patches/series0000664000076400007640000002620211156253136012457 0ustar tglxtglx# # base tree: 2.6.29-rc7 # # # Mainline + -tip fixes and updates # # # Needs to be solved upstream by BKL removal # origin.patch revert-bkl-cleanup.patch revert-preempt-bkl-revert.patch # # Patches which should go mainline # rt_mutex_setprio.patch posix-timers-prevent-broadcast-signals.patch # # Lockless QRCU # qrcu.patch # KVM - RT fixes # NECESSARY: sched-enable-irqs-in-preempt-in-notifier-call.patch # # Check what's in mainline / mm or might be # upstream material. # spinlock-trylock-cleanup-sungem.patch x86_64-tsc-sync-irqflags-fix.patch neptune-no-at-keyboard.patch rtmutex-debug.h-cleanup.patch netpoll-8139too-fix.patch kprobes-preempt-fix.patch replace-bugon-by-warn-on.patch # Suspend / resume fixups i386-mark-atomic-irq-ops-raw.patch msi-suspend-resume-workaround.patch floppy-resume-fix.patch # # assorted fixlets from -mm: # ioapic-fix-too-fast-clocks.patch move-native-irq.patch dont-unmask-io_apic.patch # # misc build beautification patches: # gcc-warnings-shut-up.patch # # Various fixlets # nfs-stats-miss-preemption.patch random-driver-latency-fix.patch # # Debugging patches # #apic-dumpstack.patch # # Revert loopback bh assumption patch # loopback-revert.patch # # -rt queue: # #inet_hash_bits.patch #inet-hash-bits-ipv6-fix.patch # # IRQ threading # generic-cmpxchg-use-raw-local-irq-variant.patch preempt-softirqs-core.patch preempt-irqs-core.patch preempt-irqs-direct-debug-keyboard.patch preempt-realtime-direct-keyboard-sparseirq-fix.patch preempt-irqs-timer.patch preempt-irqs-hrtimer.patch # i386 preempt-irqs-i386.patch #preempt-irqs-i386-ioapic-mask-quirk.patch # x8664 #preempt-irqs-x86-64-ioapic-mask-quirk.patch preempt-irqs-Kconfig.patch # # Real real time stuff :) # preempt-irqs-port-fixes.patch rt-apis.patch rt-slab-new.patch rt-page_alloc.patch # # rt-mutexes # rt-mutex-preempt-debugging.patch ## PORT-BARRIER: rt-mutex-irq-flags-checking.patch rt-mutex-trivial-tcp-preempt-fix.patch rt-mutex-trivial-route-cast-fix.patch rt-mutex-i386.patch rt-mutex-x86-64.patch rt-mutex-core.patch rt-mutex-core-fixes.patch rt-mutex-core-mutex-fixes.patch rt-mutex-core-fixes2.patch rt-mutex-fix-non-lock-kernel-config.patch slub-compile-fix.patch rt-mutex-compat-semaphores.patch # # Per-CPU locking assumption cleanups: # per-cpu-locked-infrastructure.patch percpu-locked-mm.patch drain-all-local-pages-via-sched.patch rt-page_alloc.c-cleanup.patch percpu-locked-netfilter.patch #percpu-locked-netfilter2.patch # # Various preempt fixups # net-core-preempt-fix.patch bh-uptodate-lock.patch bh-state-lock.patch jbd_assertions_smp_only.patch # # Tasklet redesign # tasklet-redesign.patch tasklet-busy-loop-hack.patch # # Diable irq poll on -rt # disable-irqpoll.patch # # Inaccurate -rt stats (should be replaced by CFS) # kstat-add-rt-stats.patch # Misc preempt-realtime-warn-and-bug-on.patch # # Posix-cpu-timers in a thread # cputimer-thread-rt_A0.patch cputimer-thread-rt-fix.patch shorten-posix-cpu-timers-name.patch # # Various broken drivers # vortex-fix.patch serial-locking-rt-cleanup.patch # # Serial optimizing # serial-slow-machines.patch # # Realtime patches # # X86_64: needs splitting preempt-realtime-x86_64.patch # i386 preempt-realtime-i386.patch remove-check-pgt-cache-calls.patch #preempt-irqs-i386-idle-poll-loop-fix.patch # # Core patch # # Note this is a convenience split up it is not supposed to compile # step by step. Needs some care, but it is way easier to handle than # the previous touch all in one patch # preempt-realtime-sched.patch preempt-realtime-sched-remove-debug.patch preempt-realtime-mmdrop-delayed.patch preempt-realtime-sched-i386.patch preempt-realtime-prevent-idle-boosting.patch # preempt-realtime-cfs-accounting-fix.patch # PORT VICTIM: schedule-tail-balance-disable-irqs.patch preempt-realtime-sched-cpupri.patch preempt-realtime-core.patch fix-net-bug-fixes.patch resurrect-softirq-code.patch preempt-realtime-net.patch preempt-realtime-net-softirq-fixups.patch dev-queue-xmit-preempt-fix.patch net-xmit-lock-owner-cleanup.patch preempt-realtime-cleanup-dev-queue-xmit.patch preempt-realtime-loopback.patch preempt-realtime-fs-block.patch preempt-realtime-acpi.patch preempt-realtime-ipc.patch #preempt-realtime-sound.patch # ftrace-compile-fixes.patch preempt-realtime-mm.patch preempt-realtime-init-show-enabled-debugs.patch preempt-realtime-compile-fixes.patch preempt-realtime-console.patch #preempt-realtime-debug-sysctl.patch preempt-realtime-ide.patch preempt-realtime-input.patch preempt-realtime-irqs.patch irq-desc-init.patch preempt-realtime-fix-irqdesc-lock-initializers.patch preempt-realtime-fix-sig-cputimer-lock.patch preempt-realtime-net-drivers.patch #preempt-realtime-netconsole.patch preempt-realtime-printk.patch # CHECKME: preempt-realtime-profiling.patch preempt-realtime-rawlocks.patch preempt-realtime-rcu.patch preempt-realtime-timer.patch fix-compilation-for-non-RT-in-timer.patch kstat-fix-spurious-system-load-spikes-in-proc-loadavgrt.patch preempt-realtimer-timer-non-rt-warning-fixes.patch preempt-realtimer-timer-more-non-rt-warning-fixes.patch gtod-optimize.patch rt-move-update-wall-time-back-to-do-timer.patch bz235099-idle-load-fix.patch preempt-realtime-usb.patch preempt-realtime-warn-and-bug-on-fix.patch preempt-realtime-debugobjects-rt-safe.patch preempt-realtime-xfs-compat-semaphore.patch rt-stop-cpus-fix.patch preempt-realtime-tracer.patch preempt-realtime-btrfs-locking-workaround.patch preempt-realtime-force-rcu-preempt.patch preempt-realtime-perfcounters.patch preempt-realtime-ipi-call-lock-raw.patch preempt-realtime-timer-cpu-hotplug-fix.patch preempt-realtime-serial-console-fix.patch preempt-realtime-disable-workqueue-tracer-on-preempt-rt.patch # CHECKME: irq-mask-fix.patch handle-pending-in-simple-irq.patch preempt-realtime-irqthreading-sparseirq-fixups.patch preempt-realtime-sparseirq-waitqueue-init-fix.patch # # Various -rt fixups # #preempt-realtime-supress-cpulock-warning.patch #preempt-realtime-supress-nohz-softirq-warning.patch #preempt-realtime-8139too-rt-irq-flags-fix.patch preempt-realtime-mellanox-driver-fix.patch # # Utility patches (not for upstream inclusion): # preempt-realtime-supress-rtc-printk.patch hrtimer-no-printk.patch # # soft watchdog queue: # #softlockup-fix.patch softlockup-add-irq-regs-h.patch #softlockup-better-printout.patch #softlockup-cleanups.patch #softlockup-use-cpu-clock.patch # # Not yet reviewed # # # START of Pete's ccur-pagecache queue # # # END of Pete's ccur-pagecache queue # # # kmap atomix fixes # kmap-atomic-prepare.patch pagefault-disable-cleanup.patch kmap-atomic-i386-fix.patch # # Highmem modifications # highmem-revert-mainline.patch highmem_rewrite.patch highmem-redo-mainline.patch rt-kmap-scale-fix.patch # # Not yet reviewed # highmem-atomic-fix.patch #select-error-leak-fix.patch fix-emergency-reboot.patch timer-freq-tweaks.patch # # Debug patches: # #pause-on-oops-head-tail.patch # # x86-64 vsyscall modifications # x86-64-tscless-vgettimeofday.patch #vsyscall-fixadder-pa.patch # # Timekeeping fixups # # x rt-time-starvation-fix.patch # x rt-time-starvation-fix-update.patch # # RT-Java testing stuff # #Add-dev-rmem-device-driver-for-real-time-JVM-testing.patch #Allocate-RTSJ-memory-for-TCK-conformance-test.patch # # Softirq modifications # #new-softirq-code.patch softirq-per-cpu-assumptions-fixes.patch #fix-migrating-softirq.patch #only-run-softirqs-from-irq-thread-when-irq-affinity-is-set.patch #fix-softirq-checks-for-non-rt-preempt-hardirq.patch smp-processor-id-fixups.patch # # Weird crap unearthed by -rt which needs to be investigated # irda-fix.patch #nf_conntrack-fix-smp-processor-id.patch # # Needs proper fix # print-might-sleep-hack.patch lockdep-rt-mutex.patch #lockstat-rt-hooks.patch #lockstat_bounce_rt.patch # # KVM: # #kvm-rt.patch # # Add RT to uname and apply the version # RT_utsname.patch # # not yet backmerged tail patches: # preempt-rt-no-slub.patch paravirt-function-pointer-fix.patch quicklist-release-before-free-page.patch quicklist-release-before-free-page-fix.patch sched-rt-stats.patch # CHECKME: mitigate-resched-flood.patch genirq-soft-resend.patch relay-fix.patch #schedule_on_each_cpu-enhance.patch #schedule_on_each_cpu-enhance-rt.patch lockdep-rt-recursion-limit-fix.patch cond_resched_softirq-WARN-fix.patch # stuff Ingo put into version.patch #export-schedule-on-each-cpu.patch # fix-alternate_node_alloc.patch hack-convert-i_alloc_sem-for-direct_io-craziness.patch dont-let-rt-rw_semaphores-do-non_owner-locks.patch # CHECKME: rt-s_files-kill-a-union.patch loadavg_fixes_weird_loads.patch # HPET patches #watchdog_use_timer_and_hpet_on_x86_64.patch # x stop-critical-timing-in-idle.patch # rt-wakeup-fix.patch disable-ist-x86_64.patch plist-debug.patch seq-irqsave.patch numa-slab-freeing.patch # Peter's patches # # workqueue PI # # CHECKME: rt-list-mods.patch # CHECKME: rt-plist-mods.patch # CHECKME: rt-workqeue-prio.patch # CHECKME: rt-workqueue-barrier.patch # CHECKME: rt-wq-barrier-fix.patch # CHECKME: rt-delayed-prio.patch # CHECKME: sched_prio.patch # x critical-timing-kconfig.patch lock-init-plist-fix.patch ntfs-local-irq-save-nort.patch dont-disable-preemption-without-IST.patch # CHECKME: filemap-dont-bug-non-atomic.patch # CHECKME: fix-bug-on-in-filemap.patch rt-sched-groups.patch printk-dont-bug-on-sched.patch user-no-irq-disable.patch proportions-raw-locks.patch # AT91 patches use-edge-triggered-irq-handler-instead-of-simple-irq.patch apic-level-smp-affinity.patch printk-in-atomic.patch printk-in-atomic-hack-fix.patch slab-irq-nopreempt-fix.patch swap-spinlock-fix.patch aacraid-compat-sem.patch # Luis's gtod updates fix_vdso_gtod_vsyscall64_2.patch git-ignore-script-lpp.patch sched-wake_up_idle_cpu-rt.patch # Adaptive Locks and lateral steal rtmutex-lateral-steal.patch rtmutex-rearrange.patch rtmutex-remove-xchg.patch adaptive-spinlock-lite-v2.patch adaptive-optimize-rt-lock-wakeup.patch adaptive-task-oncpu.patch adaptive-adjust-pi-wakeup.patch adapt-remove-extra-try-to-lock.patch adaptive-earlybreak-on-steal.patch fix-adaptive-hack.patch tglx-04-rtmutex-unify-state-manipulation.patch tglx-05-rtmutex-remove-uber-optimization.patch tglx-07-rtmutex-prevent-missed-wakeups.patch fix-config-debug-rt-mutex-lock-underflow-warnings.patch realtime-preempt-warn-about-tracing.patch sub-dont-disable-irqs.patch raw-spinlocks-for-nmi-print.patch sched-fix-dequeued-race.patch lockdep-atomic-fixup.patch seqlock-01-make-sure-that-raw_seqlock-retries.patch namespace-lock-fixes.patch sched-generic-hide-smp-warning.patch seqlock-serialize-against-writers.patch seqlocks-handle-rwlock-and-spin.patch ata-irq-save-nort.patch fix-erroneous-histogram-stop-warn-on-messages.patch # hrtimer bring back the hard/softirq seperation :( hrtimer-fix-wait-for-hrtimer.patch printk-tick-move-to-softirq-on-rt.patch hrtimer-fixup-hrtimer-callback-changes.patch blkcypher-fix.patch rt-res_counter-fix.patch preempt-realtime-paravirt-spinlocks-fix.patch # x86-32 highmem related fixups preempt-realtime-x86-32-gup-kmapatomic.patch preempt-rt-x86-pageattr-flush-unused.patch # general valid on -rt not only for x86-32 highmem preempt-rt-scatterlist-nort.patch netfilter-rcu-destroy.patch percpu-locked-netfilter-ecache.patch debugobjects-rt-safe.patch disable-maxcpus-for-now.patch version.patch patches/origin.patch0000664000076400007640001663540411156253136013573 0ustar tglxtglxdiff --git a/Documentation/ABI/testing/debugfs-kmemtrace b/Documentation/ABI/testing/debugfs-kmemtrace new file mode 100644 index 0000000..5e6a92a --- /dev/null +++ b/Documentation/ABI/testing/debugfs-kmemtrace @@ -0,0 +1,71 @@ +What: /sys/kernel/debug/kmemtrace/ +Date: July 2008 +Contact: Eduard - Gabriel Munteanu +Description: + +In kmemtrace-enabled kernels, the following files are created: + +/sys/kernel/debug/kmemtrace/ + cpu (0400) Per-CPU tracing data, see below. (binary) + total_overruns (0400) Total number of bytes which were dropped from + cpu files because of full buffer condition, + non-binary. (text) + abi_version (0400) Kernel's kmemtrace ABI version. (text) + +Each per-CPU file should be read according to the relay interface. That is, +the reader should set affinity to that specific CPU and, as currently done by +the userspace application (though there are other methods), use poll() with +an infinite timeout before every read(). Otherwise, erroneous data may be +read. The binary data has the following _core_ format: + + Event ID (1 byte) Unsigned integer, one of: + 0 - represents an allocation (KMEMTRACE_EVENT_ALLOC) + 1 - represents a freeing of previously allocated memory + (KMEMTRACE_EVENT_FREE) + Type ID (1 byte) Unsigned integer, one of: + 0 - this is a kmalloc() / kfree() + 1 - this is a kmem_cache_alloc() / kmem_cache_free() + 2 - this is a __get_free_pages() et al. + Event size (2 bytes) Unsigned integer representing the + size of this event. Used to extend + kmemtrace. Discard the bytes you + don't know about. + Sequence number (4 bytes) Signed integer used to reorder data + logged on SMP machines. Wraparound + must be taken into account, although + it is unlikely. + Caller address (8 bytes) Return address to the caller. + Pointer to mem (8 bytes) Pointer to target memory area. Can be + NULL, but not all such calls might be + recorded. + +In case of KMEMTRACE_EVENT_ALLOC events, the next fields follow: + + Requested bytes (8 bytes) Total number of requested bytes, + unsigned, must not be zero. + Allocated bytes (8 bytes) Total number of actually allocated + bytes, unsigned, must not be lower + than requested bytes. + Requested flags (4 bytes) GFP flags supplied by the caller. + Target CPU (4 bytes) Signed integer, valid for event id 1. + If equal to -1, target CPU is the same + as origin CPU, but the reverse might + not be true. + +The data is made available in the same endianness the machine has. + +Other event ids and type ids may be defined and added. Other fields may be +added by increasing event size, but see below for details. +Every modification to the ABI, including new id definitions, are followed +by bumping the ABI version by one. + +Adding new data to the packet (features) is done at the end of the mandatory +data: + Feature size (2 byte) + Feature ID (1 byte) + Feature data (Feature size - 3 bytes) + + +Users: + kmemtrace-user - git://repo.or.cz/kmemtrace-user.git + diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 6e25340..accfe2f 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -298,3 +298,15 @@ over a rather long period of time, but improvements are always welcome! Note that, rcu_assign_pointer() and rcu_dereference() relate to SRCU just as they do to other forms of RCU. + +15. The whole point of call_rcu(), synchronize_rcu(), and friends + is to wait until all pre-existing readers have finished before + carrying out some otherwise-destructive operation. It is + therefore critically important to -first- remove any path + that readers can follow that could be affected by the + destructive operation, and -only- -then- invoke call_rcu(), + synchronize_rcu(), or friends. + + Because these primitives only wait for pre-existing readers, + it is the caller's responsibility to guarantee safety to + any subsequent readers. diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt index 45932ec..b41f3e5 100644 --- a/Documentation/cputopology.txt +++ b/Documentation/cputopology.txt @@ -18,11 +18,11 @@ For an architecture to support this feature, it must define some of these macros in include/asm-XXX/topology.h: #define topology_physical_package_id(cpu) #define topology_core_id(cpu) -#define topology_thread_siblings(cpu) -#define topology_core_siblings(cpu) +#define topology_thread_cpumask(cpu) +#define topology_core_cpumask(cpu) The type of **_id is int. -The type of siblings is cpumask_t. +The type of siblings is (const) struct cpumask *. To be consistent on all architectures, include/linux/topology.h provides default definitions for any of the above macros that are diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 5ddbe35..20d3b94 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -335,3 +335,12 @@ Why: In 2.6.18 the Secmark concept was introduced to replace the "compat_net" Secmark, it is time to deprecate the older mechanism and start the process of removing the old code. Who: Paul Moore +--------------------------- + +What: sysfs ui for changing p4-clockmod parameters +When: September 2009 +Why: See commits 129f8ae9b1b5be94517da76009ea956e89104ce8 and + e088e4c9cdb618675874becb91b2fd581ee707e6. + Removal is subject to fixing any remaining bugs in ACPI which may + cause the thermal throttling not to happen at the right time. +Who: Dave Jones , Matthew Garrett diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt index 3e79e4a..b324c03 100644 --- a/Documentation/filesystems/squashfs.txt +++ b/Documentation/filesystems/squashfs.txt @@ -22,7 +22,7 @@ Squashfs filesystem features versus Cramfs: Squashfs Cramfs -Max filesystem size: 2^64 16 MiB +Max filesystem size: 2^64 256 MiB Max file size: ~ 2 TiB 16 MiB Max files: unlimited unlimited Max directories: unlimited unlimited diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt index 803b131..fd9a3e6 100644 --- a/Documentation/ftrace.txt +++ b/Documentation/ftrace.txt @@ -15,31 +15,31 @@ Introduction Ftrace is an internal tracer designed to help out developers and designers of systems to find what is going on inside the kernel. -It can be used for debugging or analyzing latencies and performance -issues that take place outside of user-space. +It can be used for debugging or analyzing latencies and +performance issues that take place outside of user-space. Although ftrace is the function tracer, it also includes an -infrastructure that allows for other types of tracing. Some of the -tracers that are currently in ftrace include a tracer to trace -context switches, the time it takes for a high priority task to -run after it was woken up, the time interrupts are disabled, and -more (ftrace allows for tracer plugins, which means that the list of -tracers can always grow). +infrastructure that allows for other types of tracing. Some of +the tracers that are currently in ftrace include a tracer to +trace context switches, the time it takes for a high priority +task to run after it was woken up, the time interrupts are +disabled, and more (ftrace allows for tracer plugins, which +means that the list of tracers can always grow). The File System --------------- -Ftrace uses the debugfs file system to hold the control files as well -as the files to display output. +Ftrace uses the debugfs file system to hold the control files as +well as the files to display output. To mount the debugfs system: # mkdir /debug # mount -t debugfs nodev /debug -(Note: it is more common to mount at /sys/kernel/debug, but for simplicity - this document will use /debug) +( Note: it is more common to mount at /sys/kernel/debug, but for + simplicity this document will use /debug) That's it! (assuming that you have ftrace configured into your kernel) @@ -50,90 +50,124 @@ of ftrace. Here is a list of some of the key files: Note: all time values are in microseconds. - current_tracer: This is used to set or display the current tracer - that is configured. - - available_tracers: This holds the different types of tracers that - have been compiled into the kernel. The tracers - listed here can be configured by echoing their name - into current_tracer. - - tracing_enabled: This sets or displays whether the current_tracer - is activated and tracing or not. Echo 0 into this - file to disable the tracer or 1 to enable it. - - trace: This file holds the output of the trace in a human readable - format (described below). - - latency_trace: This file shows the same trace but the information - is organized more to display possible latencies - in the system (described below). - - trace_pipe: The output is the same as the "trace" file but this - file is meant to be streamed with live tracing. - Reads from this file will block until new data - is retrieved. Unlike the "trace" and "latency_trace" - files, this file is a consumer. This means reading - from this file causes sequential reads to display - more current data. Once data is read from this - file, it is consumed, and will not be read - again with a sequential read. The "trace" and - "latency_trace" files are static, and if the - tracer is not adding more data, they will display - the same information every time they are read. - - trace_options: This file lets the user control the amount of data - that is displayed in one of the above output - files. - - trace_max_latency: Some of the tracers record the max latency. - For example, the time interrupts are disabled. - This time is saved in this file. The max trace - will also be stored, and displayed by either - "trace" or "latency_trace". A new max trace will - only be recorded if the latency is greater than - the value in this file. (in microseconds) - - buffer_size_kb: This sets or displays the number of kilobytes each CPU - buffer can hold. The tracer buffers are the same size - for each CPU. The displayed number is the size of the - CPU buffer and not total size of all buffers. The - trace buffers are allocated in pages (blocks of memory - that the kernel uses for allocation, usually 4 KB in size). - If the last page allocated has room for more bytes - than requested, the rest of the page will be used, - making the actual allocation bigger than requested. - (Note, the size may not be a multiple of the page size due - to buffer managment overhead.) - - This can only be updated when the current_tracer - is set to "nop". - - tracing_cpumask: This is a mask that lets the user only trace - on specified CPUS. The format is a hex string - representing the CPUS. - - set_ftrace_filter: When dynamic ftrace is configured in (see the - section below "dynamic ftrace"), the code is dynamically - modified (code text rewrite) to disable calling of the - function profiler (mcount). This lets tracing be configured - in with practically no overhead in performance. This also - has a side effect of enabling or disabling specific functions - to be traced. Echoing names of functions into this file - will limit the trace to only those functions. - - set_ftrace_notrace: This has an effect opposite to that of - set_ftrace_filter. Any function that is added here will not - be traced. If a function exists in both set_ftrace_filter - and set_ftrace_notrace, the function will _not_ be traced. - - set_ftrace_pid: Have the function tracer only trace a single thread. - - available_filter_functions: This lists the functions that ftrace - has processed and can trace. These are the function - names that you can pass to "set_ftrace_filter" or - "set_ftrace_notrace". (See the section "dynamic ftrace" - below for more details.) + current_tracer: + + This is used to set or display the current tracer + that is configured. + + available_tracers: + + This holds the different types of tracers that + have been compiled into the kernel. The + tracers listed here can be configured by + echoing their name into current_tracer. + + tracing_enabled: + + This sets or displays whether the current_tracer + is activated and tracing or not. Echo 0 into this + file to disable the tracer or 1 to enable it. + + trace: + + This file holds the output of the trace in a human + readable format (described below). + + latency_trace: + + This file shows the same trace but the information + is organized more to display possible latencies + in the system (described below). + + trace_pipe: + + The output is the same as the "trace" file but this + file is meant to be streamed with live tracing. + Reads from this file will block until new data + is retrieved. Unlike the "trace" and "latency_trace" + files, this file is a consumer. This means reading + from this file causes sequential reads to display + more current data. Once data is read from this + file, it is consumed, and will not be read + again with a sequential read. The "trace" and + "latency_trace" files are static, and if the + tracer is not adding more data, they will display + the same information every time they are read. + + trace_options: + + This file lets the user control the amount of data + that is displayed in one of the above output + files. + + tracing_max_latency: + + Some of the tracers record the max latency. + For example, the time interrupts are disabled. + This time is saved in this file. The max trace + will also be stored, and displayed by either + "trace" or "latency_trace". A new max trace will + only be recorded if the latency is greater than + the value in this file. (in microseconds) + + buffer_size_kb: + + This sets or displays the number of kilobytes each CPU + buffer can hold. The tracer buffers are the same size + for each CPU. The displayed number is the size of the + CPU buffer and not total size of all buffers. The + trace buffers are allocated in pages (blocks of memory + that the kernel uses for allocation, usually 4 KB in size). + If the last page allocated has room for more bytes + than requested, the rest of the page will be used, + making the actual allocation bigger than requested. + ( Note, the size may not be a multiple of the page size + due to buffer managment overhead. ) + + This can only be updated when the current_tracer + is set to "nop". + + tracing_cpumask: + + This is a mask that lets the user only trace + on specified CPUS. The format is a hex string + representing the CPUS. + + set_ftrace_filter: + + When dynamic ftrace is configured in (see the + section below "dynamic ftrace"), the code is dynamically + modified (code text rewrite) to disable calling of the + function profiler (mcount). This lets tracing be configured + in with practically no overhead in performance. This also + has a side effect of enabling or disabling specific functions + to be traced. Echoing names of functions into this file + will limit the trace to only those functions. + + set_ftrace_notrace: + + This has an effect opposite to that of + set_ftrace_filter. Any function that is added here will not + be traced. If a function exists in both set_ftrace_filter + and set_ftrace_notrace, the function will _not_ be traced. + + set_ftrace_pid: + + Have the function tracer only trace a single thread. + + set_graph_function: + + Set a "trigger" function where tracing should start + with the function graph tracer (See the section + "dynamic ftrace" for more details). + + available_filter_functions: + + This lists the functions that ftrace + has processed and can trace. These are the function + names that you can pass to "set_ftrace_filter" or + "set_ftrace_notrace". (See the section "dynamic ftrace" + below for more details.) The Tracers @@ -141,36 +175,66 @@ The Tracers Here is the list of current tracers that may be configured. - function - function tracer that uses mcount to trace all functions. + "function" + + Function call tracer to trace all kernel functions. + + "function_graph_tracer" + + Similar to the function tracer except that the + function tracer probes the functions on their entry + whereas the function graph tracer traces on both entry + and exit of the functions. It then provides the ability + to draw a graph of function calls similar to C code + source. + + "sched_switch" + + Traces the context switches and wakeups between tasks. + + "irqsoff" + + Traces the areas that disable interrupts and saves + the trace with the longest max latency. + See tracing_max_latency. When a new max is recorded, + it replaces the old trace. It is best to view this + trace via the latency_trace file. + + "preemptoff" + + Similar to irqsoff but traces and records the amount of + time for which preemption is disabled. + + "preemptirqsoff" - sched_switch - traces the context switches between tasks. + Similar to irqsoff and preemptoff, but traces and + records the largest time for which irqs and/or preemption + is disabled. - irqsoff - traces the areas that disable interrupts and saves - the trace with the longest max latency. - See tracing_max_latency. When a new max is recorded, - it replaces the old trace. It is best to view this - trace via the latency_trace file. + "wakeup" - preemptoff - Similar to irqsoff but traces and records the amount of - time for which preemption is disabled. + Traces and records the max latency that it takes for + the highest priority task to get scheduled after + it has been woken up. - preemptirqsoff - Similar to irqsoff and preemptoff, but traces and - records the largest time for which irqs and/or preemption - is disabled. + "hw-branch-tracer" - wakeup - Traces and records the max latency that it takes for - the highest priority task to get scheduled after - it has been woken up. + Uses the BTS CPU feature on x86 CPUs to traces all + branches executed. - nop - This is not a tracer. To remove all tracers from tracing - simply echo "nop" into current_tracer. + "nop" + + This is the "trace nothing" tracer. To remove all + tracers from tracing simply echo "nop" into + current_tracer. Examples of using the tracer ---------------------------- -Here are typical examples of using the tracers when controlling them only -with the debugfs interface (without using any user-land utilities). +Here are typical examples of using the tracers when controlling +them only with the debugfs interface (without using any +user-land utilities). Output format: -------------- @@ -187,16 +251,16 @@ Here is an example of the output format of the file "trace" bash-4251 [01] 10152.583855: _atomic_dec_and_lock <-dput -------- -A header is printed with the tracer name that is represented by the trace. -In this case the tracer is "function". Then a header showing the format. Task -name "bash", the task PID "4251", the CPU that it was running on -"01", the timestamp in . format, the function name that was -traced "path_put" and the parent function that called this function -"path_walk". The timestamp is the time at which the function was -entered. +A header is printed with the tracer name that is represented by +the trace. In this case the tracer is "function". Then a header +showing the format. Task name "bash", the task PID "4251", the +CPU that it was running on "01", the timestamp in . +format, the function name that was traced "path_put" and the +parent function that called this function "path_walk". The +timestamp is the time at which the function was entered. -The sched_switch tracer also includes tracing of task wakeups and -context switches. +The sched_switch tracer also includes tracing of task wakeups +and context switches. ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 2916:115:S ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 10:115:S @@ -205,8 +269,8 @@ context switches. kondemand/1-2916 [01] 1453.070013: 2916:115:S ==> 7:115:R ksoftirqd/1-7 [01] 1453.070013: 7:115:S ==> 0:140:R -Wake ups are represented by a "+" and the context switches are shown as -"==>". The format is: +Wake ups are represented by a "+" and the context switches are +shown as "==>". The format is: Context switches: @@ -220,19 +284,20 @@ Wake ups are represented by a "+" and the context switches are shown as :: + :: -The prio is the internal kernel priority, which is the inverse of the -priority that is usually displayed by user-space tools. Zero represents -the highest priority (99). Prio 100 starts the "nice" priorities with -100 being equal to nice -20 and 139 being nice 19. The prio "140" is -reserved for the idle task which is the lowest priority thread (pid 0). +The prio is the internal kernel priority, which is the inverse +of the priority that is usually displayed by user-space tools. +Zero represents the highest priority (99). Prio 100 starts the +"nice" priorities with 100 being equal to nice -20 and 139 being +nice 19. The prio "140" is reserved for the idle task which is +the lowest priority thread (pid 0). Latency trace format -------------------- -For traces that display latency times, the latency_trace file gives -somewhat more information to see why a latency happened. Here is a typical -trace. +For traces that display latency times, the latency_trace file +gives somewhat more information to see why a latency happened. +Here is a typical trace. # tracer: irqsoff # @@ -259,20 +324,20 @@ irqsoff latency trace v1.1.5 on 2.6.26-rc8 -0 0d.s1 98us : trace_hardirqs_on (do_softirq) +This shows that the current tracer is "irqsoff" tracing the time +for which interrupts were disabled. It gives the trace version +and the version of the kernel upon which this was executed on +(2.6.26-rc8). Then it displays the max latency in microsecs (97 +us). The number of trace entries displayed and the total number +recorded (both are three: #3/3). The type of preemption that was +used (PREEMPT). VP, KP, SP, and HP are always zero and are +reserved for later use. #P is the number of online CPUS (#P:2). -This shows that the current tracer is "irqsoff" tracing the time for which -interrupts were disabled. It gives the trace version and the version -of the kernel upon which this was executed on (2.6.26-rc8). Then it displays -the max latency in microsecs (97 us). The number of trace entries displayed -and the total number recorded (both are three: #3/3). The type of -preemption that was used (PREEMPT). VP, KP, SP, and HP are always zero -and are reserved for later use. #P is the number of online CPUS (#P:2). - -The task is the process that was running when the latency occurred. -(swapper pid: 0). +The task is the process that was running when the latency +occurred. (swapper pid: 0). -The start and stop (the functions in which the interrupts were disabled and -enabled respectively) that caused the latencies: +The start and stop (the functions in which the interrupts were +disabled and enabled respectively) that caused the latencies: apic_timer_interrupt is where the interrupts were disabled. do_softirq is where they were enabled again. @@ -308,12 +373,12 @@ The above is mostly meaningful for kernel developers. latency_trace file is relative to the start of the trace. delay: This is just to help catch your eye a bit better. And - needs to be fixed to be only relative to the same CPU. - The marks are determined by the difference between this - current trace and the next trace. - '!' - greater than preempt_mark_thresh (default 100) - '+' - greater than 1 microsecond - ' ' - less than or equal to 1 microsecond. + needs to be fixed to be only relative to the same CPU. + The marks are determined by the difference between this + current trace and the next trace. + '!' - greater than preempt_mark_thresh (default 100) + '+' - greater than 1 microsecond + ' ' - less than or equal to 1 microsecond. The rest is the same as the 'trace' file. @@ -321,14 +386,15 @@ The above is mostly meaningful for kernel developers. trace_options ------------- -The trace_options file is used to control what gets printed in the trace -output. To see what is available, simply cat the file: +The trace_options file is used to control what gets printed in +the trace output. To see what is available, simply cat the file: cat /debug/tracing/trace_options print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \ - noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj + noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj -To disable one of the options, echo in the option prepended with "no". +To disable one of the options, echo in the option prepended with +"no". echo noprint-parent > /debug/tracing/trace_options @@ -338,8 +404,8 @@ To enable an option, leave off the "no". Here are the available options: - print-parent - On function traces, display the calling function - as well as the function being traced. + print-parent - On function traces, display the calling (parent) + function as well as the function being traced. print-parent: bash-4000 [01] 1477.606694: simple_strtoul <-strict_strtoul @@ -348,15 +414,16 @@ Here are the available options: bash-4000 [01] 1477.606694: simple_strtoul - sym-offset - Display not only the function name, but also the offset - in the function. For example, instead of seeing just - "ktime_get", you will see "ktime_get+0xb/0x20". + sym-offset - Display not only the function name, but also the + offset in the function. For example, instead of + seeing just "ktime_get", you will see + "ktime_get+0xb/0x20". sym-offset: bash-4000 [01] 1477.606694: simple_strtoul+0x6/0xa0 - sym-addr - this will also display the function address as well as - the function name. + sym-addr - this will also display the function address as well + as the function name. sym-addr: bash-4000 [01] 1477.606694: simple_strtoul @@ -366,35 +433,41 @@ Here are the available options: bash 4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \ (+0.000ms): simple_strtoul (strict_strtoul) - raw - This will display raw numbers. This option is best for use with - user applications that can translate the raw numbers better than - having it done in the kernel. + raw - This will display raw numbers. This option is best for + use with user applications that can translate the raw + numbers better than having it done in the kernel. - hex - Similar to raw, but the numbers will be in a hexadecimal format. + hex - Similar to raw, but the numbers will be in a hexadecimal + format. bin - This will print out the formats in raw binary. block - TBD (needs update) - stacktrace - This is one of the options that changes the trace itself. - When a trace is recorded, so is the stack of functions. - This allows for back traces of trace sites. + stacktrace - This is one of the options that changes the trace + itself. When a trace is recorded, so is the stack + of functions. This allows for back traces of + trace sites. - userstacktrace - This option changes the trace. - It records a stacktrace of the current userspace thread. + userstacktrace - This option changes the trace. It records a + stacktrace of the current userspace thread. - sym-userobj - when user stacktrace are enabled, look up which object the - address belongs to, and print a relative address - This is especially useful when ASLR is on, otherwise you don't - get a chance to resolve the address to object/file/line after the app is no - longer running + sym-userobj - when user stacktrace are enabled, look up which + object the address belongs to, and print a + relative address. This is especially useful when + ASLR is on, otherwise you don't get a chance to + resolve the address to object/file/line after + the app is no longer running - The lookup is performed when you read trace,trace_pipe,latency_trace. Example: + The lookup is performed when you read + trace,trace_pipe,latency_trace. Example: a.out-1623 [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0 x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] - sched-tree - TBD (any users??) + sched-tree - trace all tasks that are on the runqueue, at + every scheduling event. Will add overhead if + there's a lot of tasks running at once. sched_switch @@ -431,18 +504,19 @@ of how to use it. [...] -As we have discussed previously about this format, the header shows -the name of the trace and points to the options. The "FUNCTION" -is a misnomer since here it represents the wake ups and context -switches. +As we have discussed previously about this format, the header +shows the name of the trace and points to the options. The +"FUNCTION" is a misnomer since here it represents the wake ups +and context switches. -The sched_switch file only lists the wake ups (represented with '+') -and context switches ('==>') with the previous task or current task -first followed by the next task or task waking up. The format for both -of these is PID:KERNEL-PRIO:TASK-STATE. Remember that the KERNEL-PRIO -is the inverse of the actual priority with zero (0) being the highest -priority and the nice values starting at 100 (nice -20). Below is -a quick chart to map the kernel priority to user land priorities. +The sched_switch file only lists the wake ups (represented with +'+') and context switches ('==>') with the previous task or +current task first followed by the next task or task waking up. +The format for both of these is PID:KERNEL-PRIO:TASK-STATE. +Remember that the KERNEL-PRIO is the inverse of the actual +priority with zero (0) being the highest priority and the nice +values starting at 100 (nice -20). Below is a quick chart to map +the kernel priority to user land priorities. Kernel priority: 0 to 99 ==> user RT priority 99 to 0 Kernel priority: 100 to 139 ==> user nice -20 to 19 @@ -463,10 +537,10 @@ The task states are: ftrace_enabled -------------- -The following tracers (listed below) give different output depending -on whether or not the sysctl ftrace_enabled is set. To set ftrace_enabled, -one can either use the sysctl function or set it via the proc -file system interface. +The following tracers (listed below) give different output +depending on whether or not the sysctl ftrace_enabled is set. To +set ftrace_enabled, one can either use the sysctl function or +set it via the proc file system interface. sysctl kernel.ftrace_enabled=1 @@ -474,12 +548,12 @@ file system interface. echo 1 > /proc/sys/kernel/ftrace_enabled -To disable ftrace_enabled simply replace the '1' with '0' in -the above commands. +To disable ftrace_enabled simply replace the '1' with '0' in the +above commands. -When ftrace_enabled is set the tracers will also record the functions -that are within the trace. The descriptions of the tracers -will also show an example with ftrace enabled. +When ftrace_enabled is set the tracers will also record the +functions that are within the trace. The descriptions of the +tracers will also show an example with ftrace enabled. irqsoff @@ -487,17 +561,18 @@ irqsoff When interrupts are disabled, the CPU can not react to any other external event (besides NMIs and SMIs). This prevents the timer -interrupt from triggering or the mouse interrupt from letting the -kernel know of a new mouse event. The result is a latency with the -reaction time. +interrupt from triggering or the mouse interrupt from letting +the kernel know of a new mouse event. The result is a latency +with the reaction time. -The irqsoff tracer tracks the time for which interrupts are disabled. -When a new maximum latency is hit, the tracer saves the trace leading up -to that latency point so that every time a new maximum is reached, the old -saved trace is discarded and the new trace is saved. +The irqsoff tracer tracks the time for which interrupts are +disabled. When a new maximum latency is hit, the tracer saves +the trace leading up to that latency point so that every time a +new maximum is reached, the old saved trace is discarded and the +new trace is saved. -To reset the maximum, echo 0 into tracing_max_latency. Here is an -example: +To reset the maximum, echo 0 into tracing_max_latency. Here is +an example: # echo irqsoff > /debug/tracing/current_tracer # echo 0 > /debug/tracing/tracing_max_latency @@ -532,10 +607,11 @@ irqsoff latency trace v1.1.5 on 2.6.26 Here we see that that we had a latency of 12 microsecs (which is -very good). The _write_lock_irq in sys_setpgid disabled interrupts. -The difference between the 12 and the displayed timestamp 14us occurred -because the clock was incremented between the time of recording the max -latency and the time of recording the function that had that latency. +very good). The _write_lock_irq in sys_setpgid disabled +interrupts. The difference between the 12 and the displayed +timestamp 14us occurred because the clock was incremented +between the time of recording the max latency and the time of +recording the function that had that latency. Note the above example had ftrace_enabled not set. If we set the ftrace_enabled, we get a much larger output: @@ -586,24 +662,24 @@ irqsoff latency trace v1.1.5 on 2.6.26-rc8 Here we traced a 50 microsecond latency. But we also see all the -functions that were called during that time. Note that by enabling -function tracing, we incur an added overhead. This overhead may -extend the latency times. But nevertheless, this trace has provided -some very helpful debugging information. +functions that were called during that time. Note that by +enabling function tracing, we incur an added overhead. This +overhead may extend the latency times. But nevertheless, this +trace has provided some very helpful debugging information. preemptoff ---------- -When preemption is disabled, we may be able to receive interrupts but -the task cannot be preempted and a higher priority task must wait -for preemption to be enabled again before it can preempt a lower -priority task. +When preemption is disabled, we may be able to receive +interrupts but the task cannot be preempted and a higher +priority task must wait for preemption to be enabled again +before it can preempt a lower priority task. The preemptoff tracer traces the places that disable preemption. -Like the irqsoff tracer, it records the maximum latency for which preemption -was disabled. The control of preemptoff tracer is much like the irqsoff -tracer. +Like the irqsoff tracer, it records the maximum latency for +which preemption was disabled. The control of preemptoff tracer +is much like the irqsoff tracer. # echo preemptoff > /debug/tracing/current_tracer # echo 0 > /debug/tracing/tracing_max_latency @@ -637,11 +713,12 @@ preemptoff latency trace v1.1.5 on 2.6.26-rc8 sshd-4261 0d.s1 30us : trace_preempt_on (__do_softirq) -This has some more changes. Preemption was disabled when an interrupt -came in (notice the 'h'), and was enabled while doing a softirq. -(notice the 's'). But we also see that interrupts have been disabled -when entering the preempt off section and leaving it (the 'd'). -We do not know if interrupts were enabled in the mean time. +This has some more changes. Preemption was disabled when an +interrupt came in (notice the 'h'), and was enabled while doing +a softirq. (notice the 's'). But we also see that interrupts +have been disabled when entering the preempt off section and +leaving it (the 'd'). We do not know if interrupts were enabled +in the mean time. # tracer: preemptoff # @@ -700,28 +777,30 @@ preemptoff latency trace v1.1.5 on 2.6.26-rc8 sshd-4261 0d.s1 64us : trace_preempt_on (__do_softirq) -The above is an example of the preemptoff trace with ftrace_enabled -set. Here we see that interrupts were disabled the entire time. -The irq_enter code lets us know that we entered an interrupt 'h'. -Before that, the functions being traced still show that it is not -in an interrupt, but we can see from the functions themselves that -this is not the case. +The above is an example of the preemptoff trace with +ftrace_enabled set. Here we see that interrupts were disabled +the entire time. The irq_enter code lets us know that we entered +an interrupt 'h'. Before that, the functions being traced still +show that it is not in an interrupt, but we can see from the +functions themselves that this is not the case. -Notice that __do_softirq when called does not have a preempt_count. -It may seem that we missed a preempt enabling. What really happened -is that the preempt count is held on the thread's stack and we -switched to the softirq stack (4K stacks in effect). The code -does not copy the preempt count, but because interrupts are disabled, -we do not need to worry about it. Having a tracer like this is good -for letting people know what really happens inside the kernel. +Notice that __do_softirq when called does not have a +preempt_count. It may seem that we missed a preempt enabling. +What really happened is that the preempt count is held on the +thread's stack and we switched to the softirq stack (4K stacks +in effect). The code does not copy the preempt count, but +because interrupts are disabled, we do not need to worry about +it. Having a tracer like this is good for letting people know +what really happens inside the kernel. preemptirqsoff -------------- -Knowing the locations that have interrupts disabled or preemption -disabled for the longest times is helpful. But sometimes we would -like to know when either preemption and/or interrupts are disabled. +Knowing the locations that have interrupts disabled or +preemption disabled for the longest times is helpful. But +sometimes we would like to know when either preemption and/or +interrupts are disabled. Consider the following code: @@ -741,11 +820,13 @@ The preemptoff tracer will record the total length of call_function_with_irqs_and_preemption_off() and call_function_with_preemption_off(). -But neither will trace the time that interrupts and/or preemption -is disabled. This total time is the time that we can not schedule. -To record this time, use the preemptirqsoff tracer. +But neither will trace the time that interrupts and/or +preemption is disabled. This total time is the time that we can +not schedule. To record this time, use the preemptirqsoff +tracer. -Again, using this trace is much like the irqsoff and preemptoff tracers. +Again, using this trace is much like the irqsoff and preemptoff +tracers. # echo preemptirqsoff > /debug/tracing/current_tracer # echo 0 > /debug/tracing/tracing_max_latency @@ -781,9 +862,10 @@ preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 The trace_hardirqs_off_thunk is called from assembly on x86 when -interrupts are disabled in the assembly code. Without the function -tracing, we do not know if interrupts were enabled within the preemption -points. We do see that it started with preemption enabled. +interrupts are disabled in the assembly code. Without the +function tracing, we do not know if interrupts were enabled +within the preemption points. We do see that it started with +preemption enabled. Here is a trace with ftrace_enabled set: @@ -871,40 +953,42 @@ preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 sshd-4261 0d.s1 105us : trace_preempt_on (__do_softirq) -This is a very interesting trace. It started with the preemption of -the ls task. We see that the task had the "need_resched" bit set -via the 'N' in the trace. Interrupts were disabled before the spin_lock -at the beginning of the trace. We see that a schedule took place to run -sshd. When the interrupts were enabled, we took an interrupt. -On return from the interrupt handler, the softirq ran. We took another -interrupt while running the softirq as we see from the capital 'H'. +This is a very interesting trace. It started with the preemption +of the ls task. We see that the task had the "need_resched" bit +set via the 'N' in the trace. Interrupts were disabled before +the spin_lock at the beginning of the trace. We see that a +schedule took place to run sshd. When the interrupts were +enabled, we took an interrupt. On return from the interrupt +handler, the softirq ran. We took another interrupt while +running the softirq as we see from the capital 'H'. wakeup ------ -In a Real-Time environment it is very important to know the wakeup -time it takes for the highest priority task that is woken up to the -time that it executes. This is also known as "schedule latency". -I stress the point that this is about RT tasks. It is also important -to know the scheduling latency of non-RT tasks, but the average -schedule latency is better for non-RT tasks. Tools like -LatencyTop are more appropriate for such measurements. +In a Real-Time environment it is very important to know the +wakeup time it takes for the highest priority task that is woken +up to the time that it executes. This is also known as "schedule +latency". I stress the point that this is about RT tasks. It is +also important to know the scheduling latency of non-RT tasks, +but the average schedule latency is better for non-RT tasks. +Tools like LatencyTop are more appropriate for such +measurements. Real-Time environments are interested in the worst case latency. -That is the longest latency it takes for something to happen, and -not the average. We can have a very fast scheduler that may only -have a large latency once in a while, but that would not work well -with Real-Time tasks. The wakeup tracer was designed to record -the worst case wakeups of RT tasks. Non-RT tasks are not recorded -because the tracer only records one worst case and tracing non-RT -tasks that are unpredictable will overwrite the worst case latency -of RT tasks. - -Since this tracer only deals with RT tasks, we will run this slightly -differently than we did with the previous tracers. Instead of performing -an 'ls', we will run 'sleep 1' under 'chrt' which changes the -priority of the task. +That is the longest latency it takes for something to happen, +and not the average. We can have a very fast scheduler that may +only have a large latency once in a while, but that would not +work well with Real-Time tasks. The wakeup tracer was designed +to record the worst case wakeups of RT tasks. Non-RT tasks are +not recorded because the tracer only records one worst case and +tracing non-RT tasks that are unpredictable will overwrite the +worst case latency of RT tasks. + +Since this tracer only deals with RT tasks, we will run this +slightly differently than we did with the previous tracers. +Instead of performing an 'ls', we will run 'sleep 1' under +'chrt' which changes the priority of the task. # echo wakeup > /debug/tracing/current_tracer # echo 0 > /debug/tracing/tracing_max_latency @@ -934,17 +1018,16 @@ wakeup latency trace v1.1.5 on 2.6.26-rc8 -0 1d..4 4us : schedule (cpu_idle) +Running this on an idle system, we see that it only took 4 +microseconds to perform the task switch. Note, since the trace +marker in the schedule is before the actual "switch", we stop +the tracing when the recorded task is about to schedule in. This +may change if we add a new marker at the end of the scheduler. -Running this on an idle system, we see that it only took 4 microseconds -to perform the task switch. Note, since the trace marker in the -schedule is before the actual "switch", we stop the tracing when -the recorded task is about to schedule in. This may change if -we add a new marker at the end of the scheduler. - -Notice that the recorded task is 'sleep' with the PID of 4901 and it -has an rt_prio of 5. This priority is user-space priority and not -the internal kernel priority. The policy is 1 for SCHED_FIFO and 2 -for SCHED_RR. +Notice that the recorded task is 'sleep' with the PID of 4901 +and it has an rt_prio of 5. This priority is user-space priority +and not the internal kernel priority. The policy is 1 for +SCHED_FIFO and 2 for SCHED_RR. Doing the same with chrt -r 5 and ftrace_enabled set. @@ -1001,24 +1084,25 @@ ksoftirq-7 1d..6 49us : _spin_unlock (tracing_record_cmdline) ksoftirq-7 1d..6 49us : sub_preempt_count (_spin_unlock) ksoftirq-7 1d..4 50us : schedule (__cond_resched) -The interrupt went off while running ksoftirqd. This task runs at -SCHED_OTHER. Why did not we see the 'N' set early? This may be -a harmless bug with x86_32 and 4K stacks. On x86_32 with 4K stacks -configured, the interrupt and softirq run with their own stack. -Some information is held on the top of the task's stack (need_resched -and preempt_count are both stored there). The setting of the NEED_RESCHED -bit is done directly to the task's stack, but the reading of the -NEED_RESCHED is done by looking at the current stack, which in this case -is the stack for the hard interrupt. This hides the fact that NEED_RESCHED -has been set. We do not see the 'N' until we switch back to the task's +The interrupt went off while running ksoftirqd. This task runs +at SCHED_OTHER. Why did not we see the 'N' set early? This may +be a harmless bug with x86_32 and 4K stacks. On x86_32 with 4K +stacks configured, the interrupt and softirq run with their own +stack. Some information is held on the top of the task's stack +(need_resched and preempt_count are both stored there). The +setting of the NEED_RESCHED bit is done directly to the task's +stack, but the reading of the NEED_RESCHED is done by looking at +the current stack, which in this case is the stack for the hard +interrupt. This hides the fact that NEED_RESCHED has been set. +We do not see the 'N' until we switch back to the task's assigned stack. function -------- This tracer is the function tracer. Enabling the function tracer -can be done from the debug file system. Make sure the ftrace_enabled is -set; otherwise this tracer is a nop. +can be done from the debug file system. Make sure the +ftrace_enabled is set; otherwise this tracer is a nop. # sysctl kernel.ftrace_enabled=1 # echo function > /debug/tracing/current_tracer @@ -1048,14 +1132,15 @@ set; otherwise this tracer is a nop. [...] -Note: function tracer uses ring buffers to store the above entries. -The newest data may overwrite the oldest data. Sometimes using echo to -stop the trace is not sufficient because the tracing could have overwritten -the data that you wanted to record. For this reason, it is sometimes better to -disable tracing directly from a program. This allows you to stop the -tracing at the point that you hit the part that you are interested in. -To disable the tracing directly from a C program, something like following -code snippet can be used: +Note: function tracer uses ring buffers to store the above +entries. The newest data may overwrite the oldest data. +Sometimes using echo to stop the trace is not sufficient because +the tracing could have overwritten the data that you wanted to +record. For this reason, it is sometimes better to disable +tracing directly from a program. This allows you to stop the +tracing at the point that you hit the part that you are +interested in. To disable the tracing directly from a C program, +something like following code snippet can be used: int trace_fd; [...] @@ -1070,10 +1155,10 @@ int main(int argc, char *argv[]) { } Note: Here we hard coded the path name. The debugfs mount is not -guaranteed to be at /debug (and is more commonly at /sys/kernel/debug). -For simple one time traces, the above is sufficent. For anything else, -a search through /proc/mounts may be needed to find where the debugfs -file-system is mounted. +guaranteed to be at /debug (and is more commonly at +/sys/kernel/debug). For simple one time traces, the above is +sufficent. For anything else, a search through /proc/mounts may +be needed to find where the debugfs file-system is mounted. Single thread tracing @@ -1152,49 +1237,297 @@ int main (int argc, char **argv) return 0; } + +hw-branch-tracer (x86 only) +--------------------------- + +This tracer uses the x86 last branch tracing hardware feature to +collect a branch trace on all cpus with relatively low overhead. + +The tracer uses a fixed-size circular buffer per cpu and only +traces ring 0 branches. The trace file dumps that buffer in the +following format: + +# tracer: hw-branch-tracer +# +# CPU# TO <- FROM + 0 scheduler_tick+0xb5/0x1bf <- task_tick_idle+0x5/0x6 + 2 run_posix_cpu_timers+0x2b/0x72a <- run_posix_cpu_timers+0x25/0x72a + 0 scheduler_tick+0x139/0x1bf <- scheduler_tick+0xed/0x1bf + 0 scheduler_tick+0x17c/0x1bf <- scheduler_tick+0x148/0x1bf + 2 run_posix_cpu_timers+0x9e/0x72a <- run_posix_cpu_timers+0x5e/0x72a + 0 scheduler_tick+0x1b6/0x1bf <- scheduler_tick+0x1aa/0x1bf + + +The tracer may be used to dump the trace for the oops'ing cpu on +a kernel oops into the system log. To enable this, +ftrace_dump_on_oops must be set. To set ftrace_dump_on_oops, one +can either use the sysctl function or set it via the proc system +interface. + + sysctl kernel.ftrace_dump_on_oops=1 + +or + + echo 1 > /proc/sys/kernel/ftrace_dump_on_oops + + +Here's an example of such a dump after a null pointer +dereference in a kernel module: + +[57848.105921] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 +[57848.106019] IP: [] open+0x6/0x14 [oops] +[57848.106019] PGD 2354e9067 PUD 2375e7067 PMD 0 +[57848.106019] Oops: 0002 [#1] SMP +[57848.106019] last sysfs file: /sys/devices/pci0000:00/0000:00:1e.0/0000:20:05.0/local_cpus +[57848.106019] Dumping ftrace buffer: +[57848.106019] --------------------------------- +[...] +[57848.106019] 0 chrdev_open+0xe6/0x165 <- cdev_put+0x23/0x24 +[57848.106019] 0 chrdev_open+0x117/0x165 <- chrdev_open+0xfa/0x165 +[57848.106019] 0 chrdev_open+0x120/0x165 <- chrdev_open+0x11c/0x165 +[57848.106019] 0 chrdev_open+0x134/0x165 <- chrdev_open+0x12b/0x165 +[57848.106019] 0 open+0x0/0x14 [oops] <- chrdev_open+0x144/0x165 +[57848.106019] 0 page_fault+0x0/0x30 <- open+0x6/0x14 [oops] +[57848.106019] 0 error_entry+0x0/0x5b <- page_fault+0x4/0x30 +[57848.106019] 0 error_kernelspace+0x0/0x31 <- error_entry+0x59/0x5b +[57848.106019] 0 error_sti+0x0/0x1 <- error_kernelspace+0x2d/0x31 +[57848.106019] 0 page_fault+0x9/0x30 <- error_sti+0x0/0x1 +[57848.106019] 0 do_page_fault+0x0/0x881 <- page_fault+0x1a/0x30 +[...] +[57848.106019] 0 do_page_fault+0x66b/0x881 <- is_prefetch+0x1ee/0x1f2 +[57848.106019] 0 do_page_fault+0x6e0/0x881 <- do_page_fault+0x67a/0x881 +[57848.106019] 0 oops_begin+0x0/0x96 <- do_page_fault+0x6e0/0x881 +[57848.106019] 0 trace_hw_branch_oops+0x0/0x2d <- oops_begin+0x9/0x96 +[...] +[57848.106019] 0 ds_suspend_bts+0x2a/0xe3 <- ds_suspend_bts+0x1a/0xe3 +[57848.106019] --------------------------------- +[57848.106019] CPU 0 +[57848.106019] Modules linked in: oops +[57848.106019] Pid: 5542, comm: cat Tainted: G W 2.6.28 #23 +[57848.106019] RIP: 0010:[] [] open+0x6/0x14 [oops] +[57848.106019] RSP: 0018:ffff880235457d48 EFLAGS: 00010246 +[...] + + +function graph tracer +--------------------------- + +This tracer is similar to the function tracer except that it +probes a function on its entry and its exit. This is done by +using a dynamically allocated stack of return addresses in each +task_struct. On function entry the tracer overwrites the return +address of each function traced to set a custom probe. Thus the +original return address is stored on the stack of return address +in the task_struct. + +Probing on both ends of a function leads to special features +such as: + +- measure of a function's time execution +- having a reliable call stack to draw function calls graph + +This tracer is useful in several situations: + +- you want to find the reason of a strange kernel behavior and + need to see what happens in detail on any areas (or specific + ones). + +- you are experiencing weird latencies but it's difficult to + find its origin. + +- you want to find quickly which path is taken by a specific + function + +- you just want to peek inside a working kernel and want to see + what happens there. + +# tracer: function_graph +# +# CPU DURATION FUNCTION CALLS +# | | | | | | | + + 0) | sys_open() { + 0) | do_sys_open() { + 0) | getname() { + 0) | kmem_cache_alloc() { + 0) 1.382 us | __might_sleep(); + 0) 2.478 us | } + 0) | strncpy_from_user() { + 0) | might_fault() { + 0) 1.389 us | __might_sleep(); + 0) 2.553 us | } + 0) 3.807 us | } + 0) 7.876 us | } + 0) | alloc_fd() { + 0) 0.668 us | _spin_lock(); + 0) 0.570 us | expand_files(); + 0) 0.586 us | _spin_unlock(); + + +There are several columns that can be dynamically +enabled/disabled. You can use every combination of options you +want, depending on your needs. + +- The cpu number on which the function executed is default + enabled. It is sometimes better to only trace one cpu (see + tracing_cpu_mask file) or you might sometimes see unordered + function calls while cpu tracing switch. + + hide: echo nofuncgraph-cpu > /debug/tracing/trace_options + show: echo funcgraph-cpu > /debug/tracing/trace_options + +- The duration (function's time of execution) is displayed on + the closing bracket line of a function or on the same line + than the current function in case of a leaf one. It is default + enabled. + + hide: echo nofuncgraph-duration > /debug/tracing/trace_options + show: echo funcgraph-duration > /debug/tracing/trace_options + +- The overhead field precedes the duration field in case of + reached duration thresholds. + + hide: echo nofuncgraph-overhead > /debug/tracing/trace_options + show: echo funcgraph-overhead > /debug/tracing/trace_options + depends on: funcgraph-duration + + ie: + + 0) | up_write() { + 0) 0.646 us | _spin_lock_irqsave(); + 0) 0.684 us | _spin_unlock_irqrestore(); + 0) 3.123 us | } + 0) 0.548 us | fput(); + 0) + 58.628 us | } + + [...] + + 0) | putname() { + 0) | kmem_cache_free() { + 0) 0.518 us | __phys_addr(); + 0) 1.757 us | } + 0) 2.861 us | } + 0) ! 115.305 us | } + 0) ! 116.402 us | } + + + means that the function exceeded 10 usecs. + ! means that the function exceeded 100 usecs. + + +- The task/pid field displays the thread cmdline and pid which + executed the function. It is default disabled. + + hide: echo nofuncgraph-proc > /debug/tracing/trace_options + show: echo funcgraph-proc > /debug/tracing/trace_options + + ie: + + # tracer: function_graph + # + # CPU TASK/PID DURATION FUNCTION CALLS + # | | | | | | | | | + 0) sh-4802 | | d_free() { + 0) sh-4802 | | call_rcu() { + 0) sh-4802 | | __call_rcu() { + 0) sh-4802 | 0.616 us | rcu_process_gp_end(); + 0) sh-4802 | 0.586 us | check_for_new_grace_period(); + 0) sh-4802 | 2.899 us | } + 0) sh-4802 | 4.040 us | } + 0) sh-4802 | 5.151 us | } + 0) sh-4802 | + 49.370 us | } + + +- The absolute time field is an absolute timestamp given by the + system clock since it started. A snapshot of this time is + given on each entry/exit of functions + + hide: echo nofuncgraph-abstime > /debug/tracing/trace_options + show: echo funcgraph-abstime > /debug/tracing/trace_options + + ie: + + # + # TIME CPU DURATION FUNCTION CALLS + # | | | | | | | | + 360.774522 | 1) 0.541 us | } + 360.774522 | 1) 4.663 us | } + 360.774523 | 1) 0.541 us | __wake_up_bit(); + 360.774524 | 1) 6.796 us | } + 360.774524 | 1) 7.952 us | } + 360.774525 | 1) 9.063 us | } + 360.774525 | 1) 0.615 us | journal_mark_dirty(); + 360.774527 | 1) 0.578 us | __brelse(); + 360.774528 | 1) | reiserfs_prepare_for_journal() { + 360.774528 | 1) | unlock_buffer() { + 360.774529 | 1) | wake_up_bit() { + 360.774529 | 1) | bit_waitqueue() { + 360.774530 | 1) 0.594 us | __phys_addr(); + + +You can put some comments on specific functions by using +trace_printk() For example, if you want to put a comment inside +the __might_sleep() function, you just have to include + and call trace_printk() inside __might_sleep() + +trace_printk("I'm a comment!\n") + +will produce: + + 1) | __might_sleep() { + 1) | /* I'm a comment! */ + 1) 1.449 us | } + + +You might find other useful features for this tracer in the +following "dynamic ftrace" section such as tracing only specific +functions or tasks. + dynamic ftrace -------------- If CONFIG_DYNAMIC_FTRACE is set, the system will run with virtually no overhead when function tracing is disabled. The way this works is the mcount function call (placed at the start of -every kernel function, produced by the -pg switch in gcc), starts -of pointing to a simple return. (Enabling FTRACE will include the --pg switch in the compiling of the kernel.) +every kernel function, produced by the -pg switch in gcc), +starts of pointing to a simple return. (Enabling FTRACE will +include the -pg switch in the compiling of the kernel.) At compile time every C file object is run through the recordmcount.pl script (located in the scripts directory). This script will process the C object using objdump to find all the -locations in the .text section that call mcount. (Note, only -the .text section is processed, since processing other sections -like .init.text may cause races due to those sections being freed). +locations in the .text section that call mcount. (Note, only the +.text section is processed, since processing other sections like +.init.text may cause races due to those sections being freed). -A new section called "__mcount_loc" is created that holds references -to all the mcount call sites in the .text section. This section is -compiled back into the original object. The final linker will add -all these references into a single table. +A new section called "__mcount_loc" is created that holds +references to all the mcount call sites in the .text section. +This section is compiled back into the original object. The +final linker will add all these references into a single table. On boot up, before SMP is initialized, the dynamic ftrace code -scans this table and updates all the locations into nops. It also -records the locations, which are added to the available_filter_functions -list. Modules are processed as they are loaded and before they are -executed. When a module is unloaded, it also removes its functions from -the ftrace function list. This is automatic in the module unload -code, and the module author does not need to worry about it. - -When tracing is enabled, kstop_machine is called to prevent races -with the CPUS executing code being modified (which can cause the -CPU to do undesireable things), and the nops are patched back -to calls. But this time, they do not call mcount (which is just -a function stub). They now call into the ftrace infrastructure. +scans this table and updates all the locations into nops. It +also records the locations, which are added to the +available_filter_functions list. Modules are processed as they +are loaded and before they are executed. When a module is +unloaded, it also removes its functions from the ftrace function +list. This is automatic in the module unload code, and the +module author does not need to worry about it. + +When tracing is enabled, kstop_machine is called to prevent +races with the CPUS executing code being modified (which can +cause the CPU to do undesireable things), and the nops are +patched back to calls. But this time, they do not call mcount +(which is just a function stub). They now call into the ftrace +infrastructure. One special side-effect to the recording of the functions being traced is that we can now selectively choose which functions we -wish to trace and which ones we want the mcount calls to remain as -nops. +wish to trace and which ones we want the mcount calls to remain +as nops. -Two files are used, one for enabling and one for disabling the tracing -of specified functions. They are: +Two files are used, one for enabling and one for disabling the +tracing of specified functions. They are: set_ftrace_filter @@ -1202,8 +1535,8 @@ and set_ftrace_notrace -A list of available functions that you can add to these files is listed -in: +A list of available functions that you can add to these files is +listed in: available_filter_functions @@ -1240,8 +1573,8 @@ hrtimer_interrupt sys_nanosleep -Perhaps this is not enough. The filters also allow simple wild cards. -Only the following are currently available +Perhaps this is not enough. The filters also allow simple wild +cards. Only the following are currently available * - will match functions that begin with * - will match functions that end with @@ -1251,9 +1584,9 @@ These are the only wild cards which are supported. * will not work. -Note: It is better to use quotes to enclose the wild cards, otherwise - the shell may expand the parameters into names of files in the local - directory. +Note: It is better to use quotes to enclose the wild cards, + otherwise the shell may expand the parameters into names + of files in the local directory. # echo 'hrtimer_*' > /debug/tracing/set_ftrace_filter @@ -1299,7 +1632,8 @@ This is because the '>' and '>>' act just like they do in bash. To rewrite the filters, use '>' To append to the filters, use '>>' -To clear out a filter so that all functions will be recorded again: +To clear out a filter so that all functions will be recorded +again: # echo > /debug/tracing/set_ftrace_filter # cat /debug/tracing/set_ftrace_filter @@ -1331,7 +1665,8 @@ hrtimer_get_res hrtimer_init_sleeper -The set_ftrace_notrace prevents those functions from being traced. +The set_ftrace_notrace prevents those functions from being +traced. # echo '*preempt*' '*lock*' > /debug/tracing/set_ftrace_notrace @@ -1353,13 +1688,75 @@ Produces: We can see that there's no more lock or preempt tracing. + +Dynamic ftrace with the function graph tracer +--------------------------------------------- + +Although what has been explained above concerns both the +function tracer and the function-graph-tracer, there are some +special features only available in the function-graph tracer. + +If you want to trace only one function and all of its children, +you just have to echo its name into set_graph_function: + + echo __do_fault > set_graph_function + +will produce the following "expanded" trace of the __do_fault() +function: + + 0) | __do_fault() { + 0) | filemap_fault() { + 0) | find_lock_page() { + 0) 0.804 us | find_get_page(); + 0) | __might_sleep() { + 0) 1.329 us | } + 0) 3.904 us | } + 0) 4.979 us | } + 0) 0.653 us | _spin_lock(); + 0) 0.578 us | page_add_file_rmap(); + 0) 0.525 us | native_set_pte_at(); + 0) 0.585 us | _spin_unlock(); + 0) | unlock_page() { + 0) 0.541 us | page_waitqueue(); + 0) 0.639 us | __wake_up_bit(); + 0) 2.786 us | } + 0) + 14.237 us | } + 0) | __do_fault() { + 0) | filemap_fault() { + 0) | find_lock_page() { + 0) 0.698 us | find_get_page(); + 0) | __might_sleep() { + 0) 1.412 us | } + 0) 3.950 us | } + 0) 5.098 us | } + 0) 0.631 us | _spin_lock(); + 0) 0.571 us | page_add_file_rmap(); + 0) 0.526 us | native_set_pte_at(); + 0) 0.586 us | _spin_unlock(); + 0) | unlock_page() { + 0) 0.533 us | page_waitqueue(); + 0) 0.638 us | __wake_up_bit(); + 0) 2.793 us | } + 0) + 14.012 us | } + +You can also expand several functions at once: + + echo sys_open > set_graph_function + echo sys_close >> set_graph_function + +Now if you want to go back to trace all functions you can clear +this special filter via: + + echo > set_graph_function + + trace_pipe ---------- -The trace_pipe outputs the same content as the trace file, but the effect -on the tracing is different. Every read from trace_pipe is consumed. -This means that subsequent reads will be different. The trace -is live. +The trace_pipe outputs the same content as the trace file, but +the effect on the tracing is different. Every read from +trace_pipe is consumed. This means that subsequent reads will be +different. The trace is live. # echo function > /debug/tracing/current_tracer # cat /debug/tracing/trace_pipe > /tmp/trace.out & @@ -1387,38 +1784,45 @@ is live. bash-4043 [00] 41.267111: select_task_rq_rt <-try_to_wake_up -Note, reading the trace_pipe file will block until more input is added. -By changing the tracer, trace_pipe will issue an EOF. We needed -to set the function tracer _before_ we "cat" the trace_pipe file. +Note, reading the trace_pipe file will block until more input is +added. By changing the tracer, trace_pipe will issue an EOF. We +needed to set the function tracer _before_ we "cat" the +trace_pipe file. trace entries ------------- -Having too much or not enough data can be troublesome in diagnosing -an issue in the kernel. The file buffer_size_kb is used to modify -the size of the internal trace buffers. The number listed -is the number of entries that can be recorded per CPU. To know -the full size, multiply the number of possible CPUS with the -number of entries. +Having too much or not enough data can be troublesome in +diagnosing an issue in the kernel. The file buffer_size_kb is +used to modify the size of the internal trace buffers. The +number listed is the number of entries that can be recorded per +CPU. To know the full size, multiply the number of possible CPUS +with the number of entries. # cat /debug/tracing/buffer_size_kb 1408 (units kilobytes) -Note, to modify this, you must have tracing completely disabled. To do that, -echo "nop" into the current_tracer. If the current_tracer is not set -to "nop", an EINVAL error will be returned. +Note, to modify this, you must have tracing completely disabled. +To do that, echo "nop" into the current_tracer. If the +current_tracer is not set to "nop", an EINVAL error will be +returned. # echo nop > /debug/tracing/current_tracer # echo 10000 > /debug/tracing/buffer_size_kb # cat /debug/tracing/buffer_size_kb 10000 (units kilobytes) -The number of pages which will be allocated is limited to a percentage -of available memory. Allocating too much will produce an error. +The number of pages which will be allocated is limited to a +percentage of available memory. Allocating too much will produce +an error. # echo 1000000000000 > /debug/tracing/buffer_size_kb -bash: echo: write error: Cannot allocate memory # cat /debug/tracing/buffer_size_kb 85 +----------- + +More details can be found in the source code, in the +kernel/tracing/*.c files. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 54f21a5..8869faa 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -49,6 +49,7 @@ parameter is applicable: ISAPNP ISA PnP code is enabled. ISDN Appropriate ISDN support is enabled. JOY Appropriate joystick support is enabled. + KMEMTRACE kmemtrace is enabled. LIBATA Libata driver is enabled LP Printer support is enabled. LOOP Loopback device support is enabled. @@ -492,10 +493,12 @@ and is between 256 and 4096 characters. It is defined in the file Default: 64 hpet= [X86-32,HPET] option to control HPET usage - Format: { enable (default) | disable | force } + Format: { enable (default) | disable | force | + verbose } disable: disable HPET and use PIT instead force: allow force enabled of undocumented chips (ICH4, VIA, nVidia) + verbose: show contents of HPET registers during setup com20020= [HW,NET] ARCnet - COM20020 chipset Format: @@ -604,6 +607,9 @@ and is between 256 and 4096 characters. It is defined in the file debug_objects [KNL] Enable object debugging + no_debug_objects + [KNL] Disable object debugging + debugpat [X86] Enable PAT debugging decnet.addr= [HW,NET] @@ -1047,6 +1053,15 @@ and is between 256 and 4096 characters. It is defined in the file use the HighMem zone if it exists, and the Normal zone if it does not. + kmemtrace.enable= [KNL,KMEMTRACE] Format: { yes | no } + Controls whether kmemtrace is enabled + at boot-time. + + kmemtrace.subbufs=n [KNL,KMEMTRACE] Overrides the number of + subbufs kmemtrace's relay channel has. Set this + higher than default (KMEMTRACE_N_SUBBUFS in code) if + you experience buffer overruns. + movablecore=nn[KMG] [KNL,X86-32,IA-64,PPC,X86-64] This parameter is similar to kernelcore except it specifies the amount of memory used for migratable allocations. @@ -1310,8 +1325,13 @@ and is between 256 and 4096 characters. It is defined in the file memtest= [KNL,X86] Enable memtest Format: - range: 0,4 : pattern number default : 0 + Specifies the number of memtest passes to be + performed. Each pass selects another test + pattern from a given set of patterns. Memtest + fills the memory with this pattern, validates + memory contents and reserves bad memory + regions that are detected. meye.*= [HW] Set MotionEye Camera parameters See Documentation/video4linux/meye.txt. @@ -2329,6 +2349,8 @@ and is between 256 and 4096 characters. It is defined in the file tp720= [HW,PS2] + trace_buf_size=nn[KMG] [ftrace] will set tracing buffer size. + trix= [HW,OSS] MediaTrix AudioTrix Pro Format: ,,,,,,,, diff --git a/Documentation/kmemcheck.txt b/Documentation/kmemcheck.txt new file mode 100644 index 0000000..a848d49 --- /dev/null +++ b/Documentation/kmemcheck.txt @@ -0,0 +1,129 @@ +Contents +======== + + 1. How to use + 2. Technical description + 3. Changes to the slab allocators + 4. Problems + 5. Parameters + 6. Future enhancements + + +How to use (IMPORTANT) +====================== + +Always remember this: kmemcheck _will_ give false positives. So don't enable +it and spam the mailing list with its reports; you are not going to be heard, +and it will make people's skins thicker for when the real errors are found. + +Instead, I encourage maintainers and developers to find errors in _their_ +_own_ code. And if you find false positives, you can try to work around them, +try to figure out if it's a real bug or not, or simply ignore them. Most +developers know their own code and will quickly and efficiently determine the +root cause of a kmemcheck report. This is therefore also the most efficient +way to work with kmemcheck. + +If you still want to run kmemcheck to inspect others' code, the rule of thumb +should be: If it's not obvious (to you), don't tell us about it either. Most +likely the code is correct and you'll only waste our time. If you can work +out the error, please do send the maintainer a heads up and/or a patch, but +don't expect him/her to fix something that wasn't wrong in the first place. + + +Technical description +===================== + +kmemcheck works by marking memory pages non-present. This means that whenever +somebody attempts to access the page, a page fault is generated. The page +fault handler notices that the page was in fact only hidden, and so it calls +on the kmemcheck code to make further investigations. + +When the investigations are completed, kmemcheck "shows" the page by marking +it present (as it would be under normal circumstances). This way, the +interrupted code can continue as usual. + +But after the instruction has been executed, we should hide the page again, so +that we can catch the next access too! Now kmemcheck makes use of a debugging +feature of the processor, namely single-stepping. When the processor has +finished the one instruction that generated the memory access, a debug +exception is raised. From here, we simply hide the page again and continue +execution, this time with the single-stepping feature turned off. + + +Changes to the slab allocators +============================== + +kmemcheck requires some assistance from the memory allocator in order to work. +The memory allocator needs to + +1. Tell kmemcheck about newly allocated pages and pages that are about to + be freed. This allows kmemcheck to set up and tear down the shadow memory + for the pages in question. The shadow memory stores the status of each byte + in the allocation proper, e.g. whether it is initialized or uninitialized. +2. Tell kmemcheck which parts of memory should be marked uninitialized. There + are actually a few more states, such as "not yet allocated" and "recently + freed". + +If a slab cache is set up using the SLAB_NOTRACK flag, it will never return +memory that can take page faults because of kmemcheck. + +If a slab cache is NOT set up using the SLAB_NOTRACK flag, callers can still +request memory with the __GFP_NOTRACK flag. This does not prevent the page +faults from occurring, however, but marks the object in question as being +initialized so that no warnings will ever be produced for this object. + +Currently, the SLAB and SLUB allocators are supported by kmemcheck. + + +Problems +======== + +The most prominent problem seems to be that of bit-fields. kmemcheck can only +track memory with byte granularity. Therefore, when gcc generates code to +access only one bit in a bit-field, there is really no way for kmemcheck to +know which of the other bits will be used or thrown away. Consequently, there +may be bogus warnings for bit-field accesses. We have added a "bitfields" API +to get around this problem. See include/linux/kmemcheck.h for detailed +instructions! + + +Parameters +========== + +In addition to enabling CONFIG_KMEMCHECK before the kernel is compiled, the +parameter kmemcheck=1 must be passed to the kernel when it is started in order +to actually do the tracking. So by default, there is only a very small +(probably negligible) overhead for enabling the config option. + +Similarly, kmemcheck may be turned on or off at run-time using, respectively: + +echo 1 > /proc/sys/kernel/kmemcheck + and +echo 0 > /proc/sys/kernel/kmemcheck + +Note that this is a lazy setting; once turned off, the old allocations will +still have to take a single page fault exception before tracking is turned off +for that particular page. Enabling kmemcheck on will only enable tracking for +allocations made from that point onwards. + +The default mode is the one-shot mode, where only the first error is reported +before kmemcheck is disabled. This mode can be enabled by passing kmemcheck=2 +to the kernel at boot, or running + +echo 2 > /proc/sys/kernel/kmemcheck + +when the kernel is already running. + + +Future enhancements +=================== + +There is already some preliminary support for catching use-after-free errors. +What still needs to be done is delaying kfree() so that memory is not +reallocated immediately after freeing it. [Suggested by Pekka Enberg.] + +It should be possible to allow SMP systems by duplicating the page tables for +each processor in the system. This is probably extremely difficult, however. +[Suggested by Ingo Molnar.] + +Support for instruction set extensions like XMM, SSE2, etc. diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt index 4887730..938ea22 100644 --- a/Documentation/lockdep-design.txt +++ b/Documentation/lockdep-design.txt @@ -27,33 +27,37 @@ lock-class. State ----- -The validator tracks lock-class usage history into 5 separate state bits: +The validator tracks lock-class usage history into 4n + 1 separate state bits: -- 'ever held in hardirq context' [ == hardirq-safe ] -- 'ever held in softirq context' [ == softirq-safe ] -- 'ever held with hardirqs enabled' [ == hardirq-unsafe ] -- 'ever held with softirqs and hardirqs enabled' [ == softirq-unsafe ] +- 'ever held in STATE context' +- 'ever head as readlock in STATE context' +- 'ever head with STATE enabled' +- 'ever head as readlock with STATE enabled' + +Where STATE can be either one of (kernel/lockdep_states.h) + - hardirq + - softirq + - reclaim_fs - 'ever used' [ == !unused ] -When locking rules are violated, these 4 state bits are presented in the -locking error messages, inside curlies. A contrived example: +When locking rules are violated, these state bits are presented in the +locking error messages, inside curlies. A contrived example: modprobe/2287 is trying to acquire lock: - (&sio_locks[i].lock){--..}, at: [] mutex_lock+0x21/0x24 + (&sio_locks[i].lock){-.-...}, at: [] mutex_lock+0x21/0x24 but task is already holding lock: - (&sio_locks[i].lock){--..}, at: [] mutex_lock+0x21/0x24 + (&sio_locks[i].lock){-.-...}, at: [] mutex_lock+0x21/0x24 -The bit position indicates hardirq, softirq, hardirq-read, -softirq-read respectively, and the character displayed in each -indicates: +The bit position indicates STATE, STATE-read, for each of the states listed +above, and the character displayed in each indicates: '.' acquired while irqs disabled '+' acquired in irq context '-' acquired with irqs enabled - '?' read acquired in irq context with irqs enabled. + '?' acquired in irq context with irqs enabled. Unused mutexes cannot be part of the cause of an error. diff --git a/Documentation/networking/ipv6.txt b/Documentation/networking/ipv6.txt new file mode 100644 index 0000000..268e5c1 --- /dev/null +++ b/Documentation/networking/ipv6.txt @@ -0,0 +1,35 @@ + +Options for the ipv6 module are supplied as parameters at load time. + +Module options may be given as command line arguments to the insmod +or modprobe command, but are usually specified in either the +/etc/modules.conf or /etc/modprobe.conf configuration file, or in a +distro-specific configuration file. + +The available ipv6 module parameters are listed below. If a parameter +is not specified the default value is used. + +The parameters are as follows: + +disable + + Specifies whether to load the IPv6 module, but disable all + its functionality. This might be used when another module + has a dependency on the IPv6 module being loaded, but no + IPv6 addresses or operations are desired. + + The possible values and their effects are: + + 0 + IPv6 is enabled. + + This is the default value. + + 1 + IPv6 is disabled. + + No IPv6 addresses will be added to interfaces, and + it will not be possible to open an IPv6 socket. + + A reboot is required to enable IPv6. + diff --git a/Documentation/perf-counters.txt b/Documentation/perf-counters.txt new file mode 100644 index 0000000..fddd321 --- /dev/null +++ b/Documentation/perf-counters.txt @@ -0,0 +1,147 @@ + +Performance Counters for Linux +------------------------------ + +Performance counters are special hardware registers available on most modern +CPUs. These registers count the number of certain types of hw events: such +as instructions executed, cachemisses suffered, or branches mis-predicted - +without slowing down the kernel or applications. These registers can also +trigger interrupts when a threshold number of events have passed - and can +thus be used to profile the code that runs on that CPU. + +The Linux Performance Counter subsystem provides an abstraction of these +hardware capabilities. It provides per task and per CPU counters, counter +groups, and it provides event capabilities on top of those. + +Performance counters are accessed via special file descriptors. +There's one file descriptor per virtual counter used. + +The special file descriptor is opened via the perf_counter_open() +system call: + + int sys_perf_counter_open(struct perf_counter_hw_event *hw_event_uptr, + pid_t pid, int cpu, int group_fd); + +The syscall returns the new fd. The fd can be used via the normal +VFS system calls: read() can be used to read the counter, fcntl() +can be used to set the blocking mode, etc. + +Multiple counters can be kept open at a time, and the counters +can be poll()ed. + +When creating a new counter fd, 'perf_counter_hw_event' is: + +/* + * Hardware event to monitor via a performance monitoring counter: + */ +struct perf_counter_hw_event { + s64 type; + + u64 irq_period; + u32 record_type; + + u32 disabled : 1, /* off by default */ + nmi : 1, /* NMI sampling */ + raw : 1, /* raw event type */ + __reserved_1 : 29; + + u64 __reserved_2; +}; + +/* + * Generalized performance counter event types, used by the hw_event.type + * parameter of the sys_perf_counter_open() syscall: + */ +enum hw_event_types { + /* + * Common hardware events, generalized by the kernel: + */ + PERF_COUNT_CYCLES = 0, + PERF_COUNT_INSTRUCTIONS = 1, + PERF_COUNT_CACHE_REFERENCES = 2, + PERF_COUNT_CACHE_MISSES = 3, + PERF_COUNT_BRANCH_INSTRUCTIONS = 4, + PERF_COUNT_BRANCH_MISSES = 5, + + /* + * Special "software" counters provided by the kernel, even if + * the hardware does not support performance counters. These + * counters measure various physical and sw events of the + * kernel (and allow the profiling of them as well): + */ + PERF_COUNT_CPU_CLOCK = -1, + PERF_COUNT_TASK_CLOCK = -2, + /* + * Future software events: + */ + /* PERF_COUNT_PAGE_FAULTS = -3, + PERF_COUNT_CONTEXT_SWITCHES = -4, */ +}; + +These are standardized types of events that work uniformly on all CPUs +that implements Performance Counters support under Linux. If a CPU is +not able to count branch-misses, then the system call will return +-EINVAL. + +More hw_event_types are supported as well, but they are CPU +specific and are enumerated via /sys on a per CPU basis. Raw hw event +types can be passed in under hw_event.type if hw_event.raw is 1. +For example, to count "External bus cycles while bus lock signal asserted" +events on Intel Core CPUs, pass in a 0x4064 event type value and set +hw_event.raw to 1. + +'record_type' is the type of data that a read() will provide for the +counter, and it can be one of: + +/* + * IRQ-notification data record type: + */ +enum perf_counter_record_type { + PERF_RECORD_SIMPLE = 0, + PERF_RECORD_IRQ = 1, + PERF_RECORD_GROUP = 2, +}; + +a "simple" counter is one that counts hardware events and allows +them to be read out into a u64 count value. (read() returns 8 on +a successful read of a simple counter.) + +An "irq" counter is one that will also provide an IRQ context information: +the IP of the interrupted context. In this case read() will return +the 8-byte counter value, plus the Instruction Pointer address of the +interrupted context. + +The parameter 'hw_event_period' is the number of events before waking up +a read() that is blocked on a counter fd. Zero value means a non-blocking +counter. + +The 'pid' parameter allows the counter to be specific to a task: + + pid == 0: if the pid parameter is zero, the counter is attached to the + current task. + + pid > 0: the counter is attached to a specific task (if the current task + has sufficient privilege to do so) + + pid < 0: all tasks are counted (per cpu counters) + +The 'cpu' parameter allows a counter to be made specific to a full +CPU: + + cpu >= 0: the counter is restricted to a specific CPU + cpu == -1: the counter counts on all CPUs + +(Note: the combination of 'pid == -1' and 'cpu == -1' is not valid.) + +A 'pid > 0' and 'cpu == -1' counter is a per task counter that counts +events of that task and 'follows' that task to whatever CPU the task +gets schedule to. Per task counters can be created by any user, for +their own tasks. + +A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts +all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege. + +Group counters are created by passing in a group_fd of another counter. +Groups are scheduled at once and can be used with PERF_RECORD_GROUP +to record multi-dimensional timestamps. + diff --git a/Documentation/scheduler/00-INDEX b/Documentation/scheduler/00-INDEX index aabcc3a..3c00c9c 100644 --- a/Documentation/scheduler/00-INDEX +++ b/Documentation/scheduler/00-INDEX @@ -2,8 +2,6 @@ - this file. sched-arch.txt - CPU Scheduler implementation hints for architecture specific code. -sched-coding.txt - - reference for various scheduler-related methods in the O(1) scheduler. sched-design-CFS.txt - goals, design and implementation of the Complete Fair Scheduler. sched-domains.txt diff --git a/Documentation/scheduler/sched-coding.txt b/Documentation/scheduler/sched-coding.txt deleted file mode 100644 index cbd8db7..0000000 --- a/Documentation/scheduler/sched-coding.txt +++ /dev/null @@ -1,126 +0,0 @@ - Reference for various scheduler-related methods in the O(1) scheduler - Robert Love , MontaVista Software - - -Note most of these methods are local to kernel/sched.c - this is by design. -The scheduler is meant to be self-contained and abstracted away. This document -is primarily for understanding the scheduler, not interfacing to it. Some of -the discussed interfaces, however, are general process/scheduling methods. -They are typically defined in include/linux/sched.h. - - -Main Scheduling Methods ------------------------ - -void load_balance(runqueue_t *this_rq, int idle) - Attempts to pull tasks from one cpu to another to balance cpu usage, - if needed. This method is called explicitly if the runqueues are - imbalanced or periodically by the timer tick. Prior to calling, - the current runqueue must be locked and interrupts disabled. - -void schedule() - The main scheduling function. Upon return, the highest priority - process will be active. - - -Locking -------- - -Each runqueue has its own lock, rq->lock. When multiple runqueues need -to be locked, lock acquires must be ordered by ascending &runqueue value. - -A specific runqueue is locked via - - task_rq_lock(task_t pid, unsigned long *flags) - -which disables preemption, disables interrupts, and locks the runqueue pid is -running on. Likewise, - - task_rq_unlock(task_t pid, unsigned long *flags) - -unlocks the runqueue pid is running on, restores interrupts to their previous -state, and reenables preemption. - -The routines - - double_rq_lock(runqueue_t *rq1, runqueue_t *rq2) - -and - - double_rq_unlock(runqueue_t *rq1, runqueue_t *rq2) - -safely lock and unlock, respectively, the two specified runqueues. They do -not, however, disable and restore interrupts. Users are required to do so -manually before and after calls. - - -Values ------- - -MAX_PRIO - The maximum priority of the system, stored in the task as task->prio. - Lower priorities are higher. Normal (non-RT) priorities range from - MAX_RT_PRIO to (MAX_PRIO - 1). -MAX_RT_PRIO - The maximum real-time priority of the system. Valid RT priorities - range from 0 to (MAX_RT_PRIO - 1). -MAX_USER_RT_PRIO - The maximum real-time priority that is exported to user-space. Should - always be equal to or less than MAX_RT_PRIO. Setting it less allows - kernel threads to have higher priorities than any user-space task. -MIN_TIMESLICE -MAX_TIMESLICE - Respectively, the minimum and maximum timeslices (quanta) of a process. - -Data ----- - -struct runqueue - The main per-CPU runqueue data structure. -struct task_struct - The main per-process data structure. - - -General Methods ---------------- - -cpu_rq(cpu) - Returns the runqueue of the specified cpu. -this_rq() - Returns the runqueue of the current cpu. -task_rq(pid) - Returns the runqueue which holds the specified pid. -cpu_curr(cpu) - Returns the task currently running on the given cpu. -rt_task(pid) - Returns true if pid is real-time, false if not. - - -Process Control Methods ------------------------ - -void set_user_nice(task_t *p, long nice) - Sets the "nice" value of task p to the given value. -int setscheduler(pid_t pid, int policy, struct sched_param *param) - Sets the scheduling policy and parameters for the given pid. -int set_cpus_allowed(task_t *p, unsigned long new_mask) - Sets a given task's CPU affinity and migrates it to a proper cpu. - Callers must have a valid reference to the task and assure the - task not exit prematurely. No locks can be held during the call. -set_task_state(tsk, state_value) - Sets the given task's state to the given value. -set_current_state(state_value) - Sets the current task's state to the given value. -void set_tsk_need_resched(struct task_struct *tsk) - Sets need_resched in the given task. -void clear_tsk_need_resched(struct task_struct *tsk) - Clears need_resched in the given task. -void set_need_resched() - Sets need_resched in the current task. -void clear_need_resched() - Clears need_resched in the current task. -int need_resched() - Returns true if need_resched is set in the current task, false - otherwise. -yield() - Place the current process at the end of the runqueue and call schedule. diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index 9e592c7..535aeb9 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -113,6 +113,8 @@ On all - write a character to /proc/sysrq-trigger. e.g.: 'x' - Used by xmon interface on ppc/powerpc platforms. +'z' - Dump the ftrace buffer + '0'-'9' - Sets the console log level, controlling which kernel messages will be printed to your console. ('0', for example would make it so that only emergency messages like PANICs or OOPSes would diff --git a/Documentation/tracepoints.txt b/Documentation/tracepoints.txt index 6f0a044..4ff43c6 100644 --- a/Documentation/tracepoints.txt +++ b/Documentation/tracepoints.txt @@ -45,8 +45,8 @@ In include/trace/subsys.h : #include DECLARE_TRACE(subsys_eventname, - TPPROTO(int firstarg, struct task_struct *p), - TPARGS(firstarg, p)); + TP_PROTO(int firstarg, struct task_struct *p), + TP_ARGS(firstarg, p)); In subsys/file.c (where the tracing statement must be added) : @@ -66,10 +66,10 @@ Where : - subsys is the name of your subsystem. - eventname is the name of the event to trace. -- TPPROTO(int firstarg, struct task_struct *p) is the prototype of the +- TP_PROTO(int firstarg, struct task_struct *p) is the prototype of the function called by this tracepoint. -- TPARGS(firstarg, p) are the parameters names, same as found in the +- TP_ARGS(firstarg, p) are the parameters names, same as found in the prototype. Connecting a function (probe) to a tracepoint is done by providing a diff --git a/Documentation/vm/kmemtrace.txt b/Documentation/vm/kmemtrace.txt new file mode 100644 index 0000000..a956d9b --- /dev/null +++ b/Documentation/vm/kmemtrace.txt @@ -0,0 +1,126 @@ + kmemtrace - Kernel Memory Tracer + + by Eduard - Gabriel Munteanu + + +I. Introduction +=============== + +kmemtrace helps kernel developers figure out two things: +1) how different allocators (SLAB, SLUB etc.) perform +2) how kernel code allocates memory and how much + +To do this, we trace every allocation and export information to the userspace +through the relay interface. We export things such as the number of requested +bytes, the number of bytes actually allocated (i.e. including internal +fragmentation), whether this is a slab allocation or a plain kmalloc() and so +on. + +The actual analysis is performed by a userspace tool (see section III for +details on where to get it from). It logs the data exported by the kernel, +processes it and (as of writing this) can provide the following information: +- the total amount of memory allocated and fragmentation per call-site +- the amount of memory allocated and fragmentation per allocation +- total memory allocated and fragmentation in the collected dataset +- number of cross-CPU allocation and frees (makes sense in NUMA environments) + +Moreover, it can potentially find inconsistent and erroneous behavior in +kernel code, such as using slab free functions on kmalloc'ed memory or +allocating less memory than requested (but not truly failed allocations). + +kmemtrace also makes provisions for tracing on some arch and analysing the +data on another. + +II. Design and goals +==================== + +kmemtrace was designed to handle rather large amounts of data. Thus, it uses +the relay interface to export whatever is logged to userspace, which then +stores it. Analysis and reporting is done asynchronously, that is, after the +data is collected and stored. By design, it allows one to log and analyse +on different machines and different arches. + +As of writing this, the ABI is not considered stable, though it might not +change much. However, no guarantees are made about compatibility yet. When +deemed stable, the ABI should still allow easy extension while maintaining +backward compatibility. This is described further in Documentation/ABI. + +Summary of design goals: + - allow logging and analysis to be done across different machines + - be fast and anticipate usage in high-load environments (*) + - be reasonably extensible + - make it possible for GNU/Linux distributions to have kmemtrace + included in their repositories + +(*) - one of the reasons Pekka Enberg's original userspace data analysis + tool's code was rewritten from Perl to C (although this is more than a + simple conversion) + + +III. Quick usage guide +====================== + +1) Get a kernel that supports kmemtrace and build it accordingly (i.e. enable +CONFIG_KMEMTRACE). + +2) Get the userspace tool and build it: +$ git-clone git://repo.or.cz/kmemtrace-user.git # current repository +$ cd kmemtrace-user/ +$ ./autogen.sh +$ ./configure +$ make + +3) Boot the kmemtrace-enabled kernel if you haven't, preferably in the +'single' runlevel (so that relay buffers don't fill up easily), and run +kmemtrace: +# '$' does not mean user, but root here. +$ mount -t debugfs none /sys/kernel/debug +$ mount -t proc none /proc +$ cd path/to/kmemtrace-user/ +$ ./kmemtraced +Wait a bit, then stop it with CTRL+C. +$ cat /sys/kernel/debug/kmemtrace/total_overruns # Check if we didn't + # overrun, should + # be zero. +$ (Optionally) [Run kmemtrace_check separately on each cpu[0-9]*.out file to + check its correctness] +$ ./kmemtrace-report + +Now you should have a nice and short summary of how the allocator performs. + +IV. FAQ and known issues +======================== + +Q: 'cat /sys/kernel/debug/kmemtrace/total_overruns' is non-zero, how do I fix +this? Should I worry? +A: If it's non-zero, this affects kmemtrace's accuracy, depending on how +large the number is. You can fix it by supplying a higher +'kmemtrace.subbufs=N' kernel parameter. +--- + +Q: kmemtrace_check reports errors, how do I fix this? Should I worry? +A: This is a bug and should be reported. It can occur for a variety of +reasons: + - possible bugs in relay code + - possible misuse of relay by kmemtrace + - timestamps being collected unorderly +Or you may fix it yourself and send us a patch. +--- + +Q: kmemtrace_report shows many errors, how do I fix this? Should I worry? +A: This is a known issue and I'm working on it. These might be true errors +in kernel code, which may have inconsistent behavior (e.g. allocating memory +with kmem_cache_alloc() and freeing it with kfree()). Pekka Enberg pointed +out this behavior may work with SLAB, but may fail with other allocators. + +It may also be due to lack of tracing in some unusual allocator functions. + +We don't want bug reports regarding this issue yet. +--- + +V. See also +=========== + +Documentation/kernel-parameters.txt +Documentation/ABI/testing/debugfs-kmemtrace + diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 7b4596a..e020366 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -158,7 +158,7 @@ Offset Proto Name Meaning 0202/4 2.00+ header Magic signature "HdrS" 0206/2 2.00+ version Boot protocol version supported 0208/4 2.00+ realmode_swtch Boot loader hook (see below) -020C/2 2.00+ start_sys The load-low segment (0x1000) (obsolete) +020C/2 2.00+ start_sys_seg The load-low segment (0x1000) (obsolete) 020E/2 2.00+ kernel_version Pointer to kernel version string 0210/1 2.00+ type_of_loader Boot loader identifier 0211/1 2.00+ loadflags Boot protocol option flags @@ -170,10 +170,11 @@ Offset Proto Name Meaning 0224/2 2.01+ heap_end_ptr Free memory after setup end 0226/2 N/A pad1 Unused 0228/4 2.02+ cmd_line_ptr 32-bit pointer to the kernel command line -022C/4 2.03+ initrd_addr_max Highest legal initrd address +022C/4 2.03+ ramdisk_max Highest legal initrd address 0230/4 2.05+ kernel_alignment Physical addr alignment required for kernel 0234/1 2.05+ relocatable_kernel Whether kernel is relocatable or not -0235/3 N/A pad2 Unused +0235/1 N/A pad2 Unused +0236/2 N/A pad3 Unused 0238/4 2.06+ cmdline_size Maximum size of the kernel command line 023C/4 2.07+ hardware_subarch Hardware subarchitecture 0240/8 2.07+ hardware_subarch_data Subarchitecture-specific data @@ -299,14 +300,14 @@ Protocol: 2.00+ e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version 10.17. -Field name: readmode_swtch +Field name: realmode_swtch Type: modify (optional) Offset/size: 0x208/4 Protocol: 2.00+ Boot loader hook (see ADVANCED BOOT LOADER HOOKS below.) -Field name: start_sys +Field name: start_sys_seg Type: read Offset/size: 0x20c/2 Protocol: 2.00+ @@ -468,7 +469,7 @@ Protocol: 2.02+ zero, the kernel will assume that your boot loader does not support the 2.02+ protocol. -Field name: initrd_addr_max +Field name: ramdisk_max Type: read Offset/size: 0x22c/4 Protocol: 2.03+ @@ -542,7 +543,10 @@ Protocol: 2.08+ The payload may be compressed. The format of both the compressed and uncompressed data should be determined using the standard magic - numbers. Currently only gzip compressed ELF is used. + numbers. The currently supported compression formats are gzip + (magic numbers 1F 8B or 1F 9E), bzip2 (magic number 42 5A) and LZMA + (magic number 5D 00). The uncompressed payload is currently always ELF + (magic number 7F 45 4C 46). Field name: payload_length Type: read diff --git a/Documentation/x86/earlyprintk.txt b/Documentation/x86/earlyprintk.txt new file mode 100644 index 0000000..607b1a0 --- /dev/null +++ b/Documentation/x86/earlyprintk.txt @@ -0,0 +1,101 @@ + +Mini-HOWTO for using the earlyprintk=dbgp boot option with a +USB2 Debug port key and a debug cable, on x86 systems. + +You need two computers, the 'USB debug key' special gadget and +and two USB cables, connected like this: + + [host/target] <-------> [USB debug key] <-------> [client/console] + +1. There are three specific hardware requirements: + + a.) Host/target system needs to have USB debug port capability. + + You can check this capability by looking at a 'Debug port' bit in + the lspci -vvv output: + + # lspci -vvv + ... + 00:1d.7 USB Controller: Intel Corporation 82801H (ICH8 Family) USB2 EHCI Controller #1 (rev 03) (prog-if 20 [EHCI]) + Subsystem: Lenovo ThinkPad T61 + Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B- DisINTx- + Status: Cap+ 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- SERR- /proc/sysrq-trigger + + On the host/target system you should see this help line in "dmesg" output: + + SysRq : HELP : loglevel(0-9) reBoot Crashdump terminate-all-tasks(E) memory-full-oom-kill(F) kill-all-tasks(I) saK show-backtrace-all-active-cpus(L) show-memory-usage(M) nice-all-RT-tasks(N) powerOff show-registers(P) show-all-timers(Q) unRaw Sync show-task-states(T) Unmount show-blocked-tasks(W) dump-ftrace-buffer(Z) + + On the client/console system do: + + cat /dev/ttyUSB0 + + And you should see the help line above displayed shortly after you've + provoked it on the host system. + +If it does not work then please ask about it on the linux-kernel@vger.kernel.org +mailing list or contact the x86 maintainers. diff --git a/MAINTAINERS b/MAINTAINERS index 1c2ca1d..7669d87 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2623,6 +2623,20 @@ M: jason.wessel@windriver.com L: kgdb-bugreport@lists.sourceforge.net S: Maintained +KMEMCHECK +P: Vegard Nossum +M: vegardno@ifi.uio.no +P Pekka Enberg +M: penberg@cs.helsinki.fi +L: linux-kernel@vger.kernel.org +S: Maintained + +KMEMTRACE +P: Eduard - Gabriel Munteanu +M: eduard.munteanu@linux360.ro +L: linux-kernel@vger.kernel.org +S: Maintained + KPROBES P: Ananth N Mavinakayanahalli M: ananth@in.ibm.com diff --git a/Makefile b/Makefile index d04ee0a..32ae8b1 100644 --- a/Makefile +++ b/Makefile @@ -533,8 +533,9 @@ KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN}) endif # Force gcc to behave correct even for buggy distributions -# Arch Makefiles may override this setting +ifndef CONFIG_CC_STACKPROTECTOR KBUILD_CFLAGS += $(call cc-option, -fno-stack-protector) +endif ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls @@ -551,6 +552,10 @@ ifdef CONFIG_FUNCTION_TRACER KBUILD_CFLAGS += -pg endif +ifndef CONFIG_ALLOW_WARNINGS +KBUILD_CFLAGS += -Werror ${WERROR} +endif + # We trigger additional mismatches with less inlining ifdef CONFIG_DEBUG_SECTION_MISMATCH KBUILD_CFLAGS += $(call cc-option, -fno-inline-functions-called-once) diff --git a/arch/Kconfig b/arch/Kconfig index 550dab2..a092dc7 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -6,6 +6,7 @@ config OPROFILE tristate "OProfile system profiling (EXPERIMENTAL)" depends on PROFILING depends on HAVE_OPROFILE + depends on TRACING_SUPPORT select TRACING select RING_BUFFER help diff --git a/arch/alpha/include/asm/ftrace.h b/arch/alpha/include/asm/ftrace.h new file mode 100644 index 0000000..40a8c17 --- /dev/null +++ b/arch/alpha/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/alpha/include/asm/hardirq.h b/arch/alpha/include/asm/hardirq.h index d953e23..8897146 100644 --- a/arch/alpha/include/asm/hardirq.h +++ b/arch/alpha/include/asm/hardirq.h @@ -14,17 +14,4 @@ typedef struct { void ack_bad_irq(unsigned int irq); -#define HARDIRQ_BITS 12 - -/* - * The hardirq mask has to be large enough to have - * space for potentially nestable IRQ sources in the system - * to nest on a single CPU. On Alpha, interrupts are masked at the CPU - * by IPL as well as at the system level. We only have 8 IPLs (UNIX PALcode) - * so we really only have 8 nestable IRQs, but allow some overhead - */ -#if (1 << HARDIRQ_BITS) < 16 -#error HARDIRQ_BITS is too low! -#endif - #endif /* _ALPHA_HARDIRQ_H */ diff --git a/arch/alpha/include/asm/statfs.h b/arch/alpha/include/asm/statfs.h index de35cd4..ccd2e18 100644 --- a/arch/alpha/include/asm/statfs.h +++ b/arch/alpha/include/asm/statfs.h @@ -1,6 +1,8 @@ #ifndef _ALPHA_STATFS_H #define _ALPHA_STATFS_H +#include + /* Alpha is the only 64-bit platform with 32-bit statfs. And doesn't even seem to implement statfs64 */ #define __statfs_word __u32 diff --git a/arch/alpha/include/asm/swab.h b/arch/alpha/include/asm/swab.h index 68e7089..4d682b1 100644 --- a/arch/alpha/include/asm/swab.h +++ b/arch/alpha/include/asm/swab.h @@ -1,7 +1,7 @@ #ifndef _ALPHA_SWAB_H #define _ALPHA_SWAB_H -#include +#include #include #include diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 703731a..cc78346 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -55,7 +55,7 @@ int irq_select_affinity(unsigned int irq) cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0); last_cpu = cpu; - irq_desc[irq].affinity = cpumask_of_cpu(cpu); + cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu)); irq_desc[irq].chip->set_affinity(irq, cpumask_of(cpu)); return 0; } @@ -90,7 +90,7 @@ show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%10u ", kstat_irqs(irq)); #else for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[irq]); + seq_printf(p, "%10u ", kstat_irqs_cpu(irq, j)); #endif seq_printf(p, " %14s", irq_desc[irq].chip->typename); seq_printf(p, " %c%s", diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index e16aeb6..67c19f8 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -64,7 +64,7 @@ do_entInt(unsigned long type, unsigned long vector, smp_percpu_timer_interrupt(regs); cpu = smp_processor_id(); if (cpu != boot_cpuid) { - kstat_cpu(cpu).irqs[RTC_IRQ]++; + kstat_incr_irqs_this_cpu(RTC_IRQ, irq_to_desc(RTC_IRQ)); } else { handle_irq(RTC_IRQ); } diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 5d7a16e..af71d38 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -189,9 +189,21 @@ callback_init(void * kernel_end) if (alpha_using_srm) { static struct vm_struct console_remap_vm; - unsigned long vaddr = VMALLOC_START; + unsigned long nr_pages = 0; + unsigned long vaddr; unsigned long i, j; + /* calculate needed size */ + for (i = 0; i < crb->map_entries; ++i) + nr_pages += crb->map[i].count; + + /* register the vm area */ + console_remap_vm.flags = VM_ALLOC; + console_remap_vm.size = nr_pages << PAGE_SHIFT; + vm_area_register_early(&console_remap_vm, PAGE_SIZE); + + vaddr = (unsigned long)console_remap_vm.addr; + /* Set up the third level PTEs and update the virtual addresses of the CRB entries. */ for (i = 0; i < crb->map_entries; ++i) { @@ -213,12 +225,6 @@ callback_init(void * kernel_end) vaddr += PAGE_SIZE; } } - - /* Let vmalloc know that we've allocated some space. */ - console_remap_vm.flags = VM_ALLOC; - console_remap_vm.addr = (void *) VMALLOC_START; - console_remap_vm.size = vaddr - VMALLOC_START; - vmlist = &console_remap_vm; } callback_init_done = 1; diff --git a/arch/arm/include/asm/a.out.h b/arch/arm/include/asm/a.out.h index 79489fd..083894b 100644 --- a/arch/arm/include/asm/a.out.h +++ b/arch/arm/include/asm/a.out.h @@ -2,7 +2,7 @@ #define __ARM_A_OUT_H__ #include -#include +#include struct exec { diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index f2cd18a..ee1304f 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -14,7 +14,7 @@ #ifndef __ASMARM_SETUP_H #define __ASMARM_SETUP_H -#include +#include #define COMMAND_LINE_SIZE 1024 diff --git a/arch/arm/include/asm/swab.h b/arch/arm/include/asm/swab.h index 27a689b..ca2bf2f 100644 --- a/arch/arm/include/asm/swab.h +++ b/arch/arm/include/asm/swab.h @@ -16,7 +16,7 @@ #define __ASM_ARM_SWAB_H #include -#include +#include #if !defined(__STRICT_ANSI__) || defined(__KERNEL__) # define __SWAB_64_THRU_32__ diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 363db18..6874c7d 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -76,7 +76,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%3d: ", i); for_each_present_cpu(cpu) - seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu)); seq_printf(p, " %10s", irq_desc[i].chip->name ? : "-"); seq_printf(p, " %s", action->name); for (action = action->next; action; action = action->next) @@ -104,6 +104,11 @@ static struct irq_desc bad_irq_desc = { .lock = __SPIN_LOCK_UNLOCKED(bad_irq_desc.lock), }; +#ifdef CONFIG_CPUMASK_OFFSTACK +/* We are not allocating bad_irq_desc.affinity or .pending_mask */ +#error "ARM architecture does not support CONFIG_CPUMASK_OFFSTACK." +#endif + /* * do_IRQ handles all hardware IRQ's. Decoded IRQs should not * come via this function. Instead, they should provide their @@ -161,7 +166,7 @@ void __init init_IRQ(void) irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE; #ifdef CONFIG_SMP - bad_irq_desc.affinity = CPU_MASK_ALL; + cpumask_setall(bad_irq_desc.affinity); bad_irq_desc.cpu = smp_processor_id(); #endif init_arch_irq(); @@ -191,15 +196,16 @@ void migrate_irqs(void) struct irq_desc *desc = irq_desc + i; if (desc->cpu == cpu) { - unsigned int newcpu = any_online_cpu(desc->affinity); - - if (newcpu == NR_CPUS) { + unsigned int newcpu = cpumask_any_and(desc->affinity, + cpu_online_mask); + if (newcpu >= nr_cpu_ids) { if (printk_ratelimit()) printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n", i, cpu); - cpus_setall(desc->affinity); - newcpu = any_online_cpu(desc->affinity); + cpumask_setall(desc->affinity); + newcpu = cpumask_any_and(desc->affinity, + cpu_online_mask); } route_irq(desc, i, newcpu); diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 0021607..1602373 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -64,7 +64,9 @@ SECTIONS __initramfs_end = .; #endif . = ALIGN(4096); + __per_cpu_load = .; __per_cpu_start = .; + *(.data.percpu.page_aligned) *(.data.percpu) *(.data.percpu.shared_aligned) __per_cpu_end = .; diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c index 134af97..b7f2332 100644 --- a/arch/arm/mach-at91/at91sam9263_devices.c +++ b/arch/arm/mach-at91/at91sam9263_devices.c @@ -347,6 +347,111 @@ void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data) void __init at91_add_device_mmc(short mmc_id, struct at91_mmc_data *data) {} #endif +/* -------------------------------------------------------------------- + * Compact Flash (PCMCIA or IDE) + * -------------------------------------------------------------------- */ + +#if defined(CONFIG_AT91_CF) || defined(CONFIG_AT91_CF_MODULE) || \ + defined(CONFIG_BLK_DEV_IDE_AT91) || defined(CONFIG_BLK_DEV_IDE_AT91_MODULE) + +static struct at91_cf_data cf0_data; + +static struct resource cf0_resources[] = { + [0] = { + .start = AT91_CHIPSELECT_4, + .end = AT91_CHIPSELECT_4 + SZ_256M - 1, + .flags = IORESOURCE_MEM | IORESOURCE_MEM_8AND16BIT, + } +}; + +static struct platform_device cf0_device = { + .id = 0, + .dev = { + .platform_data = &cf0_data, + }, + .resource = cf0_resources, + .num_resources = ARRAY_SIZE(cf0_resources), +}; + +static struct at91_cf_data cf1_data; + +static struct resource cf1_resources[] = { + [0] = { + .start = AT91_CHIPSELECT_5, + .end = AT91_CHIPSELECT_5 + SZ_256M - 1, + .flags = IORESOURCE_MEM | IORESOURCE_MEM_8AND16BIT, + } +}; + +static struct platform_device cf1_device = { + .id = 1, + .dev = { + .platform_data = &cf1_data, + }, + .resource = cf1_resources, + .num_resources = ARRAY_SIZE(cf1_resources), +}; + +void __init at91_add_device_cf(struct at91_cf_data *data) +{ + unsigned long ebi0_csa; + struct platform_device *pdev; + + if (!data) + return; + + /* + * assign CS4 or CS5 to SMC with Compact Flash logic support, + * we assume SMC timings are configured by board code, + * except True IDE where timings are controlled by driver + */ + ebi0_csa = at91_sys_read(AT91_MATRIX_EBI0CSA); + switch (data->chipselect) { + case 4: + at91_set_A_periph(AT91_PIN_PD6, 0); /* EBI0_NCS4/CFCS0 */ + ebi0_csa |= AT91_MATRIX_EBI0_CS4A_SMC_CF1; + cf0_data = *data; + pdev = &cf0_device; + break; + case 5: + at91_set_A_periph(AT91_PIN_PD7, 0); /* EBI0_NCS5/CFCS1 */ + ebi0_csa |= AT91_MATRIX_EBI0_CS5A_SMC_CF2; + cf1_data = *data; + pdev = &cf1_device; + break; + default: + printk(KERN_ERR "AT91 CF: bad chip-select requested (%u)\n", + data->chipselect); + return; + } + at91_sys_write(AT91_MATRIX_EBI0CSA, ebi0_csa); + + if (data->det_pin) { + at91_set_gpio_input(data->det_pin, 1); + at91_set_deglitch(data->det_pin, 1); + } + + if (data->irq_pin) { + at91_set_gpio_input(data->irq_pin, 1); + at91_set_deglitch(data->irq_pin, 1); + } + + if (data->vcc_pin) + /* initially off */ + at91_set_gpio_output(data->vcc_pin, 0); + + /* enable EBI controlled pins */ + at91_set_A_periph(AT91_PIN_PD5, 1); /* NWAIT */ + at91_set_A_periph(AT91_PIN_PD8, 0); /* CFCE1 */ + at91_set_A_periph(AT91_PIN_PD9, 0); /* CFCE2 */ + at91_set_A_periph(AT91_PIN_PD14, 0); /* CFNRW */ + + pdev->name = (data->flags & AT91_CF_TRUE_IDE) ? "at91_ide" : "at91_cf"; + platform_device_register(pdev); +} +#else +void __init at91_add_device_cf(struct at91_cf_data *data) {} +#endif /* -------------------------------------------------------------------- * NAND / SmartMedia diff --git a/arch/arm/mach-at91/include/mach/board.h b/arch/arm/mach-at91/include/mach/board.h index 0b3ae21..793fe7b 100644 --- a/arch/arm/mach-at91/include/mach/board.h +++ b/arch/arm/mach-at91/include/mach/board.h @@ -56,6 +56,9 @@ struct at91_cf_data { u8 vcc_pin; /* power switching */ u8 rst_pin; /* card reset */ u8 chipselect; /* EBI Chip Select number */ + u8 flags; +#define AT91_CF_TRUE_IDE 0x01 +#define AT91_IDE_SWAP_A0_A2 0x02 }; extern void __init at91_add_device_cf(struct at91_cf_data *data); diff --git a/arch/arm/mach-ns9xxx/irq.c b/arch/arm/mach-ns9xxx/irq.c index 22e0eb6..feb0e54 100644 --- a/arch/arm/mach-ns9xxx/irq.c +++ b/arch/arm/mach-ns9xxx/irq.c @@ -63,7 +63,6 @@ static struct irq_chip ns9xxx_chip = { #else static void handle_prio_irq(unsigned int irq, struct irq_desc *desc) { - unsigned int cpu = smp_processor_id(); struct irqaction *action; irqreturn_t action_ret; @@ -72,7 +71,7 @@ static void handle_prio_irq(unsigned int irq, struct irq_desc *desc) BUG_ON(desc->status & IRQ_INPROGRESS); desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); - kstat_cpu(cpu).irqs[irq]++; + kstat_incr_irqs_this_cpu(irq, desc); action = desc->action; if (unlikely(!action || (desc->status & IRQ_DISABLED))) diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c index f6a1345..6031e17 100644 --- a/arch/arm/mach-omap2/board-ldp.c +++ b/arch/arm/mach-omap2/board-ldp.c @@ -81,7 +81,7 @@ static inline void __init ldp_init_smc911x(void) } ldp_smc911x_resources[0].start = cs_mem_base + 0x0; - ldp_smc911x_resources[0].end = cs_mem_base + 0xf; + ldp_smc911x_resources[0].end = cs_mem_base + 0xff; udelay(100); eth_gpio = LDP_SMC911X_GPIO; diff --git a/arch/arm/oprofile/op_model_mpcore.c b/arch/arm/oprofile/op_model_mpcore.c index 6d6bd58..853d42b 100644 --- a/arch/arm/oprofile/op_model_mpcore.c +++ b/arch/arm/oprofile/op_model_mpcore.c @@ -263,7 +263,7 @@ static void em_route_irq(int irq, unsigned int cpu) const struct cpumask *mask = cpumask_of(cpu); spin_lock_irq(&desc->lock); - desc->affinity = *mask; + cpumask_copy(desc->affinity, mask); desc->chip->set_affinity(irq, mask); spin_unlock_irq(&desc->lock); } diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index b189680..05fe305 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -181,7 +181,7 @@ source "kernel/Kconfig.preempt" config QUICKLIST def_bool y -config HAVE_ARCH_BOOTMEM_NODE +config HAVE_ARCH_BOOTMEM def_bool n config ARCH_HAVE_MEMORY_PRESENT diff --git a/arch/avr32/include/asm/ftrace.h b/arch/avr32/include/asm/ftrace.h new file mode 100644 index 0000000..40a8c17 --- /dev/null +++ b/arch/avr32/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/avr32/include/asm/hardirq.h b/arch/avr32/include/asm/hardirq.h index 2673543..015bc75 100644 --- a/arch/avr32/include/asm/hardirq.h +++ b/arch/avr32/include/asm/hardirq.h @@ -20,15 +20,4 @@ void ack_bad_irq(unsigned int irq); #endif /* __ASSEMBLY__ */ -#define HARDIRQ_BITS 12 - -/* - * The hardirq mask has to be large enough to have - * space for potentially all IRQ sources in the system - * nesting on a single CPU: - */ -#if (1 << HARDIRQ_BITS) < NR_IRQS -# error HARDIRQ_BITS is too low! -#endif - #endif /* __ASM_AVR32_HARDIRQ_H */ diff --git a/arch/avr32/include/asm/swab.h b/arch/avr32/include/asm/swab.h index a14aa5b..14cc737 100644 --- a/arch/avr32/include/asm/swab.h +++ b/arch/avr32/include/asm/swab.h @@ -4,7 +4,7 @@ #ifndef __ASM_AVR32_SWAB_H #define __ASM_AVR32_SWAB_H -#include +#include #include #define __SWAB_64_THRU_32__ diff --git a/arch/avr32/kernel/irq.c b/arch/avr32/kernel/irq.c index a8e767d..9f57222 100644 --- a/arch/avr32/kernel/irq.c +++ b/arch/avr32/kernel/irq.c @@ -58,7 +58,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%3d: ", i); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu)); seq_printf(p, " %8s", irq_desc[i].chip->name ? : "-"); seq_printf(p, " %s", action->name); for (action = action->next; action; action = action->next) diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index 8f1f97d..0c1f86e 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -1129,6 +1129,7 @@ endchoice config PM_WAKEUP_BY_GPIO bool "Allow Wakeup from Standby by GPIO" + depends on PM && !BF54x config PM_WAKEUP_GPIO_NUMBER int "GPIO number" @@ -1168,6 +1169,12 @@ config PM_BFIN_WAKE_GP default n help Enable General-Purpose Wake-Up (Voltage Regulator Power-Up) + (all processors, except ADSP-BF549). This option sets + the general-purpose wake-up enable (GPWE) control bit to enable + wake-up upon detection of an active low signal on the /GPW (PH7) pin. + On ADSP-BF549 this option enables the the same functionality on the + /MRXON pin also PH7. + endmenu menu "CPU Frequency scaling" diff --git a/arch/blackfin/Kconfig.debug b/arch/blackfin/Kconfig.debug index 5f981d9..79e7e63 100644 --- a/arch/blackfin/Kconfig.debug +++ b/arch/blackfin/Kconfig.debug @@ -21,12 +21,6 @@ config DEBUG_STACK_USAGE config HAVE_ARCH_KGDB def_bool y -config KGDB_TESTCASE - tristate "KGDB: for test case in expect" - default n - help - This is a kgdb test case for automated testing. - config DEBUG_VERBOSE bool "Verbose fault messages" default y diff --git a/arch/blackfin/configs/BF518F-EZBRD_defconfig b/arch/blackfin/configs/BF518F-EZBRD_defconfig index 4fdb9e0..281f4b6 100644 --- a/arch/blackfin/configs/BF518F-EZBRD_defconfig +++ b/arch/blackfin/configs/BF518F-EZBRD_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.28-rc2 -# Fri Jan 9 17:58:41 2009 +# Linux kernel version: 2.6.28 +# Fri Feb 20 10:01:44 2009 # # CONFIG_MMU is not set # CONFIG_FPU is not set @@ -133,10 +133,15 @@ CONFIG_BF518=y # CONFIG_BF538 is not set # CONFIG_BF539 is not set # CONFIG_BF542 is not set +# CONFIG_BF542M is not set # CONFIG_BF544 is not set +# CONFIG_BF544M is not set # CONFIG_BF547 is not set +# CONFIG_BF547M is not set # CONFIG_BF548 is not set +# CONFIG_BF548M is not set # CONFIG_BF549 is not set +# CONFIG_BF549M is not set # CONFIG_BF561 is not set CONFIG_BF_REV_MIN=0 CONFIG_BF_REV_MAX=2 @@ -426,7 +431,17 @@ CONFIG_DEFAULT_TCP_CONG="cubic" # CONFIG_TIPC is not set # CONFIG_ATM is not set # CONFIG_BRIDGE is not set -# CONFIG_NET_DSA is not set +CONFIG_NET_DSA=y +# CONFIG_NET_DSA_TAG_DSA is not set +# CONFIG_NET_DSA_TAG_EDSA is not set +# CONFIG_NET_DSA_TAG_TRAILER is not set +CONFIG_NET_DSA_TAG_STPID=y +# CONFIG_NET_DSA_MV88E6XXX is not set +# CONFIG_NET_DSA_MV88E6060 is not set +# CONFIG_NET_DSA_MV88E6XXX_NEED_PPU is not set +# CONFIG_NET_DSA_MV88E6131 is not set +# CONFIG_NET_DSA_MV88E6123_61_65 is not set +CONFIG_NET_DSA_KSZ8893M=y # CONFIG_VLAN_8021Q is not set # CONFIG_DECNET is not set # CONFIG_LLC2 is not set @@ -529,6 +544,8 @@ CONFIG_MTD_COMPLEX_MAPPINGS=y # # Self-contained MTD device drivers # +# CONFIG_MTD_DATAFLASH is not set +# CONFIG_MTD_M25P80 is not set # CONFIG_MTD_SLRAM is not set # CONFIG_MTD_PHRAM is not set # CONFIG_MTD_MTDRAM is not set @@ -561,7 +578,9 @@ CONFIG_BLK_DEV_RAM_SIZE=4096 # CONFIG_BLK_DEV_HD is not set CONFIG_MISC_DEVICES=y # CONFIG_EEPROM_93CX6 is not set +# CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set +# CONFIG_C2PORT is not set CONFIG_HAVE_IDE=y # CONFIG_IDE is not set @@ -607,6 +626,7 @@ CONFIG_BFIN_RX_DESC_NUM=20 # CONFIG_SMC91X is not set # CONFIG_SMSC911X is not set # CONFIG_DM9000 is not set +# CONFIG_ENC28J60 is not set # CONFIG_IBM_NEW_EMAC_ZMII is not set # CONFIG_IBM_NEW_EMAC_RGMII is not set # CONFIG_IBM_NEW_EMAC_TAH is not set @@ -764,7 +784,23 @@ CONFIG_I2C_BLACKFIN_TWI_CLK_KHZ=100 # CONFIG_I2C_DEBUG_ALGO is not set # CONFIG_I2C_DEBUG_BUS is not set # CONFIG_I2C_DEBUG_CHIP is not set -# CONFIG_SPI is not set +CONFIG_SPI=y +# CONFIG_SPI_DEBUG is not set +CONFIG_SPI_MASTER=y + +# +# SPI Master Controller Drivers +# +CONFIG_SPI_BFIN=y +# CONFIG_SPI_BFIN_LOCK is not set +# CONFIG_SPI_BITBANG is not set + +# +# SPI Protocol Masters +# +# CONFIG_SPI_AT25 is not set +# CONFIG_SPI_SPIDEV is not set +# CONFIG_SPI_TLE62X0 is not set CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y # CONFIG_GPIOLIB is not set # CONFIG_W1 is not set @@ -788,8 +824,10 @@ CONFIG_BFIN_WDT=y # CONFIG_MFD_SM501 is not set # CONFIG_HTC_PASIC3 is not set # CONFIG_MFD_TMIO is not set +# CONFIG_PMIC_DA903X is not set # CONFIG_MFD_WM8400 is not set # CONFIG_MFD_WM8350_I2C is not set +# CONFIG_REGULATOR is not set # # Multimedia devices @@ -861,10 +899,18 @@ CONFIG_RTC_INTF_DEV=y # CONFIG_RTC_DRV_M41T80 is not set # CONFIG_RTC_DRV_S35390A is not set # CONFIG_RTC_DRV_FM3130 is not set +# CONFIG_RTC_DRV_RX8581 is not set # # SPI RTC drivers # +# CONFIG_RTC_DRV_M41T94 is not set +# CONFIG_RTC_DRV_DS1305 is not set +# CONFIG_RTC_DRV_DS1390 is not set +# CONFIG_RTC_DRV_MAX6902 is not set +# CONFIG_RTC_DRV_R9701 is not set +# CONFIG_RTC_DRV_RS5C348 is not set +# CONFIG_RTC_DRV_DS3234 is not set # # Platform RTC drivers @@ -1062,12 +1108,20 @@ CONFIG_DEBUG_INFO=y # CONFIG_DEBUG_BLOCK_EXT_DEVT is not set # CONFIG_FAULT_INJECTION is not set CONFIG_SYSCTL_SYSCALL_CHECK=y + +# +# Tracers +# +# CONFIG_SCHED_TRACER is not set +# CONFIG_CONTEXT_SWITCH_TRACER is not set +# CONFIG_BOOT_TRACER is not set # CONFIG_DYNAMIC_PRINTK_DEBUG is not set # CONFIG_SAMPLES is not set CONFIG_HAVE_ARCH_KGDB=y # CONFIG_KGDB is not set # CONFIG_DEBUG_STACKOVERFLOW is not set # CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_KGDB_TESTCASE is not set CONFIG_DEBUG_VERBOSE=y CONFIG_DEBUG_MMRS=y # CONFIG_DEBUG_HWERR is not set @@ -1100,6 +1154,7 @@ CONFIG_CRYPTO=y # # CONFIG_CRYPTO_FIPS is not set # CONFIG_CRYPTO_MANAGER is not set +# CONFIG_CRYPTO_MANAGER2 is not set # CONFIG_CRYPTO_GF128MUL is not set # CONFIG_CRYPTO_NULL is not set # CONFIG_CRYPTO_CRYPTD is not set diff --git a/arch/blackfin/configs/BF527-EZKIT_defconfig b/arch/blackfin/configs/BF527-EZKIT_defconfig index 833128b..a50050f 100644 --- a/arch/blackfin/configs/BF527-EZKIT_defconfig +++ b/arch/blackfin/configs/BF527-EZKIT_defconfig @@ -327,8 +327,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/BF533-EZKIT_defconfig b/arch/blackfin/configs/BF533-EZKIT_defconfig index 334c94b..0a2a00d 100644 --- a/arch/blackfin/configs/BF533-EZKIT_defconfig +++ b/arch/blackfin/configs/BF533-EZKIT_defconfig @@ -290,8 +290,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/BF533-STAMP_defconfig b/arch/blackfin/configs/BF533-STAMP_defconfig index 9d73343..eb02758 100644 --- a/arch/blackfin/configs/BF533-STAMP_defconfig +++ b/arch/blackfin/configs/BF533-STAMP_defconfig @@ -290,8 +290,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/BF537-STAMP_defconfig b/arch/blackfin/configs/BF537-STAMP_defconfig index 4fb4108..9e62b9f 100644 --- a/arch/blackfin/configs/BF537-STAMP_defconfig +++ b/arch/blackfin/configs/BF537-STAMP_defconfig @@ -298,8 +298,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # @@ -568,15 +568,7 @@ CONFIG_MTD_PHYSMAP_BANKWIDTH=2 # CONFIG_MTD_DOC2000 is not set # CONFIG_MTD_DOC2001 is not set # CONFIG_MTD_DOC2001PLUS is not set -CONFIG_MTD_NAND=m -# CONFIG_MTD_NAND_VERIFY_WRITE is not set -# CONFIG_MTD_NAND_ECC_SMC is not set -# CONFIG_MTD_NAND_MUSEUM_IDS is not set -# CONFIG_MTD_NAND_BFIN is not set -CONFIG_MTD_NAND_IDS=m -# CONFIG_MTD_NAND_DISKONCHIP is not set -# CONFIG_MTD_NAND_NANDSIM is not set -CONFIG_MTD_NAND_PLATFORM=m +# CONFIG_MTD_NAND is not set # CONFIG_MTD_ONENAND is not set # diff --git a/arch/blackfin/configs/BF538-EZKIT_defconfig b/arch/blackfin/configs/BF538-EZKIT_defconfig index cb32f56..dd6ad6b 100644 --- a/arch/blackfin/configs/BF538-EZKIT_defconfig +++ b/arch/blackfin/configs/BF538-EZKIT_defconfig @@ -306,8 +306,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/BF548-EZKIT_defconfig b/arch/blackfin/configs/BF548-EZKIT_defconfig index 0f86976..6bc2fb1 100644 --- a/arch/blackfin/configs/BF548-EZKIT_defconfig +++ b/arch/blackfin/configs/BF548-EZKIT_defconfig @@ -361,8 +361,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_BFIN_L2_CACHEABLE is not set # CONFIG_MPU is not set @@ -680,7 +680,7 @@ CONFIG_SCSI=y CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set # CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y +# CONFIG_SCSI_PROC_FS is not set # # SCSI support type (disk, tape, CD-ROM) diff --git a/arch/blackfin/configs/BF561-EZKIT_defconfig b/arch/blackfin/configs/BF561-EZKIT_defconfig index 042c7ad..69714fb 100644 --- a/arch/blackfin/configs/BF561-EZKIT_defconfig +++ b/arch/blackfin/configs/BF561-EZKIT_defconfig @@ -329,8 +329,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_BFIN_L2_CACHEABLE is not set # CONFIG_MPU is not set diff --git a/arch/blackfin/configs/BlackStamp_defconfig b/arch/blackfin/configs/BlackStamp_defconfig index 3a20e28..017c6ea 100644 --- a/arch/blackfin/configs/BlackStamp_defconfig +++ b/arch/blackfin/configs/BlackStamp_defconfig @@ -288,8 +288,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/CM-BF527_defconfig b/arch/blackfin/configs/CM-BF527_defconfig index 865ed85..d880ef7 100644 --- a/arch/blackfin/configs/CM-BF527_defconfig +++ b/arch/blackfin/configs/CM-BF527_defconfig @@ -332,8 +332,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set # CONFIG_MPU is not set # diff --git a/arch/blackfin/configs/CM-BF548_defconfig b/arch/blackfin/configs/CM-BF548_defconfig index efe9741..f410430 100644 --- a/arch/blackfin/configs/CM-BF548_defconfig +++ b/arch/blackfin/configs/CM-BF548_defconfig @@ -336,8 +336,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set CONFIG_L1_MAX_PIECE=16 # CONFIG_MPU is not set @@ -595,7 +595,7 @@ CONFIG_SCSI=y CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set # CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y +# CONFIG_SCSI_PROC_FS is not set # # SCSI support type (disk, tape, CD-ROM) diff --git a/arch/blackfin/configs/IP0X_defconfig b/arch/blackfin/configs/IP0X_defconfig index eae83b5..7db9387 100644 --- a/arch/blackfin/configs/IP0X_defconfig +++ b/arch/blackfin/configs/IP0X_defconfig @@ -612,7 +612,7 @@ CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 CONFIG_SCSI=y # CONFIG_SCSI_TGT is not set # CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y +# CONFIG_SCSI_PROC_FS is not set # # SCSI support type (disk, tape, CD-ROM) diff --git a/arch/blackfin/configs/SRV1_defconfig b/arch/blackfin/configs/SRV1_defconfig index fa580af..a46529c 100644 --- a/arch/blackfin/configs/SRV1_defconfig +++ b/arch/blackfin/configs/SRV1_defconfig @@ -282,8 +282,8 @@ CONFIG_BFIN_ICACHE=y CONFIG_BFIN_DCACHE=y # CONFIG_BFIN_DCACHE_BANKA is not set # CONFIG_BFIN_ICACHE_LOCK is not set -# CONFIG_BFIN_WB is not set -CONFIG_BFIN_WT=y +CONFIG_BFIN_WB=y +# CONFIG_BFIN_WT is not set CONFIG_L1_MAX_PIECE=16 # diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 606ecfd..09c3141 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -1,3 +1,4 @@ include include/asm-generic/Kbuild.asm +unifdef-y += bfin_sport.h unifdef-y += fixed_code.h diff --git a/arch/blackfin/include/asm/bfin_sport.h b/arch/blackfin/include/asm/bfin_sport.h index fe88a2c..65a651d 100644 --- a/arch/blackfin/include/asm/bfin_sport.h +++ b/arch/blackfin/include/asm/bfin_sport.h @@ -1,30 +1,9 @@ /* - * File: include/asm-blackfin/bfin_sport.h - * Based on: - * Author: Roy Huang (roy.huang@analog.com) + * bfin_sport.h - userspace header for bfin sport driver * - * Created: Thu Aug. 24 2006 - * Description: + * Copyright 2004-2008 Analog Devices Inc. * - * Modified: - * Copyright 2004-2006 Analog Devices Inc. - * - * Bugs: Enter bugs at http://blackfin.uclinux.org/ - * - * 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, see the file COPYING, or write - * to the Free Software Foundation, Inc., - * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * Licensed under the GPL-2 or later. */ #ifndef __BFIN_SPORT_H__ @@ -42,11 +21,10 @@ #define NORM_FORMAT 0x0 #define ALAW_FORMAT 0x2 #define ULAW_FORMAT 0x3 -struct sport_register; /* Function driver which use sport must initialize the structure */ struct sport_config { - /*TDM (multichannels), I2S or other mode */ + /* TDM (multichannels), I2S or other mode */ unsigned int mode:3; /* if TDM mode is selected, channels must be set */ @@ -72,12 +50,18 @@ struct sport_config { int serial_clk; int fsync_clk; - unsigned int data_format:2; /*Normal, u-law or a-law */ + unsigned int data_format:2; /* Normal, u-law or a-law */ int word_len; /* How length of the word in bits, 3-32 bits */ int dma_enabled; }; +/* Userspace interface */ +#define SPORT_IOC_MAGIC 'P' +#define SPORT_IOC_CONFIG _IOWR('P', 0x01, struct sport_config) + +#ifdef __KERNEL__ + struct sport_register { unsigned short tcr1; unsigned short reserved0; @@ -117,9 +101,6 @@ struct sport_register { unsigned long mrcs3; }; -#define SPORT_IOC_MAGIC 'P' -#define SPORT_IOC_CONFIG _IOWR('P', 0x01, struct sport_config) - struct sport_dev { struct cdev cdev; /* Char device structure */ @@ -149,6 +130,8 @@ struct sport_dev { struct sport_config config; }; +#endif + #define SPORT_TCR1 0 #define SPORT_TCR2 1 #define SPORT_TCLKDIV 2 @@ -169,4 +152,4 @@ struct sport_dev { #define SPORT_MRCS2 22 #define SPORT_MRCS3 23 -#endif /*__BFIN_SPORT_H__*/ +#endif diff --git a/arch/blackfin/include/asm/ftrace.h b/arch/blackfin/include/asm/ftrace.h new file mode 100644 index 0000000..40a8c17 --- /dev/null +++ b/arch/blackfin/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/blackfin/include/asm/ipipe.h b/arch/blackfin/include/asm/ipipe.h index 76f53d8..343b563 100644 --- a/arch/blackfin/include/asm/ipipe.h +++ b/arch/blackfin/include/asm/ipipe.h @@ -35,9 +35,9 @@ #include #include -#define IPIPE_ARCH_STRING "1.8-00" +#define IPIPE_ARCH_STRING "1.9-00" #define IPIPE_MAJOR_NUMBER 1 -#define IPIPE_MINOR_NUMBER 8 +#define IPIPE_MINOR_NUMBER 9 #define IPIPE_PATCH_NUMBER 0 #ifdef CONFIG_SMP @@ -83,9 +83,9 @@ struct ipipe_sysinfo { "%2 = CYCLES2\n" \ "CC = %2 == %0\n" \ "if ! CC jump 1b\n" \ - : "=r" (((unsigned long *)&t)[1]), \ - "=r" (((unsigned long *)&t)[0]), \ - "=r" (__cy2) \ + : "=d,a" (((unsigned long *)&t)[1]), \ + "=d,a" (((unsigned long *)&t)[0]), \ + "=d,a" (__cy2) \ : /*no input*/ : "CC"); \ t; \ }) @@ -118,35 +118,40 @@ void __ipipe_disable_irqdesc(struct ipipe_domain *ipd, #define __ipipe_disable_irq(irq) (irq_desc[irq].chip->mask(irq)) -#define __ipipe_lock_root() \ - set_bit(IPIPE_ROOTLOCK_FLAG, &ipipe_root_domain->flags) +static inline int __ipipe_check_tickdev(const char *devname) +{ + return 1; +} -#define __ipipe_unlock_root() \ - clear_bit(IPIPE_ROOTLOCK_FLAG, &ipipe_root_domain->flags) +static inline void __ipipe_lock_root(void) +{ + set_bit(IPIPE_SYNCDEFER_FLAG, &ipipe_root_cpudom_var(status)); +} + +static inline void __ipipe_unlock_root(void) +{ + clear_bit(IPIPE_SYNCDEFER_FLAG, &ipipe_root_cpudom_var(status)); +} void __ipipe_enable_pipeline(void); #define __ipipe_hook_critical_ipi(ipd) do { } while (0) -#define __ipipe_sync_pipeline(syncmask) \ - do { \ - struct ipipe_domain *ipd = ipipe_current_domain; \ - if (likely(ipd != ipipe_root_domain || !test_bit(IPIPE_ROOTLOCK_FLAG, &ipd->flags))) \ - __ipipe_sync_stage(syncmask); \ - } while (0) +#define __ipipe_sync_pipeline ___ipipe_sync_pipeline +void ___ipipe_sync_pipeline(unsigned long syncmask); void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs); int __ipipe_get_irq_priority(unsigned irq); -int __ipipe_get_irqthread_priority(unsigned irq); - void __ipipe_stall_root_raw(void); void __ipipe_unstall_root_raw(void); void __ipipe_serial_debug(const char *fmt, ...); +asmlinkage void __ipipe_call_irqtail(unsigned long addr); + DECLARE_PER_CPU(struct pt_regs, __ipipe_tick_regs); extern unsigned long __ipipe_core_clock; @@ -162,42 +167,25 @@ static inline unsigned long __ipipe_ffnz(unsigned long ul) #define __ipipe_run_irqtail() /* Must be a macro */ \ do { \ - asmlinkage void __ipipe_call_irqtail(void); \ unsigned long __pending; \ - CSYNC(); \ + CSYNC(); \ __pending = bfin_read_IPEND(); \ if (__pending & 0x8000) { \ __pending &= ~0x8010; \ if (__pending && (__pending & (__pending - 1)) == 0) \ - __ipipe_call_irqtail(); \ + __ipipe_call_irqtail(__ipipe_irq_tail_hook); \ } \ } while (0) #define __ipipe_run_isr(ipd, irq) \ do { \ if (ipd == ipipe_root_domain) { \ - /* \ - * Note: the I-pipe implements a threaded interrupt model on \ - * this arch for Linux external IRQs. The interrupt handler we \ - * call here only wakes up the associated IRQ thread. \ - */ \ - if (ipipe_virtual_irq_p(irq)) { \ - /* No irqtail here; virtual interrupts have no effect \ - on IPEND so there is no need for processing \ - deferral. */ \ - local_irq_enable_nohead(ipd); \ + local_irq_enable_hw(); \ + if (ipipe_virtual_irq_p(irq)) \ ipd->irqs[irq].handler(irq, ipd->irqs[irq].cookie); \ - local_irq_disable_nohead(ipd); \ - } else \ - /* \ - * No need to run the irqtail here either; \ - * we can't be preempted by hw IRQs, so \ - * non-Linux IRQs cannot stack over the short \ - * thread wakeup code. Which in turn means \ - * that no irqtail condition could be pending \ - * for domains above Linux in the pipeline. \ - */ \ + else \ ipd->irqs[irq].handler(irq, &__raw_get_cpu_var(__ipipe_tick_regs)); \ + local_irq_disable_hw(); \ } else { \ __clear_bit(IPIPE_SYNC_FLAG, &ipipe_cpudom_var(ipd, status)); \ local_irq_enable_nohead(ipd); \ @@ -217,42 +205,24 @@ void ipipe_init_irq_threads(void); int ipipe_start_irq_thread(unsigned irq, struct irq_desc *desc); -#define IS_SYSIRQ(irq) ((irq) > IRQ_CORETMR && (irq) <= SYS_IRQS) -#define IS_GPIOIRQ(irq) ((irq) >= GPIO_IRQ_BASE && (irq) < NR_IRQS) - +#ifdef CONFIG_GENERIC_CLOCKEVENTS +#define IRQ_SYSTMR IRQ_CORETMR +#define IRQ_PRIOTMR IRQ_CORETMR +#else #define IRQ_SYSTMR IRQ_TIMER0 #define IRQ_PRIOTMR CONFIG_IRQ_TIMER0 +#endif -#if defined(CONFIG_BF531) || defined(CONFIG_BF532) || defined(CONFIG_BF533) -#define PRIO_GPIODEMUX(irq) CONFIG_PFA -#elif defined(CONFIG_BF534) || defined(CONFIG_BF536) || defined(CONFIG_BF537) -#define PRIO_GPIODEMUX(irq) CONFIG_IRQ_PROG_INTA -#elif defined(CONFIG_BF52x) -#define PRIO_GPIODEMUX(irq) ((irq) == IRQ_PORTF_INTA ? CONFIG_IRQ_PORTF_INTA : \ - (irq) == IRQ_PORTG_INTA ? CONFIG_IRQ_PORTG_INTA : \ - (irq) == IRQ_PORTH_INTA ? CONFIG_IRQ_PORTH_INTA : \ - -1) -#elif defined(CONFIG_BF561) -#define PRIO_GPIODEMUX(irq) ((irq) == IRQ_PROG0_INTA ? CONFIG_IRQ_PROG0_INTA : \ - (irq) == IRQ_PROG1_INTA ? CONFIG_IRQ_PROG1_INTA : \ - (irq) == IRQ_PROG2_INTA ? CONFIG_IRQ_PROG2_INTA : \ - -1) +#ifdef CONFIG_BF561 #define bfin_write_TIMER_DISABLE(val) bfin_write_TMRS8_DISABLE(val) #define bfin_write_TIMER_ENABLE(val) bfin_write_TMRS8_ENABLE(val) #define bfin_write_TIMER_STATUS(val) bfin_write_TMRS8_STATUS(val) #define bfin_read_TIMER_STATUS() bfin_read_TMRS8_STATUS() #elif defined(CONFIG_BF54x) -#define PRIO_GPIODEMUX(irq) ((irq) == IRQ_PINT0 ? CONFIG_IRQ_PINT0 : \ - (irq) == IRQ_PINT1 ? CONFIG_IRQ_PINT1 : \ - (irq) == IRQ_PINT2 ? CONFIG_IRQ_PINT2 : \ - (irq) == IRQ_PINT3 ? CONFIG_IRQ_PINT3 : \ - -1) #define bfin_write_TIMER_DISABLE(val) bfin_write_TIMER_DISABLE0(val) #define bfin_write_TIMER_ENABLE(val) bfin_write_TIMER_ENABLE0(val) #define bfin_write_TIMER_STATUS(val) bfin_write_TIMER_STATUS0(val) #define bfin_read_TIMER_STATUS(val) bfin_read_TIMER_STATUS0(val) -#else -# error "no PRIO_GPIODEMUX() for this part" #endif #define __ipipe_root_tick_p(regs) ((regs->ipend & 0x10) != 0) @@ -275,4 +245,6 @@ int ipipe_start_irq_thread(unsigned irq, struct irq_desc *desc); #endif /* !CONFIG_IPIPE */ +#define ipipe_update_tick_evtdev(evtdev) do { } while (0) + #endif /* !__ASM_BLACKFIN_IPIPE_H */ diff --git a/arch/blackfin/include/asm/ipipe_base.h b/arch/blackfin/include/asm/ipipe_base.h index cb1025a..3e8acbd 100644 --- a/arch/blackfin/include/asm/ipipe_base.h +++ b/arch/blackfin/include/asm/ipipe_base.h @@ -1,5 +1,5 @@ /* -*- linux-c -*- - * include/asm-blackfin/_baseipipe.h + * include/asm-blackfin/ipipe_base.h * * Copyright (C) 2007 Philippe Gerum. * @@ -27,8 +27,9 @@ #define IPIPE_NR_XIRQS NR_IRQS #define IPIPE_IRQ_ISHIFT 5 /* 2^5 for 32bits arch. */ -/* Blackfin-specific, global domain flags */ -#define IPIPE_ROOTLOCK_FLAG 1 /* Lock pipeline for root */ +/* Blackfin-specific, per-cpu pipeline status */ +#define IPIPE_SYNCDEFER_FLAG 15 +#define IPIPE_SYNCDEFER_MASK (1L << IPIPE_SYNCDEFER_MASK) /* Blackfin traps -- i.e. exception vector numbers */ #define IPIPE_NR_FAULTS 52 /* We leave a gap after VEC_ILL_RES. */ @@ -48,11 +49,6 @@ #ifndef __ASSEMBLY__ -#include - -extern int test_bit(int nr, const void *addr); - - extern unsigned long __ipipe_root_status; /* Alias to ipipe_root_cpudom_var(status) */ static inline void __ipipe_stall_root(void) diff --git a/arch/blackfin/include/asm/irq.h b/arch/blackfin/include/asm/irq.h index 3d97790..7645e85 100644 --- a/arch/blackfin/include/asm/irq.h +++ b/arch/blackfin/include/asm/irq.h @@ -61,20 +61,38 @@ void __ipipe_restore_root(unsigned long flags); #define raw_irqs_disabled_flags(flags) (!irqs_enabled_from_flags_hw(flags)) #define local_test_iflag_hw(x) irqs_enabled_from_flags_hw(x) -#define local_save_flags(x) \ - do { \ - (x) = __ipipe_test_root() ? \ +#define local_save_flags(x) \ + do { \ + (x) = __ipipe_test_root() ? \ __all_masked_irq_flags : bfin_irq_flags; \ + barrier(); \ } while (0) -#define local_irq_save(x) \ - do { \ - (x) = __ipipe_test_and_stall_root(); \ +#define local_irq_save(x) \ + do { \ + (x) = __ipipe_test_and_stall_root() ? \ + __all_masked_irq_flags : bfin_irq_flags; \ + barrier(); \ + } while (0) + +static inline void local_irq_restore(unsigned long x) +{ + barrier(); + __ipipe_restore_root(x == __all_masked_irq_flags); +} + +#define local_irq_disable() \ + do { \ + __ipipe_stall_root(); \ + barrier(); \ } while (0) -#define local_irq_restore(x) __ipipe_restore_root(x) -#define local_irq_disable() __ipipe_stall_root() -#define local_irq_enable() __ipipe_unstall_root() +static inline void local_irq_enable(void) +{ + barrier(); + __ipipe_unstall_root(); +} + #define irqs_disabled() __ipipe_test_root() #define local_save_flags_hw(x) \ diff --git a/arch/blackfin/include/asm/percpu.h b/arch/blackfin/include/asm/percpu.h index 797c0c1..c94c7bc 100644 --- a/arch/blackfin/include/asm/percpu.h +++ b/arch/blackfin/include/asm/percpu.h @@ -3,14 +3,4 @@ #include -#ifdef CONFIG_MODULES -#define PERCPU_MODULE_RESERVE 8192 -#else -#define PERCPU_MODULE_RESERVE 0 -#endif - -#define PERCPU_ENOUGH_ROOM \ - (ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \ - PERCPU_MODULE_RESERVE) - #endif /* __ARCH_BLACKFIN_PERCPU__ */ diff --git a/arch/blackfin/include/asm/swab.h b/arch/blackfin/include/asm/swab.h index 69a051b..6403ad2 100644 --- a/arch/blackfin/include/asm/swab.h +++ b/arch/blackfin/include/asm/swab.h @@ -1,7 +1,7 @@ #ifndef _BLACKFIN_SWAB_H #define _BLACKFIN_SWAB_H -#include +#include #include #if defined(__GNUC__) && !defined(__STRICT_ANSI__) || defined(__KERNEL__) diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h index e721ce5..2920087 100644 --- a/arch/blackfin/include/asm/thread_info.h +++ b/arch/blackfin/include/asm/thread_info.h @@ -122,6 +122,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_MEMDIE 4 #define TIF_RESTORE_SIGMASK 5 /* restore signal mask in do_signal() */ #define TIF_FREEZE 6 /* is freezing for suspend */ +#define TIF_IRQ_SYNC 7 /* sync pipeline stage */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1< #include -static int create_irq_threads; - DEFINE_PER_CPU(struct pt_regs, __ipipe_tick_regs); -static DEFINE_PER_CPU(unsigned long, pending_irqthread_mask); - -static DEFINE_PER_CPU(int [IVG13 + 1], pending_irq_count); - asmlinkage void asm_do_IRQ(unsigned int irq, struct pt_regs *regs); static void __ipipe_no_irqtail(void); @@ -93,6 +87,7 @@ void __ipipe_enable_pipeline(void) */ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs) { + struct ipipe_percpu_domain_data *p = ipipe_root_cpudom_ptr(); struct ipipe_domain *this_domain, *next_domain; struct list_head *head, *pos; int m_ack, s = -1; @@ -104,7 +99,6 @@ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs) * interrupt. */ m_ack = (regs == NULL || irq == IRQ_SYSTMR || irq == IRQ_CORETMR); - this_domain = ipipe_current_domain; if (unlikely(test_bit(IPIPE_STICKY_FLAG, &this_domain->irqs[irq].control))) @@ -114,49 +108,28 @@ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs) next_domain = list_entry(head, struct ipipe_domain, p_link); if (likely(test_bit(IPIPE_WIRED_FLAG, &next_domain->irqs[irq].control))) { if (!m_ack && next_domain->irqs[irq].acknowledge != NULL) - next_domain->irqs[irq].acknowledge(irq, irq_desc + irq); - if (test_bit(IPIPE_ROOTLOCK_FLAG, &ipipe_root_domain->flags)) - s = __test_and_set_bit(IPIPE_STALL_FLAG, - &ipipe_root_cpudom_var(status)); + next_domain->irqs[irq].acknowledge(irq, irq_to_desc(irq)); + if (test_bit(IPIPE_SYNCDEFER_FLAG, &p->status)) + s = __test_and_set_bit(IPIPE_STALL_FLAG, &p->status); __ipipe_dispatch_wired(next_domain, irq); - goto finalize; - return; + goto out; } } /* Ack the interrupt. */ pos = head; - while (pos != &__ipipe_pipeline) { next_domain = list_entry(pos, struct ipipe_domain, p_link); - /* - * For each domain handling the incoming IRQ, mark it - * as pending in its log. - */ if (test_bit(IPIPE_HANDLE_FLAG, &next_domain->irqs[irq].control)) { - /* - * Domains that handle this IRQ are polled for - * acknowledging it by decreasing priority - * order. The interrupt must be made pending - * _first_ in the domain's status flags before - * the PIC is unlocked. - */ __ipipe_set_irq_pending(next_domain, irq); - if (!m_ack && next_domain->irqs[irq].acknowledge != NULL) { - next_domain->irqs[irq].acknowledge(irq, irq_desc + irq); + next_domain->irqs[irq].acknowledge(irq, irq_to_desc(irq)); m_ack = 1; } } - - /* - * If the domain does not want the IRQ to be passed - * down the interrupt pipe, exit the loop now. - */ if (!test_bit(IPIPE_PASS_FLAG, &next_domain->irqs[irq].control)) break; - pos = next_domain->p_link.next; } @@ -166,18 +139,24 @@ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs) * immediately to the current domain if the interrupt has been * marked as 'sticky'. This search does not go beyond the * current domain in the pipeline. We also enforce the - * additional root stage lock (blackfin-specific). */ + * additional root stage lock (blackfin-specific). + */ + if (test_bit(IPIPE_SYNCDEFER_FLAG, &p->status)) + s = __test_and_set_bit(IPIPE_STALL_FLAG, &p->status); - if (test_bit(IPIPE_ROOTLOCK_FLAG, &ipipe_root_domain->flags)) - s = __test_and_set_bit(IPIPE_STALL_FLAG, - &ipipe_root_cpudom_var(status)); -finalize: + /* + * If the interrupt preempted the head domain, then do not + * even try to walk the pipeline, unless an interrupt is + * pending for it. + */ + if (test_bit(IPIPE_AHEAD_FLAG, &this_domain->flags) && + ipipe_head_cpudom_var(irqpend_himask) == 0) + goto out; __ipipe_walk_pipeline(head); - +out: if (!s) - __clear_bit(IPIPE_STALL_FLAG, - &ipipe_root_cpudom_var(status)); + __clear_bit(IPIPE_STALL_FLAG, &p->status); } int __ipipe_check_root(void) @@ -187,7 +166,7 @@ int __ipipe_check_root(void) void __ipipe_enable_irqdesc(struct ipipe_domain *ipd, unsigned irq) { - struct irq_desc *desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); int prio = desc->ic_prio; desc->depth = 0; @@ -199,7 +178,7 @@ EXPORT_SYMBOL(__ipipe_enable_irqdesc); void __ipipe_disable_irqdesc(struct ipipe_domain *ipd, unsigned irq) { - struct irq_desc *desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); int prio = desc->ic_prio; if (ipd != &ipipe_root && @@ -236,15 +215,18 @@ int __ipipe_syscall_root(struct pt_regs *regs) { unsigned long flags; - /* We need to run the IRQ tail hook whenever we don't + /* + * We need to run the IRQ tail hook whenever we don't * propagate a syscall to higher domains, because we know that * important operations might be pending there (e.g. Xenomai - * deferred rescheduling). */ + * deferred rescheduling). + */ - if (!__ipipe_syscall_watched_p(current, regs->orig_p0)) { + if (regs->orig_p0 < NR_syscalls) { void (*hook)(void) = (void (*)(void))__ipipe_irq_tail_hook; hook(); - return 0; + if ((current->flags & PF_EVNOTIFY) == 0) + return 0; } /* @@ -312,112 +294,46 @@ int ipipe_trigger_irq(unsigned irq) { unsigned long flags; +#ifdef CONFIG_IPIPE_DEBUG if (irq >= IPIPE_NR_IRQS || (ipipe_virtual_irq_p(irq) && !test_bit(irq - IPIPE_VIRQ_BASE, &__ipipe_virtual_irq_map))) return -EINVAL; +#endif local_irq_save_hw(flags); - __ipipe_handle_irq(irq, NULL); - local_irq_restore_hw(flags); return 1; } -/* Move Linux IRQ to threads. */ - -static int do_irqd(void *__desc) +asmlinkage void __ipipe_sync_root(void) { - struct irq_desc *desc = __desc; - unsigned irq = desc - irq_desc; - int thrprio = desc->thr_prio; - int thrmask = 1 << thrprio; - int cpu = smp_processor_id(); - cpumask_t cpumask; - - sigfillset(¤t->blocked); - current->flags |= PF_NOFREEZE; - cpumask = cpumask_of_cpu(cpu); - set_cpus_allowed(current, cpumask); - ipipe_setscheduler_root(current, SCHED_FIFO, 50 + thrprio); - - while (!kthread_should_stop()) { - local_irq_disable(); - if (!(desc->status & IRQ_SCHEDULED)) { - set_current_state(TASK_INTERRUPTIBLE); -resched: - local_irq_enable(); - schedule(); - local_irq_disable(); - } - __set_current_state(TASK_RUNNING); - /* - * If higher priority interrupt servers are ready to - * run, reschedule immediately. We need this for the - * GPIO demux IRQ handler to unmask the interrupt line - * _last_, after all GPIO IRQs have run. - */ - if (per_cpu(pending_irqthread_mask, cpu) & ~(thrmask|(thrmask-1))) - goto resched; - if (--per_cpu(pending_irq_count[thrprio], cpu) == 0) - per_cpu(pending_irqthread_mask, cpu) &= ~thrmask; - desc->status &= ~IRQ_SCHEDULED; - desc->thr_handler(irq, &__raw_get_cpu_var(__ipipe_tick_regs)); - local_irq_enable(); - } - __set_current_state(TASK_RUNNING); - return 0; -} + unsigned long flags; -static void kick_irqd(unsigned irq, void *cookie) -{ - struct irq_desc *desc = irq_desc + irq; - int thrprio = desc->thr_prio; - int thrmask = 1 << thrprio; - int cpu = smp_processor_id(); - - if (!(desc->status & IRQ_SCHEDULED)) { - desc->status |= IRQ_SCHEDULED; - per_cpu(pending_irqthread_mask, cpu) |= thrmask; - ++per_cpu(pending_irq_count[thrprio], cpu); - wake_up_process(desc->thread); - } -} + BUG_ON(irqs_disabled()); -int ipipe_start_irq_thread(unsigned irq, struct irq_desc *desc) -{ - if (desc->thread || !create_irq_threads) - return 0; - - desc->thread = kthread_create(do_irqd, desc, "IRQ %d", irq); - if (desc->thread == NULL) { - printk(KERN_ERR "irqd: could not create IRQ thread %d!\n", irq); - return -ENOMEM; - } + local_irq_save_hw(flags); - wake_up_process(desc->thread); + clear_thread_flag(TIF_IRQ_SYNC); - desc->thr_handler = ipipe_root_domain->irqs[irq].handler; - ipipe_root_domain->irqs[irq].handler = &kick_irqd; + if (ipipe_root_cpudom_var(irqpend_himask) != 0) + __ipipe_sync_pipeline(IPIPE_IRQMASK_ANY); - return 0; + local_irq_restore_hw(flags); } -void __init ipipe_init_irq_threads(void) +void ___ipipe_sync_pipeline(unsigned long syncmask) { - unsigned irq; - struct irq_desc *desc; - - create_irq_threads = 1; + struct ipipe_domain *ipd = ipipe_current_domain; - for (irq = 0; irq < NR_IRQS; irq++) { - desc = irq_desc + irq; - if (desc->action != NULL || - (desc->status & IRQ_NOREQUEST) != 0) - ipipe_start_irq_thread(irq, desc); + if (ipd == ipipe_root_domain) { + if (test_bit(IPIPE_SYNCDEFER_FLAG, &ipipe_root_cpudom_var(status))) + return; } + + __ipipe_sync_stage(syncmask); } EXPORT_SYMBOL(show_stack); diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c index 75724ee..401bd32 100644 --- a/arch/blackfin/kernel/irqchip.c +++ b/arch/blackfin/kernel/irqchip.c @@ -70,6 +70,11 @@ static struct irq_desc bad_irq_desc = { #endif }; +#ifdef CONFIG_CPUMASK_OFFSTACK +/* We are not allocating a variable-sized bad_irq_desc.affinity */ +#error "Blackfin architecture does not support CONFIG_CPUMASK_OFFSTACK." +#endif + int show_interrupts(struct seq_file *p, void *v) { int i = *(loff_t *) v, j; @@ -83,7 +88,7 @@ int show_interrupts(struct seq_file *p, void *v) goto skip; seq_printf(p, "%3d: ", i); for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); seq_printf(p, " %8s", irq_desc[i].chip->name); seq_printf(p, " %s", action->name); for (action = action->next; action; action = action->next) @@ -144,11 +149,15 @@ asmlinkage void asm_do_IRQ(unsigned int irq, struct pt_regs *regs) #endif generic_handle_irq(irq); -#ifndef CONFIG_IPIPE /* Useless and bugous over the I-pipe: IRQs are threaded. */ - /* If we're the only interrupt running (ignoring IRQ15 which is for - syscalls), lower our priority to IRQ14 so that softirqs run at - that level. If there's another, lower-level interrupt, irq_exit - will defer softirqs to that. */ +#ifndef CONFIG_IPIPE + /* + * If we're the only interrupt running (ignoring IRQ15 which + * is for syscalls), lower our priority to IRQ14 so that + * softirqs run at that level. If there's another, + * lower-level interrupt, irq_exit will defer softirqs to + * that. If the interrupt pipeline is enabled, we are already + * running at IRQ14 priority, so we don't need this code. + */ CSYNC(); pending = bfin_read_IPEND() & ~0x8000; other_ints = pending & (pending - 1); diff --git a/arch/blackfin/kernel/kgdb_test.c b/arch/blackfin/kernel/kgdb_test.c index 3dba9c1..dbcf3e4 100644 --- a/arch/blackfin/kernel/kgdb_test.c +++ b/arch/blackfin/kernel/kgdb_test.c @@ -20,6 +20,7 @@ static char cmdline[256]; static unsigned long len; +#ifndef CONFIG_SMP static int num1 __attribute__((l1_data)); void kgdb_l1_test(void) __attribute__((l1_text)); @@ -32,6 +33,8 @@ void kgdb_l1_test(void) printk(KERN_ALERT "L1(after change) : data variable addr = 0x%p, data value is %d\n", &num1, num1); return ; } +#endif + #if L2_LENGTH static int num2 __attribute__((l2)); @@ -59,10 +62,12 @@ int kgdb_test(char *name, int len, int count, int z) static int test_proc_output(char *buf) { kgdb_test("hello world!", 12, 0x55, 0x10); +#ifndef CONFIG_SMP kgdb_l1_test(); - #if L2_LENGTH +#endif +#if L2_LENGTH kgdb_l2_test(); - #endif +#endif return 0; } diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c index 594e325..d76618d 100644 --- a/arch/blackfin/kernel/ptrace.c +++ b/arch/blackfin/kernel/ptrace.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #define TEXT_OFFSET 0 @@ -240,7 +241,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } else if (addr >= FIXED_CODE_START && addr + sizeof(tmp) <= FIXED_CODE_END) { - memcpy(&tmp, (const void *)(addr), sizeof(tmp)); + copy_from_user_page(0, 0, 0, &tmp, (const void *)(addr), sizeof(tmp)); copied = sizeof(tmp); } else @@ -320,7 +321,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } else if (addr >= FIXED_CODE_START && addr + sizeof(data) <= FIXED_CODE_END) { - memcpy((void *)(addr), &data, sizeof(data)); + copy_to_user_page(0, 0, 0, (void *)(addr), &data, sizeof(data)); copied = sizeof(data); } else diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c index e5c1162..a58687b 100644 --- a/arch/blackfin/kernel/setup.c +++ b/arch/blackfin/kernel/setup.c @@ -889,6 +889,10 @@ void __init setup_arch(char **cmdline_p) CPU, bfin_revid()); } + /* We can't run on BF548-0.1 due to ANOMALY 05000448 */ + if (bfin_cpuid() == 0x27de && bfin_revid() == 1) + panic("You can't run on this processor due to 05000448\n"); + printk(KERN_INFO "Blackfin Linux support by http://blackfin.uclinux.org/\n"); printk(KERN_INFO "Processor Speed: %lu MHz core clock and %lu MHz System Clock\n", @@ -1141,12 +1145,12 @@ static int show_cpuinfo(struct seq_file *m, void *v) icache_size = 0; seq_printf(m, "cache size\t: %d KB(L1 icache) " - "%d KB(L1 dcache-%s) %d KB(L2 cache)\n", + "%d KB(L1 dcache%s) %d KB(L2 cache)\n", icache_size, dcache_size, #if defined CONFIG_BFIN_WB - "wb" + "-wb" #elif defined CONFIG_BFIN_WT - "wt" + "-wt" #endif "", 0); diff --git a/arch/blackfin/kernel/time.c b/arch/blackfin/kernel/time.c index 172b4c5..1bbacfb 100644 --- a/arch/blackfin/kernel/time.c +++ b/arch/blackfin/kernel/time.c @@ -134,7 +134,10 @@ irqreturn_t timer_interrupt(int irq, void *dummy) write_seqlock(&xtime_lock); #if defined(CONFIG_TICK_SOURCE_SYSTMR0) && !defined(CONFIG_IPIPE) -/* FIXME: Here TIMIL0 is not set when IPIPE enabled, why? */ + /* + * TIMIL0 is latched in __ipipe_grab_irq() when the I-Pipe is + * enabled. + */ if (get_gptimer_status(0) & TIMER_STATUS_TIMIL0) { #endif do_timer(1); diff --git a/arch/blackfin/mach-bf518/boards/ezbrd.c b/arch/blackfin/mach-bf518/boards/ezbrd.c index 0e17534..41f2eac 100644 --- a/arch/blackfin/mach-bf518/boards/ezbrd.c +++ b/arch/blackfin/mach-bf518/boards/ezbrd.c @@ -113,7 +113,6 @@ static struct platform_device bfin_mac_device = { .name = "bfin_mac", .dev.platform_data = &bfin_mii_bus, }; -#endif #if defined(CONFIG_NET_DSA_KSZ8893M) || defined(CONFIG_NET_DSA_KSZ8893M_MODULE) static struct dsa_platform_data ksz8893m_switch_data = { @@ -132,6 +131,7 @@ static struct platform_device ksz8893m_switch_device = { .dev.platform_data = &ksz8893m_switch_data, }; #endif +#endif #if defined(CONFIG_MTD_M25P80) \ || defined(CONFIG_MTD_M25P80_MODULE) @@ -171,6 +171,7 @@ static struct bfin5xx_spi_chip spi_adc_chip_info = { }; #endif +#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) #if defined(CONFIG_NET_DSA_KSZ8893M) \ || defined(CONFIG_NET_DSA_KSZ8893M_MODULE) /* SPI SWITCH CHIP */ @@ -179,10 +180,11 @@ static struct bfin5xx_spi_chip spi_switch_info = { .bits_per_word = 8, }; #endif +#endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -259,6 +261,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif +#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) #if defined(CONFIG_NET_DSA_KSZ8893M) \ || defined(CONFIG_NET_DSA_KSZ8893M_MODULE) { @@ -271,24 +274,15 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .mode = SPI_MODE_3, }, #endif +#endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc_dummy", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif @@ -630,11 +624,10 @@ static struct platform_device *stamp_devices[] __initdata = { #if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) &bfin_mii_bus, &bfin_mac_device, -#endif - #if defined(CONFIG_NET_DSA_KSZ8893M) || defined(CONFIG_NET_DSA_KSZ8893M_MODULE) &ksz8893m_switch_device, #endif +#endif #if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) &bfin_spi0_device, diff --git a/arch/blackfin/mach-bf518/include/mach/anomaly.h b/arch/blackfin/mach-bf518/include/mach/anomaly.h index e5b4bef..c847bb1 100644 --- a/arch/blackfin/mach-bf518/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf518/include/mach/anomaly.h @@ -2,12 +2,12 @@ * File: include/asm-blackfin/mach-bf518/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ /* This file shoule be up to date with: - * - ???? + * - Revision B, 02/03/2009; ADSP-BF512/BF514/BF516/BF518 Blackfin Processor Anomaly List */ #ifndef _MACH_ANOMALY_H_ @@ -19,6 +19,8 @@ #define ANOMALY_05000122 (1) /* False Hardware Error from an Access in the Shadow of a Conditional Branch */ #define ANOMALY_05000245 (1) +/* Incorrect Timer Pulse Width in Single-Shot PWM_OUT Mode with External Clock */ +#define ANOMALY_05000254 (1) /* Sensitivity To Noise with Slow Input Edge Rates on External SPORT TX and RX Clocks */ #define ANOMALY_05000265 (1) /* False Hardware Errors Caused by Fetches at the Boundary of Reserved Memory */ @@ -53,6 +55,12 @@ #define ANOMALY_05000443 (1) /* Incorrect L1 Instruction Bank B Memory Map Location */ #define ANOMALY_05000444 (1) +/* Incorrect Default Hysteresis Setting for RESET, NMI, and BMODE Signals */ +#define ANOMALY_05000452 (1) +/* PWM_TRIPB Signal Not Available on PG10 */ +#define ANOMALY_05000453 (1) +/* PPI_FS3 is Driven One Half Cycle Later Than PPI Data */ +#define ANOMALY_05000455 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000125 (0) @@ -65,15 +73,20 @@ #define ANOMALY_05000263 (0) #define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) +#define ANOMALY_05000278 (0) #define ANOMALY_05000285 (0) +#define ANOMALY_05000305 (0) #define ANOMALY_05000307 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000312 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000353 (0) #define ANOMALY_05000363 (0) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (0) #define ANOMALY_05000412 (0) #define ANOMALY_05000432 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h index b50a63b..e21c1c3 100644 --- a/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h @@ -144,7 +144,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -158,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif -#ifdef CONFIG_BFIN_UART1_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART1_CTS_PIN, CONFIG_UART1_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf527/boards/cm_bf527.c b/arch/blackfin/mach-bf527/boards/cm_bf527.c index 856c097..48e69ee 100644 --- a/arch/blackfin/mach-bf527/boards/cm_bf527.c +++ b/arch/blackfin/mach-bf527/boards/cm_bf527.c @@ -487,9 +487,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -585,23 +585,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .controller_data = &ad9960_spi_chip_info, }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ + .modalias = "mmc_spi", + .max_speed_hz = 20000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf527/boards/ezbrd.c b/arch/blackfin/mach-bf527/boards/ezbrd.c index 83606fc..7fe480e 100644 --- a/arch/blackfin/mach-bf527/boards/ezbrd.c +++ b/arch/blackfin/mach-bf527/boards/ezbrd.c @@ -256,9 +256,9 @@ static struct bfin5xx_spi_chip spi_adc_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -366,23 +366,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc_dummy", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf527/include/mach/anomaly.h b/arch/blackfin/mach-bf527/include/mach/anomaly.h index 035e8d8..df6808d 100644 --- a/arch/blackfin/mach-bf527/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf527/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf527/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -167,12 +167,16 @@ #define ANOMALY_05000263 (0) #define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) +#define ANOMALY_05000278 (0) #define ANOMALY_05000285 (0) +#define ANOMALY_05000305 (0) #define ANOMALY_05000307 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000312 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000363 (0) #define ANOMALY_05000412 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h index 75722d6..e8c41fd 100644 --- a/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h @@ -144,7 +144,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -158,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif -#ifdef CONFIG_BFIN_UART1_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART1_CTS_PIN, CONFIG_UART1_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf533/boards/Kconfig b/arch/blackfin/mach-bf533/boards/Kconfig index 308c98d..8d8b3e7 100644 --- a/arch/blackfin/mach-bf533/boards/Kconfig +++ b/arch/blackfin/mach-bf533/boards/Kconfig @@ -38,9 +38,4 @@ config BFIN532_IP0X help Core support for IP04/IP04 open hardware IP-PBX. -config GENERIC_BF533_BOARD - bool "Generic" - help - Generic or Custom board support. - endchoice diff --git a/arch/blackfin/mach-bf533/boards/Makefile b/arch/blackfin/mach-bf533/boards/Makefile index 9afbe72..ff1e832 100644 --- a/arch/blackfin/mach-bf533/boards/Makefile +++ b/arch/blackfin/mach-bf533/boards/Makefile @@ -2,7 +2,6 @@ # arch/blackfin/mach-bf533/boards/Makefile # -obj-$(CONFIG_GENERIC_BF533_BOARD) += generic_board.o obj-$(CONFIG_BFIN533_STAMP) += stamp.o obj-$(CONFIG_BFIN532_IP0X) += ip0x.o obj-$(CONFIG_BFIN533_EZKIT) += ezkit.o diff --git a/arch/blackfin/mach-bf533/boards/blackstamp.c b/arch/blackfin/mach-bf533/boards/blackstamp.c index 015c18f..0765872 100644 --- a/arch/blackfin/mach-bf533/boards/blackstamp.c +++ b/arch/blackfin/mach-bf533/boards/blackstamp.c @@ -101,9 +101,9 @@ static struct bfin5xx_spi_chip spi_flash_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -129,23 +129,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 20000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 20000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf533/boards/cm_bf533.c b/arch/blackfin/mach-bf533/boards/cm_bf533.c index e7061c7..e897487 100644 --- a/arch/blackfin/mach-bf533/boards/cm_bf533.c +++ b/arch/blackfin/mach-bf533/boards/cm_bf533.c @@ -96,9 +96,9 @@ static struct bfin5xx_spi_chip ad1836_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -138,23 +138,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf533/boards/generic_board.c b/arch/blackfin/mach-bf533/boards/generic_board.c deleted file mode 100644 index 986eeec..0000000 --- a/arch/blackfin/mach-bf533/boards/generic_board.c +++ /dev/null @@ -1,126 +0,0 @@ -/* - * File: arch/blackfin/mach-bf533/generic_board.c - * Based on: arch/blackfin/mach-bf533/ezkit.c - * Author: Aidan Williams - * - * Created: 2005 - * Description: - * - * Modified: - * Copyright 2005 National ICT Australia (NICTA) - * Copyright 2004-2006 Analog Devices Inc. - * - * Bugs: Enter bugs at http://blackfin.uclinux.org/ - * - * 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, see the file COPYING, or write - * to the Free Software Foundation, Inc., - * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ - -#include -#include -#include - -/* - * Name the Board for the /proc/cpuinfo - */ -const char bfin_board_name[] = "UNKNOWN BOARD"; - -#if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) -static struct platform_device rtc_device = { - .name = "rtc-bfin", - .id = -1, -}; -#endif - -/* - * Driver needs to know address, irq and flag pin. - */ -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) -static struct resource smc91x_resources[] = { - { - .start = 0x20300300, - .end = 0x20300300 + 16, - .flags = IORESOURCE_MEM, - }, { - .start = IRQ_PROG_INTB, - .end = IRQ_PROG_INTB, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, { - .start = IRQ_PF7, - .end = IRQ_PF7, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -static struct platform_device smc91x_device = { - .name = "smc91x", - .id = 0, - .num_resources = ARRAY_SIZE(smc91x_resources), - .resource = smc91x_resources, -}; -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 -static struct resource bfin_sir0_resources[] = { - { - .start = 0xFFC00400, - .end = 0xFFC004FF, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_UART0_RX, - .end = IRQ_UART0_RX+1, - .flags = IORESOURCE_IRQ, - }, - { - .start = CH_UART0_RX, - .end = CH_UART0_RX+1, - .flags = IORESOURCE_DMA, - }, -}; - -static struct platform_device bfin_sir0_device = { - .name = "bfin_sir", - .id = 0, - .num_resources = ARRAY_SIZE(bfin_sir0_resources), - .resource = bfin_sir0_resources, -}; -#endif -#endif - -static struct platform_device *generic_board_devices[] __initdata = { -#if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) - &rtc_device, -#endif - -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) - &smc91x_device, -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 - &bfin_sir0_device, -#endif -#endif -}; - -static int __init generic_board_init(void) -{ - printk(KERN_INFO "%s(): registering device resources\n", __func__); - return platform_add_devices(generic_board_devices, ARRAY_SIZE(generic_board_devices)); -} - -arch_initcall(generic_board_init); diff --git a/arch/blackfin/mach-bf533/boards/ip0x.c b/arch/blackfin/mach-bf533/boards/ip0x.c index e30b1b7..f19b633 100644 --- a/arch/blackfin/mach-bf533/boards/ip0x.c +++ b/arch/blackfin/mach-bf533/boards/ip0x.c @@ -127,8 +127,8 @@ static struct platform_device dm9000_device2 = { #if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) /* all SPI peripherals info goes here */ -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { /* * CPOL (Clock Polarity) * 0 - Active high SCK @@ -152,14 +152,13 @@ static struct bfin5xx_spi_chip spi_mmc_chip_info = { /* Notice: for blackfin, the speed_hz is the value of register * SPI_BAUD, not the real baudrate */ static struct spi_board_info bfin_spi_board_info[] __initdata = { -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 2, .bus_num = 1, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, }, #endif }; diff --git a/arch/blackfin/mach-bf533/include/mach/anomaly.h b/arch/blackfin/mach-bf533/include/mach/anomaly.h index 0d3a034..1cf893e 100644 --- a/arch/blackfin/mach-bf533/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf533/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf533/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -160,7 +160,7 @@ #define ANOMALY_05000301 (__SILICON_REVISION__ < 6) /* SSYNCs After Writes To DMA MMR Registers May Not Be Handled Correctly */ #define ANOMALY_05000302 (__SILICON_REVISION__ < 5) -/* New Feature: Additional Hysteresis on SPORT Input Pins (Not Available On Older Silicon) */ +/* SPORT_HYS Bit in PLL_CTL Register Is Not Functional */ #define ANOMALY_05000305 (__SILICON_REVISION__ < 5) /* New Feature: Additional PPI Frame Sync Sampling Options (Not Available On Older Silicon) */ #define ANOMALY_05000306 (__SILICON_REVISION__ < 5) @@ -278,9 +278,12 @@ #define ANOMALY_05000266 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000353 (1) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (1) #define ANOMALY_05000412 (0) #define ANOMALY_05000432 (0) #define ANOMALY_05000435 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h index f3d9e49..5f517f5 100644 --- a/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h @@ -134,7 +134,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART_TX, CH_UART_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf537/boards/Kconfig b/arch/blackfin/mach-bf537/boards/Kconfig index 42a57b0..77c59da 100644 --- a/arch/blackfin/mach-bf537/boards/Kconfig +++ b/arch/blackfin/mach-bf537/boards/Kconfig @@ -33,9 +33,4 @@ config CAMSIG_MINOTAUR help Board supply package for CSP Minotaur -config GENERIC_BF537_BOARD - bool "Generic" - help - Generic or Custom board support. - endchoice diff --git a/arch/blackfin/mach-bf537/boards/Makefile b/arch/blackfin/mach-bf537/boards/Makefile index 7168cc1..68b98a7 100644 --- a/arch/blackfin/mach-bf537/boards/Makefile +++ b/arch/blackfin/mach-bf537/boards/Makefile @@ -2,7 +2,6 @@ # arch/blackfin/mach-bf537/boards/Makefile # -obj-$(CONFIG_GENERIC_BF537_BOARD) += generic_board.o obj-$(CONFIG_BFIN537_STAMP) += stamp.o obj-$(CONFIG_BFIN537_BLUETECHNIX_CM) += cm_bf537.o obj-$(CONFIG_BFIN537_BLUETECHNIX_TCM) += tcm_bf537.o diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537.c b/arch/blackfin/mach-bf537/boards/cm_bf537.c index 9cd8fb2..41c75b9 100644 --- a/arch/blackfin/mach-bf537/boards/cm_bf537.c +++ b/arch/blackfin/mach-bf537/boards/cm_bf537.c @@ -108,9 +108,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -160,23 +160,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 7, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ + .modalias = "mmc_spi", + .max_speed_hz = 20000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 1, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf537/boards/generic_board.c b/arch/blackfin/mach-bf537/boards/generic_board.c deleted file mode 100644 index da710fd..0000000 --- a/arch/blackfin/mach-bf537/boards/generic_board.c +++ /dev/null @@ -1,745 +0,0 @@ -/* - * File: arch/blackfin/mach-bf537/boards/generic_board.c - * Based on: arch/blackfin/mach-bf533/boards/ezkit.c - * Author: Aidan Williams - * - * Created: - * Description: - * - * Modified: - * Copyright 2005 National ICT Australia (NICTA) - * Copyright 2004-2008 Analog Devices Inc. - * - * Bugs: Enter bugs at http://blackfin.uclinux.org/ - * - * 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, see the file COPYING, or write - * to the Free Software Foundation, Inc., - * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ - -#include -#include -#include -#include -#include -#include -#include -#if defined(CONFIG_USB_ISP1362_HCD) || defined(CONFIG_USB_ISP1362_HCD_MODULE) -#include -#endif -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * Name the Board for the /proc/cpuinfo - */ -const char bfin_board_name[] = "UNKNOWN BOARD"; - -/* - * Driver needs to know address, irq and flag pin. - */ - -#if defined(CONFIG_USB_ISP1760_HCD) || defined(CONFIG_USB_ISP1760_HCD_MODULE) -#include -static struct resource bfin_isp1760_resources[] = { - [0] = { - .start = 0x203C0000, - .end = 0x203C0000 + 0x000fffff, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_PF7, - .end = IRQ_PF7, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct isp1760_platform_data isp1760_priv = { - .is_isp1761 = 0, - .port1_disable = 0, - .bus_width_16 = 1, - .port1_otg = 0, - .analog_oc = 0, - .dack_polarity_high = 0, - .dreq_polarity_high = 0, -}; - -static struct platform_device bfin_isp1760_device = { - .name = "isp1760-hcd", - .id = 0, - .dev = { - .platform_data = &isp1760_priv, - }, - .num_resources = ARRAY_SIZE(bfin_isp1760_resources), - .resource = bfin_isp1760_resources, -}; -#endif - -#if defined(CONFIG_BFIN_CFPCMCIA) || defined(CONFIG_BFIN_CFPCMCIA_MODULE) -static struct resource bfin_pcmcia_cf_resources[] = { - { - .start = 0x20310000, /* IO PORT */ - .end = 0x20312000, - .flags = IORESOURCE_MEM, - }, { - .start = 0x20311000, /* Attribute Memory */ - .end = 0x20311FFF, - .flags = IORESOURCE_MEM, - }, { - .start = IRQ_PF4, - .end = IRQ_PF4, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWLEVEL, - }, { - .start = 6, /* Card Detect PF6 */ - .end = 6, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device bfin_pcmcia_cf_device = { - .name = "bfin_cf_pcmcia", - .id = -1, - .num_resources = ARRAY_SIZE(bfin_pcmcia_cf_resources), - .resource = bfin_pcmcia_cf_resources, -}; -#endif - -#if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) -static struct platform_device rtc_device = { - .name = "rtc-bfin", - .id = -1, -}; -#endif - -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) -static struct resource smc91x_resources[] = { - { - .name = "smc91x-regs", - .start = 0x20300300, - .end = 0x20300300 + 16, - .flags = IORESOURCE_MEM, - }, { - - .start = IRQ_PF7, - .end = IRQ_PF7, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; -static struct platform_device smc91x_device = { - .name = "smc91x", - .id = 0, - .num_resources = ARRAY_SIZE(smc91x_resources), - .resource = smc91x_resources, -}; -#endif - -#if defined(CONFIG_DM9000) || defined(CONFIG_DM9000_MODULE) -static struct resource dm9000_resources[] = { - [0] = { - .start = 0x203FB800, - .end = 0x203FB800 + 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = 0x203FB800 + 4, - .end = 0x203FB800 + 5, - .flags = IORESOURCE_MEM, - }, - [2] = { - .start = IRQ_PF9, - .end = IRQ_PF9, - .flags = (IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE), - }, -}; - -static struct platform_device dm9000_device = { - .name = "dm9000", - .id = -1, - .num_resources = ARRAY_SIZE(dm9000_resources), - .resource = dm9000_resources, -}; -#endif - -#if defined(CONFIG_USB_SL811_HCD) || defined(CONFIG_USB_SL811_HCD_MODULE) -static struct resource sl811_hcd_resources[] = { - { - .start = 0x20340000, - .end = 0x20340000, - .flags = IORESOURCE_MEM, - }, { - .start = 0x20340004, - .end = 0x20340004, - .flags = IORESOURCE_MEM, - }, { - .start = CONFIG_USB_SL811_BFIN_IRQ, - .end = CONFIG_USB_SL811_BFIN_IRQ, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -#if defined(CONFIG_USB_SL811_BFIN_USE_VBUS) -void sl811_port_power(struct device *dev, int is_on) -{ - gpio_request(CONFIG_USB_SL811_BFIN_GPIO_VBUS, "usb:SL811_VBUS"); - gpio_direction_output(CONFIG_USB_SL811_BFIN_GPIO_VBUS, is_on); - -} -#endif - -static struct sl811_platform_data sl811_priv = { - .potpg = 10, - .power = 250, /* == 500mA */ -#if defined(CONFIG_USB_SL811_BFIN_USE_VBUS) - .port_power = &sl811_port_power, -#endif -}; - -static struct platform_device sl811_hcd_device = { - .name = "sl811-hcd", - .id = 0, - .dev = { - .platform_data = &sl811_priv, - }, - .num_resources = ARRAY_SIZE(sl811_hcd_resources), - .resource = sl811_hcd_resources, -}; -#endif - -#if defined(CONFIG_USB_ISP1362_HCD) || defined(CONFIG_USB_ISP1362_HCD_MODULE) -static struct resource isp1362_hcd_resources[] = { - { - .start = 0x20360000, - .end = 0x20360000, - .flags = IORESOURCE_MEM, - }, { - .start = 0x20360004, - .end = 0x20360004, - .flags = IORESOURCE_MEM, - }, { - .start = CONFIG_USB_ISP1362_BFIN_GPIO_IRQ, - .end = CONFIG_USB_ISP1362_BFIN_GPIO_IRQ, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -static struct isp1362_platform_data isp1362_priv = { - .sel15Kres = 1, - .clknotstop = 0, - .oc_enable = 0, - .int_act_high = 0, - .int_edge_triggered = 0, - .remote_wakeup_connected = 0, - .no_power_switching = 1, - .power_switching_mode = 0, -}; - -static struct platform_device isp1362_hcd_device = { - .name = "isp1362-hcd", - .id = 0, - .dev = { - .platform_data = &isp1362_priv, - }, - .num_resources = ARRAY_SIZE(isp1362_hcd_resources), - .resource = isp1362_hcd_resources, -}; -#endif - -#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) -static struct platform_device bfin_mii_bus = { - .name = "bfin_mii_bus", -}; - -static struct platform_device bfin_mac_device = { - .name = "bfin_mac", - .dev.platform_data = &bfin_mii_bus, -}; -#endif - -#if defined(CONFIG_USB_NET2272) || defined(CONFIG_USB_NET2272_MODULE) -static struct resource net2272_bfin_resources[] = { - { - .start = 0x20300000, - .end = 0x20300000 + 0x100, - .flags = IORESOURCE_MEM, - }, { - .start = IRQ_PF7, - .end = IRQ_PF7, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -static struct platform_device net2272_bfin_device = { - .name = "net2272", - .id = -1, - .num_resources = ARRAY_SIZE(net2272_bfin_resources), - .resource = net2272_bfin_resources, -}; -#endif - -#if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) -/* all SPI peripherals info goes here */ - -#if defined(CONFIG_MTD_M25P80) \ - || defined(CONFIG_MTD_M25P80_MODULE) -static struct mtd_partition bfin_spi_flash_partitions[] = { - { - .name = "bootloader(spi)", - .size = 0x00020000, - .offset = 0, - .mask_flags = MTD_CAP_ROM - }, { - .name = "linux kernel(spi)", - .size = 0xe0000, - .offset = 0x20000 - }, { - .name = "file system(spi)", - .size = 0x700000, - .offset = 0x00100000, - } -}; - -static struct flash_platform_data bfin_spi_flash_data = { - .name = "m25p80", - .parts = bfin_spi_flash_partitions, - .nr_parts = ARRAY_SIZE(bfin_spi_flash_partitions), - .type = "m25p64", -}; - -/* SPI flash chip (m25p64) */ -static struct bfin5xx_spi_chip spi_flash_chip_info = { - .enable_dma = 0, /* use dma transfer with this chip*/ - .bits_per_word = 8, -}; -#endif - -#if defined(CONFIG_SPI_ADC_BF533) \ - || defined(CONFIG_SPI_ADC_BF533_MODULE) -/* SPI ADC chip */ -static struct bfin5xx_spi_chip spi_adc_chip_info = { - .enable_dma = 1, /* use dma transfer with this chip*/ - .bits_per_word = 16, -}; -#endif - -#if defined(CONFIG_SND_BLACKFIN_AD1836) \ - || defined(CONFIG_SND_BLACKFIN_AD1836_MODULE) -static struct bfin5xx_spi_chip ad1836_spi_chip_info = { - .enable_dma = 0, - .bits_per_word = 16, -}; -#endif - -#if defined(CONFIG_AD9960) || defined(CONFIG_AD9960_MODULE) -static struct bfin5xx_spi_chip ad9960_spi_chip_info = { - .enable_dma = 0, - .bits_per_word = 16, -}; -#endif - -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, - .bits_per_word = 8, -}; -#endif - -#if defined(CONFIG_PBX) -static struct bfin5xx_spi_chip spi_si3xxx_chip_info = { - .ctl_reg = 0x4, /* send zero */ - .enable_dma = 0, - .bits_per_word = 8, - .cs_change_per_word = 1, -}; -#endif - -#if defined(CONFIG_TOUCHSCREEN_AD7877) || defined(CONFIG_TOUCHSCREEN_AD7877_MODULE) -static struct bfin5xx_spi_chip spi_ad7877_chip_info = { - .enable_dma = 0, - .bits_per_word = 16, -}; - -static const struct ad7877_platform_data bfin_ad7877_ts_info = { - .model = 7877, - .vref_delay_usecs = 50, /* internal, no capacitor */ - .x_plate_ohms = 419, - .y_plate_ohms = 486, - .pressure_max = 1000, - .pressure_min = 0, - .stopacq_polarity = 1, - .first_conversion_delay = 3, - .acquisition_time = 1, - .averaging = 1, - .pen_down_acc_interval = 1, -}; -#endif - -static struct spi_board_info bfin_spi_board_info[] __initdata = { -#if defined(CONFIG_MTD_M25P80) \ - || defined(CONFIG_MTD_M25P80_MODULE) - { - /* the modalias must be the same as spi device driver name */ - .modalias = "m25p80", /* Name of spi_driver for this device */ - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, /* Framework bus number */ - .chip_select = 1, /* Framework chip select. On STAMP537 it is SPISSEL1*/ - .platform_data = &bfin_spi_flash_data, - .controller_data = &spi_flash_chip_info, - .mode = SPI_MODE_3, - }, -#endif - -#if defined(CONFIG_SPI_ADC_BF533) \ - || defined(CONFIG_SPI_ADC_BF533_MODULE) - { - .modalias = "bfin_spi_adc", /* Name of spi_driver for this device */ - .max_speed_hz = 6250000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, /* Framework bus number */ - .chip_select = 1, /* Framework chip select. */ - .platform_data = NULL, /* No spi_driver specific config */ - .controller_data = &spi_adc_chip_info, - }, -#endif - -#if defined(CONFIG_SND_BLACKFIN_AD1836) \ - || defined(CONFIG_SND_BLACKFIN_AD1836_MODULE) - { - .modalias = "ad1836-spi", - .max_speed_hz = 3125000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SND_BLACKFIN_SPI_PFBIT, - .controller_data = &ad1836_spi_chip_info, - }, -#endif -#if defined(CONFIG_AD9960) || defined(CONFIG_AD9960_MODULE) - { - .modalias = "ad9960-spi", - .max_speed_hz = 10000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 1, - .controller_data = &ad9960_spi_chip_info, - }, -#endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, -#endif -#if defined(CONFIG_PBX) - { - .modalias = "fxs-spi", - .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 8 - CONFIG_J11_JUMPER, - .controller_data = &spi_si3xxx_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "fxo-spi", - .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 8 - CONFIG_J19_JUMPER, - .controller_data = &spi_si3xxx_chip_info, - .mode = SPI_MODE_3, - }, -#endif -#if defined(CONFIG_TOUCHSCREEN_AD7877) || defined(CONFIG_TOUCHSCREEN_AD7877_MODULE) - { - .modalias = "ad7877", - .platform_data = &bfin_ad7877_ts_info, - .irq = IRQ_PF6, - .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 1, - .controller_data = &spi_ad7877_chip_info, - }, -#endif -}; - -/* SPI controller data */ -static struct bfin5xx_spi_master bfin_spi0_info = { - .num_chipselect = 8, - .enable_dma = 1, /* master has the ability to do dma transfer */ - .pin_req = {P_SPI0_SCK, P_SPI0_MISO, P_SPI0_MOSI, 0}, -}; - -/* SPI (0) */ -static struct resource bfin_spi0_resource[] = { - [0] = { - .start = SPI0_REGBASE, - .end = SPI0_REGBASE + 0xFF, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = CH_SPI, - .end = CH_SPI, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device bfin_spi0_device = { - .name = "bfin-spi", - .id = 0, /* Bus number */ - .num_resources = ARRAY_SIZE(bfin_spi0_resource), - .resource = bfin_spi0_resource, - .dev = { - .platform_data = &bfin_spi0_info, /* Passed to driver */ - }, -}; -#endif /* spi master and devices */ - -#if defined(CONFIG_FB_BF537_LQ035) || defined(CONFIG_FB_BF537_LQ035_MODULE) -static struct platform_device bfin_fb_device = { - .name = "bf537-lq035", -}; -#endif - -#if defined(CONFIG_FB_BFIN_7393) || defined(CONFIG_FB_BFIN_7393_MODULE) -static struct platform_device bfin_fb_adv7393_device = { - .name = "bfin-adv7393", -}; -#endif - -#if defined(CONFIG_SERIAL_BFIN) || defined(CONFIG_SERIAL_BFIN_MODULE) -static struct resource bfin_uart_resources[] = { - { - .start = 0xFFC00400, - .end = 0xFFC004FF, - .flags = IORESOURCE_MEM, - }, { - .start = 0xFFC02000, - .end = 0xFFC020FF, - .flags = IORESOURCE_MEM, - }, -}; - -static struct platform_device bfin_uart_device = { - .name = "bfin-uart", - .id = 1, - .num_resources = ARRAY_SIZE(bfin_uart_resources), - .resource = bfin_uart_resources, -}; -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 -static struct resource bfin_sir0_resources[] = { - { - .start = 0xFFC00400, - .end = 0xFFC004FF, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_UART0_RX, - .end = IRQ_UART0_RX+1, - .flags = IORESOURCE_IRQ, - }, - { - .start = CH_UART0_RX, - .end = CH_UART0_RX+1, - .flags = IORESOURCE_DMA, - }, -}; - -static struct platform_device bfin_sir0_device = { - .name = "bfin_sir", - .id = 0, - .num_resources = ARRAY_SIZE(bfin_sir0_resources), - .resource = bfin_sir0_resources, -}; -#endif -#ifdef CONFIG_BFIN_SIR1 -static struct resource bfin_sir1_resources[] = { - { - .start = 0xFFC02000, - .end = 0xFFC020FF, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_UART1_RX, - .end = IRQ_UART1_RX+1, - .flags = IORESOURCE_IRQ, - }, - { - .start = CH_UART1_RX, - .end = CH_UART1_RX+1, - .flags = IORESOURCE_DMA, - }, -}; - -static struct platform_device bfin_sir1_device = { - .name = "bfin_sir", - .id = 1, - .num_resources = ARRAY_SIZE(bfin_sir1_resources), - .resource = bfin_sir1_resources, -}; -#endif -#endif - -#if defined(CONFIG_I2C_BLACKFIN_TWI) || defined(CONFIG_I2C_BLACKFIN_TWI_MODULE) -static struct resource bfin_twi0_resource[] = { - [0] = { - .start = TWI0_REGBASE, - .end = TWI0_REGBASE + 0xFF, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = IRQ_TWI, - .end = IRQ_TWI, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device i2c_bfin_twi_device = { - .name = "i2c-bfin-twi", - .id = 0, - .num_resources = ARRAY_SIZE(bfin_twi0_resource), - .resource = bfin_twi0_resource, -}; -#endif - -#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE) -static struct platform_device bfin_sport0_uart_device = { - .name = "bfin-sport-uart", - .id = 0, -}; - -static struct platform_device bfin_sport1_uart_device = { - .name = "bfin-sport-uart", - .id = 1, -}; -#endif - -static struct platform_device *stamp_devices[] __initdata = { -#if defined(CONFIG_BFIN_CFPCMCIA) || defined(CONFIG_BFIN_CFPCMCIA_MODULE) - &bfin_pcmcia_cf_device, -#endif - -#if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) - &rtc_device, -#endif - -#if defined(CONFIG_USB_SL811_HCD) || defined(CONFIG_USB_SL811_HCD_MODULE) - &sl811_hcd_device, -#endif - -#if defined(CONFIG_USB_ISP1362_HCD) || defined(CONFIG_USB_ISP1362_HCD_MODULE) - &isp1362_hcd_device, -#endif - -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) - &smc91x_device, -#endif - -#if defined(CONFIG_DM9000) || defined(CONFIG_DM9000_MODULE) - &dm9000_device, -#endif - -#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) - &bfin_mii_bus, - &bfin_mac_device, -#endif - -#if defined(CONFIG_USB_NET2272) || defined(CONFIG_USB_NET2272_MODULE) - &net2272_bfin_device, -#endif - -#if defined(CONFIG_USB_ISP1760_HCD) || defined(CONFIG_USB_ISP1760_HCD_MODULE) - &bfin_isp1760_device, -#endif - -#if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) - &bfin_spi0_device, -#endif - -#if defined(CONFIG_FB_BF537_LQ035) || defined(CONFIG_FB_BF537_LQ035_MODULE) - &bfin_fb_device, -#endif - -#if defined(CONFIG_FB_BFIN_7393) || defined(CONFIG_FB_BFIN_7393_MODULE) - &bfin_fb_adv7393_device, -#endif - -#if defined(CONFIG_SERIAL_BFIN) || defined(CONFIG_SERIAL_BFIN_MODULE) - &bfin_uart_device, -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 - &bfin_sir0_device, -#endif -#ifdef CONFIG_BFIN_SIR1 - &bfin_sir1_device, -#endif -#endif - -#if defined(CONFIG_I2C_BLACKFIN_TWI) || defined(CONFIG_I2C_BLACKFIN_TWI_MODULE) - &i2c_bfin_twi_device, -#endif - -#if defined(CONFIG_SERIAL_BFIN_SPORT) || defined(CONFIG_SERIAL_BFIN_SPORT_MODULE) - &bfin_sport0_uart_device, - &bfin_sport1_uart_device, -#endif -}; - -static int __init generic_init(void) -{ - printk(KERN_INFO "%s(): registering device resources\n", __func__); - platform_add_devices(stamp_devices, ARRAY_SIZE(stamp_devices)); -#if defined(CONFIG_SPI_BFIN) || defined(CONFIG_SPI_BFIN_MODULE) - spi_register_board_info(bfin_spi_board_info, - ARRAY_SIZE(bfin_spi_board_info)); -#endif - - return 0; -} - -arch_initcall(generic_init); - -void native_machine_restart(char *cmd) -{ - /* workaround reboot hang when booting from SPI */ - if ((bfin_read_SYSCR() & 0x7) == 0x3) - bfin_reset_boot_spi_cs(P_DEFAULT_BOOT_SPI_CS); -} - -#if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) -void bfin_get_ether_addr(char *addr) -{ - random_ether_addr(addr); - printk(KERN_WARNING "%s:%s: Setting Ethernet MAC to a random one\n", __FILE__, __func__); -} -EXPORT_SYMBOL(bfin_get_ether_addr); -#endif diff --git a/arch/blackfin/mach-bf537/boards/minotaur.c b/arch/blackfin/mach-bf537/boards/minotaur.c index db7d3a3..3c15981 100644 --- a/arch/blackfin/mach-bf537/boards/minotaur.c +++ b/arch/blackfin/mach-bf537/boards/minotaur.c @@ -134,9 +134,9 @@ static struct bfin5xx_spi_chip spi_flash_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -156,23 +156,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc_dummy", + .modalias = "mmc_spi", .max_speed_hz = 5000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 0, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, - { - .modalias = "spi_mmc", - .max_speed_hz = 5000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf537/boards/pnav10.c b/arch/blackfin/mach-bf537/boards/pnav10.c index 590eb3a..4e1de1e 100644 --- a/arch/blackfin/mach-bf537/boards/pnav10.c +++ b/arch/blackfin/mach-bf537/boards/pnav10.c @@ -289,9 +289,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -364,23 +364,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .controller_data = &ad9960_spi_chip_info, }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 7, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c index 3f4f203..53ad10f 100644 --- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c +++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c @@ -108,9 +108,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -160,23 +160,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) - { - .modalias = "spi_mmc_dummy", - .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ - .bus_num = 0, - .chip_select = 7, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, - .mode = SPI_MODE_3, - }, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf537/include/mach/anomaly.h b/arch/blackfin/mach-bf537/include/mach/anomaly.h index 9cb3912..1bfd80c 100644 --- a/arch/blackfin/mach-bf537/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf537/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf537/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -110,7 +110,7 @@ #define ANOMALY_05000301 (1) /* SSYNCs After Writes To CAN/DMA MMR Registers Are Not Always Handled Correctly */ #define ANOMALY_05000304 (__SILICON_REVISION__ < 3) -/* New Feature: Additional Hysteresis on SPORT Input Pins (Not Available On Older Silicon) */ +/* SPORT_HYS Bit in PLL_CTL Register Is Not Functional */ #define ANOMALY_05000305 (__SILICON_REVISION__ < 3) /* SCKELOW Bit Does Not Maintain State Through Hibernate */ #define ANOMALY_05000307 (__SILICON_REVISION__ < 3) @@ -168,9 +168,12 @@ #define ANOMALY_05000323 (0) #define ANOMALY_05000353 (1) #define ANOMALY_05000363 (0) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (1) #define ANOMALY_05000412 (0) #define ANOMALY_05000432 (0) #define ANOMALY_05000435 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h index b3f87e1..9e34700 100644 --- a/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h @@ -144,7 +144,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -158,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif -#ifdef CONFIG_BFIN_UART1_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART1_CTS_PIN, CONFIG_UART1_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf538/include/mach/anomaly.h b/arch/blackfin/mach-bf538/include/mach/anomaly.h index e130b4f..3a56998 100644 --- a/arch/blackfin/mach-bf538/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf538/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf538/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -120,13 +120,17 @@ #define ANOMALY_05000198 (0) #define ANOMALY_05000230 (0) #define ANOMALY_05000263 (0) +#define ANOMALY_05000305 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000323 (0) #define ANOMALY_05000353 (1) #define ANOMALY_05000363 (0) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (1) #define ANOMALY_05000412 (0) #define ANOMALY_05000432 (0) #define ANOMALY_05000435 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h index 40503b6..3c2811e 100644 --- a/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h @@ -144,7 +144,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -158,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif -#ifdef CONFIG_BFIN_UART1_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART1_CTS_PIN, CONFIG_UART1_RTS_PIN, #endif diff --git a/arch/blackfin/mach-bf548/include/mach/anomaly.h b/arch/blackfin/mach-bf548/include/mach/anomaly.h index 23d03c5..882e40c 100644 --- a/arch/blackfin/mach-bf548/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf548/include/mach/anomaly.h @@ -2,12 +2,12 @@ * File: include/asm-blackfin/mach-bf548/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ /* This file shoule be up to date with: - * - Revision G, 08/07/2008; ADSP-BF542/BF544/BF547/BF548/BF549 Blackfin Processor Anomaly List + * - Revision H, 01/16/2009; ADSP-BF542/BF544/BF547/BF548/BF549 Blackfin Processor Anomaly List */ #ifndef _MACH_ANOMALY_H_ @@ -91,8 +91,6 @@ #define ANOMALY_05000371 (__SILICON_REVISION__ < 2) /* USB DP/DM Data Pins May Lose State When Entering Hibernate */ #define ANOMALY_05000372 (__SILICON_REVISION__ < 1) -/* Mobile DDR Operation Not Functional */ -#define ANOMALY_05000377 (1) /* Security/Authentication Speedpath Causes Authentication To Fail To Initiate */ #define ANOMALY_05000378 (__SILICON_REVISION__ < 2) /* 16-Bit NAND FLASH Boot Mode Is Not Functional */ @@ -157,8 +155,22 @@ #define ANOMALY_05000429 (__SILICON_REVISION__ < 2) /* Software System Reset Corrupts PLL_LOCKCNT Register */ #define ANOMALY_05000430 (__SILICON_REVISION__ >= 2) +/* Incorrect Use of Stack in Lockbox Firmware During Authentication */ +#define ANOMALY_05000431 (__SILICON_REVISION__ < 3) +/* OTP Write Accesses Not Supported */ +#define ANOMALY_05000442 (__SILICON_REVISION__ < 1) /* IFLUSH Instruction at End of Hardware Loop Causes Infinite Stall */ #define ANOMALY_05000443 (1) +/* CDMAPRIO and L2DMAPRIO Bits in the SYSCR Register Are Not Functional */ +#define ANOMALY_05000446 (1) +/* UART IrDA Receiver Fails on Extended Bit Pulses */ +#define ANOMALY_05000447 (1) +/* DDR Clock Duty Cycle Spec Violation (tCH, tCL) */ +#define ANOMALY_05000448 (__SILICON_REVISION__ == 1) +/* Reduced Timing Margins on DDR Output Setup and Hold (tDS and tDH) */ +#define ANOMALY_05000449 (__SILICON_REVISION__ == 1) +/* USB DMA Mode 1 Short Packet Data Corruption */ +#define ANOMALY_05000450 (1 /* Anomalies that don't exist on this proc */ #define ANOMALY_05000125 (0) @@ -171,6 +183,8 @@ #define ANOMALY_05000263 (0) #define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) +#define ANOMALY_05000278 (0) +#define ANOMALY_05000305 (0) #define ANOMALY_05000307 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000323 (0) diff --git a/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h index e4cf35e..c05e79c 100644 --- a/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h @@ -63,7 +63,7 @@ #define UART_ENABLE_INTS(x, v) UART_SET_IER(x, v) #define UART_DISABLE_INTS(x) UART_CLEAR_IER(x, 0xF) -#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS) +#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART2_CTSRTS) # define CONFIG_SERIAL_BFIN_CTSRTS # ifndef CONFIG_UART0_CTS_PIN @@ -74,12 +74,12 @@ # define CONFIG_UART0_RTS_PIN -1 # endif -# ifndef CONFIG_UART1_CTS_PIN -# define CONFIG_UART1_CTS_PIN -1 +# ifndef CONFIG_UART2_CTS_PIN +# define CONFIG_UART2_CTS_PIN -1 # endif -# ifndef CONFIG_UART1_RTS_PIN -# define CONFIG_UART1_RTS_PIN -1 +# ifndef CONFIG_UART2_RTS_PIN +# define CONFIG_UART2_RTS_PIN -1 # endif #endif @@ -130,7 +130,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART0_TX, CH_UART0_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif @@ -144,6 +144,10 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART1_TX, CH_UART1_RX, #endif +#ifdef CONFIG_SERIAL_BFIN_CTSRTS + 0, + 0, +#endif }, #endif #ifdef CONFIG_SERIAL_BFIN_UART2 @@ -154,7 +158,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART2_TX, CH_UART2_RX, #endif -#ifdef CONFIG_BFIN_UART2_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART2_CTS_PIN, CONFIG_UART2_RTS_PIN, #endif @@ -168,6 +172,10 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART3_TX, CH_UART3_RX, #endif +#ifdef CONFIG_SERIAL_BFIN_CTSRTS + 0, + 0, +#endif }, #endif }; diff --git a/arch/blackfin/mach-bf548/include/mach/irq.h b/arch/blackfin/mach-bf548/include/mach/irq.h index 60299a7..f194625 100644 --- a/arch/blackfin/mach-bf548/include/mach/irq.h +++ b/arch/blackfin/mach-bf548/include/mach/irq.h @@ -123,8 +123,8 @@ Events (highest priority) EMU 0 #define IRQ_MXVR_ERROR BFIN_IRQ(51) /* MXVR Status (Error) Interrupt */ #define IRQ_MXVR_MSG BFIN_IRQ(52) /* MXVR Message Interrupt */ #define IRQ_MXVR_PKT BFIN_IRQ(53) /* MXVR Packet Interrupt */ -#define IRQ_EPP1_ERROR BFIN_IRQ(54) /* EPPI1 Error Interrupt */ -#define IRQ_EPP2_ERROR BFIN_IRQ(55) /* EPPI2 Error Interrupt */ +#define IRQ_EPPI1_ERROR BFIN_IRQ(54) /* EPPI1 Error Interrupt */ +#define IRQ_EPPI2_ERROR BFIN_IRQ(55) /* EPPI2 Error Interrupt */ #define IRQ_UART3_ERROR BFIN_IRQ(56) /* UART3 Status (Error) Interrupt */ #define IRQ_HOST_ERROR BFIN_IRQ(57) /* HOST Status (Error) Interrupt */ #define IRQ_PIXC_ERROR BFIN_IRQ(59) /* PIXC Status (Error) Interrupt */ @@ -361,8 +361,8 @@ Events (highest priority) EMU 0 #define IRQ_UART2_ERR IRQ_UART2_ERROR #define IRQ_CAN0_ERR IRQ_CAN0_ERROR #define IRQ_MXVR_ERR IRQ_MXVR_ERROR -#define IRQ_EPP1_ERR IRQ_EPP1_ERROR -#define IRQ_EPP2_ERR IRQ_EPP2_ERROR +#define IRQ_EPPI1_ERR IRQ_EPPI1_ERROR +#define IRQ_EPPI2_ERR IRQ_EPPI2_ERROR #define IRQ_UART3_ERR IRQ_UART3_ERROR #define IRQ_HOST_ERR IRQ_HOST_ERROR #define IRQ_PIXC_ERR IRQ_PIXC_ERROR diff --git a/arch/blackfin/mach-bf561/boards/Kconfig b/arch/blackfin/mach-bf561/boards/Kconfig index e41a67b..e4bc6d7 100644 --- a/arch/blackfin/mach-bf561/boards/Kconfig +++ b/arch/blackfin/mach-bf561/boards/Kconfig @@ -19,9 +19,4 @@ config BFIN561_BLUETECHNIX_CM help CM-BF561 support for EVAL- and DEV-Board. -config GENERIC_BF561_BOARD - bool "Generic" - help - Generic or Custom board support. - endchoice diff --git a/arch/blackfin/mach-bf561/boards/Makefile b/arch/blackfin/mach-bf561/boards/Makefile index 04add01..3a15255 100644 --- a/arch/blackfin/mach-bf561/boards/Makefile +++ b/arch/blackfin/mach-bf561/boards/Makefile @@ -2,7 +2,6 @@ # arch/blackfin/mach-bf561/boards/Makefile # -obj-$(CONFIG_GENERIC_BF561_BOARD) += generic_board.o obj-$(CONFIG_BFIN561_BLUETECHNIX_CM) += cm_bf561.o obj-$(CONFIG_BFIN561_EZKIT) += ezkit.o obj-$(CONFIG_BFIN561_TEPLA) += tepla.o diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c index 6880d1e..f623c6b 100644 --- a/arch/blackfin/mach-bf561/boards/cm_bf561.c +++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c @@ -105,9 +105,9 @@ static struct bfin5xx_spi_chip ad9960_spi_chip_info = { }; #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) -static struct bfin5xx_spi_chip spi_mmc_chip_info = { - .enable_dma = 1, +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) +static struct bfin5xx_spi_chip mmc_spi_chip_info = { + .enable_dma = 0, .bits_per_word = 8, }; #endif @@ -155,14 +155,13 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .controller_data = &ad9960_spi_chip_info, }, #endif -#if defined(CONFIG_SPI_MMC) || defined(CONFIG_SPI_MMC_MODULE) +#if defined(CONFIG_MMC_SPI) || defined(CONFIG_MMC_SPI_MODULE) { - .modalias = "spi_mmc", + .modalias = "mmc_spi", .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = CONFIG_SPI_MMC_CS_CHAN, - .platform_data = NULL, - .controller_data = &spi_mmc_chip_info, + .chip_select = 5, + .controller_data = &mmc_spi_chip_info, .mode = SPI_MODE_3, }, #endif diff --git a/arch/blackfin/mach-bf561/boards/generic_board.c b/arch/blackfin/mach-bf561/boards/generic_board.c deleted file mode 100644 index 0ba366a..0000000 --- a/arch/blackfin/mach-bf561/boards/generic_board.c +++ /dev/null @@ -1,113 +0,0 @@ -/* - * File: arch/blackfin/mach-bf561/generic_board.c - * Based on: arch/blackfin/mach-bf533/ezkit.c - * Author: Aidan Williams - * - * Created: - * Description: - * - * Modified: - * Copyright 2005 National ICT Australia (NICTA) - * Copyright 2004-2006 Analog Devices Inc. - * - * Bugs: Enter bugs at http://blackfin.uclinux.org/ - * - * 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, see the file COPYING, or write - * to the Free Software Foundation, Inc., - * 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ - -#include -#include -#include - -const char bfin_board_name[] = "UNKNOWN BOARD"; - -/* - * Driver needs to know address, irq and flag pin. - */ -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) -static struct resource smc91x_resources[] = { - { - .start = 0x2C010300, - .end = 0x2C010300 + 16, - .flags = IORESOURCE_MEM, - }, { - .start = IRQ_PROG_INTB, - .end = IRQ_PROG_INTB, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, { - .start = IRQ_PF9, - .end = IRQ_PF9, - .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, - }, -}; - -static struct platform_device smc91x_device = { - .name = "smc91x", - .id = 0, - .num_resources = ARRAY_SIZE(smc91x_resources), - .resource = smc91x_resources, -}; -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 -static struct resource bfin_sir0_resources[] = { - { - .start = 0xFFC00400, - .end = 0xFFC004FF, - .flags = IORESOURCE_MEM, - }, - { - .start = IRQ_UART0_RX, - .end = IRQ_UART0_RX+1, - .flags = IORESOURCE_IRQ, - }, - { - .start = CH_UART0_RX, - .end = CH_UART0_RX+1, - .flags = IORESOURCE_DMA, - }, -}; - -static struct platform_device bfin_sir0_device = { - .name = "bfin_sir", - .id = 0, - .num_resources = ARRAY_SIZE(bfin_sir0_resources), - .resource = bfin_sir0_resources, -}; -#endif -#endif - -static struct platform_device *generic_board_devices[] __initdata = { -#if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE) - &smc91x_device, -#endif - -#if defined(CONFIG_BFIN_SIR) || defined(CONFIG_BFIN_SIR_MODULE) -#ifdef CONFIG_BFIN_SIR0 - &bfin_sir0_device, -#endif -#endif -}; - -static int __init generic_board_init(void) -{ - printk(KERN_INFO "%s(): registering device resources\n", __func__); - return platform_add_devices(generic_board_devices, - ARRAY_SIZE(generic_board_devices)); -} - -arch_initcall(generic_board_init); diff --git a/arch/blackfin/mach-bf561/include/mach/anomaly.h b/arch/blackfin/mach-bf561/include/mach/anomaly.h index 1a9e175..d0b0b35 100644 --- a/arch/blackfin/mach-bf561/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf561/include/mach/anomaly.h @@ -2,7 +2,7 @@ * File: include/asm-blackfin/mach-bf561/anomaly.h * Bugs: Enter bugs at http://blackfin.uclinux.org/ * - * Copyright (C) 2004-2008 Analog Devices Inc. + * Copyright (C) 2004-2009 Analog Devices Inc. * Licensed under the GPL-2 or later. */ @@ -224,7 +224,7 @@ #define ANOMALY_05000301 (1) /* SSYNCs After Writes To DMA MMR Registers May Not Be Handled Correctly */ #define ANOMALY_05000302 (1) -/* New Feature: Additional Hysteresis on SPORT Input Pins (Not Available On Older Silicon) */ +/* SPORT_HYS Bit in PLL_CTL Register Is Not Functional */ #define ANOMALY_05000305 (__SILICON_REVISION__ < 5) /* SCKELOW Bit Does Not Maintain State Through Hibernate */ #define ANOMALY_05000307 (__SILICON_REVISION__ < 5) @@ -283,8 +283,11 @@ #define ANOMALY_05000273 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000353 (1) +#define ANOMALY_05000380 (0) #define ANOMALY_05000386 (1) #define ANOMALY_05000432 (0) #define ANOMALY_05000435 (0) +#define ANOMALY_05000447 (0) +#define ANOMALY_05000448 (0) #endif diff --git a/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h index 043bfcf..ca8c5f6 100644 --- a/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h +++ b/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h @@ -134,7 +134,7 @@ struct bfin_serial_res bfin_serial_resource[] = { CH_UART_TX, CH_UART_RX, #endif -#ifdef CONFIG_BFIN_UART0_CTSRTS +#ifdef CONFIG_SERIAL_BFIN_CTSRTS CONFIG_UART0_CTS_PIN, CONFIG_UART0_RTS_PIN, #endif diff --git a/arch/blackfin/mach-common/arch_checks.c b/arch/blackfin/mach-common/arch_checks.c index 98133b9..80d39b2 100644 --- a/arch/blackfin/mach-common/arch_checks.c +++ b/arch/blackfin/mach-common/arch_checks.c @@ -62,3 +62,12 @@ #if (CONFIG_BOOT_LOAD & 0x3) # error "The kernel load address must be 4 byte aligned" #endif + +/* The entire kernel must be able to make a 24bit pcrel call to start of L1 */ +#if ((0xffffffff - L1_CODE_START + 1) + CONFIG_BOOT_LOAD) > 0x1000000 +# error "The kernel load address is too high; keep it below 10meg for safety" +#endif + +#if ANOMALY_05000448 +# error You are using a part with anomaly 05000448, this issue causes random memory read/write failures - that means random crashes. +#endif diff --git a/arch/blackfin/mach-common/cache.S b/arch/blackfin/mach-common/cache.S index 3c98dac..aa0648c 100644 --- a/arch/blackfin/mach-common/cache.S +++ b/arch/blackfin/mach-common/cache.S @@ -66,11 +66,33 @@ /* Invalidate all instruction cache lines assocoiated with this memory area */ ENTRY(_blackfin_icache_flush_range) +/* + * Walkaround to avoid loading wrong instruction after invalidating icache + * and following sequence is met. + * + * 1) One instruction address is cached in the instruction cache. + * 2) This instruction in SDRAM is changed. + * 3) IFLASH[P0] is executed only once in blackfin_icache_flush_range(). + * 4) This instruction is executed again, but the old one is loaded. + */ + P0 = R0; + IFLUSH[P0]; do_flush IFLUSH, , nop ENDPROC(_blackfin_icache_flush_range) /* Flush all cache lines assocoiated with this area of memory. */ ENTRY(_blackfin_icache_dcache_flush_range) +/* + * Walkaround to avoid loading wrong instruction after invalidating icache + * and following sequence is met. + * + * 1) One instruction address is cached in the instruction cache. + * 2) This instruction in SDRAM is changed. + * 3) IFLASH[P0] is executed only once in blackfin_icache_flush_range(). + * 4) This instruction is executed again, but the old one is loaded. + */ + P0 = R0; + IFLUSH[P0]; do_flush FLUSH, IFLUSH ENDPROC(_blackfin_icache_dcache_flush_range) diff --git a/arch/blackfin/mach-common/clocks-init.c b/arch/blackfin/mach-common/clocks-init.c index 9dddb6f..3539365 100644 --- a/arch/blackfin/mach-common/clocks-init.c +++ b/arch/blackfin/mach-common/clocks-init.c @@ -17,7 +17,7 @@ #define SDGCTL_WIDTH (1 << 31) /* SDRAM external data path width */ #define PLL_CTL_VAL \ (((CONFIG_VCO_MULT & 63) << 9) | CLKIN_HALF | \ - (PLL_BYPASS << 8) | (ANOMALY_05000265 ? 0x8000 : 0)) + (PLL_BYPASS << 8) | (ANOMALY_05000305 ? 0 : 0x8000)) __attribute__((l1_text)) static void do_sync(void) diff --git a/arch/blackfin/mach-common/dpmc_modes.S b/arch/blackfin/mach-common/dpmc_modes.S index 4da50bc..8009a51 100644 --- a/arch/blackfin/mach-common/dpmc_modes.S +++ b/arch/blackfin/mach-common/dpmc_modes.S @@ -376,10 +376,22 @@ ENTRY(_do_hibernate) #endif #ifdef PINT0_ASSIGN + PM_SYS_PUSH(PINT0_MASK_SET) + PM_SYS_PUSH(PINT1_MASK_SET) + PM_SYS_PUSH(PINT2_MASK_SET) + PM_SYS_PUSH(PINT3_MASK_SET) PM_SYS_PUSH(PINT0_ASSIGN) PM_SYS_PUSH(PINT1_ASSIGN) PM_SYS_PUSH(PINT2_ASSIGN) PM_SYS_PUSH(PINT3_ASSIGN) + PM_SYS_PUSH(PINT0_INVERT_SET) + PM_SYS_PUSH(PINT1_INVERT_SET) + PM_SYS_PUSH(PINT2_INVERT_SET) + PM_SYS_PUSH(PINT3_INVERT_SET) + PM_SYS_PUSH(PINT0_EDGE_SET) + PM_SYS_PUSH(PINT1_EDGE_SET) + PM_SYS_PUSH(PINT2_EDGE_SET) + PM_SYS_PUSH(PINT3_EDGE_SET) #endif PM_SYS_PUSH(EBIU_AMBCTL0) @@ -714,10 +726,22 @@ ENTRY(_do_hibernate) PM_SYS_POP(EBIU_AMBCTL0) #ifdef PINT0_ASSIGN + PM_SYS_POP(PINT3_EDGE_SET) + PM_SYS_POP(PINT2_EDGE_SET) + PM_SYS_POP(PINT1_EDGE_SET) + PM_SYS_POP(PINT0_EDGE_SET) + PM_SYS_POP(PINT3_INVERT_SET) + PM_SYS_POP(PINT2_INVERT_SET) + PM_SYS_POP(PINT1_INVERT_SET) + PM_SYS_POP(PINT0_INVERT_SET) PM_SYS_POP(PINT3_ASSIGN) PM_SYS_POP(PINT2_ASSIGN) PM_SYS_POP(PINT1_ASSIGN) PM_SYS_POP(PINT0_ASSIGN) + PM_SYS_POP(PINT3_MASK_SET) + PM_SYS_POP(PINT2_MASK_SET) + PM_SYS_POP(PINT1_MASK_SET) + PM_SYS_POP(PINT0_MASK_SET) #endif #ifdef SICA_IWR1 diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S index 88de053..21e65a3 100644 --- a/arch/blackfin/mach-common/entry.S +++ b/arch/blackfin/mach-common/entry.S @@ -600,6 +600,19 @@ ENTRY(_system_call) p2 = [p2]; [p2+(TASK_THREAD+THREAD_KSP)] = sp; +#ifdef CONFIG_IPIPE + r0 = sp; + SP += -12; + call ___ipipe_syscall_root; + SP += 12; + cc = r0 == 1; + if cc jump .Lsyscall_really_exit; + cc = r0 == -1; + if cc jump .Lresume_userspace; + r3 = [sp + PT_R3]; + r4 = [sp + PT_R4]; + p0 = [sp + PT_ORIG_P0]; +#endif /* CONFIG_IPIPE */ /* Check the System Call */ r7 = __NR_syscall; @@ -654,6 +667,17 @@ ENTRY(_system_call) r7 = r7 & r4; .Lsyscall_resched: +#ifdef CONFIG_IPIPE + cc = BITTST(r7, TIF_IRQ_SYNC); + if !cc jump .Lsyscall_no_irqsync; + [--sp] = reti; + r0 = [sp++]; + SP += -12; + call ___ipipe_sync_root; + SP += 12; + jump .Lresume_userspace_1; +.Lsyscall_no_irqsync: +#endif cc = BITTST(r7, TIF_NEED_RESCHED); if !cc jump .Lsyscall_sigpending; @@ -685,6 +709,10 @@ ENTRY(_system_call) .Lsyscall_really_exit: r5 = [sp + PT_RESERVED]; rets = r5; +#ifdef CONFIG_IPIPE + [--sp] = reti; + r5 = [sp++]; +#endif /* CONFIG_IPIPE */ rts; ENDPROC(_system_call) @@ -771,6 +799,15 @@ _new_old_task: ENDPROC(_resume) ENTRY(_ret_from_exception) +#ifdef CONFIG_IPIPE + [--sp] = rets; + SP += -12; + call ___ipipe_check_root + SP += 12 + rets = [sp++]; + cc = r0 == 0; + if cc jump 4f; /* not on behalf of Linux, get out */ +#endif /* CONFIG_IPIPE */ p2.l = lo(IPEND); p2.h = hi(IPEND); @@ -827,6 +864,28 @@ ENTRY(_ret_from_exception) rts; ENDPROC(_ret_from_exception) +#ifdef CONFIG_IPIPE + +_sync_root_irqs: + [--sp] = reti; /* Reenable interrupts */ + r0 = [sp++]; + jump.l ___ipipe_sync_root + +_resume_kernel_from_int: + r0.l = _sync_root_irqs + r0.h = _sync_root_irqs + [--sp] = rets; + [--sp] = ( r7:4, p5:3 ); + SP += -12; + call ___ipipe_call_irqtail + SP += 12; + ( r7:4, p5:3 ) = [sp++]; + rets = [sp++]; + rts +#else +#define _resume_kernel_from_int 2f +#endif + ENTRY(_return_from_int) /* If someone else already raised IRQ 15, do nothing. */ csync; @@ -848,7 +907,7 @@ ENTRY(_return_from_int) r1 = r0 - r1; r2 = r0 & r1; cc = r2 == 0; - if !cc jump 2f; + if !cc jump _resume_kernel_from_int; /* Lower the interrupt level to 15. */ p0.l = lo(EVT15); diff --git a/arch/blackfin/mach-common/interrupt.S b/arch/blackfin/mach-common/interrupt.S index 43c4eb9..0069c2d 100644 --- a/arch/blackfin/mach-common/interrupt.S +++ b/arch/blackfin/mach-common/interrupt.S @@ -235,6 +235,7 @@ ENDPROC(_evt_system_call) #ifdef CONFIG_IPIPE ENTRY(___ipipe_call_irqtail) + p0 = r0; r0.l = 1f; r0.h = 1f; reti = r0; @@ -242,9 +243,6 @@ ENTRY(___ipipe_call_irqtail) 1: [--sp] = rets; [--sp] = ( r7:4, p5:3 ); - p0.l = ___ipipe_irq_tail_hook; - p0.h = ___ipipe_irq_tail_hook; - p0 = [p0]; sp += -12; call (p0); sp += 12; @@ -259,7 +257,7 @@ ENTRY(___ipipe_call_irqtail) p0.h = hi(EVT14); [p0] = r0; csync; - r0 = 0x401f; + r0 = 0x401f (z); sti r0; raise 14; [--sp] = reti; /* IRQs on. */ @@ -277,11 +275,7 @@ ENTRY(___ipipe_call_irqtail) p0.h = _bfin_irq_flags; r0 = [p0]; sti r0; -#if 0 /* FIXME: this actually raises scheduling latencies */ - /* Reenable interrupts */ - [--sp] = reti; - r0 = [sp++]; -#endif rts; ENDPROC(___ipipe_call_irqtail) + #endif /* CONFIG_IPIPE */ diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c index 2024945..a7d7b2d 100644 --- a/arch/blackfin/mach-common/ints-priority.c +++ b/arch/blackfin/mach-common/ints-priority.c @@ -161,11 +161,15 @@ static void bfin_core_unmask_irq(unsigned int irq) static void bfin_internal_mask_irq(unsigned int irq) { + unsigned long flags; + #ifdef CONFIG_BF53x + local_irq_save_hw(flags); bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() & ~(1 << SIC_SYSIRQ(irq))); #else unsigned mask_bank, mask_bit; + local_irq_save_hw(flags); mask_bank = SIC_SYSIRQ(irq) / 32; mask_bit = SIC_SYSIRQ(irq) % 32; bfin_write_SIC_IMASK(mask_bank, bfin_read_SIC_IMASK(mask_bank) & @@ -175,15 +179,20 @@ static void bfin_internal_mask_irq(unsigned int irq) ~(1 << mask_bit)); #endif #endif + local_irq_restore_hw(flags); } static void bfin_internal_unmask_irq(unsigned int irq) { + unsigned long flags; + #ifdef CONFIG_BF53x + local_irq_save_hw(flags); bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() | (1 << SIC_SYSIRQ(irq))); #else unsigned mask_bank, mask_bit; + local_irq_save_hw(flags); mask_bank = SIC_SYSIRQ(irq) / 32; mask_bit = SIC_SYSIRQ(irq) % 32; bfin_write_SIC_IMASK(mask_bank, bfin_read_SIC_IMASK(mask_bank) | @@ -193,6 +202,7 @@ static void bfin_internal_unmask_irq(unsigned int irq) (1 << mask_bit)); #endif #endif + local_irq_restore_hw(flags); } #ifdef CONFIG_PM @@ -390,7 +400,7 @@ static void bfin_demux_error_irq(unsigned int int_err_irq, static inline void bfin_set_irq_handler(unsigned irq, irq_flow_handler_t handle) { #ifdef CONFIG_IPIPE - _set_irq_handler(irq, handle_edge_irq); + _set_irq_handler(irq, handle_level_irq); #else struct irq_desc *desc = irq_desc + irq; /* May not call generic set_irq_handler() due to spinlock @@ -1055,13 +1065,18 @@ int __init init_arch_irq(void) #endif default: #ifdef CONFIG_IPIPE - /* - * We want internal interrupt sources to be masked, because - * ISRs may trigger interrupts recursively (e.g. DMA), but - * interrupts are _not_ masked at CPU level. So let's handle - * them as level interrupts. - */ - set_irq_handler(irq, handle_level_irq); + /* + * We want internal interrupt sources to be + * masked, because ISRs may trigger interrupts + * recursively (e.g. DMA), but interrupts are + * _not_ masked at CPU level. So let's handle + * most of them as level interrupts, except + * the timer interrupt which is special. + */ + if (irq == IRQ_SYSTMR || irq == IRQ_CORETMR) + set_irq_handler(irq, handle_simple_irq); + else + set_irq_handler(irq, handle_level_irq); #else /* !CONFIG_IPIPE */ set_irq_handler(irq, handle_simple_irq); #endif /* !CONFIG_IPIPE */ @@ -1123,9 +1138,8 @@ int __init init_arch_irq(void) #ifdef CONFIG_IPIPE for (irq = 0; irq < NR_IRQS; irq++) { - struct irq_desc *desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); desc->ic_prio = __ipipe_get_irq_priority(irq); - desc->thr_prio = __ipipe_get_irqthread_priority(irq); } #endif /* CONFIG_IPIPE */ @@ -1208,76 +1222,21 @@ int __ipipe_get_irq_priority(unsigned irq) return IVG15; } -int __ipipe_get_irqthread_priority(unsigned irq) -{ - int ient, prio; - int demux_irq; - - /* The returned priority value is rescaled to [0..IVG13+1] - * with 0 being the lowest effective priority level. */ - - if (irq <= IRQ_CORETMR) - return IVG13 - irq + 1; - - /* GPIO IRQs are given the priority of the demux - * interrupt. */ - if (IS_GPIOIRQ(irq)) { -#if defined(CONFIG_BF54x) - u32 bank = PINT_2_BANK(irq2pint_lut[irq - SYS_IRQS]); - demux_irq = (bank == 0 ? IRQ_PINT0 : - bank == 1 ? IRQ_PINT1 : - bank == 2 ? IRQ_PINT2 : - IRQ_PINT3); -#elif defined(CONFIG_BF561) - demux_irq = (irq >= IRQ_PF32 ? IRQ_PROG2_INTA : - irq >= IRQ_PF16 ? IRQ_PROG1_INTA : - IRQ_PROG0_INTA); -#elif defined(CONFIG_BF52x) - demux_irq = (irq >= IRQ_PH0 ? IRQ_PORTH_INTA : - irq >= IRQ_PG0 ? IRQ_PORTG_INTA : - IRQ_PORTF_INTA); -#else - demux_irq = irq; -#endif - return IVG13 - PRIO_GPIODEMUX(demux_irq) + 1; - } - - /* The GPIO demux interrupt is given a lower priority - * than the GPIO IRQs, so that its threaded handler - * unmasks the interrupt line after the decoded IRQs - * have been processed. */ - prio = PRIO_GPIODEMUX(irq); - /* demux irq? */ - if (prio != -1) - return IVG13 - prio; - - for (ient = 0; ient < NR_PERI_INTS; ient++) { - struct ivgx *ivg = ivg_table + ient; - if (ivg->irqno == irq) { - for (prio = 0; prio <= IVG13-IVG7; prio++) { - if (ivg7_13[prio].ifirst <= ivg && - ivg7_13[prio].istop > ivg) - return IVG7 - prio; - } - } - } - - return 0; -} - /* Hw interrupts are disabled on entry (check SAVE_CONTEXT). */ #ifdef CONFIG_DO_IRQ_L1 __attribute__((l1_text)) #endif asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs) { + struct ipipe_percpu_domain_data *p = ipipe_root_cpudom_ptr(); + struct ipipe_domain *this_domain = ipipe_current_domain; struct ivgx *ivg_stop = ivg7_13[vec-IVG7].istop; struct ivgx *ivg = ivg7_13[vec-IVG7].ifirst; - int irq; + int irq, s; if (likely(vec == EVT_IVTMR_P)) { irq = IRQ_CORETMR; - goto handle_irq; + goto core_tick; } SSYNC(); @@ -1319,24 +1278,39 @@ asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs) irq = ivg->irqno; if (irq == IRQ_SYSTMR) { +#ifdef CONFIG_GENERIC_CLOCKEVENTS +core_tick: +#else bfin_write_TIMER_STATUS(1); /* Latch TIMIL0 */ +#endif /* This is basically what we need from the register frame. */ __raw_get_cpu_var(__ipipe_tick_regs).ipend = regs->ipend; __raw_get_cpu_var(__ipipe_tick_regs).pc = regs->pc; - if (!ipipe_root_domain_p) - __raw_get_cpu_var(__ipipe_tick_regs).ipend |= 0x10; - else + if (this_domain != ipipe_root_domain) __raw_get_cpu_var(__ipipe_tick_regs).ipend &= ~0x10; + else + __raw_get_cpu_var(__ipipe_tick_regs).ipend |= 0x10; } -handle_irq: +#ifndef CONFIG_GENERIC_CLOCKEVENTS +core_tick: +#endif + if (this_domain == ipipe_root_domain) { + s = __test_and_set_bit(IPIPE_SYNCDEFER_FLAG, &p->status); + barrier(); + } ipipe_trace_irq_entry(irq); __ipipe_handle_irq(irq, regs); - ipipe_trace_irq_exit(irq); + ipipe_trace_irq_exit(irq); - if (ipipe_root_domain_p) - return !test_bit(IPIPE_STALL_FLAG, &ipipe_root_cpudom_var(status)); + if (this_domain == ipipe_root_domain) { + set_thread_flag(TIF_IRQ_SYNC); + if (!s) { + __clear_bit(IPIPE_SYNCDEFER_FLAG, &p->status); + return !test_bit(IPIPE_STALL_FLAG, &p->status); + } + } return 0; } diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 77c9928..93eab61 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -158,10 +158,14 @@ static irqreturn_t ipi_handler(int irq, void *dev_instance) kfree(msg); break; case BFIN_IPI_CALL_FUNC: + spin_unlock(&msg_queue->lock); ipi_call_function(cpu, msg); + spin_lock(&msg_queue->lock); break; case BFIN_IPI_CPU_STOP: + spin_unlock(&msg_queue->lock); ipi_cpu_stop(cpu); + spin_lock(&msg_queue->lock); kfree(msg); break; default: @@ -457,7 +461,7 @@ void smp_icache_flush_range_others(unsigned long start, unsigned long end) smp_flush_data.start = start; smp_flush_data.end = end; - if (smp_call_function(&ipi_flush_icache, &smp_flush_data, 1)) + if (smp_call_function(&ipi_flush_icache, &smp_flush_data, 0)) printk(KERN_WARNING "SMP: failed to run I-cache flush request on other CPUs\n"); } EXPORT_SYMBOL_GPL(smp_icache_flush_range_others); diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c index d0532b7..9c3629b 100644 --- a/arch/blackfin/mm/init.c +++ b/arch/blackfin/mm/init.c @@ -104,7 +104,7 @@ void __init paging_init(void) } } -asmlinkage void init_pda(void) +asmlinkage void __init init_pda(void) { unsigned int cpu = raw_smp_processor_id(); diff --git a/arch/cris/include/asm/ftrace.h b/arch/cris/include/asm/ftrace.h new file mode 100644 index 0000000..40a8c17 --- /dev/null +++ b/arch/cris/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/cris/kernel/irq.c b/arch/cris/kernel/irq.c index 2dfac8c..7f642fc 100644 --- a/arch/cris/kernel/irq.c +++ b/arch/cris/kernel/irq.c @@ -66,7 +66,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%10u ", kstat_irqs(i)); #else for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); #endif seq_printf(p, " %14s", irq_desc[i].chip->typename); seq_printf(p, " %s", action->name); diff --git a/arch/frv/kernel/irq.c b/arch/frv/kernel/irq.c index 73abae7..af3e824 100644 --- a/arch/frv/kernel/irq.c +++ b/arch/frv/kernel/irq.c @@ -74,7 +74,7 @@ int show_interrupts(struct seq_file *p, void *v) if (action) { seq_printf(p, "%3d: ", i); for_each_present_cpu(cpu) - seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu)); seq_printf(p, " %10s", irq_desc[i].chip->name ? : "-"); seq_printf(p, " %s", action->name); for (action = action->next; diff --git a/arch/h8300/include/asm/ftrace.h b/arch/h8300/include/asm/ftrace.h new file mode 100644 index 0000000..40a8c17 --- /dev/null +++ b/arch/h8300/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/h8300/include/asm/swab.h b/arch/h8300/include/asm/swab.h index c108f39..39abbf5 100644 --- a/arch/h8300/include/asm/swab.h +++ b/arch/h8300/include/asm/swab.h @@ -1,7 +1,7 @@ #ifndef _H8300_SWAB_H #define _H8300_SWAB_H -#include +#include #if defined(__GNUC__) && !defined(__STRICT_ANSI__) || defined(__KERNEL__) # define __SWAB_64_THRU_32__ diff --git a/arch/h8300/kernel/irq.c b/arch/h8300/kernel/irq.c index ef4f004..74f8dd7 100644 --- a/arch/h8300/kernel/irq.c +++ b/arch/h8300/kernel/irq.c @@ -183,7 +183,7 @@ asmlinkage void do_IRQ(int irq) #if defined(CONFIG_PROC_FS) int show_interrupts(struct seq_file *p, void *v) { - int i = *(loff_t *) v, j; + int i = *(loff_t *) v; struct irqaction * action; unsigned long flags; @@ -196,7 +196,7 @@ int show_interrupts(struct seq_file *p, void *v) if (!action) goto unlock; seq_printf(p, "%3d: ",i); - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs(i)); seq_printf(p, " %14s", irq_desc[i].chip->name); seq_printf(p, "-%-8s", irq_desc[i].name); seq_printf(p, " %s", action->name); diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 153e727..294a3b1 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -22,6 +22,9 @@ config IA64 select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_DYNAMIC_FTRACE if (!ITANIUM) + select HAVE_FUNCTION_TRACER select HAVE_DMA_ATTRS select HAVE_KVM select HAVE_ARCH_TRACEHOOK diff --git a/arch/ia64/dig/Makefile b/arch/ia64/dig/Makefile index 5c02838..2f7cadd 100644 --- a/arch/ia64/dig/Makefile +++ b/arch/ia64/dig/Makefile @@ -7,8 +7,8 @@ obj-y := setup.o ifeq ($(CONFIG_DMAR), y) -obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o dig_vtd_iommu.o +obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o else obj-$(CONFIG_IA64_GENERIC) += machvec.o endif -obj-$(CONFIG_IA64_DIG_VTD) += dig_vtd_iommu.o + diff --git a/arch/ia64/dig/dig_vtd_iommu.c b/arch/ia64/dig/dig_vtd_iommu.c deleted file mode 100644 index 1c8a079..0000000 --- a/arch/ia64/dig/dig_vtd_iommu.c +++ /dev/null @@ -1,59 +0,0 @@ -#include -#include -#include -#include - -void * -vtd_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flags) -{ - return intel_alloc_coherent(dev, size, dma_handle, flags); -} -EXPORT_SYMBOL_GPL(vtd_alloc_coherent); - -void -vtd_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle) -{ - intel_free_coherent(dev, size, vaddr, dma_handle); -} -EXPORT_SYMBOL_GPL(vtd_free_coherent); - -dma_addr_t -vtd_map_single_attrs(struct device *dev, void *addr, size_t size, - int dir, struct dma_attrs *attrs) -{ - return intel_map_single(dev, (phys_addr_t)addr, size, dir); -} -EXPORT_SYMBOL_GPL(vtd_map_single_attrs); - -void -vtd_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, - int dir, struct dma_attrs *attrs) -{ - intel_unmap_single(dev, iova, size, dir); -} -EXPORT_SYMBOL_GPL(vtd_unmap_single_attrs); - -int -vtd_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, - int dir, struct dma_attrs *attrs) -{ - return intel_map_sg(dev, sglist, nents, dir); -} -EXPORT_SYMBOL_GPL(vtd_map_sg_attrs); - -void -vtd_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, - int nents, int dir, struct dma_attrs *attrs) -{ - intel_unmap_sg(dev, sglist, nents, dir); -} -EXPORT_SYMBOL_GPL(vtd_unmap_sg_attrs); - -int -vtd_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return 0; -} -EXPORT_SYMBOL_GPL(vtd_dma_mapping_error); diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c index 2769dbf..e4a80d8 100644 --- a/arch/ia64/hp/common/hwsw_iommu.c +++ b/arch/ia64/hp/common/hwsw_iommu.c @@ -13,49 +13,34 @@ */ #include +#include #include - #include +extern struct dma_map_ops sba_dma_ops, swiotlb_dma_ops; + /* swiotlb declarations & definitions: */ extern int swiotlb_late_init_with_default_size (size_t size); -/* hwiommu declarations & definitions: */ - -extern ia64_mv_dma_alloc_coherent sba_alloc_coherent; -extern ia64_mv_dma_free_coherent sba_free_coherent; -extern ia64_mv_dma_map_single_attrs sba_map_single_attrs; -extern ia64_mv_dma_unmap_single_attrs sba_unmap_single_attrs; -extern ia64_mv_dma_map_sg_attrs sba_map_sg_attrs; -extern ia64_mv_dma_unmap_sg_attrs sba_unmap_sg_attrs; -extern ia64_mv_dma_supported sba_dma_supported; -extern ia64_mv_dma_mapping_error sba_dma_mapping_error; - -#define hwiommu_alloc_coherent sba_alloc_coherent -#define hwiommu_free_coherent sba_free_coherent -#define hwiommu_map_single_attrs sba_map_single_attrs -#define hwiommu_unmap_single_attrs sba_unmap_single_attrs -#define hwiommu_map_sg_attrs sba_map_sg_attrs -#define hwiommu_unmap_sg_attrs sba_unmap_sg_attrs -#define hwiommu_dma_supported sba_dma_supported -#define hwiommu_dma_mapping_error sba_dma_mapping_error -#define hwiommu_sync_single_for_cpu machvec_dma_sync_single -#define hwiommu_sync_sg_for_cpu machvec_dma_sync_sg -#define hwiommu_sync_single_for_device machvec_dma_sync_single -#define hwiommu_sync_sg_for_device machvec_dma_sync_sg - - /* * Note: we need to make the determination of whether or not to use * the sw I/O TLB based purely on the device structure. Anything else * would be unreliable or would be too intrusive. */ -static inline int -use_swiotlb (struct device *dev) +static inline int use_swiotlb(struct device *dev) { - return dev && dev->dma_mask && !hwiommu_dma_supported(dev, *dev->dma_mask); + return dev && dev->dma_mask && + !sba_dma_ops.dma_supported(dev, *dev->dma_mask); } +struct dma_map_ops *hwsw_dma_get_ops(struct device *dev) +{ + if (use_swiotlb(dev)) + return &swiotlb_dma_ops; + return &sba_dma_ops; +} +EXPORT_SYMBOL(hwsw_dma_get_ops); + void __init hwsw_init (void) { @@ -71,125 +56,3 @@ hwsw_init (void) #endif } } - -void * -hwsw_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags) -{ - if (use_swiotlb(dev)) - return swiotlb_alloc_coherent(dev, size, dma_handle, flags); - else - return hwiommu_alloc_coherent(dev, size, dma_handle, flags); -} - -void -hwsw_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle) -{ - if (use_swiotlb(dev)) - swiotlb_free_coherent(dev, size, vaddr, dma_handle); - else - hwiommu_free_coherent(dev, size, vaddr, dma_handle); -} - -dma_addr_t -hwsw_map_single_attrs(struct device *dev, void *addr, size_t size, int dir, - struct dma_attrs *attrs) -{ - if (use_swiotlb(dev)) - return swiotlb_map_single_attrs(dev, addr, size, dir, attrs); - else - return hwiommu_map_single_attrs(dev, addr, size, dir, attrs); -} -EXPORT_SYMBOL(hwsw_map_single_attrs); - -void -hwsw_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, - int dir, struct dma_attrs *attrs) -{ - if (use_swiotlb(dev)) - return swiotlb_unmap_single_attrs(dev, iova, size, dir, attrs); - else - return hwiommu_unmap_single_attrs(dev, iova, size, dir, attrs); -} -EXPORT_SYMBOL(hwsw_unmap_single_attrs); - -int -hwsw_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, - int dir, struct dma_attrs *attrs) -{ - if (use_swiotlb(dev)) - return swiotlb_map_sg_attrs(dev, sglist, nents, dir, attrs); - else - return hwiommu_map_sg_attrs(dev, sglist, nents, dir, attrs); -} -EXPORT_SYMBOL(hwsw_map_sg_attrs); - -void -hwsw_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, - int dir, struct dma_attrs *attrs) -{ - if (use_swiotlb(dev)) - return swiotlb_unmap_sg_attrs(dev, sglist, nents, dir, attrs); - else - return hwiommu_unmap_sg_attrs(dev, sglist, nents, dir, attrs); -} -EXPORT_SYMBOL(hwsw_unmap_sg_attrs); - -void -hwsw_sync_single_for_cpu (struct device *dev, dma_addr_t addr, size_t size, int dir) -{ - if (use_swiotlb(dev)) - swiotlb_sync_single_for_cpu(dev, addr, size, dir); - else - hwiommu_sync_single_for_cpu(dev, addr, size, dir); -} - -void -hwsw_sync_sg_for_cpu (struct device *dev, struct scatterlist *sg, int nelems, int dir) -{ - if (use_swiotlb(dev)) - swiotlb_sync_sg_for_cpu(dev, sg, nelems, dir); - else - hwiommu_sync_sg_for_cpu(dev, sg, nelems, dir); -} - -void -hwsw_sync_single_for_device (struct device *dev, dma_addr_t addr, size_t size, int dir) -{ - if (use_swiotlb(dev)) - swiotlb_sync_single_for_device(dev, addr, size, dir); - else - hwiommu_sync_single_for_device(dev, addr, size, dir); -} - -void -hwsw_sync_sg_for_device (struct device *dev, struct scatterlist *sg, int nelems, int dir) -{ - if (use_swiotlb(dev)) - swiotlb_sync_sg_for_device(dev, sg, nelems, dir); - else - hwiommu_sync_sg_for_device(dev, sg, nelems, dir); -} - -int -hwsw_dma_supported (struct device *dev, u64 mask) -{ - if (hwiommu_dma_supported(dev, mask)) - return 1; - return swiotlb_dma_supported(dev, mask); -} - -int -hwsw_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return hwiommu_dma_mapping_error(dev, dma_addr) || - swiotlb_dma_mapping_error(dev, dma_addr); -} - -EXPORT_SYMBOL(hwsw_dma_mapping_error); -EXPORT_SYMBOL(hwsw_dma_supported); -EXPORT_SYMBOL(hwsw_alloc_coherent); -EXPORT_SYMBOL(hwsw_free_coherent); -EXPORT_SYMBOL(hwsw_sync_single_for_cpu); -EXPORT_SYMBOL(hwsw_sync_single_for_device); -EXPORT_SYMBOL(hwsw_sync_sg_for_cpu); -EXPORT_SYMBOL(hwsw_sync_sg_for_device); diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 6d5e6c5..56ceb68 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -36,6 +36,7 @@ #include /* hweight64() */ #include #include +#include #include /* ia64_get_itc() */ #include @@ -908,11 +909,13 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt) * * See Documentation/PCI/PCI-DMA-mapping.txt */ -dma_addr_t -sba_map_single_attrs(struct device *dev, void *addr, size_t size, int dir, - struct dma_attrs *attrs) +static dma_addr_t sba_map_page(struct device *dev, struct page *page, + unsigned long poff, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { struct ioc *ioc; + void *addr = page_address(page) + poff; dma_addr_t iovp; dma_addr_t offset; u64 *pdir_start; @@ -990,7 +993,14 @@ sba_map_single_attrs(struct device *dev, void *addr, size_t size, int dir, #endif return SBA_IOVA(ioc, iovp, offset); } -EXPORT_SYMBOL(sba_map_single_attrs); + +static dma_addr_t sba_map_single_attrs(struct device *dev, void *addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return sba_map_page(dev, virt_to_page(addr), + (unsigned long)addr & ~PAGE_MASK, size, dir, attrs); +} #ifdef ENABLE_MARK_CLEAN static SBA_INLINE void @@ -1026,8 +1036,8 @@ sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size) * * See Documentation/PCI/PCI-DMA-mapping.txt */ -void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, - int dir, struct dma_attrs *attrs) +static void sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct ioc *ioc; #if DELAYED_RESOURCE_CNT > 0 @@ -1094,7 +1104,12 @@ void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, spin_unlock_irqrestore(&ioc->res_lock, flags); #endif /* DELAYED_RESOURCE_CNT == 0 */ } -EXPORT_SYMBOL(sba_unmap_single_attrs); + +void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + sba_unmap_page(dev, iova, size, dir, attrs); +} /** * sba_alloc_coherent - allocate/map shared mem for DMA @@ -1104,7 +1119,7 @@ EXPORT_SYMBOL(sba_unmap_single_attrs); * * See Documentation/PCI/PCI-DMA-mapping.txt */ -void * +static void * sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags) { struct ioc *ioc; @@ -1167,7 +1182,8 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp * * See Documentation/PCI/PCI-DMA-mapping.txt */ -void sba_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle) +static void sba_free_coherent (struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle) { sba_unmap_single_attrs(dev, dma_handle, size, 0, NULL); free_pages((unsigned long) vaddr, get_order(size)); @@ -1422,8 +1438,9 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev, * * See Documentation/PCI/PCI-DMA-mapping.txt */ -int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, - int dir, struct dma_attrs *attrs) +static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct ioc *ioc; int coalesced, filled = 0; @@ -1502,7 +1519,6 @@ int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, return filled; } -EXPORT_SYMBOL(sba_map_sg_attrs); /** * sba_unmap_sg_attrs - unmap Scatter/Gather list @@ -1514,8 +1530,9 @@ EXPORT_SYMBOL(sba_map_sg_attrs); * * See Documentation/PCI/PCI-DMA-mapping.txt */ -void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, - int nents, int dir, struct dma_attrs *attrs) +static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) { #ifdef ASSERT_PDIR_SANITY struct ioc *ioc; @@ -1551,7 +1568,6 @@ void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, #endif } -EXPORT_SYMBOL(sba_unmap_sg_attrs); /************************************************************** * @@ -2064,6 +2080,8 @@ static struct acpi_driver acpi_sba_ioc_driver = { }, }; +extern struct dma_map_ops swiotlb_dma_ops; + static int __init sba_init(void) { @@ -2077,6 +2095,7 @@ sba_init(void) * a successful kdump kernel boot is to use the swiotlb. */ if (is_kdump_kernel()) { + dma_ops = &swiotlb_dma_ops; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to initialize software I/O TLB:" " Try machvec=dig boot option"); @@ -2092,6 +2111,7 @@ sba_init(void) * If we didn't find something sba_iommu can claim, we * need to setup the swiotlb and switch to the dig machvec. */ + dma_ops = &swiotlb_dma_ops; if (swiotlb_late_init_with_default_size(64 * (1<<20)) != 0) panic("Unable to find SBA IOMMU or initialize " "software I/O TLB: Try machvec=dig boot option"); @@ -2138,15 +2158,13 @@ nosbagart(char *str) return 1; } -int -sba_dma_supported (struct device *dev, u64 mask) +static int sba_dma_supported (struct device *dev, u64 mask) { /* make sure it's at least 32bit capable */ return ((mask & 0xFFFFFFFFUL) == 0xFFFFFFFFUL); } -int -sba_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +static int sba_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } @@ -2176,7 +2194,22 @@ sba_page_override(char *str) __setup("sbapagesize=",sba_page_override); -EXPORT_SYMBOL(sba_dma_mapping_error); -EXPORT_SYMBOL(sba_dma_supported); -EXPORT_SYMBOL(sba_alloc_coherent); -EXPORT_SYMBOL(sba_free_coherent); +struct dma_map_ops sba_dma_ops = { + .alloc_coherent = sba_alloc_coherent, + .free_coherent = sba_free_coherent, + .map_page = sba_map_page, + .unmap_page = sba_unmap_page, + .map_sg = sba_map_sg_attrs, + .unmap_sg = sba_unmap_sg_attrs, + .sync_single_for_cpu = machvec_dma_sync_single, + .sync_sg_for_cpu = machvec_dma_sync_sg, + .sync_single_for_device = machvec_dma_sync_single, + .sync_sg_for_device = machvec_dma_sync_sg, + .dma_supported = sba_dma_supported, + .mapping_error = sba_dma_mapping_error, +}; + +void sba_dma_init(void) +{ + dma_ops = &sba_dma_ops; +} diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h index 1f912d9..36c0009 100644 --- a/arch/ia64/include/asm/dma-mapping.h +++ b/arch/ia64/include/asm/dma-mapping.h @@ -11,99 +11,128 @@ #define ARCH_HAS_DMA_GET_REQUIRED_MASK -struct dma_mapping_ops { - int (*mapping_error)(struct device *dev, - dma_addr_t dma_addr); - void* (*alloc_coherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp); - void (*free_coherent)(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle); - dma_addr_t (*map_single)(struct device *hwdev, unsigned long ptr, - size_t size, int direction); - void (*unmap_single)(struct device *dev, dma_addr_t addr, - size_t size, int direction); - void (*sync_single_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_for_device)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_range_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_single_range_for_device)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_sg_for_cpu)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - void (*sync_sg_for_device)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - int (*map_sg)(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); - void (*unmap_sg)(struct device *hwdev, - struct scatterlist *sg, int nents, - int direction); - int (*dma_supported_op)(struct device *hwdev, u64 mask); - int is_phys; -}; - -extern struct dma_mapping_ops *dma_ops; +extern struct dma_map_ops *dma_ops; extern struct ia64_machine_vector ia64_mv; extern void set_iommu_machvec(void); -#define dma_alloc_coherent(dev, size, handle, gfp) \ - platform_dma_alloc_coherent(dev, size, handle, (gfp) | GFP_DMA) +extern void machvec_dma_sync_single(struct device *, dma_addr_t, size_t, + enum dma_data_direction); +extern void machvec_dma_sync_sg(struct device *, struct scatterlist *, int, + enum dma_data_direction); -/* coherent mem. is cheap */ -static inline void * -dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flag) +static inline void *dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *daddr, gfp_t gfp) { - return dma_alloc_coherent(dev, size, dma_handle, flag); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->alloc_coherent(dev, size, daddr, gfp); } -#define dma_free_coherent platform_dma_free_coherent -static inline void -dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle) + +static inline void dma_free_coherent(struct device *dev, size_t size, + void *caddr, dma_addr_t daddr) +{ + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->free_coherent(dev, size, caddr, daddr); +} + +#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) +#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) + +static inline dma_addr_t dma_map_single_attrs(struct device *dev, + void *caddr, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->map_page(dev, virt_to_page(caddr), + (unsigned long)caddr & ~PAGE_MASK, size, + dir, attrs); +} + +static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t daddr, + size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->unmap_page(dev, daddr, size, dir, attrs); +} + +#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL) +#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, NULL) + +static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->map_sg(dev, sgl, nents, dir, attrs); +} + +static inline void dma_unmap_sg_attrs(struct device *dev, + struct scatterlist *sgl, int nents, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->unmap_sg(dev, sgl, nents, dir, attrs); +} + +#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL) +#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, NULL) + +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t daddr, + size_t size, + enum dma_data_direction dir) { - dma_free_coherent(dev, size, cpu_addr, dma_handle); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->sync_single_for_cpu(dev, daddr, size, dir); } -#define dma_map_single_attrs platform_dma_map_single_attrs -static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, - size_t size, int dir) + +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, + int nents, enum dma_data_direction dir) { - return dma_map_single_attrs(dev, cpu_addr, size, dir, NULL); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->sync_sg_for_cpu(dev, sgl, nents, dir); } -#define dma_map_sg_attrs platform_dma_map_sg_attrs -static inline int dma_map_sg(struct device *dev, struct scatterlist *sgl, - int nents, int dir) + +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t daddr, + size_t size, + enum dma_data_direction dir) { - return dma_map_sg_attrs(dev, sgl, nents, dir, NULL); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->sync_single_for_device(dev, daddr, size, dir); } -#define dma_unmap_single_attrs platform_dma_unmap_single_attrs -static inline void dma_unmap_single(struct device *dev, dma_addr_t cpu_addr, - size_t size, int dir) + +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, + int nents, + enum dma_data_direction dir) { - return dma_unmap_single_attrs(dev, cpu_addr, size, dir, NULL); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->sync_sg_for_device(dev, sgl, nents, dir); } -#define dma_unmap_sg_attrs platform_dma_unmap_sg_attrs -static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sgl, - int nents, int dir) + +static inline int dma_mapping_error(struct device *dev, dma_addr_t daddr) +{ + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->mapping_error(dev, daddr); +} + +static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, + size_t offset, size_t size, + enum dma_data_direction dir) { - return dma_unmap_sg_attrs(dev, sgl, nents, dir, NULL); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->map_page(dev, page, offset, size, dir, NULL); } -#define dma_sync_single_for_cpu platform_dma_sync_single_for_cpu -#define dma_sync_sg_for_cpu platform_dma_sync_sg_for_cpu -#define dma_sync_single_for_device platform_dma_sync_single_for_device -#define dma_sync_sg_for_device platform_dma_sync_sg_for_device -#define dma_mapping_error platform_dma_mapping_error -#define dma_map_page(dev, pg, off, size, dir) \ - dma_map_single(dev, page_address(pg) + (off), (size), (dir)) -#define dma_unmap_page(dev, dma_addr, size, dir) \ - dma_unmap_single(dev, dma_addr, size, dir) +static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + dma_unmap_single(dev, addr, size, dir); +} /* * Rest of this file is part of the "Advanced DMA API". Use at your own risk. @@ -115,7 +144,11 @@ static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sgl, #define dma_sync_single_range_for_device(dev, dma_handle, offset, size, dir) \ dma_sync_single_for_device(dev, dma_handle, size, dir) -#define dma_supported platform_dma_supported +static inline int dma_supported(struct device *dev, u64 mask) +{ + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->dma_supported(dev, mask); +} static inline int dma_set_mask (struct device *dev, u64 mask) @@ -141,11 +174,4 @@ dma_cache_sync (struct device *dev, void *vaddr, size_t size, #define dma_is_consistent(d, h) (1) /* all we do is coherent memory... */ -static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) -{ - return dma_ops; -} - - - #endif /* _ASM_IA64_DMA_MAPPING_H */ diff --git a/arch/ia64/include/asm/fpu.h b/arch/ia64/include/asm/fpu.h index 3859558..0c26157 100644 --- a/arch/ia64/include/asm/fpu.h +++ b/arch/ia64/include/asm/fpu.h @@ -6,8 +6,6 @@ * David Mosberger-Tang */ -#include - /* floating point status register: */ #define FPSR_TRAP_VD (1 << 0) /* invalid op trap disabled */ #define FPSR_TRAP_DD (1 << 1) /* denormal trap disabled */ diff --git a/arch/ia64/include/asm/ftrace.h b/arch/ia64/include/asm/ftrace.h new file mode 100644 index 0000000..d20db3c --- /dev/null +++ b/arch/ia64/include/asm/ftrace.h @@ -0,0 +1,28 @@ +#ifndef _ASM_IA64_FTRACE_H +#define _ASM_IA64_FTRACE_H + +#ifdef CONFIG_FUNCTION_TRACER +#define MCOUNT_INSN_SIZE 32 /* sizeof mcount call */ + +#ifndef __ASSEMBLY__ +extern void _mcount(unsigned long pfs, unsigned long r1, unsigned long b0, unsigned long r0); +#define mcount _mcount + +#include +/* In IA64, MCOUNT_ADDR is set in link time, so it's not a constant at compile time */ +#define MCOUNT_ADDR (((struct fnptr *)mcount)->ip) +#define FTRACE_ADDR (((struct fnptr *)ftrace_caller)->ip) + +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* second bundle, insn 2 */ + return addr - 0x12; +} + +struct dyn_arch_ftrace { +}; +#endif + +#endif /* CONFIG_FUNCTION_TRACER */ + +#endif /* _ASM_IA64_FTRACE_H */ diff --git a/arch/ia64/include/asm/gcc_intrin.h b/arch/ia64/include/asm/gcc_intrin.h index 0f5b559..c2c5fd8 100644 --- a/arch/ia64/include/asm/gcc_intrin.h +++ b/arch/ia64/include/asm/gcc_intrin.h @@ -6,6 +6,7 @@ * Copyright (C) 2002,2003 Suresh Siddha */ +#include #include /* define this macro to get some asm stmts included in 'c' files */ diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h index 140e495..d514cd9 100644 --- a/arch/ia64/include/asm/hardirq.h +++ b/arch/ia64/include/asm/hardirq.h @@ -20,16 +20,6 @@ #define local_softirq_pending() (local_cpu_data->softirq_pending) -#define HARDIRQ_BITS 14 - -/* - * The hardirq mask has to be large enough to have space for potentially all IRQ sources - * in the system nesting on a single CPU: - */ -#if (1 << HARDIRQ_BITS) < NR_IRQS -# error HARDIRQ_BITS is too low! -#endif - extern void __iomem *ipi_base_addr; void ack_bad_irq(unsigned int irq); diff --git a/arch/ia64/include/asm/intrinsics.h b/arch/ia64/include/asm/intrinsics.h index a3e44a5..c47830e 100644 --- a/arch/ia64/include/asm/intrinsics.h +++ b/arch/ia64/include/asm/intrinsics.h @@ -10,6 +10,7 @@ #ifndef __ASSEMBLY__ +#include /* include compiler specific intrinsics */ #include #ifdef __INTEL_COMPILER diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h index bfa86b6..2b0a38e 100644 --- a/arch/ia64/include/asm/kvm.h +++ b/arch/ia64/include/asm/kvm.h @@ -21,8 +21,7 @@ * */ -#include - +#include #include /* Select x86 specific features in */ diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h index fe87b21..367d299 100644 --- a/arch/ia64/include/asm/machvec.h +++ b/arch/ia64/include/asm/machvec.h @@ -11,7 +11,6 @@ #define _ASM_IA64_MACHVEC_H #include -#include /* forward declarations: */ struct device; @@ -45,24 +44,8 @@ typedef void ia64_mv_kernel_launch_event_t(void); /* DMA-mapping interface: */ typedef void ia64_mv_dma_init (void); -typedef void *ia64_mv_dma_alloc_coherent (struct device *, size_t, dma_addr_t *, gfp_t); -typedef void ia64_mv_dma_free_coherent (struct device *, size_t, void *, dma_addr_t); -typedef dma_addr_t ia64_mv_dma_map_single (struct device *, void *, size_t, int); -typedef void ia64_mv_dma_unmap_single (struct device *, dma_addr_t, size_t, int); -typedef int ia64_mv_dma_map_sg (struct device *, struct scatterlist *, int, int); -typedef void ia64_mv_dma_unmap_sg (struct device *, struct scatterlist *, int, int); -typedef void ia64_mv_dma_sync_single_for_cpu (struct device *, dma_addr_t, size_t, int); -typedef void ia64_mv_dma_sync_sg_for_cpu (struct device *, struct scatterlist *, int, int); -typedef void ia64_mv_dma_sync_single_for_device (struct device *, dma_addr_t, size_t, int); -typedef void ia64_mv_dma_sync_sg_for_device (struct device *, struct scatterlist *, int, int); -typedef int ia64_mv_dma_mapping_error(struct device *, dma_addr_t dma_addr); -typedef int ia64_mv_dma_supported (struct device *, u64); - -typedef dma_addr_t ia64_mv_dma_map_single_attrs (struct device *, void *, size_t, int, struct dma_attrs *); -typedef void ia64_mv_dma_unmap_single_attrs (struct device *, dma_addr_t, size_t, int, struct dma_attrs *); -typedef int ia64_mv_dma_map_sg_attrs (struct device *, struct scatterlist *, int, int, struct dma_attrs *); -typedef void ia64_mv_dma_unmap_sg_attrs (struct device *, struct scatterlist *, int, int, struct dma_attrs *); typedef u64 ia64_mv_dma_get_required_mask (struct device *); +typedef struct dma_map_ops *ia64_mv_dma_get_ops(struct device *); /* * WARNING: The legacy I/O space is _architected_. Platforms are @@ -114,8 +97,6 @@ machvec_noop_bus (struct pci_bus *bus) extern void machvec_setup (char **); extern void machvec_timer_interrupt (int, void *); -extern void machvec_dma_sync_single (struct device *, dma_addr_t, size_t, int); -extern void machvec_dma_sync_sg (struct device *, struct scatterlist *, int, int); extern void machvec_tlb_migrate_finish (struct mm_struct *); # if defined (CONFIG_IA64_HP_SIM) @@ -148,19 +129,8 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *); # define platform_global_tlb_purge ia64_mv.global_tlb_purge # define platform_tlb_migrate_finish ia64_mv.tlb_migrate_finish # define platform_dma_init ia64_mv.dma_init -# define platform_dma_alloc_coherent ia64_mv.dma_alloc_coherent -# define platform_dma_free_coherent ia64_mv.dma_free_coherent -# define platform_dma_map_single_attrs ia64_mv.dma_map_single_attrs -# define platform_dma_unmap_single_attrs ia64_mv.dma_unmap_single_attrs -# define platform_dma_map_sg_attrs ia64_mv.dma_map_sg_attrs -# define platform_dma_unmap_sg_attrs ia64_mv.dma_unmap_sg_attrs -# define platform_dma_sync_single_for_cpu ia64_mv.dma_sync_single_for_cpu -# define platform_dma_sync_sg_for_cpu ia64_mv.dma_sync_sg_for_cpu -# define platform_dma_sync_single_for_device ia64_mv.dma_sync_single_for_device -# define platform_dma_sync_sg_for_device ia64_mv.dma_sync_sg_for_device -# define platform_dma_mapping_error ia64_mv.dma_mapping_error -# define platform_dma_supported ia64_mv.dma_supported # define platform_dma_get_required_mask ia64_mv.dma_get_required_mask +# define platform_dma_get_ops ia64_mv.dma_get_ops # define platform_irq_to_vector ia64_mv.irq_to_vector # define platform_local_vector_to_irq ia64_mv.local_vector_to_irq # define platform_pci_get_legacy_mem ia64_mv.pci_get_legacy_mem @@ -203,19 +173,8 @@ struct ia64_machine_vector { ia64_mv_global_tlb_purge_t *global_tlb_purge; ia64_mv_tlb_migrate_finish_t *tlb_migrate_finish; ia64_mv_dma_init *dma_init; - ia64_mv_dma_alloc_coherent *dma_alloc_coherent; - ia64_mv_dma_free_coherent *dma_free_coherent; - ia64_mv_dma_map_single_attrs *dma_map_single_attrs; - ia64_mv_dma_unmap_single_attrs *dma_unmap_single_attrs; - ia64_mv_dma_map_sg_attrs *dma_map_sg_attrs; - ia64_mv_dma_unmap_sg_attrs *dma_unmap_sg_attrs; - ia64_mv_dma_sync_single_for_cpu *dma_sync_single_for_cpu; - ia64_mv_dma_sync_sg_for_cpu *dma_sync_sg_for_cpu; - ia64_mv_dma_sync_single_for_device *dma_sync_single_for_device; - ia64_mv_dma_sync_sg_for_device *dma_sync_sg_for_device; - ia64_mv_dma_mapping_error *dma_mapping_error; - ia64_mv_dma_supported *dma_supported; ia64_mv_dma_get_required_mask *dma_get_required_mask; + ia64_mv_dma_get_ops *dma_get_ops; ia64_mv_irq_to_vector *irq_to_vector; ia64_mv_local_vector_to_irq *local_vector_to_irq; ia64_mv_pci_get_legacy_mem_t *pci_get_legacy_mem; @@ -254,19 +213,8 @@ struct ia64_machine_vector { platform_global_tlb_purge, \ platform_tlb_migrate_finish, \ platform_dma_init, \ - platform_dma_alloc_coherent, \ - platform_dma_free_coherent, \ - platform_dma_map_single_attrs, \ - platform_dma_unmap_single_attrs, \ - platform_dma_map_sg_attrs, \ - platform_dma_unmap_sg_attrs, \ - platform_dma_sync_single_for_cpu, \ - platform_dma_sync_sg_for_cpu, \ - platform_dma_sync_single_for_device, \ - platform_dma_sync_sg_for_device, \ - platform_dma_mapping_error, \ - platform_dma_supported, \ platform_dma_get_required_mask, \ + platform_dma_get_ops, \ platform_irq_to_vector, \ platform_local_vector_to_irq, \ platform_pci_get_legacy_mem, \ @@ -302,6 +250,9 @@ extern void machvec_init_from_cmdline(const char *cmdline); # error Unknown configuration. Update arch/ia64/include/asm/machvec.h. # endif /* CONFIG_IA64_GENERIC */ +extern void swiotlb_dma_init(void); +extern struct dma_map_ops *dma_get_ops(struct device *); + /* * Define default versions so we can extend machvec for new platforms without having * to update the machvec files for all existing platforms. @@ -332,43 +283,10 @@ extern void machvec_init_from_cmdline(const char *cmdline); # define platform_kernel_launch_event machvec_noop #endif #ifndef platform_dma_init -# define platform_dma_init swiotlb_init -#endif -#ifndef platform_dma_alloc_coherent -# define platform_dma_alloc_coherent swiotlb_alloc_coherent -#endif -#ifndef platform_dma_free_coherent -# define platform_dma_free_coherent swiotlb_free_coherent -#endif -#ifndef platform_dma_map_single_attrs -# define platform_dma_map_single_attrs swiotlb_map_single_attrs -#endif -#ifndef platform_dma_unmap_single_attrs -# define platform_dma_unmap_single_attrs swiotlb_unmap_single_attrs -#endif -#ifndef platform_dma_map_sg_attrs -# define platform_dma_map_sg_attrs swiotlb_map_sg_attrs -#endif -#ifndef platform_dma_unmap_sg_attrs -# define platform_dma_unmap_sg_attrs swiotlb_unmap_sg_attrs -#endif -#ifndef platform_dma_sync_single_for_cpu -# define platform_dma_sync_single_for_cpu swiotlb_sync_single_for_cpu -#endif -#ifndef platform_dma_sync_sg_for_cpu -# define platform_dma_sync_sg_for_cpu swiotlb_sync_sg_for_cpu -#endif -#ifndef platform_dma_sync_single_for_device -# define platform_dma_sync_single_for_device swiotlb_sync_single_for_device -#endif -#ifndef platform_dma_sync_sg_for_device -# define platform_dma_sync_sg_for_device swiotlb_sync_sg_for_device -#endif -#ifndef platform_dma_mapping_error -# define platform_dma_mapping_error swiotlb_dma_mapping_error +# define platform_dma_init swiotlb_dma_init #endif -#ifndef platform_dma_supported -# define platform_dma_supported swiotlb_dma_supported +#ifndef platform_dma_get_ops +# define platform_dma_get_ops dma_get_ops #endif #ifndef platform_dma_get_required_mask # define platform_dma_get_required_mask ia64_dma_get_required_mask diff --git a/arch/ia64/include/asm/machvec_dig_vtd.h b/arch/ia64/include/asm/machvec_dig_vtd.h index 3400b56..6ab1de5 100644 --- a/arch/ia64/include/asm/machvec_dig_vtd.h +++ b/arch/ia64/include/asm/machvec_dig_vtd.h @@ -2,14 +2,6 @@ #define _ASM_IA64_MACHVEC_DIG_VTD_h extern ia64_mv_setup_t dig_setup; -extern ia64_mv_dma_alloc_coherent vtd_alloc_coherent; -extern ia64_mv_dma_free_coherent vtd_free_coherent; -extern ia64_mv_dma_map_single_attrs vtd_map_single_attrs; -extern ia64_mv_dma_unmap_single_attrs vtd_unmap_single_attrs; -extern ia64_mv_dma_map_sg_attrs vtd_map_sg_attrs; -extern ia64_mv_dma_unmap_sg_attrs vtd_unmap_sg_attrs; -extern ia64_mv_dma_supported iommu_dma_supported; -extern ia64_mv_dma_mapping_error vtd_dma_mapping_error; extern ia64_mv_dma_init pci_iommu_alloc; /* @@ -22,17 +14,5 @@ extern ia64_mv_dma_init pci_iommu_alloc; #define platform_name "dig_vtd" #define platform_setup dig_setup #define platform_dma_init pci_iommu_alloc -#define platform_dma_alloc_coherent vtd_alloc_coherent -#define platform_dma_free_coherent vtd_free_coherent -#define platform_dma_map_single_attrs vtd_map_single_attrs -#define platform_dma_unmap_single_attrs vtd_unmap_single_attrs -#define platform_dma_map_sg_attrs vtd_map_sg_attrs -#define platform_dma_unmap_sg_attrs vtd_unmap_sg_attrs -#define platform_dma_sync_single_for_cpu machvec_dma_sync_single -#define platform_dma_sync_sg_for_cpu machvec_dma_sync_sg -#define platform_dma_sync_single_for_device machvec_dma_sync_single -#define platform_dma_sync_sg_for_device machvec_dma_sync_sg -#define platform_dma_supported iommu_dma_supported -#define platform_dma_mapping_error vtd_dma_mapping_error #endif /* _ASM_IA64_MACHVEC_DIG_VTD_h */ diff --git a/arch/ia64/include/asm/machvec_hpzx1.h b/arch/ia64/include/asm/machvec_hpzx1.h index 2f57f51..3bd83d7 100644 --- a/arch/ia64/include/asm/machvec_hpzx1.h +++ b/arch/ia64/include/asm/machvec_hpzx1.h @@ -2,14 +2,7 @@ #define _ASM_IA64_MACHVEC_HPZX1_h extern ia64_mv_setup_t dig_setup; -extern ia64_mv_dma_alloc_coherent sba_alloc_coherent; -extern ia64_mv_dma_free_coherent sba_free_coherent; -extern ia64_mv_dma_map_single_attrs sba_map_single_attrs; -extern ia64_mv_dma_unmap_single_attrs sba_unmap_single_attrs; -extern ia64_mv_dma_map_sg_attrs sba_map_sg_attrs; -extern ia64_mv_dma_unmap_sg_attrs sba_unmap_sg_attrs; -extern ia64_mv_dma_supported sba_dma_supported; -extern ia64_mv_dma_mapping_error sba_dma_mapping_error; +extern ia64_mv_dma_init sba_dma_init; /* * This stuff has dual use! @@ -20,18 +13,6 @@ extern ia64_mv_dma_mapping_error sba_dma_mapping_error; */ #define platform_name "hpzx1" #define platform_setup dig_setup -#define platform_dma_init machvec_noop -#define platform_dma_alloc_coherent sba_alloc_coherent -#define platform_dma_free_coherent sba_free_coherent -#define platform_dma_map_single_attrs sba_map_single_attrs -#define platform_dma_unmap_single_attrs sba_unmap_single_attrs -#define platform_dma_map_sg_attrs sba_map_sg_attrs -#define platform_dma_unmap_sg_attrs sba_unmap_sg_attrs -#define platform_dma_sync_single_for_cpu machvec_dma_sync_single -#define platform_dma_sync_sg_for_cpu machvec_dma_sync_sg -#define platform_dma_sync_single_for_device machvec_dma_sync_single -#define platform_dma_sync_sg_for_device machvec_dma_sync_sg -#define platform_dma_supported sba_dma_supported -#define platform_dma_mapping_error sba_dma_mapping_error +#define platform_dma_init sba_dma_init #endif /* _ASM_IA64_MACHVEC_HPZX1_h */ diff --git a/arch/ia64/include/asm/machvec_hpzx1_swiotlb.h b/arch/ia64/include/asm/machvec_hpzx1_swiotlb.h index a842cdd..1091ac3 100644 --- a/arch/ia64/include/asm/machvec_hpzx1_swiotlb.h +++ b/arch/ia64/include/asm/machvec_hpzx1_swiotlb.h @@ -2,18 +2,7 @@ #define _ASM_IA64_MACHVEC_HPZX1_SWIOTLB_h extern ia64_mv_setup_t dig_setup; -extern ia64_mv_dma_alloc_coherent hwsw_alloc_coherent; -extern ia64_mv_dma_free_coherent hwsw_free_coherent; -extern ia64_mv_dma_map_single_attrs hwsw_map_single_attrs; -extern ia64_mv_dma_unmap_single_attrs hwsw_unmap_single_attrs; -extern ia64_mv_dma_map_sg_attrs hwsw_map_sg_attrs; -extern ia64_mv_dma_unmap_sg_attrs hwsw_unmap_sg_attrs; -extern ia64_mv_dma_supported hwsw_dma_supported; -extern ia64_mv_dma_mapping_error hwsw_dma_mapping_error; -extern ia64_mv_dma_sync_single_for_cpu hwsw_sync_single_for_cpu; -extern ia64_mv_dma_sync_sg_for_cpu hwsw_sync_sg_for_cpu; -extern ia64_mv_dma_sync_single_for_device hwsw_sync_single_for_device; -extern ia64_mv_dma_sync_sg_for_device hwsw_sync_sg_for_device; +extern ia64_mv_dma_get_ops hwsw_dma_get_ops; /* * This stuff has dual use! @@ -23,20 +12,8 @@ extern ia64_mv_dma_sync_sg_for_device hwsw_sync_sg_for_device; * the macros are used directly. */ #define platform_name "hpzx1_swiotlb" - #define platform_setup dig_setup #define platform_dma_init machvec_noop -#define platform_dma_alloc_coherent hwsw_alloc_coherent -#define platform_dma_free_coherent hwsw_free_coherent -#define platform_dma_map_single_attrs hwsw_map_single_attrs -#define platform_dma_unmap_single_attrs hwsw_unmap_single_attrs -#define platform_dma_map_sg_attrs hwsw_map_sg_attrs -#define platform_dma_unmap_sg_attrs hwsw_unmap_sg_attrs -#define platform_dma_supported hwsw_dma_supported -#define platform_dma_mapping_error hwsw_dma_mapping_error -#define platform_dma_sync_single_for_cpu hwsw_sync_single_for_cpu -#define platform_dma_sync_sg_for_cpu hwsw_sync_sg_for_cpu -#define platform_dma_sync_single_for_device hwsw_sync_single_for_device -#define platform_dma_sync_sg_for_device hwsw_sync_sg_for_device +#define platform_dma_get_ops hwsw_dma_get_ops #endif /* _ASM_IA64_MACHVEC_HPZX1_SWIOTLB_h */ diff --git a/arch/ia64/include/asm/machvec_sn2.h b/arch/ia64/include/asm/machvec_sn2.h index f1a6e0d..f061a30 100644 --- a/arch/ia64/include/asm/machvec_sn2.h +++ b/arch/ia64/include/asm/machvec_sn2.h @@ -55,19 +55,8 @@ extern ia64_mv_readb_t __sn_readb_relaxed; extern ia64_mv_readw_t __sn_readw_relaxed; extern ia64_mv_readl_t __sn_readl_relaxed; extern ia64_mv_readq_t __sn_readq_relaxed; -extern ia64_mv_dma_alloc_coherent sn_dma_alloc_coherent; -extern ia64_mv_dma_free_coherent sn_dma_free_coherent; -extern ia64_mv_dma_map_single_attrs sn_dma_map_single_attrs; -extern ia64_mv_dma_unmap_single_attrs sn_dma_unmap_single_attrs; -extern ia64_mv_dma_map_sg_attrs sn_dma_map_sg_attrs; -extern ia64_mv_dma_unmap_sg_attrs sn_dma_unmap_sg_attrs; -extern ia64_mv_dma_sync_single_for_cpu sn_dma_sync_single_for_cpu; -extern ia64_mv_dma_sync_sg_for_cpu sn_dma_sync_sg_for_cpu; -extern ia64_mv_dma_sync_single_for_device sn_dma_sync_single_for_device; -extern ia64_mv_dma_sync_sg_for_device sn_dma_sync_sg_for_device; -extern ia64_mv_dma_mapping_error sn_dma_mapping_error; -extern ia64_mv_dma_supported sn_dma_supported; extern ia64_mv_dma_get_required_mask sn_dma_get_required_mask; +extern ia64_mv_dma_init sn_dma_init; extern ia64_mv_migrate_t sn_migrate; extern ia64_mv_kernel_launch_event_t sn_kernel_launch_event; extern ia64_mv_setup_msi_irq_t sn_setup_msi_irq; @@ -111,20 +100,8 @@ extern ia64_mv_pci_fixup_bus_t sn_pci_fixup_bus; #define platform_pci_get_legacy_mem sn_pci_get_legacy_mem #define platform_pci_legacy_read sn_pci_legacy_read #define platform_pci_legacy_write sn_pci_legacy_write -#define platform_dma_init machvec_noop -#define platform_dma_alloc_coherent sn_dma_alloc_coherent -#define platform_dma_free_coherent sn_dma_free_coherent -#define platform_dma_map_single_attrs sn_dma_map_single_attrs -#define platform_dma_unmap_single_attrs sn_dma_unmap_single_attrs -#define platform_dma_map_sg_attrs sn_dma_map_sg_attrs -#define platform_dma_unmap_sg_attrs sn_dma_unmap_sg_attrs -#define platform_dma_sync_single_for_cpu sn_dma_sync_single_for_cpu -#define platform_dma_sync_sg_for_cpu sn_dma_sync_sg_for_cpu -#define platform_dma_sync_single_for_device sn_dma_sync_single_for_device -#define platform_dma_sync_sg_for_device sn_dma_sync_sg_for_device -#define platform_dma_mapping_error sn_dma_mapping_error -#define platform_dma_supported sn_dma_supported #define platform_dma_get_required_mask sn_dma_get_required_mask +#define platform_dma_init sn_dma_init #define platform_migrate sn_migrate #define platform_kernel_launch_event sn_kernel_launch_event #ifdef CONFIG_PCI_MSI diff --git a/arch/ia64/include/asm/percpu.h b/arch/ia64/include/asm/percpu.h index 77f30b6..30cf465 100644 --- a/arch/ia64/include/asm/percpu.h +++ b/arch/ia64/include/asm/percpu.h @@ -27,12 +27,12 @@ extern void *per_cpu_init(void); #else /* ! SMP */ -#define PER_CPU_ATTRIBUTES __attribute__((__section__(".data.percpu"))) - #define per_cpu_init() (__phys_per_cpu_start) #endif /* SMP */ +#define PER_CPU_BASE_SECTION ".data.percpu" + /* * Be extremely careful when taking the address of this variable! Due to virtual * remapping, it is different from the canonical address returned by __get_cpu_var(var)! diff --git a/arch/ia64/include/asm/swab.h b/arch/ia64/include/asm/swab.h index 6aa58b6..c89a8cb 100644 --- a/arch/ia64/include/asm/swab.h +++ b/arch/ia64/include/asm/swab.h @@ -6,7 +6,7 @@ * David Mosberger-Tang , Hewlett-Packard Co. */ -#include +#include #include #include diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 32f3af1..3193f44 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -84,7 +84,7 @@ void build_cpu_to_node_map(void); .child = NULL, \ .groups = NULL, \ .min_interval = 8, \ - .max_interval = 8*(min(num_online_cpus(), 32)), \ + .max_interval = 8*(min(num_online_cpus(), 32U)), \ .busy_factor = 64, \ .imbalance_pct = 125, \ .cache_nice_tries = 2, \ diff --git a/arch/ia64/include/asm/uv/uv.h b/arch/ia64/include/asm/uv/uv.h new file mode 100644 index 0000000..61b5bdf --- /dev/null +++ b/arch/ia64/include/asm/uv/uv.h @@ -0,0 +1,13 @@ +#ifndef _ASM_IA64_UV_UV_H +#define _ASM_IA64_UV_UV_H + +#include +#include + +static inline int is_uv_system(void) +{ + /* temporary support for running on hardware simulator */ + return IS_MEDUSA() || ia64_platform_is("uv"); +} + +#endif /* _ASM_IA64_UV_UV_H */ diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index c381ea9..dc62df0 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -2,12 +2,16 @@ # Makefile for the linux kernel. # +ifdef CONFIG_DYNAMIC_FTRACE +CFLAGS_REMOVE_ftrace.o = -pg +endif + extra-y := head.o init_task.o vmlinux.lds obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \ irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o \ salinfo.o setup.o signal.o sys_ia64.o time.o traps.o unaligned.o \ - unwind.o mca.o mca_asm.o topology.o + unwind.o mca.o mca_asm.o topology.o dma-mapping.o obj-$(CONFIG_IA64_BRL_EMU) += brl_emu.o obj-$(CONFIG_IA64_GENERIC) += acpi-ext.o @@ -28,6 +32,7 @@ obj-$(CONFIG_IA64_CYCLONE) += cyclone.o obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR) += uncached.o @@ -43,9 +48,7 @@ ifneq ($(CONFIG_IA64_ESI),) obj-y += esi_stub.o # must be in kernel proper endif obj-$(CONFIG_DMAR) += pci-dma.o -ifeq ($(CONFIG_DMAR), y) obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o -endif # The gate DSO image is built using a special linker script. targets += gate.so gate-syms.o diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index d541671..bdef2ce 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -199,6 +199,10 @@ char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size) return __va(phys_addr); } +void __init __acpi_unmap_table(char *map, unsigned long size) +{ +} + /* -------------------------------------------------------------------------- Boot-time Table Parsing -------------------------------------------------------------------------- */ diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c new file mode 100644 index 0000000..086a2ae --- /dev/null +++ b/arch/ia64/kernel/dma-mapping.c @@ -0,0 +1,13 @@ +#include + +/* Set this to 1 if there is a HW IOMMU in the system */ +int iommu_detected __read_mostly; + +struct dma_map_ops *dma_ops; +EXPORT_SYMBOL(dma_ops); + +struct dma_map_ops *dma_get_ops(struct device *dev) +{ + return dma_ops; +} +EXPORT_SYMBOL(dma_get_ops); diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index e5341e2..7e3382b 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -47,6 +47,7 @@ #include #include #include +#include #include "minstate.h" @@ -1404,6 +1405,105 @@ GLOBAL_ENTRY(unw_init_running) br.ret.sptk.many rp END(unw_init_running) +#ifdef CONFIG_FUNCTION_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE +GLOBAL_ENTRY(_mcount) + br ftrace_stub +END(_mcount) + +.here: + br.ret.sptk.many b0 + +GLOBAL_ENTRY(ftrace_caller) + alloc out0 = ar.pfs, 8, 0, 4, 0 + mov out3 = r0 + ;; + mov out2 = b0 + add r3 = 0x20, r3 + mov out1 = r1; + br.call.sptk.many b0 = ftrace_patch_gp + //this might be called from module, so we must patch gp +ftrace_patch_gp: + movl gp=__gp + mov b0 = r3 + ;; +.global ftrace_call; +ftrace_call: +{ + .mlx + nop.m 0x0 + movl r3 = .here;; +} + alloc loc0 = ar.pfs, 4, 4, 2, 0 + ;; + mov loc1 = b0 + mov out0 = b0 + mov loc2 = r8 + mov loc3 = r15 + ;; + adds out0 = -MCOUNT_INSN_SIZE, out0 + mov out1 = in2 + mov b6 = r3 + + br.call.sptk.many b0 = b6 + ;; + mov ar.pfs = loc0 + mov b0 = loc1 + mov r8 = loc2 + mov r15 = loc3 + br ftrace_stub + ;; +END(ftrace_caller) + +#else +GLOBAL_ENTRY(_mcount) + movl r2 = ftrace_stub + movl r3 = ftrace_trace_function;; + ld8 r3 = [r3];; + ld8 r3 = [r3];; + cmp.eq p7,p0 = r2, r3 +(p7) br.sptk.many ftrace_stub + ;; + + alloc loc0 = ar.pfs, 4, 4, 2, 0 + ;; + mov loc1 = b0 + mov out0 = b0 + mov loc2 = r8 + mov loc3 = r15 + ;; + adds out0 = -MCOUNT_INSN_SIZE, out0 + mov out1 = in2 + mov b6 = r3 + + br.call.sptk.many b0 = b6 + ;; + mov ar.pfs = loc0 + mov b0 = loc1 + mov r8 = loc2 + mov r15 = loc3 + br ftrace_stub + ;; +END(_mcount) +#endif + +GLOBAL_ENTRY(ftrace_stub) + mov r3 = b0 + movl r2 = _mcount_ret_helper + ;; + mov b6 = r2 + mov b7 = r3 + br.ret.sptk.many b6 + +_mcount_ret_helper: + mov b0 = r42 + mov r1 = r41 + mov ar.pfs = r40 + br b7 +END(ftrace_stub) + +#endif /* CONFIG_FUNCTION_TRACER */ + .rodata .align 8 .globl sys_call_table diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c new file mode 100644 index 0000000..7fc8c96 --- /dev/null +++ b/arch/ia64/kernel/ftrace.c @@ -0,0 +1,206 @@ +/* + * Dynamic function tracing support. + * + * Copyright (C) 2008 Shaohua Li + * + * For licencing details, see COPYING. + * + * Defines low-level handling of mcount calls when the kernel + * is compiled with the -pg flag. When using dynamic ftrace, the + * mcount call-sites get patched lazily with NOP till they are + * enabled. All code mutation routines here take effect atomically. + */ + +#include +#include + +#include +#include + +/* In IA64, each function will be added below two bundles with -pg option */ +static unsigned char __attribute__((aligned(8))) +ftrace_orig_code[MCOUNT_INSN_SIZE] = { + 0x02, 0x40, 0x31, 0x10, 0x80, 0x05, /* alloc r40=ar.pfs,12,8,0 */ + 0xb0, 0x02, 0x00, 0x00, 0x42, 0x40, /* mov r43=r0;; */ + 0x05, 0x00, 0xc4, 0x00, /* mov r42=b0 */ + 0x11, 0x48, 0x01, 0x02, 0x00, 0x21, /* mov r41=r1 */ + 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, /* nop.i 0x0 */ + 0x08, 0x00, 0x00, 0x50 /* br.call.sptk.many b0 = _mcount;; */ +}; + +struct ftrace_orig_insn { + u64 dummy1, dummy2, dummy3; + u64 dummy4:64-41+13; + u64 imm20:20; + u64 dummy5:3; + u64 sign:1; + u64 dummy6:4; +}; + +/* mcount stub will be converted below for nop */ +static unsigned char ftrace_nop_code[MCOUNT_INSN_SIZE] = { + 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MII] nop.m 0x0 */ + 0x30, 0x00, 0x00, 0x60, 0x00, 0x00, /* mov r3=ip */ + 0x00, 0x00, 0x04, 0x00, /* nop.i 0x0 */ + 0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0x0 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* nop.x 0x0;; */ + 0x00, 0x00, 0x04, 0x00 +}; + +static unsigned char *ftrace_nop_replace(void) +{ + return ftrace_nop_code; +} + +/* + * mcount stub will be converted below for call + * Note: Just the last instruction is changed against nop + * */ +static unsigned char __attribute__((aligned(8))) +ftrace_call_code[MCOUNT_INSN_SIZE] = { + 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MII] nop.m 0x0 */ + 0x30, 0x00, 0x00, 0x60, 0x00, 0x00, /* mov r3=ip */ + 0x00, 0x00, 0x04, 0x00, /* nop.i 0x0 */ + 0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0x0 */ + 0xff, 0xff, 0xff, 0xff, 0x7f, 0x00, /* brl.many .;;*/ + 0xf8, 0xff, 0xff, 0xc8 +}; + +struct ftrace_call_insn { + u64 dummy1, dummy2; + u64 dummy3:48; + u64 imm39_l:16; + u64 imm39_h:23; + u64 dummy4:13; + u64 imm20:20; + u64 dummy5:3; + u64 i:1; + u64 dummy6:4; +}; + +static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + struct ftrace_call_insn *code = (void *)ftrace_call_code; + unsigned long offset = addr - (ip + 0x10); + + code->imm39_l = offset >> 24; + code->imm39_h = offset >> 40; + code->imm20 = offset >> 4; + code->i = offset >> 63; + return ftrace_call_code; +} + +static int +ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code, int do_check) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + + /* + * Note: Due to modules and __init, code can + * disappear and change, we need to protect against faulting + * as well as code changing. We do this by using the + * probe_kernel_* functions. + * + * No real locking needed, this code is run through + * kstop_machine, or before SMP starts. + */ + + if (!do_check) + goto skip_check; + + /* read the text we want to modify */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ + if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + +skip_check: + /* replace the text with the new text */ + if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE)) + return -EPERM; + flush_icache_range(ip, ip + MCOUNT_INSN_SIZE); + + return 0; +} + +static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE]; + unsigned long ip = rec->ip; + + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + if (rec->flags & FTRACE_FL_CONVERTED) { + struct ftrace_call_insn *call_insn, *tmp_call; + + call_insn = (void *)ftrace_call_code; + tmp_call = (void *)replaced; + call_insn->imm39_l = tmp_call->imm39_l; + call_insn->imm39_h = tmp_call->imm39_h; + call_insn->imm20 = tmp_call->imm20; + call_insn->i = tmp_call->i; + if (memcmp(replaced, ftrace_call_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + return 0; + } else { + struct ftrace_orig_insn *call_insn, *tmp_call; + + call_insn = (void *)ftrace_orig_code; + tmp_call = (void *)replaced; + call_insn->sign = tmp_call->sign; + call_insn->imm20 = tmp_call->imm20; + if (memcmp(replaced, ftrace_orig_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + return 0; + } +} + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + int ret; + char *new; + + ret = ftrace_make_nop_check(rec, addr); + if (ret) + return ret; + new = ftrace_nop_replace(); + return ftrace_modify_code(rec->ip, NULL, new, 0); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + unsigned char *old, *new; + + old= ftrace_nop_replace(); + new = ftrace_call_replace(ip, addr); + return ftrace_modify_code(ip, old, new, 1); +} + +/* in IA64, _mcount can't directly call ftrace_stub. Only jump is ok */ +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip; + unsigned long addr = ((struct fnptr *)ftrace_call)->ip; + + if (func == ftrace_stub) + return 0; + ip = ((struct fnptr *)func)->ip; + + ia64_patch_imm64(addr + 2, ip); + + flush_icache_range(addr, addr + 16); + return 0; +} + +/* run from kstop_machine */ +int __init ftrace_dyn_arch_init(void *data) +{ + *(unsigned long *)data = 0; + + return 0; +} diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 6da1f20..2d31186 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -112,3 +112,9 @@ EXPORT_SYMBOL_GPL(esi_call_phys); #endif extern char ia64_ivt[]; EXPORT_SYMBOL(ia64_ivt); + +#include +#ifdef CONFIG_FUNCTION_TRACER +/* mcount is defined in assembly */ +EXPORT_SYMBOL(_mcount); +#endif diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index e131250..166e0d8 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -880,7 +880,7 @@ iosapic_unregister_intr (unsigned int gsi) if (iosapic_intr_info[irq].count == 0) { #ifdef CONFIG_SMP /* Clear affinity */ - cpus_setall(idesc->affinity); + cpumask_setall(idesc->affinity); #endif /* Clear the interrupt information */ iosapic_intr_info[irq].dest = 0; diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index a58f64c..7429752 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -80,7 +80,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%10u ", kstat_irqs(i)); #else for_each_online_cpu(j) { - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); } #endif seq_printf(p, " %14s", irq_desc[i].chip->name); @@ -103,7 +103,7 @@ static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 }; void set_irq_affinity_info (unsigned int irq, int hwid, int redir) { if (irq < NR_IRQS) { - cpumask_copy(&irq_desc[irq].affinity, + cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu_logical_id(hwid))); irq_redir[irq] = (char) (redir & 0xff); } @@ -148,7 +148,7 @@ static void migrate_irqs(void) if (desc->status == IRQ_PER_CPU) continue; - if (cpumask_any_and(&irq_desc[irq].affinity, cpu_online_mask) + if (cpumask_any_and(irq_desc[irq].affinity, cpu_online_mask) >= nr_cpu_ids) { /* * Save it for phase 2 processing diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 28d3d48..927ad02 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -493,11 +493,13 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs) saved_tpr = ia64_getreg(_IA64_REG_CR_TPR); ia64_srlz_d(); while (vector != IA64_SPURIOUS_INT_VECTOR) { + struct irq_desc *desc = irq_to_desc(vector); + if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) { smp_local_flush_tlb(); - kstat_this_cpu.irqs[vector]++; + kstat_incr_irqs_this_cpu(vector, desc); } else if (unlikely(IS_RESCHEDULE(vector))) - kstat_this_cpu.irqs[vector]++; + kstat_incr_irqs_this_cpu(vector, desc); else { int irq = local_vector_to_irq(vector); @@ -551,11 +553,13 @@ void ia64_process_pending_intr(void) * Perform normal interrupt style processing */ while (vector != IA64_SPURIOUS_INT_VECTOR) { + struct irq_desc *desc = irq_to_desc(vector); + if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) { smp_local_flush_tlb(); - kstat_this_cpu.irqs[vector]++; + kstat_incr_irqs_this_cpu(vector, desc); } else if (unlikely(IS_RESCHEDULE(vector))) - kstat_this_cpu.irqs[vector]++; + kstat_incr_irqs_this_cpu(vector, desc); else { struct pt_regs *old_regs = set_irq_regs(NULL); int irq = local_vector_to_irq(vector); diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 9adac44..f90be51 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -870,7 +870,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) return 1; ss_probe: -#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER) +#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PM) if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ ia64_psr(regs)->ri = p->ainsn.slot; diff --git a/arch/ia64/kernel/machvec.c b/arch/ia64/kernel/machvec.c index 7ccb228..d41a40e 100644 --- a/arch/ia64/kernel/machvec.c +++ b/arch/ia64/kernel/machvec.c @@ -1,5 +1,5 @@ #include - +#include #include #include @@ -75,14 +75,16 @@ machvec_timer_interrupt (int irq, void *dev_id) EXPORT_SYMBOL(machvec_timer_interrupt); void -machvec_dma_sync_single (struct device *hwdev, dma_addr_t dma_handle, size_t size, int dir) +machvec_dma_sync_single(struct device *hwdev, dma_addr_t dma_handle, size_t size, + enum dma_data_direction dir) { mb(); } EXPORT_SYMBOL(machvec_dma_sync_single); void -machvec_dma_sync_sg (struct device *hwdev, struct scatterlist *sg, int n, int dir) +machvec_dma_sync_sg(struct device *hwdev, struct scatterlist *sg, int n, + enum dma_data_direction dir) { mb(); } diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c index 8903393..dcb6b7c 100644 --- a/arch/ia64/kernel/msi_ia64.c +++ b/arch/ia64/kernel/msi_ia64.c @@ -75,7 +75,7 @@ static void ia64_set_msi_irq_affinity(unsigned int irq, msg.data = data; write_msi_msg(irq, &msg); - irq_desc[irq].affinity = cpumask_of_cpu(cpu); + cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu)); } #endif /* CONFIG_SMP */ @@ -187,7 +187,7 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) msg.address_lo |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu)); dmar_msi_write(irq, &msg); - irq_desc[irq].affinity = *mask; + cpumask_copy(irq_desc[irq].affinity, mask); } #endif /* CONFIG_SMP */ diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c index d0ada06..e4cb443 100644 --- a/arch/ia64/kernel/pci-dma.c +++ b/arch/ia64/kernel/pci-dma.c @@ -32,9 +32,6 @@ int force_iommu __read_mostly = 1; int force_iommu __read_mostly; #endif -/* Set this to 1 if there is a HW IOMMU in the system */ -int iommu_detected __read_mostly; - /* Dummy device used for NULL arguments (normally ISA). Better would be probably a smaller DMA mask, but this is bug-to-bug compatible to i386. */ @@ -44,18 +41,7 @@ struct device fallback_dev = { .dma_mask = &fallback_dev.coherent_dma_mask, }; -void __init pci_iommu_alloc(void) -{ - /* - * The order of these functions is important for - * fall-back/fail-over reasons - */ - detect_intel_iommu(); - -#ifdef CONFIG_SWIOTLB - pci_swiotlb_init(); -#endif -} +extern struct dma_map_ops intel_dma_ops; static int __init pci_iommu_init(void) { @@ -79,15 +65,12 @@ iommu_dma_init(void) return; } -struct dma_mapping_ops *dma_ops; -EXPORT_SYMBOL(dma_ops); - int iommu_dma_supported(struct device *dev, u64 mask) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); - if (ops->dma_supported_op) - return ops->dma_supported_op(dev, mask); + if (ops->dma_supported) + return ops->dma_supported(dev, mask); /* Copied from i386. Doesn't make much sense, because it will only work for pci_alloc_coherent. @@ -116,4 +99,25 @@ int iommu_dma_supported(struct device *dev, u64 mask) } EXPORT_SYMBOL(iommu_dma_supported); +void __init pci_iommu_alloc(void) +{ + dma_ops = &intel_dma_ops; + + dma_ops->sync_single_for_cpu = machvec_dma_sync_single; + dma_ops->sync_sg_for_cpu = machvec_dma_sync_sg; + dma_ops->sync_single_for_device = machvec_dma_sync_single; + dma_ops->sync_sg_for_device = machvec_dma_sync_sg; + dma_ops->dma_supported = iommu_dma_supported; + + /* + * The order of these functions is important for + * fall-back/fail-over reasons + */ + detect_intel_iommu(); + +#ifdef CONFIG_SWIOTLB + pci_swiotlb_init(); +#endif +} + #endif diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c index 16c5051..573f02c 100644 --- a/arch/ia64/kernel/pci-swiotlb.c +++ b/arch/ia64/kernel/pci-swiotlb.c @@ -13,23 +13,37 @@ int swiotlb __read_mostly; EXPORT_SYMBOL(swiotlb); -struct dma_mapping_ops swiotlb_dma_ops = { - .mapping_error = swiotlb_dma_mapping_error, - .alloc_coherent = swiotlb_alloc_coherent, +static void *ia64_swiotlb_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + if (dev->coherent_dma_mask != DMA_64BIT_MASK) + gfp |= GFP_DMA; + return swiotlb_alloc_coherent(dev, size, dma_handle, gfp); +} + +struct dma_map_ops swiotlb_dma_ops = { + .alloc_coherent = ia64_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, - .map_single = swiotlb_map_single, - .unmap_single = swiotlb_unmap_single, + .map_page = swiotlb_map_page, + .unmap_page = swiotlb_unmap_page, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, .sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu, .sync_single_range_for_device = swiotlb_sync_single_range_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, - .map_sg = swiotlb_map_sg, - .unmap_sg = swiotlb_unmap_sg, - .dma_supported_op = swiotlb_dma_supported, + .dma_supported = swiotlb_dma_supported, + .mapping_error = swiotlb_dma_mapping_error, }; +void __init swiotlb_dma_init(void) +{ + dma_ops = &swiotlb_dma_ops; + swiotlb_init(); +} + void __init pci_swiotlb_init(void) { if (!iommu_detected) { diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index 10a7d47..3765efc 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -213,16 +213,9 @@ SECTIONS { *(.data.cacheline_aligned) } /* Per-cpu data: */ - percpu : { } :percpu . = ALIGN(PERCPU_PAGE_SIZE); - __phys_per_cpu_start = .; - .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET) - { - __per_cpu_start = .; - *(.data.percpu) - *(.data.percpu.shared_aligned) - __per_cpu_end = .; - } + PERCPU_VADDR(PERCPU_ADDR, :percpu) + __phys_per_cpu_start = __per_cpu_load; . = __phys_per_cpu_start + PERCPU_PAGE_SIZE; /* ensure percpu data fits * into percpu page size */ diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c index ca553b0..81e4289 100644 --- a/arch/ia64/sn/kernel/msi_sn.c +++ b/arch/ia64/sn/kernel/msi_sn.c @@ -205,7 +205,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq, msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff); write_msi_msg(irq, &msg); - irq_desc[irq].affinity = *cpu_mask; + cpumask_copy(irq_desc[irq].affinity, cpu_mask); } #endif /* CONFIG_SMP */ diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index 863f501..8c130e8 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -10,7 +10,7 @@ */ #include -#include +#include #include #include #include @@ -31,7 +31,7 @@ * this function. Of course, SN only supports devices that have 32 or more * address bits when using the PMU. */ -int sn_dma_supported(struct device *dev, u64 mask) +static int sn_dma_supported(struct device *dev, u64 mask) { BUG_ON(dev->bus != &pci_bus_type); @@ -39,7 +39,6 @@ int sn_dma_supported(struct device *dev, u64 mask) return 0; return 1; } -EXPORT_SYMBOL(sn_dma_supported); /** * sn_dma_set_mask - set the DMA mask @@ -75,8 +74,8 @@ EXPORT_SYMBOL(sn_dma_set_mask); * queue for a SCSI controller). See Documentation/DMA-API.txt for * more information. */ -void *sn_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t * dma_handle, gfp_t flags) +static void *sn_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t * dma_handle, gfp_t flags) { void *cpuaddr; unsigned long phys_addr; @@ -124,7 +123,6 @@ void *sn_dma_alloc_coherent(struct device *dev, size_t size, return cpuaddr; } -EXPORT_SYMBOL(sn_dma_alloc_coherent); /** * sn_pci_free_coherent - free memory associated with coherent DMAable region @@ -136,8 +134,8 @@ EXPORT_SYMBOL(sn_dma_alloc_coherent); * Frees the memory allocated by dma_alloc_coherent(), potentially unmapping * any associated IOMMU mappings. */ -void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle) +static void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle) { struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); @@ -147,7 +145,6 @@ void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, provider->dma_unmap(pdev, dma_handle, 0); free_pages((unsigned long)cpu_addr, get_order(size)); } -EXPORT_SYMBOL(sn_dma_free_coherent); /** * sn_dma_map_single_attrs - map a single page for DMA @@ -173,10 +170,12 @@ EXPORT_SYMBOL(sn_dma_free_coherent); * TODO: simplify our interface; * figure out how to save dmamap handle so can use two step. */ -dma_addr_t sn_dma_map_single_attrs(struct device *dev, void *cpu_addr, - size_t size, int direction, - struct dma_attrs *attrs) +static dma_addr_t sn_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { + void *cpu_addr = page_address(page) + offset; dma_addr_t dma_addr; unsigned long phys_addr; struct pci_dev *pdev = to_pci_dev(dev); @@ -201,7 +200,6 @@ dma_addr_t sn_dma_map_single_attrs(struct device *dev, void *cpu_addr, } return dma_addr; } -EXPORT_SYMBOL(sn_dma_map_single_attrs); /** * sn_dma_unmap_single_attrs - unamp a DMA mapped page @@ -215,21 +213,20 @@ EXPORT_SYMBOL(sn_dma_map_single_attrs); * by @dma_handle into the coherence domain. On SN, we're always cache * coherent, so we just need to free any ATEs associated with this mapping. */ -void sn_dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr, - size_t size, int direction, - struct dma_attrs *attrs) +static void sn_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); BUG_ON(dev->bus != &pci_bus_type); - provider->dma_unmap(pdev, dma_addr, direction); + provider->dma_unmap(pdev, dma_addr, dir); } -EXPORT_SYMBOL(sn_dma_unmap_single_attrs); /** - * sn_dma_unmap_sg_attrs - unmap a DMA scatterlist + * sn_dma_unmap_sg - unmap a DMA scatterlist * @dev: device to unmap * @sg: scatterlist to unmap * @nhwentries: number of scatterlist entries @@ -238,9 +235,9 @@ EXPORT_SYMBOL(sn_dma_unmap_single_attrs); * * Unmap a set of streaming mode DMA translations. */ -void sn_dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl, - int nhwentries, int direction, - struct dma_attrs *attrs) +static void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nhwentries, enum dma_data_direction dir, + struct dma_attrs *attrs) { int i; struct pci_dev *pdev = to_pci_dev(dev); @@ -250,15 +247,14 @@ void sn_dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl, BUG_ON(dev->bus != &pci_bus_type); for_each_sg(sgl, sg, nhwentries, i) { - provider->dma_unmap(pdev, sg->dma_address, direction); + provider->dma_unmap(pdev, sg->dma_address, dir); sg->dma_address = (dma_addr_t) NULL; sg->dma_length = 0; } } -EXPORT_SYMBOL(sn_dma_unmap_sg_attrs); /** - * sn_dma_map_sg_attrs - map a scatterlist for DMA + * sn_dma_map_sg - map a scatterlist for DMA * @dev: device to map for * @sg: scatterlist to map * @nhwentries: number of entries @@ -272,8 +268,9 @@ EXPORT_SYMBOL(sn_dma_unmap_sg_attrs); * * Maps each entry of @sg for DMA. */ -int sn_dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl, - int nhwentries, int direction, struct dma_attrs *attrs) +static int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, + int nhwentries, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long phys_addr; struct scatterlist *saved_sg = sgl, *sg; @@ -310,8 +307,7 @@ int sn_dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl, * Free any successfully allocated entries. */ if (i > 0) - sn_dma_unmap_sg_attrs(dev, saved_sg, i, - direction, attrs); + sn_dma_unmap_sg(dev, saved_sg, i, dir, attrs); return 0; } @@ -320,41 +316,36 @@ int sn_dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl, return nhwentries; } -EXPORT_SYMBOL(sn_dma_map_sg_attrs); -void sn_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, - size_t size, int direction) +static void sn_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir) { BUG_ON(dev->bus != &pci_bus_type); } -EXPORT_SYMBOL(sn_dma_sync_single_for_cpu); -void sn_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, - size_t size, int direction) +static void sn_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, + size_t size, + enum dma_data_direction dir) { BUG_ON(dev->bus != &pci_bus_type); } -EXPORT_SYMBOL(sn_dma_sync_single_for_device); -void sn_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nelems, int direction) +static void sn_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir) { BUG_ON(dev->bus != &pci_bus_type); } -EXPORT_SYMBOL(sn_dma_sync_sg_for_cpu); -void sn_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nelems, int direction) +static void sn_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir) { BUG_ON(dev->bus != &pci_bus_type); } -EXPORT_SYMBOL(sn_dma_sync_sg_for_device); -int sn_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +static int sn_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } -EXPORT_SYMBOL(sn_dma_mapping_error); u64 sn_dma_get_required_mask(struct device *dev) { @@ -471,3 +462,23 @@ int sn_pci_legacy_write(struct pci_bus *bus, u16 port, u32 val, u8 size) out: return ret; } + +static struct dma_map_ops sn_dma_ops = { + .alloc_coherent = sn_dma_alloc_coherent, + .free_coherent = sn_dma_free_coherent, + .map_page = sn_dma_map_page, + .unmap_page = sn_dma_unmap_page, + .map_sg = sn_dma_map_sg, + .unmap_sg = sn_dma_unmap_sg, + .sync_single_for_cpu = sn_dma_sync_single_for_cpu, + .sync_sg_for_cpu = sn_dma_sync_sg_for_cpu, + .sync_single_for_device = sn_dma_sync_single_for_device, + .sync_sg_for_device = sn_dma_sync_sg_for_device, + .mapping_error = sn_dma_mapping_error, + .dma_supported = sn_dma_supported, +}; + +void sn_dma_init(void) +{ + dma_ops = &sn_dma_ops; +} diff --git a/arch/ia64/sn/pci/pcibr/pcibr_dma.c b/arch/ia64/sn/pci/pcibr/pcibr_dma.c index e626e50..060df4a 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c @@ -135,11 +135,10 @@ pcibr_dmatrans_direct64(struct pcidev_info * info, u64 paddr, if (SN_DMA_ADDRTYPE(dma_flags) == SN_DMA_ADDR_PHYS) pci_addr = IS_PIC_SOFT(pcibus_info) ? PHYS_TO_DMA(paddr) : - PHYS_TO_TIODMA(paddr) | dma_attributes; + PHYS_TO_TIODMA(paddr); else - pci_addr = IS_PIC_SOFT(pcibus_info) ? - paddr : - paddr | dma_attributes; + pci_addr = paddr; + pci_addr |= dma_attributes; /* Handle Bus mode */ if (IS_PCIX(pcibus_info)) diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c index 2aeae46..8dfd31e 100644 --- a/arch/m32r/kernel/irq.c +++ b/arch/m32r/kernel/irq.c @@ -49,7 +49,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%10u ", kstat_irqs(i)); #else for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); #endif seq_printf(p, " %14s", irq_desc[i].chip->typename); seq_printf(p, " %s", action->name); diff --git a/arch/m68k/include/asm/ftrace.h b/arch/m68k/include/asm/ftrace.h new file mode 100644 index 0000000..40a8c17 --- /dev/null +++ b/arch/m68k/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/m68knommu/platform/5206e/config.c b/arch/m68knommu/platform/5206e/config.c index d01a5d2..db90254 100644 --- a/arch/m68knommu/platform/5206e/config.c +++ b/arch/m68knommu/platform/5206e/config.c @@ -17,6 +17,7 @@ #include #include #include +#include /***************************************************************************/ diff --git a/arch/m68knommu/platform/528x/config.c b/arch/m68knommu/platform/528x/config.c index dfdb5c2..44baeb2 100644 --- a/arch/m68knommu/platform/528x/config.c +++ b/arch/m68knommu/platform/528x/config.c @@ -24,7 +24,6 @@ #include #include #include -#include #ifdef CONFIG_MTD_PARTITIONS #include @@ -33,233 +32,6 @@ /***************************************************************************/ void coldfire_reset(void); -static void coldfire_qspi_cs_control(u8 cs, u8 command); - -/***************************************************************************/ - -#if defined(CONFIG_SPI) - -#if defined(CONFIG_WILDFIRE) -#define SPI_NUM_CHIPSELECTS 0x02 -#define SPI_PAR_VAL 0x07 /* Enable DIN, DOUT, CLK */ -#define SPI_CS_MASK 0x18 - -#define FLASH_BLOCKSIZE (1024*64) -#define FLASH_NUMBLOCKS 16 -#define FLASH_TYPE "m25p80" - -#define M25P80_CS 0 -#define MMC_CS 1 - -#ifdef CONFIG_MTD_PARTITIONS -static struct mtd_partition stm25p_partitions[] = { - /* sflash */ - [0] = { - .name = "stm25p80", - .offset = 0x00000000, - .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS, - .mask_flags = 0 - } -}; - -#endif - -#elif defined(CONFIG_WILDFIREMOD) - -#define SPI_NUM_CHIPSELECTS 0x08 -#define SPI_PAR_VAL 0x07 /* Enable DIN, DOUT, CLK */ -#define SPI_CS_MASK 0x78 - -#define FLASH_BLOCKSIZE (1024*64) -#define FLASH_NUMBLOCKS 64 -#define FLASH_TYPE "m25p32" -/* Reserve 1M for the kernel parition */ -#define FLASH_KERNEL_SIZE (1024 * 1024) - -#define M25P80_CS 5 -#define MMC_CS 6 - -#ifdef CONFIG_MTD_PARTITIONS -static struct mtd_partition stm25p_partitions[] = { - /* sflash */ - [0] = { - .name = "kernel", - .offset = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS - FLASH_KERNEL_SIZE, - .size = FLASH_KERNEL_SIZE, - .mask_flags = 0 - }, - [1] = { - .name = "image", - .offset = 0x00000000, - .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS - FLASH_KERNEL_SIZE, - .mask_flags = 0 - }, - [2] = { - .name = "all", - .offset = 0x00000000, - .size = FLASH_BLOCKSIZE * FLASH_NUMBLOCKS, - .mask_flags = 0 - } -}; -#endif - -#else -#define SPI_NUM_CHIPSELECTS 0x04 -#define SPI_PAR_VAL 0x7F /* Enable DIN, DOUT, CLK, CS0 - CS4 */ -#endif - -#ifdef MMC_CS -static struct coldfire_spi_chip flash_chip_info = { - .mode = SPI_MODE_0, - .bits_per_word = 16, - .del_cs_to_clk = 17, - .del_after_trans = 1, - .void_write_data = 0 -}; - -static struct coldfire_spi_chip mmc_chip_info = { - .mode = SPI_MODE_0, - .bits_per_word = 16, - .del_cs_to_clk = 17, - .del_after_trans = 1, - .void_write_data = 0xFFFF -}; -#endif - -#ifdef M25P80_CS -static struct flash_platform_data stm25p80_platform_data = { - .name = "ST M25P80 SPI Flash chip", -#ifdef CONFIG_MTD_PARTITIONS - .parts = stm25p_partitions, - .nr_parts = sizeof(stm25p_partitions) / sizeof(*stm25p_partitions), -#endif - .type = FLASH_TYPE -}; -#endif - -static struct spi_board_info spi_board_info[] __initdata = { -#ifdef M25P80_CS - { - .modalias = "m25p80", - .max_speed_hz = 16000000, - .bus_num = 1, - .chip_select = M25P80_CS, - .platform_data = &stm25p80_platform_data, - .controller_data = &flash_chip_info - }, -#endif -#ifdef MMC_CS - { - .modalias = "mmc_spi", - .max_speed_hz = 16000000, - .bus_num = 1, - .chip_select = MMC_CS, - .controller_data = &mmc_chip_info - } -#endif -}; - -static struct coldfire_spi_master coldfire_master_info = { - .bus_num = 1, - .num_chipselect = SPI_NUM_CHIPSELECTS, - .irq_source = MCF5282_QSPI_IRQ_SOURCE, - .irq_vector = MCF5282_QSPI_IRQ_VECTOR, - .irq_mask = ((0x01 << MCF5282_QSPI_IRQ_SOURCE) | 0x01), - .irq_lp = 0x2B, /* Level 5 and Priority 3 */ - .par_val = SPI_PAR_VAL, - .cs_control = coldfire_qspi_cs_control, -}; - -static struct resource coldfire_spi_resources[] = { - [0] = { - .name = "qspi-par", - .start = MCF5282_QSPI_PAR, - .end = MCF5282_QSPI_PAR, - .flags = IORESOURCE_MEM - }, - - [1] = { - .name = "qspi-module", - .start = MCF5282_QSPI_QMR, - .end = MCF5282_QSPI_QMR + 0x18, - .flags = IORESOURCE_MEM - }, - - [2] = { - .name = "qspi-int-level", - .start = MCF5282_INTC0 + MCFINTC_ICR0 + MCF5282_QSPI_IRQ_SOURCE, - .end = MCF5282_INTC0 + MCFINTC_ICR0 + MCF5282_QSPI_IRQ_SOURCE, - .flags = IORESOURCE_MEM - }, - - [3] = { - .name = "qspi-int-mask", - .start = MCF5282_INTC0 + MCFINTC_IMRL, - .end = MCF5282_INTC0 + MCFINTC_IMRL, - .flags = IORESOURCE_MEM - } -}; - -static struct platform_device coldfire_spi = { - .name = "spi_coldfire", - .id = -1, - .resource = coldfire_spi_resources, - .num_resources = ARRAY_SIZE(coldfire_spi_resources), - .dev = { - .platform_data = &coldfire_master_info, - } -}; - -static void coldfire_qspi_cs_control(u8 cs, u8 command) -{ - u8 cs_bit = ((0x01 << cs) << 3) & SPI_CS_MASK; - -#if defined(CONFIG_WILDFIRE) - u8 cs_mask = ~(((0x01 << cs) << 3) & SPI_CS_MASK); -#endif -#if defined(CONFIG_WILDFIREMOD) - u8 cs_mask = (cs << 3) & SPI_CS_MASK; -#endif - - /* - * Don't do anything if the chip select is not - * one of the port qs pins. - */ - if (command & QSPI_CS_INIT) { -#if defined(CONFIG_WILDFIRE) - MCF5282_GPIO_DDRQS |= cs_bit; - MCF5282_GPIO_PQSPAR &= ~cs_bit; -#endif - -#if defined(CONFIG_WILDFIREMOD) - MCF5282_GPIO_DDRQS |= SPI_CS_MASK; - MCF5282_GPIO_PQSPAR &= ~SPI_CS_MASK; -#endif - } - - if (command & QSPI_CS_ASSERT) { - MCF5282_GPIO_PORTQS &= ~SPI_CS_MASK; - MCF5282_GPIO_PORTQS |= cs_mask; - } else if (command & QSPI_CS_DROP) { - MCF5282_GPIO_PORTQS |= SPI_CS_MASK; - } -} - -static int __init spi_dev_init(void) -{ - int retval; - - retval = platform_device_register(&coldfire_spi); - if (retval < 0) - return retval; - - if (ARRAY_SIZE(spi_board_info)) - retval = spi_register_board_info(spi_board_info, ARRAY_SIZE(spi_board_info)); - - return retval; -} - -#endif /* CONFIG_SPI */ /***************************************************************************/ diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index ac5d541..6c5b409 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -3,6 +3,8 @@ /* * Architecture specific compatibility types */ +#include +#include #include #include #include @@ -218,4 +220,9 @@ struct compat_shmid64_ds { compat_ulong_t __unused2; }; +static inline int is_compat_task(void) +{ + return test_thread_flag(TIF_32BIT); +} + #endif /* _ASM_COMPAT_H */ diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h new file mode 100644 index 0000000..40a8c17 --- /dev/null +++ b/arch/mips/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index abc62aa..3214ade 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -66,7 +66,7 @@ extern void smtc_forward_irq(unsigned int irq); */ #define IRQ_AFFINITY_HOOK(irq) \ do { \ - if (!cpu_isset(smp_processor_id(), irq_desc[irq].affinity)) { \ + if (!cpumask_test_cpu(smp_processor_id(), irq_desc[irq].affinity)) {\ smtc_forward_irq(irq); \ irq_exit(); \ return; \ diff --git a/arch/mips/include/asm/sigcontext.h b/arch/mips/include/asm/sigcontext.h index 9ce0607..9e89cf9 100644 --- a/arch/mips/include/asm/sigcontext.h +++ b/arch/mips/include/asm/sigcontext.h @@ -9,6 +9,7 @@ #ifndef _ASM_SIGCONTEXT_H #define _ASM_SIGCONTEXT_H +#include #include #if _MIPS_SIM == _MIPS_SIM_ABI32 diff --git a/arch/mips/include/asm/swab.h b/arch/mips/include/asm/swab.h index 88f1f7d..99993c0 100644 --- a/arch/mips/include/asm/swab.h +++ b/arch/mips/include/asm/swab.h @@ -9,7 +9,7 @@ #define _ASM_SWAB_H #include -#include +#include #define __SWAB_64_THRU_32__ diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 494a49a..87deb8f 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -187,7 +187,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask); } - irq_desc[irq].affinity = *cpumask; + cpumask_copy(irq_desc[irq].affinity, cpumask); spin_unlock_irqrestore(&gic_lock, flags); } diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index 4b4007b..7b845ba 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -108,7 +108,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%10u ", kstat_irqs(i)); #else for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); #endif seq_printf(p, " %14s", irq_desc[i].chip->name); seq_printf(p, " %s", action->name); diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index b6cca01..5f5af7d 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -686,7 +686,7 @@ void smtc_forward_irq(unsigned int irq) * and efficiency, we just pick the easiest one to find. */ - target = first_cpu(irq_desc[irq].affinity); + target = cpumask_first(irq_desc[irq].affinity); /* * We depend on the platform code to have correctly processed @@ -921,11 +921,13 @@ void ipi_decode(struct smtc_ipi *pipi) struct clock_event_device *cd; void *arg_copy = pipi->arg; int type_copy = pipi->type; + int irq = MIPS_CPU_IRQ_BASE + 1; + smtc_ipi_nq(&freeIPIq, pipi); switch (type_copy) { case SMTC_CLOCK_TICK: irq_enter(); - kstat_this_cpu.irqs[MIPS_CPU_IRQ_BASE + 1]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); cd = &per_cpu(mips_clockevent_device, cpu); cd->event_handler(cd); irq_exit(); diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c index aabd727..5ba3188 100644 --- a/arch/mips/mti-malta/malta-smtc.c +++ b/arch/mips/mti-malta/malta-smtc.c @@ -116,7 +116,7 @@ struct plat_smp_ops msmtc_smp_ops = { void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) { - cpumask_t tmask = *affinity; + cpumask_t tmask; int cpu = 0; void smtc_set_irq_affinity(unsigned int irq, cpumask_t aff); @@ -139,11 +139,12 @@ void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) * be made to forward to an offline "CPU". */ + cpumask_copy(&tmask, affinity); for_each_cpu(cpu, affinity) { if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu)) cpu_clear(cpu, tmask); } - irq_desc[irq].affinity = tmask; + cpumask_copy(irq_desc[irq].affinity, &tmask); if (cpus_empty(tmask)) /* diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c index f8b18af..0ecd5fe 100644 --- a/arch/mips/sgi-ip22/ip22-int.c +++ b/arch/mips/sgi-ip22/ip22-int.c @@ -155,7 +155,7 @@ static void indy_buserror_irq(void) int irq = SGI_BUSERR_IRQ; irq_enter(); - kstat_this_cpu.irqs[irq]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); ip22_be_interrupt(irq); irq_exit(); } diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c index 3dcb27e..c8f7d23 100644 --- a/arch/mips/sgi-ip22/ip22-time.c +++ b/arch/mips/sgi-ip22/ip22-time.c @@ -122,7 +122,7 @@ void indy_8254timer_irq(void) char c; irq_enter(); - kstat_this_cpu.irqs[irq]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); printk(KERN_ALERT "Oops, got 8254 interrupt.\n"); ArcRead(0, &c, 1, &cnt); ArcEnterInteractiveMode(); diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c index dddfda8..3146916 100644 --- a/arch/mips/sibyte/bcm1480/smp.c +++ b/arch/mips/sibyte/bcm1480/smp.c @@ -178,9 +178,10 @@ struct plat_smp_ops bcm1480_smp_ops = { void bcm1480_mailbox_interrupt(void) { int cpu = smp_processor_id(); + int irq = K_BCM1480_INT_MBOX_0_0; unsigned int action; - kstat_this_cpu.irqs[K_BCM1480_INT_MBOX_0_0]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); /* Load the mailbox register to figure out what we're supposed to do */ action = (__raw_readq(mailbox_0_regs[cpu]) >> 48) & 0xffff; diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c index 5950a28..cad1400 100644 --- a/arch/mips/sibyte/sb1250/smp.c +++ b/arch/mips/sibyte/sb1250/smp.c @@ -166,9 +166,10 @@ struct plat_smp_ops sb_smp_ops = { void sb1250_mailbox_interrupt(void) { int cpu = smp_processor_id(); + int irq = K_INT_MBOX_0; unsigned int action; - kstat_this_cpu.irqs[K_INT_MBOX_0]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); /* Load the mailbox register to figure out what we're supposed to do */ action = (____raw_readq(mailbox_regs[cpu]) >> 48) & 0xffff; diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c index 56c64cc..50fdb5c 100644 --- a/arch/mn10300/kernel/irq.c +++ b/arch/mn10300/kernel/irq.c @@ -221,7 +221,7 @@ int show_interrupts(struct seq_file *p, void *v) if (action) { seq_printf(p, "%3d: ", i); for_each_present_cpu(cpu) - seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu)); seq_printf(p, " %14s.%u", irq_desc[i].chip->name, (GxICR(i) & GxICR_LEVEL) >> GxICR_LEVEL_SHIFT); diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c index 10811e9..2e370d8 100644 --- a/arch/mn10300/kernel/mn10300-watchdog.c +++ b/arch/mn10300/kernel/mn10300-watchdog.c @@ -130,6 +130,7 @@ void watchdog_interrupt(struct pt_regs *regs, enum exception_code excep) * the stack NMI-atomically, it's safe to use smp_processor_id(). */ int sum, cpu = smp_processor_id(); + int irq = NMIIRQ; u8 wdt, tmp; wdt = WDCTR & ~WDCTR_WDCNE; @@ -138,7 +139,7 @@ void watchdog_interrupt(struct pt_regs *regs, enum exception_code excep) NMICR = NMICR_WDIF; nmi_count(cpu)++; - kstat_this_cpu.irqs[NMIIRQ]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); sum = irq_stat[cpu].__irq_count; if (last_irq_sums[cpu] == sum) { diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h new file mode 100644 index 0000000..40a8c17 --- /dev/null +++ b/arch/parisc/include/asm/ftrace.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index c584b00..430f1ae 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -336,10 +336,11 @@ #define NUM_PDC_RESULT 32 #if !defined(__ASSEMBLY__) -#ifdef __KERNEL__ #include +#ifdef __KERNEL__ + extern int pdc_type; /* Values for pdc_type */ diff --git a/arch/parisc/include/asm/swab.h b/arch/parisc/include/asm/swab.h index 3ff16c5..e78403b 100644 --- a/arch/parisc/include/asm/swab.h +++ b/arch/parisc/include/asm/swab.h @@ -1,7 +1,7 @@ #ifndef _PARISC_SWAB_H #define _PARISC_SWAB_H -#include +#include #include #define __SWAB_64_THRU_32__ diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index ac2c822..c1e6666 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -120,7 +120,7 @@ int cpu_check_affinity(unsigned int irq, cpumask_t *dest) if (CHECK_IRQ_PER_CPU(irq)) { /* Bad linux design decision. The mask has already * been set; we must reset it */ - irq_desc[irq].affinity = CPU_MASK_ALL; + cpumask_setall(irq_desc[irq].affinity); return -EINVAL; } @@ -136,7 +136,7 @@ static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest) if (cpu_check_affinity(irq, dest)) return; - irq_desc[irq].affinity = *dest; + cpumask_copy(irq_desc[irq].affinity, dest); } #endif @@ -183,7 +183,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%3d: ", i); #ifdef CONFIG_SMP for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); #else seq_printf(p, "%10u ", kstat_irqs(i)); #endif @@ -295,7 +295,7 @@ int txn_alloc_irq(unsigned int bits_wide) unsigned long txn_affinity_addr(unsigned int irq, int cpu) { #ifdef CONFIG_SMP - irq_desc[irq].affinity = cpumask_of_cpu(cpu); + cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu)); #endif return per_cpu(cpu_data, cpu).txn_addr; @@ -352,7 +352,7 @@ void do_cpu_irq_mask(struct pt_regs *regs) irq = eirr_to_irq(eirr_val); #ifdef CONFIG_SMP - dest = irq_desc[irq].affinity; + cpumask_copy(&dest, irq_desc[irq].affinity); if (CHECK_IRQ_PER_CPU(irq_desc[irq].status) && !cpu_isset(smp_processor_id(), dest)) { int cpu = first_cpu(dest); diff --git a/arch/powerpc/configs/40x/virtex_defconfig b/arch/powerpc/configs/40x/virtex_defconfig index b688838..f5698f9 100644 --- a/arch/powerpc/configs/40x/virtex_defconfig +++ b/arch/powerpc/configs/40x/virtex_defconfig @@ -686,7 +686,7 @@ CONFIG_SERIAL_UARTLITE_CONSOLE=y CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y # CONFIG_SERIAL_JSM is not set -# CONFIG_SERIAL_OF_PLATFORM is not set +CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL is not set CONFIG_UNIX98_PTYS=y # CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set diff --git a/arch/powerpc/configs/44x/virtex5_defconfig b/arch/powerpc/configs/44x/virtex5_defconfig index 15aab1c..1bf0a63 100644 --- a/arch/powerpc/configs/44x/virtex5_defconfig +++ b/arch/powerpc/configs/44x/virtex5_defconfig @@ -691,7 +691,7 @@ CONFIG_SERIAL_UARTLITE_CONSOLE=y CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y # CONFIG_SERIAL_JSM is not set -# CONFIG_SERIAL_OF_PLATFORM is not set +CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL is not set CONFIG_UNIX98_PTYS=y # CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig index aa5855a..15900dc 100644 --- a/arch/powerpc/configs/linkstation_defconfig +++ b/arch/powerpc/configs/linkstation_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.29-rc2 -# Mon Jan 26 15:35:29 2009 +# Linux kernel version: 2.6.29-rc6 +# Fri Mar 6 00:07:38 2009 # # CONFIG_PPC64 is not set @@ -71,6 +71,15 @@ CONFIG_POSIX_MQUEUE=y # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set # CONFIG_AUDIT is not set + +# +# RCU Subsystem +# +CONFIG_CLASSIC_RCU=y +# CONFIG_TREE_RCU is not set +# CONFIG_PREEMPT_RCU is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU_TRACE is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -88,6 +97,7 @@ CONFIG_NAMESPACES=y # CONFIG_IPC_NS is not set # CONFIG_USER_NS is not set # CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -153,11 +163,6 @@ CONFIG_DEFAULT_AS=y # CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="anticipatory" -CONFIG_CLASSIC_RCU=y -# CONFIG_TREE_RCU is not set -# CONFIG_PREEMPT_RCU is not set -# CONFIG_TREE_RCU_TRACE is not set -# CONFIG_PREEMPT_RCU_TRACE is not set # CONFIG_FREEZER is not set # @@ -294,7 +299,6 @@ CONFIG_NET=y # # Networking options # -# CONFIG_NET_NS is not set CONFIG_COMPAT_NET_DEV_OPS=y CONFIG_PACKET=y CONFIG_PACKET_MMAP=y @@ -508,8 +512,8 @@ CONFIG_MTD_CONCAT=y CONFIG_MTD_PARTITIONS=y # CONFIG_MTD_TESTS is not set # CONFIG_MTD_REDBOOT_PARTS is not set -# CONFIG_MTD_CMDLINE_PARTS is not set -# CONFIG_MTD_OF_PARTS is not set +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_OF_PARTS=y # CONFIG_MTD_AR7_PARTS is not set # @@ -587,7 +591,6 @@ CONFIG_MTD_PHYSMAP=y # LPDDR flash memory drivers # # CONFIG_MTD_LPDDR is not set -# CONFIG_MTD_QINFO_PROBE is not set # # UBI - Unsorted block images @@ -617,13 +620,19 @@ CONFIG_BLK_DEV_RAM_SIZE=8192 # CONFIG_BLK_DEV_HD is not set CONFIG_MISC_DEVICES=y # CONFIG_PHANTOM is not set -# CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set # CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set # CONFIG_HP_ILO is not set # CONFIG_C2PORT is not set + +# +# EEPROM support +# +# CONFIG_EEPROM_AT24 is not set +CONFIG_EEPROM_LEGACY=m +# CONFIG_EEPROM_93CX6 is not set CONFIG_HAVE_IDE=y # CONFIG_IDE is not set @@ -839,6 +848,7 @@ CONFIG_R8169=y # CONFIG_QLA3XXX is not set # CONFIG_ATL1 is not set # CONFIG_ATL1E is not set +# CONFIG_ATL1C is not set # CONFIG_JME is not set CONFIG_NETDEV_10000=y # CONFIG_CHELSIO_T1 is not set @@ -1037,8 +1047,6 @@ CONFIG_I2C_MPC=y # Miscellaneous I2C Chip support # # CONFIG_DS1682 is not set -# CONFIG_EEPROM_AT24 is not set -CONFIG_EEPROM_LEGACY=m # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCA9539 is not set diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig index 86512c8..9490346 100644 --- a/arch/powerpc/configs/storcenter_defconfig +++ b/arch/powerpc/configs/storcenter_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.29-rc2 -# Mon Jan 26 15:35:46 2009 +# Linux kernel version: 2.6.29-rc6 +# Fri Mar 6 00:09:08 2009 # # CONFIG_PPC64 is not set @@ -71,6 +71,15 @@ CONFIG_SYSVIPC_SYSCTL=y # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set # CONFIG_AUDIT is not set + +# +# RCU Subsystem +# +CONFIG_CLASSIC_RCU=y +# CONFIG_TREE_RCU is not set +# CONFIG_PREEMPT_RCU is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU_TRACE is not set # CONFIG_IKCONFIG is not set CONFIG_LOG_BUF_SHIFT=14 CONFIG_GROUP_SCHED=y @@ -144,11 +153,6 @@ CONFIG_IOSCHED_CFQ=y CONFIG_DEFAULT_CFQ=y # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="cfq" -CONFIG_CLASSIC_RCU=y -# CONFIG_TREE_RCU is not set -# CONFIG_PREEMPT_RCU is not set -# CONFIG_TREE_RCU_TRACE is not set -# CONFIG_PREEMPT_RCU_TRACE is not set # CONFIG_FREEZER is not set # @@ -377,8 +381,8 @@ CONFIG_MTD=y CONFIG_MTD_PARTITIONS=y # CONFIG_MTD_TESTS is not set # CONFIG_MTD_REDBOOT_PARTS is not set -# CONFIG_MTD_CMDLINE_PARTS is not set -# CONFIG_MTD_OF_PARTS is not set +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_OF_PARTS=y # CONFIG_MTD_AR7_PARTS is not set # @@ -452,7 +456,6 @@ CONFIG_MTD_PHYSMAP=y # LPDDR flash memory drivers # # CONFIG_MTD_LPDDR is not set -# CONFIG_MTD_QINFO_PROBE is not set # # UBI - Unsorted block images @@ -478,13 +481,19 @@ CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_HD is not set CONFIG_MISC_DEVICES=y # CONFIG_PHANTOM is not set -# CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set # CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set # CONFIG_HP_ILO is not set # CONFIG_C2PORT is not set + +# +# EEPROM support +# +# CONFIG_EEPROM_AT24 is not set +# CONFIG_EEPROM_LEGACY is not set +# CONFIG_EEPROM_93CX6 is not set CONFIG_HAVE_IDE=y CONFIG_IDE=y @@ -677,6 +686,7 @@ CONFIG_R8169=y # CONFIG_QLA3XXX is not set # CONFIG_ATL1 is not set # CONFIG_ATL1E is not set +# CONFIG_ATL1C is not set # CONFIG_JME is not set # CONFIG_NETDEV_10000 is not set # CONFIG_TR is not set @@ -818,8 +828,6 @@ CONFIG_I2C_MPC=y # Miscellaneous I2C Chip support # # CONFIG_DS1682 is not set -# CONFIG_EEPROM_AT24 is not set -# CONFIG_EEPROM_LEGACY is not set # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCA9539 is not set @@ -1159,6 +1167,7 @@ CONFIG_JFFS2_RTIME=y # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set # CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_EXPORTFS=m # # Partition Types diff --git a/arch/powerpc/include/asm/bootx.h b/arch/powerpc/include/asm/bootx.h index 57b82e3..60a3c9e 100644 --- a/arch/powerpc/include/asm/bootx.h +++ b/arch/powerpc/include/asm/bootx.h @@ -9,7 +9,7 @@ #ifndef __ASM_BOOTX_H__ #define __ASM_BOOTX_H__ -#include +#include #ifdef macintosh #include diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index cd46f02..b5600ce 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -7,7 +7,7 @@ #include #endif -#include +#include #include #include #include diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index f75a5fc..e10f151 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -131,5 +131,36 @@ static inline int irqs_disabled_flags(unsigned long flags) */ struct hw_interrupt_type; +#ifdef CONFIG_PERF_COUNTERS +static inline unsigned long get_perf_counter_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, perf_counter_pending))); + return x; +} + +static inline void set_perf_counter_pending(int x) +{ + asm volatile("stb %0,%1(13)" : : + "r" (x), + "i" (offsetof(struct paca_struct, perf_counter_pending))); +} + +extern void perf_counter_do_pending(void); + +#else + +static inline unsigned long get_perf_counter_pending(void) +{ + return 0; +} + +static inline void set_perf_counter_pending(int x) {} +static inline void perf_counter_do_pending(void) {} +#endif /* CONFIG_PERF_COUNTERS */ + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HW_IRQ_H */ diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index f993e41..4e0cf65 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -20,7 +20,7 @@ #ifndef __LINUX_KVM_POWERPC_H #define __LINUX_KVM_POWERPC_H -#include +#include struct kvm_regs { __u64 pc; diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 082b3ae..6ef0557 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -99,6 +99,7 @@ struct paca_struct { u8 soft_enabled; /* irq soft-enable flag */ u8 hard_enabled; /* set if irqs are enabled in MSR */ u8 io_sync; /* writel() needs spin_unlock sync */ + u8 perf_counter_pending; /* PM interrupt while soft-disabled */ /* Stuff for accurate time accounting */ u64 user_time; /* accumulated usermode TB ticks */ diff --git a/arch/powerpc/include/asm/perf_counter.h b/arch/powerpc/include/asm/perf_counter.h new file mode 100644 index 0000000..9d7ff6d --- /dev/null +++ b/arch/powerpc/include/asm/perf_counter.h @@ -0,0 +1,72 @@ +/* + * Performance counter support - PowerPC-specific definitions. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include + +#define MAX_HWCOUNTERS 8 +#define MAX_EVENT_ALTERNATIVES 8 + +/* + * This struct provides the constants and functions needed to + * describe the PMU on a particular POWER-family CPU. + */ +struct power_pmu { + int n_counter; + int max_alternatives; + u64 add_fields; + u64 test_adder; + int (*compute_mmcr)(unsigned int events[], int n_ev, + unsigned int hwc[], u64 mmcr[]); + int (*get_constraint)(unsigned int event, u64 *mskp, u64 *valp); + int (*get_alternatives)(unsigned int event, unsigned int alt[]); + void (*disable_pmc)(unsigned int pmc, u64 mmcr[]); + int n_generic; + int *generic_events; +}; + +extern struct power_pmu *ppmu; + +/* + * The power_pmu.get_constraint function returns a 64-bit value and + * a 64-bit mask that express the constraints between this event and + * other events. + * + * The value and mask are divided up into (non-overlapping) bitfields + * of three different types: + * + * Select field: this expresses the constraint that some set of bits + * in MMCR* needs to be set to a specific value for this event. For a + * select field, the mask contains 1s in every bit of the field, and + * the value contains a unique value for each possible setting of the + * MMCR* bits. The constraint checking code will ensure that two events + * that set the same field in their masks have the same value in their + * value dwords. + * + * Add field: this expresses the constraint that there can be at most + * N events in a particular class. A field of k bits can be used for + * N <= 2^(k-1) - 1. The mask has the most significant bit of the field + * set (and the other bits 0), and the value has only the least significant + * bit of the field set. In addition, the 'add_fields' and 'test_adder' + * in the struct power_pmu for this processor come into play. The + * add_fields value contains 1 in the LSB of the field, and the + * test_adder contains 2^(k-1) - 1 - N in the field. + * + * NAND field: this expresses the constraint that you may not have events + * in all of a set of classes. (For example, on PPC970, you can't select + * events from the FPU, ISU and IDU simultaneously, although any two are + * possible.) For N classes, the field is N+1 bits wide, and each class + * is assigned one bit from the least-significant N bits. The mask has + * only the most-significant bit set, and the value has only the bit + * for the event's class set. The test_adder has the least significant + * bit set in the field. + * + * If an event is not subject to the constraint expressed by a particular + * field, then it will have 0 in both the mask and value for that field. + */ diff --git a/arch/powerpc/include/asm/ps3fb.h b/arch/powerpc/include/asm/ps3fb.h index 3f121fe..e7233a8 100644 --- a/arch/powerpc/include/asm/ps3fb.h +++ b/arch/powerpc/include/asm/ps3fb.h @@ -19,6 +19,7 @@ #ifndef _ASM_POWERPC_PS3FB_H_ #define _ASM_POWERPC_PS3FB_H_ +#include #include /* ioctl */ diff --git a/arch/powerpc/include/asm/spu_info.h b/arch/powerpc/include/asm/spu_info.h index 3545efb..1286c82 100644 --- a/arch/powerpc/include/asm/spu_info.h +++ b/arch/powerpc/include/asm/spu_info.h @@ -23,9 +23,10 @@ #ifndef _SPU_INFO_H #define _SPU_INFO_H +#include + #ifdef __KERNEL__ #include -#include #else struct mfc_cq_sr { __u64 mfc_cq_data0_RW; diff --git a/arch/powerpc/include/asm/swab.h b/arch/powerpc/include/asm/swab.h index ef824ae..c581e3e 100644 --- a/arch/powerpc/include/asm/swab.h +++ b/arch/powerpc/include/asm/swab.h @@ -8,7 +8,7 @@ * 2 of the License, or (at your option) any later version. */ -#include +#include #include #ifdef __GNUC__ diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 72353f6..d312eec 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -322,3 +322,4 @@ SYSCALL_SPU(epoll_create1) SYSCALL_SPU(dup3) SYSCALL_SPU(pipe2) SYSCALL(inotify_init1) +SYSCALL_SPU(perf_counter_open) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index e07d0c7..7cef5af 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -341,10 +341,11 @@ #define __NR_dup3 316 #define __NR_pipe2 317 #define __NR_inotify_init1 318 +#define __NR_perf_counter_open 319 #ifdef __KERNEL__ -#define __NR_syscalls 319 +#define __NR_syscalls 320 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 8d1a419..8e5e2c7 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -94,6 +94,8 @@ obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o +obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o power4-pmu.o ppc970-pmu.o \ + power5-pmu.o power5+-pmu.o power6-pmu.o obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 19ee491..3734973 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -131,6 +131,7 @@ int main(void) DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr)); DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled)); DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled)); + DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending)); DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache)); DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr)); DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id)); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 383ed6e..f30b4e5 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -526,6 +526,15 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) 2: TRACE_AND_RESTORE_IRQ(r5); +#ifdef CONFIG_PERF_COUNTERS + /* check paca->perf_counter_pending if we're enabling ints */ + lbz r3,PACAPERFPEND(r13) + and. r3,r3,r5 + beq 27f + bl .perf_counter_do_pending +27: +#endif /* CONFIG_PERF_COUNTERS */ + /* extract EE bit and use it to restore paca->hard_enabled */ ld r3,_MSR(r1) rldicl r4,r3,49,63 /* r0 = (r3 >> 15) & 1 */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 23b8b5e..5c9a255 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -104,6 +104,13 @@ static inline notrace void set_soft_enabled(unsigned long enable) : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled))); } +#ifdef CONFIG_PERF_COUNTERS +notrace void __weak perf_counter_do_pending(void) +{ + set_perf_counter_pending(0); +} +#endif + notrace void raw_local_irq_restore(unsigned long en) { /* @@ -135,6 +142,9 @@ notrace void raw_local_irq_restore(unsigned long en) iseries_handle_interrupts(); } + if (get_perf_counter_pending()) + perf_counter_do_pending(); + /* * if (get_paca()->hard_enabled) return; * But again we need to take care that gcc gets hard_enabled directly @@ -190,7 +200,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%3d: ", i); #ifdef CONFIG_SMP for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); #else seq_printf(p, "%10u ", kstat_irqs(i)); #endif /* CONFIG_SMP */ @@ -231,7 +241,7 @@ void fixup_irqs(cpumask_t map) if (irq_desc[irq].status & IRQ_PER_CPU) continue; - cpus_and(mask, irq_desc[irq].affinity, map); + cpumask_and(&mask, irq_desc[irq].affinity, &map); if (any_online_cpu(mask) == NR_CPUS) { printk("Breaking affinity for irq %i\n", irq); mask = map; diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c new file mode 100644 index 0000000..0e33d27 --- /dev/null +++ b/arch/powerpc/kernel/perf_counter.c @@ -0,0 +1,874 @@ +/* + * Performance counter support - powerpc architecture code + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct cpu_hw_counters { + int n_counters; + int n_percpu; + int disabled; + int n_added; + struct perf_counter *counter[MAX_HWCOUNTERS]; + unsigned int events[MAX_HWCOUNTERS]; + u64 mmcr[3]; + u8 pmcs_enabled; +}; +DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters); + +struct power_pmu *ppmu; + +/* + * Normally, to ignore kernel events we set the FCS (freeze counters + * in supervisor mode) bit in MMCR0, but if the kernel runs with the + * hypervisor bit set in the MSR, or if we are running on a processor + * where the hypervisor bit is forced to 1 (as on Apple G5 processors), + * then we need to use the FCHV bit to ignore kernel events. + */ +static unsigned int freeze_counters_kernel = MMCR0_FCS; + +void perf_counter_print_debug(void) +{ +} + +/* + * Read one performance monitor counter (PMC). + */ +static unsigned long read_pmc(int idx) +{ + unsigned long val; + + switch (idx) { + case 1: + val = mfspr(SPRN_PMC1); + break; + case 2: + val = mfspr(SPRN_PMC2); + break; + case 3: + val = mfspr(SPRN_PMC3); + break; + case 4: + val = mfspr(SPRN_PMC4); + break; + case 5: + val = mfspr(SPRN_PMC5); + break; + case 6: + val = mfspr(SPRN_PMC6); + break; + case 7: + val = mfspr(SPRN_PMC7); + break; + case 8: + val = mfspr(SPRN_PMC8); + break; + default: + printk(KERN_ERR "oops trying to read PMC%d\n", idx); + val = 0; + } + return val; +} + +/* + * Write one PMC. + */ +static void write_pmc(int idx, unsigned long val) +{ + switch (idx) { + case 1: + mtspr(SPRN_PMC1, val); + break; + case 2: + mtspr(SPRN_PMC2, val); + break; + case 3: + mtspr(SPRN_PMC3, val); + break; + case 4: + mtspr(SPRN_PMC4, val); + break; + case 5: + mtspr(SPRN_PMC5, val); + break; + case 6: + mtspr(SPRN_PMC6, val); + break; + case 7: + mtspr(SPRN_PMC7, val); + break; + case 8: + mtspr(SPRN_PMC8, val); + break; + default: + printk(KERN_ERR "oops trying to write PMC%d\n", idx); + } +} + +/* + * Check if a set of events can all go on the PMU at once. + * If they can't, this will look at alternative codes for the events + * and see if any combination of alternative codes is feasible. + * The feasible set is returned in event[]. + */ +static int power_check_constraints(unsigned int event[], int n_ev) +{ + u64 mask, value, nv; + unsigned int alternatives[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 smasks[MAX_HWCOUNTERS], svalues[MAX_HWCOUNTERS]; + int n_alt[MAX_HWCOUNTERS], choice[MAX_HWCOUNTERS]; + int i, j; + u64 addf = ppmu->add_fields; + u64 tadd = ppmu->test_adder; + + if (n_ev > ppmu->n_counter) + return -1; + + /* First see if the events will go on as-is */ + for (i = 0; i < n_ev; ++i) { + alternatives[i][0] = event[i]; + if (ppmu->get_constraint(event[i], &amasks[i][0], + &avalues[i][0])) + return -1; + choice[i] = 0; + } + value = mask = 0; + for (i = 0; i < n_ev; ++i) { + nv = (value | avalues[i][0]) + (value & avalues[i][0] & addf); + if ((((nv + tadd) ^ value) & mask) != 0 || + (((nv + tadd) ^ avalues[i][0]) & amasks[i][0]) != 0) + break; + value = nv; + mask |= amasks[i][0]; + } + if (i == n_ev) + return 0; /* all OK */ + + /* doesn't work, gather alternatives... */ + if (!ppmu->get_alternatives) + return -1; + for (i = 0; i < n_ev; ++i) { + n_alt[i] = ppmu->get_alternatives(event[i], alternatives[i]); + for (j = 1; j < n_alt[i]; ++j) + ppmu->get_constraint(alternatives[i][j], + &amasks[i][j], &avalues[i][j]); + } + + /* enumerate all possibilities and see if any will work */ + i = 0; + j = -1; + value = mask = nv = 0; + while (i < n_ev) { + if (j >= 0) { + /* we're backtracking, restore context */ + value = svalues[i]; + mask = smasks[i]; + j = choice[i]; + } + /* + * See if any alternative k for event i, + * where k > j, will satisfy the constraints. + */ + while (++j < n_alt[i]) { + nv = (value | avalues[i][j]) + + (value & avalues[i][j] & addf); + if ((((nv + tadd) ^ value) & mask) == 0 && + (((nv + tadd) ^ avalues[i][j]) + & amasks[i][j]) == 0) + break; + } + if (j >= n_alt[i]) { + /* + * No feasible alternative, backtrack + * to event i-1 and continue enumerating its + * alternatives from where we got up to. + */ + if (--i < 0) + return -1; + } else { + /* + * Found a feasible alternative for event i, + * remember where we got up to with this event, + * go on to the next event, and start with + * the first alternative for it. + */ + choice[i] = j; + svalues[i] = value; + smasks[i] = mask; + value = nv; + mask |= amasks[i][j]; + ++i; + j = -1; + } + } + + /* OK, we have a feasible combination, tell the caller the solution */ + for (i = 0; i < n_ev; ++i) + event[i] = alternatives[i][choice[i]]; + return 0; +} + +/* + * Check if newly-added counters have consistent settings for + * exclude_{user,kernel,hv} with each other and any previously + * added counters. + */ +static int check_excludes(struct perf_counter **ctrs, int n_prev, int n_new) +{ + int eu, ek, eh; + int i, n; + struct perf_counter *counter; + + n = n_prev + n_new; + if (n <= 1) + return 0; + + eu = ctrs[0]->hw_event.exclude_user; + ek = ctrs[0]->hw_event.exclude_kernel; + eh = ctrs[0]->hw_event.exclude_hv; + if (n_prev == 0) + n_prev = 1; + for (i = n_prev; i < n; ++i) { + counter = ctrs[i]; + if (counter->hw_event.exclude_user != eu || + counter->hw_event.exclude_kernel != ek || + counter->hw_event.exclude_hv != eh) + return -EAGAIN; + } + return 0; +} + +static void power_perf_read(struct perf_counter *counter) +{ + long val, delta, prev; + + if (!counter->hw.idx) + return; + /* + * Performance monitor interrupts come even when interrupts + * are soft-disabled, as long as interrupts are hard-enabled. + * Therefore we treat them like NMIs. + */ + do { + prev = atomic64_read(&counter->hw.prev_count); + barrier(); + val = read_pmc(counter->hw.idx); + } while (atomic64_cmpxchg(&counter->hw.prev_count, prev, val) != prev); + + /* The counters are only 32 bits wide */ + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &counter->count); + atomic64_sub(delta, &counter->hw.period_left); +} + +/* + * Disable all counters to prevent PMU interrupts and to allow + * counters to be added or removed. + */ +u64 hw_perf_save_disable(void) +{ + struct cpu_hw_counters *cpuhw; + unsigned long ret; + unsigned long flags; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_counters); + + ret = cpuhw->disabled; + if (!ret) { + cpuhw->disabled = 1; + cpuhw->n_added = 0; + + /* + * Check if we ever enabled the PMU on this cpu. + */ + if (!cpuhw->pmcs_enabled) { + if (ppc_md.enable_pmcs) + ppc_md.enable_pmcs(); + cpuhw->pmcs_enabled = 1; + } + + /* + * Set the 'freeze counters' bit. + * The barrier is to make sure the mtspr has been + * executed and the PMU has frozen the counters + * before we return. + */ + mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) | MMCR0_FC); + mb(); + } + local_irq_restore(flags); + return ret; +} + +/* + * Re-enable all counters if disable == 0. + * If we were previously disabled and counters were added, then + * put the new config on the PMU. + */ +void hw_perf_restore(u64 disable) +{ + struct perf_counter *counter; + struct cpu_hw_counters *cpuhw; + unsigned long flags; + long i; + unsigned long val; + s64 left; + unsigned int hwc_index[MAX_HWCOUNTERS]; + + if (disable) + return; + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_counters); + cpuhw->disabled = 0; + + /* + * If we didn't change anything, or only removed counters, + * no need to recalculate MMCR* settings and reset the PMCs. + * Just reenable the PMU with the current MMCR* settings + * (possibly updated for removal of counters). + */ + if (!cpuhw->n_added) { + mtspr(SPRN_MMCRA, cpuhw->mmcr[2]); + mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); + mtspr(SPRN_MMCR0, cpuhw->mmcr[0]); + if (cpuhw->n_counters == 0) + get_lppaca()->pmcregs_in_use = 0; + goto out; + } + + /* + * Compute MMCR* values for the new set of counters + */ + if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_counters, hwc_index, + cpuhw->mmcr)) { + /* shouldn't ever get here */ + printk(KERN_ERR "oops compute_mmcr failed\n"); + goto out; + } + + /* + * Add in MMCR0 freeze bits corresponding to the + * hw_event.exclude_* bits for the first counter. + * We have already checked that all counters have the + * same values for these bits as the first counter. + */ + counter = cpuhw->counter[0]; + if (counter->hw_event.exclude_user) + cpuhw->mmcr[0] |= MMCR0_FCP; + if (counter->hw_event.exclude_kernel) + cpuhw->mmcr[0] |= freeze_counters_kernel; + if (counter->hw_event.exclude_hv) + cpuhw->mmcr[0] |= MMCR0_FCHV; + + /* + * Write the new configuration to MMCR* with the freeze + * bit set and set the hardware counters to their initial values. + * Then unfreeze the counters. + */ + get_lppaca()->pmcregs_in_use = 1; + mtspr(SPRN_MMCRA, cpuhw->mmcr[2]); + mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); + mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)) + | MMCR0_FC); + + /* + * Read off any pre-existing counters that need to move + * to another PMC. + */ + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (counter->hw.idx && counter->hw.idx != hwc_index[i] + 1) { + power_perf_read(counter); + write_pmc(counter->hw.idx, 0); + counter->hw.idx = 0; + } + } + + /* + * Initialize the PMCs for all the new and moved counters. + */ + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (counter->hw.idx) + continue; + val = 0; + if (counter->hw_event.irq_period) { + left = atomic64_read(&counter->hw.period_left); + if (left < 0x80000000L) + val = 0x80000000L - left; + } + atomic64_set(&counter->hw.prev_count, val); + counter->hw.idx = hwc_index[i] + 1; + write_pmc(counter->hw.idx, val); + } + mb(); + cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE; + mtspr(SPRN_MMCR0, cpuhw->mmcr[0]); + + out: + local_irq_restore(flags); +} + +static int collect_events(struct perf_counter *group, int max_count, + struct perf_counter *ctrs[], unsigned int *events) +{ + int n = 0; + struct perf_counter *counter; + + if (!is_software_counter(group)) { + if (n >= max_count) + return -1; + ctrs[n] = group; + events[n++] = group->hw.config; + } + list_for_each_entry(counter, &group->sibling_list, list_entry) { + if (!is_software_counter(counter) && + counter->state != PERF_COUNTER_STATE_OFF) { + if (n >= max_count) + return -1; + ctrs[n] = counter; + events[n++] = counter->hw.config; + } + } + return n; +} + +static void counter_sched_in(struct perf_counter *counter, int cpu) +{ + counter->state = PERF_COUNTER_STATE_ACTIVE; + counter->oncpu = cpu; + if (is_software_counter(counter)) + counter->hw_ops->enable(counter); +} + +/* + * Called to enable a whole group of counters. + * Returns 1 if the group was enabled, or -EAGAIN if it could not be. + * Assumes the caller has disabled interrupts and has + * frozen the PMU with hw_perf_save_disable. + */ +int hw_perf_group_sched_in(struct perf_counter *group_leader, + struct perf_cpu_context *cpuctx, + struct perf_counter_context *ctx, int cpu) +{ + struct cpu_hw_counters *cpuhw; + long i, n, n0; + struct perf_counter *sub; + + cpuhw = &__get_cpu_var(cpu_hw_counters); + n0 = cpuhw->n_counters; + n = collect_events(group_leader, ppmu->n_counter - n0, + &cpuhw->counter[n0], &cpuhw->events[n0]); + if (n < 0) + return -EAGAIN; + if (check_excludes(cpuhw->counter, n0, n)) + return -EAGAIN; + if (power_check_constraints(cpuhw->events, n + n0)) + return -EAGAIN; + cpuhw->n_counters = n0 + n; + cpuhw->n_added += n; + + /* + * OK, this group can go on; update counter states etc., + * and enable any software counters + */ + for (i = n0; i < n0 + n; ++i) + cpuhw->counter[i]->hw.config = cpuhw->events[i]; + cpuctx->active_oncpu += n; + n = 1; + counter_sched_in(group_leader, cpu); + list_for_each_entry(sub, &group_leader->sibling_list, list_entry) { + if (sub->state != PERF_COUNTER_STATE_OFF) { + counter_sched_in(sub, cpu); + ++n; + } + } + ctx->nr_active += n; + + return 1; +} + +/* + * Add a counter to the PMU. + * If all counters are not already frozen, then we disable and + * re-enable the PMU in order to get hw_perf_restore to do the + * actual work of reconfiguring the PMU. + */ +static int power_perf_enable(struct perf_counter *counter) +{ + struct cpu_hw_counters *cpuhw; + unsigned long flags; + u64 pmudis; + int n0; + int ret = -EAGAIN; + + local_irq_save(flags); + pmudis = hw_perf_save_disable(); + + /* + * Add the counter to the list (if there is room) + * and check whether the total set is still feasible. + */ + cpuhw = &__get_cpu_var(cpu_hw_counters); + n0 = cpuhw->n_counters; + if (n0 >= ppmu->n_counter) + goto out; + cpuhw->counter[n0] = counter; + cpuhw->events[n0] = counter->hw.config; + if (check_excludes(cpuhw->counter, n0, 1)) + goto out; + if (power_check_constraints(cpuhw->events, n0 + 1)) + goto out; + + counter->hw.config = cpuhw->events[n0]; + ++cpuhw->n_counters; + ++cpuhw->n_added; + + ret = 0; + out: + hw_perf_restore(pmudis); + local_irq_restore(flags); + return ret; +} + +/* + * Remove a counter from the PMU. + */ +static void power_perf_disable(struct perf_counter *counter) +{ + struct cpu_hw_counters *cpuhw; + long i; + u64 pmudis; + unsigned long flags; + + local_irq_save(flags); + pmudis = hw_perf_save_disable(); + + power_perf_read(counter); + + cpuhw = &__get_cpu_var(cpu_hw_counters); + for (i = 0; i < cpuhw->n_counters; ++i) { + if (counter == cpuhw->counter[i]) { + while (++i < cpuhw->n_counters) + cpuhw->counter[i-1] = cpuhw->counter[i]; + --cpuhw->n_counters; + ppmu->disable_pmc(counter->hw.idx - 1, cpuhw->mmcr); + write_pmc(counter->hw.idx, 0); + counter->hw.idx = 0; + break; + } + } + if (cpuhw->n_counters == 0) { + /* disable exceptions if no counters are running */ + cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); + } + + hw_perf_restore(pmudis); + local_irq_restore(flags); +} + +struct hw_perf_counter_ops power_perf_ops = { + .enable = power_perf_enable, + .disable = power_perf_disable, + .read = power_perf_read +}; + +const struct hw_perf_counter_ops * +hw_perf_counter_init(struct perf_counter *counter) +{ + unsigned long ev; + struct perf_counter *ctrs[MAX_HWCOUNTERS]; + unsigned int events[MAX_HWCOUNTERS]; + int n; + + if (!ppmu) + return NULL; + if ((s64)counter->hw_event.irq_period < 0) + return NULL; + ev = counter->hw_event.type; + if (!counter->hw_event.raw) { + if (ev >= ppmu->n_generic || + ppmu->generic_events[ev] == 0) + return NULL; + ev = ppmu->generic_events[ev]; + } + counter->hw.config_base = ev; + counter->hw.idx = 0; + + /* + * If we are not running on a hypervisor, force the + * exclude_hv bit to 0 so that we don't care what + * the user set it to. + */ + if (!firmware_has_feature(FW_FEATURE_LPAR)) + counter->hw_event.exclude_hv = 0; + + /* + * If this is in a group, check if it can go on with all the + * other hardware counters in the group. We assume the counter + * hasn't been linked into its leader's sibling list at this point. + */ + n = 0; + if (counter->group_leader != counter) { + n = collect_events(counter->group_leader, ppmu->n_counter - 1, + ctrs, events); + if (n < 0) + return NULL; + } + events[n] = ev; + ctrs[n] = counter; + if (check_excludes(ctrs, n, 1)) + return NULL; + if (power_check_constraints(events, n + 1)) + return NULL; + + counter->hw.config = events[n]; + atomic64_set(&counter->hw.period_left, counter->hw_event.irq_period); + return &power_perf_ops; +} + +/* + * Handle wakeups. + */ +void perf_counter_do_pending(void) +{ + int i; + struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters); + struct perf_counter *counter; + + set_perf_counter_pending(0); + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (counter && counter->wakeup_pending) { + counter->wakeup_pending = 0; + wake_up(&counter->waitq); + } + } +} + +/* + * Record data for an irq counter. + * This function was lifted from the x86 code; maybe it should + * go in the core? + */ +static void perf_store_irq_data(struct perf_counter *counter, u64 data) +{ + struct perf_data *irqdata = counter->irqdata; + + if (irqdata->len > PERF_DATA_BUFLEN - sizeof(u64)) { + irqdata->overrun++; + } else { + u64 *p = (u64 *) &irqdata->data[irqdata->len]; + + *p = data; + irqdata->len += sizeof(u64); + } +} + +/* + * Record all the values of the counters in a group + */ +static void perf_handle_group(struct perf_counter *counter) +{ + struct perf_counter *leader, *sub; + + leader = counter->group_leader; + list_for_each_entry(sub, &leader->sibling_list, list_entry) { + if (sub != counter) + sub->hw_ops->read(sub); + perf_store_irq_data(counter, sub->hw_event.type); + perf_store_irq_data(counter, atomic64_read(&sub->count)); + } +} + +/* + * A counter has overflowed; update its count and record + * things if requested. Note that interrupts are hard-disabled + * here so there is no possibility of being interrupted. + */ +static void record_and_restart(struct perf_counter *counter, long val, + struct pt_regs *regs) +{ + s64 prev, delta, left; + int record = 0; + + /* we don't have to worry about interrupts here */ + prev = atomic64_read(&counter->hw.prev_count); + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &counter->count); + + /* + * See if the total period for this counter has expired, + * and update for the next period. + */ + val = 0; + left = atomic64_read(&counter->hw.period_left) - delta; + if (counter->hw_event.irq_period) { + if (left <= 0) { + left += counter->hw_event.irq_period; + if (left <= 0) + left = counter->hw_event.irq_period; + record = 1; + } + if (left < 0x80000000L) + val = 0x80000000L - left; + } + write_pmc(counter->hw.idx, val); + atomic64_set(&counter->hw.prev_count, val); + atomic64_set(&counter->hw.period_left, left); + + /* + * Finally record data if requested. + */ + if (record) { + switch (counter->hw_event.record_type) { + case PERF_RECORD_SIMPLE: + break; + case PERF_RECORD_IRQ: + perf_store_irq_data(counter, instruction_pointer(regs)); + counter->wakeup_pending = 1; + break; + case PERF_RECORD_GROUP: + perf_handle_group(counter); + counter->wakeup_pending = 1; + break; + } + } +} + +/* + * Performance monitor interrupt stuff + */ +static void perf_counter_interrupt(struct pt_regs *regs) +{ + int i; + struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters); + struct perf_counter *counter; + long val; + int need_wakeup = 0, found = 0; + + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + val = read_pmc(counter->hw.idx); + if ((int)val < 0) { + /* counter has overflowed */ + found = 1; + record_and_restart(counter, val, regs); + if (counter->wakeup_pending) + need_wakeup = 1; + } + } + + /* + * In case we didn't find and reset the counter that caused + * the interrupt, scan all counters and reset any that are + * negative, to avoid getting continual interrupts. + * Any that we processed in the previous loop will not be negative. + */ + if (!found) { + for (i = 0; i < ppmu->n_counter; ++i) { + val = read_pmc(i + 1); + if ((int)val < 0) + write_pmc(i + 1, 0); + } + } + + /* + * Reset MMCR0 to its normal value. This will set PMXE and + * clear FC (freeze counters) and PMAO (perf mon alert occurred) + * and thus allow interrupts to occur again. + * XXX might want to use MSR.PM to keep the counters frozen until + * we get back out of this interrupt. + */ + mtspr(SPRN_MMCR0, cpuhw->mmcr[0]); + + /* + * If we need a wakeup, check whether interrupts were soft-enabled + * when we took the interrupt. If they were, we can wake stuff up + * immediately; otherwise we'll have to set a flag and do the + * wakeup when interrupts get soft-enabled. + */ + if (need_wakeup) { + if (regs->softe) { + irq_enter(); + perf_counter_do_pending(); + irq_exit(); + } else { + set_perf_counter_pending(1); + } + } +} + +void hw_perf_counter_setup(int cpu) +{ + struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu); + + memset(cpuhw, 0, sizeof(*cpuhw)); + cpuhw->mmcr[0] = MMCR0_FC; +} + +extern struct power_pmu power4_pmu; +extern struct power_pmu ppc970_pmu; +extern struct power_pmu power5_pmu; +extern struct power_pmu power5p_pmu; +extern struct power_pmu power6_pmu; + +static int init_perf_counters(void) +{ + unsigned long pvr; + + if (reserve_pmc_hardware(perf_counter_interrupt)) { + printk(KERN_ERR "Couldn't init performance monitor subsystem\n"); + return -EBUSY; + } + + /* XXX should get this from cputable */ + pvr = mfspr(SPRN_PVR); + switch (PVR_VER(pvr)) { + case PV_POWER4: + case PV_POWER4p: + ppmu = &power4_pmu; + break; + case PV_970: + case PV_970FX: + case PV_970MP: + ppmu = &ppc970_pmu; + break; + case PV_POWER5: + ppmu = &power5_pmu; + break; + case PV_POWER5p: + ppmu = &power5p_pmu; + break; + case 0x3e: + ppmu = &power6_pmu; + break; + } + + /* + * Use FCHV to ignore kernel events if MSR.HV is set. + */ + if (mfmsr() & MSR_HV) + freeze_counters_kernel = MMCR0_FCHV; + + return 0; +} + +arch_initcall(init_perf_counters); diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c new file mode 100644 index 0000000..1407b19 --- /dev/null +++ b/arch/powerpc/kernel/power4-pmu.c @@ -0,0 +1,557 @@ +/* + * Performance counter support for POWER4 (GP) and POWER4+ (GQ) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER4 + */ +#define PM_PMC_SH 12 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_UNIT_SH 8 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_LOWER_SH 6 +#define PM_LOWER_MSK 1 +#define PM_LOWER_MSKS 0x40 +#define PM_BYTE_SH 4 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_PMCSEL_MSK 7 + +/* + * Unit code values + */ +#define PM_FPU 1 +#define PM_ISU1 2 +#define PM_IFU 3 +#define PM_IDU0 4 +#define PM_ISU1_ALT 6 +#define PM_ISU2 7 +#define PM_IFU_ALT 8 +#define PM_LSU0 9 +#define PM_LSU1 0xc +#define PM_GPS 0xf + +/* + * Bits in MMCR0 for POWER4 + */ +#define MMCR0_PMC1SEL_SH 8 +#define MMCR0_PMC2SEL_SH 1 +#define MMCR_PMCSEL_MSK 0x1f + +/* + * Bits in MMCR1 for POWER4 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTC0SEL_SH 61 +#define MMCR1_TTM1SEL_SH 59 +#define MMCR1_TTC1SEL_SH 58 +#define MMCR1_TTM2SEL_SH 56 +#define MMCR1_TTC2SEL_SH 55 +#define MMCR1_TTM3SEL_SH 53 +#define MMCR1_TTC3SEL_SH 52 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 50 +#define MMCR1_TD_CP_DBG1SEL_SH 48 +#define MMCR1_TD_CP_DBG2SEL_SH 46 +#define MMCR1_TD_CP_DBG3SEL_SH 44 +#define MMCR1_DEBUG0SEL_SH 43 +#define MMCR1_DEBUG1SEL_SH 42 +#define MMCR1_DEBUG2SEL_SH 41 +#define MMCR1_DEBUG3SEL_SH 40 +#define MMCR1_PMC1_ADDER_SEL_SH 39 +#define MMCR1_PMC2_ADDER_SEL_SH 38 +#define MMCR1_PMC6_ADDER_SEL_SH 37 +#define MMCR1_PMC5_ADDER_SEL_SH 36 +#define MMCR1_PMC8_ADDER_SEL_SH 35 +#define MMCR1_PMC7_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC3SEL_SH 27 +#define MMCR1_PMC4SEL_SH 22 +#define MMCR1_PMC5SEL_SH 17 +#define MMCR1_PMC6SEL_SH 12 +#define MMCR1_PMC7SEL_SH 7 +#define MMCR1_PMC8SEL_SH 2 /* note bit 0 is in MMCRA for GP */ + +static short mmcr1_adder_bits[8] = { + MMCR1_PMC1_ADDER_SEL_SH, + MMCR1_PMC2_ADDER_SEL_SH, + MMCR1_PMC3_ADDER_SEL_SH, + MMCR1_PMC4_ADDER_SEL_SH, + MMCR1_PMC5_ADDER_SEL_SH, + MMCR1_PMC6_ADDER_SEL_SH, + MMCR1_PMC7_ADDER_SEL_SH, + MMCR1_PMC8_ADDER_SEL_SH +}; + +/* + * Bits in MMCRA + */ +#define MMCRA_PMC8SEL0_SH 17 /* PMC8SEL bit 0 for GP */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * |[ >[ >[ >|||[ >[ >< >< >< >< ><><><><><><><><> + * | UC1 UC2 UC3 ||| PS1 PS2 B0 B1 B2 B3 P1P2P3P4P5P6P7P8 + * \SMPL ||\TTC3SEL + * |\TTC_IFU_SEL + * \TTM2SEL0 + * + * SMPL - SAMPLE_ENABLE constraint + * 56: SAMPLE_ENABLE value 0x0100_0000_0000_0000 + * + * UC1 - unit constraint 1: can't have all three of FPU/ISU1/IDU0|ISU2 + * 55: UC1 error 0x0080_0000_0000_0000 + * 54: FPU events needed 0x0040_0000_0000_0000 + * 53: ISU1 events needed 0x0020_0000_0000_0000 + * 52: IDU0|ISU2 events needed 0x0010_0000_0000_0000 + * + * UC2 - unit constraint 2: can't have all three of FPU/IFU/LSU0 + * 51: UC2 error 0x0008_0000_0000_0000 + * 50: FPU events needed 0x0004_0000_0000_0000 + * 49: IFU events needed 0x0002_0000_0000_0000 + * 48: LSU0 events needed 0x0001_0000_0000_0000 + * + * UC3 - unit constraint 3: can't have all four of LSU0/IFU/IDU0|ISU2/ISU1 + * 47: UC3 error 0x8000_0000_0000 + * 46: LSU0 events needed 0x4000_0000_0000 + * 45: IFU events needed 0x2000_0000_0000 + * 44: IDU0|ISU2 events needed 0x1000_0000_0000 + * 43: ISU1 events needed 0x0800_0000_0000 + * + * TTM2SEL0 + * 42: 0 = IDU0 events needed + * 1 = ISU2 events needed 0x0400_0000_0000 + * + * TTC_IFU_SEL + * 41: 0 = IFU.U events needed + * 1 = IFU.L events needed 0x0200_0000_0000 + * + * TTC3SEL + * 40: 0 = LSU1.U events needed + * 1 = LSU1.L events needed 0x0100_0000_0000 + * + * PS1 + * 39: PS1 error 0x0080_0000_0000 + * 36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000 + * + * PS2 + * 35: PS2 error 0x0008_0000_0000 + * 32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000 + * + * B0 + * 28-31: Byte 0 event source 0xf000_0000 + * 1 = FPU + * 2 = ISU1 + * 3 = IFU + * 4 = IDU0 + * 7 = ISU2 + * 9 = LSU0 + * c = LSU1 + * f = GPS + * + * B1, B2, B3 + * 24-27, 20-23, 16-19: Byte 1, 2, 3 event sources + * + * P8 + * 15: P8 error 0x8000 + * 14-15: Count of events needing PMC8 + * + * P1..P7 + * 0-13: Count of events needing PMC1..PMC7 + * + * Note: this doesn't allow events using IFU.U to be combined with events + * using IFU.L, though that is feasible (using TTM0 and TTM2). However + * there are no listed events for IFU.L (they are debug events not + * verified for performance monitoring) so this shouldn't cause a + * problem. + */ + +static struct unitinfo { + u64 value, mask; + int unit; + int lowerbit; +} p4_unitinfo[16] = { + [PM_FPU] = { 0x44000000000000ull, 0x88000000000000ull, PM_FPU, 0 }, + [PM_ISU1] = { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 }, + [PM_ISU1_ALT] = + { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 }, + [PM_IFU] = { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 }, + [PM_IFU_ALT] = + { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 }, + [PM_IDU0] = { 0x10100000000000ull, 0x80840000000000ull, PM_IDU0, 1 }, + [PM_ISU2] = { 0x10140000000000ull, 0x80840000000000ull, PM_ISU2, 0 }, + [PM_LSU0] = { 0x01400000000000ull, 0x08800000000000ull, PM_LSU0, 0 }, + [PM_LSU1] = { 0x00000000000000ull, 0x00010000000000ull, PM_LSU1, 40 }, + [PM_GPS] = { 0x00000000000000ull, 0x00000000000000ull, PM_GPS, 0 } +}; + +static unsigned char direct_marked_event[8] = { + (1<<2) | (1<<3), /* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */ + (1<<3) | (1<<5), /* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */ + (1<<3), /* PMC3: PM_MRK_ST_CMPL_INT */ + (1<<4) | (1<<5), /* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */ + (1<<4) | (1<<5), /* PMC5: PM_MRK_GRP_TIMEO */ + (1<<3) | (1<<4) | (1<<5), + /* PMC6: PM_MRK_ST_GPS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */ + (1<<4) | (1<<5), /* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */ + (1<<4), /* PMC8: PM_MRK_LSU_FIN */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int p4_marked_instr_event(unsigned int event) +{ + int pmc, psel, unit, byte, bit; + unsigned int mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc) { + if (direct_marked_event[pmc - 1] & (1 << psel)) + return 1; + if (psel == 0) /* add events */ + bit = (pmc <= 4)? pmc - 1: 8 - pmc; + else if (psel == 6) /* decode events */ + bit = 4; + else + return 0; + } else + bit = psel; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + mask = 0; + switch (unit) { + case PM_LSU1: + if (event & PM_LOWER_MSKS) + mask = 1 << 28; /* byte 7 bit 4 */ + else + mask = 6 << 24; /* byte 3 bits 1 and 2 */ + break; + case PM_LSU0: + /* byte 3, bit 3; byte 2 bits 0,2,3,4,5; byte 1 */ + mask = 0x083dff00; + } + return (mask >> (byte * 8 + bit)) & 1; +} + +static int p4_get_constraint(unsigned int event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, lower, sh; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 8) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + grp = ((pmc - 1) >> 1) & 1; + } + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit) { + lower = (event >> PM_LOWER_SH) & PM_LOWER_MSK; + + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8. + */ + if (!pmc) + grp = byte & 1; + + if (!p4_unitinfo[unit].unit) + return -1; + mask |= p4_unitinfo[unit].mask; + value |= p4_unitinfo[unit].value; + sh = p4_unitinfo[unit].lowerbit; + if (sh > 1) + value |= (u64)lower << sh; + else if (lower != sh) + return -1; + unit = p4_unitinfo[unit].unit; + + /* Set byte lane select field */ + mask |= 0xfULL << (28 - 4 * byte); + value |= (u64)unit << (28 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2/5/6 field */ + mask |= 0x8000000000ull; + value |= 0x1000000000ull; + } else { + /* increment PMC3/4/7/8 field */ + mask |= 0x800000000ull; + value |= 0x100000000ull; + } + + /* Marked instruction events need sample_enable set */ + if (p4_marked_instr_event(event)) { + mask |= 1ull << 56; + value |= 1ull << 56; + } + + /* PMCSEL=6 decode events on byte 2 need sample_enable clear */ + if (pmc && (event & PM_PMCSEL_MSK) == 6 && byte == 2) + mask |= 1ull << 56; + + *maskp = mask; + *valp = value; + return 0; +} + +static unsigned int ppc_inst_cmpl[] = { + 0x1001, 0x4001, 0x6001, 0x7001, 0x8001 +}; + +static int p4_get_alternatives(unsigned int event, unsigned int alt[]) +{ + int i, j, na; + + alt[0] = event; + na = 1; + + /* 2 possibilities for PM_GRP_DISP_REJECT */ + if (event == 0x8003 || event == 0x0224) { + alt[1] = event ^ (0x8003 ^ 0x0224); + return 2; + } + + /* 2 possibilities for PM_ST_MISS_L1 */ + if (event == 0x0c13 || event == 0x0c23) { + alt[1] = event ^ (0x0c13 ^ 0x0c23); + return 2; + } + + /* several possibilities for PM_INST_CMPL */ + for (i = 0; i < ARRAY_SIZE(ppc_inst_cmpl); ++i) { + if (event == ppc_inst_cmpl[i]) { + for (j = 0; j < ARRAY_SIZE(ppc_inst_cmpl); ++j) + if (j != i) + alt[na++] = ppc_inst_cmpl[j]; + break; + } + } + + return na; +} + +static int p4_compute_mmcr(unsigned int event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0; + unsigned int pmc, unit, byte, psel, lower; + unsigned int ttm, grp; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + unsigned int unitlower = 0; + int i; + + if (n_ev > 8) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2/5/6 vs 3/4/7/8 use */ + ++pmc_grp_use[((pmc - 1) >> 1) & 1]; + } + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + lower = (event[i] >> PM_LOWER_SH) & PM_LOWER_MSK; + if (unit) { + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (unit == 6 || unit == 8) + /* map alt ISU1/IFU codes: 6->2, 8->3 */ + unit = (unit >> 1) - 1; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + lower <<= unit; + if (unituse[unit] && lower != (unitlower & lower)) + return -1; + unituse[unit] = 1; + unitlower |= lower; + } + } + if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * Units 1,2,3 are on TTM0, 4,6,7 on TTM1, 8,10 on TTM2. + * Each TTMx can only select one unit, but since + * units 2 and 6 are both ISU1, and 3 and 8 are both IFU, + * we have some choices. + */ + if (unituse[2] & (unituse[1] | (unituse[3] & unituse[9]))) { + unituse[6] = 1; /* Move 2 to 6 */ + unituse[2] = 0; + } + if (unituse[3] & (unituse[1] | unituse[2])) { + unituse[8] = 1; /* Move 3 to 8 */ + unituse[3] = 0; + unitlower = (unitlower & ~8) | ((unitlower & 8) << 5); + } + /* Check only one unit per TTMx */ + if (unituse[1] + unituse[2] + unituse[3] > 1 || + unituse[4] + unituse[6] + unituse[7] > 1 || + unituse[8] + unituse[9] > 1 || + (unituse[5] | unituse[10] | unituse[11] | + unituse[13] | unituse[14])) + return -1; + + /* Set TTMxSEL fields. Note, units 1-3 => TTM0SEL codes 0-2 */ + mmcr1 |= (u64)(unituse[3] * 2 + unituse[2]) << MMCR1_TTM0SEL_SH; + mmcr1 |= (u64)(unituse[7] * 3 + unituse[6] * 2) << MMCR1_TTM1SEL_SH; + mmcr1 |= (u64)unituse[9] << MMCR1_TTM2SEL_SH; + + /* Set TTCxSEL fields. */ + if (unitlower & 0xe) + mmcr1 |= 1ull << MMCR1_TTC0SEL_SH; + if (unitlower & 0xf0) + mmcr1 |= 1ull << MMCR1_TTC1SEL_SH; + if (unitlower & 0xf00) + mmcr1 |= 1ull << MMCR1_TTC2SEL_SH; + if (unitlower & 0x7000) + mmcr1 |= 1ull << MMCR1_TTC3SEL_SH; + + /* Set byte lane select fields. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == 0xf) { + /* special case for GPS */ + mmcr1 |= 1ull << (MMCR1_DEBUG0SEL_SH - byte); + } else { + if (!unituse[unit]) + ttm = unit - 1; /* 2->1, 3->2 */ + else + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2*byte); + } + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + if (!pmc) { + /* Bus event or 00xxx direct event (off or cycles) */ + if (unit) + psel |= 0x10 | ((byte & 2) << 2); + for (pmc = 0; pmc < 8; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (unit) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 4) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else { + /* Direct event */ + --pmc; + if (psel == 0 && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << mmcr1_adder_bits[pmc]; + else if (psel == 6 && byte == 3) + /* seem to need to set sample_enable here */ + mmcra |= MMCRA_SAMPLE_ENABLE; + psel |= 8; + } + if (pmc <= 1) + mmcr0 |= psel << (MMCR0_PMC1SEL_SH - 7 * pmc); + else + mmcr1 |= psel << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)); + if (pmc == 7) /* PMC8 */ + mmcra |= (psel & 1) << MMCRA_PMC8SEL0_SH; + hwc[i] = pmc; + if (p4_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + } + + if (pmc_inuse & 1) + mmcr0 |= MMCR0_PMC1CE; + if (pmc_inuse & 0xfe) + mmcr0 |= MMCR0_PMCjCE; + + mmcra |= 0x2000; /* mark only one IOP per PPC instruction */ + + /* Return MMCRx values */ + mmcr[0] = mmcr0; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void p4_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + /* + * Setting the PMCxSEL field to 0 disables PMC x. + * (Note that pmc is 0-based here, not 1-based.) + */ + if (pmc <= 1) { + mmcr[0] &= ~(0x1fUL << (MMCR0_PMC1SEL_SH - 7 * pmc)); + } else { + mmcr[1] &= ~(0x1fUL << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2))); + if (pmc == 7) + mmcr[2] &= ~(1UL << MMCRA_PMC8SEL0_SH); + } +} + +static int p4_generic_events[] = { + [PERF_COUNT_CPU_CYCLES] = 7, + [PERF_COUNT_INSTRUCTIONS] = 0x1001, + [PERF_COUNT_CACHE_REFERENCES] = 0x8c10, /* PM_LD_REF_L1 */ + [PERF_COUNT_CACHE_MISSES] = 0x3c10, /* PM_LD_MISS_L1 */ + [PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x330, /* PM_BR_ISSUED */ + [PERF_COUNT_BRANCH_MISSES] = 0x331, /* PM_BR_MPRED_CR */ +}; + +struct power_pmu power4_pmu = { + .n_counter = 8, + .max_alternatives = 5, + .add_fields = 0x0000001100005555ull, + .test_adder = 0x0011083300000000ull, + .compute_mmcr = p4_compute_mmcr, + .get_constraint = p4_get_constraint, + .get_alternatives = p4_get_alternatives, + .disable_pmc = p4_disable_pmc, + .n_generic = ARRAY_SIZE(p4_generic_events), + .generic_events = p4_generic_events, +}; diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c new file mode 100644 index 0000000..cec21ea --- /dev/null +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -0,0 +1,452 @@ +/* + * Performance counter support for POWER5 (not POWER5++) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3) + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_BYTE_SH 12 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 7 +#define PM_GRS_SH 8 /* Storage subsystem mux select */ +#define PM_GRS_MSK 7 +#define PM_BUSEVENT_MSK 0x80 /* Set if event uses event bus */ +#define PM_PMCSEL_MSK 0x7f + +/* Values in PM_UNIT field */ +#define PM_FPU 0 +#define PM_ISU0 1 +#define PM_IFU 2 +#define PM_ISU1 3 +#define PM_IDU 4 +#define PM_ISU0_ALT 6 +#define PM_GRS 7 +#define PM_LSU0 8 +#define PM_LSU1 0xc +#define PM_LASTUNIT 0xc + +/* + * Bits in MMCR1 for POWER5+ + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 60 +#define MMCR1_TTM2SEL_SH 58 +#define MMCR1_TTM3SEL_SH 56 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 54 +#define MMCR1_TD_CP_DBG1SEL_SH 52 +#define MMCR1_TD_CP_DBG2SEL_SH 50 +#define MMCR1_TD_CP_DBG3SEL_SH 48 +#define MMCR1_GRS_L2SEL_SH 46 +#define MMCR1_GRS_L2SEL_MSK 3 +#define MMCR1_GRS_L3SEL_SH 44 +#define MMCR1_GRS_L3SEL_MSK 3 +#define MMCR1_GRS_MCSEL_SH 41 +#define MMCR1_GRS_MCSEL_MSK 7 +#define MMCR1_GRS_FABSEL_SH 39 +#define MMCR1_GRS_FABSEL_MSK 3 +#define MMCR1_PMC1_ADDER_SEL_SH 35 +#define MMCR1_PMC2_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC1SEL_SH 25 +#define MMCR1_PMC2SEL_SH 17 +#define MMCR1_PMC3SEL_SH 9 +#define MMCR1_PMC4SEL_SH 1 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0x7f + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * [ ><><>< ><> <><>[ > < >< >< >< ><><><><> + * NC G0G1G2 G3 T0T1 UC B0 B1 B2 B3 P4P3P2P1 + * + * NC - number of counters + * 51: NC error 0x0008_0000_0000_0000 + * 48-50: number of events needing PMC1-4 0x0007_0000_0000_0000 + * + * G0..G3 - GRS mux constraints + * 46-47: GRS_L2SEL value + * 44-45: GRS_L3SEL value + * 41-44: GRS_MCSEL value + * 39-40: GRS_FABSEL value + * Note that these match up with their bit positions in MMCR1 + * + * T0 - TTM0 constraint + * 36-37: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0x30_0000_0000 + * + * T1 - TTM1 constraint + * 34-35: TTM1SEL value (0=IDU, 3=GRS) 0x0c_0000_0000 + * + * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS + * 33: UC3 error 0x02_0000_0000 + * 32: FPU|IFU|ISU1 events needed 0x01_0000_0000 + * 31: ISU0 events needed 0x01_8000_0000 + * 30: IDU|GRS events needed 0x00_4000_0000 + * + * B0 + * 20-23: Byte 0 event source 0x00f0_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 16-19, 12-15, 8-11: Byte 1, 2, 3 event sources + * + * P4 + * 7: P1 error 0x80 + * 6-7: Count of events needing PMC4 + * + * P1..P3 + * 0-6: Count of events needing PMC1..PMC3 + */ + +static const int grsel_shift[8] = { + MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, + MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, + MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH +}; + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0x3200000000ull, 0x0100000000ull }, + [PM_ISU0] = { 0x0200000000ull, 0x0080000000ull }, + [PM_ISU1] = { 0x3200000000ull, 0x3100000000ull }, + [PM_IFU] = { 0x3200000000ull, 0x2100000000ull }, + [PM_IDU] = { 0x0e00000000ull, 0x0040000000ull }, + [PM_GRS] = { 0x0e00000000ull, 0x0c40000000ull }, +}; + +static int power5p_get_constraint(unsigned int event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh; + int bit, fmask; + u64 mask = 0, value = 0; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 4) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + } + if (event & PM_BUSEVENT_MSK) { + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + /* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */ + ++unit; + byte &= 3; + } + if (unit == PM_GRS) { + bit = event & 7; + fmask = (bit == 6)? 7: 3; + sh = grsel_shift[bit]; + mask |= (u64)fmask << sh; + value |= (u64)((event >> PM_GRS_SH) & fmask) << sh; + } + /* Set byte lane select field */ + mask |= 0xfULL << (20 - 4 * byte); + value |= (u64)unit << (20 - 4 * byte); + } + mask |= 0x8000000000000ull; + value |= 0x1000000000000ull; + *maskp = mask; + *valp = value; + return 0; +} + +#define MAX_ALT 3 /* at most 3 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x100c0, 0x40001f }, /* PM_GCT_FULL_CYC */ + { 0x120e4, 0x400002 }, /* PM_GRP_DISP_REJECT */ + { 0x230e2, 0x323087 }, /* PM_BR_PRED_CR */ + { 0x230e3, 0x223087, 0x3230a0 }, /* PM_BR_PRED_TA */ + { 0x410c7, 0x441084 }, /* PM_THRD_L2MISS_BOTH_CYC */ + { 0x800c4, 0xc20e0 }, /* PM_DTLB_MISS */ + { 0xc50c6, 0xc60e0 }, /* PM_MRK_DTLB_MISS */ + { 0x100009, 0x200009 }, /* PM_INST_CMPL */ + { 0x200015, 0x300015 }, /* PM_LSU_LMQ_SRQ_EMPTY_CYC */ + { 0x300009, 0x400009 }, /* PM_INST_DISP */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(unsigned int event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static const unsigned char bytedecode_alternatives[4][4] = { + /* PMC 1 */ { 0x21, 0x23, 0x25, 0x27 }, + /* PMC 2 */ { 0x07, 0x17, 0x0e, 0x1e }, + /* PMC 3 */ { 0x20, 0x22, 0x24, 0x26 }, + /* PMC 4 */ { 0x07, 0x17, 0x0e, 0x1e } +}; + +/* + * Some direct events for decodes of event bus byte 3 have alternative + * PMCSEL values on other counters. This returns the alternative + * event code for those that do, or -1 otherwise. This also handles + * alternative PCMSEL values for add events. + */ +static int find_alternative_bdecode(unsigned int event) +{ + int pmc, altpmc, pp, j; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc == 0 || pmc > 4) + return -1; + altpmc = 5 - pmc; /* 1 <-> 4, 2 <-> 3 */ + pp = event & PM_PMCSEL_MSK; + for (j = 0; j < 4; ++j) { + if (bytedecode_alternatives[pmc - 1][j] == pp) { + return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) | + (altpmc << PM_PMC_SH) | + bytedecode_alternatives[altpmc - 1][j]; + } + } + + /* new decode alternatives for power5+ */ + if (pmc == 1 && (pp == 0x0d || pp == 0x0e)) + return event + (2 << PM_PMC_SH) + (0x2e - 0x0d); + if (pmc == 3 && (pp == 0x2e || pp == 0x2f)) + return event - (2 << PM_PMC_SH) - (0x2e - 0x0d); + + /* alternative add event encodings */ + if (pp == 0x10 || pp == 0x28) + return ((event ^ (0x10 ^ 0x28)) & ~PM_PMC_MSKS) | + (altpmc << PM_PMC_SH); + + return -1; +} + +static int power5p_get_alternatives(unsigned int event, unsigned int alt[]) +{ + int i, j, ae, nalt = 1; + + alt[0] = event; + nalt = 1; + i = find_alternative(event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != event) + alt[nalt++] = ae; + } + } else { + ae = find_alternative_bdecode(event); + if (ae > 0) + alt[nalt++] = ae; + } + return nalt; +} + +static int power5p_compute_mmcr(unsigned int event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm; + int i, isbus, bit, grsel; + unsigned int pmc_inuse = 0; + unsigned char busbyte[4]; + unsigned char unituse[16]; + int ttmuse; + + if (n_ev > 4) + return -1; + + /* First pass to count resource use */ + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 4) + return -1; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + } + if (event[i] & PM_BUSEVENT_MSK) { + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + ++unit; + byte &= 3; + } + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU0 can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU0] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) { + unituse[PM_ISU0_ALT] = 1; /* move ISU to TTM1 */ + unituse[PM_ISU0] = 0; + } + /* Set TTM[01]SEL fields. */ + ttmuse = 0; + for (i = PM_FPU; i <= PM_ISU1; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH; + } + ttmuse = 0; + for (; i <= PM_GRS; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH; + } + if (ttmuse > 1) + return -1; + + /* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) { + /* get ISU0 through TTM1 rather than TTM0 */ + unit = PM_ISU0_ALT; + } else if (unit == PM_LSU1 + 1) { + /* select lower word of LSU1 for this byte */ + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + isbus = event[i] & PM_BUSEVENT_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + for (pmc = 0; pmc < 4; ++pmc) { + if (!(pmc_inuse & (1 << pmc))) + break; + } + if (pmc >= 4) + return -1; + pmc_inuse |= 1 << pmc; + } else { + /* Direct event */ + --pmc; + if (isbus && (byte & 2) && + (psel == 8 || psel == 0x10 || psel == 0x28)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc); + } + if (isbus && unit == PM_GRS) { + bit = psel & 7; + grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK; + mmcr1 |= (u64)grsel << grsel_shift[bit]; + } + if ((psel & 0x58) == 0x40 && (byte & 1) != ((pmc >> 1) & 1)) + /* select alternate byte lane */ + psel |= 0x10; + if (pmc <= 3) + mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc); + hwc[i] = pmc; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = 0; + return 0; +} + +static void power5p_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power5p_generic_events[] = { + [PERF_COUNT_CPU_CYCLES] = 0xf, + [PERF_COUNT_INSTRUCTIONS] = 0x100009, + [PERF_COUNT_CACHE_REFERENCES] = 0x1c10a8, /* LD_REF_L1 */ + [PERF_COUNT_CACHE_MISSES] = 0x3c1088, /* LD_MISS_L1 */ + [PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x230e4, /* BR_ISSUED */ + [PERF_COUNT_BRANCH_MISSES] = 0x230e5, /* BR_MPRED_CR */ +}; + +struct power_pmu power5p_pmu = { + .n_counter = 4, + .max_alternatives = MAX_ALT, + .add_fields = 0x7000000000055ull, + .test_adder = 0x3000040000000ull, + .compute_mmcr = power5p_compute_mmcr, + .get_constraint = power5p_get_constraint, + .get_alternatives = power5p_get_alternatives, + .disable_pmc = power5p_disable_pmc, + .n_generic = ARRAY_SIZE(power5p_generic_events), + .generic_events = power5p_generic_events, +}; diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c new file mode 100644 index 0000000..379ed10 --- /dev/null +++ b/arch/powerpc/kernel/power5-pmu.c @@ -0,0 +1,475 @@ +/* + * Performance counter support for POWER5 (not POWER5++) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER5 (not POWER5++) + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_BYTE_SH 12 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 7 +#define PM_GRS_SH 8 /* Storage subsystem mux select */ +#define PM_GRS_MSK 7 +#define PM_BUSEVENT_MSK 0x80 /* Set if event uses event bus */ +#define PM_PMCSEL_MSK 0x7f + +/* Values in PM_UNIT field */ +#define PM_FPU 0 +#define PM_ISU0 1 +#define PM_IFU 2 +#define PM_ISU1 3 +#define PM_IDU 4 +#define PM_ISU0_ALT 6 +#define PM_GRS 7 +#define PM_LSU0 8 +#define PM_LSU1 0xc +#define PM_LASTUNIT 0xc + +/* + * Bits in MMCR1 for POWER5 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 60 +#define MMCR1_TTM2SEL_SH 58 +#define MMCR1_TTM3SEL_SH 56 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 54 +#define MMCR1_TD_CP_DBG1SEL_SH 52 +#define MMCR1_TD_CP_DBG2SEL_SH 50 +#define MMCR1_TD_CP_DBG3SEL_SH 48 +#define MMCR1_GRS_L2SEL_SH 46 +#define MMCR1_GRS_L2SEL_MSK 3 +#define MMCR1_GRS_L3SEL_SH 44 +#define MMCR1_GRS_L3SEL_MSK 3 +#define MMCR1_GRS_MCSEL_SH 41 +#define MMCR1_GRS_MCSEL_MSK 7 +#define MMCR1_GRS_FABSEL_SH 39 +#define MMCR1_GRS_FABSEL_MSK 3 +#define MMCR1_PMC1_ADDER_SEL_SH 35 +#define MMCR1_PMC2_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC1SEL_SH 25 +#define MMCR1_PMC2SEL_SH 17 +#define MMCR1_PMC3SEL_SH 9 +#define MMCR1_PMC4SEL_SH 1 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0x7f + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * <><>[ ><><>< ><> [ >[ >[ >< >< >< >< ><><><><><><> + * T0T1 NC G0G1G2 G3 UC PS1PS2 B0 B1 B2 B3 P6P5P4P3P2P1 + * + * T0 - TTM0 constraint + * 54-55: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0xc0_0000_0000_0000 + * + * T1 - TTM1 constraint + * 52-53: TTM1SEL value (0=IDU, 3=GRS) 0x30_0000_0000_0000 + * + * NC - number of counters + * 51: NC error 0x0008_0000_0000_0000 + * 48-50: number of events needing PMC1-4 0x0007_0000_0000_0000 + * + * G0..G3 - GRS mux constraints + * 46-47: GRS_L2SEL value + * 44-45: GRS_L3SEL value + * 41-44: GRS_MCSEL value + * 39-40: GRS_FABSEL value + * Note that these match up with their bit positions in MMCR1 + * + * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS + * 37: UC3 error 0x20_0000_0000 + * 36: FPU|IFU|ISU1 events needed 0x10_0000_0000 + * 35: ISU0 events needed 0x08_0000_0000 + * 34: IDU|GRS events needed 0x04_0000_0000 + * + * PS1 + * 33: PS1 error 0x2_0000_0000 + * 31-32: count of events needing PMC1/2 0x1_8000_0000 + * + * PS2 + * 30: PS2 error 0x4000_0000 + * 28-29: count of events needing PMC3/4 0x3000_0000 + * + * B0 + * 24-27: Byte 0 event source 0x0f00_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 20-23, 16-19, 12-15: Byte 1, 2, 3 event sources + * + * P1..P6 + * 0-11: Count of events needing PMC1..PMC6 + */ + +static const int grsel_shift[8] = { + MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, + MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, + MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH +}; + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0xc0002000000000ull, 0x00001000000000ull }, + [PM_ISU0] = { 0x00002000000000ull, 0x00000800000000ull }, + [PM_ISU1] = { 0xc0002000000000ull, 0xc0001000000000ull }, + [PM_IFU] = { 0xc0002000000000ull, 0x80001000000000ull }, + [PM_IDU] = { 0x30002000000000ull, 0x00000400000000ull }, + [PM_GRS] = { 0x30002000000000ull, 0x30000400000000ull }, +}; + +static int power5_get_constraint(unsigned int event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh; + int bit, fmask; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + if (pmc <= 4) + grp = (pmc - 1) >> 1; + else if (event != 0x500009 && event != 0x600005) + return -1; + } + if (event & PM_BUSEVENT_MSK) { + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + /* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */ + ++unit; + byte &= 3; + } + if (unit == PM_GRS) { + bit = event & 7; + fmask = (bit == 6)? 7: 3; + sh = grsel_shift[bit]; + mask |= (u64)fmask << sh; + value |= (u64)((event >> PM_GRS_SH) & fmask) << sh; + } + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2; bytes 1 and 3 on PMC3/4. + */ + if (!pmc) + grp = byte & 1; + /* Set byte lane select field */ + mask |= 0xfULL << (24 - 4 * byte); + value |= (u64)unit << (24 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2 field */ + mask |= 0x200000000ull; + value |= 0x080000000ull; + } else if (grp == 1) { + /* increment PMC3/4 field */ + mask |= 0x40000000ull; + value |= 0x10000000ull; + } + if (pmc < 5) { + /* need a counter from PMC1-4 set */ + mask |= 0x8000000000000ull; + value |= 0x1000000000000ull; + } + *maskp = mask; + *valp = value; + return 0; +} + +#define MAX_ALT 3 /* at most 3 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x120e4, 0x400002 }, /* PM_GRP_DISP_REJECT */ + { 0x410c7, 0x441084 }, /* PM_THRD_L2MISS_BOTH_CYC */ + { 0x100005, 0x600005 }, /* PM_RUN_CYC */ + { 0x100009, 0x200009, 0x500009 }, /* PM_INST_CMPL */ + { 0x300009, 0x400009 }, /* PM_INST_DISP */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(unsigned int event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static const unsigned char bytedecode_alternatives[4][4] = { + /* PMC 1 */ { 0x21, 0x23, 0x25, 0x27 }, + /* PMC 2 */ { 0x07, 0x17, 0x0e, 0x1e }, + /* PMC 3 */ { 0x20, 0x22, 0x24, 0x26 }, + /* PMC 4 */ { 0x07, 0x17, 0x0e, 0x1e } +}; + +/* + * Some direct events for decodes of event bus byte 3 have alternative + * PMCSEL values on other counters. This returns the alternative + * event code for those that do, or -1 otherwise. + */ +static int find_alternative_bdecode(unsigned int event) +{ + int pmc, altpmc, pp, j; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc == 0 || pmc > 4) + return -1; + altpmc = 5 - pmc; /* 1 <-> 4, 2 <-> 3 */ + pp = event & PM_PMCSEL_MSK; + for (j = 0; j < 4; ++j) { + if (bytedecode_alternatives[pmc - 1][j] == pp) { + return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) | + (altpmc << PM_PMC_SH) | + bytedecode_alternatives[altpmc - 1][j]; + } + } + return -1; +} + +static int power5_get_alternatives(unsigned int event, unsigned int alt[]) +{ + int i, j, ae, nalt = 1; + + alt[0] = event; + nalt = 1; + i = find_alternative(event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != event) + alt[nalt++] = ae; + } + } else { + ae = find_alternative_bdecode(event); + if (ae > 0) + alt[nalt++] = ae; + } + return nalt; +} + +static int power5_compute_mmcr(unsigned int event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm, grp; + int i, isbus, bit, grsel; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + int ttmuse; + + if (n_ev > 6) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2 vs 3/4 use */ + if (pmc <= 4) + ++pmc_grp_use[(pmc - 1) >> 1]; + } + if (event[i] & PM_BUSEVENT_MSK) { + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + ++unit; + byte &= 3; + } + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + if (pmc_grp_use[0] > 2 || pmc_grp_use[1] > 2) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU0 can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU0] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) { + unituse[PM_ISU0_ALT] = 1; /* move ISU to TTM1 */ + unituse[PM_ISU0] = 0; + } + /* Set TTM[01]SEL fields. */ + ttmuse = 0; + for (i = PM_FPU; i <= PM_ISU1; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH; + } + ttmuse = 0; + for (; i <= PM_GRS; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH; + } + if (ttmuse > 1) + return -1; + + /* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) { + /* get ISU0 through TTM1 rather than TTM0 */ + unit = PM_ISU0_ALT; + } else if (unit == PM_LSU1 + 1) { + /* select lower word of LSU1 for this byte */ + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + isbus = event[i] & PM_BUSEVENT_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + for (pmc = 0; pmc < 4; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (isbus) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 2) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else if (pmc <= 4) { + /* Direct event */ + --pmc; + if ((psel == 8 || psel == 0x10) && isbus && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc); + } else { + /* Instructions or run cycles on PMC5/6 */ + --pmc; + } + if (isbus && unit == PM_GRS) { + bit = psel & 7; + grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK; + mmcr1 |= (u64)grsel << grsel_shift[bit]; + } + if (pmc <= 3) + mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc); + hwc[i] = pmc; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = 0; + return 0; +} + +static void power5_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power5_generic_events[] = { + [PERF_COUNT_CPU_CYCLES] = 0xf, + [PERF_COUNT_INSTRUCTIONS] = 0x100009, + [PERF_COUNT_CACHE_REFERENCES] = 0x4c1090, /* LD_REF_L1 */ + [PERF_COUNT_CACHE_MISSES] = 0x3c1088, /* LD_MISS_L1 */ + [PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x230e4, /* BR_ISSUED */ + [PERF_COUNT_BRANCH_MISSES] = 0x230e5, /* BR_MPRED_CR */ +}; + +struct power_pmu power5_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT, + .add_fields = 0x7000090000555ull, + .test_adder = 0x3000490000000ull, + .compute_mmcr = power5_compute_mmcr, + .get_constraint = power5_get_constraint, + .get_alternatives = power5_get_alternatives, + .disable_pmc = power5_disable_pmc, + .n_generic = ARRAY_SIZE(power5_generic_events), + .generic_events = power5_generic_events, +}; diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c new file mode 100644 index 0000000..b1f61f3 --- /dev/null +++ b/arch/powerpc/kernel/power6-pmu.c @@ -0,0 +1,283 @@ +/* + * Performance counter support for POWER6 processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER6 + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0x7 +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* Unit event comes (TTMxSEL encoding) */ +#define PM_UNIT_MSK 0xf +#define PM_UNIT_MSKS (PM_UNIT_MSK << PM_UNIT_SH) +#define PM_LLAV 0x8000 /* Load lookahead match value */ +#define PM_LLA 0x4000 /* Load lookahead match enable */ +#define PM_BYTE_SH 12 /* Byte of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_SUBUNIT_SH 8 /* Subunit event comes from (NEST_SEL enc.) */ +#define PM_SUBUNIT_MSK 7 +#define PM_SUBUNIT_MSKS (PM_SUBUNIT_MSK << PM_SUBUNIT_SH) +#define PM_PMCSEL_MSK 0xff /* PMCxSEL value */ +#define PM_BUSEVENT_MSK 0xf3700 + +/* + * Bits in MMCR1 for POWER6 + */ +#define MMCR1_TTM0SEL_SH 60 +#define MMCR1_TTMSEL_SH(n) (MMCR1_TTM0SEL_SH - (n) * 4) +#define MMCR1_TTMSEL_MSK 0xf +#define MMCR1_TTMSEL(m, n) (((m) >> MMCR1_TTMSEL_SH(n)) & MMCR1_TTMSEL_MSK) +#define MMCR1_NESTSEL_SH 45 +#define MMCR1_NESTSEL_MSK 0x7 +#define MMCR1_NESTSEL(m) (((m) >> MMCR1_NESTSEL_SH) & MMCR1_NESTSEL_MSK) +#define MMCR1_PMC1_LLA ((u64)1 << 44) +#define MMCR1_PMC1_LLA_VALUE ((u64)1 << 39) +#define MMCR1_PMC1_ADDR_SEL ((u64)1 << 35) +#define MMCR1_PMC1SEL_SH 24 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0xff + +/* + * Assign PMC numbers and compute MMCR1 value for a set of events + */ +static int p6_compute_mmcr(unsigned int event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + int i; + unsigned int pmc, ev, b, u, s, psel; + unsigned int ttmset = 0; + unsigned int pmc_inuse = 0; + + if (n_ev > 4) + return -1; + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; /* collision! */ + pmc_inuse |= 1 << (pmc - 1); + } + } + for (i = 0; i < n_ev; ++i) { + ev = event[i]; + pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + --pmc; + } else { + /* can go on any PMC; find a free one */ + for (pmc = 0; pmc < 4; ++pmc) + if (!(pmc_inuse & (1 << pmc))) + break; + pmc_inuse |= 1 << pmc; + } + hwc[i] = pmc; + psel = ev & PM_PMCSEL_MSK; + if (ev & PM_BUSEVENT_MSK) { + /* this event uses the event bus */ + b = (ev >> PM_BYTE_SH) & PM_BYTE_MSK; + u = (ev >> PM_UNIT_SH) & PM_UNIT_MSK; + /* check for conflict on this byte of event bus */ + if ((ttmset & (1 << b)) && MMCR1_TTMSEL(mmcr1, b) != u) + return -1; + mmcr1 |= (u64)u << MMCR1_TTMSEL_SH(b); + ttmset |= 1 << b; + if (u == 5) { + /* Nest events have a further mux */ + s = (ev >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK; + if ((ttmset & 0x10) && + MMCR1_NESTSEL(mmcr1) != s) + return -1; + ttmset |= 0x10; + mmcr1 |= (u64)s << MMCR1_NESTSEL_SH; + } + if (0x30 <= psel && psel <= 0x3d) { + /* these need the PMCx_ADDR_SEL bits */ + if (b >= 2) + mmcr1 |= MMCR1_PMC1_ADDR_SEL >> pmc; + } + /* bus select values are different for PMC3/4 */ + if (pmc >= 2 && (psel & 0x90) == 0x80) + psel ^= 0x20; + } + if (ev & PM_LLA) { + mmcr1 |= MMCR1_PMC1_LLA >> pmc; + if (ev & PM_LLAV) + mmcr1 |= MMCR1_PMC1_LLA_VALUE >> pmc; + } + mmcr1 |= (u64)psel << MMCR1_PMCSEL_SH(pmc); + } + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0xe) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = 0; + return 0; +} + +/* + * Layout of constraint bits: + * + * 0-1 add field: number of uses of PMC1 (max 1) + * 2-3, 4-5, 6-7: ditto for PMC2, 3, 4 + * 8-10 select field: nest (subunit) event selector + * 16-19 select field: unit on byte 0 of event bus + * 20-23, 24-27, 28-31 ditto for bytes 1, 2, 3 + */ +static int p6_get_constraint(unsigned int event, u64 *maskp, u64 *valp) +{ + int pmc, byte, sh; + unsigned int mask = 0, value = 0; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 4) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + } + if (event & PM_BUSEVENT_MSK) { + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + sh = byte * 4; + mask |= PM_UNIT_MSKS << sh; + value |= (event & PM_UNIT_MSKS) << sh; + if ((event & PM_UNIT_MSKS) == (5 << PM_UNIT_SH)) { + mask |= PM_SUBUNIT_MSKS; + value |= event & PM_SUBUNIT_MSKS; + } + } + *maskp = mask; + *valp = value; + return 0; +} + +#define MAX_ALT 4 /* at most 4 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x0130e8, 0x2000f6, 0x3000fc }, /* PM_PTEG_RELOAD_VALID */ + { 0x080080, 0x10000d, 0x30000c, 0x4000f0 }, /* PM_LD_MISS_L1 */ + { 0x080088, 0x200054, 0x3000f0 }, /* PM_ST_MISS_L1 */ + { 0x10000a, 0x2000f4 }, /* PM_RUN_CYC */ + { 0x10000b, 0x2000f5 }, /* PM_RUN_COUNT */ + { 0x10000e, 0x400010 }, /* PM_PURR */ + { 0x100010, 0x4000f8 }, /* PM_FLUSH */ + { 0x10001a, 0x200010 }, /* PM_MRK_INST_DISP */ + { 0x100026, 0x3000f8 }, /* PM_TB_BIT_TRANS */ + { 0x100054, 0x2000f0 }, /* PM_ST_FIN */ + { 0x100056, 0x2000fc }, /* PM_L1_ICACHE_MISS */ + { 0x1000f0, 0x40000a }, /* PM_INST_IMC_MATCH_CMPL */ + { 0x1000f8, 0x200008 }, /* PM_GCT_EMPTY_CYC */ + { 0x1000fc, 0x400006 }, /* PM_LSU_DERAT_MISS_CYC */ + { 0x20000e, 0x400007 }, /* PM_LSU_DERAT_MISS */ + { 0x200012, 0x300012 }, /* PM_INST_DISP */ + { 0x2000f2, 0x3000f2 }, /* PM_INST_DISP */ + { 0x2000f8, 0x300010 }, /* PM_EXT_INT */ + { 0x2000fe, 0x300056 }, /* PM_DATA_FROM_L2MISS */ + { 0x2d0030, 0x30001a }, /* PM_MRK_FPU_FIN */ + { 0x30000a, 0x400018 }, /* PM_MRK_INST_FIN */ + { 0x3000f6, 0x40000e }, /* PM_L1_DCACHE_RELOAD_VALID */ + { 0x3000fe, 0x400056 }, /* PM_DATA_FROM_L3MISS */ +}; + +/* + * This could be made more efficient with a binary search on + * a presorted list, if necessary + */ +static int find_alternatives_list(unsigned int event) +{ + int i, j; + unsigned int alt; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + return -1; + for (j = 0; j < MAX_ALT; ++j) { + alt = event_alternatives[i][j]; + if (!alt || event < alt) + break; + if (event == alt) + return i; + } + } + return -1; +} + +static int p6_get_alternatives(unsigned int event, unsigned int alt[]) +{ + int i, j; + unsigned int aevent, psel, pmc; + unsigned int nalt = 1; + + alt[0] = event; + + /* check the alternatives table */ + i = find_alternatives_list(event); + if (i >= 0) { + /* copy out alternatives from list */ + for (j = 0; j < MAX_ALT; ++j) { + aevent = event_alternatives[i][j]; + if (!aevent) + break; + if (aevent != event) + alt[nalt++] = aevent; + } + + } else { + /* Check for alternative ways of computing sum events */ + /* PMCSEL 0x32 counter N == PMCSEL 0x34 counter 5-N */ + psel = event & (PM_PMCSEL_MSK & ~1); /* ignore edge bit */ + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc && (psel == 0x32 || psel == 0x34)) + alt[nalt++] = ((event ^ 0x6) & ~PM_PMC_MSKS) | + ((5 - pmc) << PM_PMC_SH); + + /* PMCSEL 0x38 counter N == PMCSEL 0x3a counter N+/-2 */ + if (pmc && (psel == 0x38 || psel == 0x3a)) + alt[nalt++] = ((event ^ 0x2) & ~PM_PMC_MSKS) | + ((pmc > 2? pmc - 2: pmc + 2) << PM_PMC_SH); + } + + return nalt; +} + +static void p6_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + /* Set PMCxSEL to 0 to disable PMCx */ + mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power6_generic_events[] = { + [PERF_COUNT_CPU_CYCLES] = 0x1e, + [PERF_COUNT_INSTRUCTIONS] = 2, + [PERF_COUNT_CACHE_REFERENCES] = 0x280030, /* LD_REF_L1 */ + [PERF_COUNT_CACHE_MISSES] = 0x30000c, /* LD_MISS_L1 */ + [PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x410a0, /* BR_PRED */ + [PERF_COUNT_BRANCH_MISSES] = 0x400052, /* BR_MPRED */ +}; + +struct power_pmu power6_pmu = { + .n_counter = 4, + .max_alternatives = MAX_ALT, + .add_fields = 0x55, + .test_adder = 0, + .compute_mmcr = p6_compute_mmcr, + .get_constraint = p6_get_constraint, + .get_alternatives = p6_get_alternatives, + .disable_pmc = p6_disable_pmc, + .n_generic = ARRAY_SIZE(power6_generic_events), + .generic_events = power6_generic_events, +}; diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c new file mode 100644 index 0000000..c325658 --- /dev/null +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -0,0 +1,375 @@ +/* + * Performance counter support for PPC970-family processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for PPC970 + */ +#define PM_PMC_SH 12 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_UNIT_SH 8 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_BYTE_SH 4 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_PMCSEL_MSK 0xf + +/* Values in PM_UNIT field */ +#define PM_NONE 0 +#define PM_FPU 1 +#define PM_VPU 2 +#define PM_ISU 3 +#define PM_IFU 4 +#define PM_IDU 5 +#define PM_STS 6 +#define PM_LSU0 7 +#define PM_LSU1U 8 +#define PM_LSU1L 9 +#define PM_LASTUNIT 9 + +/* + * Bits in MMCR0 for PPC970 + */ +#define MMCR0_PMC1SEL_SH 8 +#define MMCR0_PMC2SEL_SH 1 +#define MMCR_PMCSEL_MSK 0x1f + +/* + * Bits in MMCR1 for PPC970 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 59 +#define MMCR1_TTM3SEL_SH 53 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 50 +#define MMCR1_TD_CP_DBG1SEL_SH 48 +#define MMCR1_TD_CP_DBG2SEL_SH 46 +#define MMCR1_TD_CP_DBG3SEL_SH 44 +#define MMCR1_PMC1_ADDER_SEL_SH 39 +#define MMCR1_PMC2_ADDER_SEL_SH 38 +#define MMCR1_PMC6_ADDER_SEL_SH 37 +#define MMCR1_PMC5_ADDER_SEL_SH 36 +#define MMCR1_PMC8_ADDER_SEL_SH 35 +#define MMCR1_PMC7_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC3SEL_SH 27 +#define MMCR1_PMC4SEL_SH 22 +#define MMCR1_PMC5SEL_SH 17 +#define MMCR1_PMC6SEL_SH 12 +#define MMCR1_PMC7SEL_SH 7 +#define MMCR1_PMC8SEL_SH 2 + +static short mmcr1_adder_bits[8] = { + MMCR1_PMC1_ADDER_SEL_SH, + MMCR1_PMC2_ADDER_SEL_SH, + MMCR1_PMC3_ADDER_SEL_SH, + MMCR1_PMC4_ADDER_SEL_SH, + MMCR1_PMC5_ADDER_SEL_SH, + MMCR1_PMC6_ADDER_SEL_SH, + MMCR1_PMC7_ADDER_SEL_SH, + MMCR1_PMC8_ADDER_SEL_SH +}; + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * <><>[ >[ >[ >< >< >< >< ><><><><><><><><> + * T0T1 UC PS1 PS2 B0 B1 B2 B3 P1P2P3P4P5P6P7P8 + * + * T0 - TTM0 constraint + * 46-47: TTM0SEL value (0=FPU, 2=IFU, 3=VPU) 0xC000_0000_0000 + * + * T1 - TTM1 constraint + * 44-45: TTM1SEL value (0=IDU, 3=STS) 0x3000_0000_0000 + * + * UC - unit constraint: can't have all three of FPU|IFU|VPU, ISU, IDU|STS + * 43: UC3 error 0x0800_0000_0000 + * 42: FPU|IFU|VPU events needed 0x0400_0000_0000 + * 41: ISU events needed 0x0200_0000_0000 + * 40: IDU|STS events needed 0x0100_0000_0000 + * + * PS1 + * 39: PS1 error 0x0080_0000_0000 + * 36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000 + * + * PS2 + * 35: PS2 error 0x0008_0000_0000 + * 32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000 + * + * B0 + * 28-31: Byte 0 event source 0xf000_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 24-27, 20-23, 16-19: Byte 1, 2, 3 event sources + * + * P1 + * 15: P1 error 0x8000 + * 14-15: Count of events needing PMC1 + * + * P2..P8 + * 0-13: Count of events needing PMC2..PMC8 + */ + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0xc80000000000ull, 0x040000000000ull }, + [PM_VPU] = { 0xc80000000000ull, 0xc40000000000ull }, + [PM_ISU] = { 0x080000000000ull, 0x020000000000ull }, + [PM_IFU] = { 0xc80000000000ull, 0x840000000000ull }, + [PM_IDU] = { 0x380000000000ull, 0x010000000000ull }, + [PM_STS] = { 0x380000000000ull, 0x310000000000ull }, +}; + +static int p970_get_constraint(unsigned int event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 8) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + grp = ((pmc - 1) >> 1) & 1; + } + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit) { + if (unit > PM_LASTUNIT) + return -1; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8. + */ + if (!pmc) + grp = byte & 1; + /* Set byte lane select field */ + mask |= 0xfULL << (28 - 4 * byte); + value |= (u64)unit << (28 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2/5/6 field */ + mask |= 0x8000000000ull; + value |= 0x1000000000ull; + } else if (grp == 1) { + /* increment PMC3/4/7/8 field */ + mask |= 0x800000000ull; + value |= 0x100000000ull; + } + *maskp = mask; + *valp = value; + return 0; +} + +static int p970_get_alternatives(unsigned int event, unsigned int alt[]) +{ + alt[0] = event; + + /* 2 alternatives for LSU empty */ + if (event == 0x2002 || event == 0x3002) { + alt[1] = event ^ 0x1000; + return 2; + } + + return 1; +} + +static int p970_compute_mmcr(unsigned int event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm, grp; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + unsigned char unitmap[] = { 0, 0<<3, 3<<3, 1<<3, 2<<3, 0|4, 3|4 }; + unsigned char ttmuse[2]; + unsigned char pmcsel[8]; + int i; + + if (n_ev > 8) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2/5/6 vs 3/4/7/8 use */ + ++pmc_grp_use[((pmc - 1) >> 1) & 1]; + } + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit) { + if (unit > PM_LASTUNIT) + return -1; + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_VPU])) + unitmap[PM_ISU] = 2 | 4; /* move ISU to TTM1 */ + /* Set TTM[01]SEL fields. */ + ttmuse[0] = ttmuse[1] = 0; + for (i = PM_FPU; i <= PM_STS; ++i) { + if (!unituse[i]) + continue; + ttm = unitmap[i]; + ++ttmuse[(ttm >> 2) & 1]; + mmcr1 |= (u64)(ttm & ~4) << MMCR1_TTM1SEL_SH; + } + /* Check only one unit per TTMx */ + if (ttmuse[0] > 1 || ttmuse[1] > 1) + return -1; + + /* Set byte lane select fields and TTM3SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit <= PM_STS) + ttm = (unitmap[unit] >> 2) & 1; + else if (unit == PM_LSU0) + ttm = 2; + else { + ttm = 3; + if (unit == PM_LSU1L && byte >= 2) + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + memset(pmcsel, 0x8, sizeof(pmcsel)); /* 8 means don't count */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + if (unit) + psel |= 0x10 | ((byte & 2) << 2); + else + psel |= 8; + for (pmc = 0; pmc < 8; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (unit) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 4) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else { + /* Direct event */ + --pmc; + if (psel == 0 && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << mmcr1_adder_bits[pmc]; + } + pmcsel[pmc] = psel; + hwc[i] = pmc; + } + for (pmc = 0; pmc < 2; ++pmc) + mmcr0 |= pmcsel[pmc] << (MMCR0_PMC1SEL_SH - 7 * pmc); + for (; pmc < 8; ++pmc) + mmcr1 |= (u64)pmcsel[pmc] << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)); + if (pmc_inuse & 1) + mmcr0 |= MMCR0_PMC1CE; + if (pmc_inuse & 0xfe) + mmcr0 |= MMCR0_PMCjCE; + + mmcra |= 0x2000; /* mark only one IOP per PPC instruction */ + + /* Return MMCRx values */ + mmcr[0] = mmcr0; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void p970_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + int shift, i; + + if (pmc <= 1) { + shift = MMCR0_PMC1SEL_SH - 7 * pmc; + i = 0; + } else { + shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2); + i = 1; + } + /* + * Setting the PMCxSEL field to 0x08 disables PMC x. + */ + mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift); +} + +static int ppc970_generic_events[] = { + [PERF_COUNT_CPU_CYCLES] = 7, + [PERF_COUNT_INSTRUCTIONS] = 1, + [PERF_COUNT_CACHE_REFERENCES] = 0x8810, /* PM_LD_REF_L1 */ + [PERF_COUNT_CACHE_MISSES] = 0x3810, /* PM_LD_MISS_L1 */ + [PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x431, /* PM_BR_ISSUED */ + [PERF_COUNT_BRANCH_MISSES] = 0x327, /* PM_GRP_BR_MPRED */ +}; + +struct power_pmu ppc970_pmu = { + .n_counter = 8, + .max_alternatives = 2, + .add_fields = 0x001100005555ull, + .test_adder = 0x013300000000ull, + .compute_mmcr = p970_compute_mmcr, + .get_constraint = p970_get_constraint, + .get_alternatives = p970_get_alternatives, + .disable_pmc = p970_disable_pmc, + .n_generic = ARRAY_SIZE(ppc970_generic_events), + .generic_events = ppc970_generic_events, +}; diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 161b9b9..67f07f4 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -181,13 +181,7 @@ SECTIONS __initramfs_end = .; } #endif - . = ALIGN(PAGE_SIZE); - .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { - __per_cpu_start = .; - *(.data.percpu) - *(.data.percpu.shared_aligned) - __per_cpu_end = .; - } + PERCPU(PAGE_SIZE) . = ALIGN(8); .machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) { diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c index fb371f5..d6b772b 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc610.c +++ b/arch/powerpc/platforms/86xx/gef_sbc610.c @@ -142,6 +142,10 @@ static void __init gef_sbc610_nec_fixup(struct pci_dev *pdev) { unsigned int val; + /* Do not do the fixup on other platforms! */ + if (!machine_is(gef_sbc610)) + return; + printk(KERN_INFO "Running NEC uPD720101 Fixup\n"); /* Ensure ports 1, 2, 3, 4 & 5 are enabled */ diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index e868b5c..dc0f3c9 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -1,6 +1,7 @@ config PPC64 bool "64-bit kernel" default n + select HAVE_PERF_COUNTERS help This option selects whether a 32-bit or a 64-bit kernel will be built. diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 28c04da..1f0d774 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -254,7 +254,7 @@ static void handle_iic_irq(unsigned int irq, struct irq_desc *desc) goto out_eoi; } - kstat_cpu(cpu).irqs[irq]++; + kstat_incr_irqs_this_cpu(irq, desc); /* Mark the IRQ currently in progress.*/ desc->status |= IRQ_INPROGRESS; diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 6a0ad19..f085369 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -508,7 +508,7 @@ static void __spu_add_to_rq(struct spu_context *ctx) list_add_tail(&ctx->rq, &spu_prio->runq[ctx->prio]); set_bit(ctx->prio, spu_prio->bitmap); if (!spu_prio->nr_waiting++) - __mod_timer(&spusched_timer, jiffies + SPUSCHED_TICK); + mod_timer(&spusched_timer, jiffies + SPUSCHED_TICK); } } diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index 2ca7be6..244f997 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -12,7 +12,6 @@ #include #include -#include #include #include @@ -22,39 +21,6 @@ #include "mpc10x.h" -static struct mtd_partition linkstation_physmap_partitions[] = { - { - .name = "mtd_firmimg", - .offset = 0x000000, - .size = 0x300000, - }, - { - .name = "mtd_bootcode", - .offset = 0x300000, - .size = 0x070000, - }, - { - .name = "mtd_status", - .offset = 0x370000, - .size = 0x010000, - }, - { - .name = "mtd_conf", - .offset = 0x380000, - .size = 0x080000, - }, - { - .name = "mtd_allflash", - .offset = 0x000000, - .size = 0x400000, - }, - { - .name = "mtd_data", - .offset = 0x310000, - .size = 0x0f0000, - }, -}; - static __initdata struct of_device_id of_bus_ids[] = { { .type = "soc", }, { .compatible = "simple-bus", }, @@ -99,10 +65,6 @@ static int __init linkstation_add_bridge(struct device_node *dev) static void __init linkstation_setup_arch(void) { struct device_node *np; -#ifdef CONFIG_MTD_PHYSMAP - physmap_set_partitions(linkstation_physmap_partitions, - ARRAY_SIZE(linkstation_physmap_partitions)); -#endif /* Lookup PCI host bridges */ for_each_compatible_node(np, "pci", "mpc10x-pci") diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c index 8864e48..613070e 100644 --- a/arch/powerpc/platforms/embedded6xx/storcenter.c +++ b/arch/powerpc/platforms/embedded6xx/storcenter.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include @@ -26,32 +25,6 @@ #include "mpc10x.h" -#ifdef CONFIG_MTD_PHYSMAP -static struct mtd_partition storcenter_physmap_partitions[] = { - { - .name = "kernel", - .offset = 0x000000, - .size = 0x170000, - }, - { - .name = "rootfs", - .offset = 0x170000, - .size = 0x590000, - }, - { - .name = "uboot", - .offset = 0x700000, - .size = 0x040000, - }, - { - .name = "config", - .offset = 0x740000, - .size = 0x0c0000, - }, -}; -#endif - - static __initdata struct of_device_id storcenter_of_bus[] = { { .name = "soc", }, {}, @@ -96,11 +69,6 @@ static void __init storcenter_setup_arch(void) { struct device_node *np; -#ifdef CONFIG_MTD_PHYSMAP - physmap_set_partitions(storcenter_physmap_partitions, - ARRAY_SIZE(storcenter_physmap_partitions)); -#endif - /* Lookup PCI host bridges */ for_each_compatible_node(np, "pci", "mpc10x-pci") storcenter_add_bridge(np); diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 84e058f..80b5134 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -153,9 +153,10 @@ static int get_irq_server(unsigned int virq, unsigned int strict_check) { int server; /* For the moment only implement delivery to all cpus or one cpu */ - cpumask_t cpumask = irq_desc[virq].affinity; + cpumask_t cpumask; cpumask_t tmp = CPU_MASK_NONE; + cpumask_copy(&cpumask, irq_desc[virq].affinity); if (!distribute_irqs) return default_server; @@ -869,7 +870,7 @@ void xics_migrate_irqs_away(void) virq, cpu); /* Reset affinity to all cpus */ - irq_desc[virq].affinity = CPU_MASK_ALL; + cpumask_setall(irq_desc[virq].affinity); desc->chip->set_affinity(virq, cpu_all_mask); unlock: spin_unlock_irqrestore(&desc->lock, flags); diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index a35297d..532e205 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -566,9 +566,10 @@ static void __init mpic_scan_ht_pics(struct mpic *mpic) #ifdef CONFIG_SMP static int irq_choose_cpu(unsigned int virt_irq) { - cpumask_t mask = irq_desc[virt_irq].affinity; + cpumask_t mask; int cpuid; + cpumask_copy(&mask, irq_desc[virt_irq].affinity); if (cpus_equal(mask, CPU_MASK_ALL)) { static int irq_rover; static DEFINE_SPINLOCK(irq_rover_lock); diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c index 72da416..15b6d45 100644 --- a/arch/sh/boards/board-ap325rxa.c +++ b/arch/sh/boards/board-ap325rxa.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include