3 files changed, 117 insertions, 45 deletions

diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 2c1db77d7848..f05a35a59694 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -92,75 +92,111 @@ ENDPROC(ret_from_fork)
 #define CALL(x) .long x
 
 #ifdef CONFIG_FUNCTION_TRACER
+/*
+ * When compiling with -pg, gcc inserts a call to the mcount routine at the
+ * start of every function.  In mcount, apart from the function's address (in
+ * lr), we need to get hold of the function's caller's address.
+ *
+ * Older GCCs (pre-4.4) inserted a call to a routine called mcount like this:
+ *
+ *      bl      mcount
+ *
+ * These versions have the limitation that in order for the mcount routine to
+ * be able to determine the function's caller's address, an APCS-style frame
+ * pointer (which is set up with something like the code below) is required.
+ *
+ *      mov     ip, sp
+ *      push    {fp, ip, lr, pc}
+ *      sub     fp, ip, #4
+ *
+ * With EABI, these frame pointers are not available unless -mapcs-frame is
+ * specified, and if building as Thumb-2, not even then.
+ *
+ * Newer GCCs (4.4+) solve this problem by introducing a new version of mcount,
+ * with call sites like:
+ *
+ *      push    {lr}
+ *      bl      __gnu_mcount_nc
+ *
+ * With these compilers, frame pointers are not necessary.
+ *
+ * mcount can be thought of as a function called in the middle of a subroutine
+ * call.  As such, it needs to be transparent for both the caller and the
+ * callee: the original lr needs to be restored when leaving mcount, and no
+ * registers should be clobbered.  (In the __gnu_mcount_nc implementation, we
+ * clobber the ip register.  This is OK because the ARM calling convention
+ * allows it to be clobbered in subroutines and doesn't use it to hold
+ * parameters.)
+ */
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
-        stmdb sp!, {r0-r3, lr}
-        mov r0, lr
-        sub r0, r0, #MCOUNT_INSN_SIZE
+        stmdb   sp!, {r0-r3, lr}
+        mov     r0, lr
+        sub     r0, r0, #MCOUNT_INSN_SIZE
 
         .globl mcount_call
 mcount_call:
-        bl ftrace_stub
-        ldr lr, [fp, #-4]                       @ restore lr
-        ldmia sp!, {r0-r3, pc}
+        bl      ftrace_stub
+        ldr     lr, [fp, #-4]                   @ restore lr
+        ldmia   sp!, {r0-r3, pc}
 
 ENTRY(ftrace_caller)
-        stmdb sp!, {r0-r3, lr}
-        ldr r1, [fp, #-4]
-        mov r0, lr
-        sub r0, r0, #MCOUNT_INSN_SIZE
+        stmdb   sp!, {r0-r3, lr}
+        ldr     r1, [fp, #-4]
+        mov     r0, lr
+        sub     r0, r0, #MCOUNT_INSN_SIZE
 
         .globl ftrace_call
 ftrace_call:
-        bl ftrace_stub
-        ldr lr, [fp, #-4]                       @ restore lr
-        ldmia sp!, {r0-r3, pc}
+        bl      ftrace_stub
+        ldr     lr, [fp, #-4]                   @ restore lr
+        ldmia   sp!, {r0-r3, pc}
 
 #else
 
 ENTRY(__gnu_mcount_nc)
-        stmdb sp!, {r0-r3, lr}
-        ldr r0, =ftrace_trace_function
-        ldr r2, [r0]
-        adr r0, ftrace_stub
-        cmp r0, r2
-        bne gnu_trace
-        ldmia sp!, {r0-r3, ip, lr}
-        mov pc, ip
+        stmdb   sp!, {r0-r3, lr}
+        ldr     r0, =ftrace_trace_function
+        ldr     r2, [r0]
+        adr     r0, ftrace_stub
+        cmp     r0, r2
+        bne     gnu_trace
+        ldmia   sp!, {r0-r3, ip, lr}
+        mov     pc, ip
 
 gnu_trace:
-        ldr r1, [sp, #20]                       @ lr of instrumented routine
-        mov r0, lr
-        sub r0, r0, #MCOUNT_INSN_SIZE
-        mov lr, pc
-        mov pc, r2
-        ldmia sp!, {r0-r3, ip, lr}
-        mov pc, ip
+        ldr     r1, [sp, #20]                   @ lr of instrumented routine
+        mov     r0, lr
+        sub     r0, r0, #MCOUNT_INSN_SIZE
+        mov     lr, pc
+        mov     pc, r2
+        ldmia   sp!, {r0-r3, ip, lr}
+        mov     pc, ip
 
 ENTRY(mcount)
-        stmdb sp!, {r0-r3, lr}
-        ldr r0, =ftrace_trace_function
-        ldr r2, [r0]
-        adr r0, ftrace_stub
-        cmp r0, r2
-        bne trace
-        ldr lr, [fp, #-4]                       @ restore lr
-        ldmia sp!, {r0-r3, pc}
+        stmdb   sp!, {r0-r3, lr}
+        ldr     r0, =ftrace_trace_function
+        ldr     r2, [r0]
+        adr     r0, ftrace_stub
+        cmp     r0, r2
+        bne     trace
+        ldr     lr, [fp, #-4]                   @ restore lr
+        ldmia   sp!, {r0-r3, pc}
 
 trace:
-        ldr r1, [fp, #-4]                       @ lr of instrumented routine
-        mov r0, lr
-        sub r0, r0, #MCOUNT_INSN_SIZE
-        mov lr, pc
-        mov pc, r2
-        ldr lr, [fp, #-4]                       @ restore lr
-        ldmia sp!, {r0-r3, pc}
+        ldr     r1, [fp, #-4]                   @ lr of instrumented routine
+        mov     r0, lr
+        sub     r0, r0, #MCOUNT_INSN_SIZE
+        mov     lr, pc
+        mov     pc, r2
+        ldr     lr, [fp, #-4]                   @ restore lr
+        ldmia   sp!, {r0-r3, pc}
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
         .globl ftrace_stub
 ftrace_stub:
-        mov pc, lr
+        mov     pc, lr
 
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
index 827753966301..56418f98cd01 100644
--- a/arch/arm/kernel/etm.c
+++ b/arch/arm/kernel/etm.c
@@ -543,7 +543,9 @@ static int __init etm_probe(struct amba_device *dev, struct amba_id *id)
         t->etm_portsz = 1;
 
         etm_unlock(t);
-        ret = etm_readl(t, CSCR_PRSR);
+        (void)etm_readl(t, ETMMR_PDSR);
+        /* dummy first read */
+        (void)etm_readl(&tracer, ETMMR_OSSRR);
 
         t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf;
         etm_writel(t, 0x440, ETMR_CTRL);
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index c628bdf6c430..6b4605893f1e 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -102,7 +102,9 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                 unsigned long loc;
                 Elf32_Sym *sym;
                 s32 offset;
+#ifdef CONFIG_THUMB2_KERNEL
                 u32 upper, lower, sign, j1, j2;
+#endif
 
                 offset = ELF32_R_SYM(rel->r_info);
                 if (offset < 0 || offset > (symsec->sh_size / sizeof(Elf32_Sym))) {
@@ -185,6 +187,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                                         (offset & 0x0fff);
                         break;
 
+#ifdef CONFIG_THUMB2_KERNEL
                 case R_ARM_THM_CALL:
                 case R_ARM_THM_JUMP24:
                         upper = *(u16 *)loc;
@@ -233,9 +236,40 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
                         *(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
                                                   (j1 << 13) | (j2 << 11) |
                                                   ((offset >> 1) & 0x07ff));
+                        break;
+
+                case R_ARM_THM_MOVW_ABS_NC:
+                case R_ARM_THM_MOVT_ABS:
                         upper = *(u16 *)loc;
                         lower = *(u16 *)(loc + 2);
+
+                        /*
+                         * MOVT/MOVW instructions encoding in Thumb-2:
+                         *
+                         * i    = upper[10]
+                         * imm4 = upper[3:0]
+                         * imm3 = lower[14:12]
+                         * imm8 = lower[7:0]
+                         *
+                         * imm16 = imm4:i:imm3:imm8
+                         */
+                        offset = ((upper & 0x000f) << 12) |
+                                ((upper & 0x0400) << 1) |
+                                ((lower & 0x7000) >> 4) | (lower & 0x00ff);
+                        offset = (offset ^ 0x8000) - 0x8000;
+                        offset += sym->st_value;
+
+                        if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
+                                offset >>= 16;
+
+                        *(u16 *)loc = (u16)((upper & 0xfbf0) |
+                                            ((offset & 0xf000) >> 12) |
+                                            ((offset & 0x0800) >> 1));
+                        *(u16 *)(loc + 2) = (u16)((lower & 0x8f00) |
+                                                  ((offset & 0x0700) << 4) |
+                                                  (offset & 0x00ff));
                         break;
+#endif
 
                 default:
                         printk(KERN_ERR "%s: unknown relocation: %u\n",