14 files changed, 99 insertions, 135 deletions

diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 3ef40b703c4a..e746becd9d6f 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -268,19 +268,13 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  * their hooks, a bitfield is reserved for use by the platform near the
  * top of MMIO addresses (not PIO, those have to cope the hard way).
  *
- * This bit field is 12 bits and is at the top of the IO virtual
- * addresses PCI_IO_INDIRECT_TOKEN_MASK.
+ * The highest address in the kernel virtual space are:
  *
- * The kernel virtual space is thus:
+ *  d0003fffffffffff    # with Hash MMU
+ *  c00fffffffffffff    # with Radix MMU
  *
- *  0xD000000000000000          : vmalloc
- *  0xD000080000000000          : PCI PHB IO space
- *  0xD000080080000000          : ioremap
- *  0xD0000fffffffffff          : end of ioremap region
- *
- * Since the top 4 bits are reserved as the region ID, we use thus
- * the next 12 bits and keep 4 bits available for the future if the
- * virtual address space is ever to be extended.
+ * The top 4 bits are reserved as the region ID on hash, leaving us 8 bits
+ * that can be used for the field.
  *
  * The direct IO mapping operations will then mask off those bits
  * before doing the actual access, though that only happen when
@@ -292,8 +286,8 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  */
 
 #ifdef CONFIG_PPC_INDIRECT_MMIO
-#define PCI_IO_IND_TOKEN_MASK   0x0fff000000000000ul
-#define PCI_IO_IND_TOKEN_SHIFT  48
+#define PCI_IO_IND_TOKEN_SHIFT  52
+#define PCI_IO_IND_TOKEN_MASK   (0xfful << PCI_IO_IND_TOKEN_SHIFT)
 #define PCI_FIX_ADDR(addr)                                              \
         ((PCI_IO_ADDR)(((unsigned long)(addr)) & ~PCI_IO_IND_TOKEN_MASK))
 #define PCI_GET_ADDR_TOKEN(addr)                                        \
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 6093bc8f74e5..a6e9e314c707 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -493,6 +493,8 @@
                                         __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_SLBFEE_DOT(t, b)    stringify_in_c(.long PPC_INST_SLBFEE | \
                                         __PPC_RT(t) | __PPC_RB(b))
+#define __PPC_SLBFEE_DOT(t, b)  stringify_in_c(.long PPC_INST_SLBFEE |  \
+                                               ___PPC_RT(t) | ___PPC_RB(b))
 #define PPC_ICBT(c,a,b)         stringify_in_c(.long PPC_INST_ICBT | \
                                        __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b))
 /* PASemi instructions */
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index f73886a1a7f5..0b8a735b6d85 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -54,6 +54,7 @@ struct pt_regs
 
 #ifdef CONFIG_PPC64
         unsigned long ppr;
+        unsigned long __pad;    /* Maintain 16 byte interrupt stack alignment */
 #endif
 };
 #endif
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2a51e4cc8246..236c1151a3a7 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -636,6 +636,8 @@ static void *__init alloc_stack(unsigned long limit, int cpu)
 {
         unsigned long pa;
 
+        BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);
+
         pa = memblock_alloc_base_nid(THREAD_SIZE, THREAD_SIZE, limit,
                                         early_cpu_to_node(cpu), MEMBLOCK_NONE);
         if (!pa) {
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 4bf051d3e21e..b65c8a34ad6e 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -950,7 +950,6 @@ int ftrace_disable_ftrace_graph_caller(void)
  */
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 {
-        struct ftrace_graph_ent trace;
         unsigned long return_hooker;
 
         if (unlikely(ftrace_graph_is_dead()))
@@ -961,18 +960,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 
         return_hooker = ppc_function_entry(return_to_handler);
 
-        trace.func = ip;
-        trace.depth = current->curr_ret_stack + 1;
-
-        /* Only trace if the calling function expects to */
-        if (!ftrace_graph_entry(&trace))
-                goto out;
-
-        if (ftrace_push_return_trace(parent, ip, &trace.depth, 0,
-                                     NULL) == -EBUSY)
-                goto out;
-
-        parent = return_hooker;
+        if (!function_graph_enter(parent, ip, 0, NULL))
+                parent = return_hooker;
 out:
         return parent;
 }
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d65b961661fb..a56f8413758a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -983,6 +983,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
                 ret = kvmhv_enter_nested_guest(vcpu);
                 if (ret == H_INTERRUPT) {
                         kvmppc_set_gpr(vcpu, 3, 0);
+                        vcpu->arch.hcall_needed = 0;
                         return -EINTR;
                 }
                 break;
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 491b0f715d6b..ea1d7c808319 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -6,8 +6,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace
 
 /*
  * Tracepoint for guest mode entry.
@@ -120,4 +118,10 @@ TRACE_EVENT(kvm_check_requests,
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+
 #include <trace/define_trace.h>
diff --git a/arch/powerpc/kvm/trace_booke.h b/arch/powerpc/kvm/trace_booke.h
index ac640e81fdc5..3837842986aa 100644
--- a/arch/powerpc/kvm/trace_booke.h
+++ b/arch/powerpc/kvm/trace_booke.h
@@ -6,8 +6,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm_booke
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace_booke
 
 #define kvm_trace_symbol_exit \
         {0, "CRITICAL"}, \
@@ -218,4 +216,11 @@ TRACE_EVENT(kvm_booke_queue_irqprio,
 #endif
 
 /* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_booke
+
 #include <trace/define_trace.h>
diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h
index bcfe8a987f6a..8a1e3b0047f1 100644
--- a/arch/powerpc/kvm/trace_hv.h
+++ b/arch/powerpc/kvm/trace_hv.h
@@ -9,8 +9,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm_hv
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace_hv
 
 #define kvm_trace_symbol_hcall \
         {H_REMOVE,                      "H_REMOVE"}, \
@@ -497,4 +495,11 @@ TRACE_EVENT(kvmppc_run_vcpu_exit,
 #endif /* _TRACE_KVM_HV_H */
 
 /* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_hv
+
 #include <trace/define_trace.h>
diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h
index 2f9a8829552b..46a46d328fbf 100644
--- a/arch/powerpc/kvm/trace_pr.h
+++ b/arch/powerpc/kvm/trace_pr.h
@@ -8,8 +8,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm_pr
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace_pr
 
 TRACE_EVENT(kvm_book3s_reenter,
         TP_PROTO(int r, struct kvm_vcpu *vcpu),
@@ -257,4 +255,11 @@ TRACE_EVENT(kvm_exit,
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_pr
+
 #include <trace/define_trace.h>
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 3a048e98a132..ce28ae5ca080 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1178,7 +1178,7 @@ static long vphn_get_associativity(unsigned long cpu,
 
         switch (rc) {
         case H_FUNCTION:
-                printk(KERN_INFO
+                printk_once(KERN_INFO
                         "VPHN is not supported. Disabling polling...\n");
                 stop_topology_update();
                 break;
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index c3fdf2969d9f..bc3914d54e26 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -19,6 +19,7 @@
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/paca.h>
+#include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
 #include <asm/smp.h>
@@ -58,27 +59,19 @@ static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
         return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags);
 }
 
-static void assert_slb_exists(unsigned long ea)
+static void assert_slb_presence(bool present, unsigned long ea)
 {
 #ifdef CONFIG_DEBUG_VM
         unsigned long tmp;
 
         WARN_ON_ONCE(mfmsr() & MSR_EE);
 
-        asm volatile("slbfee. %0, %1" : "=r"(tmp) : "r"(ea) : "cr0");
-        WARN_ON(tmp == 0);
-#endif
-}
-
-static void assert_slb_notexists(unsigned long ea)
-{
-#ifdef CONFIG_DEBUG_VM
-        unsigned long tmp;
+        if (!cpu_has_feature(CPU_FTR_ARCH_206))
+                return;
 
-        WARN_ON_ONCE(mfmsr() & MSR_EE);
+        asm volatile(__PPC_SLBFEE_DOT(%0, %1) : "=r"(tmp) : "r"(ea) : "cr0");
 
-        asm volatile("slbfee. %0, %1" : "=r"(tmp) : "r"(ea) : "cr0");
-        WARN_ON(tmp != 0);
+        WARN_ON(present == (tmp == 0));
 #endif
 }
 
@@ -114,7 +107,7 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize,
          */
         slb_shadow_update(ea, ssize, flags, index);
 
-        assert_slb_notexists(ea);
+        assert_slb_presence(false, ea);
         asm volatile("slbmte  %0,%1" :
                      : "r" (mk_vsid_data(ea, ssize, flags)),
                        "r" (mk_esid_data(ea, ssize, index))
@@ -137,7 +130,7 @@ void __slb_restore_bolted_realmode(void)
                        "r" (be64_to_cpu(p->save_area[index].esid)));
         }
 
-        assert_slb_exists(local_paca->kstack);
+        assert_slb_presence(true, local_paca->kstack);
 }
 
 /*
@@ -185,7 +178,7 @@ void slb_flush_and_restore_bolted(void)
                      :: "r" (be64_to_cpu(p->save_area[KSTACK_INDEX].vsid)),
                         "r" (be64_to_cpu(p->save_area[KSTACK_INDEX].esid))
                      : "memory");
-        assert_slb_exists(get_paca()->kstack);
+        assert_slb_presence(true, get_paca()->kstack);
 
         get_paca()->slb_cache_ptr = 0;
 
@@ -443,9 +436,9 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
                                 ea = (unsigned long)
                                         get_paca()->slb_cache[i] << SID_SHIFT;
                                 /*
-                                 * Could assert_slb_exists here, but hypervisor
-                                 * or machine check could have come in and
-                                 * removed the entry at this point.
+                                 * Could assert_slb_presence(true) here, but
+                                 * hypervisor or machine check could have come
+                                 * in and removed the entry at this point.
                                  */
 
                                 slbie_data = ea;
@@ -676,7 +669,7 @@ static long slb_insert_entry(unsigned long ea, unsigned long context,
          * User preloads should add isync afterwards in case the kernel
          * accesses user memory before it returns to userspace with rfid.
          */
-        assert_slb_notexists(ea);
+        assert_slb_presence(false, ea);
         asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data));
 
         barrier();
@@ -715,7 +708,7 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
                         return -EFAULT;
 
                 if (ea < H_VMALLOC_END)
-                        flags = get_paca()->vmalloc_sllp;
+                        flags = local_paca->vmalloc_sllp;
                 else
                         flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
         } else {
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 50b129785aee..17482f5de3e2 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -166,7 +166,33 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
         PPC_BLR();
 }
 
-static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
+static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx,
+                                       u64 func)
+{
+#ifdef PPC64_ELF_ABI_v1
+        /* func points to the function descriptor */
+        PPC_LI64(b2p[TMP_REG_2], func);
+        /* Load actual entry point from function descriptor */
+        PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
+        /* ... and move it to LR */
+        PPC_MTLR(b2p[TMP_REG_1]);
+        /*
+         * Load TOC from function descriptor at offset 8.
+         * We can clobber r2 since we get called through a
+         * function pointer (so caller will save/restore r2)
+         * and since we don't use a TOC ourself.
+         */
+        PPC_BPF_LL(2, b2p[TMP_REG_2], 8);
+#else
+        /* We can clobber r12 */
+        PPC_FUNC_ADDR(12, func);
+        PPC_MTLR(12);
+#endif
+        PPC_BLRL();
+}
+
+static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx,
+                                       u64 func)
 {
         unsigned int i, ctx_idx = ctx->idx;
 
@@ -273,7 +299,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 {
         const struct bpf_insn *insn = fp->insnsi;
         int flen = fp->len;
-        int i;
+        int i, ret;
 
         /* Start of epilogue code - will only be valid 2nd pass onwards */
         u32 exit_addr = addrs[flen];
@@ -284,8 +310,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
                 u32 src_reg = b2p[insn[i].src_reg];
                 s16 off = insn[i].off;
                 s32 imm = insn[i].imm;
+                bool func_addr_fixed;
+                u64 func_addr;
                 u64 imm64;
-                u8 *func;
                 u32 true_cond;
                 u32 tmp_idx;
 
@@ -711,23 +738,15 @@ emit_clear:
                 case BPF_JMP | BPF_CALL:
                         ctx->seen |= SEEN_FUNC;
 
-                        /* bpf function call */
-                        if (insn[i].src_reg == BPF_PSEUDO_CALL)
-                                if (!extra_pass)
-                                        func = NULL;
-                                else if (fp->aux->func && off < fp->aux->func_cnt)
-                                        /* use the subprog id from the off
-                                         * field to lookup the callee address
-                                         */
-                                        func = (u8 *) fp->aux->func[off]->bpf_func;
-                                else
-                                        return -EINVAL;
-                        /* kernel helper call */
-                        else
-                                func = (u8 *) __bpf_call_base + imm;
-
-                        bpf_jit_emit_func_call(image, ctx, (u64)func);
+                        ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
+                                                    &func_addr, &func_addr_fixed);
+                        if (ret < 0)
+                                return ret;
 
+                        if (func_addr_fixed)
+                                bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
+                        else
+                                bpf_jit_emit_func_call_rel(image, ctx, func_addr);
                         /* move return value from r3 to BPF_REG_0 */
                         PPC_MR(b2p[BPF_REG_0], 3);
                         break;
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 6f60e0931922..75b935252981 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -102,63 +102,6 @@ struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index)
 }
 EXPORT_SYMBOL(pnv_pci_get_npu_dev);
 
-#define NPU_DMA_OP_UNSUPPORTED()                                        \
-        dev_err_once(dev, "%s operation unsupported for NVLink devices\n", \
-                __func__)
-
-static void *dma_npu_alloc(struct device *dev, size_t size,
-                           dma_addr_t *dma_handle, gfp_t flag,
-                           unsigned long attrs)
-{
-        NPU_DMA_OP_UNSUPPORTED();
-        return NULL;
-}
-
-static void dma_npu_free(struct device *dev, size_t size,
-                         void *vaddr, dma_addr_t dma_handle,
-                         unsigned long attrs)
-{
-        NPU_DMA_OP_UNSUPPORTED();
-}
-
-static dma_addr_t dma_npu_map_page(struct device *dev, struct page *page,
-                                   unsigned long offset, size_t size,
-                                   enum dma_data_direction direction,
-                                   unsigned long attrs)
-{
-        NPU_DMA_OP_UNSUPPORTED();
-        return 0;
-}
-
-static int dma_npu_map_sg(struct device *dev, struct scatterlist *sglist,
-                          int nelems, enum dma_data_direction direction,
-                          unsigned long attrs)
-{
-        NPU_DMA_OP_UNSUPPORTED();
-        return 0;
-}
-
-static int dma_npu_dma_supported(struct device *dev, u64 mask)
-{
-        NPU_DMA_OP_UNSUPPORTED();
-        return 0;
-}
-
-static u64 dma_npu_get_required_mask(struct device *dev)
-{
-        NPU_DMA_OP_UNSUPPORTED();
-        return 0;
-}
-
-static const struct dma_map_ops dma_npu_ops = {
-        .map_page               = dma_npu_map_page,
-        .map_sg                 = dma_npu_map_sg,
-        .alloc                  = dma_npu_alloc,
-        .free                   = dma_npu_free,
-        .dma_supported          = dma_npu_dma_supported,
-        .get_required_mask      = dma_npu_get_required_mask,
-};
-
 /*
  * Returns the PE assoicated with the PCI device of the given
  * NPU. Returns the linked pci device if pci_dev != NULL.
@@ -270,10 +213,11 @@ static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe)
         rc = pnv_npu_set_window(npe, 0, gpe->table_group.tables[0]);
 
         /*
-         * We don't initialise npu_pe->tce32_table as we always use
-         * dma_npu_ops which are nops.
+         * NVLink devices use the same TCE table configuration as
+         * their parent device so drivers shouldn't be doing DMA
+         * operations directly on these devices.
          */
-        set_dma_ops(&npe->pdev->dev, &dma_npu_ops);
+        set_dma_ops(&npe->pdev->dev, NULL);
 }
 
 /*