tile: support ftrace on tilegx

This commit adds support for static ftrace, graph function support,
and dynamic tracer support.

Signed-off-by: Tony Lu <zlu@tilera.com>
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>

4 files changed, 477 insertions, 0 deletions

diff --git a/arch/tile/kernel/Makefile b/arch/tile/kernel/Makefile
index c4a957aad26a..2e6eaa11b60d 100644
--- a/arch/tile/kernel/Makefile
+++ b/arch/tile/kernel/Makefile
@@ -9,6 +9,11 @@ obj-y := backtrace.o entry.o hvglue.o irq.o messaging.o \
         sysfs.o time.o traps.o unaligned.o vdso.o \
         intvec_$(BITS).o regs_$(BITS).o tile-desc_$(BITS).o
 
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
+endif
+
 obj-$(CONFIG_HARDWALL)          += hardwall.o
 obj-$(CONFIG_COMPAT)            += compat.o compat_signal.o
 obj-$(CONFIG_SMP)               += smpboot.o smp.o tlb.o
@@ -22,5 +27,6 @@ obj-$(CONFIG_PCI)		+= pci.o
 endif
 obj-$(CONFIG_TILE_USB)          += usb.o
 obj-$(CONFIG_TILE_HVGLUE_TRACE) += hvglue_trace.o
+obj-$(CONFIG_FUNCTION_TRACER)   += ftrace.o mcount_64.o
 
 obj-y                           += vdso/
diff --git a/arch/tile/kernel/ftrace.c b/arch/tile/kernel/ftrace.c
new file mode 100644
index 000000000000..f1c452092eeb
--- /dev/null
+++ b/arch/tile/kernel/ftrace.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   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, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * TILE-Gx specific ftrace support
+ */
+
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+#include <asm/sections.h>
+
+#include <arch/opcode.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+static inline tilegx_bundle_bits NOP(void)
+{
+        return create_UnaryOpcodeExtension_X0(FNOP_UNARY_OPCODE_X0) |
+                create_RRROpcodeExtension_X0(UNARY_RRR_0_OPCODE_X0) |
+                create_Opcode_X0(RRR_0_OPCODE_X0) |
+                create_UnaryOpcodeExtension_X1(NOP_UNARY_OPCODE_X1) |
+                create_RRROpcodeExtension_X1(UNARY_RRR_0_OPCODE_X1) |
+                create_Opcode_X1(RRR_0_OPCODE_X1);
+}
+
+static int machine_stopped __read_mostly;
+
+int ftrace_arch_code_modify_prepare(void)
+{
+        machine_stopped = 1;
+        return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+        flush_icache_range(0, CHIP_L1I_CACHE_SIZE());
+        machine_stopped = 0;
+        return 0;
+}
+
+/*
+ * Put { move r10, lr; jal ftrace_caller } in a bundle, this lets dynamic
+ * tracer just add one cycle overhead to every kernel function when disabled.
+ */
+static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
+                                       bool link)
+{
+        tilegx_bundle_bits opcode_x0, opcode_x1;
+        long pcrel_by_instr = (addr - pc) >> TILEGX_LOG2_BUNDLE_SIZE_IN_BYTES;
+
+        if (link) {
+                /* opcode: jal addr */
+                opcode_x1 =
+                        create_Opcode_X1(JUMP_OPCODE_X1) |
+                        create_JumpOpcodeExtension_X1(JAL_JUMP_OPCODE_X1) |
+                        create_JumpOff_X1(pcrel_by_instr);
+        } else {
+                /* opcode: j addr */
+                opcode_x1 =
+                        create_Opcode_X1(JUMP_OPCODE_X1) |
+                        create_JumpOpcodeExtension_X1(J_JUMP_OPCODE_X1) |
+                        create_JumpOff_X1(pcrel_by_instr);
+        }
+
+        if (addr == FTRACE_ADDR) {
+                /* opcode: or r10, lr, zero */
+                opcode_x0 =
+                        create_Dest_X0(10) |
+                        create_SrcA_X0(TREG_LR) |
+                        create_SrcB_X0(TREG_ZERO) |
+                        create_RRROpcodeExtension_X0(OR_RRR_0_OPCODE_X0) |
+                        create_Opcode_X0(RRR_0_OPCODE_X0);
+        } else {
+                /* opcode: fnop */
+                opcode_x0 =
+                        create_UnaryOpcodeExtension_X0(FNOP_UNARY_OPCODE_X0) |
+                        create_RRROpcodeExtension_X0(UNARY_RRR_0_OPCODE_X0) |
+                        create_Opcode_X0(RRR_0_OPCODE_X0);
+        }
+
+        return opcode_x1 | opcode_x0;
+}
+
+static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
+{
+        return NOP();
+}
+
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+{
+        return ftrace_gen_branch(pc, addr, true);
+}
+
+static int ftrace_modify_code(unsigned long pc, unsigned long old,
+                              unsigned long new)
+{
+        unsigned long pc_wr;
+
+        /* Check if the address is in kernel text space and module space. */
+        if (!kernel_text_address(pc))
+                return -EINVAL;
+
+        /* Operate on writable kernel text mapping. */
+        pc_wr = pc - MEM_SV_START + PAGE_OFFSET;
+
+        if (probe_kernel_write((void *)pc_wr, &new, MCOUNT_INSN_SIZE))
+                return -EPERM;
+
+        smp_wmb();
+
+        if (!machine_stopped && num_online_cpus() > 1)
+                flush_icache_range(pc, pc + MCOUNT_INSN_SIZE);
+
+        return 0;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+        unsigned long pc, old;
+        unsigned long new;
+        int ret;
+
+        pc = (unsigned long)&ftrace_call;
+        memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE);
+        new = ftrace_call_replace(pc, (unsigned long)func);
+
+        ret = ftrace_modify_code(pc, old, new);
+
+        return ret;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+        unsigned long new, old;
+        unsigned long ip = rec->ip;
+
+        old = ftrace_nop_replace(rec);
+        new = ftrace_call_replace(ip, addr);
+
+        return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_make_nop(struct module *mod,
+                    struct dyn_ftrace *rec, unsigned long addr)
+{
+        unsigned long ip = rec->ip;
+        unsigned long old;
+        unsigned long new;
+        int ret;
+
+        old = ftrace_call_replace(ip, addr);
+        new = ftrace_nop_replace(rec);
+        ret = ftrace_modify_code(ip, old, new);
+
+        return ret;