summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel
diff options
context:
space:
mode:
authorAndré Fabian Silva Delgado <emulatorman@parabola.nu>2015-12-15 14:52:16 -0300
committerAndré Fabian Silva Delgado <emulatorman@parabola.nu>2015-12-15 14:52:16 -0300
commit8d91c1e411f55d7ea91b1183a2e9f8088fb4d5be (patch)
treee9891aa6c295060d065adffd610c4f49ecf884f3 /arch/powerpc/kernel
parenta71852147516bc1cb5b0b3cbd13639bfd4022dc8 (diff)
Linux-libre 4.3.2-gnu
Diffstat (limited to 'arch/powerpc/kernel')
-rw-r--r--arch/powerpc/kernel/Makefile1
-rw-r--r--arch/powerpc/kernel/asm-offsets.c10
-rw-r--r--arch/powerpc/kernel/dma-iommu.c2
-rw-r--r--arch/powerpc/kernel/dma-swiotlb.c4
-rw-r--r--arch/powerpc/kernel/dma.c118
-rw-r--r--arch/powerpc/kernel/eeh.c4
-rw-r--r--arch/powerpc/kernel/eeh_pe.c22
-rw-r--r--arch/powerpc/kernel/entry_32.S7
-rw-r--r--arch/powerpc/kernel/entry_64.S28
-rw-r--r--arch/powerpc/kernel/exceptions-64e.S13
-rw-r--r--arch/powerpc/kernel/fsl_booke_entry_mapping.S15
-rw-r--r--arch/powerpc/kernel/irq.c2
-rw-r--r--arch/powerpc/kernel/jump_label.c2
-rw-r--r--arch/powerpc/kernel/kvm.c1
-rw-r--r--arch/powerpc/kernel/misc_32.S19
-rw-r--r--arch/powerpc/kernel/misc_64.S13
-rw-r--r--arch/powerpc/kernel/nvram_64.c10
-rw-r--r--arch/powerpc/kernel/pci-common.c72
-rw-r--r--arch/powerpc/kernel/pci_of_scan.c8
-rw-r--r--arch/powerpc/kernel/process.c14
-rw-r--r--arch/powerpc/kernel/prom.c25
-rw-r--r--arch/powerpc/kernel/prom_init.c25
-rw-r--r--arch/powerpc/kernel/ptrace.c89
-rw-r--r--arch/powerpc/kernel/rtas.c11
-rw-r--r--arch/powerpc/kernel/setup_32.c6
-rw-r--r--arch/powerpc/kernel/signal_32.c5
-rw-r--r--arch/powerpc/kernel/signal_64.c21
-rw-r--r--arch/powerpc/kernel/time.c24
-rw-r--r--arch/powerpc/kernel/trace_clock.c15
29 files changed, 392 insertions, 194 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 12868b1c4..ba336930d 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -118,6 +118,7 @@ obj-$(CONFIG_PPC_IO_WORKAROUNDS) += io-workarounds.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
+obj-$(CONFIG_TRACING) += trace_clock.o
ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
obj-y += iomap.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 98230579d..221d584d0 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -213,7 +213,6 @@ int main(void)
offsetof(struct tlb_core_data, esel_max));
DEFINE(TCD_ESEL_FIRST,
offsetof(struct tlb_core_data, esel_first));
- DEFINE(TCD_LOCK, offsetof(struct tlb_core_data, lock));
#endif /* CONFIG_PPC_BOOK3E */
#ifdef CONFIG_PPC_STD_MMU_64
@@ -512,6 +511,8 @@ int main(void)
DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty));
DEFINE(VCPU_HEIR, offsetof(struct kvm_vcpu, arch.emul_inst));
+ DEFINE(VCPU_CPU, offsetof(struct kvm_vcpu, cpu));
+ DEFINE(VCPU_THREAD_CPU, offsetof(struct kvm_vcpu, arch.thread_cpu));
#endif
#ifdef CONFIG_PPC_BOOK3S
DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
@@ -674,7 +675,14 @@ int main(void)
HSTATE_FIELD(HSTATE_DSCR, host_dscr);
HSTATE_FIELD(HSTATE_DABR, dabr);
HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
+ HSTATE_FIELD(HSTATE_SPLIT_MODE, kvm_split_mode);
DEFINE(IPI_PRIORITY, IPI_PRIORITY);
+ DEFINE(KVM_SPLIT_RPR, offsetof(struct kvm_split_mode, rpr));
+ DEFINE(KVM_SPLIT_PMMAR, offsetof(struct kvm_split_mode, pmmar));
+ DEFINE(KVM_SPLIT_LDBAR, offsetof(struct kvm_split_mode, ldbar));
+ DEFINE(KVM_SPLIT_SIZE, offsetof(struct kvm_split_mode, subcore_size));
+ DEFINE(KVM_SPLIT_DO_NAP, offsetof(struct kvm_split_mode, do_nap));
+ DEFINE(KVM_SPLIT_NAPPED, offsetof(struct kvm_split_mode, napped));
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 4c68bfe41..41a7d9d49 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -73,7 +73,7 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
}
/* We support DMA to/from any memory page via the iommu */
-static int dma_iommu_dma_supported(struct device *dev, u64 mask)
+int dma_iommu_dma_supported(struct device *dev, u64 mask)
{
struct iommu_table *tbl = get_iommu_table_base(dev);
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 6e8d764ce..c6689f658 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -47,8 +47,8 @@ static u64 swiotlb_powerpc_get_required(struct device *dev)
* for everything else.
*/
struct dma_map_ops swiotlb_dma_ops = {
- .alloc = dma_direct_alloc_coherent,
- .free = dma_direct_free_coherent,
+ .alloc = __dma_direct_alloc_coherent,
+ .free = __dma_direct_free_coherent,
.mmap = dma_direct_mmap_coherent,
.map_sg = swiotlb_map_sg_attrs,
.unmap_sg = swiotlb_unmap_sg_attrs,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 35e4dcc5d..3f1472a78 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -16,6 +16,7 @@
#include <asm/bug.h>
#include <asm/machdep.h>
#include <asm/swiotlb.h>
+#include <asm/iommu.h>
/*
* Generic direct DMA implementation
@@ -39,9 +40,31 @@ static u64 __maybe_unused get_pfn_limit(struct device *dev)
return pfn;
}
-void *dma_direct_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag,
- struct dma_attrs *attrs)
+static int dma_direct_dma_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_PPC64
+ u64 limit = get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
+
+ /* Limit fits in the mask, we are good */
+ if (mask >= limit)
+ return 1;
+
+#ifdef CONFIG_FSL_SOC
+ /* Freescale gets another chance via ZONE_DMA/ZONE_DMA32, however
+ * that will have to be refined if/when they support iommus
+ */
+ return 1;
+#endif
+ /* Sorry ... */
+ return 0;
+#else
+ return 1;
+#endif
+}
+
+void *__dma_direct_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag,
+ struct dma_attrs *attrs)
{
void *ret;
#ifdef CONFIG_NOT_COHERENT_CACHE
@@ -96,9 +119,9 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
#endif
}
-void dma_direct_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle,
- struct dma_attrs *attrs)
+void __dma_direct_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
#ifdef CONFIG_NOT_COHERENT_CACHE
__dma_free_coherent(size, vaddr);
@@ -107,6 +130,51 @@ void dma_direct_free_coherent(struct device *dev, size_t size,
#endif
}
+static void *dma_direct_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag,
+ struct dma_attrs *attrs)
+{
+ struct iommu_table *iommu;
+
+ /* The coherent mask may be smaller than the real mask, check if
+ * we can really use the direct ops
+ */
+ if (dma_direct_dma_supported(dev, dev->coherent_dma_mask))
+ return __dma_direct_alloc_coherent(dev, size, dma_handle,
+ flag, attrs);
+
+ /* Ok we can't ... do we have an iommu ? If not, fail */
+ iommu = get_iommu_table_base(dev);
+ if (!iommu)
+ return NULL;
+
+ /* Try to use the iommu */
+ return iommu_alloc_coherent(dev, iommu, size, dma_handle,
+ dev->coherent_dma_mask, flag,
+ dev_to_node(dev));
+}
+
+static void dma_direct_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
+{
+ struct iommu_table *iommu;
+
+ /* See comments in dma_direct_alloc_coherent() */
+ if (dma_direct_dma_supported(dev, dev->coherent_dma_mask))
+ return __dma_direct_free_coherent(dev, size, vaddr, dma_handle,
+ attrs);
+ /* Maybe we used an iommu ... */
+ iommu = get_iommu_table_base(dev);
+
+ /* If we hit that we should have never allocated in the first
+ * place so how come we are freeing ?
+ */
+ if (WARN_ON(!iommu))
+ return;
+ iommu_free_coherent(iommu, size, vaddr, dma_handle);
+}
+
int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t handle, size_t size,
struct dma_attrs *attrs)
@@ -147,18 +215,6 @@ 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 so platforms can set the limit in case
- * they have limited DMA windows
- */
- return mask >= get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
-#else
- return 1;
-#endif
-}
-
static u64 dma_direct_get_required_mask(struct device *dev)
{
u64 end, mask;
@@ -230,6 +286,25 @@ struct dma_map_ops dma_direct_ops = {
};
EXPORT_SYMBOL(dma_direct_ops);
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+ if (!dma_supported(dev, mask)) {
+ /*
+ * We need to special case the direct DMA ops which can
+ * support a fallback for coherent allocations. There
+ * is no dma_op->set_coherent_mask() so we have to do
+ * things the hard way:
+ */
+ if (get_dma_ops(dev) != &dma_direct_ops ||
+ get_iommu_table_base(dev) == NULL ||
+ !dma_iommu_dma_supported(dev, mask))
+ return -EIO;
+ }
+ dev->coherent_dma_mask = mask;
+ return 0;
+}
+EXPORT_SYMBOL(dma_set_coherent_mask);
+
#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
int __dma_set_mask(struct device *dev, u64 dma_mask)
@@ -278,6 +353,13 @@ u64 dma_get_required_mask(struct device *dev)
if (ppc_md.dma_get_required_mask)
return ppc_md.dma_get_required_mask(dev);
+ if (dev_is_pci(dev)) {
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct pci_controller *phb = pci_bus_to_host(pdev->bus);
+ if (phb->controller_ops.dma_get_required_mask)
+ return phb->controller_ops.dma_get_required_mask(pdev);
+ }
+
return __dma_get_required_mask(dev);
}
EXPORT_SYMBOL_GPL(dma_get_required_mask);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 01c961d5d..e968533e3 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -765,14 +765,14 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
break;
case pcie_hot_reset:
- eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED);
eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
eeh_ops->reset(pe, EEH_RESET_HOT);
break;
case pcie_warm_reset:
- eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED);
eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 35f0b6225..8654cb166 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -657,6 +657,28 @@ void eeh_pe_state_clear(struct eeh_pe *pe, int state)
eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
}
+/**
+ * eeh_pe_state_mark_with_cfg - Mark PE state with unblocked config space
+ * @pe: PE
+ * @state: PE state to be set
+ *
+ * Set specified flag to PE and its child PEs. The PCI config space
+ * of some PEs is blocked automatically when EEH_PE_ISOLATED is set,
+ * which isn't needed in some situations. The function allows to set
+ * the specified flag to indicated PEs without blocking their PCI
+ * config space.
+ */
+void eeh_pe_state_mark_with_cfg(struct eeh_pe *pe, int state)
+{
+ eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
+ if (!(state & EEH_PE_ISOLATED))
+ return;
+
+ /* Clear EEH_PE_CFG_BLOCKED, which might be set just now */
+ state = EEH_PE_CFG_BLOCKED;
+ eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
+}
+
/*
* Some PCI bridges (e.g. PLX bridges) have primary/secondary
* buses assigned explicitly by firmware, and we probably have
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 46fc0f4d8..2405631e9 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -20,6 +20,7 @@
*/
#include <linux/errno.h>
+#include <linux/err.h>
#include <linux/sys.h>
#include <linux/threads.h>
#include <asm/reg.h>
@@ -354,7 +355,7 @@ ret_from_syscall:
SYNC
MTMSRD(r10)
lwz r9,TI_FLAGS(r12)
- li r8,-_LAST_ERRNO
+ li r8,-MAX_ERRNO
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
bne- syscall_exit_work
cmplw 0,r3,r8
@@ -457,6 +458,10 @@ syscall_dotrace:
lwz r7,GPR7(r1)
lwz r8,GPR8(r1)
REST_NVGPRS(r1)
+
+ cmplwi r0,NR_syscalls
+ /* Return code is already in r3 thanks to do_syscall_trace_enter() */
+ bge- ret_from_syscall
b syscall_dotrace_cont
syscall_exit_work:
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 579e0f9a2..a94f155db 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -19,6 +19,7 @@
*/
#include <linux/errno.h>
+#include <linux/err.h>
#include <asm/unistd.h>
#include <asm/processor.h>
#include <asm/page.h>
@@ -150,8 +151,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
CURRENT_THREAD_INFO(r11, r1)
ld r10,TI_FLAGS(r11)
andi. r11,r10,_TIF_SYSCALL_DOTRACE
- bne syscall_dotrace
-.Lsyscall_dotrace_cont:
+ bne syscall_dotrace /* does not return */
cmpldi 0,r0,NR_syscalls
bge- syscall_enosys
@@ -207,7 +207,7 @@ system_call: /* label this so stack traces look sane */
#endif /* CONFIG_PPC_BOOK3E */
ld r9,TI_FLAGS(r12)
- li r11,-_LAST_ERRNO
+ li r11,-MAX_ERRNO
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
bne- syscall_exit_work
cmpld r3,r11
@@ -245,22 +245,34 @@ syscall_dotrace:
bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_syscall_trace_enter
+
/*
- * Restore argument registers possibly just changed.
- * We use the return value of do_syscall_trace_enter
- * for the call number to look up in the table (r0).
+ * We use the return value of do_syscall_trace_enter() as the syscall
+ * number. If the syscall was rejected for any reason do_syscall_trace_enter()
+ * returns an invalid syscall number and the test below against
+ * NR_syscalls will fail.
*/
mr r0,r3
+
+ /* Restore argument registers just clobbered and/or possibly changed. */
ld r3,GPR3(r1)
ld r4,GPR4(r1)
ld r5,GPR5(r1)
ld r6,GPR6(r1)
ld r7,GPR7(r1)
ld r8,GPR8(r1)
+
+ /* Repopulate r9 and r10 for the system_call path */
addi r9,r1,STACK_FRAME_OVERHEAD
CURRENT_THREAD_INFO(r10, r1)
ld r10,TI_FLAGS(r10)
- b .Lsyscall_dotrace_cont
+
+ cmpldi r0,NR_syscalls
+ blt+ system_call
+
+ /* Return code is already in r3 thanks to do_syscall_trace_enter() */
+ b .Lsyscall_exit
+
syscall_enosys:
li r3,-ENOSYS
@@ -277,7 +289,7 @@ syscall_exit_work:
beq+ 0f
REST_NVGPRS(r1)
b 2f
-0: cmpld r3,r11 /* r10 is -LAST_ERRNO */
+0: cmpld r3,r11 /* r11 is -MAX_ERRNO */
blt+ 1f
andi. r0,r9,_TIF_NOERROR
bne- 1f
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 3e68d1c69..f3bd5e747 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1313,11 +1313,14 @@ skpinv: addi r6,r6,1 /* Increment */
sync
isync
-/* The mapping only needs to be cache-coherent on SMP */
-#ifdef CONFIG_SMP
-#define M_IF_SMP MAS2_M
+/*
+ * The mapping only needs to be cache-coherent on SMP, except on
+ * Freescale e500mc derivatives where it's also needed for coherent DMA.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
+#define M_IF_NEEDED MAS2_M
#else
-#define M_IF_SMP 0
+#define M_IF_NEEDED 0
#endif
/* 6. Setup KERNELBASE mapping in TLB[0]
@@ -1332,7 +1335,7 @@ skpinv: addi r6,r6,1 /* Increment */
ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
mtspr SPRN_MAS1,r6
- LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | M_IF_SMP)
+ LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | M_IF_NEEDED)
mtspr SPRN_MAS2,r6
rlwinm r5,r5,0,0,25
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index f22e7e44f..83dd0f677 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -152,11 +152,14 @@ skpinv: addi r6,r6,1 /* Increment */
tlbivax 0,r9
TLBSYNC
-/* The mapping only needs to be cache-coherent on SMP */
-#ifdef CONFIG_SMP
-#define M_IF_SMP MAS2_M
+/*
+ * The mapping only needs to be cache-coherent on SMP, except on
+ * Freescale e500mc derivatives where it's also needed for coherent DMA.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
+#define M_IF_NEEDED MAS2_M
#else
-#define M_IF_SMP 0
+#define M_IF_NEEDED 0
#endif
#if defined(ENTRY_MAPPING_BOOT_SETUP)
@@ -167,8 +170,8 @@ skpinv: addi r6,r6,1 /* Increment */
lis r6,(MAS1_VALID|MAS1_IPROT)@h
ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
mtspr SPRN_MAS1,r6
- lis r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_SMP)@h
- ori r6,r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_SMP)@l
+ lis r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@h
+ ori r6,r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@l
mtspr SPRN_MAS2,r6
mtspr SPRN_MAS3,r8
tlbwe
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 45096033d..290559df1 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -441,7 +441,7 @@ void migrate_irqs(void)
chip = irq_data_get_irq_chip(data);
- cpumask_and(mask, data->affinity, map);
+ cpumask_and(mask, irq_data_get_affinity_mask(data), map);
if (cpumask_any(mask) >= nr_cpu_ids) {
pr_warn("Breaking affinity for irq %i\n", irq);
cpumask_copy(mask, map);
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index a1ed8a8c7..647247209 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -17,7 +17,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
{
u32 *addr = (u32 *)(unsigned long)entry->code;
- if (type == JUMP_LABEL_ENABLE)
+ if (type == JUMP_LABEL_JMP)
patch_branch(addr, entry->target, 0);
else
patch_instruction(addr, PPC_INST_NOP);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 33aa4ddf5..9ad37f827 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -649,7 +649,6 @@ static void kvm_check_ins(u32 *inst, u32 features)
kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
}
break;
- break;
#endif
}
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 7c6bb4b17..ed3ab509f 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -596,25 +596,6 @@ _GLOBAL(copy_page)
b 2b
/*
- * void atomic_clear_mask(atomic_t mask, atomic_t *addr)
- * void atomic_set_mask(atomic_t mask, atomic_t *addr);
- */
-_GLOBAL(atomic_clear_mask)
-10: lwarx r5,0,r4
- andc r5,r5,r3
- PPC405_ERR77(0,r4)
- stwcx. r5,0,r4
- bne- 10b
- blr
-_GLOBAL(atomic_set_mask)
-10: lwarx r5,0,r4
- or r5,r5,r3
- PPC405_ERR77(0,r4)
- stwcx. r5,0,r4
- bne- 10b
- blr
-
-/*
* Extended precision shifts.
*
* Updated to be valid for shift counts from 0 to 63 inclusive.
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 4e314b90c..6e4168cf4 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -475,9 +475,18 @@ _GLOBAL(kexec_wait)
#ifdef CONFIG_KEXEC /* use no memory without kexec */
lwz r4,0(r5)
cmpwi 0,r4,0
- bnea 0x60
+ beq 99b
+#ifdef CONFIG_PPC_BOOK3S_64
+ li r10,0x60
+ mfmsr r11
+ clrrdi r11,r11,1 /* Clear MSR_LE */
+ mtsrr0 r10
+ mtsrr1 r11
+ rfid
+#else
+ ba 0x60
+#endif
#endif
- b 99b
/* this can be in text because we won't change it until we are
* running in real anyways
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 1e703f8eb..98ba106a5 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -541,10 +541,9 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
time->tv_nsec = 0;
}
- *buf = kmalloc(length, GFP_KERNEL);
+ *buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
if (*buf == NULL)
return -ENOMEM;
- memcpy(*buf, buff + hdr_size, length);
kfree(buff);
if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
@@ -582,9 +581,10 @@ static int nvram_pstore_init(void)
spin_lock_init(&nvram_pstore_info.buf_lock);
rc = pstore_register(&nvram_pstore_info);
- if (rc != 0)
- pr_err("nvram: pstore_register() failed, defaults to "
- "kmsg_dump; returned %d\n", rc);
+ if (rc && (rc != -EPERM))
+ /* Print error only when pstore.backend == nvram */
+ pr_err("nvram: pstore_register() failed, returned %d. "
+ "Defaults to kmsg_dump\n", rc);
return rc;
}
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index b9de34d44..7587b2ae5 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -823,23 +823,15 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
(reg.start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
/* Only print message if not re-assigning */
if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC))
- pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] "
- "is unassigned\n",
- pci_name(dev), i,
- (unsigned long long)res->start,
- (unsigned long long)res->end,
- (unsigned int)res->flags);
+ pr_debug("PCI:%s Resource %d %pR is unassigned\n",
+ pci_name(dev), i, res);
res->end -= res->start;
res->start = 0;
res->flags |= IORESOURCE_UNSET;
continue;
}
- pr_debug("PCI:%s Resource %d %016llx-%016llx [%x]\n",
- pci_name(dev), i,
- (unsigned long long)res->start,\
- (unsigned long long)res->end,
- (unsigned int)res->flags);
+ pr_debug("PCI:%s Resource %d %pR\n", pci_name(dev), i, res);
}
/* Call machine specific resource fixup */
@@ -943,11 +935,7 @@ static void pcibios_fixup_bridge(struct pci_bus *bus)
continue;
}
- pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x]\n",
- pci_name(dev), i,
- (unsigned long long)res->start,\
- (unsigned long long)res->end,
- (unsigned int)res->flags);
+ pr_debug("PCI:%s Bus rsrc %d %pR\n", pci_name(dev), i, res);
/* Try to detect uninitialized P2P bridge resources,
* and clear them out so they get re-assigned later
@@ -1132,10 +1120,8 @@ static int reparent_resources(struct resource *parent,
*pp = NULL;
for (p = res->child; p != NULL; p = p->sibling) {
p->parent = res;
- pr_debug("PCI: Reparented %s [%llx..%llx] under %s\n",
- p->name,
- (unsigned long long)p->start,
- (unsigned long long)p->end, res->name);
+ pr_debug("PCI: Reparented %s %pR under %s\n",
+ p->name, p, res->name);
}
return 0;
}
@@ -1204,14 +1190,9 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
}
}
- pr_debug("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx "
- "[0x%x], parent %p (%s)\n",
- bus->self ? pci_name(bus->self) : "PHB",
- bus->number, i,
- (unsigned long long)res->start,
- (unsigned long long)res->end,
- (unsigned int)res->flags,
- pr, (pr && pr->name) ? pr->name : "nil");
+ pr_debug("PCI: %s (bus %d) bridge rsrc %d: %pR, parent %p (%s)\n",
+ bus->self ? pci_name(bus->self) : "PHB", bus->number,
+ i, res, pr, (pr && pr->name) ? pr->name : "nil");
if (pr && !(pr->flags & IORESOURCE_UNSET)) {
struct pci_dev *dev = bus->self;
@@ -1253,11 +1234,8 @@ static inline void alloc_resource(struct pci_dev *dev, int idx)
{
struct resource *pr, *r = &dev->resource[idx];
- pr_debug("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n",
- pci_name(dev), idx,
- (unsigned long long)r->start,
- (unsigned long long)r->end,
- (unsigned int)r->flags);
+ pr_debug("PCI: Allocating %s: Resource %d: %pR\n",
+ pci_name(dev), idx, r);
pr = pci_find_parent_resource(dev, r);
if (!pr || (pr->flags & IORESOURCE_UNSET) ||
@@ -1265,11 +1243,7 @@ static inline void alloc_resource(struct pci_dev *dev, int idx)
printk(KERN_WARNING "PCI: Cannot allocate resource region %d"
" of device %s, will remap\n", idx, pci_name(dev));
if (pr)
- pr_debug("PCI: parent is %p: %016llx-%016llx [%x]\n",
- pr,
- (unsigned long long)pr->start,
- (unsigned long long)pr->end,
- (unsigned int)pr->flags);
+ pr_debug("PCI: parent is %p: %pR\n", pr, pr);
/* We'll assign a new address later */
r->flags |= IORESOURCE_UNSET;
r->end -= r->start;
@@ -1431,12 +1405,8 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
if (r->parent || !r->start || !r->flags)
continue;
- pr_debug("PCI: Claiming %s: "
- "Resource %d: %016llx..%016llx [%x]\n",
- pci_name(dev), i,
- (unsigned long long)r->start,
- (unsigned long long)r->end,
- (unsigned int)r->flags);
+ pr_debug("PCI: Claiming %s: Resource %d: %pR\n",
+ pci_name(dev), i, r);
if (pci_claim_resource(dev, i) == 0)
continue;
@@ -1520,11 +1490,8 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
} else {
offset = pcibios_io_space_offset(hose);
- pr_debug("PCI: PHB IO resource = %08llx-%08llx [%lx] off 0x%08llx\n",
- (unsigned long long)res->start,
- (unsigned long long)res->end,
- (unsigned long)res->flags,
- (unsigned long long)offset);
+ pr_debug("PCI: PHB IO resource = %pR off 0x%08llx\n",
+ res, (unsigned long long)offset);
pci_add_resource_offset(resources, res, offset);
}
@@ -1541,11 +1508,8 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
offset = hose->mem_offset[i];
- pr_debug("PCI: PHB MEM resource %d = %08llx-%08llx [%lx] off 0x%08llx\n", i,
- (unsigned long long)res->start,
- (unsigned long long)res->end,
- (unsigned long)res->flags,
- (unsigned long long)offset);
+ pr_debug("PCI: PHB MEM resource %d = %pR off 0x%08llx\n", i,
+ res, (unsigned long long)offset);
pci_add_resource_offset(resources, res, offset);
}
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index efc3fa54c..2e710c158 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -102,7 +102,7 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
} else if (i == dev->rom_base_reg) {
res = &dev->resource[PCI_ROM_RESOURCE];
- flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE;
+ flags |= IORESOURCE_READONLY;
} else {
printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i);
continue;
@@ -126,7 +126,6 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
{
struct pci_dev *dev;
const char *type;
- struct pci_slot *slot;
dev = pci_alloc_dev(bus);
if (!dev)
@@ -145,10 +144,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
dev->needs_freset = 0; /* pcie fundamental reset required */
set_pcie_port_type(dev);
- list_for_each_entry(slot, &dev->bus->slots, list)
- if (PCI_SLOT(dev->devfn) == slot->number)
- dev->slot = slot;
-
+ pci_dev_assign_slot(dev);
dev->vendor = get_int_prop(node, "vendor-id", 0xffff);
dev->device = get_int_prop(node, "device-id", 0xffff);
dev->subsystem_vendor = get_int_prop(node, "subsystem-vendor-id", 0);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 64e6e9d9e..75b6676c1 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -86,7 +86,7 @@ void giveup_fpu_maybe_transactional(struct task_struct *tsk)
if (tsk == current && tsk->thread.regs &&
MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
!test_thread_flag(TIF_RESTORE_TM)) {
- tsk->thread.tm_orig_msr = tsk->thread.regs->msr;
+ tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
set_thread_flag(TIF_RESTORE_TM);
}
@@ -104,7 +104,7 @@ void giveup_altivec_maybe_transactional(struct task_struct *tsk)
if (tsk == current && tsk->thread.regs &&
MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
!test_thread_flag(TIF_RESTORE_TM)) {
- tsk->thread.tm_orig_msr = tsk->thread.regs->msr;
+ tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
set_thread_flag(TIF_RESTORE_TM);
}
@@ -540,7 +540,7 @@ static void tm_reclaim_thread(struct thread_struct *thr,
* the thread will no longer be transactional.
*/
if (test_ti_thread_flag(ti, TIF_RESTORE_TM)) {
- msr_diff = thr->tm_orig_msr & ~thr->regs->msr;
+ msr_diff = thr->ckpt_regs.msr & ~thr->regs->msr;
if (msr_diff & MSR_FP)
memcpy(&thr->transact_fp, &thr->fp_state,
sizeof(struct thread_fp_state));
@@ -591,10 +591,10 @@ static inline void tm_reclaim_task(struct task_struct *tsk)
/* Stash the original thread MSR, as giveup_fpu et al will
* modify it. We hold onto it to see whether the task used
* FP & vector regs. If the TIF_RESTORE_TM flag is set,
- * tm_orig_msr is already set.
+ * ckpt_regs.msr is already set.
*/
if (!test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_TM))
- thr->tm_orig_msr = thr->regs->msr;
+ thr->ckpt_regs.msr = thr->regs->msr;
TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, "
"ccr=%lx, msr=%lx, trap=%lx)\n",
@@ -663,7 +663,7 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new)
tm_restore_sprs(&new->thread);
return;
}
- msr = new->thread.tm_orig_msr;
+ msr = new->thread.ckpt_regs.msr;
/* Recheckpoint to restore original checkpointed register state. */
TM_DEBUG("*** tm_recheckpoint of pid %d "
"(new->msr 0x%lx, new->origmsr 0x%lx)\n",
@@ -723,7 +723,7 @@ void restore_tm_state(struct pt_regs *regs)
if (!MSR_TM_ACTIVE(regs->msr))
return;
- msr_diff = current->thread.tm_orig_msr & ~regs->msr;
+ msr_diff = current->thread.ckpt_regs.msr & ~regs->msr;
msr_diff &= MSR_FP | MSR_VEC | MSR_VSX;
if (msr_diff & MSR_FP) {
fp_enable();
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 8b888b12a..bef76c503 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -218,22 +218,18 @@ static void __init check_cpu_pa_features(unsigned long node)
}
#ifdef CONFIG_PPC_STD_MMU_64
-static void __init check_cpu_slb_size(unsigned long node)
+static void __init init_mmu_slb_size(unsigned long node)
{
const __be32 *slb_size_ptr;
- slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL);
- if (slb_size_ptr != NULL) {
- mmu_slb_size = be32_to_cpup(slb_size_ptr);
- return;
- }
- slb_size_ptr = of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
- if (slb_size_ptr != NULL) {
+ slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL) ? :
+ of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
+
+ if (slb_size_ptr)
mmu_slb_size = be32_to_cpup(slb_size_ptr);
- }
}
#else
-#define check_cpu_slb_size(node) do { } while(0)
+#define init_mmu_slb_size(node) do { } while(0)
#endif
static struct feature_property {
@@ -380,7 +376,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
check_cpu_feature_properties(node);
check_cpu_pa_features(node);
- check_cpu_slb_size(node);
+ init_mmu_slb_size(node);
#ifdef CONFIG_PPC64
if (nthreads > 1)
@@ -476,9 +472,10 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
flags = of_read_number(&dm[3], 1);
/* skip DRC index, pad, assoc. list index, flags */
dm += 4;
- /* skip this block if the reserved bit is set in flags (0x80)
- or if the block is not assigned to this partition (0x8) */
- if ((flags & 0x80) || !(flags & 0x8))
+ /* skip this block if the reserved bit is set in flags
+ or if the block is not assigned to this partition */
+ if ((flags & DRCONF_MEM_RESERVED) ||
+ !(flags & DRCONF_MEM_ASSIGNED))
continue;
size = memblock_size;
rngs = 1;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index fcca8077e..15099c416 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -641,6 +641,15 @@ static void __init early_cmdline_parse(void)
#define W(x) ((x) >> 24) & 0xff, ((x) >> 16) & 0xff, \
((x) >> 8) & 0xff, (x) & 0xff
+/* Firmware expects the value to be n - 1, where n is the # of vectors */
+#define NUM_VECTORS(n) ((n) - 1)
+
+/*
+ * Firmware expects 1 + n - 2, where n is the length of the option vector in
+ * bytes. The 1 accounts for the length byte itself, the - 2 .. ?
+ */
+#define VECTOR_LENGTH(n) (1 + (n) - 2)
+
unsigned char ibm_architecture_vec[] = {
W(0xfffe0000), W(0x003a0000), /* POWER5/POWER5+ */
W(0xffff0000), W(0x003e0000), /* POWER6 */
@@ -651,16 +660,16 @@ unsigned char ibm_architecture_vec[] = {
W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */
W(0xffffffff), W(0x0f000002), /* all 2.05-compliant */
W(0xfffffffe), W(0x0f000001), /* all 2.04-compliant and earlier */
- 6 - 1, /* 6 option vectors */
+ NUM_VECTORS(6), /* 6 option vectors */
/* option vector 1: processor architectures supported */
- 3 - 2, /* length */
+ VECTOR_LENGTH(2), /* length */
0, /* don't ignore, don't halt */
OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 |
OV1_PPC_2_04 | OV1_PPC_2_05 | OV1_PPC_2_06 | OV1_PPC_2_07,
/* option vector 2: Open Firmware options supported */
- 34 - 2, /* length */
+ VECTOR_LENGTH(33), /* length */
OV2_REAL_MODE,
0, 0,
W(0xffffffff), /* real_base */
@@ -674,17 +683,17 @@ unsigned char ibm_architecture_vec[] = {
48, /* max log_2(hash table size) */
/* option vector 3: processor options supported */
- 3 - 2, /* length */
+ VECTOR_LENGTH(2), /* length */
0, /* don't ignore, don't halt */
OV3_FP | OV3_VMX | OV3_DFP,
/* option vector 4: IBM PAPR implementation */
- 3 - 2, /* length */
+ VECTOR_LENGTH(2), /* length */
0, /* don't halt */
OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */
/* option vector 5: PAPR/OF options */
- 19 - 2, /* length */
+ VECTOR_LENGTH(18), /* length */
0, /* don't ignore, don't halt */
OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
@@ -717,12 +726,12 @@ unsigned char ibm_architecture_vec[] = {
OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
OV5_FEAT(OV5_PFO_HW_842),
OV5_FEAT(OV5_SUB_PROCESSORS),
+
/* option vector 6: IBM PAPR hints */
- 4 - 2, /* length */
+ VECTOR_LENGTH(3), /* length */
0,
0,
OV6_LINUX,
-
};
/* Old method - ELF header with PT_NOTE sections only works on BE */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index f21897b42..737c0d0b5 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1762,26 +1762,81 @@ long arch_ptrace(struct task_struct *child, long request,
return ret;
}
-/*
- * We must return the syscall number to actually look up in the table.
- * This can be -1L to skip running any syscall at all.
+#ifdef CONFIG_SECCOMP
+static int do_seccomp(struct pt_regs *regs)
+{
+ if (!test_thread_flag(TIF_SECCOMP))
+ return 0;
+
+ /*
+ * The ABI we present to seccomp tracers is that r3 contains
+ * the syscall return value and orig_gpr3 contains the first
+ * syscall parameter. This is different to the ptrace ABI where
+ * both r3 and orig_gpr3 contain the first syscall parameter.
+ */
+ regs->gpr[3] = -ENOSYS;
+
+ /*
+ * We use the __ version here because we have already checked
+ * TIF_SECCOMP. If this fails, there is nothing left to do, we
+ * have already loaded -ENOSYS into r3, or seccomp has put
+ * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
+ */
+ if (__secure_computing())
+ return -1;
+
+ /*
+ * The syscall was allowed by seccomp, restore the register
+ * state to what ptrace and audit expect.
+ * Note that we use orig_gpr3, which means a seccomp tracer can
+ * modify the first syscall parameter (in orig_gpr3) and also
+ * allow the syscall to proceed.
+ */
+ regs->gpr[3] = regs->orig_gpr3;
+
+ return 0;
+}
+#else
+static inline int do_seccomp(struct pt_regs *regs) { return 0; }
+#endif /* CONFIG_SECCOMP */
+
+/**
+ * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
+ * @regs: the pt_regs of the task to trace (current)
+ *
+ * Performs various types of tracing on syscall entry. This includes seccomp,
+ * ptrace, syscall tracepoints and audit.
+ *
+ * The pt_regs are potentially visible to userspace via ptrace, so their
+ * contents is ABI.
+ *
+ * One or more of the tracers may modify the contents of pt_regs, in particular
+ * to modify arguments or even the syscall number itself.
+ *
+ * It's also possible that a tracer can choose to reject the system call. In
+ * that case this function will return an illegal syscall number, and will put
+ * an appropriate return value in regs->r3.
+ *
+ * Return: the (possibly changed) syscall number.
*/
long do_syscall_trace_enter(struct pt_regs *regs)
{
- long ret = 0;
+ bool abort = false;
user_exit();
- secure_computing_strict(regs->gpr[0]);
+ if (do_seccomp(regs))
+ return -1;
- if (test_thread_flag(TIF_SYSCALL_TRACE) &&
- tracehook_report_syscall_entry(regs))
+ if (test_thread_flag(TIF_SYSCALL_TRACE)) {
/*
- * Tracing decided this syscall should not happen.
- * We'll return a bogus call number to get an ENOSYS
- * error, but leave the original number in regs->gpr[0].
+ * The tracer may decide to abort the syscall, if so tracehook
+ * will return !0. Note that the tracer may also just change
+ * regs->gpr[0] to an invalid syscall number, that is handled
+ * below on the exit path.
*/
- ret = -1L;
+ abort = tracehook_report_syscall_entry(regs) != 0;
+ }
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
trace_sys_enter(regs, regs->gpr[0]);
@@ -1798,7 +1853,17 @@ long do_syscall_trace_enter(struct pt_regs *regs)
regs->gpr[5] & 0xffffffff,
regs->gpr[6] & 0xffffffff);
- return ret ?: regs->gpr[0];
+ if (abort || regs->gpr[0] >= NR_syscalls) {
+ /*
+ * If we are aborting explicitly, or if the syscall number is
+ * now invalid, set the return value to -ENOSYS.
+ */
+ regs->gpr[3] = -ENOSYS;
+ return -1;
+ }
+
+ /* Return the possibly modified but valid syscall number */
+ return regs->gpr[0];
}
void do_syscall_trace_leave(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index caffb10e7..5a753fae8 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -478,8 +478,9 @@ unsigned int rtas_busy_delay_time(int status)
if (status == RTAS_BUSY) {
ms = 1;
- } else if (status >= 9900 && status <= 9905) {
- order = status - 9900;
+ } else if (status >= RTAS_EXTENDED_DELAY_MIN &&
+ status <= RTAS_EXTENDED_DELAY_MAX) {
+ order = status - RTAS_EXTENDED_DELAY_MIN;
for (ms = 1; order > 0; order--)
ms *= 10;
}
@@ -658,7 +659,8 @@ int rtas_set_indicator_fast(int indicator, int index, int new_value)
rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value);
- WARN_ON(rc == -2 || (rc >= 9900 && rc <= 9905));
+ WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN &&
+ rc <= RTAS_EXTENDED_DELAY_MAX));
if (rc < 0)
return rtas_error_rc(rc);
@@ -1041,6 +1043,9 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (!rtas.entry)
+ return -EINVAL;
+
if (copy_from_user(&args, uargs, 3 * sizeof(u32)) != 0)
return -EFAULT;
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index bb02e9f69..ad8c9db61 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -38,6 +38,7 @@
#include <asm/udbg.h>
#include <asm/mmu_context.h>
#include <asm/epapr_hcalls.h>
+#include <asm/code-patching.h>
#define DBG(fmt...)
@@ -109,6 +110,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
* This is called very early on the boot process, after a minimal
* MMU environment has been set up but before MMU_init is called.
*/
+extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
+
notrace void __init machine_init(u64 dt_ptr)
{
lockdep_init();
@@ -116,6 +119,9 @@ notrace void __init machine_init(u64 dt_ptr)
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
+ patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP);
+ patch_instruction(&memset_nocache_branch, PPC_INST_NOP);
+
/* Do some early initialization based on the flat device tree */
early_init_devtree(__va(dt_ptr));
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index da50e0c9c..0dbee465a 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -949,6 +949,11 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
err |= __put_user(s->si_overrun, &d->si_overrun);
err |= __put_user(s->si_int, &d->si_int);
break;
+ case __SI_SYS >> 16:
+ err |= __put_user(ptr_to_compat(s->si_call_addr), &d->si_call_addr);
+ err |= __put_user(s->si_syscall, &d->si_syscall);
+ err |= __put_user(s->si_arch, &d->si_arch);
+ break;
case __SI_RT >> 16: /* This is not generated by the kernel as of now. */
case __SI_MESGQ >> 16:
err |= __put_user(s->si_int, &d->si_int);
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index c7c24d2e2..20756dfb9 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -74,6 +74,19 @@ static const char fmt64[] = KERN_INFO \
"%s[%d]: bad frame in %s: %016lx nip %016lx lr %016lx\n";
/*
+ * This computes a quad word aligned pointer inside the vmx_reserve array
+ * element. For historical reasons sigcontext might not be quad word aligned,
+ * but the location we write the VMX regs to must be. See the comment in
+ * sigcontext for more detail.
+ */
+#ifdef CONFIG_ALTIVEC
+static elf_vrreg_t __user *sigcontext_vmx_regs(struct sigcontext __user *sc)
+{
+ return (elf_vrreg_t __user *) (((unsigned long)sc->vmx_reserve + 15) & ~0xful);
+}
+#endif
+
+/*
* Set up the sigcontext for the signal frame.
*/
@@ -90,7 +103,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
* v_regs pointer or not
*/
#ifdef CONFIG_ALTIVEC
- elf_vrreg_t __user *v_regs = (elf_vrreg_t __user *)(((unsigned long)sc->vmx_reserve + 15) & ~0xful);
+ elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
#endif
unsigned long msr = regs->msr;
long err = 0;
@@ -181,10 +194,8 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
* v_regs pointer or not.
*/
#ifdef CONFIG_ALTIVEC
- elf_vrreg_t __user *v_regs = (elf_vrreg_t __user *)
- (((unsigned long)sc->vmx_reserve + 15) & ~0xful);
- elf_vrreg_t __user *tm_v_regs = (elf_vrreg_t __user *)
- (((unsigned long)tm_sc->vmx_reserve + 15) & ~0xful);
+ elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
+ elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc);
#endif
unsigned long msr = regs->msr;
long err = 0;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 43922509a..1be1092c7 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -99,16 +99,17 @@ static struct clocksource clocksource_timebase = {
static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev);
-static void decrementer_set_mode(enum clock_event_mode mode,
- struct clock_event_device *dev);
+static int decrementer_shutdown(struct clock_event_device *evt);
struct clock_event_device decrementer_clockevent = {
- .name = "decrementer",
- .rating = 200,
- .irq = 0,
- .set_next_event = decrementer_set_next_event,
- .set_mode = decrementer_set_mode,
- .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP,
+ .name = "decrementer",
+ .rating = 200,
+ .irq = 0,
+ .set_next_event = decrementer_set_next_event,
+ .set_state_shutdown = decrementer_shutdown,
+ .tick_resume = decrementer_shutdown,
+ .features = CLOCK_EVT_FEAT_ONESHOT |
+ CLOCK_EVT_FEAT_C3STOP,
};
EXPORT_SYMBOL(decrementer_clockevent);
@@ -862,11 +863,10 @@ static int decrementer_set_next_event(unsigned long evt,
return 0;
}
-static void decrementer_set_mode(enum clock_event_mode mode,
- struct clock_event_device *dev)
+static int decrementer_shutdown(struct clock_event_device *dev)
{
- if (mode != CLOCK_EVT_MODE_ONESHOT)
- decrementer_set_next_event(DECREMENTER_MAX, dev);
+ decrementer_set_next_event(DECREMENTER_MAX, dev);
+ return 0;
}
/* Interrupt handler for the timer broadcast IPI */
diff --git a/arch/powerpc/kernel/trace_clock.c b/arch/powerpc/kernel/trace_clock.c
new file mode 100644
index 000000000..491706909
--- /dev/null
+++ b/arch/powerpc/kernel/trace_clock.c
@@ -0,0 +1,15 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include <asm/trace_clock.h>
+#include <asm/time.h>
+
+u64 notrace trace_clock_ppc_tb(void)
+{
+ return get_tb();
+}