Merge branch 'for-2.6.23' of master.kernel.org:/pub/scm/linux/kernel/git/arnd/cell-2.6

* 'for-2.6.23' of master.kernel.org:/pub/scm/linux/kernel/git/arnd/cell-2.6: (37 commits)
  [CELL] spufs: rework list management and associated locking
  [CELL] oprofile: add support to OProfile for profiling CELL BE SPUs
  [CELL] oprofile: enable SPU switch notification to detect currently active SPU tasks
  [CELL] spu_base: locking cleanup
  [CELL] cell: indexing of SPUs based on firmware vicinity properties
  [CELL] spufs: integration of SPE affinity with the scheduller
  [CELL] cell: add placement computation for scheduling of affinity contexts
  [CELL] spufs: extension of spu_create to support affinity definition
  [CELL] cell: add hardcoded spu vicinity information for QS20
  [CELL] cell: add vicinity information on spus
  [CELL] cell: add per BE structure with info about its SPUs
  [CELL] spufs: use find_first_bit() instead of sched_find_first_bit()
  [CELL] spufs: remove unused file argument from spufs_run_spu()
  [CELL] spufs: change decrementer restore timing
  [CELL] spufs: dont halt decrementer at restore step 47
  [CELL] spufs: limit saving MFC_CNTL bits
  [CELL] spufs: fix read and write for decr_status file
  [CELL] spufs: fix decr_status meanings
  [CELL] spufs: remove needless context save/restore code
  [CELL] spufs: fix array size of channel index
  ...

8 files changed, 106 insertions, 23 deletions

diff --git a/include/asm-powerpc/oprofile_impl.h b/include/asm-powerpc/oprofile_impl.h
index 8d6b47f7b300..938fefb4c4bc 100644
--- a/include/asm-powerpc/oprofile_impl.h
+++ b/include/asm-powerpc/oprofile_impl.h
@@ -39,14 +39,16 @@ struct op_system_config {
 
 /* Per-arch configuration */
 struct op_powerpc_model {
-        void (*reg_setup) (struct op_counter_config *,
+        int (*reg_setup) (struct op_counter_config *,
                            struct op_system_config *,
                            int num_counters);
-        void (*cpu_setup) (struct op_counter_config *);
-        void (*start) (struct op_counter_config *);
-        void (*global_start) (struct op_counter_config *);
+        int  (*cpu_setup) (struct op_counter_config *);
+        int  (*start) (struct op_counter_config *);
+        int  (*global_start) (struct op_counter_config *);
         void (*stop) (void);
         void (*global_stop) (void);
+        int (*sync_start)(void);
+        int (*sync_stop)(void);
         void (*handle_interrupt) (struct pt_regs *,
                                   struct op_counter_config *);
         int num_counters;
diff --git a/include/asm-powerpc/pmi.h b/include/asm-powerpc/pmi.h
index cb0f8aa43088..2259d4ce3846 100644
--- a/include/asm-powerpc/pmi.h
+++ b/include/asm-powerpc/pmi.h
@@ -55,13 +55,13 @@ typedef struct {
 struct pmi_handler {
         struct list_head node;
         u8 type;
-        void (*handle_pmi_message) (struct of_device *, pmi_message_t);
+        void (*handle_pmi_message) (pmi_message_t);
 };
 
-void pmi_register_handler(struct of_device *, struct pmi_handler *);
-void pmi_unregister_handler(struct of_device *, struct pmi_handler *);
+int pmi_register_handler(struct pmi_handler *);
+void pmi_unregister_handler(struct pmi_handler *);
 
-void pmi_send_message(struct of_device *, pmi_message_t);
+int pmi_send_message(pmi_message_t);
 
 #endif /* __KERNEL__ */
 #endif /* _POWERPC_PMI_H */
diff --git a/include/asm-powerpc/spu.h b/include/asm-powerpc/spu.h
index eedc828cef2d..8836c0f1f2f7 100644
--- a/include/asm-powerpc/spu.h
+++ b/include/asm-powerpc/spu.h
@@ -107,10 +107,10 @@ struct spu_runqueue;
 struct device_node;
 
 enum spu_utilization_state {
-        SPU_UTIL_SYSTEM,
         SPU_UTIL_USER,
+        SPU_UTIL_SYSTEM,
         SPU_UTIL_IOWAIT,
-        SPU_UTIL_IDLE,
+        SPU_UTIL_IDLE_LOADED,
         SPU_UTIL_MAX
 };
 
@@ -121,9 +121,9 @@ struct spu {
         unsigned long problem_phys;
         struct spu_problem __iomem *problem;
         struct spu_priv2 __iomem *priv2;
-        struct list_head list;
-        struct list_head sched_list;
+        struct list_head cbe_list;
         struct list_head full_list;
+        enum { SPU_FREE, SPU_USED } alloc_state;
         int number;
         unsigned int irqs[3];
         u32 node;
@@ -137,6 +137,7 @@ struct spu {
         struct spu_runqueue *rq;
         unsigned long long timestamp;
         pid_t pid;
+        pid_t tgid;
         int class_0_pending;
         spinlock_t register_lock;
 
@@ -165,11 +166,14 @@ struct spu {
 
         struct sys_device sysdev;
 
+        int has_mem_affinity;
+        struct list_head aff_list;
+
         struct {
                 /* protected by interrupt reentrancy */
-                enum spu_utilization_state utilization_state;
-                unsigned long tstamp;           /* time of last ctx switch */
-                unsigned long times[SPU_UTIL_MAX];
+                enum spu_utilization_state util_state;
+                unsigned long long tstamp;
+                unsigned long long times[SPU_UTIL_MAX];
                 unsigned long long vol_ctx_switch;
                 unsigned long long invol_ctx_switch;
                 unsigned long long min_flt;
@@ -181,13 +185,29 @@ struct spu {
         } stats;
 };
 
-struct spu *spu_alloc(void);
-struct spu *spu_alloc_node(int node);
-void spu_free(struct spu *spu);
+struct cbe_spu_info {
+        struct mutex list_mutex;
+        struct list_head spus;
+        int n_spus;
+        int nr_active;
+        atomic_t reserved_spus;
+};
+
+extern struct cbe_spu_info cbe_spu_info[];
+
+void spu_init_channels(struct spu *spu);
 int spu_irq_class_0_bottom(struct spu *spu);
 int spu_irq_class_1_bottom(struct spu *spu);
 void spu_irq_setaffinity(struct spu *spu, int cpu);
 
+#ifdef CONFIG_KEXEC
+void crash_register_spus(struct list_head *list);
+#else
+static inline void crash_register_spus(struct list_head *list)
+{
+}
+#endif
+
 extern void spu_invalidate_slbs(struct spu *spu);
 extern void spu_associate_mm(struct spu *spu, struct mm_struct *mm);
 
@@ -195,6 +215,20 @@ extern void spu_associate_mm(struct spu *spu, struct mm_struct *mm);
 struct mm_struct;
 extern void spu_flush_all_slbs(struct mm_struct *mm);
 
+/* This interface allows a profiler (e.g., OProfile) to store a ref
+ * to spu context information that it creates.  This caching technique
+ * avoids the need to recreate this information after a save/restore operation.
+ *
+ * Assumes the caller has already incremented the ref count to
+ * profile_info; then spu_context_destroy must call kref_put
+ * on prof_info_kref.
+ */
+void spu_set_profile_private_kref(struct spu_context *ctx,
+                                  struct kref *prof_info_kref,
+                                  void ( * prof_info_release) (struct kref *kref));
+
+void *spu_get_profile_private_kref(struct spu_context *ctx);
+
 /* system callbacks from the SPU */
 struct spu_syscall_block {
         u64 nr_ret;
@@ -206,7 +240,8 @@ extern long spu_sys_callback(struct spu_syscall_block *s);
 struct file;
 extern struct spufs_calls {
         asmlinkage long (*create_thread)(const char __user *name,
-                                        unsigned int flags, mode_t mode);
+                                        unsigned int flags, mode_t mode,
+                                        struct file *neighbor);
         asmlinkage long (*spu_run)(struct file *filp, __u32 __user *unpc,
                                                 __u32 __user *ustatus);
         struct module *owner;
@@ -233,8 +268,10 @@ struct spu_coredump_calls {
 #define SPU_CREATE_GANG                 0x0002
 #define SPU_CREATE_NOSCHED              0x0004
 #define SPU_CREATE_ISOLATE              0x0008
+#define SPU_CREATE_AFFINITY_SPU         0x0010
+#define SPU_CREATE_AFFINITY_MEM         0x0020
 
-#define SPU_CREATE_FLAG_ALL             0x000f /* mask of all valid flags */
+#define SPU_CREATE_FLAG_ALL             0x003f /* mask of all valid flags */
 
 
 #ifdef CONFIG_SPU_FS_MODULE
@@ -403,6 +440,7 @@ struct spu_priv2 {
 #define MFC_CNTL_RESUME_DMA_QUEUE               (0ull << 0)
 #define MFC_CNTL_SUSPEND_DMA_QUEUE              (1ull << 0)
 #define MFC_CNTL_SUSPEND_DMA_QUEUE_MASK         (1ull << 0)
+#define MFC_CNTL_SUSPEND_MASK                   (1ull << 4)
 #define MFC_CNTL_NORMAL_DMA_QUEUE_OPERATION     (0ull << 8)
 #define MFC_CNTL_SUSPEND_IN_PROGRESS            (1ull << 8)
 #define MFC_CNTL_SUSPEND_COMPLETE               (3ull << 8)
diff --git a/include/asm-powerpc/spu_csa.h b/include/asm-powerpc/spu_csa.h
index c48ae185c874..e87794d5d4ea 100644
--- a/include/asm-powerpc/spu_csa.h
+++ b/include/asm-powerpc/spu_csa.h
@@ -50,6 +50,12 @@
 #define SPU_STOPPED_STATUS_P_I  8
 #define SPU_STOPPED_STATUS_R    9
 
+/*
+ * Definitions for software decrementer status flag.
+ */
+#define SPU_DECR_STATUS_RUNNING 0x1
+#define SPU_DECR_STATUS_WRAPPED 0x2
+
 #ifndef  __ASSEMBLY__
 /**
  * spu_reg128 - generic 128-bit register definition.
@@ -63,7 +69,7 @@ struct spu_reg128 {
  * @gprs: Array of saved registers.
  * @fpcr: Saved floating point status control register.
  * @decr: Saved decrementer value.
- * @decr_status: Indicates decrementer run status.
+ * @decr_status: Indicates software decrementer status flags.
  * @ppu_mb: Saved PPU mailbox data.
  * @ppuint_mb: Saved PPU interrupting mailbox data.
  * @tag_mask: Saved tag group mask.
diff --git a/include/linux/dcookies.h b/include/linux/dcookies.h
index 0fe7cdf326f7..98c69ab80c84 100644
--- a/include/linux/dcookies.h
+++ b/include/linux/dcookies.h
@@ -12,6 +12,7 @@
 
 #ifdef CONFIG_PROFILING
  
+#include <linux/dcache.h>
 #include <linux/types.h>
  
 struct dcookie_user;
diff --git a/include/linux/elf-em.h b/include/linux/elf-em.h
index 0311bad838b1..5834e843a946 100644
--- a/include/linux/elf-em.h
+++ b/include/linux/elf-em.h
@@ -20,7 +20,8 @@
 #define EM_PARISC       15      /* HPPA */
 #define EM_SPARC32PLUS  18      /* Sun's "v8plus" */
 #define EM_PPC          20      /* PowerPC */
-#define EM_PPC64        21       /* PowerPC64 */
+#define EM_PPC64        21       /* PowerPC64 */
+#define EM_SPU          23      /* Cell BE SPU */
 #define EM_SH           42      /* SuperH */
 #define EM_SPARCV9      43      /* SPARC v9 64-bit */
 #define EM_IA_64        50      /* HP/Intel IA-64 */
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 0d514b252454..041bb31100f4 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -17,6 +17,26 @@
 #include <linux/spinlock.h>
 #include <asm/atomic.h>
  
+/* Each escaped entry is prefixed by ESCAPE_CODE
+ * then one of the following codes, then the
+ * relevant data.
+ * These #defines live in this file so that arch-specific
+ * buffer sync'ing code can access them.
+ */
+#define ESCAPE_CODE                     ~0UL
+#define CTX_SWITCH_CODE                 1
+#define CPU_SWITCH_CODE                 2
+#define COOKIE_SWITCH_CODE              3
+#define KERNEL_ENTER_SWITCH_CODE        4
+#define KERNEL_EXIT_SWITCH_CODE         5
+#define MODULE_LOADED_CODE              6
+#define CTX_TGID_CODE                   7
+#define TRACE_BEGIN_CODE                8
+#define TRACE_END_CODE                  9
+#define XEN_ENTER_SWITCH_CODE           10
+#define SPU_PROFILING_CODE              11
+#define SPU_CTX_SWITCH_CODE             12
+
 struct super_block;
 struct dentry;
 struct file_operations;
@@ -35,6 +55,14 @@ struct oprofile_operations {
         int (*start)(void);
         /* Stop delivering interrupts. */
         void (*stop)(void);
+        /* Arch-specific buffer sync functions.
+         * Return value = 0:  Success
+         * Return value = -1: Failure
+         * Return value = 1:  Run generic sync function
+         */
+        int (*sync_start)(void);
+        int (*sync_stop)(void);
+
         /* Initiate a stack backtrace. Optional. */
         void (*backtrace)(struct pt_regs * const regs, unsigned int depth);
         /* CPU identification string. */
@@ -56,6 +84,13 @@ int oprofile_arch_init(struct oprofile_operations * ops);
 void oprofile_arch_exit(void);
 
 /**
+ * Add data to the event buffer.
+ * The data passed is free-form, but typically consists of
+ * file offsets, dcookies, context information, and ESCAPE codes.
+ */
+void add_event_entry(unsigned long data);
+
+/**
  * Add a sample. This may be called from any context. Pass
  * smp_processor_id() as cpu.
  */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7a8b1e3322e0..61def7c8fbb3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -549,7 +549,7 @@ asmlinkage long sys_inotify_rm_watch(int fd, u32 wd);
 asmlinkage long sys_spu_run(int fd, __u32 __user *unpc,
                                  __u32 __user *ustatus);
 asmlinkage long sys_spu_create(const char __user *name,
-                unsigned int flags, mode_t mode);
+                unsigned int flags, mode_t mode, int fd);
 
 asmlinkage long sys_mknodat(int dfd, const char __user * filename, int mode,
                             unsigned dev);