17 files changed, 172 insertions, 81 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 2c8e756d19a3..d67bcd84f329 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -284,6 +284,10 @@ int main(void)
         DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32));
         DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
         DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+        DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size));
+        DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size));
+        DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size));
+        DEFINE(CFG_DCACHE_LOGBLOCKSZ, offsetof(struct vdso_data, dcache_log_block_size));
 #ifdef CONFIG_PPC64
         DEFINE(CFG_SYSCALL_MAP64, offsetof(struct vdso_data, syscall_map_64));
         DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec));
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 214780798289..053cac19f714 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -19,6 +19,9 @@
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/completion.h>
+#include <linux/cpumask.h>
 
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -34,6 +37,8 @@
 #include <asm/lmb.h>
 #include <asm/udbg.h>
 #include <asm/syscalls.h>
+#include <asm/smp.h>
+#include <asm/atomic.h>
 
 struct rtas_t rtas = {
         .lock = SPIN_LOCK_UNLOCKED
@@ -41,8 +46,10 @@ struct rtas_t rtas = {
 EXPORT_SYMBOL(rtas);
 
 struct rtas_suspend_me_data {
-        long waiting;
-        struct rtas_args *args;
+        atomic_t working; /* number of cpus accessing this struct */
+        int token; /* ibm,suspend-me */
+        int error;
+        struct completion *complete; /* wait on this until working == 0 */
 };
 
 DEFINE_SPINLOCK(rtas_data_buf_lock);
@@ -631,18 +638,18 @@ void rtas_halt(void)
 /* Must be in the RMO region, so we place it here */
 static char rtas_os_term_buf[2048];
 
-void rtas_os_term(char *str)
+void rtas_panic_msg(char *str)
 {
-        int status;
+        snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
+}
 
-        if (panic_timeout)
-                return;
+void rtas_os_term(void)
+{
+        int status;
 
         if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term"))
                 return;
 
-        snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
-
         do {
                 status = rtas_call(rtas_token("ibm,os-term"), 1, 1, NULL,
                                    __pa(rtas_os_term_buf));
@@ -657,50 +664,62 @@ static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
 #ifdef CONFIG_PPC_PSERIES
 static void rtas_percpu_suspend_me(void *info)
 {
-        int i;
         long rc;
-        long flags;
+        unsigned long msr_save;
+        int cpu;
         struct rtas_suspend_me_data *data =
                 (struct rtas_suspend_me_data *)info;
 
-        /*
-         * We use "waiting" to indicate our state.  As long
-         * as it is >0, we are still trying to all join up.
-         * If it goes to 0, we have successfully joined up and
-         * one thread got H_CONTINUE.  If any error happens,
-         * we set it to <0.
-         */
-        local_irq_save(flags);
-        do {
-                rc = plpar_hcall_norets(H_JOIN);
-                smp_rmb();
-        } while (rc == H_SUCCESS && data->waiting > 0);
-        if (rc == H_SUCCESS)
-                goto out;
+        atomic_inc(&data->working);
+
+        /* really need to ensure MSR.EE is off for H_JOIN */
+        msr_save = mfmsr();
+        mtmsr(msr_save & ~(MSR_EE));
+
+        rc = plpar_hcall_norets(H_JOIN);
 
-        if (rc == H_CONTINUE) {
-                data->waiting = 0;
-                data->args->args[data->args->nargs] =
-                        rtas_call(ibm_suspend_me_token, 0, 1, NULL);
-                for_each_possible_cpu(i)
-                        plpar_hcall_norets(H_PROD,i);
+        mtmsr(msr_save);
+
+        if (rc == H_SUCCESS) {
+                /* This cpu was prodded and the suspend is complete. */
+                goto out;
+        } else if (rc == H_CONTINUE) {
+                /* All other cpus are in H_JOIN, this cpu does
+                 * the suspend.
+                 */
+                printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n",
+                       smp_processor_id());
+                data->error = rtas_call(data->token, 0, 1, NULL);
+
+                if (data->error)
+                        printk(KERN_DEBUG "ibm,suspend-me returned %d\n",
+                               data->error);
         } else {
-                data->waiting = -EBUSY;
-                printk(KERN_ERR "Error on H_JOIN hypervisor call\n");
+                printk(KERN_ERR "H_JOIN on cpu %i failed with rc = %ld\n",
+                       smp_processor_id(), rc);
+                data->error = rc;
         }
-
+        /* This cpu did the suspend or got an error; in either case,
+         * we need to prod all other other cpus out of join state.
+         * Extra prods are harmless.
+         */
+        for_each_online_cpu(cpu)
+                plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
 out:
-        local_irq_restore(flags);
-        return;
+        if (atomic_dec_return(&data->working) == 0)
+                complete(data->complete);
 }
 
 static int rtas_ibm_suspend_me(struct rtas_args *args)
 {
-        int i;
         long state;
         long rc;
         unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
         struct rtas_suspend_me_data data;
+        DECLARE_COMPLETION_ONSTACK(done);
+
+        if (!rtas_service_present("ibm,suspend-me"))
+                return -ENOSYS;
 
         /* Make sure the state is valid */
         rc = plpar_hcall(H_VASI_STATE, retbuf,
@@ -721,25 +740,23 @@ static int rtas_ibm_suspend_me(struct rtas_args *args)
                 return 0;
         }
 
-        data.waiting = 1;
-        data.args = args;
+        atomic_set(&data.working, 0);
+        data.token = rtas_token("ibm,suspend-me");
+        data.error = 0;
+        data.complete = &done;
 
         /* Call function on all CPUs.  One of us will make the
          * rtas call
          */
         if (on_each_cpu(rtas_percpu_suspend_me, &data, 1, 0))
-                data.waiting = -EINVAL;
+                data.error = -EINVAL;
 
-        if (data.waiting != 0)
-                printk(KERN_ERR "Error doing global join\n");
+        wait_for_completion(&done);
 
-        /* Prod each CPU.  This won't hurt, and will wake
-         * anyone we successfully put to sleep with H_JOIN.
-         */
-        for_each_possible_cpu(i)
-                plpar_hcall_norets(H_PROD, i);
+        if (data.error != 0)
+                printk(KERN_ERR "Error doing global join\n");
 
-        return data.waiting;
+        return data.error;
 }
 #else /* CONFIG_PPC_PSERIES */
 static int rtas_ibm_suspend_me(struct rtas_args *args)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index c0d77723ba11..a925a8eae121 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -241,8 +241,9 @@ void account_system_vtime(struct task_struct *tsk)
                 /* deltascaled includes both user and system time.
                  * Hence scale it based on the purr ratio to estimate
                  * the system time */
-                deltascaled = deltascaled * get_paca()->system_time /
-                        (get_paca()->system_time + get_paca()->user_time);
+                if (get_paca()->user_time)
+                        deltascaled = deltascaled * get_paca()->system_time /
+                             (get_paca()->system_time + get_paca()->user_time);
                 delta += get_paca()->system_time;
                 get_paca()->system_time = 0;
         }
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 2322ba5cce4c..3702df7dc567 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -699,11 +699,22 @@ static int __init vdso_init(void)
         vdso_data->icache_size = ppc64_caches.isize;
         vdso_data->icache_line_size = ppc64_caches.iline_size;
 
+        /* XXXOJN: Blocks should be added to ppc64_caches and used instead */
+        vdso_data->dcache_block_size = ppc64_caches.dline_size;
+        vdso_data->icache_block_size = ppc64_caches.iline_size;
+        vdso_data->dcache_log_block_size = ppc64_caches.log_dline_size;
+        vdso_data->icache_log_block_size = ppc64_caches.log_iline_size;
+
         /*
          * Calculate the size of the 64 bits vDSO
          */
         vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT;
         DBG("vdso64_kbase: %p, 0x%x pages\n", vdso64_kbase, vdso64_pages);
+#else
+        vdso_data->dcache_block_size = L1_CACHE_BYTES;
+        vdso_data->dcache_log_block_size = L1_CACHE_SHIFT;
+        vdso_data->icache_block_size = L1_CACHE_BYTES;
+        vdso_data->icache_log_block_size = L1_CACHE_SHIFT;
 #endif /* CONFIG_PPC64 */
 
 
diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S
index 9cb319992c38..1ba6feb71b31 100644
--- a/arch/powerpc/kernel/vdso32/cacheflush.S
+++ b/arch/powerpc/kernel/vdso32/cacheflush.S
@@ -23,29 +23,46 @@
  *
  * Flushes the data cache & invalidate the instruction cache for the
  * provided range [start, end[
- *
- * Note: all CPUs supported by this kernel have a 128 bytes cache
- * line size so we don't have to peek that info from the datapage
  */
 V_FUNCTION_BEGIN(__kernel_sync_dicache)
   .cfi_startproc
-        li      r5,127
-        andc    r6,r3,r5                /* round low to line bdy */
+        mflr    r12
+  .cfi_register lr,r12
+        mr      r11,r3
+        bl      __get_datapage@local
+        mtlr    r12
+        mr      r10,r3
+
+        lwz     r7,CFG_DCACHE_BLOCKSZ(r10)
+        addi    r5,r7,-1
+        andc    r6,r11,r5               /* round low to line bdy */
         subf    r8,r6,r4                /* compute length */
         add     r8,r8,r5                /* ensure we get enough */
-        srwi.   r8,r8,7                 /* compute line count */
+        lwz     r9,CFG_DCACHE_LOGBLOCKSZ(r10)
+        srw.    r8,r8,r9                /* compute line count */
         crclr   cr0*4+so
         beqlr                           /* nothing to do? */
         mtctr   r8
-        mr      r3,r6
-1:      dcbst   0,r3
-        addi    r3,r3,128
+1:      dcbst   0,r6
+        add     r6,r6,r7
         bdnz    1b
         sync
+
+/* Now invalidate the instruction cache */
+
+        lwz     r7,CFG_ICACHE_BLOCKSZ(r10)
+        addi    r5,r7,-1
+        andc    r6,r11,r5               /* round low to line bdy */
+        subf    r8,r6,r4                /* compute length */
+        add     r8,r8,r5
+        lwz     r9,CFG_ICACHE_LOGBLOCKSZ(r10)
+        srw.    r8,r8,r9                /* compute line count */
+        crclr   cr0*4+so
+        beqlr                           /* nothing to do? */
         mtctr   r8
-1:      icbi    0,r6
-        addi    r6,r6,128
-        bdnz    1b
+2:      icbi    0,r6
+        add     r6,r6,r7
+        bdnz    2b
         isync
         li      r3,0
         blr
diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S
index 66a36d3cc6ad..69c5af2b3c96 100644
--- a/arch/powerpc/kernel/vdso64/cacheflush.S
+++ b/arch/powerpc/kernel/vdso64/cacheflush.S
@@ -23,29 +23,46 @@
  *
  * Flushes the data cache & invalidate the instruction cache for the
  * provided range [start, end[
- *
- * Note: all CPUs supported by this kernel have a 128 bytes cache
- * line size so we don't have to peek that info from the datapage
  */
 V_FUNCTION_BEGIN(__kernel_sync_dicache)
   .cfi_startproc
-        li      r5,127
-        andc    r6,r3,r5                /* round low to line bdy */
+        mflr    r12
+  .cfi_register lr,r12
+        mr      r11,r3
+        bl      V_LOCAL_FUNC(__get_datapage)
+        mtlr    r12
+        mr      r10,r3
+
+        lwz     r7,CFG_DCACHE_BLOCKSZ(r10)
+        addi    r5,r7,-1
+        andc    r6,r11,r5               /* round low to line bdy */
         subf    r8,r6,r4                /* compute length */
         add     r8,r8,r5                /* ensure we get enough */
-        srwi.   r8,r8,7                 /* compute line count */
+        lwz     r9,CFG_DCACHE_LOGBLOCKSZ(r10)
+        srw.    r8,r8,r9                /* compute line count */
         crclr   cr0*4+so
         beqlr                           /* nothing to do? */
         mtctr   r8
-        mr      r3,r6
-1:      dcbst   0,r3
-        addi    r3,r3,128
+1:      dcbst   0,r6
+        add     r6,r6,r7
         bdnz    1b
         sync
+
+/* Now invalidate the instruction cache */
+
+        lwz     r7,CFG_ICACHE_BLOCKSZ(r10)
+        addi    r5,r7,-1
+        andc    r6,r11,r5               /* round low to line bdy */
+        subf    r8,r6,r4                /* compute length */
+        add     r8,r8,r5
+        lwz     r9,CFG_ICACHE_LOGBLOCKSZ(r10)
+        srw.    r8,r8,r9                /* compute line count */
+        crclr   cr0*4+so
+        beqlr                           /* nothing to do? */
         mtctr   r8
-1:      icbi    0,r6
-        addi    r6,r6,128
-        bdnz    1b
+2:      icbi    0,r6
+        add     r6,r6,r7
+        bdnz    2b
         isync
         li      r3,0
         blr
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index 9e85bda76216..50448d5de9d2 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -20,6 +20,7 @@
 #include <asm/lmb.h>
 #include <asm/abs_addr.h>
 #include <asm/firmware.h>
+#include <asm/iseries/hv_call.h>
 
 struct stab_entry {
         unsigned long esid_data;
diff --git a/arch/powerpc/platforms/40x/walnut.c b/arch/powerpc/platforms/40x/walnut.c
index eb0c136b1c44..ff6db2431798 100644
--- a/arch/powerpc/platforms/40x/walnut.c
+++ b/arch/powerpc/platforms/40x/walnut.c
@@ -17,12 +17,13 @@
  */
 
 #include <linux/init.h>
+#include <linux/of_platform.h>
+
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/time.h>
 #include <asm/uic.h>
-#include <asm/of_platform.h>
 
 static struct of_device_id walnut_of_bus[] = {
         { .compatible = "ibm,plb3", },
diff --git a/arch/powerpc/platforms/44x/bamboo.c b/arch/powerpc/platforms/44x/bamboo.c
index 470e1a3fd755..be23f112184f 100644
--- a/arch/powerpc/platforms/44x/bamboo.c
+++ b/arch/powerpc/platforms/44x/bamboo.c
@@ -14,12 +14,13 @@
  * option) any later version.
  */
 #include <linux/init.h>
+#include <linux/of_platform.h>
+
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/time.h>
 #include <asm/uic.h>
-#include <asm/of_platform.h>
 #include "44x.h"
 
 static struct of_device_id bamboo_of_bus[] = {
diff --git a/arch/powerpc/platforms/44x/ebony.c b/arch/powerpc/platforms/44x/ebony.c
index 40e18fcb666c..6cd3476767cc 100644
--- a/arch/powerpc/platforms/44x/ebony.c
+++ b/arch/powerpc/platforms/44x/ebony.c
@@ -17,12 +17,13 @@
  */
 
 #include <linux/init.h>
+#include <linux/of_platform.h>
+
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/time.h>
 #include <asm/uic.h>
-#include <asm/of_platform.h>
 
 #include "44x.h"
 
diff --git a/arch/powerpc/platforms/44x/sequoia.c b/arch/powerpc/platforms/44x/sequoia.c
index 30700b31d43b..21a9dd14f297 100644
--- a/arch/powerpc/platforms/44x/sequoia.c
+++ b/arch/powerpc/platforms/44x/sequoia.c
@@ -14,12 +14,13 @@
  * option) any later version.
  */
 #include <linux/init.h>
+#include <linux/of_platform.h>
+
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/time.h>
 #include <asm/uic.h>
-#include <asm/of_platform.h>
 #include "44x.h"
 
 static struct of_device_id sequoia_of_bus[] = {
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 0966d093db43..c0e968a4c211 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -171,6 +171,7 @@ static int spufs_rmdir(struct inode *parent, struct dentry *dir)
 {
         /* remove all entries */
         spufs_prune_dir(dir);
+        d_drop(dir);
 
         return simple_rmdir(parent, dir);
 }
diff --git a/arch/powerpc/platforms/embedded6xx/prpmc2800.c b/arch/powerpc/platforms/embedded6xx/prpmc2800.c
index e484cac75095..653a5eb91c90 100644
--- a/arch/powerpc/platforms/embedded6xx/prpmc2800.c
+++ b/arch/powerpc/platforms/embedded6xx/prpmc2800.c
@@ -144,6 +144,7 @@ static int __init prpmc2800_probe(void)
                 strncpy(prpmc2800_platform_name, m,
                         min((int)len, PLATFORM_NAME_MAX - 1));
 
+        _set_L2CR(_get_L2CR() | L2CR_L2E);
         return 1;
 }
 
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 3a5d112af5e0..3d62060498b4 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -214,7 +214,7 @@ static __init void pas_init_IRQ(void)
         printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
 
         mpic = mpic_alloc(mpic_node, openpic_addr,
-                          MPIC_PRIMARY|MPIC_LARGE_VECTORS|MPIC_WANTS_RESET,
+                          MPIC_PRIMARY|MPIC_LARGE_VECTORS,
                           0, 0, " PAS-OPIC  ");
         BUG_ON(!mpic);
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 16e4e401b820..306a9d07491d 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -21,7 +21,7 @@ config PPC_SPLPAR
 
 config EEH
         bool "PCI Extended Error Handling (EEH)" if EMBEDDED
-        depends on PPC_PSERIES
+        depends on PPC_PSERIES && PCI
         default y if !EMBEDDED
 
 config SCANLOG
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index fdb9b1c8f977..fdeefe54ea91 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -507,7 +507,8 @@ define_machine(pseries) {
         .restart                = rtas_restart,
         .power_off              = pSeries_power_off,
         .halt                   = rtas_halt,
-        .panic                  = rtas_os_term,
+        .panic                  = rtas_panic_msg,
+        .machine_shutdown       = rtas_os_term,
         .get_boot_time          = rtas_get_boot_time,
         .get_rtc_time           = rtas_get_rtc_time,
         .set_rtc_time           = rtas_set_rtc_time,
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 5149716c734d..847a5496b869 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -97,6 +97,22 @@ static void uic_ack_irq(unsigned int virq)
         spin_unlock_irqrestore(&uic->lock, flags);
 }
 
+static void uic_mask_ack_irq(unsigned int virq)
+{
+        struct uic *uic = get_irq_chip_data(virq);
+        unsigned int src = uic_irq_to_hw(virq);
+        unsigned long flags;
+        u32 er, sr;
+
+        sr = 1 << (31-src);
+        spin_lock_irqsave(&uic->lock, flags);
+        er = mfdcr(uic->dcrbase + UIC_ER);
+        er &= ~sr;
+        mtdcr(uic->dcrbase + UIC_ER, er);
+        mtdcr(uic->dcrbase + UIC_SR, sr);
+        spin_unlock_irqrestore(&uic->lock, flags);
+}
+
 static int uic_set_irq_type(unsigned int virq, unsigned int flow_type)
 {
         struct uic *uic = get_irq_chip_data(virq);
@@ -152,7 +168,7 @@ static struct irq_chip uic_irq_chip = {
         .typename       = " UIC  ",
         .unmask         = uic_unmask_irq,
         .mask           = uic_mask_irq,
-/*      .mask_ack       = uic_mask_irq_and_ack, */
+        .mask_ack       = uic_mask_ack_irq,
         .ack            = uic_ack_irq,
         .set_type       = uic_set_irq_type,
 };