10 files changed, 130 insertions, 148 deletions

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index c9aac24b02e2..6eb75b80488c 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -100,6 +100,14 @@ static inline void hard_irq_disable(void)
         get_paca()->irq_happened |= PACA_IRQ_HARD_DIS;
 }
 
+/* include/linux/interrupt.h needs hard_irq_disable to be a macro */
+#define hard_irq_disable        hard_irq_disable
+
+static inline bool lazy_irq_pending(void)
+{
+        return !!(get_paca()->irq_happened & ~PACA_IRQ_HARD_DIS);
+}
+
 /*
  * This is called by asynchronous interrupts to conditionally
  * re-enable hard interrupts when soft-disabled after having
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index ed1718feb9d9..5971c85df136 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -558,27 +558,54 @@ _GLOBAL(ret_from_except_lite)
         mtmsrd  r10,1             /* Update machine state */
 #endif /* CONFIG_PPC_BOOK3E */
 
-#ifdef CONFIG_PREEMPT
         clrrdi  r9,r1,THREAD_SHIFT      /* current_thread_info() */
-        li      r0,_TIF_NEED_RESCHED    /* bits to check */
         ld      r3,_MSR(r1)
         ld      r4,TI_FLAGS(r9)
-        /* Move MSR_PR bit in r3 to _TIF_SIGPENDING position in r0 */
-        rlwimi  r0,r3,32+TIF_SIGPENDING-MSR_PR_LG,_TIF_SIGPENDING
-        and.    r0,r4,r0        /* check NEED_RESCHED and maybe SIGPENDING */
-        bne     do_work
-
-#else /* !CONFIG_PREEMPT */
-        ld      r3,_MSR(r1)     /* Returning to user mode? */
         andi.   r3,r3,MSR_PR
-        beq     restore         /* if not, just restore regs and return */
+        beq     resume_kernel
 
         /* Check current_thread_info()->flags */
+        andi.   r0,r4,_TIF_USER_WORK_MASK
+        beq     restore
+
+        andi.   r0,r4,_TIF_NEED_RESCHED
+        beq     1f
+        bl      .restore_interrupts
+        bl      .schedule
+        b       .ret_from_except_lite
+
+1:      bl      .save_nvgprs
+        bl      .restore_interrupts
+        addi    r3,r1,STACK_FRAME_OVERHEAD
+        bl      .do_notify_resume
+        b       .ret_from_except
+
+resume_kernel:
+#ifdef CONFIG_PREEMPT
+        /* Check if we need to preempt */
+        andi.   r0,r4,_TIF_NEED_RESCHED
+        beq+    restore
+        /* Check that preempt_count() == 0 and interrupts are enabled */
+        lwz     r8,TI_PREEMPT(r9)
+        cmpwi   cr1,r8,0
+        ld      r0,SOFTE(r1)
+        cmpdi   r0,0
+        crandc  eq,cr1*4+eq,eq
+        bne     restore
+
+        /*
+         * Here we are preempting the current task. We want to make
+         * sure we are soft-disabled first
+         */
+        SOFT_DISABLE_INTS(r3,r4)
+1:      bl      .preempt_schedule_irq
+
+        /* Re-test flags and eventually loop */
         clrrdi  r9,r1,THREAD_SHIFT
         ld      r4,TI_FLAGS(r9)
-        andi.   r0,r4,_TIF_USER_WORK_MASK
-        bne     do_work
-#endif /* !CONFIG_PREEMPT */
+        andi.   r0,r4,_TIF_NEED_RESCHED
+        bne     1b
+#endif /* CONFIG_PREEMPT */
 
         .globl  fast_exc_return_irq
 fast_exc_return_irq:
@@ -759,50 +786,6 @@ restore_check_irq_replay:
 #endif /* CONFIG_PPC_BOOK3E */
 1:      b       .ret_from_except /* What else to do here ? */
  
-
-
-3:
-do_work:
-#ifdef CONFIG_PREEMPT
-        andi.   r0,r3,MSR_PR    /* Returning to user mode? */
-        bne     user_work
-        /* Check that preempt_count() == 0 and interrupts are enabled */
-        lwz     r8,TI_PREEMPT(r9)
-        cmpwi   cr1,r8,0
-        ld      r0,SOFTE(r1)
-        cmpdi   r0,0
-        crandc  eq,cr1*4+eq,eq
-        bne     restore
-
-        /*
-         * Here we are preempting the current task. We want to make
-         * sure we are soft-disabled first
-         */
-        SOFT_DISABLE_INTS(r3,r4)
-1:      bl      .preempt_schedule_irq
-
-        /* Re-test flags and eventually loop */
-        clrrdi  r9,r1,THREAD_SHIFT
-        ld      r4,TI_FLAGS(r9)
-        andi.   r0,r4,_TIF_NEED_RESCHED
-        bne     1b
-        b       restore
-
-user_work:
-#endif /* CONFIG_PREEMPT */
-
-        andi.   r0,r4,_TIF_NEED_RESCHED
-        beq     1f
-        bl      .restore_interrupts
-        bl      .schedule
-        b       .ret_from_except_lite
-
-1:      bl      .save_nvgprs
-        bl      .restore_interrupts
-        addi    r3,r1,STACK_FRAME_OVERHEAD
-        bl      .do_notify_resume
-        b       .ret_from_except
-
 unrecov_restore:
         addi    r3,r1,STACK_FRAME_OVERHEAD
         bl      .unrecoverable_exception
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 7835a5e1ea5f..1b415027ec0e 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -277,7 +277,7 @@ EXPORT_SYMBOL(arch_local_irq_restore);
  * NOTE: This is called with interrupts hard disabled but not marked
  * as such in paca->irq_happened, so we need to resync this.
  */
-void restore_interrupts(void)
+void notrace restore_interrupts(void)
 {
         if (irqs_disabled()) {
                 local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 1b488e5305c5..0794a3017b1b 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1312,7 +1312,7 @@ static struct opal_secondary_data {
 
 extern char opal_secondary_entry;
 
-static void prom_query_opal(void)
+static void __init prom_query_opal(void)
 {
         long rc;
 
@@ -1436,7 +1436,7 @@ static void __init prom_opal_hold_cpus(void)
         prom_debug("prom_opal_hold_cpus: end...\n");
 }
 
-static void prom_opal_takeover(void)
+static void __init prom_opal_takeover(void)
 {
         struct opal_secondary_data *data = &RELOC(opal_secondary_data);
         struct opal_takeover_args *args = &data->args;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c6af1d623839..3abe1b86e583 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -268,24 +268,45 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
         return err;
 }
 
-static void kvmppc_update_vpa(struct kvm *kvm, struct kvmppc_vpa *vpap)
+static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 {
+        struct kvm *kvm = vcpu->kvm;
         void *va;
         unsigned long nb;
+        unsigned long gpa;
 
-        vpap->update_pending = 0;
-        va = NULL;
-        if (vpap->next_gpa) {
-                va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb);
-                if (nb < vpap->len) {
-                        /*
-                         * If it's now too short, it must be that userspace
-                         * has changed the mappings underlying guest memory,
-                         * so unregister the region.
-                         */
+        /*
+         * We need to pin the page pointed to by vpap->next_gpa,
+         * but we can't call kvmppc_pin_guest_page under the lock
+         * as it does get_user_pages() and down_read().  So we
+         * have to drop the lock, pin the page, then get the lock
+         * again and check that a new area didn't get registered
+         * in the meantime.
+         */
+        for (;;) {
+                gpa = vpap->next_gpa;
+                spin_unlock(&vcpu->arch.vpa_update_lock);
+                va = NULL;
+                nb = 0;
+                if (gpa)
+                        va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb);
+                spin_lock(&vcpu->arch.vpa_update_lock);
+                if (gpa == vpap->next_gpa)
+                        break;
+                /* sigh... unpin that one and try again */
+                if (va)
                         kvmppc_unpin_guest_page(kvm, va);
-                        va = NULL;
-                }
+        }
+
+        vpap->update_pending = 0;
+        if (va && nb < vpap->len) {
+                /*
+                 * If it's now too short, it must be that userspace
+                 * has changed the mappings underlying guest memory,
+                 * so unregister the region.
+                 */
+                kvmppc_unpin_guest_page(kvm, va);
+                va = NULL;
         }
         if (vpap->pinned_addr)
                 kvmppc_unpin_guest_page(kvm, vpap->pinned_addr);
@@ -296,20 +317,18 @@ static void kvmppc_update_vpa(struct kvm *kvm, struct kvmppc_vpa *vpap)
 
 static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 {
-        struct kvm *kvm = vcpu->kvm;
-
         spin_lock(&vcpu->arch.vpa_update_lock);
         if (vcpu->arch.vpa.update_pending) {
-                kvmppc_update_vpa(kvm, &vcpu->arch.vpa);
+                kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
                 init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
         }
         if (vcpu->arch.dtl.update_pending) {
-                kvmppc_update_vpa(kvm, &vcpu->arch.dtl);
+                kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
                 vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
                 vcpu->arch.dtl_index = 0;
         }
         if (vcpu->arch.slb_shadow.update_pending)
-                kvmppc_update_vpa(kvm, &vcpu->arch.slb_shadow);
+                kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
         spin_unlock(&vcpu->arch.vpa_update_lock);
 }
 
@@ -800,12 +819,39 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
         struct kvm_vcpu *vcpu, *vcpu0, *vnext;
         long ret;
         u64 now;
-        int ptid, i;
+        int ptid, i, need_vpa_update;
 
         /* don't start if any threads have a signal pending */
-        list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+        need_vpa_update = 0;
+        list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
                 if (signal_pending(vcpu->arch.run_task))
                         return 0;
+                need_vpa_update |= vcpu->arch.vpa.update_pending |
+                        vcpu->arch.slb_shadow.update_pending |
+                        vcpu->arch.dtl.update_pending;
+        }
+
+        /*
+         * Initialize *vc, in particular vc->vcore_state, so we can
+         * drop the vcore lock if necessary.
+         */
+        vc->n_woken = 0;
+        vc->nap_count = 0;
+        vc->entry_exit_count = 0;
+        vc->vcore_state = VCORE_RUNNING;
+        vc->in_guest = 0;
+        vc->napping_threads = 0;
+
+        /*
+         * Updating any of the vpas requires calling kvmppc_pin_guest_page,
+         * which can't be called with any spinlocks held.
+         */
+        if (need_vpa_update) {
+                spin_unlock(&vc->lock);
+                list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+                        kvmppc_update_vpas(vcpu);
+                spin_lock(&vc->lock);
+        }
 
         /*
          * Make sure we are running on thread 0, and that
@@ -838,20 +884,10 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
                 if (vcpu->arch.ceded)
                         vcpu->arch.ptid = ptid++;
 
-        vc->n_woken = 0;
-        vc->nap_count = 0;
-        vc->entry_exit_count = 0;
-        vc->vcore_state = VCORE_RUNNING;
         vc->stolen_tb += mftb() - vc->preempt_tb;
-        vc->in_guest = 0;
         vc->pcpu = smp_processor_id();
-        vc->napping_threads = 0;
         list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
                 kvmppc_start_thread(vcpu);
-                if (vcpu->arch.vpa.update_pending ||
-                    vcpu->arch.slb_shadow.update_pending ||
-                    vcpu->arch.dtl.update_pending)
-                        kvmppc_update_vpas(vcpu);
                 kvmppc_create_dtl_entry(vcpu, vc);
         }
         /* Grab any remaining hw threads so they can't go into the kernel */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b6edbb3b4a54..6e8f677f5646 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -635,7 +635,7 @@ static inline int __init read_usm_ranges(const u32 **usm)
  */
 static void __init parse_drconf_memory(struct device_node *memory)
 {
-        const u32 *dm, *usm;
+        const u32 *uninitialized_var(dm), *usm;
         unsigned int n, rc, ranges, is_kexec_kdump = 0;
         unsigned long lmb_size, base, size, sz;
         int nid;
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index 55ba3855a97f..7d3a3b5619a2 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -105,6 +105,7 @@ sk_load_byte_msh_positive_offset:
         mr      r4, r_addr;                                     \
         li      r6, SIZE;                                       \
         bl      skb_copy_bits;                                  \
+        nop;                                                    \
         /* R3 = 0 on success */                                 \
         addi    r1, r1, BPF_PPC_SLOWPATH_FRAME;                 \
         ld      r0, 16(r1);                                     \
@@ -156,6 +157,7 @@ bpf_slow_path_byte_msh:
         mr      r4, r_addr;                                     \
         li      r5, SIZE;                                       \
         bl      bpf_internal_load_pointer_neg_helper;           \
+        nop;                                                    \
         /* R3 != 0 on success */                                \
         addi    r1, r1, BPF_PPC_SLOWPATH_FRAME;                 \
         ld      r0, 16(r1);                                     \
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 0915b1ad66ce..2d311c0caf8e 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -106,7 +106,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
                 tcep++;
         }
 
-        if (tbl->it_type == TCE_PCI_SWINV_CREATE)
+        if (tbl->it_type & TCE_PCI_SWINV_CREATE)
                 tce_invalidate_pSeries_sw(tbl, tces, tcep - 1);
         return 0;
 }
@@ -121,7 +121,7 @@ static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
         while (npages--)
                 *(tcep++) = 0;
 
-        if (tbl->it_type == TCE_PCI_SWINV_FREE)
+        if (tbl->it_type & TCE_PCI_SWINV_FREE)
                 tce_invalidate_pSeries_sw(tbl, tces, tcep - 1);
 }
 
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 36f957f31842..8733a86ad52e 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -68,9 +68,7 @@ static const char *pseries_nvram_os_partitions[] = {
 };
 
 static void oops_to_nvram(struct kmsg_dumper *dumper,
-                enum kmsg_dump_reason reason,
-                const char *old_msgs, unsigned long old_len,
-                const char *new_msgs, unsigned long new_len);
+                          enum kmsg_dump_reason reason);
 
 static struct kmsg_dumper nvram_kmsg_dumper = {
         .dump = oops_to_nvram
@@ -504,28 +502,6 @@ int __init pSeries_nvram_init(void)
 }
 
 /*
- * Try to capture the last capture_len bytes of the printk buffer.  Return
- * the amount actually captured.
- */
-static size_t capture_last_msgs(const char *old_msgs, size_t old_len,
-                                const char *new_msgs, size_t new_len,
-                                char *captured, size_t capture_len)
-{
-        if (new_len >= capture_len) {
-                memcpy(captured, new_msgs + (new_len - capture_len),
-                                                                capture_len);
-                return capture_len;
-        } else {
-                /* Grab the end of old_msgs. */
-                size_t old_tail_len = min(old_len, capture_len - new_len);
-                memcpy(captured, old_msgs + (old_len - old_tail_len),
-                                                                old_tail_len);
-                memcpy(captured + old_tail_len, new_msgs, new_len);
-                return old_tail_len + new_len;
-        }
-}
-
-/*
  * Are we using the ibm,rtas-log for oops/panic reports?  And if so,
  * would logging this oops/panic overwrite an RTAS event that rtas_errd
  * hasn't had a chance to read and process?  Return 1 if so, else 0.
@@ -541,27 +517,6 @@ static int clobbering_unread_rtas_event(void)
                                                 NVRAM_RTAS_READ_TIMEOUT);
 }
 
-/* Squeeze out each line's <n> severity prefix. */
-static size_t elide_severities(char *buf, size_t len)
-{
-        char *in, *out, *buf_end = buf + len;
-        /* Assume a <n> at the very beginning marks the start of a line. */
-        int newline = 1;
-
-        in = out = buf;
-        while (in < buf_end) {
-                if (newline && in+3 <= buf_end &&
-                                *in == '<' && isdigit(in[1]) && in[2] == '>') {
-                        in += 3;
-                        newline = 0;
-                } else {
-                        newline = (*in == '\n');
-                        *out++ = *in++;
-                }
-        }
-        return out - buf;
-}
-
 /* Derived from logfs_compress() */
 static int nvram_compress(const void *in, void *out, size_t inlen,
                                                         size_t outlen)
@@ -619,9 +574,7 @@ static int zip_oops(size_t text_len)
  * partition.  If that's too much, go back and capture uncompressed text.
  */
 static void oops_to_nvram(struct kmsg_dumper *dumper,
-                enum kmsg_dump_reason reason,
-                const char *old_msgs, unsigned long old_len,
-                const char *new_msgs, unsigned long new_len)
+                          enum kmsg_dump_reason reason)
 {
         static unsigned int oops_count = 0;
         static bool panicking = false;
@@ -660,14 +613,14 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
                 return;
 
         if (big_oops_buf) {
-                text_len = capture_last_msgs(old_msgs, old_len,
-                        new_msgs, new_len, big_oops_buf, big_oops_buf_sz);
-                text_len = elide_severities(big_oops_buf, text_len);
+                kmsg_dump_get_buffer(dumper, false,
+                                     big_oops_buf, big_oops_buf_sz, &text_len);
                 rc = zip_oops(text_len);
         }
         if (rc != 0) {
-                text_len = capture_last_msgs(old_msgs, old_len,
-                                new_msgs, new_len, oops_data, oops_data_sz);
+                kmsg_dump_rewind(dumper);
+                kmsg_dump_get_buffer(dumper, true,
+                                     oops_data, oops_data_sz, &text_len);
                 err_type = ERR_TYPE_KERNEL_PANIC;
                 *oops_len = (u16) text_len;
         }
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
index 41a34bc4a9a2..e61483e8e960 100644
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -106,7 +106,7 @@ static void check_and_cede_processor(void)
          * we first hard disable then check.
          */
         hard_irq_disable();
-        if (get_paca()->irq_happened == 0)
+        if (!lazy_irq_pending())
                 cede_processor();
 }