summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kernel')
-rw-r--r--arch/powerpc/kernel/Makefile2
-rw-r--r--arch/powerpc/kernel/asm-offsets.c2
-rw-r--r--arch/powerpc/kernel/dma-swiotlb.c48
-rw-r--r--arch/powerpc/kernel/dma.c6
-rw-r--r--arch/powerpc/kernel/entry_32.S127
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S19
-rw-r--r--arch/powerpc/kernel/head_32.S17
-rw-r--r--arch/powerpc/kernel/mpc7450-pmu.c4
-rw-r--r--arch/powerpc/kernel/of_device.c2
-rw-r--r--arch/powerpc/kernel/perf_callchain.c527
-rw-r--r--arch/powerpc/kernel/perf_counter.c8
-rw-r--r--arch/powerpc/kernel/power4-pmu.c3
-rw-r--r--arch/powerpc/kernel/power5+-pmu.c5
-rw-r--r--arch/powerpc/kernel/power5-pmu.c3
-rw-r--r--arch/powerpc/kernel/power6-pmu.c3
-rw-r--r--arch/powerpc/kernel/power7-pmu.c10
-rw-r--r--arch/powerpc/kernel/ppc970-pmu.c6
-rw-r--r--arch/powerpc/kernel/process.c2
-rw-r--r--arch/powerpc/kernel/ptrace.c17
-rw-r--r--arch/powerpc/kernel/ptrace32.c1
-rw-r--r--arch/powerpc/kernel/rtas.c69
-rw-r--r--arch/powerpc/kernel/setup_32.c2
-rw-r--r--arch/powerpc/kernel/smp.c3
-rw-r--r--arch/powerpc/kernel/udbg_16550.c2
-rw-r--r--arch/powerpc/kernel/vector.S6
25 files changed, 793 insertions, 101 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index b73396b9390..9619285f64e 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -97,7 +97,7 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
-obj-$(CONFIG_PPC_PERF_CTRS) += perf_counter.o
+obj-$(CONFIG_PPC_PERF_CTRS) += perf_counter.o perf_callchain.o
obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \
power5+-pmu.o power6-pmu.o power7-pmu.o
obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 561b6465231..197b15646ee 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -67,6 +67,8 @@ int main(void)
DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id));
#ifdef CONFIG_PPC64
DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context));
+ DEFINE(SIGSEGV, SIGSEGV);
+ DEFINE(NMI_MASK, NMI_MASK);
#else
DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 68ccf11e4f1..e8a57de85bc 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -24,50 +24,12 @@
int swiotlb __read_mostly;
unsigned int ppc_swiotlb_enable;
-void *swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t addr)
-{
- unsigned long pfn = PFN_DOWN(swiotlb_bus_to_phys(hwdev, addr));
- void *pageaddr = page_address(pfn_to_page(pfn));
-
- if (pageaddr != NULL)
- return pageaddr + (addr % PAGE_SIZE);
- return NULL;
-}
-
-dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
-{
- return paddr + get_dma_direct_offset(hwdev);
-}
-
-phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
-
-{
- return baddr - get_dma_direct_offset(hwdev);
-}
-
-/*
- * Determine if an address needs bounce buffering via swiotlb.
- * Going forward I expect the swiotlb code to generalize on using
- * a dma_ops->addr_needs_map, and this function will move from here to the
- * generic swiotlb code.
- */
-int
-swiotlb_arch_address_needs_mapping(struct device *hwdev, dma_addr_t addr,
- size_t size)
-{
- struct dma_mapping_ops *dma_ops = get_dma_ops(hwdev);
-
- BUG_ON(!dma_ops);
- return dma_ops->addr_needs_map(hwdev, addr, size);
-}
-
/*
* Determine if an address is reachable by a pci device, or if we must bounce.
*/
static int
swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
{
- u64 mask = dma_get_mask(hwdev);
dma_addr_t max;
struct pci_controller *hose;
struct pci_dev *pdev = to_pci_dev(hwdev);
@@ -79,16 +41,9 @@ swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
if ((addr + size > max) | (addr < hose->dma_window_base_cur))
return 1;
- return !is_buffer_dma_capable(mask, addr, size);
-}
-
-static int
-swiotlb_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
-{
- return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+ return 0;
}
-
/*
* At the moment, all platforms that use this code only require
* swiotlb to be used if we're operating on HIGHMEM. Since
@@ -104,7 +59,6 @@ struct dma_mapping_ops swiotlb_dma_ops = {
.dma_supported = swiotlb_dma_supported,
.map_page = swiotlb_map_page,
.unmap_page = swiotlb_unmap_page,
- .addr_needs_map = swiotlb_addr_needs_map,
.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 20a60d661ba..ccf129d47d8 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -7,6 +7,7 @@
#include <linux/device.h>
#include <linux/dma-mapping.h>
+#include <linux/lmb.h>
#include <asm/bug.h>
#include <asm/abs_addr.h>
@@ -90,11 +91,10 @@ static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
static int dma_direct_dma_supported(struct device *dev, u64 mask)
{
#ifdef CONFIG_PPC64
- /* Could be improved to check for memory though it better be
- * done via some global so platforms can set the limit in case
+ /* Could be improved so platforms can set the limit in case
* they have limited DMA windows
*/
- return mask >= DMA_BIT_MASK(32);
+ return mask >= (lmb_end_of_DRAM() - 1);
#else
return 1;
#endif
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 4dd38f12915..3cadba60a4b 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -191,11 +191,49 @@ transfer_to_handler_cont:
mflr r9
lwz r11,0(r9) /* virtual address of handler */
lwz r9,4(r9) /* where to go when done */
+#ifdef CONFIG_TRACE_IRQFLAGS
+ lis r12,reenable_mmu@h
+ ori r12,r12,reenable_mmu@l
+ mtspr SPRN_SRR0,r12
+ mtspr SPRN_SRR1,r10
+ SYNC
+ RFI
+reenable_mmu: /* re-enable mmu so we can */
+ mfmsr r10
+ lwz r12,_MSR(r1)
+ xor r10,r10,r12
+ andi. r10,r10,MSR_EE /* Did EE change? */
+ beq 1f
+
+ /* Save handler and return address into the 2 unused words
+ * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
+ * else can be recovered from the pt_regs except r3 which for
+ * normal interrupts has been set to pt_regs and for syscalls
+ * is an argument, so we temporarily use ORIG_GPR3 to save it
+ */
+ stw r9,8(r1)
+ stw r11,12(r1)
+ stw r3,ORIG_GPR3(r1)
+ bl trace_hardirqs_off
+ lwz r0,GPR0(r1)
+ lwz r3,ORIG_GPR3(r1)
+ lwz r4,GPR4(r1)
+ lwz r5,GPR5(r1)
+ lwz r6,GPR6(r1)
+ lwz r7,GPR7(r1)
+ lwz r8,GPR8(r1)
+ lwz r9,8(r1)
+ lwz r11,12(r1)
+1: mtctr r11
+ mtlr r9
+ bctr /* jump to handler */
+#else /* CONFIG_TRACE_IRQFLAGS */
mtspr SPRN_SRR0,r11
mtspr SPRN_SRR1,r10
mtlr r9
SYNC
RFI /* jump to handler, enable MMU */
+#endif /* CONFIG_TRACE_IRQFLAGS */
#if defined (CONFIG_6xx) || defined(CONFIG_E500)
4: rlwinm r12,r12,0,~_TLF_NAPPING
@@ -251,6 +289,31 @@ _GLOBAL(DoSyscall)
#ifdef SHOW_SYSCALLS
bl do_show_syscall
#endif /* SHOW_SYSCALLS */
+#ifdef CONFIG_TRACE_IRQFLAGS
+ /* Return from syscalls can (and generally will) hard enable
+ * interrupts. You aren't supposed to call a syscall with
+ * interrupts disabled in the first place. However, to ensure
+ * that we get it right vs. lockdep if it happens, we force
+ * that hard enable here with appropriate tracing if we see
+ * that we have been called with interrupts off
+ */
+ mfmsr r11
+ andi. r12,r11,MSR_EE
+ bne+ 1f
+ /* We came in with interrupts disabled, we enable them now */
+ bl trace_hardirqs_on
+ mfmsr r11
+ lwz r0,GPR0(r1)
+ lwz r3,GPR3(r1)
+ lwz r4,GPR4(r1)
+ ori r11,r11,MSR_EE
+ lwz r5,GPR5(r1)
+ lwz r6,GPR6(r1)
+ lwz r7,GPR7(r1)
+ lwz r8,GPR8(r1)
+ mtmsr r11
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
rlwinm r10,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */
lwz r11,TI_FLAGS(r10)
andi. r11,r11,_TIF_SYSCALL_T_OR_A
@@ -275,6 +338,7 @@ ret_from_syscall:
rlwinm r12,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */
/* disable interrupts so current_thread_info()->flags can't change */
LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
+ /* Note: We don't bother telling lockdep about it */
SYNC
MTMSRD(r10)
lwz r9,TI_FLAGS(r12)
@@ -288,6 +352,19 @@ ret_from_syscall:
oris r11,r11,0x1000 /* Set SO bit in CR */
stw r11,_CCR(r1)
syscall_exit_cont:
+ lwz r8,_MSR(r1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+ /* If we are going to return from the syscall with interrupts
+ * off, we trace that here. It shouldn't happen though but we
+ * want to catch the bugger if it does right ?
+ */
+ andi. r10,r8,MSR_EE
+ bne+ 1f
+ stw r3,GPR3(r1)
+ bl trace_hardirqs_off
+ lwz r3,GPR3(r1)
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
/* If the process has its own DBCR0 value, load it up. The internal
debug mode bit tells us that dbcr0 should be loaded. */
@@ -311,7 +388,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
mtlr r4
mtcr r5
lwz r7,_NIP(r1)
- lwz r8,_MSR(r1)
FIX_SRR1(r8, r0)
lwz r2,GPR2(r1)
lwz r1,GPR1(r1)
@@ -394,7 +470,9 @@ syscall_exit_work:
andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
beq ret_from_except
- /* Re-enable interrupts */
+ /* Re-enable interrupts. There is no need to trace that with
+ * lockdep as we are supposed to have IRQs on at this point
+ */
ori r10,r10,MSR_EE
SYNC
MTMSRD(r10)
@@ -705,6 +783,7 @@ ret_from_except:
/* Hard-disable interrupts so that current_thread_info()->flags
* can't change between when we test it and when we return
* from the interrupt. */
+ /* Note: We don't bother telling lockdep about it */
LOAD_MSR_KERNEL(r10,MSR_KERNEL)
SYNC /* Some chip revs have problems here... */
MTMSRD(r10) /* disable interrupts */
@@ -744,11 +823,24 @@ resume_kernel:
beq+ restore
andi. r0,r3,MSR_EE /* interrupts off? */
beq restore /* don't schedule if so */
+#ifdef CONFIG_TRACE_IRQFLAGS
+ /* Lockdep thinks irqs are enabled, we need to call
+ * preempt_schedule_irq with IRQs off, so we inform lockdep
+ * now that we -did- turn them off already
+ */
+ bl trace_hardirqs_off
+#endif
1: bl preempt_schedule_irq
rlwinm r9,r1,0,0,(31-THREAD_SHIFT)
lwz r3,TI_FLAGS(r9)
andi. r0,r3,_TIF_NEED_RESCHED
bne- 1b
+#ifdef CONFIG_TRACE_IRQFLAGS
+ /* And now, to properly rebalance the above, we tell lockdep they
+ * are being turned back on, which will happen when we return
+ */
+ bl trace_hardirqs_on
+#endif
#else
resume_kernel:
#endif /* CONFIG_PREEMPT */
@@ -765,6 +857,28 @@ restore:
stw r6,icache_44x_need_flush@l(r4)
1:
#endif /* CONFIG_44x */
+
+ lwz r9,_MSR(r1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+ /* Lockdep doesn't know about the fact that IRQs are temporarily turned
+ * off in this assembly code while peeking at TI_FLAGS() and such. However
+ * we need to inform it if the exception turned interrupts off, and we
+ * are about to trun them back on.
+ *
+ * The problem here sadly is that we don't know whether the exceptions was
+ * one that turned interrupts off or not. So we always tell lockdep about
+ * turning them on here when we go back to wherever we came from with EE
+ * on, even if that may meen some redudant calls being tracked. Maybe later
+ * we could encode what the exception did somewhere or test the exception
+ * type in the pt_regs but that sounds overkill
+ */
+ andi. r10,r9,MSR_EE
+ beq 1f
+ bl trace_hardirqs_on
+ lwz r9,_MSR(r1)
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
lwz r0,GPR0(r1)
lwz r2,GPR2(r1)
REST_4GPRS(3, r1)
@@ -782,7 +896,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
stwcx. r0,0,r1 /* to clear the reservation */
#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
- lwz r9,_MSR(r1)
andi. r10,r9,MSR_RI /* check if this exception occurred */
beql nonrecoverable /* at a bad place (MSR:RI = 0) */
@@ -805,7 +918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
MTMSRD(r10) /* clear the RI bit */
.globl exc_exit_restart
exc_exit_restart:
- lwz r9,_MSR(r1)
lwz r12,_NIP(r1)
FIX_SRR1(r9,r10)
mtspr SPRN_SRR0,r12
@@ -1035,11 +1147,18 @@ do_work: /* r10 contains MSR_KERNEL here */
beq do_user_signal
do_resched: /* r10 contains MSR_KERNEL here */
+ /* Note: We don't need to inform lockdep that we are enabling
+ * interrupts here. As far as it knows, they are already enabled
+ */
ori r10,r10,MSR_EE
SYNC
MTMSRD(r10) /* hard-enable interrupts */
bl schedule
recheck:
+ /* Note: And we don't tell it we are disabling them again
+ * neither. Those disable/enable cycles used to peek at
+ * TI_FLAGS aren't advertised.
+ */
LOAD_MSR_KERNEL(r10,MSR_KERNEL)
SYNC
MTMSRD(r10) /* disable interrupts */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index eb898112e57..8ac85e08ffa 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -729,6 +729,11 @@ BEGIN_FTR_SECTION
bne- do_ste_alloc /* If so handle it */
END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
+ clrrdi r11,r1,THREAD_SHIFT
+ lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */
+ andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */
+ bne 77f /* then don't call hash_page now */
+
/*
* On iSeries, we soft-disable interrupts here, then
* hard-enable interrupts so that the hash_page code can spin on
@@ -833,6 +838,20 @@ handle_page_fault:
bl .low_hash_fault
b .ret_from_except
+/*
+ * We come here as a result of a DSI at a point where we don't want
+ * to call hash_page, such as when we are accessing memory (possibly
+ * user memory) inside a PMU interrupt that occurred while interrupts
+ * were soft-disabled. We want to invoke the exception handler for
+ * the access, or panic if there isn't a handler.
+ */
+77: bl .save_nvgprs
+ mr r4,r3
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ li r5,SIGSEGV
+ bl .bad_page_fault
+ b .ret_from_except
+
/* here we have a segment miss */
do_ste_alloc:
bl .ste_allocate /* try to insert stab entry */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 48469463f89..fc213294275 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -1124,9 +1124,8 @@ mmu_off:
RFI
/*
- * Use the first pair of BAT registers to map the 1st 16MB
- * of RAM to PAGE_OFFSET. From this point on we can't safely
- * call OF any more.
+ * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET
+ * (we keep one for debugging) and on others, we use one 256M BAT.
*/
initial_bats:
lis r11,PAGE_OFFSET@h
@@ -1136,12 +1135,16 @@ initial_bats:
bne 4f
ori r11,r11,4 /* set up BAT registers for 601 */
li r8,0x7f /* valid, block length = 8MB */
- oris r9,r11,0x800000@h /* set up BAT reg for 2nd 8M */
- oris r10,r8,0x800000@h /* set up BAT reg for 2nd 8M */
mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */
mtspr SPRN_IBAT0L,r8 /* lower BAT register */
- mtspr SPRN_IBAT1U,r9
- mtspr SPRN_IBAT1L,r10
+ addis r11,r11,0x800000@h
+ addis r8,r8,0x800000@h
+ mtspr SPRN_IBAT1U,r11
+ mtspr SPRN_IBAT1L,r8
+ addis r11,r11,0x800000@h
+ addis r8,r8,0x800000@h
+ mtspr SPRN_IBAT2U,r11
+ mtspr SPRN_IBAT2L,r8
isync
blr
diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c
index 75ff47fed7b..cc466d039af 100644
--- a/arch/powerpc/kernel/mpc7450-pmu.c
+++ b/arch/powerpc/kernel/mpc7450-pmu.c
@@ -10,7 +10,6 @@
*/
#include <linux/string.h>
#include <linux/perf_counter.h>
-#include <linux/string.h>
#include <asm/reg.h>
#include <asm/cputable.h>
@@ -408,7 +407,8 @@ struct power_pmu mpc7450_pmu = {
static int init_mpc7450_pmu(void)
{
- if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450"))
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450"))
return -ENODEV;
return register_power_pmu(&mpc7450_pmu);
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index fa983a59c4c..a359cb08e90 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -76,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np,
dev->dev.archdata.of_node = np;
if (bus_id)
- dev_set_name(&dev->dev, bus_id);
+ dev_set_name(&dev->dev, "%s", bus_id);
else
of_device_make_bus_id(dev);
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
new file mode 100644
index 00000000000..f74b62c6751
--- /dev/null
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -0,0 +1,527 @@
+/*
+ * Performance counter callchain support - powerpc architecture code
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corporation.
+ *
+ * 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
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_counter.h>
+#include <linux/percpu.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <asm/ptrace.h>
+#include <asm/pgtable.h>
+#include <asm/sigcontext.h>
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#ifdef CONFIG_PPC64
+#include "ppc32.h"
+#endif
+
+/*
+ * Store another value in a callchain_entry.
+ */
+static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+ unsigned int nr = entry->nr;
+
+ if (nr < PERF_MAX_STACK_DEPTH) {
+ entry->ip[nr] = ip;
+ entry->nr = nr + 1;
+ }
+}
+
+/*
+ * Is sp valid as the address of the next kernel stack frame after prev_sp?
+ * The next frame may be in a different stack area but should not go
+ * back down in the same stack area.
+ */
+static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
+{
+ if (sp & 0xf)
+ return 0; /* must be 16-byte aligned */
+ if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
+ return 0;
+ if (sp >= prev_sp + STACK_FRAME_OVERHEAD)
+ return 1;
+ /*
+ * sp could decrease when we jump off an interrupt stack
+ * back to the regular process stack.
+ */
+ if ((sp & ~(THREAD_SIZE - 1)) != (prev_sp & ~(THREAD_SIZE - 1)))
+ return 1;
+ return 0;
+}
+
+static void perf_callchain_kernel(struct pt_regs *regs,
+ struct perf_callchain_entry *entry)
+{
+ unsigned long sp, next_sp;
+ unsigned long next_ip;
+ unsigned long lr;
+ long level = 0;
+ unsigned long *fp;
+
+ lr = regs->link;
+ sp = regs->gpr[1];
+ callchain_store(entry, PERF_CONTEXT_KERNEL);
+ callchain_store(entry, regs->nip);
+
+ if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
+ return;
+
+ for (;;) {
+ fp = (unsigned long *) sp;
+ next_sp = fp[0];
+
+ if (next_sp == sp + STACK_INT_FRAME_SIZE &&
+ fp[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
+ /*
+ * This looks like an interrupt frame for an
+ * interrupt that occurred in the kernel
+ */
+ regs = (struct pt_regs *)(sp + STACK_FRAME_OVERHEAD);
+ next_ip = regs->nip;
+ lr = regs->link;
+ level = 0;
+ callchain_store(entry, PERF_CONTEXT_KERNEL);
+
+ } else {
+ if (level == 0)
+ next_ip = lr;
+ else
+ next_ip = fp[STACK_FRAME_LR_SAVE];
+
+ /*
+ * We can't tell which of the first two addresses
+ * we get are valid, but we can filter out the
+ * obviously bogus ones here. We replace them
+ * with 0 rather than removing them entirely so
+ * that userspace can tell which is which.
+ */
+ if ((level == 1 && next_ip == lr) ||
+ (level <= 1 && !kernel_text_address(next_ip)))
+ next_ip = 0;
+
+ ++level;
+ }
+
+ callchain_store(entry, next_ip);
+ if (!valid_next_sp(next_sp, sp))
+ return;
+ sp = next_sp;
+ }
+}
+
+#ifdef CONFIG_PPC64
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define is_huge_psize(pagesize) (HPAGE_SHIFT && mmu_huge_psizes[pagesize])
+#else
+#define is_huge_psize(pagesize) 0
+#endif
+
+/*
+ * On 64-bit we don't want to invoke hash_page on user addresses from
+ * interrupt context, so if the access faults, we read the page tables
+ * to find which page (if any) is mapped and access it directly.
+ */
+static int read_user_stack_slow(void __user *ptr, void *ret, int nb)
+{
+ pgd_t *pgdir;
+ pte_t *ptep, pte;
+ int pagesize;
+ unsigned long addr = (unsigned long) ptr;
+ unsigned long offset;
+ unsigned long pfn;
+ void *kaddr;
+
+ pgdir = current->mm->pgd;
+ if (!pgdir)
+ return -EFAULT;
+
+ pagesize = get_slice_psize(current->mm, addr);
+
+ /* align address to page boundary */
+ offset = addr & ((1ul << mmu_psize_defs[pagesize].shift) - 1);
+ addr -= offset;
+
+ if (is_huge_psize(pagesize))
+ ptep = huge_pte_offset(current->mm, addr);
+ else
+ ptep = find_linux_pte(pgdir, addr);
+
+ if (ptep == NULL)
+ return -EFAULT;
+ pte = *ptep;
+ if (!pte_present(pte) || !(pte_val(pte) & _PAGE_USER))
+ return -EFAULT;
+ pfn = pte_pfn(pte);
+ if (!page_is_ram(pfn))
+ return -EFAULT;
+
+ /* no highmem to worry about here */
+ kaddr = pfn_to_kaddr(pfn);
+ memcpy(ret, kaddr + offset, nb);
+ return 0;
+}
+
+static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
+{
+ if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned long) ||
+ ((unsigned long)ptr & 7))
+ return -EFAULT;
+
+ if (!__get_user_inatomic(*ret, ptr))
+ return 0;
+
+ return read_user_stack_slow(ptr, ret, 8);
+}
+
+static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
+{
+ if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
+ ((unsigned long)ptr & 3))
+ return -EFAULT;
+
+ if (!__get_user_inatomic(*ret, ptr))
+ return 0;
+
+ return read_user_stack_slow(ptr, ret, 4);
+}
+
+static inline int valid_user_sp(unsigned long sp, int is_64)
+{
+ if (!sp || (sp & 7) || sp > (is_64 ? TASK_SIZE : 0x100000000UL) - 32)
+ return 0;
+ return 1;
+}
+
+/*
+ * 64-bit user processes use the same stack frame for RT and non-RT signals.
+ */
+struct signal_frame_64 {
+ char dummy[__SIGNAL_FRAMESIZE];
+ struct ucontext uc;
+ unsigned long unused[2];
+ unsigned int tramp[6];
+ struct siginfo *pinfo;
+ void *puc;
+ struct siginfo info;
+ char abigap[288];
+};
+
+static int is_sigreturn_64_address(unsigned long nip, unsigned long fp)
+{
+ if (nip == fp + offsetof(struct signal_frame_64, tramp))
+ return 1;
+ if (vdso64_rt_sigtramp && current->mm->context.vdso_base &&
+ nip == current->mm->context.vdso_base + vdso64_rt_sigtramp)
+ return 1;
+ return 0;
+}
+
+/*
+ * Do some sanity checking on the signal frame pointed to by sp.
+ * We check the pinfo and puc pointers in the frame.
+ */
+static int sane_signal_64_frame(unsigned long sp)
+{
+ struct signal_frame_64 __user *sf;
+ unsigned long pinfo, puc;
+
+ sf = (struct signal_frame_64 __user *) sp;
+ if (read_user_stack_64((unsigned long __user *) &sf->pinfo, &pinfo) ||
+ read_user_stack_64((unsigned long __user *) &sf->puc, &puc))
+ return 0;
+ return pinfo == (unsigned long) &sf->info &&
+ puc == (unsigned long) &sf->uc;
+}
+
+static void perf_callchain_user_64(struct pt_regs *regs,
+ struct perf_callchain_entry *entry)
+{
+ unsigned long sp, next_sp;
+ unsigned long next_ip;
+ unsigned long lr;
+ long level = 0;
+ struct signal_frame_64 __user *sigframe;
+ unsigned long __user *fp, *uregs;
+
+ next_ip = regs->nip;
+ lr = regs->link;
+ sp = regs->gpr[1];
+ callchain_store(entry, PERF_CONTEXT_USER);
+ callchain_store(entry, next_ip);
+
+ for (;;) {
+ fp = (unsigned long __user *) sp;
+ if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
+ return;
+ if (level > 0 && read_user_stack_64(&fp[2], &next_ip))
+ return;
+
+ /*
+ * Note: the next_sp - sp >= signal frame size check
+ * is true when next_sp < sp, which can happen when
+ * transitioning from an alternate signal stack to the
+ * normal stack.
+ */
+ if (next_sp - sp >= sizeof(struct signal_frame_64) &&
+ (is_sigreturn_64_address(next_ip, sp) ||
+ (level <= 1 && is_sigreturn_64_address(lr, sp))) &&
+ sane_signal_64_frame(sp)) {
+ /*
+ * This looks like an signal frame
+ */
+ sigframe = (struct signal_frame_64 __user *) sp;
+ uregs = sigframe->uc.uc_mcontext.gp_regs;
+ if (read_user_stack_64(&uregs[PT_NIP], &next_ip) ||
+ read_user_stack_64(&uregs[PT_LNK], &lr) ||
+ read_user_stack_64(&uregs[PT_R1], &sp))
+ return;
+ level = 0;
+ callchain_store(entry, PERF_CONTEXT_USER);
+ callchain_store(entry, next_ip);
+ continue;
+ }
+
+ if (level == 0)
+ next_ip = lr;
+ callchain_store(entry, next_ip);
+ ++level;
+ sp = next_sp;
+ }
+}
+
+static inline int current_is_64bit(void)
+{
+ /*
+ * We can't use test_thread_flag() here because we may be on an
+ * interrupt stack, and the thread flags don't get copied over
+ * from the thread_info on the main stack to the interrupt stack.
+ */
+ return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT);
+}
+
+#else /* CONFIG_PPC64 */
+/*
+ * On 32-bit we just access the address and let hash_page create a
+ * HPTE if necessary, so there is no need to fall back to reading
+ * the page tables. Since this is called at interrupt level,
+ * do_page_fault() won't treat a DSI as a page fault.
+ */
+static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
+{
+ if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
+ ((unsigned long)ptr & 3))
+ return -EFAULT;
+
+ return __get_user_inatomic(*ret, ptr);
+}
+
+static inline void perf_callchain_user_64(struct pt_regs *regs,
+ struct perf_callchain_entry *entry)
+{
+}
+
+static inline int current_is_64bit(void)
+{
+ return 0;
+}
+
+static inline int valid_user_sp(unsigned long sp, int is_64)
+{
+ if (!sp || (sp & 7) || sp > TASK_SIZE - 32)
+ return 0;
+ return 1;
+}
+
+#define __SIGNAL_FRAMESIZE32 __SIGNAL_FRAMESIZE
+#define sigcontext32 sigcontext
+#define mcontext32 mcontext
+#define ucontext32 ucontext
+#define compat_siginfo_t struct siginfo
+
+#endif /* CONFIG_PPC64 */
+
+/*
+ * Layout for non-RT signal frames
+ */
+struct signal_frame_32 {
+ char dummy[__SIGNAL_FRAMESIZE32];
+ struct sigcontext32 sctx;
+ struct mcontext32 mctx;
+ int abigap[56];
+};
+
+/*
+ * Layout for RT signal frames
+ */
+struct rt_signal_frame_32 {
+ char dummy[__SIGNAL_FRAMESIZE32 + 16];
+ compat_siginfo_t info;
+ struct ucontext32 uc;
+ int abigap[56];
+};
+
+static int is_sigreturn_32_address(unsigned int nip, unsigned int fp)
+{
+ if (nip == fp + offsetof(struct signal_frame_32, mctx.mc_pad))
+ return 1;
+ if (vdso32_sigtramp && current->mm->context.vdso_base &&
+ nip == current->mm->context.vdso_base + vdso32_sigtramp)
+ return 1;
+ return 0;
+}
+
+static int is_rt_sigreturn_32_address(unsigned int nip, unsigned int fp)
+{
+ if (nip == fp + offsetof(struct rt_signal_frame_32,
+ uc.uc_mcontext.mc_pad))
+ return 1;
+ if (vdso32_rt_sigtramp && current->mm->context.vdso_base &&
+ nip == current->mm->context.vdso_base + vdso32_rt_sigtramp)
+ return 1;
+ return 0;
+}
+
+static int sane_signal_32_frame(unsigned int sp)
+{
+ struct signal_frame_32 __user *sf;
+ unsigned int regs;
+
+ sf = (struct signal_frame_32 __user *) (unsigned long) sp;
+ if (read_user_stack_32((unsigned int __user *) &sf->sctx.regs, &regs))
+ return 0;
+ return regs == (unsigned long) &sf->mctx;
+}
+
+static int sane_rt_signal_32_frame(unsigned int sp)
+{
+ struct rt_signal_frame_32 __user *sf;
+ unsigned int regs;
+
+ sf = (struct rt_signal_frame_32 __user *) (unsigned long) sp;
+ if (read_user_stack_32((unsigned int __user *) &sf->uc.uc_regs, &regs))
+ return 0;
+ return regs == (unsigned long) &sf->uc.uc_mcontext;
+}
+
+static unsigned int __user *signal_frame_32_regs(unsigned int sp,
+ unsigned int next_sp, unsigned int next_ip)
+{
+ struct mcontext32 __user *mctx = NULL;
+ struct signal_frame_32 __user *sf;
+ struct rt_signal_frame_32 __user *rt_sf;
+
+ /*
+ * Note: the next_sp - sp >= signal frame size check
+ * is true when next_sp < sp, for example, when
+ * transitioning from an alternate signal stack to the
+ * normal stack.
+ */
+ if (next_sp - sp >= sizeof(struct signal_frame_32) &&
+ is_sigreturn_32_address(next_ip, sp) &&
+ sane_signal_32_frame(sp)) {
+ sf = (struct signal_frame_32 __user *) (unsigned long) sp;
+ mctx = &sf->mctx;
+ }
+
+ if (!mctx && next_sp - sp >= sizeof(struct rt_signal_frame_32) &&
+ is_rt_sigreturn_32_address(next_ip, sp) &&
+ sane_rt_signal_32_frame(sp)) {
+ rt_sf = (struct rt_signal_frame_32 __user *) (unsigned long) sp;
+ mctx = &rt_sf->uc.uc_mcontext;
+ }
+
+ if (!mctx)
+ return NULL;
+ return mctx->mc_gregs;
+}
+
+static void perf_callchain_user_32(struct pt_regs *regs,
+ struct perf_callchain_entry *entry)
+{
+ unsigned int sp, next_sp;
+ unsigned int next_ip;
+ unsigned int lr;
+ long level = 0;
+ unsigned int __user *fp, *uregs;
+
+ next_ip = regs->nip;
+ lr = regs->link;
+ sp = regs->gpr[1];
+ callchain_store(entry, PERF_CONTEXT_USER);
+ callchain_store(entry, next_ip);
+
+ while (entry->nr < PERF_MAX_STACK_DEPTH) {
+ fp = (unsigned int __user *) (unsigned long) sp;
+ if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
+ return;
+ if (level > 0 && read_user_stack_32(&fp[1], &next_ip))
+ return;
+
+ uregs = signal_frame_32_regs(sp, next_sp, next_ip);
+ if (!uregs && level <= 1)
+ uregs = signal_frame_32_regs(sp, next_sp, lr);
+ if (uregs) {
+ /*
+ * This looks like an signal frame, so restart
+ * the stack trace with the values in it.
+ */
+ if (read_user_stack_32(&uregs[PT_NIP], &next_ip) ||
+ read_user_stack_32(&uregs[PT_LNK], &lr) ||
+ read_user_stack_32(&uregs[PT_R1], &sp))
+ return;
+ level = 0;
+ callchain_store(entry, PERF_CONTEXT_USER);
+ callchain_store(entry, next_ip);
+ continue;
+ }
+
+ if (level == 0)
+ next_ip = lr;
+ callchain_store(entry, next_ip);
+ ++level;
+ sp = next_sp;
+ }
+}
+
+/*
+ * Since we can't get PMU interrupts inside a PMU interrupt handler,
+ * we don't need separate irq and nmi entries here.
+ */
+static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
+
+struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+ struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
+
+ entry->nr = 0;
+
+ if (current->pid == 0) /* idle task? */
+ return entry;
+
+ if (!user_mode(regs)) {
+ perf_callchain_kernel(regs, entry);
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+
+ if (regs) {
+ if (current_is_64bit())
+ perf_callchain_user_64(regs, entry);
+ else
+ perf_callchain_user_32(regs, entry);
+ }
+
+ return entry;
+}
diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
index 809fdf94b95..70e1f57f7dd 100644
--- a/arch/powerpc/kernel/perf_counter.c
+++ b/arch/powerpc/kernel/perf_counter.c
@@ -518,6 +518,8 @@ void hw_perf_disable(void)
struct cpu_hw_counters *cpuhw;
unsigned long flags;
+ if (!ppmu)
+ return;
local_irq_save(flags);
cpuhw = &__get_cpu_var(cpu_hw_counters);
@@ -572,6 +574,8 @@ void hw_perf_enable(void)
int n_lim;
int idx;
+ if (!ppmu)
+ return;
local_irq_save(flags);
cpuhw = &__get_cpu_var(cpu_hw_counters);
if (!cpuhw->disabled) {
@@ -737,6 +741,8 @@ int hw_perf_group_sched_in(struct perf_counter *group_leader,
long i, n, n0;
struct perf_counter *sub;
+ if (!ppmu)
+ return 0;
cpuhw = &__get_cpu_var(cpu_hw_counters);
n0 = cpuhw->n_counters;
n = collect_events(group_leader, ppmu->n_counter - n0,
@@ -1281,6 +1287,8 @@ void hw_perf_counter_setup(int cpu)
{
struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu);
+ if (!ppmu)
+ return;
memset(cpuhw, 0, sizeof(*cpuhw));
cpuhw->mmcr[0] = MMCR0_FC;
}
diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c
index db90b0c5c27..3c90a3d9173 100644
--- a/arch/powerpc/kernel/power4-pmu.c
+++ b/arch/powerpc/kernel/power4-pmu.c
@@ -606,7 +606,8 @@ static struct power_pmu power4_pmu = {
static int init_power4_pmu(void)
{
- if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power4"))
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power4"))
return -ENODEV;
return register_power_pmu(&power4_pmu);
diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c
index f4adca8e98a..31918af3e35 100644
--- a/arch/powerpc/kernel/power5+-pmu.c
+++ b/arch/powerpc/kernel/power5+-pmu.c
@@ -678,8 +678,9 @@ static struct power_pmu power5p_pmu = {
static int init_power5p_pmu(void)
{
- if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+")
- && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5++"))
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+")
+ && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5++")))
return -ENODEV;
return register_power_pmu(&power5p_pmu);
diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c
index 29b2c6c0e83..867f6f66396 100644
--- a/arch/powerpc/kernel/power5-pmu.c
+++ b/arch/powerpc/kernel/power5-pmu.c
@@ -618,7 +618,8 @@ static struct power_pmu power5_pmu = {
static int init_power5_pmu(void)
{
- if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5"))
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5"))
return -ENODEV;
return register_power_pmu(&power5_pmu);
diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c
index 09ae5bf5bda..fa21890531d 100644
--- a/arch/powerpc/kernel/power6-pmu.c
+++ b/arch/powerpc/kernel/power6-pmu.c
@@ -537,7 +537,8 @@ static struct power_pmu power6_pmu = {
static int init_power6_pmu(void)
{
- if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6"))
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6"))
return -ENODEV;
return register_power_pmu(&power6_pmu);
diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c
index 5d755ef7ac8..018d094d92f 100644
--- a/arch/powerpc/kernel/power7-pmu.c
+++ b/arch/powerpc/kernel/power7-pmu.c
@@ -317,7 +317,7 @@ static int power7_generic_events[] = {
*/
static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0x400f0, 0xc880 },
+ [C(OP_READ)] = { 0xc880, 0x400f0 },
[C(OP_WRITE)] = { 0, 0x300f0 },
[C(OP_PREFETCH)] = { 0xd8b8, 0 },
},
@@ -327,8 +327,8 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_PREFETCH)] = { 0x408a, 0 },
},
[C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0x6080, 0x6084 },
- [C(OP_WRITE)] = { 0x6082, 0x6086 },
+ [C(OP_READ)] = { 0x16080, 0x26080 },
+ [C(OP_WRITE)] = { 0x16082, 0x26082 },
[C(OP_PREFETCH)] = { 0, 0 },
},
[C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
@@ -358,6 +358,7 @@ static struct power_pmu power7_pmu = {
.get_constraint = power7_get_constraint,
.get_alternatives = power7_get_alternatives,
.disable_pmc = power7_disable_pmc,
+ .flags = PPMU_ALT_SIPR,
.n_generic = ARRAY_SIZE(power7_generic_events),
.generic_events = power7_generic_events,
.cache_events = &power7_cache_events,
@@ -365,7 +366,8 @@ static struct power_pmu power7_pmu = {
static int init_power7_pmu(void)
{
- if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7"))
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7"))
return -ENODEV;
return register_power_pmu(&power7_pmu);
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
index 6637c87fe70..75dccb71a04 100644
--- a/arch/powerpc/kernel/ppc970-pmu.c
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -10,7 +10,6 @@
*/
#include <linux/string.h>
#include <linux/perf_counter.h>
-#include <linux/string.h>
#include <asm/reg.h>
#include <asm/cputable.h>
@@ -489,8 +488,9 @@ static struct power_pmu ppc970_pmu = {
static int init_ppc970_pmu(void)
{
- if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970")
- && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970MP"))
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970")
+ && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970MP")))
return -ENODEV;
return register_power_pmu(&ppc970_pmu);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3e7135bbe40..892a9f2e6d7 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -528,7 +528,7 @@ void show_regs(struct pt_regs * regs)
for (i = 0; i < 32; i++) {
if ((i % REGS_PER_LINE) == 0)
- printk("\n" KERN_INFO "GPR%02d: ", i);
+ printk("\nGPR%02d: ", i);
printk(REG " ", regs->gpr[i]);
if (i == LAST_VOLATILE && !FULL_REGS(regs))
break;
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 9fa2c7dcd05..ef149880c14 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -736,15 +736,16 @@ void user_disable_single_step(struct task_struct *task)
{
struct pt_regs *regs = task->thread.regs;
-
-#if defined(CONFIG_BOOKE)
- /* If DAC then do not single step, skip */
- if (task->thread.dabr)
- return;
-#endif
-
if (regs != NULL) {
-#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+#if defined(CONFIG_BOOKE)
+ /* If DAC don't clear DBCRO_IDM or MSR_DE */
+ if (task->thread.dabr)
+ task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT);
+ else {
+ task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT | DBCR0_IDM);
+ regs->msr &= ~MSR_DE;
+ }
+#elif defined(CONFIG_40x)
task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT | DBCR0_IDM);
regs->msr &= ~MSR_DE;
#else
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c
index 297632cba04..8a6daf4129f 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace32.c
@@ -21,7 +21,6 @@
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
-#include <linux/smp_lock.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/regset.h>
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index ee4c7609b64..c434823b8c8 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -38,9 +38,10 @@
#include <asm/syscalls.h>
#include <asm/smp.h>
#include <asm/atomic.h>
+#include <asm/time.h>
struct rtas_t rtas = {
- .lock = SPIN_LOCK_UNLOCKED
+ .lock = __RAW_SPIN_LOCK_UNLOCKED
};
EXPORT_SYMBOL(rtas);
@@ -67,6 +68,28 @@ unsigned long rtas_rmo_buf;
void (*rtas_flash_term_hook)(int);
EXPORT_SYMBOL(rtas_flash_term_hook);
+/* RTAS use home made raw locking instead of spin_lock_irqsave
+ * because those can be called from within really nasty contexts
+ * such as having the timebase stopped which would lockup with
+ * normal locks and spinlock debugging enabled
+ */
+static unsigned long lock_rtas(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ preempt_disable();
+ __raw_spin_lock_flags(&rtas.lock, flags);
+ return flags;
+}
+
+static void unlock_rtas(unsigned long flags)
+{
+ __raw_spin_unlock(&rtas.lock);
+ local_irq_restore(flags);
+ preempt_enable();
+}
+
/*
* call_rtas_display_status and call_rtas_display_status_delay
* are designed only for very early low-level debugging, which
@@ -79,7 +102,7 @@ static void call_rtas_display_status(char c)
if (!rtas.base)
return;
- spin_lock_irqsave(&rtas.lock, s);
+ s = lock_rtas();
args->token = 10;
args->nargs = 1;
@@ -89,7 +112,7 @@ static void call_rtas_display_status(char c)
enter_rtas(__pa(args));
- spin_unlock_irqrestore(&rtas.lock, s);
+ unlock_rtas(s);
}
static void call_rtas_display_status_delay(char c)
@@ -411,8 +434,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
return -1;
- /* Gotta do something different here, use global lock for now... */
- spin_lock_irqsave(&rtas.lock, s);
+ s = lock_rtas();
rtas_args = &rtas.args;
rtas_args->token = token;
@@ -439,8 +461,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
outputs[i] = rtas_args->rets[i+1];
ret = (nret > 0)? rtas_args->rets[0]: 0;
- /* Gotta do something different here, use global lock for now... */
- spin_unlock_irqrestore(&rtas.lock, s);
+ unlock_rtas(s);
if (buff_copy) {
log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
@@ -837,7 +858,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
buff_copy = get_errorlog_buffer();
- spin_lock_irqsave(&rtas.lock, flags);
+ flags = lock_rtas();
rtas.args = args;
enter_rtas(__pa(&rtas.args));
@@ -848,7 +869,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
if (args.rets[0] == -1)
errbuf = __fetch_rtas_last_error(buff_copy);
- spin_unlock_irqrestore(&rtas.lock, flags);
+ unlock_rtas(flags);
if (buff_copy) {
if (errbuf)
@@ -951,3 +972,33 @@ int __init early_init_dt_scan_rtas(unsigned long node,
/* break now */
return 1;
}
+
+static raw_spinlock_t timebase_lock;
+static u64 timebase = 0;
+
+void __cpuinit rtas_give_timebase(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ hard_irq_disable();
+ __raw_spin_lock(&timebase_lock);
+ rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
+ timebase = get_tb();
+ __raw_spin_unlock(&timebase_lock);
+
+ while (timebase)
+ barrier();
+ rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
+ local_irq_restore(flags);
+}
+
+void __cpuinit rtas_take_timebase(void)
+{
+ while (!timebase)
+ barrier();
+ __raw_spin_lock(&timebase_lock);
+ set_tb(timebase >> 32, timebase & 0xffffffff);
+ timebase = 0;
+ __raw_spin_unlock(&timebase_lock);
+}
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 1d154248cf4..e1e3059cf34 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -119,6 +119,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
*/
notrace void __init machine_init(unsigned long dt_ptr)
{
+ lockdep_init();
+
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 65484b2200b..0b47de07302 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -68,7 +68,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
/* SMP operations for this machine */
struct smp_ops_t *smp_ops;
-static volatile unsigned int cpu_callin_map[NR_CPUS];
+/* Can't be static due to PowerMac hackery */
+volatile unsigned int cpu_callin_map[NR_CPUS];
int smt_enabled_at_boot = 1;
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 0362a891e54..acb74a17bbb 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -219,7 +219,7 @@ void udbg_init_pas_realmode(void)
#ifdef CONFIG_PPC_EARLY_DEBUG_44x
#include <platforms/44x/44x.h>
-static int udbg_44x_as1_flush(void)
+static void udbg_44x_as1_flush(void)
{
if (udbg_comport) {
while ((as1_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index ef36cbbc588..ea4d64644d0 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -80,10 +80,10 @@ _GLOBAL(load_up_altivec)
mtvscr vr0
REST_32VRS(0,r4,r5)
#ifndef CONFIG_SMP
- /* Update last_task_used_math to 'current' */
+ /* Update last_task_used_altivec to 'current' */
subi r4,r5,THREAD /* Back to 'current' */
fromreal(r4)
- PPC_STL r4,ADDROFF(last_task_used_math)(r3)
+ PPC_STL r4,ADDROFF(last_task_used_altivec)(r3)
#endif /* CONFIG_SMP */
/* restore registers and return */
blr
@@ -172,7 +172,7 @@ _GLOBAL(load_up_vsx)
oris r12,r12,MSR_VSX@h
std r12,_MSR(r1)
#ifndef CONFIG_SMP
- /* Update last_task_used_math to 'current' */
+ /* Update last_task_used_vsx to 'current' */
ld r4,PACACURRENT(r13)
std r4,0(r3)
#endif /* CONFIG_SMP */