From 2cb6e93e9af77a2e4ff20bd5119dbd7fdc6aeea4 Mon Sep 17 00:00:00 2001
From: Thomas Preud'homme <address@hidden>
Date: Sun, 4 Nov 2012 00:40:05 +0100
Subject: [PATCH 2/2] Generate PLT thumb stub only when necessary

Generate PLT thumb stub for an ARM PLT entry only when at least one
Thumb instruction branches to that entry.

Warning: To save space, this commit reuses the bit 0 of entries of
got_offsets array. Make sure to ignore this bit when using the GOT
offset in one of these entries.
---
 tcc.h    |    2 +-
 tccelf.c |   41 +++++++++++++++++++++++++++++------------
 2 files changed, 30 insertions(+), 13 deletions(-)

diff --git a/tcc.h b/tcc.h
index 4e88782..25c160c 100644
--- a/tcc.h
+++ b/tcc.h
@@ -527,7 +527,7 @@ struct TCCState {
     /* got handling */
     Section *got;
     Section *plt;
-    unsigned long *got_offsets;
+    unsigned long *got_offsets; /* bit 0 set = PLT entry requires thumb stub */
     int nb_got_offsets;
     /* give the correspondance from symtab indexes to dynsym indexes */
     int *symtab_to_dynsym;
diff --git a/tccelf.c b/tccelf.c
index d0e4c3b..a12dd24 100644
--- a/tccelf.c
+++ b/tccelf.c
@@ -581,7 +581,7 @@ ST_FUNC void relocate_section(TCCState *s1, Section *s)
             break;
         case R_386_GOT32:
             /* we load the got offset */
-            *(int *)ptr += s1->got_offsets[sym_index];
+            *(int *)ptr += s1->got_offsets[sym_index] & -2;
             break;
         case R_386_16:
             if (s1->output_format != TCC_OUTPUT_FORMAT_BINARY) {
@@ -758,7 +758,7 @@ ST_FUNC void relocate_section(TCCState *s1, Section *s)
             break;
         case R_ARM_GOT_BREL:
             /* we load the got offset */
-            *(int *)ptr += s1->got_offsets[sym_index];
+            *(int *)ptr += s1->got_offsets[sym_index] & -2;
             break;
         case R_ARM_COPY:
             break;
@@ -864,14 +864,14 @@ ST_FUNC void relocate_section(TCCState *s1, Section *s)
             }
 #endif
             *(int *)ptr += (s1->got->sh_addr - addr +
-                            s1->got_offsets[sym_index] - 4);
+                            (s1->got_offsets[sym_index] & -2) - 4);
             break;
         case R_X86_64_GOTTPOFF:
             *(int *)ptr += val - s1->got->sh_addr;
             break;
         case R_X86_64_GOT32:
             /* we load the got offset */
-            *(int *)ptr += s1->got_offsets[sym_index];
+            *(int *)ptr += s1->got_offsets[sym_index] & -2;
             break;
 #else
 #error unsupported processor
@@ -957,7 +957,7 @@ static void put_got_offset(TCCState *s1, int index, unsigned long val)
                (n - s1->nb_got_offsets) * sizeof(unsigned long));
         s1->nb_got_offsets = n;
     }
-    s1->got_offsets[index] = val;
+    s1->got_offsets[index] |= val;
 }
 
 /* XXX: suppress that */
@@ -1022,7 +1022,7 @@ static void put_got_entry(TCCState *s1,
 
     /* if a got entry already exists for that symbol, no need to add one */
     if (sym_index < s1->nb_got_offsets &&
-        s1->got_offsets[sym_index] != 0)
+        s1->got_offsets[sym_index] & -2)
         return;
     
     put_got_offset(s1, sym_index, s1->got->data_offset);
@@ -1102,10 +1102,13 @@ static void put_got_entry(TCCState *s1,
                 put32(p + 12, 0xe5bef008);
             }
 
-            p = section_ptr_add(plt, 20);
-            put32(p  , 0x4778); // bx pc
-            put32(p+2, 0x46c0); // nop
-            p += 4;
+            if (s1->got_offsets[sym_index] & 1) {
+                p = section_ptr_add(plt, 20);
+                put32(p  , 0x4778); // bx pc
+                put32(p+2, 0x46c0); // nop
+                p += 4;
+            } else
+                p = section_ptr_add(plt, 16);
             put32(p  , 0xe59fc004); // ldr ip, [pc, #4] // offset in GOT
             put32(p+4, 0xe08fc00c); // add ip, pc, ip // absolute address or offset
             put32(p+8, 0xe59cf000); // ldr pc, [ip] // load absolute address or load offset
@@ -1494,7 +1497,7 @@ ST_FUNC void fill_got_entry(TCCState *s1, ElfW_Rel *rel)
 
 	if (sym_index >= s1->nb_got_offsets)
 		return;
-	offset = s1->got_offsets[sym_index];
+	offset = s1->got_offsets[sym_index] & -2;
 	section_reserve(s1->got, offset + PTR_SIZE);
 #ifdef TCC_TARGET_X86_64
 	/* only works for x86-64 */
@@ -2068,7 +2071,8 @@ static int elf_output_file(TCCState *s1, const char *filename)
                     x=s1->got->sh_addr - s1->plt->sh_addr - 12;
                     p += 16;
                     while (p < p_end) {
-                        p += 4;
+                        if (get32(p) == 0x46c04778) /* PLT Thumb stub present */
+                            p += 4;
                         put32(p + 12, x + get32(p + 12) + s1->plt->data - p);
                         p += 16;
                     }
@@ -2597,6 +2601,19 @@ ST_FUNC int tcc_load_object_file(TCCState *s1,
                 rel->r_info = ELFW(R_INFO)(sym_index, type);
                 /* offset the relocation offset */
                 rel->r_offset += offseti;
+#ifdef TCC_TARGET_ARM
+                /* Jumps and branches from a Thumb code to a PLT entry need
+                   special handling since PLT entries are ARM code.
+                   Unconditional bl instructions referencing PLT entries are
+                   handled by converting these instructions into blx
+                   instructions. Other case of instructions referencing a PLT
+                   entry require to add a Thumb stub before the PLT entry to
+                   switch to ARM mode. We set bit 0 of the got offset of a
+                   symbol to indicate such a case. */
+                if (type == R_ARM_THM_JUMP24) {
+                    put_got_offset(s1, sym_index, 1);
+                }
+#endif
             }
             break;
         default:
-- 
1.7.10.4