10 files changed, 183 insertions, 107 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d8958be5f31a..502c7a4e73f7 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -80,10 +80,11 @@ int main(void)
         DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
 #else
         DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
+        DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
+        DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 #endif /* CONFIG_PPC64 */
 
         DEFINE(KSP, offsetof(struct thread_struct, ksp));
-        DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
         DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 #ifdef CONFIG_BOOKE
         DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0adab06ce5c0..572bb5b95f35 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -661,7 +661,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
         /* number of bytes needed for the bitmap */
         sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
 
-        page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz));
+        page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz));
         if (!page)
                 panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
         tbl->it_map = page_address(page);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c69440cef7af..c7cb8c232d2f 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -441,50 +441,6 @@ void migrate_irqs(void)
 }
 #endif
 
-static inline void handle_one_irq(unsigned int irq)
-{
-        struct thread_info *curtp, *irqtp;
-        unsigned long saved_sp_limit;
-        struct irq_desc *desc;
-
-        desc = irq_to_desc(irq);
-        if (!desc)
-                return;
-
-        /* Switch to the irq stack to handle this */
-        curtp = current_thread_info();
-        irqtp = hardirq_ctx[smp_processor_id()];
-
-        if (curtp == irqtp) {
-                /* We're already on the irq stack, just handle it */
-                desc->handle_irq(irq, desc);
-                return;
-        }
-
-        saved_sp_limit = current->thread.ksp_limit;
-
-        irqtp->task = curtp->task;
-        irqtp->flags = 0;
-
-        /* Copy the softirq bits in preempt_count so that the
-         * softirq checks work in the hardirq context. */
-        irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
-                               (curtp->preempt_count & SOFTIRQ_MASK);
-
-        current->thread.ksp_limit = (unsigned long)irqtp +
-                _ALIGN_UP(sizeof(struct thread_info), 16);
-
-        call_handle_irq(irq, desc, irqtp, desc->handle_irq);
-        current->thread.ksp_limit = saved_sp_limit;
-        irqtp->task = NULL;
-
-        /* Set any flag that may have been set on the
-         * alternate stack
-         */
-        if (irqtp->flags)
-                set_bits(irqtp->flags, &curtp->flags);
-}
-
 static inline void check_stack_overflow(void)
 {
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -501,9 +457,9 @@ static inline void check_stack_overflow(void)
 #endif
 }
 
-void do_IRQ(struct pt_regs *regs)
+void __do_irq(struct pt_regs *regs)
 {
-        struct pt_regs *old_regs = set_irq_regs(regs);
+        struct irq_desc *desc;
         unsigned int irq;
 
         irq_enter();
@@ -519,18 +475,57 @@ void do_IRQ(struct pt_regs *regs)
          */
         irq = ppc_md.get_irq();
 
-        /* We can hard enable interrupts now */
+        /* We can hard enable interrupts now to allow perf interrupts */
         may_hard_irq_enable();
 
         /* And finally process it */
-        if (irq != NO_IRQ)
-                handle_one_irq(irq);
-        else
+        if (unlikely(irq == NO_IRQ))
                 __get_cpu_var(irq_stat).spurious_irqs++;
+        else {
+                desc = irq_to_desc(irq);
+                if (likely(desc))
+                        desc->handle_irq(irq, desc);
+        }
 
         trace_irq_exit(regs);
 
         irq_exit();
+}
+
+void do_IRQ(struct pt_regs *regs)
+{
+        struct pt_regs *old_regs = set_irq_regs(regs);
+        struct thread_info *curtp, *irqtp, *sirqtp;
+
+        /* Switch to the irq stack to handle this */
+        curtp = current_thread_info();
+        irqtp = hardirq_ctx[raw_smp_processor_id()];
+        sirqtp = softirq_ctx[raw_smp_processor_id()];
+
+        /* Already there ? */
+        if (unlikely(curtp == irqtp || curtp == sirqtp)) {
+                __do_irq(regs);
+                set_irq_regs(old_regs);
+                return;
+        }
+
+        /* Prepare the thread_info in the irq stack */
+        irqtp->task = curtp->task;
+        irqtp->flags = 0;
+
+        /* Copy the preempt_count so that the [soft]irq checks work. */
+        irqtp->preempt_count = curtp->preempt_count;
+
+        /* Switch stack and call */
+        call_do_irq(regs, irqtp);
+
+        /* Restore stack limit */
+        irqtp->task = NULL;
+
+        /* Copy back updates to the thread_info */
+        if (irqtp->flags)
+                set_bits(irqtp->flags, &curtp->flags);
+
         set_irq_regs(old_regs);
 }
 
@@ -592,28 +587,22 @@ void irq_ctx_init(void)
                 memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
                 tp = softirq_ctx[i];
                 tp->cpu = i;
-                tp->preempt_count = 0;
 
                 memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
                 tp = hardirq_ctx[i];
                 tp->cpu = i;
-                tp->preempt_count = HARDIRQ_OFFSET;
         }
 }
 
 static inline void do_softirq_onstack(void)
 {
         struct thread_info *curtp, *irqtp;
-        unsigned long saved_sp_limit = current->thread.ksp_limit;
 
         curtp = current_thread_info();
         irqtp = softirq_ctx[smp_processor_id()];
         irqtp->task = curtp->task;
         irqtp->flags = 0;
-        current->thread.ksp_limit = (unsigned long)irqtp +
-                                    _ALIGN_UP(sizeof(struct thread_info), 16);
         call_do_softirq(irqtp);
-        current->thread.ksp_limit = saved_sp_limit;
         irqtp->task = NULL;
 
         /* Set any flag that may have been set on the
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 777d999f563b..2b0ad9845363 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -36,26 +36,41 @@
 
         .text
 
+/*
+ * We store the saved ksp_limit in the unused part
+ * of the STACK_FRAME_OVERHEAD
+ */
 _GLOBAL(call_do_softirq)
         mflr    r0
         stw     r0,4(r1)
+        lwz     r10,THREAD+KSP_LIMIT(r2)
+        addi    r11,r3,THREAD_INFO_GAP
         stwu    r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
         mr      r1,r3
+        stw     r10,8(r1)
+        stw     r11,THREAD+KSP_LIMIT(r2)
         bl      __do_softirq
+        lwz     r10,8(r1)
         lwz     r1,0(r1)
         lwz     r0,4(r1)
+        stw     r10,THREAD+KSP_LIMIT(r2)
         mtlr    r0
         blr
 
-_GLOBAL(call_handle_irq)
+_GLOBAL(call_do_irq)
         mflr    r0
         stw     r0,4(r1)
-        mtctr   r6
-        stwu    r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-        mr      r1,r5
-        bctrl
+        lwz     r10,THREAD+KSP_LIMIT(r2)
+        addi    r11,r3,THREAD_INFO_GAP
+        stwu    r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+        mr      r1,r4
+        stw     r10,8(r1)
+        stw     r11,THREAD+KSP_LIMIT(r2)
+        bl      __do_irq
+        lwz     r10,8(r1)
         lwz     r1,0(r1)
         lwz     r0,4(r1)
+        stw     r10,THREAD+KSP_LIMIT(r2)
         mtlr    r0
         blr
 
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 971d7e78aff2..e59caf874d05 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -40,14 +40,12 @@ _GLOBAL(call_do_softirq)
         mtlr    r0
         blr
 
-_GLOBAL(call_handle_irq)
-        ld      r8,0(r6)
+_GLOBAL(call_do_irq)
         mflr    r0
         std     r0,16(r1)
-        mtctr   r8
-        stdu    r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-        mr      r1,r5
-        bctrl
+        stdu    r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+        mr      r1,r4
+        bl      .__do_irq
         ld      r1,0(r1)
         ld      r0,16(r1)
         mtlr    r0
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 6f428da53e20..96d2fdf3aa9e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1000,9 +1000,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
         kregs = (struct pt_regs *) sp;
         sp -= STACK_FRAME_OVERHEAD;
         p->thread.ksp = sp;
+#ifdef CONFIG_PPC32
         p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
                                 _ALIGN_UP(sizeof(struct thread_info), 16);
-
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
         p->thread.ptrace_bps[0] = NULL;
 #endif
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 12e656ffe60e..5fe2842e8bab 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -196,6 +196,8 @@ static int __initdata mem_reserve_cnt;
 
 static cell_t __initdata regbuf[1024];
 
+static bool rtas_has_query_cpu_stopped;
+
 
 /*
  * Error results ... some OF calls will return "-1" on error, some
@@ -1574,6 +1576,11 @@ static void __init prom_instantiate_rtas(void)
         prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
                      &val, sizeof(val));
 
+        /* Check if it supports "query-cpu-stopped-state" */
+        if (prom_getprop(rtas_node, "query-cpu-stopped-state",
+                         &val, sizeof(val)) != PROM_ERROR)
+                rtas_has_query_cpu_stopped = true;
+
 #if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__)
         /* PowerVN takeover hack */
         prom_rtas_data = base;
@@ -1815,6 +1822,18 @@ static void __init prom_hold_cpus(void)
                 = (void *) LOW_ADDR(__secondary_hold_acknowledge);
         unsigned long secondary_hold = LOW_ADDR(__secondary_hold);
 
+        /*
+         * On pseries, if RTAS supports "query-cpu-stopped-state",
+         * we skip this stage, the CPUs will be started by the
+         * kernel using RTAS.
+         */
+        if ((of_platform == PLATFORM_PSERIES ||
+             of_platform == PLATFORM_PSERIES_LPAR) &&
+            rtas_has_query_cpu_stopped) {
+                prom_printf("prom_hold_cpus: skipped\n");
+                return;
+        }
+
         prom_debug("prom_hold_cpus: start...\n");
         prom_debug("    1) spinloop       = 0x%x\n", (unsigned long)spinloop);
         prom_debug("    1) *spinloop      = 0x%x\n", *spinloop);
@@ -3011,6 +3030,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
          * On non-powermacs, put all CPUs in spin-loops.
          *
          * PowerMacs use a different mechanism to spin CPUs
+         *
+         * (This must be done after instanciating RTAS)
          */
         if (of_platform != PLATFORM_POWERMAC &&
             of_platform != PLATFORM_OPAL)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 27a90b99ef67..b4e667663d9b 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -17,6 +17,7 @@
 #include <asm/machdep.h>
 #include <asm/smp.h>
 #include <asm/pmc.h>
+#include <asm/firmware.h>
 
 #include "cacheinfo.h"
 
@@ -179,15 +180,25 @@ SYSFS_PMCSETUP(spurr, SPRN_SPURR);
 SYSFS_PMCSETUP(dscr, SPRN_DSCR);
 SYSFS_PMCSETUP(pir, SPRN_PIR);
 
+/*
+  Lets only enable read for phyp resources and
+  enable write when needed with a separate function.
+  Lets be conservative and default to pseries.
+*/
 static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
 static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
-static DEVICE_ATTR(purr, 0600, show_purr, store_purr);
+static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
 
 unsigned long dscr_default = 0;
 EXPORT_SYMBOL(dscr_default);
 
+static void add_write_permission_dev_attr(struct device_attribute *attr)
+{
+        attr->attr.mode |= 0200;
+}
+
 static ssize_t show_dscr_default(struct device *dev,
                 struct device_attribute *attr, char *buf)
 {
@@ -394,8 +405,11 @@ static void register_cpu_online(unsigned int cpu)
         if (cpu_has_feature(CPU_FTR_MMCRA))
                 device_create_file(s, &dev_attr_mmcra);
 
-        if (cpu_has_feature(CPU_FTR_PURR))
+        if (cpu_has_feature(CPU_FTR_PURR)) {
+                if (!firmware_has_feature(FW_FEATURE_LPAR))
+                        add_write_permission_dev_attr(&dev_attr_purr);
                 device_create_file(s, &dev_attr_purr);
+        }
 
         if (cpu_has_feature(CPU_FTR_SPURR))
                 device_create_file(s, &dev_attr_spurr);
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 7b60b9851469..cd809eaa8b5c 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -79,6 +79,11 @@ _GLOBAL(tm_abort)
         TABORT(R3)
         blr
 
+        .section        ".toc","aw"
+DSCR_DEFAULT:
+        .tc dscr_default[TC],dscr_default
+
+        .section        ".text"
 
 /* void tm_reclaim(struct thread_struct *thread,
  *                 unsigned long orig_msr,
@@ -123,6 +128,7 @@ _GLOBAL(tm_reclaim)
         mr      r15, r14
         ori     r15, r15, MSR_FP
         li      r16, MSR_RI
+        ori     r16, r16, MSR_EE /* IRQs hard off */
         andc    r15, r15, r16
         oris    r15, r15, MSR_VEC@h
 #ifdef CONFIG_VSX
@@ -187,11 +193,18 @@ dont_backup_fp:
         std     r1, PACATMSCRATCH(r13)
         ld      r1, PACAR1(r13)
 
+        /* Store the PPR in r11 and reset to decent value */
+        std     r11, GPR11(r1)                  /* Temporary stash */
+        mfspr   r11, SPRN_PPR
+        HMT_MEDIUM
+
         /* Now get some more GPRS free */
         std     r7, GPR7(r1)                    /* Temporary stash */
         std     r12, GPR12(r1)                  /* ''   ''    ''   */
         ld      r12, STACK_PARAM(0)(r1)         /* Param 0, thread_struct * */
 
+        std     r11, THREAD_TM_PPR(r12)         /* Store PPR and free r11 */
+
         addi    r7, r12, PT_CKPT_REGS           /* Thread's ckpt_regs */
 
         /* Make r7 look like an exception frame so that we
@@ -203,15 +216,19 @@ dont_backup_fp:
         SAVE_GPR(0, r7)                         /* user r0 */
         SAVE_GPR(2, r7)                 /* user r2 */
         SAVE_4GPRS(3, r7)                       /* user r3-r6 */
-        SAVE_4GPRS(8, r7)                       /* user r8-r11 */
+        SAVE_GPR(8, r7)                         /* user r8 */
+        SAVE_GPR(9, r7)                         /* user r9 */
+        SAVE_GPR(10, r7)                        /* user r10 */
         ld      r3, PACATMSCRATCH(r13)          /* user r1 */
         ld      r4, GPR7(r1)                    /* user r7 */
-        ld      r5, GPR12(r1)                   /* user r12 */
-        GET_SCRATCH0(6)                         /* user r13 */
+        ld      r5, GPR11(r1)                   /* user r11 */
+        ld      r6, GPR12(r1)                   /* user r12 */
+        GET_SCRATCH0(8)                         /* user r13 */
         std     r3, GPR1(r7)
         std     r4, GPR7(r7)
-        std     r5, GPR12(r7)
-        std     r6, GPR13(r7)
+        std     r5, GPR11(r7)
+        std     r6, GPR12(r7)
+        std     r8, GPR13(r7)
 
         SAVE_NVGPRS(r7)                         /* user r14-r31 */
 
@@ -234,14 +251,12 @@ dont_backup_fp:
         std     r6, _XER(r7)
 
 
-        /* ******************** TAR, PPR, DSCR ********** */
+        /* ******************** TAR, DSCR ********** */
         mfspr   r3, SPRN_TAR
-        mfspr   r4, SPRN_PPR
-        mfspr   r5, SPRN_DSCR
+        mfspr   r4, SPRN_DSCR
 
         std     r3, THREAD_TM_TAR(r12)
-        std     r4, THREAD_TM_PPR(r12)
-        std     r5, THREAD_TM_DSCR(r12)
+        std     r4, THREAD_TM_DSCR(r12)
 
         /* MSR and flags:  We don't change CRs, and we don't need to alter
          * MSR.
@@ -258,7 +273,7 @@ dont_backup_fp:
         std     r3, THREAD_TM_TFHAR(r12)
         std     r4, THREAD_TM_TFIAR(r12)
 
-        /* AMR and PPR are checkpointed too, but are unsupported by Linux. */
+        /* AMR is checkpointed too, but is unsupported by Linux. */
 
         /* Restore original MSR/IRQ state & clear TM mode */
         ld      r14, TM_FRAME_L0(r1)            /* Orig MSR */
@@ -274,6 +289,12 @@ dont_backup_fp:
         mtcr    r4
         mtlr    r0
         ld      r2, 40(r1)
+
+        /* Load system default DSCR */
+        ld      r4, DSCR_DEFAULT@toc(r2)
+        ld      r0, 0(r4)
+        mtspr   SPRN_DSCR, r0
+
         blr
 
 
@@ -358,25 +379,24 @@ dont_restore_fp:
 
 restore_gprs:
 
-        /* ******************** TAR, PPR, DSCR ********** */
-        ld      r4, THREAD_TM_TAR(r3)
-        ld      r5, THREAD_TM_PPR(r3)
-        ld      r6, THREAD_TM_DSCR(r3)
+        /* ******************** CR,LR,CCR,MSR ********** */
+        ld      r4, _CTR(r7)
+        ld      r5, _LINK(r7)
+        ld      r6, _CCR(r7)
+        ld      r8, _XER(r7)
 
-        mtspr   SPRN_TAR,       r4
-        mtspr   SPRN_PPR,       r5
-        mtspr   SPRN_DSCR,      r6
+        mtctr   r4
+        mtlr    r5
+        mtcr    r6
+        mtxer   r8
 
-        /* ******************** CR,LR,CCR,MSR ********** */
-        ld      r3, _CTR(r7)
-        ld      r4, _LINK(r7)
-        ld      r5, _CCR(r7)
-        ld      r6, _XER(r7)
+        /* ******************** TAR ******************** */
+        ld      r4, THREAD_TM_TAR(r3)
+        mtspr   SPRN_TAR,       r4
 
-        mtctr   r3
-        mtlr    r4
-        mtcr    r5
-        mtxer   r6
+        /* Load up the PPR and DSCR in GPRs only at this stage */
+        ld      r5, THREAD_TM_DSCR(r3)
+        ld      r6, THREAD_TM_PPR(r3)
 
         /* Clear the MSR RI since we are about to change R1.  EE is already off
          */
@@ -384,19 +404,26 @@ restore_gprs:
         mtmsrd  r4, 1
 
         REST_4GPRS(0, r7)                       /* GPR0-3 */
-        REST_GPR(4, r7)                         /* GPR4-6 */
-        REST_GPR(5, r7)
-        REST_GPR(6, r7)
+        REST_GPR(4, r7)                         /* GPR4 */
         REST_4GPRS(8, r7)                       /* GPR8-11 */
         REST_2GPRS(12, r7)                      /* GPR12-13 */
 
         REST_NVGPRS(r7)                         /* GPR14-31 */
 
-        ld      r7, GPR7(r7)                    /* GPR7 */
+        /* Load up PPR and DSCR here so we don't run with user values for long
+         */
+        mtspr   SPRN_DSCR, r5
+        mtspr   SPRN_PPR, r6
+
+        REST_GPR(5, r7)                         /* GPR5-7 */
+        REST_GPR(6, r7)
+        ld      r7, GPR7(r7)
 
         /* Commit register state as checkpointed state: */
         TRECHKPT
 
+        HMT_MEDIUM
+
         /* Our transactional state has now changed.
          *
          * Now just get out of here.  Transactional (current) state will be
@@ -419,6 +446,12 @@ restore_gprs:
         mtcr    r4
         mtlr    r0
         ld      r2, 40(r1)
+
+        /* Load system default DSCR */
+        ld      r4, DSCR_DEFAULT@toc(r2)
+        ld      r0, 0(r4)
+        mtspr   SPRN_DSCR, r0
+
         blr
 
         /* ****************************************************************** */
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 78a350670de3..d38cc08b16c7 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1530,11 +1530,15 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
         const char *cp;
 
         dn = dev->of_node;
-        if (!dn)
-                return -ENODEV;
+        if (!dn) {
+                strcat(buf, "\n");
+                return strlen(buf);
+        }
         cp = of_get_property(dn, "compatible", NULL);
-        if (!cp)
-                return -ENODEV;
+        if (!cp) {
+                strcat(buf, "\n");
+                return strlen(buf);
+        }
 
         return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp);
 }