #define CMD_RESET 5 /* reset any module */ /* @@ -162,6 +136,7 @@ void machine_halt(void) */ } +void (*chassis_power_off)(void); /* * This routine is called from sys_reboot to actually turn off the @@ -170,8 +145,8 @@ void machine_halt(void) void machine_power_off(void) { /* If there is a registered power off handler, call it. */ - if(pm_power_off) - pm_power_off(); + if (chassis_power_off) + chassis_power_off(); /* Put the soft power button back under hardware control. * If the user had already pressed the power button, the @@ -187,6 +162,8 @@ void machine_power_off(void) KERN_EMERG "Please power this system off now."); } +void (*pm_power_off)(void) = machine_power_off; +EXPORT_SYMBOL(pm_power_off); /* * Create a kernel thread diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 27160e8bf15b..413292f1a4a3 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -91,7 +91,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) int copied; #ifdef __LP64__ - if (is_compat_task(child)) { + if (personality(child->personality) == PER_LINUX32) { unsigned int tmp; addr &= 0xffffffffL; @@ -123,7 +123,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) case PTRACE_POKEDATA: ret = 0; #ifdef __LP64__ - if (is_compat_task(child)) { + if (personality(child->personality) == PER_LINUX32) { unsigned int tmp = (unsigned int)data; DBG("sys_ptrace(POKE%s, %d, %lx, %lx)\n", request == PTRACE_POKETEXT ? "TEXT" : "DATA", @@ -146,7 +146,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) case PTRACE_PEEKUSR: { ret = -EIO; #ifdef __LP64__ - if (is_compat_task(child)) { + if (personality(child->personality) == PER_LINUX32) { unsigned int tmp; if (addr & (sizeof(int)-1)) @@ -205,7 +205,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) goto out_tsk; } #ifdef __LP64__ - if (is_compat_task(child)) { + if (personality(child->personality) == PER_LINUX32) { if (addr & (sizeof(int)-1)) goto out_tsk; if ((addr = translate_usr_offset(addr)) < 0) diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 3a25a7bd673e..05767e83cf2d 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -317,7 +317,7 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, if(personality(current->personality) == PER_LINUX32) { DBG(1,"setup_rt_frame: frame->info = 0x%p\n", &compat_frame->info); - err |= compat_copy_siginfo_to_user(&compat_frame->info, info); + err |= copy_siginfo_to_user32(&compat_frame->info, info); DBG(1,"SETUP_RT_FRAME: 1\n"); compat_val = (compat_int_t)current->sas_ss_sp; err |= __put_user(compat_val, &compat_frame->uc.uc_stack.ss_sp); diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c index 0792e20efef3..a6b4231cafa1 100644 --- a/arch/parisc/kernel/signal32.c +++ b/arch/parisc/kernel/signal32.c @@ -31,7 +31,6 @@ #include #include -#include #include #include "signal32.h" @@ -398,3 +397,104 @@ setup_sigcontext32(struct compat_sigcontext __user *sc, struct compat_regfile __ return err; } + +int +copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from) +{ + unsigned long tmp; + int err; + + if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) + return -EFAULT; + + err = __get_user(to->si_signo, &from->si_signo); + err |= __get_user(to->si_errno, &from->si_errno); + err |= __get_user(to->si_code, &from->si_code); + + if (to->si_code < 0) + err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE); + else { + switch (to->si_code >> 16) { + case __SI_CHLD >> 16: + err |= __get_user(to->si_utime, &from->si_utime); + err |= __get_user(to->si_stime, &from->si_stime); + err |= __get_user(to->si_status, &from->si_status); + default: + err |= __get_user(to->si_pid, &from->si_pid); + err |= __get_user(to->si_uid, &from->si_uid); + break; + case __SI_FAULT >> 16: + err |= __get_user(tmp, &from->si_addr); + to->si_addr = (void __user *) tmp; + break; + case __SI_POLL >> 16: + err |= __get_user(to->si_band, &from->si_band); + err |= __get_user(to->si_fd, &from->si_fd); + break; + case __SI_RT >> 16: /* This is not generated by the kernel as of now. */ + case __SI_MESGQ >> 16: + err |= __get_user(to->si_pid, &from->si_pid); + err |= __get_user(to->si_uid, &from->si_uid); + err |= __get_user(to->si_int, &from->si_int); + break; + } + } + return err; +} + +int +copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from) +{ + unsigned int addr; + int err; + + if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) + return -EFAULT; + + /* If you change siginfo_t structure, please be sure + this code is fixed accordingly. + It should never copy any pad contained in the structure + to avoid security leaks, but must copy the generic + 3 ints plus the relevant union member. + This routine must convert siginfo from 64bit to 32bit as well + at the same time. */ + err = __put_user(from->si_signo, &to->si_signo); + err |= __put_user(from->si_errno, &to->si_errno); + err |= __put_user((short)from->si_code, &to->si_code); + if (from->si_code < 0) + err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE); + else { + switch (from->si_code >> 16) { + case __SI_CHLD >> 16: + err |= __put_user(from->si_utime, &to->si_utime); + err |= __put_user(from->si_stime, &to->si_stime); + err |= __put_user(from->si_status, &to->si_status); + default: + err |= __put_user(from->si_pid, &to->si_pid); + err |= __put_user(from->si_uid, &to->si_uid); + break; + case __SI_FAULT >> 16: + /* avoid type-checking warnings by copying _pad[0] in lieu of si_addr... */ + err |= __put_user(from->_sifields._pad[0], &to->si_addr); + break; + case __SI_POLL >> 16: + err |= __put_user(from->si_band, &to->si_band); + err |= __put_user(from->si_fd, &to->si_fd); + break; + case __SI_TIMER >> 16: + err |= __put_user(from->si_tid, &to->si_tid); + err |= __put_user(from->si_overrun, &to->si_overrun); + addr = (unsigned long) from->si_ptr; + err |= __put_user(addr, &to->si_ptr); + break; + case __SI_RT >> 16: /* Not generated by the kernel as of now. */ + case __SI_MESGQ >> 16: + err |= __put_user(from->si_uid, &to->si_uid); + err |= __put_user(from->si_pid, &to->si_pid); + addr = (unsigned long) from->si_ptr; + err |= __put_user(addr, &to->si_ptr); + break; + } + } + return err; +} diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h index 4d1569e717cc..e39b38a67a87 100644 --- a/arch/parisc/kernel/signal32.h +++ b/arch/parisc/kernel/signal32.h @@ -20,8 +20,34 @@ #define _PARISC64_KERNEL_SIGNAL32_H #include -#include -#include + +typedef compat_uptr_t compat_sighandler_t; + +typedef struct compat_sigaltstack { + compat_uptr_t ss_sp; + compat_int_t ss_flags; + compat_size_t ss_size; +} compat_stack_t; + +/* Most things should be clean enough to redefine this at will, if care + is taken to make libc match. */ + +struct compat_sigaction { + compat_sighandler_t sa_handler; + compat_uint_t sa_flags; + compat_sigset_t sa_mask; /* mask last for extensibility */ +}; + +/* 32-bit ucontext as seen from an 64-bit kernel */ +struct compat_ucontext { + compat_uint_t uc_flags; + compat_uptr_t uc_link; + compat_stack_t uc_stack; /* struct compat_sigaltstack (12 bytes)*/ + /* FIXME: Pad out to get uc_mcontext to start at an 8-byte aligned boundary */ + compat_uint_t pad[1]; + struct compat_sigcontext uc_mcontext; + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; /* ELF32 signal handling */ @@ -29,6 +55,103 @@ struct k_sigaction32 { struct compat_sigaction sa; }; +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[((128/sizeof(int)) - 3)]; + + /* kill() */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + char _pad[sizeof(unsigned int) - sizeof(int)]; + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + +int copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from); +int copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from); + +/* In a deft move of uber-hackery, we decide to carry the top half of all + * 64-bit registers in a non-portable, non-ABI, hidden structure. + * Userspace can read the hidden structure if it *wants* but is never + * guaranteed to be in the same place. Infact the uc_sigmask from the + * ucontext_t structure may push the hidden register file downards + */ +struct compat_regfile { + /* Upper half of all the 64-bit registers that were truncated + on a copy to a 32-bit userspace */ + compat_int_t rf_gr[32]; + compat_int_t rf_iasq[2]; + compat_int_t rf_iaoq[2]; + compat_int_t rf_sar; +}; + +#define COMPAT_SIGRETURN_TRAMP 4 +#define COMPAT_SIGRESTARTBLOCK_TRAMP 5 +#define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + \ + COMPAT_SIGRESTARTBLOCK_TRAMP) + +struct compat_rt_sigframe { + /* XXX: Must match trampoline size in arch/parisc/kernel/signal.c + Secondary to that it must protect the ERESTART_RESTARTBLOCK + trampoline we left on the stack (we were bad and didn't + change sp so we could run really fast.) */ + compat_uint_t tramp[COMPAT_TRAMP_SIZE]; + compat_siginfo_t info; + struct compat_ucontext uc; + /* Hidden location of truncated registers, *must* be last. */ + struct compat_regfile regs; +}; + +/* + * The 32-bit ABI wants at least 48 bytes for a function call frame: + * 16 bytes for arg0-arg3, and 32 bytes for magic (the only part of + * which Linux/parisc uses is sp-20 for the saved return pointer...) + * Then, the stack pointer must be rounded to a cache line (64 bytes). + */ +#define SIGFRAME32 64 +#define FUNCTIONCALLFRAME32 48 +#define PARISC_RT_SIGFRAME_SIZE32 (((sizeof(struct compat_rt_sigframe) + FUNCTIONCALLFRAME32) + SIGFRAME32) & -SIGFRAME32) + void sigset_32to64(sigset_t *s64, compat_sigset_t *s32); void sigset_64to32(compat_sigset_t *s32, sigset_t *s64); int do_sigaltstack32 (const compat_stack_t __user *uss32, diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index d66163492890..af88afef41bd 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -650,6 +650,8 @@ end_linux_gateway_page: #define LWS_ENTRY(_name_) .word (lws_##_name_ - linux_gateway_page) #endif + .section .rodata,"a" + .align 4096 /* Light-weight-syscall table */ /* Start of lws table. */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 32cbc0489324..51d2480627d1 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -374,5 +374,24 @@ ENTRY_SAME(keyctl) ENTRY_SAME(ioprio_set) ENTRY_SAME(ioprio_get) + ENTRY_SAME(inotify_init) + ENTRY_SAME(inotify_add_watch) /* 270 */ + ENTRY_SAME(inotify_rm_watch) + ENTRY_COMP(pselect6) + ENTRY_COMP(ppoll) + ENTRY_SAME(migrate_pages) + ENTRY_COMP(openat) /* 275 */ + ENTRY_SAME(mkdirat) + ENTRY_SAME(mknodat) + ENTRY_SAME(fchownat) + ENTRY_COMP(futimesat) + ENTRY_COMP(newfstatat) /* 280 */ + ENTRY_SAME(unlinkat) + ENTRY_SAME(renameat) + ENTRY_SAME(linkat) + ENTRY_SAME(symlinkat) + ENTRY_SAME(readlinkat) /* 285 */ + ENTRY_SAME(fchmodat) + ENTRY_SAME(faccessat) /* Nothing yet */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 15914f0235a0..ff200608c851 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -193,10 +193,9 @@ void show_stack(struct task_struct *task, unsigned long *s) HERE: asm volatile ("copy %%r30, %0" : "=r"(sp)); - r = (struct pt_regs *)kmalloc(sizeof(struct pt_regs), GFP_KERNEL); + r = kzalloc(sizeof(struct pt_regs), GFP_KERNEL); if (!r) return; - memset(r, 0, sizeof(struct pt_regs)); r->iaoq[0] = (unsigned long)&&HERE; r->gr[2] = (unsigned long)__builtin_return_address(0); r->gr[30] = sp; diff --git a/arch/parisc/math-emu/decode_exc.c b/arch/parisc/math-emu/decode_exc.c index f84f2586672b..66c8a9f6a27e 100644 --- a/arch/parisc/math-emu/decode_exc.c +++ b/arch/parisc/math-emu/decode_exc.c @@ -337,6 +337,7 @@ decode_fpu(unsigned int Fpu_register[], unsigned int trap_counts[]) } break; case INVALIDEXCEPTION: + case OPC_2E_INVALIDEXCEPTION: update_trap_counts(Fpu_register, aflags, bflags, trap_counts); return SIGNALCODE(SIGFPE, FPE_FLTINV); case DIVISIONBYZEROEXCEPTION: diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 720287d46e55..7847ca13d6c2 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -371,17 +371,11 @@ static void __init setup_bootmem(void) void free_initmem(void) { - /* FIXME: */ -#if 0 - printk(KERN_INFO "NOT FREEING INITMEM (%dk)\n", - (&__init_end - &__init_begin) >> 10); - return; -#else unsigned long addr; printk(KERN_INFO "Freeing unused kernel memory: "); -#if 1 +#ifdef CONFIG_DEBUG_KERNEL /* Attempt to catch anyone trying to execute code here * by filling the page with BRK insns. * @@ -414,9 +408,21 @@ void free_initmem(void) pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE); printk("%luk freed\n", (unsigned long)(&__init_end - &__init_begin) >> 10); -#endif } + +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void) +{ + extern char __start_rodata, __end_rodata; + /* rodata memory was already mapped with KERNEL_RO access rights by + pagetable_init() and map_pages(). No need to do additional stuff here */ + printk (KERN_INFO "Write protecting the kernel read-only data: %luk\n", + (unsigned long)(&__end_rodata - &__start_rodata) >> 10); +} +#endif + + /* * Just an arbitrary offset to serve as a "hole" between mapping areas * (between top of physical memory and a potential pcxl dma mapping @@ -477,11 +483,6 @@ void __init mem_init(void) } -int do_check_pgt_cache(int low, int high) -{ - return 0; -} - unsigned long *empty_zero_page __read_mostly; void show_mem(void) @@ -690,7 +691,7 @@ static void __init pagetable_init(void) #ifdef CONFIG_BLK_DEV_INITRD if (initrd_end && initrd_end > mem_limit) { - printk("initrd: mapping %08lx-%08lx\n", initrd_start, initrd_end); + printk(KERN_INFO "initrd: mapping %08lx-%08lx\n", initrd_start, initrd_end); map_pages(initrd_start, __pa(initrd_start), initrd_end - initrd_start, PAGE_KERNEL); } @@ -792,8 +793,6 @@ map_hpux_gateway_page(struct task_struct *tsk, struct mm_struct *mm) EXPORT_SYMBOL(map_hpux_gateway_page); #endif -extern void flush_tlb_all_local(void); - void __init paging_init(void) { int i; @@ -802,7 +801,7 @@ void __init paging_init(void) pagetable_init(); gateway_init(); flush_cache_all_local(); /* start with known state */ - flush_tlb_all_local(); + flush_tlb_all_local(NULL); for (i = 0; i < npmem_ranges; i++) { unsigned long zones_size[MAX_NR_ZONES] = { 0, 0, 0 }; @@ -993,7 +992,7 @@ void flush_tlb_all(void) do_recycle++; } spin_unlock(&sid_lock); - on_each_cpu((void (*)(void *))flush_tlb_all_local, NULL, 1, 1); + on_each_cpu(flush_tlb_all_local, NULL, 1, 1); if (do_recycle) { spin_lock(&sid_lock); recycle_sids(recycle_ndirty,recycle_dirty_array); diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index f970ace208d3..c7a799a09516 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -134,7 +134,6 @@ static int __init add_legacy_soc_port(struct device_node *np, return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags); } -#ifdef CONFIG_ISA static int __init add_legacy_isa_port(struct device_node *np, struct device_node *isa_brg) { @@ -168,7 +167,6 @@ static int __init add_legacy_isa_port(struct device_node *np, return add_legacy_port(np, index, UPIO_PORT, reg[1], taddr, NO_IRQ, UPF_BOOT_AUTOCONF); } -#endif #ifdef CONFIG_PCI static int __init add_legacy_pci_port(struct device_node *np, @@ -276,7 +274,6 @@ void __init find_legacy_serial_ports(void) of_node_put(soc); } -#ifdef CONFIG_ISA /* First fill our array with ISA ports */ for (np = NULL; (np = of_find_node_by_type(np, "serial"));) { struct device_node *isa = of_get_parent(np); @@ -287,7 +284,6 @@ void __init find_legacy_serial_ports(void) } of_node_put(isa); } -#endif #ifdef CONFIG_PCI /* Next, try to locate PCI ports */ diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3747ab0dac3f..c6d0595da6b5 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -254,11 +254,9 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs); */ long sys_sigsuspend(old_sigset_t mask) { - sigset_t saveset; - mask &= _BLOCKABLE; spin_lock_irq(¤t->sighand->siglock); - saveset = current->blocked; + current->saved_sigmask = current->blocked; siginitset(¤t->blocked, mask); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c index c32c623001dc..356a739e52b2 100644 --- a/arch/powerpc/platforms/powermac/pfunc_core.c +++ b/arch/powerpc/platforms/powermac/pfunc_core.c @@ -862,21 +862,28 @@ int pmf_register_irq_client(struct device_node *target, spin_unlock_irqrestore(&pmf_lock, flags); return -ENODEV; } + if (list_empty(&func->irq_clients)) + func->dev->handlers->irq_enable(func); list_add(&client->link, &func->irq_clients); + client->func = func; spin_unlock_irqrestore(&pmf_lock, flags); return 0; } EXPORT_SYMBOL_GPL(pmf_register_irq_client); -void pmf_unregister_irq_client(struct device_node *np, - const char *name, - struct pmf_irq_client *client) +void pmf_unregister_irq_client(struct pmf_irq_client *client) { + struct pmf_function *func = client->func; unsigned long flags; + BUG_ON(func == NULL); + spin_lock_irqsave(&pmf_lock, flags); + client->func = NULL; list_del(&client->link); + if (list_empty(&func->irq_clients)) + func->dev->handlers->irq_disable(func); spin_unlock_irqrestore(&pmf_lock, flags); } EXPORT_SYMBOL_GPL(pmf_unregister_irq_client); diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 21934784f936..bdaa8aabdaa6 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -58,6 +58,7 @@ pcibios_find_pci_bus(struct device_node *dn) return find_bus_among_children(pdn->phb->bus, dn); } +EXPORT_SYMBOL_GPL(pcibios_find_pci_bus); /** * pcibios_remove_pci_devices - remove all devices under this bus @@ -106,6 +107,7 @@ pcibios_fixup_new_pci_devices(struct pci_bus *bus, int fix_bus) } } } +EXPORT_SYMBOL_GPL(pcibios_fixup_new_pci_devices); static int pcibios_pci_config_bridge(struct pci_dev *dev) @@ -172,3 +174,4 @@ pcibios_add_pci_devices(struct pci_bus * bus) pcibios_pci_config_bridge(dev); } } +EXPORT_SYMBOL_GPL(pcibios_add_pci_devices); diff --git a/arch/ppc/syslib/mv64x60.c b/arch/ppc/syslib/mv64x60.c index 94ea346b7b4b..1f01b7e2376b 100644 --- a/arch/ppc/syslib/mv64x60.c +++ b/arch/ppc/syslib/mv64x60.c @@ -313,7 +313,7 @@ static struct platform_device mpsc1_device = { }; #endif -#ifdef CONFIG_MV643XX_ETH +#if defined(CONFIG_MV643XX_ETH) || defined(CONFIG_MV643XX_ETH_MODULE) static struct resource mv64x60_eth_shared_resources[] = { [0] = { .name = "ethernet shared base", @@ -456,7 +456,7 @@ static struct platform_device *mv64x60_pd_devs[] __initdata = { &mpsc0_device, &mpsc1_device, #endif -#ifdef CONFIG_MV643XX_ETH +#if defined(CONFIG_MV643XX_ETH) || defined(CONFIG_MV643XX_ETH_MODULE) &mv64x60_eth_shared_device, #endif #ifdef CONFIG_MV643XX_ETH_0 diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 7d23edc6facb..3525c91204d4 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,13 +1,12 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.15-rc2 -# Mon Nov 21 13:51:30 2005 +# Linux kernel version: 2.6.16-rc1 +# Thu Jan 19 10:58:53 2006 # CONFIG_MMU=y CONFIG_RWSEM_XCHGADD_ALGORITHM=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_S390=y -CONFIG_UID16=y # # Code maturity level options @@ -29,18 +28,20 @@ CONFIG_POSIX_MQUEUE=y CONFIG_SYSCTL=y CONFIG_AUDIT=y # CONFIG_AUDITSYSCALL is not set -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y # CONFIG_CPUSETS is not set CONFIG_INITRAMFS_SOURCE="" +CONFIG_UID16=y +# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set # CONFIG_EMBEDDED is not set CONFIG_KALLSYMS=y # CONFIG_KALLSYMS_ALL is not set # CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y +CONFIG_ELF_CORE=y CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y @@ -49,8 +50,10 @@ CONFIG_CC_ALIGN_FUNCTIONS=0 CONFIG_CC_ALIGN_LABELS=0 CONFIG_CC_ALIGN_LOOPS=0 CONFIG_CC_ALIGN_JUMPS=0 +CONFIG_SLAB=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 +# CONFIG_SLOB is not set # # Loadable module support @@ -76,11 +79,11 @@ CONFIG_IOSCHED_NOOP=y CONFIG_IOSCHED_AS=y CONFIG_IOSCHED_DEADLINE=y CONFIG_IOSCHED_CFQ=y -CONFIG_DEFAULT_AS=y -# CONFIG_DEFAULT_DEADLINE is not set +# CONFIG_DEFAULT_AS is not set +CONFIG_DEFAULT_DEADLINE=y # CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set -CONFIG_DEFAULT_IOSCHED="anticipatory" +CONFIG_DEFAULT_IOSCHED="deadline" # # Base setup @@ -193,6 +196,11 @@ CONFIG_IPV6=y # SCTP Configuration (EXPERIMENTAL) # # CONFIG_IP_SCTP is not set + +# +# TIPC Configuration (EXPERIMENTAL) +# +# CONFIG_TIPC is not set # CONFIG_ATM is not set # CONFIG_BRIDGE is not set # CONFIG_VLAN_8021Q is not set @@ -362,6 +370,7 @@ CONFIG_DM_MULTIPATH=y # CONFIG_UNIX98_PTYS=y CONFIG_UNIX98_PTY_COUNT=2048 +# CONFIG_HANGCHECK_TIMER is not set # # Watchdog Cards @@ -488,6 +497,7 @@ CONFIG_FS_MBCACHE=y # CONFIG_JFS_FS is not set # CONFIG_FS_POSIX_ACL is not set # CONFIG_XFS_FS is not set +# CONFIG_OCFS2_FS is not set # CONFIG_MINIX_FS is not set # CONFIG_ROMFS_FS is not set CONFIG_INOTIFY=y @@ -520,6 +530,7 @@ CONFIG_TMPFS=y # CONFIG_HUGETLB_PAGE is not set CONFIG_RAMFS=y # CONFIG_RELAYFS_FS is not set +# CONFIG_CONFIGFS_FS is not set # # Miscellaneous filesystems @@ -584,6 +595,7 @@ CONFIG_MSDOS_PARTITION=y # CONFIG_SGI_PARTITION is not set # CONFIG_ULTRIX_PARTITION is not set # CONFIG_SUN_PARTITION is not set +# CONFIG_KARMA_PARTITION is not set # CONFIG_EFI_PARTITION is not set # @@ -592,7 +604,7 @@ CONFIG_MSDOS_PARTITION=y # CONFIG_NLS is not set # -# Profiling support +# Instrumentation Support # # CONFIG_PROFILING is not set @@ -600,19 +612,21 @@ CONFIG_MSDOS_PARTITION=y # Kernel hacking # # CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y CONFIG_LOG_BUF_SHIFT=17 -CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_DETECT_SOFTLOCKUP is not set # CONFIG_SCHEDSTATS is not set # CONFIG_DEBUG_SLAB is not set -CONFIG_DEBUG_PREEMPT=y +# CONFIG_DEBUG_PREEMPT is not set +CONFIG_DEBUG_MUTEXES=y # CONFIG_DEBUG_SPINLOCK is not set # CONFIG_DEBUG_SPINLOCK_SLEEP is not set # CONFIG_DEBUG_KOBJECT is not set # CONFIG_DEBUG_INFO is not set -CONFIG_DEBUG_FS=y +# CONFIG_DEBUG_FS is not set # CONFIG_DEBUG_VM is not set +CONFIG_FORCED_INLINING=y # CONFIG_RCU_TORTURE_TEST is not set # diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index fa2b3bc22f20..ef706694a0c1 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -1,8 +1,7 @@ /* - * arch/s390/kernel/signal32.c + * arch/s390/kernel/compat_signal.c * - * S390 version - * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright (C) IBM Corp. 2000,2006 * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) * Gerhard Tonn (ton@de.ibm.com) * @@ -52,8 +51,6 @@ typedef struct struct ucontext32 uc; } rt_sigframe32; -asmlinkage int FASTCALL(do_signal(struct pt_regs *regs, sigset_t *oldset)); - int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { int err; @@ -161,66 +158,6 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) return err; } -/* - * Atomically swap in the new signal mask, and wait for a signal. - */ -asmlinkage int -sys32_sigsuspend(struct pt_regs * regs,int history0, int history1, old_sigset_t mask) -{ - sigset_t saveset; - - mask &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); - saveset = current->blocked; - siginitset(¤t->blocked, mask); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - regs->gprs[2] = -EINTR; - - while (1) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - if (do_signal(regs, &saveset)) - return -EINTR; - } -} - -asmlinkage int -sys32_rt_sigsuspend(struct pt_regs * regs, compat_sigset_t __user *unewset, - size_t sigsetsize) -{ - sigset_t saveset, newset; - compat_sigset_t set32; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - - if (copy_from_user(&set32, unewset, sizeof(set32))) - return -EFAULT; - switch (_NSIG_WORDS) { - case 4: newset.sig[3] = set32.sig[6] + (((long)set32.sig[7]) << 32); - case 3: newset.sig[2] = set32.sig[4] + (((long)set32.sig[5]) << 32); - case 2: newset.sig[1] = set32.sig[2] + (((long)set32.sig[3]) << 32); - case 1: newset.sig[0] = set32.sig[0] + (((long)set32.sig[1]) << 32); - } - sigdelsetmask(&newset, ~_BLOCKABLE); - - spin_lock_irq(¤t->sighand->siglock); - saveset = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - regs->gprs[2] = -EINTR; - - while (1) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - if (do_signal(regs, &saveset)) - return -EINTR; - } -} - asmlinkage long sys32_sigaction(int sig, const struct old_sigaction32 __user *act, struct old_sigaction32 __user *oact) @@ -520,7 +457,7 @@ static inline int map_signal(int sig) return sig; } -static void setup_frame32(int sig, struct k_sigaction *ka, +static int setup_frame32(int sig, struct k_sigaction *ka, sigset_t *set, struct pt_regs * regs) { sigframe32 __user *frame = get_sigframe(ka, regs, sizeof(sigframe32)); @@ -565,13 +502,14 @@ static void setup_frame32(int sig, struct k_sigaction *ka, /* Place signal number on stack to allow backtrace from handler. */ if (__put_user(regs->gprs[2], (int __user *) &frame->signo)) goto give_sigsegv; - return; + return 0; give_sigsegv: force_sigsegv(sig, current); + return -EFAULT; } -static void setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, +static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs * regs) { int err = 0; @@ -615,31 +553,37 @@ static void setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, regs->gprs[2] = map_signal(sig); regs->gprs[3] = (__u64) &frame->info; regs->gprs[4] = (__u64) &frame->uc; - return; + return 0; give_sigsegv: force_sigsegv(sig, current); + return -EFAULT; } /* * OK, we're invoking a handler */ -void +int handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs * regs) { + int ret; + /* Set up the stack frame */ if (ka->sa.sa_flags & SA_SIGINFO) - setup_rt_frame32(sig, ka, info, oldset, regs); + ret = setup_rt_frame32(sig, ka, info, oldset, regs); else - setup_frame32(sig, ka, oldset, regs); + ret = setup_frame32(sig, ka, oldset, regs); - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); - if (!(ka->sa.sa_flags & SA_NODEFER)) - sigaddset(¤t->blocked,sig); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + if (ret == 0) { + spin_lock_irq(¤t->sighand->siglock); + sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + if (!(ka->sa.sa_flags & SA_NODEFER)) + sigaddset(¤t->blocked,sig); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + } + return ret; } diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index cfde1905d07d..83b33fe1923c 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1,9 +1,8 @@ /* -* arch/s390/kernel/sys_wrapper31.S +* arch/s390/kernel/compat_wrapper.S * wrapper for 31 bit compatible system calls. * -* S390 version -* Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation +* Copyright (C) IBM Corp. 2000,2006 * Author(s): Gerhard Tonn (ton@de.ibm.com), * Thomas Spatzier (tspat@de.ibm.com) */ @@ -288,7 +287,12 @@ sys32_setregid16_wrapper: llgfr %r3,%r3 # __kernel_old_gid_emu31_t jg sys32_setregid16 # branch to system call -#sys32_sigsuspend_wrapper # done in sigsuspend_glue + .globl sys_sigsuspend_wrapper +sys_sigsuspend_wrapper: + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + llgfr %r4,%r4 # old_sigset_t + jg sys_sigsuspend .globl compat_sys_sigpending_wrapper compat_sys_sigpending_wrapper: @@ -855,7 +859,11 @@ sys32_rt_sigqueueinfo_wrapper: llgtr %r4,%r4 # siginfo_emu31_t * jg sys32_rt_sigqueueinfo # branch to system call -#sys32_rt_sigsuspend_wrapper # done in rt_sigsuspend_glue + .globl compat_sys_rt_sigsuspend_wrapper +compat_sys_rt_sigsuspend_wrapper: + llgtr %r2,%r2 # compat_sigset_t * + llgfr %r3,%r3 # compat_size_t + jg compat_sys_rt_sigsuspend .globl sys32_pread64_wrapper sys32_pread64_wrapper: @@ -1475,3 +1483,122 @@ sys_inotify_rm_watch_wrapper: lgfr %r2,%r2 # int llgfr %r3,%r3 # u32 jg sys_inotify_rm_watch + + .globl compat_sys_openat_wrapper +compat_sys_openat_wrapper: + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + lgfr %r5,%r5 # int + jg compat_sys_openat + + .globl sys_mkdirat_wrapper +sys_mkdirat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + jg sys_mkdirat + + .globl sys_mknodat_wrapper +sys_mknodat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + llgfr %r5,%r5 # unsigned int + jg sys_mknodat + + .globl sys_fchownat_wrapper +sys_fchownat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # uid_t + llgfr %r5,%r5 # gid_t + lgfr %r6,%r6 # int + jg sys_fchownat + + .globl compat_sys_futimesat_wrapper +compat_sys_futimesat_wrapper: + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # struct timeval * + jg compat_sys_futimesat + + .globl compat_sys_newfstatat_wrapper +compat_sys_newfstatat_wrapper: + llgfr %r2,%r2 # unsigned int + llgtr %r3,%r3 # char * + llgtr %r4,%r4 # struct stat * + lgfr %r5,%r5 # int + jg compat_sys_newfstatat + + .globl sys_unlinkat_wrapper +sys_unlinkat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + jg sys_unlinkat + + .globl sys_renameat_wrapper +sys_renameat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + llgtr %r5,%r5 # const char * + jg sys_renameat + + .globl sys_linkat_wrapper +sys_linkat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + llgtr %r5,%r5 # const char * + jg sys_linkat + + .globl sys_symlinkat_wrapper +sys_symlinkat_wrapper: + llgtr %r2,%r2 # const char * + lgfr %r3,%r3 # int + llgtr %r4,%r4 # const char * + jg sys_symlinkat + + .globl sys_readlinkat_wrapper +sys_readlinkat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + llgtr %r4,%r4 # char * + lgfr %r5,%r5 # int + jg sys_readlinkat + + .globl sys_fchmodat_wrapper +sys_fchmodat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + llgfr %r4,%r4 # mode_t + jg sys_fchmodat + + .globl sys_faccessat_wrapper +sys_faccessat_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char * + lgfr %r4,%r4 # int + jg sys_faccessat + + .globl compat_sys_pselect6_wrapper +compat_sys_pselect6_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # fd_set * + llgtr %r4,%r4 # fd_set * + llgtr %r5,%r5 # fd_set * + llgtr %r6,%r6 # struct timespec * + llgt %r0,164(%r15) # void * + stg %r0,160(%r15) + jg compat_sys_pselect6 + + .globl compat_sys_ppoll_wrapper +compat_sys_ppoll_wrapper: + llgtr %r2,%r2 # struct pollfd * + llgfr %r3,%r3 # unsigned int + llgtr %r4,%r4 # struct timespec * + llgtr %r5,%r5 # const sigset_t * + llgfr %r6,%r6 # size_t + jg compat_sys_ppoll diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 27b07730b7b8..b2448487854c 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -2,8 +2,7 @@ * arch/s390/kernel/entry.S * S390 low-level entry points. * - * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright (C) IBM Corp. 1999,2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Hartmut Penner (hp@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), @@ -50,9 +49,10 @@ SP_ILC = STACK_FRAME_OVERHEAD + __PT_ILC SP_TRAP = STACK_FRAME_OVERHEAD + __PT_TRAP SP_SIZE = STACK_FRAME_OVERHEAD + __PT_SIZE -_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING | \ - _TIF_RESTART_SVC | _TIF_SINGLE_STEP ) -_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) +_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK | _TIF_NEED_RESCHED | \ + _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_SINGLE_STEP ) +_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK | _TIF_NEED_RESCHED | \ + _TIF_MCCK_PENDING) STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT @@ -251,8 +251,8 @@ sysc_work: bo BASED(sysc_mcck_pending) tm __TI_flags+3(%r9),_TIF_NEED_RESCHED bo BASED(sysc_reschedule) - tm __TI_flags+3(%r9),_TIF_SIGPENDING - bo BASED(sysc_sigpending) + tm __TI_flags+3(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK) + bnz BASED(sysc_sigpending) tm __TI_flags+3(%r9),_TIF_RESTART_SVC bo BASED(sysc_restart) tm __TI_flags+3(%r9),_TIF_SINGLE_STEP @@ -276,12 +276,11 @@ sysc_mcck_pending: br %r1 # TIF bit will be cleared by handler # -# _TIF_SIGPENDING is set, call do_signal +# _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal # sysc_sigpending: ni __TI_flags+3(%r9),255-_TIF_SINGLE_STEP # clear TIF_SINGLE_STEP la %r2,SP_PTREGS(%r15) # load pt_regs - sr %r3,%r3 # clear *oldset l %r1,BASED(.Ldo_signal) basr %r14,%r1 # call do_signal tm __TI_flags+3(%r9),_TIF_RESTART_SVC @@ -397,30 +396,6 @@ sys_rt_sigreturn_glue: l %r1,BASED(.Lrt_sigreturn) br %r1 # branch to sys_sigreturn -# -# sigsuspend and rt_sigsuspend need pt_regs as an additional -# parameter and they have to skip the store of %r2 into the -# user register %r2 because the return value was set in -# sigsuspend and rt_sigsuspend already and must not be overwritten! -# - -sys_sigsuspend_glue: - lr %r5,%r4 # move mask back - lr %r4,%r3 # move history1 parameter - lr %r3,%r2 # move history0 parameter - la %r2,SP_PTREGS(%r15) # load pt_regs as first parameter - l %r1,BASED(.Lsigsuspend) - la %r14,4(%r14) # skip store of return value - br %r1 # branch to sys_sigsuspend - -sys_rt_sigsuspend_glue: - lr %r4,%r3 # move sigsetsize parameter - lr %r3,%r2 # move unewset parameter - la %r2,SP_PTREGS(%r15) # load pt_regs as first parameter - l %r1,BASED(.Lrt_sigsuspend) - la %r14,4(%r14) # skip store of return value - br %r1 # branch to sys_rt_sigsuspend - sys_sigaltstack_glue: la %r4,SP_PTREGS(%r15) # load pt_regs as parameter l %r1,BASED(.Lsigaltstack) @@ -604,15 +579,16 @@ io_work: lr %r15,%r1 # # One of the work bits is on. Find out which one. -# Checked are: _TIF_SIGPENDING, _TIF_NEED_RESCHED and _TIF_MCCK_PENDING +# Checked are: _TIF_SIGPENDING, _TIF_RESTORE_SIGMASK, _TIF_NEED_RESCHED +# and _TIF_MCCK_PENDING # io_work_loop: tm __TI_flags+3(%r9),_TIF_MCCK_PENDING bo BASED(io_mcck_pending) tm __TI_flags+3(%r9),_TIF_NEED_RESCHED bo BASED(io_reschedule) - tm __TI_flags+3(%r9),_TIF_SIGPENDING - bo BASED(io_sigpending) + tm __TI_flags+3(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK) + bnz BASED(io_sigpending) b BASED(io_leave) # @@ -636,12 +612,11 @@ io_reschedule: b BASED(io_work_loop) # -# _TIF_SIGPENDING is set, call do_signal +# _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal # io_sigpending: stosm __SF_EMPTY(%r15),0x03 # reenable interrupts la %r2,SP_PTREGS(%r15) # load pt_regs - sr %r3,%r3 # clear *oldset l %r1,BASED(.Ldo_signal) basr %r14,%r1 # call do_signal stnsm __SF_EMPTY(%r15),0xfc # disable I/O and ext. interrupts diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 369ab4413ec7..2ac095bc0e25 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -1,9 +1,8 @@ /* - * arch/s390/kernel/entry.S + * arch/s390/kernel/entry64.S * S390 low-level entry points. * - * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright (C) IBM Corp. 1999,2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Hartmut Penner (hp@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), @@ -53,9 +52,10 @@ SP_SIZE = STACK_FRAME_OVERHEAD + __PT_SIZE STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT -_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING | \ - _TIF_RESTART_SVC | _TIF_SINGLE_STEP ) -_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) +_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK | _TIF_NEED_RESCHED | \ + _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_SINGLE_STEP ) +_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK | _TIF_NEED_RESCHED | \ + _TIF_MCCK_PENDING) #define BASED(name) name-system_call(%r13) @@ -249,8 +249,8 @@ sysc_work: jo sysc_mcck_pending tm __TI_flags+7(%r9),_TIF_NEED_RESCHED jo sysc_reschedule - tm __TI_flags+7(%r9),_TIF_SIGPENDING - jo sysc_sigpending + tm __TI_flags+7(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK) + jnz sysc_sigpending tm __TI_flags+7(%r9),_TIF_RESTART_SVC jo sysc_restart tm __TI_flags+7(%r9),_TIF_SINGLE_STEP @@ -272,12 +272,11 @@ sysc_mcck_pending: jg s390_handle_mcck # TIF bit will be cleared by handler # -# _TIF_SIGPENDING is set, call do_signal +# _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal # sysc_sigpending: ni __TI_flags+7(%r9),255-_TIF_SINGLE_STEP # clear TIF_SINGLE_STEP la %r2,SP_PTREGS(%r15) # load pt_regs - sgr %r3,%r3 # clear *oldset brasl %r14,do_signal # call do_signal tm __TI_flags+7(%r9),_TIF_RESTART_SVC jo sysc_restart @@ -414,52 +413,6 @@ sys32_rt_sigreturn_glue: jg sys32_rt_sigreturn # branch to sys32_sigreturn #endif -# -# sigsuspend and rt_sigsuspend need pt_regs as an additional -# parameter and they have to skip the store of %r2 into the -# user register %r2 because the return value was set in -# sigsuspend and rt_sigsuspend already and must not be overwritten! -# - -sys_sigsuspend_glue: - lgr %r5,%r4 # move mask back - lgr %r4,%r3 # move history1 parameter - lgr %r3,%r2 # move history0 parameter - la %r2,SP_PTREGS(%r15) # load pt_regs as first parameter - la %r14,6(%r14) # skip store of return value - jg sys_sigsuspend # branch to sys_sigsuspend - -#ifdef CONFIG_COMPAT -sys32_sigsuspend_glue: - llgfr %r4,%r4 # unsigned long - lgr %r5,%r4 # move mask back - lgfr %r3,%r3 # int - lgr %r4,%r3 # move history1 parameter - lgfr %r2,%r2 # int - lgr %r3,%r2 # move history0 parameter - la %r2,SP_PTREGS(%r15) # load pt_regs as first parameter - la %r14,6(%r14) # skip store of return value - jg sys32_sigsuspend # branch to sys32_sigsuspend -#endif - -sys_rt_sigsuspend_glue: - lgr %r4,%r3 # move sigsetsize parameter - lgr %r3,%r2 # move unewset parameter - la %r2,SP_PTREGS(%r15) # load pt_regs as first parameter - la %r14,6(%r14) # skip store of return value - jg sys_rt_sigsuspend # branch to sys_rt_sigsuspend - -#ifdef CONFIG_COMPAT -sys32_rt_sigsuspend_glue: - llgfr %r3,%r3 # size_t - lgr %r4,%r3 # move sigsetsize parameter - llgtr %r2,%r2 # sigset_emu31_t * - lgr %r3,%r2 # move unewset parameter - la %r2,SP_PTREGS(%r15) # load pt_regs as first parameter - la %r14,6(%r14) # skip store of return value - jg sys32_rt_sigsuspend # branch to sys32_rt_sigsuspend -#endif - sys_sigaltstack_glue: la %r4,SP_PTREGS(%r15) # load pt_regs as parameter jg sys_sigaltstack # branch to sys_sigreturn @@ -646,15 +599,16 @@ io_work: lgr %r15,%r1 # # One of the work bits is on. Find out which one. -# Checked are: _TIF_SIGPENDING, _TIF_NEED_RESCHED and _TIF_MCCK_PENDING +# Checked are: _TIF_SIGPENDING, _TIF_RESTORE_SIGPENDING, _TIF_NEED_RESCHED +# and _TIF_MCCK_PENDING # io_work_loop: tm __TI_flags+7(%r9),_TIF_MCCK_PENDING jo io_mcck_pending tm __TI_flags+7(%r9),_TIF_NEED_RESCHED jo io_reschedule - tm __TI_flags+7(%r9),_TIF_SIGPENDING - jo io_sigpending + tm __TI_flags+7(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK) + jnz io_sigpending j io_leave # @@ -676,12 +630,11 @@ io_reschedule: j io_work_loop # -# _TIF_SIGPENDING is set, call do_signal +# _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal # io_sigpending: stosm __SF_EMPTY(%r15),0x03 # reenable interrupts la %r2,SP_PTREGS(%r15) # load pt_regs - slgr %r3,%r3 # clear *oldset brasl %r14,do_signal # call do_signal stnsm __SF_EMPTY(%r15),0xfc # disable I/O and ext. interrupts j io_work_loop diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 6ae4a77270b5..ae1927e48cfb 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -1,8 +1,7 @@ /* * arch/s390/kernel/signal.c * - * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright (C) IBM Corp. 1999,2006 * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) * * Based on Intel version @@ -51,60 +50,24 @@ typedef struct struct ucontext uc; } rt_sigframe; -int do_signal(struct pt_regs *regs, sigset_t *oldset); - /* * Atomically swap in the new signal mask, and wait for a signal. */ asmlinkage int -sys_sigsuspend(struct pt_regs * regs, int history0, int history1, - old_sigset_t mask) +sys_sigsuspend(int history0, int history1, old_sigset_t mask) { - sigset_t saveset; - mask &= _BLOCKABLE; spin_lock_irq(¤t->sighand->siglock); - saveset = current->blocked; + current->saved_sigmask = current->blocked; siginitset(¤t->blocked, mask); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - regs->gprs[2] = -EINTR; - while (1) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - if (do_signal(regs, &saveset)) - return -EINTR; - } -} + current->state = TASK_INTERRUPTIBLE; + schedule(); + set_thread_flag(TIF_RESTORE_SIGMASK); -asmlinkage long -sys_rt_sigsuspend(struct pt_regs *regs, sigset_t __user *unewset, - size_t sigsetsize) -{ - sigset_t saveset, newset; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - - if (copy_from_user(&newset, unewset, sizeof(newset))) - return -EFAULT; - sigdelsetmask(&newset, ~_BLOCKABLE); - - spin_lock_irq(¤t->sighand->siglock); - saveset = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - regs->gprs[2] = -EINTR; - - while (1) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - if (do_signal(regs, &saveset)) - return -EINTR; - } + return -ERESTARTNOHAND; } asmlinkage long @@ -306,8 +269,8 @@ static inline int map_signal(int sig) return sig; } -static void setup_frame(int sig, struct k_sigaction *ka, - sigset_t *set, struct pt_regs * regs) +static int setup_frame(int sig, struct k_sigaction *ka, + sigset_t *set, struct pt_regs * regs) { sigframe __user *frame; @@ -355,13 +318,14 @@ static void setup_frame(int sig, struct k_sigaction *ka, /* Place signal number on stack to allow backtrace from handler. */ if (__put_user(regs->gprs[2], (int __user *) &frame->signo)) goto give_sigsegv; - return; + return 0; give_sigsegv: force_sigsegv(sig, current); + return -EFAULT; } -static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, +static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs * regs) { int err = 0; @@ -409,32 +373,39 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->gprs[2] = map_signal(sig); regs->gprs[3] = (unsigned long) &frame->info; regs->gprs[4] = (unsigned long) &frame->uc; - return; + return 0; give_sigsegv: force_sigsegv(sig, current); + return -EFAULT; } /* * OK, we're invoking a handler */ -static void +static int handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs * regs) { + int ret; + /* Set up the stack frame */ if (ka->sa.sa_flags & SA_SIGINFO) - setup_rt_frame(sig, ka, info, oldset, regs); + ret = setup_rt_frame(sig, ka, info, oldset, regs); else - setup_frame(sig, ka, oldset, regs); + ret = setup_frame(sig, ka, oldset, regs); - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); - if (!(ka->sa.sa_flags & SA_NODEFER)) - sigaddset(¤t->blocked,sig); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + if (ret == 0) { + spin_lock_irq(¤t->sighand->siglock); + sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + if (!(ka->sa.sa_flags & SA_NODEFER)) + sigaddset(¤t->blocked,sig); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + } + + return ret; } /* @@ -446,12 +417,13 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, * the kernel can handle, and then we build all the user-level signal handling * stack-frames in one go after that. */ -int do_signal(struct pt_regs *regs, sigset_t *oldset) +void do_signal(struct pt_regs *regs) { unsigned long retval = 0, continue_addr = 0, restart_addr = 0; siginfo_t info; int signr; struct k_sigaction ka; + sigset_t *oldset; /* * We want the common case to go fast, which @@ -460,9 +432,11 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) * if so. */ if (!user_mode(regs)) - return 1; + return; - if (!oldset) + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + oldset = ¤t->saved_sigmask; + else oldset = ¤t->blocked; /* Are we from a system call? */ @@ -473,12 +447,14 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) /* Prepare for system call restart. We do this here so that a debugger will see the already changed PSW. */ - if (retval == -ERESTARTNOHAND || - retval == -ERESTARTSYS || - retval == -ERESTARTNOINTR) { + switch (retval) { + case -ERESTARTNOHAND: + case -ERESTARTSYS: + case -ERESTARTNOINTR: regs->gprs[2] = regs->orig_gpr2; regs->psw.addr = restart_addr; - } else if (retval == -ERESTART_RESTARTBLOCK) { + break; + case -ERESTART_RESTARTBLOCK: regs->gprs[2] = -EINTR; } } @@ -503,17 +479,38 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) /* Whee! Actually deliver the signal. */ #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_31BIT)) { - extern void handle_signal32(unsigned long sig, - struct k_sigaction *ka, - siginfo_t *info, - sigset_t *oldset, - struct pt_regs *regs); - handle_signal32(signr, &ka, &info, oldset, regs); - return 1; + extern int handle_signal32(unsigned long sig, + struct k_sigaction *ka, + siginfo_t *info, + sigset_t *oldset, + struct pt_regs *regs); + if (handle_signal32( + signr, &ka, &info, oldset, regs) == 0) { + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + clear_thread_flag(TIF_RESTORE_SIGMASK); + } + return; } #endif - handle_signal(signr, &ka, &info, oldset, regs); - return 1; + if (handle_signal(signr, &ka, &info, oldset, regs) == 0) { + /* + * A signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TIF_RESTORE_SIGMASK flag. + */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + clear_thread_flag(TIF_RESTORE_SIGMASK); + } + return; + } + + /* + * If there's no signal to deliver, we just put the saved sigmask back. + */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) { + clear_thread_flag(TIF_RESTORE_SIGMASK); + sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } /* Restart a different system call. */ @@ -522,5 +519,4 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) regs->gprs[2] = __NR_restart_syscall; set_thread_flag(TIF_RESTART_SVC); } - return 0; } diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 426d7cafdab3..3280345efacd 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -80,7 +80,7 @@ NI_SYSCALL /* old sgetmask syscall*/ NI_SYSCALL /* old ssetmask syscall*/ SYSCALL(sys_setreuid16,sys_ni_syscall,sys32_setreuid16_wrapper) /* old setreuid16 syscall */ SYSCALL(sys_setregid16,sys_ni_syscall,sys32_setregid16_wrapper) /* old setregid16 syscall */ -SYSCALL(sys_sigsuspend_glue,sys_sigsuspend_glue,sys32_sigsuspend_glue) +SYSCALL(sys_sigsuspend,sys_sigsuspend,sys_sigsuspend_wrapper) SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending_wrapper) SYSCALL(sys_sethostname,sys_sethostname,sys32_sethostname_wrapper) SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit_wrapper) /* 75 */ @@ -187,7 +187,7 @@ SYSCALL(sys_rt_sigprocmask,sys_rt_sigprocmask,sys32_rt_sigprocmask_wrapper) /* 1 SYSCALL(sys_rt_sigpending,sys_rt_sigpending,sys32_rt_sigpending_wrapper) SYSCALL(sys_rt_sigtimedwait,sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait_wrapper) SYSCALL(sys_rt_sigqueueinfo,sys_rt_sigqueueinfo,sys32_rt_sigqueueinfo_wrapper) -SYSCALL(sys_rt_sigsuspend_glue,sys_rt_sigsuspend_glue,sys32_rt_sigsuspend_glue) +SYSCALL(sys_rt_sigsuspend,sys_rt_sigsuspend,compat_sys_rt_sigsuspend_wrapper) SYSCALL(sys_pread64,sys_pread64,sys32_pread64_wrapper) /* 180 */ SYSCALL(sys_pwrite64,sys_pwrite64,sys32_pwrite64_wrapper) SYSCALL(sys_chown16,sys_ni_syscall,sys32_chown16_wrapper) /* old chown16 syscall */ @@ -293,5 +293,21 @@ SYSCALL(sys_waitid,sys_waitid,compat_sys_waitid_wrapper) SYSCALL(sys_ioprio_set,sys_ioprio_set,sys_ioprio_set_wrapper) SYSCALL(sys_ioprio_get,sys_ioprio_get,sys_ioprio_get_wrapper) SYSCALL(sys_inotify_init,sys_inotify_init,sys_inotify_init) -SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,sys_inotify_add_watch_wrapper) +SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,sys_inotify_add_watch_wrapper) /* 285 */ SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,sys_inotify_rm_watch_wrapper) +NI_SYSCALL /* 287 sys_migrate_pages */ +SYSCALL(sys_openat,sys_openat,compat_sys_openat_wrapper) +SYSCALL(sys_mkdirat,sys_mkdirat,sys_mkdirat_wrapper) +SYSCALL(sys_mknodat,sys_mknodat,sys_mknodat_wrapper) /* 290 */ +SYSCALL(sys_fchownat,sys_fchownat,sys_fchownat_wrapper) +SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat_wrapper) +SYSCALL(sys_newfstatat,sys_newfstatat,compat_sys_newfstatat_wrapper) +SYSCALL(sys_unlinkat,sys_unlinkat,sys_unlinkat_wrapper) +SYSCALL(sys_renameat,sys_renameat,sys_renameat_wrapper) /* 295 */ +SYSCALL(sys_linkat,sys_linkat,sys_linkat_wrapper) +SYSCALL(sys_symlinkat,sys_symlinkat,sys_symlinkat_wrapper) +SYSCALL(sys_readlinkat,sys_readlinkat,sys_readlinkat_wrapper) +SYSCALL(sys_fchmodat,sys_fchmodat,sys_fchmodat_wrapper) +SYSCALL(sys_faccessat,sys_faccessat,sys_faccessat_wrapper) /* 300 */ +SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6_wrapper) +SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll_wrapper) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 7c0fe152a111..fea043b69b91 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -61,9 +61,18 @@ extern unsigned long wall_jiffies; */ unsigned long long sched_clock(void) { - return ((get_clock() - jiffies_timer_cc) * 1000) >> 12; + return ((get_clock() - jiffies_timer_cc) * 125) >> 9; } +/* + * Monotonic_clock - returns # of nanoseconds passed since time_init() + */ +unsigned long long monotonic_clock(void) +{ + return sched_clock(); +} +EXPORT_SYMBOL(monotonic_clock); + void tod_to_timeval(__u64 todval, struct timespec *xtime) { unsigned long long sec; diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index f20b51ff1d86..e05d087a6eae 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -6,4 +6,4 @@ EXTRA_AFLAGS := -traditional lib-y += delay.o string.o lib-y += $(if $(CONFIG_64BIT),uaccess64.o,uaccess.o) -lib-$(CONFIG_SMP) += spinlock.o \ No newline at end of file +lib-$(CONFIG_SMP) += spinlock.o diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 01bc7d589afe..504d56f8ca7f 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -396,14 +396,8 @@ source "arch/sh/boards/renesas/hs7751rvoip/Kconfig" source "arch/sh/boards/renesas/rts7751r2d/Kconfig" -config SH_PCLK_FREQ_BOOL - bool "Set default pclk frequency" - default y if !SH_RTC - default n - config SH_PCLK_FREQ int "Peripheral clock frequency (in Hz)" - depends on SH_PCLK_FREQ_BOOL default "50000000" if CPU_SUBTYPE_SH7750 || CPU_SUBTYPE_SH7780 default "60000000" if CPU_SUBTYPE_SH7751 default "33333333" if CPU_SUBTYPE_SH7300 || CPU_SUBTYPE_SH7770 || CPU_SUBTYPE_SH7760 diff --git a/arch/sh/boards/superh/microdev/io.c b/arch/sh/boards/superh/microdev/io.c index fe83b2c03076..1ed7f880b8c7 100644 --- a/arch/sh/boards/superh/microdev/io.c +++ b/arch/sh/boards/superh/microdev/io.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include /* * we need to have a 'safe' address to re-direct all I/O requests @@ -52,8 +52,90 @@ #define IO_ISP1161_PHYS 0xa7700000ul /* Physical address of Philips ISP1161x USB chip */ #define IO_SUPERIO_PHYS 0xa7800000ul /* Physical address of SMSC FDC37C93xAPM SuperIO chip */ -#define PORT2ADDR(x) (microdev_isa_port2addr(x)) +/* + * map I/O ports to memory-mapped addresses + */ +static unsigned long microdev_isa_port2addr(unsigned long offset) +{ + unsigned long result; + if ((offset >= IO_LAN91C111_BASE) && + (offset < IO_LAN91C111_BASE + IO_LAN91C111_EXTENT)) { + /* + * SMSC LAN91C111 Ethernet chip + */ + result = IO_LAN91C111_PHYS + offset - IO_LAN91C111_BASE; + } else if ((offset >= IO_SUPERIO_BASE) && + (offset < IO_SUPERIO_BASE + IO_SUPERIO_EXTENT)) { + /* + * SMSC FDC37C93xAPM SuperIO chip + * + * Configuration Registers + */ + result = IO_SUPERIO_PHYS + (offset << 1); +#if 0 + } else if (offset == KBD_DATA_REG || offset == KBD_CNTL_REG || + offset == KBD_STATUS_REG) { + /* + * SMSC FDC37C93xAPM SuperIO chip + * + * PS/2 Keyboard + Mouse (ports 0x60 and 0x64). + */ + result = IO_SUPERIO_PHYS + (offset << 1); +#endif + } else if (((offset >= IO_IDE1_BASE) && + (offset < IO_IDE1_BASE + IO_IDE_EXTENT)) || + (offset == IO_IDE1_MISC)) { + /* + * SMSC FDC37C93xAPM SuperIO chip + * + * IDE #1 + */ + result = IO_SUPERIO_PHYS + (offset << 1); + } else if (((offset >= IO_IDE2_BASE) && + (offset < IO_IDE2_BASE + IO_IDE_EXTENT)) || + (offset == IO_IDE2_MISC)) { + /* + * SMSC FDC37C93xAPM SuperIO chip + * + * IDE #2 + */ + result = IO_SUPERIO_PHYS + (offset << 1); + } else if ((offset >= IO_SERIAL1_BASE) && + (offset < IO_SERIAL1_BASE + IO_SERIAL_EXTENT)) { + /* + * SMSC FDC37C93xAPM SuperIO chip + * + * Serial #1 + */ + result = IO_SUPERIO_PHYS + (offset << 1); + } else if ((offset >= IO_SERIAL2_BASE) && + (offset < IO_SERIAL2_BASE + IO_SERIAL_EXTENT)) { + /* + * SMSC FDC37C93xAPM SuperIO chip + * + * Serial #2 + */ + result = IO_SUPERIO_PHYS + (offset << 1); + } else if ((offset >= IO_ISP1161_BASE) && + (offset < IO_ISP1161_BASE + IO_ISP1161_EXTENT)) { + /* + * Philips USB ISP1161x chip + */ + result = IO_ISP1161_PHYS + offset - IO_ISP1161_BASE; + } else { + /* + * safe default. + */ + printk("Warning: unexpected port in %s( offset = 0x%lx )\n", + __FUNCTION__, offset); + result = PVR; + } + + return result; +} + +#define PORT2ADDR(x) (microdev_isa_port2addr(x)) static inline void delay(void) { @@ -94,6 +176,17 @@ unsigned int microdev_inl(unsigned long port) return *(volatile unsigned int*)PORT2ADDR(port); } +void microdev_outw(unsigned short b, unsigned long port) +{ +#ifdef CONFIG_PCI + if (port >= PCIBIOS_MIN_IO) { + microdev_pci_outw(b, port); + return; + } +#endif + *(volatile unsigned short*)PORT2ADDR(port) = b; +} + void microdev_outb(unsigned char b, unsigned long port) { #ifdef CONFIG_PCI @@ -158,17 +251,6 @@ void microdev_outb(unsigned char b, unsigned long port) } } -void microdev_outw(unsigned short b, unsigned long port) -{ -#ifdef CONFIG_PCI - if (port >= PCIBIOS_MIN_IO) { - microdev_pci_outw(b, port); - return; - } -#endif - *(volatile unsigned short*)PORT2ADDR(port) = b; -} - void microdev_outl(unsigned int b, unsigned long port) { #ifdef CONFIG_PCI @@ -284,87 +366,3 @@ void microdev_outsl(unsigned long port, const void *buffer, unsigned long count) while (count--) *port_addr = *buf++; } - -/* - * map I/O ports to memory-mapped addresses - */ -unsigned long microdev_isa_port2addr(unsigned long offset) -{ - unsigned long result; - - if ((offset >= IO_LAN91C111_BASE) && - (offset < IO_LAN91C111_BASE + IO_LAN91C111_EXTENT)) { - /* - * SMSC LAN91C111 Ethernet chip - */ - result = IO_LAN91C111_PHYS + offset - IO_LAN91C111_BASE; - } else if ((offset >= IO_SUPERIO_BASE) && - (offset < IO_SUPERIO_BASE + IO_SUPERIO_EXTENT)) { - /* - * SMSC FDC37C93xAPM SuperIO chip - * - * Configuration Registers - */ - result = IO_SUPERIO_PHYS + (offset << 1); -#if 0 - } else if (offset == KBD_DATA_REG || offset == KBD_CNTL_REG || - offset == KBD_STATUS_REG) { - /* - * SMSC FDC37C93xAPM SuperIO chip - * - * PS/2 Keyboard + Mouse (ports 0x60 and 0x64). - */ - result = IO_SUPERIO_PHYS + (offset << 1); -#endif - } else if (((offset >= IO_IDE1_BASE) && - (offset < IO_IDE1_BASE + IO_IDE_EXTENT)) || - (offset == IO_IDE1_MISC)) { - /* - * SMSC FDC37C93xAPM SuperIO chip - * - * IDE #1 - */ - result = IO_SUPERIO_PHYS + (offset << 1); - } else if (((offset >= IO_IDE2_BASE) && - (offset < IO_IDE2_BASE + IO_IDE_EXTENT)) || - (offset == IO_IDE2_MISC)) { - /* - * SMSC FDC37C93xAPM SuperIO chip - * - * IDE #2 - */ - result = IO_SUPERIO_PHYS + (offset << 1); - } else if ((offset >= IO_SERIAL1_BASE) && - (offset < IO_SERIAL1_BASE + IO_SERIAL_EXTENT)) { - /* - * SMSC FDC37C93xAPM SuperIO chip - * - * Serial #1 - */ - result = IO_SUPERIO_PHYS + (offset << 1); - } else if ((offset >= IO_SERIAL2_BASE) && - (offset < IO_SERIAL2_BASE + IO_SERIAL_EXTENT)) { - /* - * SMSC FDC37C93xAPM SuperIO chip - * - * Serial #2 - */ - result = IO_SUPERIO_PHYS + (offset << 1); - } else if ((offset >= IO_ISP1161_BASE) && - (offset < IO_ISP1161_BASE + IO_ISP1161_EXTENT)) { - /* - * Philips USB ISP1161x chip - */ - result = IO_ISP1161_PHYS + offset - IO_ISP1161_BASE; - } else { - /* - * safe default. - */ - printk("Warning: unexpected port in %s( offset = 0x%lx )\n", - __FUNCTION__, offset); - result = PVR; - } - - return result; -} - diff --git a/arch/sh/boards/superh/microdev/irq.c b/arch/sh/boards/superh/microdev/irq.c index 1395c1e65da4..efcbd86b7cd2 100644 --- a/arch/sh/boards/superh/microdev/irq.c +++ b/arch/sh/boards/superh/microdev/irq.c @@ -15,7 +15,7 @@ #include #include -#include +#include #define NUM_EXTERNAL_IRQS 16 /* IRL0 .. IRL15 */ diff --git a/arch/sh/boards/superh/microdev/setup.c b/arch/sh/boards/superh/microdev/setup.c index 1c1d65fb12df..892b14d31405 100644 --- a/arch/sh/boards/superh/microdev/setup.c +++ b/arch/sh/boards/superh/microdev/setup.c @@ -3,7 +3,7 @@ * * Copyright (C) 2003 Sean McGoogan (Sean.McGoogan@superh.com) * Copyright (C) 2003, 2004 SuperH, Inc. - * Copyright (C) 2004 Paul Mundt + * Copyright (C) 2004, 2005 Paul Mundt * * SuperH SH4-202 MicroDev board support. * @@ -15,11 +15,10 @@ #include #include #include +#include