8 files changed, 109 insertions, 52 deletions

diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 7e2c9fe44ac1..821e152e093c 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -2,6 +2,11 @@
  *  FPU support code, moved here from head.S so that it can be used
  *  by chips which use other head-whatever.S files.
  *
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ *    Copyright (C) 1996 Paul Mackerras.
+ *    Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
  *  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
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 7ee685433319..12c5971d6565 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -322,7 +322,8 @@ EXPORT_SYMBOL(do_softirq);
 
 static LIST_HEAD(irq_hosts);
 static spinlock_t irq_big_lock = SPIN_LOCK_UNLOCKED;
-
+static DEFINE_PER_CPU(unsigned int, irq_radix_reader);
+static unsigned int irq_radix_writer;
 struct irq_map_entry irq_map[NR_IRQS];
 static unsigned int irq_virq_count = NR_IRQS;
 static struct irq_host *irq_default_host;
@@ -455,6 +456,58 @@ void irq_set_virq_count(unsigned int count)
                 irq_virq_count = count;
 }
 
+/* radix tree not lockless safe ! we use a brlock-type mecanism
+ * for now, until we can use a lockless radix tree
+ */
+static void irq_radix_wrlock(unsigned long *flags)
+{
+        unsigned int cpu, ok;
+
+        spin_lock_irqsave(&irq_big_lock, *flags);
+        irq_radix_writer = 1;
+        smp_mb();
+        do {
+                barrier();
+                ok = 1;
+                for_each_possible_cpu(cpu) {
+                        if (per_cpu(irq_radix_reader, cpu)) {
+                                ok = 0;
+                                break;
+                        }
+                }
+                if (!ok)
+                        cpu_relax();
+        } while(!ok);
+}
+
+static void irq_radix_wrunlock(unsigned long flags)
+{
+        smp_wmb();
+        irq_radix_writer = 0;
+        spin_unlock_irqrestore(&irq_big_lock, flags);
+}
+
+static void irq_radix_rdlock(unsigned long *flags)
+{
+        local_irq_save(*flags);
+        __get_cpu_var(irq_radix_reader) = 1;
+        smp_mb();
+        if (likely(irq_radix_writer == 0))
+                return;
+        __get_cpu_var(irq_radix_reader) = 0;
+        smp_wmb();
+        spin_lock(&irq_big_lock);
+        __get_cpu_var(irq_radix_reader) = 1;
+        spin_unlock(&irq_big_lock);
+}
+
+static void irq_radix_rdunlock(unsigned long flags)
+{
+        __get_cpu_var(irq_radix_reader) = 0;
+        local_irq_restore(flags);
+}
+
+
 unsigned int irq_create_mapping(struct irq_host *host,
                                 irq_hw_number_t hwirq)
 {
@@ -604,13 +657,9 @@ void irq_dispose_mapping(unsigned int virq)
                 /* Check if radix tree allocated yet */
                 if (host->revmap_data.tree.gfp_mask == 0)
                         break;
-                /* XXX radix tree not safe ! remove lock whem it becomes safe
-                 * and use some RCU sync to make sure everything is ok before we
-                 * can re-use that map entry
-                 */
-                spin_lock_irqsave(&irq_big_lock, flags);
+                irq_radix_wrlock(&flags);
                 radix_tree_delete(&host->revmap_data.tree, hwirq);
-                spin_unlock_irqrestore(&irq_big_lock, flags);
+                irq_radix_wrunlock(flags);
                 break;
         }
 
@@ -677,25 +726,24 @@ unsigned int irq_radix_revmap(struct irq_host *host,
         if (tree->gfp_mask == 0)
                 return irq_find_mapping(host, hwirq);
 
-        /* XXX Current radix trees are NOT SMP safe !!! Remove that lock
-         * when that is fixed (when Nick's patch gets in
-         */
-        spin_lock_irqsave(&irq_big_lock, flags);
-
         /* Now try to resolve */
+        irq_radix_rdlock(&flags);
         ptr = radix_tree_lookup(tree, hwirq);
+        irq_radix_rdunlock(flags);
+
         /* Found it, return */
         if (ptr) {
                 virq = ptr - irq_map;
-                goto bail;
+                return virq;
         }
 
         /* If not there, try to insert it */
         virq = irq_find_mapping(host, hwirq);
-        if (virq != NO_IRQ)
+        if (virq != NO_IRQ) {
+                irq_radix_wrlock(&flags);
                 radix_tree_insert(tree, hwirq, &irq_map[virq]);
- bail:
-        spin_unlock_irqrestore(&irq_big_lock, flags);
+                irq_radix_wrunlock(flags);
+        }
         return virq;
 }
 
@@ -806,12 +854,12 @@ static int irq_late_init(void)
         struct irq_host *h;
         unsigned long flags;
 
-        spin_lock_irqsave(&irq_big_lock, flags);
+        irq_radix_wrlock(&flags);
         list_for_each_entry(h, &irq_hosts, link) {
                 if (h->revmap_type == IRQ_HOST_MAP_TREE)
                         INIT_RADIX_TREE(&h->revmap_data.tree, GFP_ATOMIC);
         }
-        spin_unlock_irqrestore(&irq_big_lock, flags);
+        irq_radix_wrunlock(flags);
 
         return 0;
 }
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 2fce7738e9e2..138134c8c17d 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -1289,6 +1289,9 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 
         DBG("Try to map irq for %s...\n", pci_name(pci_dev));
 
+#ifdef DEBUG
+        memset(&oirq, 0xff, sizeof(oirq));
+#endif
         /* Try to get a mapping from the device-tree */
         if (of_irq_map_pci(pci_dev, &oirq)) {
                 u8 line, pin;
@@ -1314,8 +1317,9 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
                 if (virq != NO_IRQ)
                         set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
         } else {
-                DBG(" -> got one, spec %d cells (0x%08x...) on %s\n",
-                    oirq.size, oirq.specifier[0], oirq.controller->full_name);
+                DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
+                    oirq.size, oirq.specifier[0], oirq.specifier[1],
+                    oirq.controller->full_name);
 
                 virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
                                              oirq.size);
@@ -1324,6 +1328,9 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
                 DBG(" -> failed to map !\n");
                 return -1;
         }
+
+        DBG(" -> mapped to linux irq %d\n", virq);
+
         pci_dev->irq = virq;
         pci_write_config_byte(pci_dev, PCI_INTERRUPT_LINE, virq);
 
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index f6a05f090b25..39d3bfcabcd2 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -126,10 +126,6 @@ EXPORT_SYMBOL(pci_bus_mem_base_phys);
 EXPORT_SYMBOL(pci_bus_to_hose);
 #endif /* CONFIG_PCI */
 
-#ifdef CONFIG_NOT_COHERENT_CACHE
-EXPORT_SYMBOL(flush_dcache_all);
-#endif
-
 EXPORT_SYMBOL(start_thread);
 EXPORT_SYMBOL(kernel_thread);
 
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 462bced40c12..4394e545f9f7 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -646,13 +646,13 @@ static unsigned char ibm_architecture_vec[] = {
         5 - 1,                          /* 5 option vectors */
 
         /* option vector 1: processor architectures supported */
-        3 - 1,                          /* length */
+        3 - 2,                          /* length */
         0,                              /* don't ignore, don't halt */
         OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 |
         OV1_PPC_2_04 | OV1_PPC_2_05,
 
         /* option vector 2: Open Firmware options supported */
-        34 - 1,                         /* length */
+        34 - 2,                         /* length */
         OV2_REAL_MODE,
         0, 0,
         W(0xffffffff),                  /* real_base */
@@ -666,16 +666,16 @@ static unsigned char ibm_architecture_vec[] = {
         48,                             /* max log_2(hash table size) */
 
         /* option vector 3: processor options supported */
-        3 - 1,                          /* length */
+        3 - 2,                          /* length */
         0,                              /* don't ignore, don't halt */
         OV3_FP | OV3_VMX,
 
         /* option vector 4: IBM PAPR implementation */
-        2 - 1,                          /* length */
+        2 - 2,                          /* length */
         0,                              /* don't halt */
 
         /* option vector 5: PAPR/OF options */
-        3 - 1,                          /* length */
+        3 - 2,                          /* length */
         0,                              /* don't ignore, don't halt */
         OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES,
 };
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index 11052c212ad5..a10825a5dfe6 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -639,14 +639,17 @@ void of_irq_map_init(unsigned int flags)
 
 }
 
-int of_irq_map_raw(struct device_node *parent, u32 *intspec, u32 *addr,
-                   struct of_irq *out_irq)
+int of_irq_map_raw(struct device_node *parent, u32 *intspec, u32 ointsize,
+                   u32 *addr, struct of_irq *out_irq)
 {
         struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL;
         u32 *tmp, *imap, *imask;
         u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0;
         int imaplen, match, i;
 
+        DBG("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n",
+            parent->full_name, intspec[0], intspec[1], ointsize);
+
         ipar = of_node_get(parent);
 
         /* First get the #interrupt-cells property of the current cursor
@@ -670,6 +673,9 @@ int of_irq_map_raw(struct device_node *parent, u32 *intspec, u32 *addr,
 
         DBG("of_irq_map_raw: ipar=%s, size=%d\n", ipar->full_name, intsize);
 
+        if (ointsize != intsize)
+                return -EINVAL;
+
         /* Look for this #address-cells. We have to implement the old linux
          * trick of looking for the parent here as some device-trees rely on it
          */
@@ -875,12 +881,15 @@ int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq
         }
         intsize = *tmp;
 
+        DBG(" intsize=%d intlen=%d\n", intsize, intlen);
+
         /* Check index */
         if ((index + 1) * intsize > intlen)
                 return -EINVAL;
 
         /* Get new specifier and map it */
-        res = of_irq_map_raw(p, intspec + index * intsize, addr, out_irq);
+        res = of_irq_map_raw(p, intspec + index * intsize, intsize,
+                             addr, out_irq);
         of_node_put(p);
         return res;
 }
@@ -965,7 +974,7 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
         laddr[0] = (pdev->bus->number << 16)
                 | (pdev->devfn << 8);
         laddr[1]  = laddr[2] = 0;
-        return of_irq_map_raw(ppnode, &lspec, laddr, out_irq);
+        return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq);
 }
 EXPORT_SYMBOL_GPL(of_irq_map_pci);
 #endif /* CONFIG_PCI */
diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c
index f19e2e0e61e7..de59c6c31a5b 100644
--- a/arch/powerpc/kernel/smp-tbsync.c
+++ b/arch/powerpc/kernel/smp-tbsync.c
@@ -45,8 +45,9 @@ void __devinit smp_generic_take_timebase(void)
 {
         int cmd;
         u64 tb;
+        unsigned long flags;
 
-        local_irq_disable();
+        local_irq_save(flags);
         while (!running)
                 barrier();
         rmb();
@@ -70,7 +71,7 @@ void __devinit smp_generic_take_timebase(void)
                         set_tb(tb >> 32, tb & 0xfffffffful);
                 enter_contest(tbsync->mark, -1);
         }
-        local_irq_enable();
+        local_irq_restore(flags);
 }
 
 static int __devinit start_contest(int cmd, long offset, int num)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 18e59e43d2b3..a124499e65d9 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -125,15 +125,8 @@ static long timezone_offset;
 unsigned long ppc_proc_freq;
 unsigned long ppc_tb_freq;
 
-u64 tb_last_jiffy __cacheline_aligned_in_smp;
-unsigned long tb_last_stamp;
-
-/*
- * Note that on ppc32 this only stores the bottom 32 bits of
- * the timebase value, but that's enough to tell when a jiffy
- * has passed.
- */
-DEFINE_PER_CPU(unsigned long, last_jiffy);
+static u64 tb_last_jiffy __cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(u64, last_jiffy);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 /*
@@ -458,7 +451,7 @@ void do_gettimeofday(struct timeval *tv)
                 do {
                         seq = read_seqbegin_irqsave(&xtime_lock, flags);
                         sec = xtime.tv_sec;
-                        nsec = xtime.tv_nsec + tb_ticks_since(tb_last_stamp);
+                        nsec = xtime.tv_nsec + tb_ticks_since(tb_last_jiffy);
                 } while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
                 usec = nsec / 1000;
                 while (usec >= 1000000) {
@@ -700,7 +693,6 @@ void timer_interrupt(struct pt_regs * regs)
                 tb_next_jiffy = tb_last_jiffy + tb_ticks_per_jiffy;
                 if (per_cpu(last_jiffy, cpu) >= tb_next_jiffy) {
                         tb_last_jiffy = tb_next_jiffy;
-                        tb_last_stamp = per_cpu(last_jiffy, cpu);
                         do_timer(regs);
                         timer_recalc_offset(tb_last_jiffy);
                         timer_check_rtc();
@@ -749,7 +741,7 @@ void __init smp_space_timers(unsigned int max_cpus)
         int i;
         unsigned long half = tb_ticks_per_jiffy / 2;
         unsigned long offset = tb_ticks_per_jiffy / max_cpus;
-        unsigned long previous_tb = per_cpu(last_jiffy, boot_cpuid);
+        u64 previous_tb = per_cpu(last_jiffy, boot_cpuid);
 
         /* make sure tb > per_cpu(last_jiffy, cpu) for all cpus always */
         previous_tb -= tb_ticks_per_jiffy;
@@ -830,7 +822,7 @@ int do_settimeofday(struct timespec *tv)
          * and therefore the (jiffies - wall_jiffies) computation
          * has been removed.
          */
-        tb_delta = tb_ticks_since(tb_last_stamp);
+        tb_delta = tb_ticks_since(tb_last_jiffy);
         tb_delta = mulhdu(tb_delta, do_gtod.varp->tb_to_xs); /* in xsec */
         new_nsec -= SCALE_XSEC(tb_delta, 1000000000);
 
@@ -950,8 +942,7 @@ void __init time_init(void)
         if (__USE_RTC()) {
                 /* 601 processor: dec counts down by 128 every 128ns */
                 ppc_tb_freq = 1000000000;
-                tb_last_stamp = get_rtcl();
-                tb_last_jiffy = tb_last_stamp;
+                tb_last_jiffy = get_rtcl();
         } else {
                 /* Normal PowerPC with timebase register */
                 ppc_md.calibrate_decr();
@@ -959,7 +950,7 @@ void __init time_init(void)
                        ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
                 printk(KERN_DEBUG "time_init: processor frequency   = %lu.%.6lu MHz\n",
                        ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
-                tb_last_stamp = tb_last_jiffy = get_tb();
+                tb_last_jiffy = get_tb();
         }
 
         tb_ticks_per_jiffy = ppc_tb_freq / HZ;
@@ -1036,7 +1027,7 @@ void __init time_init(void)
         do_gtod.varp = &do_gtod.vars[0];
         do_gtod.var_idx = 0;
         do_gtod.varp->tb_orig_stamp = tb_last_jiffy;
-        __get_cpu_var(last_jiffy) = tb_last_stamp;
+        __get_cpu_var(last_jiffy) = tb_last_jiffy;
         do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
         do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
         do_gtod.varp->tb_to_xs = tb_to_xs;