Merge changes to config examples and configuration issues
diff --git a/ChangeLog b/ChangeLog
index 2ba5a50..a16a948 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -5,6 +5,11 @@
 (and various x509 structures got a new member)
 
 = PolarSSL 1.3 branch
+Security
+   * Fix length checking for AEAD ciphersuites (found by Codenomicon).
+     It was possible to crash the server (and client) using crafted messages
+     when a GCM suite was chosen.
+
 Features
    * Add CCM module and cipher mode to Cipher Layer
    * Support for CCM and CCM_8 ciphersuites
@@ -31,6 +36,27 @@
    * Fix symlink command for cross compiling with CMake (found by Andre
      Heinecke)
    * Fix DER output of gen_key app (found by Gergely Budai)
+   * Very small records were incorrectly rejected when truncated HMAC was in
+     use with some ciphersuites and versions (RC4 in all versions, CBC with
+     versions < TLS 1.1).
+   * Very large records using more than 224 bytes of padding were incorrectly
+     rejected with CBC-based ciphersuites and TLS >= 1.1
+   * Very large records using less padding could cause a buffer overread of up
+     to 32 bytes with CBC-based ciphersuites and TLS >= 1.1
+   * Restore ability to use a v1 cert as a CA if trusted locally. (This had
+     been removed in 1.3.6.)
+   * Restore ability to locally trust a self-signed cert that is not a proper
+     CA for use as an end entity certificate. (This had been removed in
+     1.3.6.)
+   * Fix preprocessor checks for bn_mul PPC asm (found by Barry K. Nathan).
+   * Use \n\t rather than semicolons for bn_mul asm, since some assemblers
+     interpret semicolons as comment delimiters (found by Barry K. Nathan).
+   * Fix off-by-one error in parsing Supported Point Format extension that
+     caused some handshakes to fail.
+   * Fix possible miscomputation of the premaster secret with DHE-PSK key
+     exchange that caused some handshakes to fail with other implementations.
+     (Failure rate <= 1/255 with common DHM moduli.)
+   * Disable broken Sparc64 bn_mul assembly (found by Florian Obser).
 
 = PolarSSL 1.3.7 released on 2014-05-02
 Features
diff --git a/configs/README.txt b/configs/README.txt
index 7527fdb..bab500d 100644
--- a/configs/README.txt
+++ b/configs/README.txt
@@ -8,6 +8,8 @@
 them, you can pick one of the following methods:
 
 1. Replace the default file include/polarssl/config.h with the chosen one.
+   (Depending on your compiler, you may need to ajust the line with
+   #include "polarssl/check_config.h" then.)
 
 2. Define POLARSSL_CONFIG_FILE and adjust the include path accordingly.
    For example, using make:
diff --git a/configs/config-mini-tls1_1.h b/configs/config-mini-tls1_1.h
index fd1b0e8..338fecf 100644
--- a/configs/config-mini-tls1_1.h
+++ b/configs/config-mini-tls1_1.h
@@ -51,6 +51,6 @@
 /* For testing with compat.sh */
 #define POLARSSL_FS_IO
 
-#include "check_config.h"
+#include "polarssl/check_config.h"
 
 #endif /* POLARSSL_CONFIG_H */
diff --git a/configs/config-psk-rc4-tls1_0.h b/configs/config-psk-rc4-tls1_0.h
index e4fc452..c967b4c 100644
--- a/configs/config-psk-rc4-tls1_0.h
+++ b/configs/config-psk-rc4-tls1_0.h
@@ -35,6 +35,6 @@
 #define POLARSSL_SSL_SRV_C
 #define POLARSSL_SSL_TLS_C
 
-#include "check_config.h"
+#include "polarssl/check_config.h"
 
 #endif /* POLARSSL_CONFIG_H */
diff --git a/configs/config-suite-b.h b/configs/config-suite-b.h
index 0600c2e..d10cf63 100644
--- a/configs/config-suite-b.h
+++ b/configs/config-suite-b.h
@@ -85,6 +85,6 @@
  */
 #define SSL_MAX_CONTENT_LEN             1024
 
-#include "check_config.h"
+#include "polarssl/check_config.h"
 
 #endif /* POLARSSL_CONFIG_H */
diff --git a/include/polarssl/bn_mul.h b/include/polarssl/bn_mul.h
index 39dee41..64b59ff 100644
--- a/include/polarssl/bn_mul.h
+++ b/include/polarssl/bn_mul.h
@@ -48,102 +48,95 @@
 #if defined(__GNUC__)
 #if defined(__i386__)
 
-#define MULADDC_INIT                \
-    asm( "                          \
-        movl   %%ebx, %0;           \
-        movl   %5, %%esi;           \
-        movl   %6, %%edi;           \
-        movl   %7, %%ecx;           \
-        movl   %8, %%ebx;           \
-        "
+#define MULADDC_INIT                        \
+    asm(                                    \
+        "movl   %%ebx, %0           \n\t"   \
+        "movl   %5, %%esi           \n\t"   \
+        "movl   %6, %%edi           \n\t"   \
+        "movl   %7, %%ecx           \n\t"   \
+        "movl   %8, %%ebx           \n\t"
 
-#define MULADDC_CORE                \
-        "                           \
-        lodsl;                      \
-        mull   %%ebx;               \
-        addl   %%ecx,   %%eax;      \
-        adcl   $0,      %%edx;      \
-        addl   (%%edi), %%eax;      \
-        adcl   $0,      %%edx;      \
-        movl   %%edx,   %%ecx;      \
-        stosl;                      \
-        "
+#define MULADDC_CORE                        \
+        "lodsl                      \n\t"   \
+        "mull   %%ebx               \n\t"   \
+        "addl   %%ecx,   %%eax      \n\t"   \
+        "adcl   $0,      %%edx      \n\t"   \
+        "addl   (%%edi), %%eax      \n\t"   \
+        "adcl   $0,      %%edx      \n\t"   \
+        "movl   %%edx,   %%ecx      \n\t"   \
+        "stosl                      \n\t"
 
 #if defined(POLARSSL_HAVE_SSE2)
 
-#define MULADDC_HUIT                    \
-        "                               \
-        movd     %%ecx,     %%mm1;      \
-        movd     %%ebx,     %%mm0;      \
-        movd     (%%edi),   %%mm3;      \
-        paddq    %%mm3,     %%mm1;      \
-        movd     (%%esi),   %%mm2;      \
-        pmuludq  %%mm0,     %%mm2;      \
-        movd     4(%%esi),  %%mm4;      \
-        pmuludq  %%mm0,     %%mm4;      \
-        movd     8(%%esi),  %%mm6;      \
-        pmuludq  %%mm0,     %%mm6;      \
-        movd     12(%%esi), %%mm7;      \
-        pmuludq  %%mm0,     %%mm7;      \
-        paddq    %%mm2,     %%mm1;      \
-        movd     4(%%edi),  %%mm3;      \
-        paddq    %%mm4,     %%mm3;      \
-        movd     8(%%edi),  %%mm5;      \
-        paddq    %%mm6,     %%mm5;      \
-        movd     12(%%edi), %%mm4;      \
-        paddq    %%mm4,     %%mm7;      \
-        movd     %%mm1,     (%%edi);    \
-        movd     16(%%esi), %%mm2;      \
-        pmuludq  %%mm0,     %%mm2;      \
-        psrlq    $32,       %%mm1;      \
-        movd     20(%%esi), %%mm4;      \
-        pmuludq  %%mm0,     %%mm4;      \
-        paddq    %%mm3,     %%mm1;      \
-        movd     24(%%esi), %%mm6;      \
-        pmuludq  %%mm0,     %%mm6;      \
-        movd     %%mm1,     4(%%edi);   \
-        psrlq    $32,       %%mm1;      \
-        movd     28(%%esi), %%mm3;      \
-        pmuludq  %%mm0,     %%mm3;      \
-        paddq    %%mm5,     %%mm1;      \
-        movd     16(%%edi), %%mm5;      \
-        paddq    %%mm5,     %%mm2;      \
-        movd     %%mm1,     8(%%edi);   \
-        psrlq    $32,       %%mm1;      \
-        paddq    %%mm7,     %%mm1;      \
-        movd     20(%%edi), %%mm5;      \
-        paddq    %%mm5,     %%mm4;      \
-        movd     %%mm1,     12(%%edi);  \
-        psrlq    $32,       %%mm1;      \
-        paddq    %%mm2,     %%mm1;      \
-        movd     24(%%edi), %%mm5;      \
-        paddq    %%mm5,     %%mm6;      \
-        movd     %%mm1,     16(%%edi);  \
-        psrlq    $32,       %%mm1;      \
-        paddq    %%mm4,     %%mm1;      \
-        movd     28(%%edi), %%mm5;      \
-        paddq    %%mm5,     %%mm3;      \
-        movd     %%mm1,     20(%%edi);  \
-        psrlq    $32,       %%mm1;      \
-        paddq    %%mm6,     %%mm1;      \
-        movd     %%mm1,     24(%%edi);  \
-        psrlq    $32,       %%mm1;      \
-        paddq    %%mm3,     %%mm1;      \
-        movd     %%mm1,     28(%%edi);  \
-        addl     $32,       %%edi;      \
-        addl     $32,       %%esi;      \
-        psrlq    $32,       %%mm1;      \
-        movd     %%mm1,     %%ecx;      \
-        "
+#define MULADDC_HUIT                            \
+        "movd     %%ecx,     %%mm1      \n\t"   \
+        "movd     %%ebx,     %%mm0      \n\t"   \
+        "movd     (%%edi),   %%mm3      \n\t"   \
+        "paddq    %%mm3,     %%mm1      \n\t"   \
+        "movd     (%%esi),   %%mm2      \n\t"   \
+        "pmuludq  %%mm0,     %%mm2      \n\t"   \
+        "movd     4(%%esi),  %%mm4      \n\t"   \
+        "pmuludq  %%mm0,     %%mm4      \n\t"   \
+        "movd     8(%%esi),  %%mm6      \n\t"   \
+        "pmuludq  %%mm0,     %%mm6      \n\t"   \
+        "movd     12(%%esi), %%mm7      \n\t"   \
+        "pmuludq  %%mm0,     %%mm7      \n\t"   \
+        "paddq    %%mm2,     %%mm1      \n\t"   \
+        "movd     4(%%edi),  %%mm3      \n\t"   \
+        "paddq    %%mm4,     %%mm3      \n\t"   \
+        "movd     8(%%edi),  %%mm5      \n\t"   \
+        "paddq    %%mm6,     %%mm5      \n\t"   \
+        "movd     12(%%edi), %%mm4      \n\t"   \
+        "paddq    %%mm4,     %%mm7      \n\t"   \
+        "movd     %%mm1,     (%%edi)    \n\t"   \
+        "movd     16(%%esi), %%mm2      \n\t"   \
+        "pmuludq  %%mm0,     %%mm2      \n\t"   \
+        "psrlq    $32,       %%mm1      \n\t"   \
+        "movd     20(%%esi), %%mm4      \n\t"   \
+        "pmuludq  %%mm0,     %%mm4      \n\t"   \
+        "paddq    %%mm3,     %%mm1      \n\t"   \
+        "movd     24(%%esi), %%mm6      \n\t"   \
+        "pmuludq  %%mm0,     %%mm6      \n\t"   \
+        "movd     %%mm1,     4(%%edi)   \n\t"   \
+        "psrlq    $32,       %%mm1      \n\t"   \
+        "movd     28(%%esi), %%mm3      \n\t"   \
+        "pmuludq  %%mm0,     %%mm3      \n\t"   \
+        "paddq    %%mm5,     %%mm1      \n\t"   \
+        "movd     16(%%edi), %%mm5      \n\t"   \
+        "paddq    %%mm5,     %%mm2      \n\t"   \
+        "movd     %%mm1,     8(%%edi)   \n\t"   \
+        "psrlq    $32,       %%mm1      \n\t"   \
+        "paddq    %%mm7,     %%mm1      \n\t"   \
+        "movd     20(%%edi), %%mm5      \n\t"   \
+        "paddq    %%mm5,     %%mm4      \n\t"   \
+        "movd     %%mm1,     12(%%edi)  \n\t"   \
+        "psrlq    $32,       %%mm1      \n\t"   \
+        "paddq    %%mm2,     %%mm1      \n\t"   \
+        "movd     24(%%edi), %%mm5      \n\t"   \
+        "paddq    %%mm5,     %%mm6      \n\t"   \
+        "movd     %%mm1,     16(%%edi)  \n\t"   \
+        "psrlq    $32,       %%mm1      \n\t"   \
+        "paddq    %%mm4,     %%mm1      \n\t"   \
+        "movd     28(%%edi), %%mm5      \n\t"   \
+        "paddq    %%mm5,     %%mm3      \n\t"   \
+        "movd     %%mm1,     20(%%edi)  \n\t"   \
+        "psrlq    $32,       %%mm1      \n\t"   \
+        "paddq    %%mm6,     %%mm1      \n\t"   \
+        "movd     %%mm1,     24(%%edi)  \n\t"   \
+        "psrlq    $32,       %%mm1      \n\t"   \
+        "paddq    %%mm3,     %%mm1      \n\t"   \
+        "movd     %%mm1,     28(%%edi)  \n\t"   \
+        "addl     $32,       %%edi      \n\t"   \
+        "addl     $32,       %%esi      \n\t"   \
+        "psrlq    $32,       %%mm1      \n\t"   \
+        "movd     %%mm1,     %%ecx      \n\t"
 
-#define MULADDC_STOP            \
-        "                       \
-        emms;                   \
-        movl   %4, %%ebx;       \
-        movl   %%ecx, %1;       \
-        movl   %%edi, %2;       \
-        movl   %%esi, %3;       \
-        "                       \
+#define MULADDC_STOP                    \
+        "emms                   \n\t"   \
+        "movl   %4, %%ebx       \n\t"   \
+        "movl   %%ecx, %1       \n\t"   \
+        "movl   %%edi, %2       \n\t"   \
+        "movl   %%esi, %3       \n\t"   \
         : "=m" (t), "=m" (c), "=m" (d), "=m" (s)        \
         : "m" (t), "m" (s), "m" (d), "m" (c), "m" (b)   \
         : "eax", "ecx", "edx", "esi", "edi"             \
@@ -151,13 +144,11 @@
 
 #else
 
-#define MULADDC_STOP            \
-        "                       \
-        movl   %4, %%ebx;       \
-        movl   %%ecx, %1;       \
-        movl   %%edi, %2;       \
-        movl   %%esi, %3;       \
-        "                       \
+#define MULADDC_STOP                    \
+        "movl   %4, %%ebx       \n\t"   \
+        "movl   %%ecx, %1       \n\t"   \
+        "movl   %%edi, %2       \n\t"   \
+        "movl   %%esi, %3       \n\t"   \
         : "=m" (t), "=m" (c), "=m" (d), "=m" (s)        \
         : "m" (t), "m" (s), "m" (d), "m" (c), "m" (b)   \
         : "eax", "ecx", "edx", "esi", "edi"             \
@@ -167,36 +158,30 @@
 
 #if defined(__amd64__) || defined (__x86_64__)
 
-#define MULADDC_INIT                \
-    asm(                            \
-        "                           \
-        movq   %3, %%rsi;           \
-        movq   %4, %%rdi;           \
-        movq   %5, %%rcx;           \
-        movq   %6, %%rbx;           \
-        xorq   %%r8, %%r8;          \
-        "
+#define MULADDC_INIT                        \
+    asm(                                    \
+        "movq   %3, %%rsi           \n\t"   \
+        "movq   %4, %%rdi           \n\t"   \
+        "movq   %5, %%rcx           \n\t"   \
+        "movq   %6, %%rbx           \n\t"   \
+        "xorq   %%r8, %%r8          \n\t"
 
-#define MULADDC_CORE                \
-        "                           \
-        movq   (%%rsi), %%rax;      \
-        mulq   %%rbx;               \
-        addq   $8,      %%rsi;      \
-        addq   %%rcx,   %%rax;      \
-        movq   %%r8,    %%rcx;      \
-        adcq   $0,      %%rdx;      \
-        nop;                        \
-        addq   %%rax,   (%%rdi);    \
-        adcq   %%rdx,   %%rcx;      \
-        addq   $8,      %%rdi;      \
-        "
+#define MULADDC_CORE                        \
+        "movq   (%%rsi), %%rax      \n\t"   \
+        "mulq   %%rbx               \n\t"   \
+        "addq   $8,      %%rsi      \n\t"   \
+        "addq   %%rcx,   %%rax      \n\t"   \
+        "movq   %%r8,    %%rcx      \n\t"   \
+        "adcq   $0,      %%rdx      \n\t"   \
+        "nop                        \n\t"   \
+        "addq   %%rax,   (%%rdi)    \n\t"   \
+        "adcq   %%rdx,   %%rcx      \n\t"   \
+        "addq   $8,      %%rdi      \n\t"
 
-#define MULADDC_STOP                \
-        "                           \
-        movq   %%rcx, %0;           \
-        movq   %%rdi, %1;           \
-        movq   %%rsi, %2;           \
-        "                           \
+#define MULADDC_STOP                        \
+        "movq   %%rcx, %0           \n\t"   \
+        "movq   %%rdi, %1           \n\t"   \
+        "movq   %%rsi, %2           \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)                      \
         : "m" (s), "m" (d), "m" (c), "m" (b)                \
         : "rax", "rcx", "rdx", "rbx", "rsi", "rdi", "r8"    \
@@ -206,123 +191,108 @@
 
 #if defined(__mc68020__) || defined(__mcpu32__)
 
-#define MULADDC_INIT            \
-    asm(                        \
-        "                       \
-        movl   %3, %%a2;        \
-        movl   %4, %%a3;        \
-        movl   %5, %%d3;        \
-        movl   %6, %%d2;        \
-        moveq  #0, %%d0;        \
-        "
+#define MULADDC_INIT                    \
+    asm(                                \
+        "movl   %3, %%a2        \n\t"   \
+        "movl   %4, %%a3        \n\t"   \
+        "movl   %5, %%d3        \n\t"   \
+        "movl   %6, %%d2        \n\t"   \
+        "moveq  #0, %%d0        \n\t"
 
-#define MULADDC_CORE            \
-        "                       \
-        movel  %%a2@+, %%d1;    \
-        mulul  %%d2, %%d4:%%d1; \
-        addl   %%d3, %%d1;      \
-        addxl  %%d0, %%d4;      \
-        moveq  #0,   %%d3;      \
-        addl   %%d1, %%a3@+;    \
-        addxl  %%d4, %%d3;      \
-        "
+#define MULADDC_CORE                    \
+        "movel  %%a2@+, %%d1    \n\t"   \
+        "mulul  %%d2, %%d4:%%d1 \n\t"   \
+        "addl   %%d3, %%d1      \n\t"   \
+        "addxl  %%d0, %%d4      \n\t"   \
+        "moveq  #0,   %%d3      \n\t"   \
+        "addl   %%d1, %%a3@+    \n\t"   \
+        "addxl  %%d4, %%d3      \n\t"
 
-#define MULADDC_STOP            \
-        "                       \
-        movl   %%d3, %0;        \
-        movl   %%a3, %1;        \
-        movl   %%a2, %2;        \
-        "                       \
+#define MULADDC_STOP                    \
+        "movl   %%d3, %0        \n\t"   \
+        "movl   %%a3, %1        \n\t"   \
+        "movl   %%a2, %2        \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)              \
         : "m" (s), "m" (d), "m" (c), "m" (b)        \
         : "d0", "d1", "d2", "d3", "d4", "a2", "a3"  \
     );
 
-#define MULADDC_HUIT                \
-        "                           \
-        movel  %%a2@+,  %%d1;       \
-        mulul  %%d2,    %%d4:%%d1;  \
-        addxl  %%d3,    %%d1;       \
-        addxl  %%d0,    %%d4;       \
-        addl   %%d1,    %%a3@+;     \
-        movel  %%a2@+,  %%d1;       \
-        mulul  %%d2,    %%d3:%%d1;  \
-        addxl  %%d4,    %%d1;       \
-        addxl  %%d0,    %%d3;       \
-        addl   %%d1,    %%a3@+;     \
-        movel  %%a2@+,  %%d1;       \
-        mulul  %%d2,    %%d4:%%d1;  \
-        addxl  %%d3,    %%d1;       \
-        addxl  %%d0,    %%d4;       \
-        addl   %%d1,    %%a3@+;     \
-        movel  %%a2@+,  %%d1;       \
-        mulul  %%d2,    %%d3:%%d1;  \
-        addxl  %%d4,    %%d1;       \
-        addxl  %%d0,    %%d3;       \
-        addl   %%d1,    %%a3@+;     \
-        movel  %%a2@+,  %%d1;       \
-        mulul  %%d2,    %%d4:%%d1;  \
-        addxl  %%d3,    %%d1;       \
-        addxl  %%d0,    %%d4;       \
-        addl   %%d1,    %%a3@+;     \
-        movel  %%a2@+,  %%d1;       \
-        mulul  %%d2,    %%d3:%%d1;  \
-        addxl  %%d4,    %%d1;       \
-        addxl  %%d0,    %%d3;       \
-        addl   %%d1,    %%a3@+;     \
-        movel  %%a2@+,  %%d1;       \
-        mulul  %%d2,    %%d4:%%d1;  \
-        addxl  %%d3,    %%d1;       \
-        addxl  %%d0,    %%d4;       \
-        addl   %%d1,    %%a3@+;     \
-        movel  %%a2@+,  %%d1;       \
-        mulul  %%d2,    %%d3:%%d1;  \
-        addxl  %%d4,    %%d1;       \
-        addxl  %%d0,    %%d3;       \
-        addl   %%d1,    %%a3@+;     \
-        addxl  %%d0,    %%d3;       \
-        "
+#define MULADDC_HUIT                        \
+        "movel  %%a2@+,  %%d1       \n\t"   \
+        "mulul  %%d2,    %%d4:%%d1  \n\t"   \
+        "addxl  %%d3,    %%d1       \n\t"   \
+        "addxl  %%d0,    %%d4       \n\t"   \
+        "addl   %%d1,    %%a3@+     \n\t"   \
+        "movel  %%a2@+,  %%d1       \n\t"   \
+        "mulul  %%d2,    %%d3:%%d1  \n\t"   \
+        "addxl  %%d4,    %%d1       \n\t"   \
+        "addxl  %%d0,    %%d3       \n\t"   \
+        "addl   %%d1,    %%a3@+     \n\t"   \
+        "movel  %%a2@+,  %%d1       \n\t"   \
+        "mulul  %%d2,    %%d4:%%d1  \n\t"   \
+        "addxl  %%d3,    %%d1       \n\t"   \
+        "addxl  %%d0,    %%d4       \n\t"   \
+        "addl   %%d1,    %%a3@+     \n\t"   \
+        "movel  %%a2@+,  %%d1       \n\t"   \
+        "mulul  %%d2,    %%d3:%%d1  \n\t"   \
+        "addxl  %%d4,    %%d1       \n\t"   \
+        "addxl  %%d0,    %%d3       \n\t"   \
+        "addl   %%d1,    %%a3@+     \n\t"   \
+        "movel  %%a2@+,  %%d1       \n\t"   \
+        "mulul  %%d2,    %%d4:%%d1  \n\t"   \
+        "addxl  %%d3,    %%d1       \n\t"   \
+        "addxl  %%d0,    %%d4       \n\t"   \
+        "addl   %%d1,    %%a3@+     \n\t"   \
+        "movel  %%a2@+,  %%d1       \n\t"   \
+        "mulul  %%d2,    %%d3:%%d1  \n\t"   \
+        "addxl  %%d4,    %%d1       \n\t"   \
+        "addxl  %%d0,    %%d3       \n\t"   \
+        "addl   %%d1,    %%a3@+     \n\t"   \
+        "movel  %%a2@+,  %%d1       \n\t"   \
+        "mulul  %%d2,    %%d4:%%d1  \n\t"   \
+        "addxl  %%d3,    %%d1       \n\t"   \
+        "addxl  %%d0,    %%d4       \n\t"   \
+        "addl   %%d1,    %%a3@+     \n\t"   \
+        "movel  %%a2@+,  %%d1       \n\t"   \
+        "mulul  %%d2,    %%d3:%%d1  \n\t"   \
+        "addxl  %%d4,    %%d1       \n\t"   \
+        "addxl  %%d0,    %%d3       \n\t"   \
+        "addl   %%d1,    %%a3@+     \n\t"   \
+        "addxl  %%d0,    %%d3       \n\t"
 
 #endif /* MC68000 */
 
-#if defined(__powerpc__)   || defined(__ppc__)
 #if defined(__powerpc64__) || defined(__ppc64__)
 
 #if defined(__MACH__) && defined(__APPLE__)
 
-#define MULADDC_INIT                \
-    asm(                            \
-        "                           \
-        ld     r3, %3;              \
-        ld     r4, %4;              \
-        ld     r5, %5;              \
-        ld     r6, %6;              \
-        addi   r3, r3, -8;          \
-        addi   r4, r4, -8;          \
-        addic  r5, r5,  0;          \
-        "
+#define MULADDC_INIT                        \
+    asm(                                    \
+        "ld     r3, %3              \n\t"   \
+        "ld     r4, %4              \n\t"   \
+        "ld     r5, %5              \n\t"   \
+        "ld     r6, %6              \n\t"   \
+        "addi   r3, r3, -8          \n\t"   \
+        "addi   r4, r4, -8          \n\t"   \
+        "addic  r5, r5,  0          \n\t"
 
-#define MULADDC_CORE                \
-        "                           \
-        ldu    r7, 8(r3);           \
-        mulld  r8, r7, r6;          \
-        mulhdu r9, r7, r6;          \
-        adde   r8, r8, r5;          \
-        ld     r7, 8(r4);           \
-        addze  r5, r9;              \
-        addc   r8, r8, r7;          \
-        stdu   r8, 8(r4);           \
-        "
+#define MULADDC_CORE                        \
+        "ldu    r7, 8(r3)           \n\t"   \
+        "mulld  r8, r7, r6          \n\t"   \
+        "mulhdu r9, r7, r6          \n\t"   \
+        "adde   r8, r8, r5          \n\t"   \
+        "ld     r7, 8(r4)           \n\t"   \
+        "addze  r5, r9              \n\t"   \
+        "addc   r8, r8, r7          \n\t"   \
+        "stdu   r8, 8(r4)           \n\t"
 
-#define MULADDC_STOP                \
-        "                           \
-        addze  r5, r5;              \
-        addi   r4, r4, 8;           \
-        addi   r3, r3, 8;           \
-        std    r5, %0;              \
-        std    r4, %1;              \
-        std    r3, %2;              \
-        "                           \
+#define MULADDC_STOP                        \
+        "addze  r5, r5              \n\t"   \
+        "addi   r4, r4, 8           \n\t"   \
+        "addi   r3, r3, 8           \n\t"   \
+        "std    r5, %0              \n\t"   \
+        "std    r4, %1              \n\t"   \
+        "std    r3, %2              \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)              \
         : "m" (s), "m" (d), "m" (c), "m" (b)        \
         : "r3", "r4", "r5", "r6", "r7", "r8", "r9"  \
@@ -331,39 +301,33 @@
 
 #else /* __MACH__ && __APPLE__ */
 
-#define MULADDC_INIT                \
-    asm(                            \
-        "                           \
-        ld     %%r3, %3;            \
-        ld     %%r4, %4;            \
-        ld     %%r5, %5;            \
-        ld     %%r6, %6;            \
-        addi   %%r3, %%r3, -8;      \
-        addi   %%r4, %%r4, -8;      \
-        addic  %%r5, %%r5,  0;      \
-        "
+#define MULADDC_INIT                        \
+    asm(                                    \
+        "ld     %%r3, %3            \n\t"   \
+        "ld     %%r4, %4            \n\t"   \
+        "ld     %%r5, %5            \n\t"   \
+        "ld     %%r6, %6            \n\t"   \
+        "addi   %%r3, %%r3, -8      \n\t"   \
+        "addi   %%r4, %%r4, -8      \n\t"   \
+        "addic  %%r5, %%r5,  0      \n\t"
 
-#define MULADDC_CORE                \
-        "                           \
-        ldu    %%r7, 8(%%r3);       \
-        mulld  %%r8, %%r7, %%r6;    \
-        mulhdu %%r9, %%r7, %%r6;    \
-        adde   %%r8, %%r8, %%r5;    \
-        ld     %%r7, 8(%%r4);       \
-        addze  %%r5, %%r9;          \
-        addc   %%r8, %%r8, %%r7;    \
-        stdu   %%r8, 8(%%r4);       \
-        "
+#define MULADDC_CORE                        \
+        "ldu    %%r7, 8(%%r3)       \n\t"   \
+        "mulld  %%r8, %%r7, %%r6    \n\t"   \
+        "mulhdu %%r9, %%r7, %%r6    \n\t"   \
+        "adde   %%r8, %%r8, %%r5    \n\t"   \
+        "ld     %%r7, 8(%%r4)       \n\t"   \
+        "addze  %%r5, %%r9          \n\t"   \
+        "addc   %%r8, %%r8, %%r7    \n\t"   \
+        "stdu   %%r8, 8(%%r4)       \n\t"
 
-#define MULADDC_STOP                \
-        "                           \
-        addze  %%r5, %%r5;          \
-        addi   %%r4, %%r4, 8;       \
-        addi   %%r3, %%r3, 8;       \
-        std    %%r5, %0;            \
-        std    %%r4, %1;            \
-        std    %%r3, %2;            \
-        "                           \
+#define MULADDC_STOP                        \
+        "addze  %%r5, %%r5          \n\t"   \
+        "addi   %%r4, %%r4, 8       \n\t"   \
+        "addi   %%r3, %%r3, 8       \n\t"   \
+        "std    %%r5, %0            \n\t"   \
+        "std    %%r4, %1            \n\t"   \
+        "std    %%r3, %2            \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)              \
         : "m" (s), "m" (d), "m" (c), "m" (b)        \
         : "r3", "r4", "r5", "r6", "r7", "r8", "r9"  \
@@ -371,43 +335,37 @@
 
 #endif /* __MACH__ && __APPLE__ */
 
-#else /* PPC32 */
+#elif defined(__powerpc__) || defined(__ppc__) /* end PPC64/begin PPC32  */
 
 #if defined(__MACH__) && defined(__APPLE__)
 
-#define MULADDC_INIT            \
-    asm(                        \
-        "                       \
-        lwz    r3, %3;          \
-        lwz    r4, %4;          \
-        lwz    r5, %5;          \
-        lwz    r6, %6;          \
-        addi   r3, r3, -4;      \
-        addi   r4, r4, -4;      \
-        addic  r5, r5,  0;      \
-        "
+#define MULADDC_INIT                    \
+    asm(                                \
+        "lwz    r3, %3          \n\t"   \
+        "lwz    r4, %4          \n\t"   \
+        "lwz    r5, %5          \n\t"   \
+        "lwz    r6, %6          \n\t"   \
+        "addi   r3, r3, -4      \n\t"   \
+        "addi   r4, r4, -4      \n\t"   \
+        "addic  r5, r5,  0      \n\t"
 
-#define MULADDC_CORE            \
-        "                       \
-        lwzu   r7, 4(r3);       \
-        mullw  r8, r7, r6;      \
-        mulhwu r9, r7, r6;      \
-        adde   r8, r8, r5;      \
-        lwz    r7, 4(r4);       \
-        addze  r5, r9;          \
-        addc   r8, r8, r7;      \
-        stwu   r8, 4(r4);       \
-        "
+#define MULADDC_CORE                    \
+        "lwzu   r7, 4(r3)       \n\t"   \
+        "mullw  r8, r7, r6      \n\t"   \
+        "mulhwu r9, r7, r6      \n\t"   \
+        "adde   r8, r8, r5      \n\t"   \
+        "lwz    r7, 4(r4)       \n\t"   \
+        "addze  r5, r9          \n\t"   \
+        "addc   r8, r8, r7      \n\t"   \
+        "stwu   r8, 4(r4)       \n\t"
 
-#define MULADDC_STOP            \
-        "                       \
-        addze  r5, r5;          \
-        addi   r4, r4, 4;       \
-        addi   r3, r3, 4;       \
-        stw    r5, %0;          \
-        stw    r4, %1;          \
-        stw    r3, %2;          \
-        "                       \
+#define MULADDC_STOP                    \
+        "addze  r5, r5          \n\t"   \
+        "addi   r4, r4, 4       \n\t"   \
+        "addi   r3, r3, 4       \n\t"   \
+        "stw    r5, %0          \n\t"   \
+        "stw    r4, %1          \n\t"   \
+        "stw    r3, %2          \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)              \
         : "m" (s), "m" (d), "m" (c), "m" (b)        \
         : "r3", "r4", "r5", "r6", "r7", "r8", "r9"  \
@@ -415,39 +373,33 @@
 
 #else /* __MACH__ && __APPLE__ */
 
-#define MULADDC_INIT                \
-    asm(                            \
-        "                           \
-        lwz    %%r3, %3;            \
-        lwz    %%r4, %4;            \
-        lwz    %%r5, %5;            \
-        lwz    %%r6, %6;            \
-        addi   %%r3, %%r3, -4;      \
-        addi   %%r4, %%r4, -4;      \
-        addic  %%r5, %%r5,  0;      \
-        "
+#define MULADDC_INIT                        \
+    asm(                                    \
+        "lwz    %%r3, %3            \n\t"   \
+        "lwz    %%r4, %4            \n\t"   \
+        "lwz    %%r5, %5            \n\t"   \
+        "lwz    %%r6, %6            \n\t"   \
+        "addi   %%r3, %%r3, -4      \n\t"   \
+        "addi   %%r4, %%r4, -4      \n\t"   \
+        "addic  %%r5, %%r5,  0      \n\t"
 
-#define MULADDC_CORE                \
-        "                           \
-        lwzu   %%r7, 4(%%r3);       \
-        mullw  %%r8, %%r7, %%r6;    \
-        mulhwu %%r9, %%r7, %%r6;    \
-        adde   %%r8, %%r8, %%r5;    \
-        lwz    %%r7, 4(%%r4);       \
-        addze  %%r5, %%r9;          \
-        addc   %%r8, %%r8, %%r7;    \
-        stwu   %%r8, 4(%%r4);       \
-        "
+#define MULADDC_CORE                        \
+        "lwzu   %%r7, 4(%%r3)       \n\t"   \
+        "mullw  %%r8, %%r7, %%r6    \n\t"   \
+        "mulhwu %%r9, %%r7, %%r6    \n\t"   \
+        "adde   %%r8, %%r8, %%r5    \n\t"   \
+        "lwz    %%r7, 4(%%r4)       \n\t"   \
+        "addze  %%r5, %%r9          \n\t"   \
+        "addc   %%r8, %%r8, %%r7    \n\t"   \
+        "stwu   %%r8, 4(%%r4)       \n\t"
 
-#define MULADDC_STOP                \
-        "                           \
-        addze  %%r5, %%r5;          \
-        addi   %%r4, %%r4, 4;       \
-        addi   %%r3, %%r3, 4;       \
-        stw    %%r5, %0;            \
-        stw    %%r4, %1;            \
-        stw    %%r3, %2;            \
-        "                           \
+#define MULADDC_STOP                        \
+        "addze  %%r5, %%r5          \n\t"   \
+        "addi   %%r4, %%r4, 4       \n\t"   \
+        "addi   %%r3, %%r3, 4       \n\t"   \
+        "stw    %%r5, %0            \n\t"   \
+        "stw    %%r4, %1            \n\t"   \
+        "stw    %%r3, %2            \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)              \
         : "m" (s), "m" (d), "m" (c), "m" (b)        \
         : "r3", "r4", "r5", "r6", "r7", "r8", "r9"  \
@@ -456,40 +408,37 @@
 #endif /* __MACH__ && __APPLE__ */
 
 #endif /* PPC32 */
-#endif /* PPC64 */
 
-#if defined(__sparc__) && defined(__sparc64__)
+/*
+ * The Sparc64 assembly is reported to be broken.
+ * Disable it for now, until we're able to fix it.
+ */
+#if 0 && defined(__sparc__) && defined(__sparc64__)
 
-#define MULADDC_INIT                            \
-    asm(                                        \
-         "                                      \
-                ldx     %3, %%o0;               \
-                ldx     %4, %%o1;               \
-                ld      %5, %%o2;               \
-                ld      %6, %%o3;               \
-         "
+#define MULADDC_INIT                                    \
+    asm(                                                \
+                "ldx     %3, %%o0               \n\t"   \
+                "ldx     %4, %%o1               \n\t"   \
+                "ld      %5, %%o2               \n\t"   \
+                "ld      %6, %%o3               \n\t"
 
-#define MULADDC_CORE                            \
-         "                                      \
-                ld      [%%o0], %%o4;           \
-                inc     4, %%o0;                \
-                ld      [%%o1], %%o5;           \
-                umul    %%o3, %%o4, %%o4;       \
-                addcc   %%o4, %%o2, %%o4;       \
-                rd      %%y, %%g1;              \
-                addx    %%g1, 0, %%g1;          \
-                addcc   %%o4, %%o5, %%o4;       \
-                st      %%o4, [%%o1];           \
-                addx    %%g1, 0, %%o2;          \
-                inc     4, %%o1;                \
-        "
+#define MULADDC_CORE                                    \
+                "ld      [%%o0], %%o4           \n\t"   \
+                "inc     4, %%o0                \n\t"   \
+                "ld      [%%o1], %%o5           \n\t"   \
+                "umul    %%o3, %%o4, %%o4       \n\t"   \
+                "addcc   %%o4, %%o2, %%o4       \n\t"   \
+                "rd      %%y, %%g1              \n\t"   \
+                "addx    %%g1, 0, %%g1          \n\t"   \
+                "addcc   %%o4, %%o5, %%o4       \n\t"   \
+                "st      %%o4, [%%o1]           \n\t"   \
+                "addx    %%g1, 0, %%o2          \n\t"   \
+                "inc     4, %%o1                \n\t"
 
-#define MULADDC_STOP                            \
-        "                                       \
-                st      %%o2, %0;               \
-                stx     %%o1, %1;               \
-                stx     %%o0, %2;               \
-        "                                       \
+        #define MULADDC_STOP                            \
+                "st      %%o2, %0               \n\t"   \
+                "stx     %%o1, %1               \n\t"   \
+                "stx     %%o0, %2               \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)          \
         : "m" (s), "m" (d), "m" (c), "m" (b)    \
         : "g1", "o0", "o1", "o2", "o3", "o4",   \
@@ -499,36 +448,30 @@
 
 #if defined(__sparc__) && !defined(__sparc64__)
 
-#define MULADDC_INIT                            \
-    asm(                                        \
-         "                                      \
-                ld      %3, %%o0;               \
-                ld      %4, %%o1;               \
-                ld      %5, %%o2;               \
-                ld      %6, %%o3;               \
-         "
+#define MULADDC_INIT                                    \
+    asm(                                                \
+                "ld      %3, %%o0               \n\t"   \
+                "ld      %4, %%o1               \n\t"   \
+                "ld      %5, %%o2               \n\t"   \
+                "ld      %6, %%o3               \n\t"
 
-#define MULADDC_CORE                            \
-         "                                      \
-                ld      [%%o0], %%o4;           \
-                inc     4, %%o0;                \
-                ld      [%%o1], %%o5;           \
-                umul    %%o3, %%o4, %%o4;       \
-                addcc   %%o4, %%o2, %%o4;       \
-                rd      %%y, %%g1;              \
-                addx    %%g1, 0, %%g1;          \
-                addcc   %%o4, %%o5, %%o4;       \
-                st      %%o4, [%%o1];           \
-                addx    %%g1, 0, %%o2;          \
-                inc     4, %%o1;                \
-        "
+#define MULADDC_CORE                                    \
+                "ld      [%%o0], %%o4           \n\t"   \
+                "inc     4, %%o0                \n\t"   \
+                "ld      [%%o1], %%o5           \n\t"   \
+                "umul    %%o3, %%o4, %%o4       \n\t"   \
+                "addcc   %%o4, %%o2, %%o4       \n\t"   \
+                "rd      %%y, %%g1              \n\t"   \
+                "addx    %%g1, 0, %%g1          \n\t"   \
+                "addcc   %%o4, %%o5, %%o4       \n\t"   \
+                "st      %%o4, [%%o1]           \n\t"   \
+                "addx    %%g1, 0, %%o2          \n\t"   \
+                "inc     4, %%o1                \n\t"
 
-#define MULADDC_STOP                            \
-        "                                       \
-                st      %%o2, %0;               \
-                st      %%o1, %1;               \
-                st      %%o0, %2;               \
-        "                                       \
+#define MULADDC_STOP                                    \
+                "st      %%o2, %0               \n\t"   \
+                "st      %%o1, %1               \n\t"   \
+                "st      %%o0, %2               \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)          \
         : "m" (s), "m" (d), "m" (c), "m" (b)    \
         : "g1", "o0", "o1", "o2", "o3", "o4",   \
@@ -539,52 +482,46 @@
 
 #if defined(__microblaze__) || defined(microblaze)
 
-#define MULADDC_INIT            \
-    asm(                        \
-        "                       \
-        lwi   r3,   %3;         \
-        lwi   r4,   %4;         \
-        lwi   r5,   %5;         \
-        lwi   r6,   %6;         \
-        andi  r7,   r6, 0xffff; \
-        bsrli r6,   r6, 16;     \
-        "
+#define MULADDC_INIT                    \
+    asm(                                \
+        "lwi   r3,   %3         \n\t"   \
+        "lwi   r4,   %4         \n\t"   \
+        "lwi   r5,   %5         \n\t"   \
+        "lwi   r6,   %6         \n\t"   \
+        "andi  r7,   r6, 0xffff \n\t"   \
+        "bsrli r6,   r6, 16     \n\t"
 
-#define MULADDC_CORE            \
-        "                       \
-        lhui  r8,   r3,   0;    \
-        addi  r3,   r3,   2;    \
-        lhui  r9,   r3,   0;    \
-        addi  r3,   r3,   2;    \
-        mul   r10,  r9,  r6;    \
-        mul   r11,  r8,  r7;    \
-        mul   r12,  r9,  r7;    \
-        mul   r13,  r8,  r6;    \
-        bsrli  r8, r10,  16;    \
-        bsrli  r9, r11,  16;    \
-        add   r13, r13,  r8;    \
-        add   r13, r13,  r9;    \
-        bslli r10, r10,  16;    \
-        bslli r11, r11,  16;    \
-        add   r12, r12, r10;    \
-        addc  r13, r13,  r0;    \
-        add   r12, r12, r11;    \
-        addc  r13, r13,  r0;    \
-        lwi   r10,  r4,   0;    \
-        add   r12, r12, r10;    \
-        addc  r13, r13,  r0;    \
-        add   r12, r12,  r5;    \
-        addc   r5, r13,  r0;    \
-        swi   r12,  r4,   0;    \
-        addi   r4,  r4,   4;    \
-        "
+#define MULADDC_CORE                    \
+        "lhui  r8,   r3,   0    \n\t"   \
+        "addi  r3,   r3,   2    \n\t"   \
+        "lhui  r9,   r3,   0    \n\t"   \
+        "addi  r3,   r3,   2    \n\t"   \
+        "mul   r10,  r9,  r6    \n\t"   \
+        "mul   r11,  r8,  r7    \n\t"   \
+        "mul   r12,  r9,  r7    \n\t"   \
+        "mul   r13,  r8,  r6    \n\t"   \
+        "bsrli  r8, r10,  16    \n\t"   \
+        "bsrli  r9, r11,  16    \n\t"   \
+        "add   r13, r13,  r8    \n\t"   \
+        "add   r13, r13,  r9    \n\t"   \
+        "bslli r10, r10,  16    \n\t"   \
+        "bslli r11, r11,  16    \n\t"   \
+        "add   r12, r12, r10    \n\t"   \
+        "addc  r13, r13,  r0    \n\t"   \
+        "add   r12, r12, r11    \n\t"   \
+        "addc  r13, r13,  r0    \n\t"   \
+        "lwi   r10,  r4,   0    \n\t"   \
+        "add   r12, r12, r10    \n\t"   \
+        "addc  r13, r13,  r0    \n\t"   \
+        "add   r12, r12,  r5    \n\t"   \
+        "addc   r5, r13,  r0    \n\t"   \
+        "swi   r12,  r4,   0    \n\t"   \
+        "addi   r4,  r4,   4    \n\t"
 
-#define MULADDC_STOP            \
-        "                       \
-        swi   r5,   %0;         \
-        swi   r4,   %1;         \
-        swi   r3,   %2;         \
-        "                       \
+#define MULADDC_STOP                    \
+        "swi   r5,   %0         \n\t"   \
+        "swi   r4,   %1         \n\t"   \
+        "swi   r3,   %2         \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)              \
         : "m" (s), "m" (d), "m" (c), "m" (b)        \
         : "r3", "r4"  "r5", "r6", "r7", "r8",       \
@@ -595,33 +532,27 @@
 
 #if defined(__tricore__)
 
-#define MULADDC_INIT                    \
-    asm(                                \
-        "                               \
-        ld.a   %%a2, %3;                \
-        ld.a   %%a3, %4;                \
-        ld.w   %%d4, %5;                \
-        ld.w   %%d1, %6;                \
-        xor    %%d5, %%d5;              \
-        "
+#define MULADDC_INIT                            \
+    asm(                                        \
+        "ld.a   %%a2, %3                \n\t"   \
+        "ld.a   %%a3, %4                \n\t"   \
+        "ld.w   %%d4, %5                \n\t"   \
+        "ld.w   %%d1, %6                \n\t"   \
+        "xor    %%d5, %%d5              \n\t"
 
-#define MULADDC_CORE                    \
-        "                               \
-        ld.w   %%d0,   [%%a2+];         \
-        madd.u %%e2, %%e4, %%d0, %%d1;  \
-        ld.w   %%d0,   [%%a3];          \
-        addx   %%d2,    %%d2,  %%d0;    \
-        addc   %%d3,    %%d3,    0;     \
-        mov    %%d4,    %%d3;           \
-        st.w  [%%a3+],  %%d2;           \
-        "
+#define MULADDC_CORE                            \
+        "ld.w   %%d0,   [%%a2+]         \n\t"   \
+        "madd.u %%e2, %%e4, %%d0, %%d1  \n\t"   \
+        "ld.w   %%d0,   [%%a3]          \n\t"   \
+        "addx   %%d2,    %%d2,  %%d0    \n\t"   \
+        "addc   %%d3,    %%d3,    0     \n\t"   \
+        "mov    %%d4,    %%d3           \n\t"   \
+        "st.w  [%%a3+],  %%d2           \n\t"
 
-#define MULADDC_STOP                    \
-        "                               \
-        st.w   %0, %%d4;                \
-        st.a   %1, %%a3;                \
-        st.a   %2, %%a2;                \
-        "                               \
+#define MULADDC_STOP                            \
+        "st.w   %0, %%d4                \n\t"   \
+        "st.a   %1, %%a3                \n\t"   \
+        "st.a   %2, %%a2                \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)          \
         : "m" (s), "m" (d), "m" (c), "m" (b)    \
         : "d0", "d1", "e2", "d4", "a2", "a3"    \
@@ -633,59 +564,53 @@
 
 #if defined(__thumb__) && !defined(__thumb2__)
 
-#define MULADDC_INIT                            \
-    asm(                                        \
-         "                                      \
-            ldr    r0, %3;                      \
-            ldr    r1, %4;                      \
-            ldr    r2, %5;                      \
-            ldr    r3, %6;                      \
-            lsr    r7, r3, #16;                 \
-            mov    r9, r7;                      \
-            lsl    r7, r3, #16;                 \
-            lsr    r7, r7, #16;                 \
-            mov    r8, r7;                      \
-         "
+#define MULADDC_INIT                                    \
+    asm(                                                \
+            "ldr    r0, %3                      \n\t"   \
+            "ldr    r1, %4                      \n\t"   \
+            "ldr    r2, %5                      \n\t"   \
+            "ldr    r3, %6                      \n\t"   \
+            "lsr    r7, r3, #16                 \n\t"   \
+            "mov    r9, r7                      \n\t"   \
+            "lsl    r7, r3, #16                 \n\t"   \
+            "lsr    r7, r7, #16                 \n\t"   \
+            "mov    r8, r7                      \n\t"
 
-#define MULADDC_CORE                            \
-         "                                      \
-            ldmia  r0!, {r6};                   \
-            lsr    r7, r6, #16;                 \
-            lsl    r6, r6, #16;                 \
-            lsr    r6, r6, #16;                 \
-            mov    r4, r8;                      \
-            mul    r4, r6;                      \
-            mov    r3, r9;                      \
-            mul    r6, r3;                      \
-            mov    r5, r9;                      \
-            mul    r5, r7;                      \
-            mov    r3, r8;                      \
-            mul    r7, r3;                      \
-            lsr    r3, r6, #16;                 \
-            add    r5, r5, r3;                  \
-            lsr    r3, r7, #16;                 \
-            add    r5, r5, r3;                  \
-            add    r4, r4, r2;                  \
-            mov    r2, #0;                      \
-            adc    r5, r2;                      \
-            lsl    r3, r6, #16;                 \
-            add    r4, r4, r3;                  \
-            adc    r5, r2;                      \
-            lsl    r3, r7, #16;                 \
-            add    r4, r4, r3;                  \
-            adc    r5, r2;                      \
-            ldr    r3, [r1];                    \
-            add    r4, r4, r3;                  \
-            adc    r2, r5;                      \
-            stmia  r1!, {r4};                   \
-         "
+#define MULADDC_CORE                                    \
+            "ldmia  r0!, {r6}                   \n\t"   \
+            "lsr    r7, r6, #16                 \n\t"   \
+            "lsl    r6, r6, #16                 \n\t"   \
+            "lsr    r6, r6, #16                 \n\t"   \
+            "mov    r4, r8                      \n\t"   \
+            "mul    r4, r6                      \n\t"   \
+            "mov    r3, r9                      \n\t"   \
+            "mul    r6, r3                      \n\t"   \
+            "mov    r5, r9                      \n\t"   \
+            "mul    r5, r7                      \n\t"   \
+            "mov    r3, r8                      \n\t"   \
+            "mul    r7, r3                      \n\t"   \
+            "lsr    r3, r6, #16                 \n\t"   \
+            "add    r5, r5, r3                  \n\t"   \
+            "lsr    r3, r7, #16                 \n\t"   \
+            "add    r5, r5, r3                  \n\t"   \
+            "add    r4, r4, r2                  \n\t"   \
+            "mov    r2, #0                      \n\t"   \
+            "adc    r5, r2                      \n\t"   \
+            "lsl    r3, r6, #16                 \n\t"   \
+            "add    r4, r4, r3                  \n\t"   \
+            "adc    r5, r2                      \n\t"   \
+            "lsl    r3, r7, #16                 \n\t"   \
+            "add    r4, r4, r3                  \n\t"   \
+            "adc    r5, r2                      \n\t"   \
+            "ldr    r3, [r1]                    \n\t"   \
+            "add    r4, r4, r3                  \n\t"   \
+            "adc    r2, r5                      \n\t"   \
+            "stmia  r1!, {r4}                   \n\t"
 
-#define MULADDC_STOP                            \
-         "                                      \
-            str    r2, %0;                      \
-            str    r1, %1;                      \
-            str    r0, %2;                      \
-         "                                      \
+#define MULADDC_STOP                                    \
+            "str    r2, %0                      \n\t"   \
+            "str    r1, %1                      \n\t"   \
+            "str    r0, %2                      \n\t"   \
          : "=m" (c),  "=m" (d), "=m" (s)        \
          : "m" (s), "m" (d), "m" (c), "m" (b)   \
          : "r0", "r1", "r2", "r3", "r4", "r5",  \
@@ -694,32 +619,26 @@
 
 #else
 
-#define MULADDC_INIT                            \
-    asm(                                        \
-         "                                     \
-            ldr    r0, %3;                      \
-            ldr    r1, %4;                      \
-            ldr    r2, %5;                      \
-            ldr    r3, %6;                      \
-         "
+#define MULADDC_INIT                                    \
+    asm(                                                \
+            "ldr    r0, %3                      \n\t"   \
+            "ldr    r1, %4                      \n\t"   \
+            "ldr    r2, %5                      \n\t"   \
+            "ldr    r3, %6                      \n\t"
 
-#define MULADDC_CORE                            \
-         "                                      \
-            ldr    r4, [r0], #4;                \
-            mov    r5, #0;                      \
-            ldr    r6, [r1];                    \
-            umlal  r2, r5, r3, r4;              \
-            adds   r7, r6, r2;                  \
-            adc    r2, r5, #0;                  \
-            str    r7, [r1], #4;                \
-         "
+#define MULADDC_CORE                                    \
+            "ldr    r4, [r0], #4                \n\t"   \
+            "mov    r5, #0                      \n\t"   \
+            "ldr    r6, [r1]                    \n\t"   \
+            "umlal  r2, r5, r3, r4              \n\t"   \
+            "adds   r7, r6, r2                  \n\t"   \
+            "adc    r2, r5, #0                  \n\t"   \
+            "str    r7, [r1], #4                \n\t"
 
-#define MULADDC_STOP                            \
-         "                                      \
-            str    r2, %0;                      \
-            str    r1, %1;                      \
-            str    r0, %2;                      \
-         "                                      \
+#define MULADDC_STOP                                    \
+            "str    r2, %0                      \n\t"   \
+            "str    r1, %1                      \n\t"   \
+            "str    r0, %2                      \n\t"   \
          : "=m" (c),  "=m" (d), "=m" (s)        \
          : "m" (s), "m" (d), "m" (c), "m" (b)   \
          : "r0", "r1", "r2", "r3", "r4", "r5",  \
@@ -732,38 +651,32 @@
 
 #if defined(__alpha__)
 
-#define MULADDC_INIT            \
-    asm(                        \
-        "                       \
-        ldq    $1, %3;          \
-        ldq    $2, %4;          \
-        ldq    $3, %5;          \
-        ldq    $4, %6;          \
-        "
+#define MULADDC_INIT                    \
+    asm(                                \
+        "ldq    $1, %3          \n\t"   \
+        "ldq    $2, %4          \n\t"   \
+        "ldq    $3, %5          \n\t"   \
+        "ldq    $4, %6          \n\t"
 
-#define MULADDC_CORE            \
-        "                       \
-        ldq    $6,  0($1);      \
-        addq   $1,  8, $1;      \
-        mulq   $6, $4, $7;      \
-        umulh  $6, $4, $6;      \
-        addq   $7, $3, $7;      \
-        cmpult $7, $3, $3;      \
-        ldq    $5,  0($2);      \
-        addq   $7, $5, $7;      \
-        cmpult $7, $5, $5;      \
-        stq    $7,  0($2);      \
-        addq   $2,  8, $2;      \
-        addq   $6, $3, $3;      \
-        addq   $5, $3, $3;      \
-        "
+#define MULADDC_CORE                    \
+        "ldq    $6,  0($1)      \n\t"   \
+        "addq   $1,  8, $1      \n\t"   \
+        "mulq   $6, $4, $7      \n\t"   \
+        "umulh  $6, $4, $6      \n\t"   \
+        "addq   $7, $3, $7      \n\t"   \
+        "cmpult $7, $3, $3      \n\t"   \
+        "ldq    $5,  0($2)      \n\t"   \
+        "addq   $7, $5, $7      \n\t"   \
+        "cmpult $7, $5, $5      \n\t"   \
+        "stq    $7,  0($2)      \n\t"   \
+        "addq   $2,  8, $2      \n\t"   \
+        "addq   $6, $3, $3      \n\t"   \
+        "addq   $5, $3, $3      \n\t"
 
-#define MULADDC_STOP                            \
-        "                       \
-        stq    $3, %0;          \
-        stq    $2, %1;          \
-        stq    $1, %2;          \
-        "                       \
+#define MULADDC_STOP                                    \
+        "stq    $3, %0          \n\t"   \
+        "stq    $2, %1          \n\t"   \
+        "stq    $1, %2          \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)              \
         : "m" (s), "m" (d), "m" (c), "m" (b)        \
         : "$1", "$2", "$3", "$4", "$5", "$6", "$7"  \
@@ -772,39 +685,33 @@
 
 #if defined(__mips__) && !defined(__mips64__)
 
-#define MULADDC_INIT            \
-    asm(                        \
-        "                       \
-        lw     $10, %3;         \
-        lw     $11, %4;         \
-        lw     $12, %5;         \
-        lw     $13, %6;         \
-        "
+#define MULADDC_INIT                    \
+    asm(                                \
+        "lw     $10, %3         \n\t"   \
+        "lw     $11, %4         \n\t"   \
+        "lw     $12, %5         \n\t"   \
+        "lw     $13, %6         \n\t"
 
-#define MULADDC_CORE            \
-        "                       \
-        lw     $14, 0($10);     \
-        multu  $13, $14;        \
-        addi   $10, $10, 4;     \
-        mflo   $14;             \
-        mfhi   $9;              \
-        addu   $14, $12, $14;   \
-        lw     $15, 0($11);     \
-        sltu   $12, $14, $12;   \
-        addu   $15, $14, $15;   \
-        sltu   $14, $15, $14;   \
-        addu   $12, $12, $9;    \
-        sw     $15, 0($11);     \
-        addu   $12, $12, $14;   \
-        addi   $11, $11, 4;     \
-        "
+#define MULADDC_CORE                    \
+        "lw     $14, 0($10)     \n\t"   \
+        "multu  $13, $14        \n\t"   \
+        "addi   $10, $10, 4     \n\t"   \
+        "mflo   $14             \n\t"   \
+        "mfhi   $9              \n\t"   \
+        "addu   $14, $12, $14   \n\t"   \
+        "lw     $15, 0($11)     \n\t"   \
+        "sltu   $12, $14, $12   \n\t"   \
+        "addu   $15, $14, $15   \n\t"   \
+        "sltu   $14, $15, $14   \n\t"   \
+        "addu   $12, $12, $9    \n\t"   \
+        "sw     $15, 0($11)     \n\t"   \
+        "addu   $12, $12, $14   \n\t"   \
+        "addi   $11, $11, 4     \n\t"
 
-#define MULADDC_STOP            \
-        "                       \
-        sw     $12, %0;         \
-        sw     $11, %1;         \
-        sw     $10, %2;         \
-        "                       \
+#define MULADDC_STOP                    \
+        "sw     $12, %0         \n\t"   \
+        "sw     $11, %1         \n\t"   \
+        "sw     $10, %2         \n\t"   \
         : "=m" (c), "=m" (d), "=m" (s)                      \
         : "m" (s), "m" (d), "m" (c), "m" (b)                \
         : "$9", "$10", "$11", "$12", "$13", "$14", "$15"    \
diff --git a/include/polarssl/ssl.h b/include/polarssl/ssl.h
index 21ed42e..91e3981 100644
--- a/include/polarssl/ssl.h
+++ b/include/polarssl/ssl.h
@@ -258,8 +258,8 @@
 /* \} name SECTION: Module settings */
 
 /*
- * Allow an extra 301 bytes for the record header
- * and encryption overhead: counter (8) + header (5) + MAC (32) + padding (256)
+ * Allow an extra 301 bytes for the record header and encryption overhead:
+ * counter (8) + header (5) + IV(16) + MAC (48) + padding (256)
  * and allow for a maximum of 1024 of compression expansion if
  * enabled.
  */
@@ -269,7 +269,7 @@
 #define SSL_COMPRESSION_ADD             0
 #endif
 
-#define SSL_BUFFER_LEN (SSL_MAX_CONTENT_LEN + SSL_COMPRESSION_ADD + 301)
+#define SSL_BUFFER_LEN (SSL_MAX_CONTENT_LEN + SSL_COMPRESSION_ADD + 333)
 
 #define SSL_EMPTY_RENEGOTIATION_INFO    0xFF   /**< renegotiation info ext */
 
diff --git a/include/polarssl/x509_crl.h b/include/polarssl/x509_crl.h
index 3016b87..9f597a8 100644
--- a/include/polarssl/x509_crl.h
+++ b/include/polarssl/x509_crl.h
@@ -75,7 +75,7 @@
     x509_buf raw;           /**< The raw certificate data (DER). */
     x509_buf tbs;           /**< The raw certificate body (DER). The part that is To Be Signed. */
 
-    int version;
+    int version;            /**< CRL version (1=v1, 2=v2) */
     x509_buf sig_oid1;
 
     x509_buf issuer_raw;    /**< The raw issuer data (DER). */
diff --git a/include/polarssl/x509_crt.h b/include/polarssl/x509_crt.h
index e90e357..4bf8e56 100644
--- a/include/polarssl/x509_crt.h
+++ b/include/polarssl/x509_crt.h
@@ -59,7 +59,7 @@
     x509_buf raw;               /**< The raw certificate data (DER). */
     x509_buf tbs;               /**< The raw certificate body (DER). The part that is To Be Signed. */
 
-    int version;                /**< The X.509 version. (0=v1, 1=v2, 2=v3) */
+    int version;                /**< The X.509 version. (1=v1, 2=v2, 3=v3) */
     x509_buf serial;            /**< Unique id for certificate issued by a specific CA. */
     x509_buf sig_oid1;          /**< Signature algorithm, e.g. sha1RSA */
 
diff --git a/include/polarssl/x509_csr.h b/include/polarssl/x509_csr.h
index bbe6bec..6591e38 100644
--- a/include/polarssl/x509_csr.h
+++ b/include/polarssl/x509_csr.h
@@ -56,7 +56,7 @@
     x509_buf raw;           /**< The raw CSR data (DER). */
     x509_buf cri;           /**< The raw CertificateRequestInfo body (DER). */
 
-    int version;
+    int version;            /**< CSR version (1=v1). */
 
     x509_buf  subject_raw;  /**< The raw subject data (DER). */
     x509_name subject;      /**< The parsed subject data (named information object). */
diff --git a/library/aesni.c b/library/aesni.c
index 9bd780f..97f646e 100644
--- a/library/aesni.c
+++ b/library/aesni.c
@@ -51,8 +51,8 @@
 
     if( ! done )
     {
-        asm( "movl  $1, %%eax   \n"
-             "cpuid             \n"
+        asm( "movl  $1, %%eax   \n\t"
+             "cpuid             \n\t"
              : "=c" (c)
              :
              : "eax", "ebx", "edx" );
@@ -96,35 +96,35 @@
                      const unsigned char input[16],
                      unsigned char output[16] )
 {
-    asm( "movdqu    (%3), %%xmm0    \n" // load input
-         "movdqu    (%1), %%xmm1    \n" // load round key 0
-         "pxor      %%xmm1, %%xmm0  \n" // round 0
-         "addq      $16, %1         \n" // point to next round key
-         "subl      $1, %0          \n" // normal rounds = nr - 1
-         "test      %2, %2          \n" // mode?
-         "jz        2f              \n" // 0 = decrypt
+    asm( "movdqu    (%3), %%xmm0    \n\t" // load input
+         "movdqu    (%1), %%xmm1    \n\t" // load round key 0
+         "pxor      %%xmm1, %%xmm0  \n\t" // round 0
+         "addq      $16, %1         \n\t" // point to next round key
+         "subl      $1, %0          \n\t" // normal rounds = nr - 1
+         "test      %2, %2          \n\t" // mode?
+         "jz        2f              \n\t" // 0 = decrypt
 
-         "1:                        \n" // encryption loop
-         "movdqu    (%1), %%xmm1    \n" // load round key
-         AESENC     xmm1_xmm0      "\n" // do round
-         "addq      $16, %1         \n" // point to next round key
-         "subl      $1, %0          \n" // loop
-         "jnz       1b              \n"
-         "movdqu    (%1), %%xmm1    \n" // load round key
-         AESENCLAST xmm1_xmm0      "\n" // last round
-         "jmp       3f              \n"
+         "1:                        \n\t" // encryption loop
+         "movdqu    (%1), %%xmm1    \n\t" // load round key
+         AESENC     xmm1_xmm0      "\n\t" // do round
+         "addq      $16, %1         \n\t" // point to next round key
+         "subl      $1, %0          \n\t" // loop
+         "jnz       1b              \n\t"
+         "movdqu    (%1), %%xmm1    \n\t" // load round key
+         AESENCLAST xmm1_xmm0      "\n\t" // last round
+         "jmp       3f              \n\t"
 
-         "2:                        \n" // decryption loop
-         "movdqu    (%1), %%xmm1    \n"
-         AESDEC     xmm1_xmm0      "\n" // do round
-         "addq      $16, %1         \n"
-         "subl      $1, %0          \n"
-         "jnz       2b              \n"
-         "movdqu    (%1), %%xmm1    \n" // load round key
-         AESDECLAST xmm1_xmm0      "\n" // last round
+         "2:                        \n\t" // decryption loop
+         "movdqu    (%1), %%xmm1    \n\t"
+         AESDEC     xmm1_xmm0      "\n\t" // do round
+         "addq      $16, %1         \n\t"
+         "subl      $1, %0          \n\t"
+         "jnz       2b              \n\t"
+         "movdqu    (%1), %%xmm1    \n\t" // load round key
+         AESDECLAST xmm1_xmm0      "\n\t" // last round
 
-         "3:                        \n"
-         "movdqu    %%xmm0, (%4)    \n" // export output
+         "3:                        \n\t"
+         "movdqu    %%xmm0, (%4)    \n\t" // export output
          :
          : "r" (ctx->nr), "r" (ctx->rk), "r" (mode), "r" (input), "r" (output)
          : "memory", "cc", "xmm0", "xmm1" );
@@ -151,44 +151,44 @@
         bb[i] = b[15 - i];
     }
 
-    asm( "movdqu (%0), %%xmm0               \n" // a1:a0
-         "movdqu (%1), %%xmm1               \n" // b1:b0
+    asm( "movdqu (%0), %%xmm0               \n\t" // a1:a0
+         "movdqu (%1), %%xmm1               \n\t" // b1:b0
 
          /*
           * Caryless multiplication xmm2:xmm1 = xmm0 * xmm1
           * using [CLMUL-WP] algorithm 1 (p. 13).
           */
-         "movdqa %%xmm1, %%xmm2             \n" // copy of b1:b0
-         "movdqa %%xmm1, %%xmm3             \n" // same
-         "movdqa %%xmm1, %%xmm4             \n" // same
-         PCLMULQDQ xmm0_xmm1 ",0x00         \n" // a0*b0 = c1:c0
-         PCLMULQDQ xmm0_xmm2 ",0x11         \n" // a1*b1 = d1:d0
-         PCLMULQDQ xmm0_xmm3 ",0x10         \n" // a0*b1 = e1:e0
-         PCLMULQDQ xmm0_xmm4 ",0x01         \n" // a1*b0 = f1:f0
-         "pxor %%xmm3, %%xmm4               \n" // e1+f1:e0+f0
-         "movdqa %%xmm4, %%xmm3             \n" // same
-         "psrldq $8, %%xmm4                 \n" // 0:e1+f1
-         "pslldq $8, %%xmm3                 \n" // e0+f0:0
-         "pxor %%xmm4, %%xmm2               \n" // d1:d0+e1+f1
-         "pxor %%xmm3, %%xmm1               \n" // c1+e0+f1:c0
+         "movdqa %%xmm1, %%xmm2             \n\t" // copy of b1:b0
+         "movdqa %%xmm1, %%xmm3             \n\t" // same
+         "movdqa %%xmm1, %%xmm4             \n\t" // same
+         PCLMULQDQ xmm0_xmm1 ",0x00         \n\t" // a0*b0 = c1:c0
+         PCLMULQDQ xmm0_xmm2 ",0x11         \n\t" // a1*b1 = d1:d0
+         PCLMULQDQ xmm0_xmm3 ",0x10         \n\t" // a0*b1 = e1:e0
+         PCLMULQDQ xmm0_xmm4 ",0x01         \n\t" // a1*b0 = f1:f0
+         "pxor %%xmm3, %%xmm4               \n\t" // e1+f1:e0+f0
+         "movdqa %%xmm4, %%xmm3             \n\t" // same
+         "psrldq $8, %%xmm4                 \n\t" // 0:e1+f1
+         "pslldq $8, %%xmm3                 \n\t" // e0+f0:0
+         "pxor %%xmm4, %%xmm2               \n\t" // d1:d0+e1+f1
+         "pxor %%xmm3, %%xmm1               \n\t" // c1+e0+f1:c0
 
          /*
           * Now shift the result one bit to the left,
           * taking advantage of [CLMUL-WP] eq 27 (p. 20)
           */
-         "movdqa %%xmm1, %%xmm3             \n" // r1:r0
-         "movdqa %%xmm2, %%xmm4             \n" // r3:r2
-         "psllq $1, %%xmm1                  \n" // r1<<1:r0<<1
-         "psllq $1, %%xmm2                  \n" // r3<<1:r2<<1
-         "psrlq $63, %%xmm3                 \n" // r1>>63:r0>>63
-         "psrlq $63, %%xmm4                 \n" // r3>>63:r2>>63
-         "movdqa %%xmm3, %%xmm5             \n" // r1>>63:r0>>63
-         "pslldq $8, %%xmm3                 \n" // r0>>63:0
-         "pslldq $8, %%xmm4                 \n" // r2>>63:0
-         "psrldq $8, %%xmm5                 \n" // 0:r1>>63
-         "por %%xmm3, %%xmm1                \n" // r1<<1|r0>>63:r0<<1
-         "por %%xmm4, %%xmm2                \n" // r3<<1|r2>>62:r2<<1
-         "por %%xmm5, %%xmm2                \n" // r3<<1|r2>>62:r2<<1|r1>>63
+         "movdqa %%xmm1, %%xmm3             \n\t" // r1:r0
+         "movdqa %%xmm2, %%xmm4             \n\t" // r3:r2
+         "psllq $1, %%xmm1                  \n\t" // r1<<1:r0<<1
+         "psllq $1, %%xmm2                  \n\t" // r3<<1:r2<<1
+         "psrlq $63, %%xmm3                 \n\t" // r1>>63:r0>>63
+         "psrlq $63, %%xmm4                 \n\t" // r3>>63:r2>>63
+         "movdqa %%xmm3, %%xmm5             \n\t" // r1>>63:r0>>63
+         "pslldq $8, %%xmm3                 \n\t" // r0>>63:0
+         "pslldq $8, %%xmm4                 \n\t" // r2>>63:0
+         "psrldq $8, %%xmm5                 \n\t" // 0:r1>>63
+         "por %%xmm3, %%xmm1                \n\t" // r1<<1|r0>>63:r0<<1
+         "por %%xmm4, %%xmm2                \n\t" // r3<<1|r2>>62:r2<<1
+         "por %%xmm5, %%xmm2                \n\t" // r3<<1|r2>>62:r2<<1|r1>>63
 
          /*
           * Now reduce modulo the GCM polynomial x^128 + x^7 + x^2 + x + 1
@@ -196,44 +196,44 @@
           * Currently xmm2:xmm1 holds x3:x2:x1:x0 (already shifted).
           */
          /* Step 2 (1) */
-         "movdqa %%xmm1, %%xmm3             \n" // x1:x0
-         "movdqa %%xmm1, %%xmm4             \n" // same
-         "movdqa %%xmm1, %%xmm5             \n" // same
-         "psllq $63, %%xmm3                 \n" // x1<<63:x0<<63 = stuff:a
-         "psllq $62, %%xmm4                 \n" // x1<<62:x0<<62 = stuff:b
-         "psllq $57, %%xmm5                 \n" // x1<<57:x0<<57 = stuff:c
+         "movdqa %%xmm1, %%xmm3             \n\t" // x1:x0
+         "movdqa %%xmm1, %%xmm4             \n\t" // same
+         "movdqa %%xmm1, %%xmm5             \n\t" // same
+         "psllq $63, %%xmm3                 \n\t" // x1<<63:x0<<63 = stuff:a
+         "psllq $62, %%xmm4                 \n\t" // x1<<62:x0<<62 = stuff:b
+         "psllq $57, %%xmm5                 \n\t" // x1<<57:x0<<57 = stuff:c
 
          /* Step 2 (2) */
-         "pxor %%xmm4, %%xmm3               \n" // stuff:a+b
-         "pxor %%xmm5, %%xmm3               \n" // stuff:a+b+c
-         "pslldq $8, %%xmm3                 \n" // a+b+c:0
-         "pxor %%xmm3, %%xmm1               \n" // x1+a+b+c:x0 = d:x0
+         "pxor %%xmm4, %%xmm3               \n\t" // stuff:a+b
+         "pxor %%xmm5, %%xmm3               \n\t" // stuff:a+b+c
+         "pslldq $8, %%xmm3                 \n\t" // a+b+c:0
+         "pxor %%xmm3, %%xmm1               \n\t" // x1+a+b+c:x0 = d:x0
 
          /* Steps 3 and 4 */
-         "movdqa %%xmm1,%%xmm0              \n" // d:x0
-         "movdqa %%xmm1,%%xmm4              \n" // same
-         "movdqa %%xmm1,%%xmm5              \n" // same
-         "psrlq $1, %%xmm0                  \n" // e1:x0>>1 = e1:e0'
-         "psrlq $2, %%xmm4                  \n" // f1:x0>>2 = f1:f0'
-         "psrlq $7, %%xmm5                  \n" // g1:x0>>7 = g1:g0'
-         "pxor %%xmm4, %%xmm0               \n" // e1+f1:e0'+f0'
-         "pxor %%xmm5, %%xmm0               \n" // e1+f1+g1:e0'+f0'+g0'
-         // e0'+f0'+g0' is almost e0+f0+g0, except for some missing
-         // bits carried from d. Now get those bits back in.
-         "movdqa %%xmm1,%%xmm3              \n" // d:x0
-         "movdqa %%xmm1,%%xmm4              \n" // same
-         "movdqa %%xmm1,%%xmm5              \n" // same
-         "psllq $63, %%xmm3                 \n" // d<<63:stuff
-         "psllq $62, %%xmm4                 \n" // d<<62:stuff
-         "psllq $57, %%xmm5                 \n" // d<<57:stuff
-         "pxor %%xmm4, %%xmm3               \n" // d<<63+d<<62:stuff
-         "pxor %%xmm5, %%xmm3               \n" // missing bits of d:stuff
-         "psrldq $8, %%xmm3                 \n" // 0:missing bits of d
-         "pxor %%xmm3, %%xmm0               \n" // e1+f1+g1:e0+f0+g0
-         "pxor %%xmm1, %%xmm0               \n" // h1:h0
-         "pxor %%xmm2, %%xmm0               \n" // x3+h1:x2+h0
+         "movdqa %%xmm1,%%xmm0              \n\t" // d:x0
+         "movdqa %%xmm1,%%xmm4              \n\t" // same
+         "movdqa %%xmm1,%%xmm5              \n\t" // same
+         "psrlq $1, %%xmm0                  \n\t" // e1:x0>>1 = e1:e0'
+         "psrlq $2, %%xmm4                  \n\t" // f1:x0>>2 = f1:f0'
+         "psrlq $7, %%xmm5                  \n\t" // g1:x0>>7 = g1:g0'
+         "pxor %%xmm4, %%xmm0               \n\t" // e1+f1:e0'+f0'
+         "pxor %%xmm5, %%xmm0               \n\t" // e1+f1+g1:e0'+f0'+g0'
+         // e0'+f0'+g0' is almost e0+f0+g0, ex\tcept for some missing
+         // bits carried from d. Now get those\t bits back in.
+         "movdqa %%xmm1,%%xmm3              \n\t" // d:x0
+         "movdqa %%xmm1,%%xmm4              \n\t" // same
+         "movdqa %%xmm1,%%xmm5              \n\t" // same
+         "psllq $63, %%xmm3                 \n\t" // d<<63:stuff
+         "psllq $62, %%xmm4                 \n\t" // d<<62:stuff
+         "psllq $57, %%xmm5                 \n\t" // d<<57:stuff
+         "pxor %%xmm4, %%xmm3               \n\t" // d<<63+d<<62:stuff
+         "pxor %%xmm5, %%xmm3               \n\t" // missing bits of d:stuff
+         "psrldq $8, %%xmm3                 \n\t" // 0:missing bits of d
+         "pxor %%xmm3, %%xmm0               \n\t" // e1+f1+g1:e0+f0+g0
+         "pxor %%xmm1, %%xmm0               \n\t" // h1:h0
+         "pxor %%xmm2, %%xmm0               \n\t" // x3+h1:x2+h0
 
-         "movdqu %%xmm0, (%2)               \n" // done
+         "movdqu %%xmm0, (%2)               \n\t" // done
          :
          : "r" (aa), "r" (bb), "r" (cc)
          : "memory", "cc", "xmm0", "xmm1", "xmm2", "xmm3", "xmm4", "xmm5" );
@@ -257,9 +257,9 @@
     memcpy( ik, fk, 16 );
 
     for( fk -= 16, ik += 16; fk > fwdkey; fk -= 16, ik += 16 )
-        asm( "movdqu (%0), %%xmm0       \n"
-             AESIMC  xmm0_xmm0         "\n"
-             "movdqu %%xmm0, (%1)       \n"
+        asm( "movdqu (%0), %%xmm0       \n\t"
+             AESIMC  xmm0_xmm0         "\n\t"
+             "movdqu %%xmm0, (%1)       \n\t"
              :
              : "r" (fk), "r" (ik)
              : "memory", "xmm0" );
@@ -273,9 +273,9 @@
 static void aesni_setkey_enc_128( unsigned char *rk,
                                   const unsigned char *key )
 {
-    asm( "movdqu (%1), %%xmm0               \n" // copy the original key
-         "movdqu %%xmm0, (%0)               \n" // as round key 0
-         "jmp 2f                            \n" // skip auxiliary routine
+    asm( "movdqu (%1), %%xmm0               \n\t" // copy the original key
+         "movdqu %%xmm0, (%0)               \n\t" // as round key 0
+         "jmp 2f                            \n\t" // skip auxiliary routine
 
          /*
           * Finish generating the next round key.
@@ -287,31 +287,31 @@
           * with r4 = X + r0, r5 = r4 + r1, r6 = r5 + r2, r7 = r6 + r3
           * and those are written to the round key buffer.
           */
-         "1:                                \n"
-         "pshufd $0xff, %%xmm1, %%xmm1      \n" // X:X:X:X
-         "pxor %%xmm0, %%xmm1               \n" // X+r3:X+r2:X+r1:r4
-         "pslldq $4, %%xmm0                 \n" // r2:r1:r0:0
-         "pxor %%xmm0, %%xmm1               \n" // X+r3+r2:X+r2+r1:r5:r4
-         "pslldq $4, %%xmm0                 \n" // etc
-         "pxor %%xmm0, %%xmm1               \n"
-         "pslldq $4, %%xmm0                 \n"
-         "pxor %%xmm1, %%xmm0               \n" // update xmm0 for next time!
-         "add $16, %0                       \n" // point to next round key
-         "movdqu %%xmm0, (%0)               \n" // write it
-         "ret                               \n"
+         "1:                                \n\t"
+         "pshufd $0xff, %%xmm1, %%xmm1      \n\t" // X:X:X:X
+         "pxor %%xmm0, %%xmm1               \n\t" // X+r3:X+r2:X+r1:r4
+         "pslldq $4, %%xmm0                 \n\t" // r2:r1:r0:0
+         "pxor %%xmm0, %%xmm1               \n\t" // X+r3+r2:X+r2+r1:r5:r4
+         "pslldq $4, %%xmm0                 \n\t" // etc
+         "pxor %%xmm0, %%xmm1               \n\t"
+         "pslldq $4, %%xmm0                 \n\t"
+         "pxor %%xmm1, %%xmm0               \n\t" // update xmm0 for next time!
+         "add $16, %0                       \n\t" // point to next round key
+         "movdqu %%xmm0, (%0)               \n\t" // write it
+         "ret                               \n\t"
 
          /* Main "loop" */
-         "2:                                \n"
-         AESKEYGENA xmm0_xmm1 ",0x01        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x02        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x04        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x08        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x10        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x20        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x40        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x80        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x1B        \ncall 1b   \n"
-         AESKEYGENA xmm0_xmm1 ",0x36        \ncall 1b   \n"
+         "2:                                \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x01        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x02        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x04        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x08        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x10        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x20        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x40        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x80        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x1B        \n\tcall 1b \n\t"
+         AESKEYGENA xmm0_xmm1 ",0x36        \n\tcall 1b \n\t"
          :
          : "r" (rk), "r" (key)
          : "memory", "cc", "0" );
@@ -323,13 +323,13 @@
 static void aesni_setkey_enc_192( unsigned char *rk,
                                   const unsigned char *key )
 {
-    asm( "movdqu (%1), %%xmm0   \n" // copy original round key
-         "movdqu %%xmm0, (%0)   \n"
-         "add $16, %0           \n"
-         "movq 16(%1), %%xmm1   \n"
-         "movq %%xmm1, (%0)     \n"
-         "add $8, %0            \n"
-         "jmp 2f                \n" // skip auxiliary routine
+    asm( "movdqu (%1), %%xmm0   \n\t" // copy original round key
+         "movdqu %%xmm0, (%0)   \n\t"
+         "add $16, %0           \n\t"
+         "movq 16(%1), %%xmm1   \n\t"
+         "movq %%xmm1, (%0)     \n\t"
+         "add $8, %0            \n\t"
+         "jmp 2f                \n\t" // skip auxiliary routine
 
          /*
           * Finish generating the next 6 quarter-keys.
@@ -340,34 +340,34 @@
           * On exit, xmm0 is r9:r8:r7:r6 and xmm1 is stuff:stuff:r11:r10
           * and those are written to the round key buffer.
           */
-         "1:                            \n"
-         "pshufd $0x55, %%xmm2, %%xmm2  \n" // X:X:X:X
-         "pxor %%xmm0, %%xmm2           \n" // X+r3:X+r2:X+r1:r4
-         "pslldq $4, %%xmm0             \n" // etc
-         "pxor %%xmm0, %%xmm2           \n"
-         "pslldq $4, %%xmm0             \n"
-         "pxor %%xmm0, %%xmm2           \n"
-         "pslldq $4, %%xmm0             \n"
-         "pxor %%xmm2, %%xmm0           \n" // update xmm0 = r9:r8:r7:r6
-         "movdqu %%xmm0, (%0)           \n"
-         "add $16, %0                   \n"
-         "pshufd $0xff, %%xmm0, %%xmm2  \n" // r9:r9:r9:r9
-         "pxor %%xmm1, %%xmm2           \n" // stuff:stuff:r9+r5:r10
-         "pslldq $4, %%xmm1             \n" // r2:r1:r0:0
-         "pxor %%xmm2, %%xmm1           \n" // update xmm1 = stuff:stuff:r11:r10
-         "movq %%xmm1, (%0)             \n"
-         "add $8, %0                    \n"
-         "ret                           \n"
+         "1:                            \n\t"
+         "pshufd $0x55, %%xmm2, %%xmm2  \n\t" // X:X:X:X
+         "pxor %%xmm0, %%xmm2           \n\t" // X+r3:X+r2:X+r1:r4
+         "pslldq $4, %%xmm0             \n\t" // etc
+         "pxor %%xmm0, %%xmm2           \n\t"
+         "pslldq $4, %%xmm0             \n\t"
+         "pxor %%xmm0, %%xmm2           \n\t"
+         "pslldq $4, %%xmm0             \n\t"
+         "pxor %%xmm2, %%xmm0           \n\t" // update xmm0 = r9:r8:r7:r6
+         "movdqu %%xmm0, (%0)           \n\t"
+         "add $16, %0                   \n\t"
+         "pshufd $0xff, %%xmm0, %%xmm2  \n\t" // r9:r9:r9:r9
+         "pxor %%xmm1, %%xmm2           \n\t" // stuff:stuff:r9+r5:r10
+         "pslldq $4, %%xmm1             \n\t" // r2:r1:r0:0
+         "pxor %%xmm2, %%xmm1           \n\t" // xmm1 = stuff:stuff:r11:r10
+         "movq %%xmm1, (%0)             \n\t"
+         "add $8, %0                    \n\t"
+         "ret                           \n\t"
 
-         "2:                            \n"
-         AESKEYGENA xmm1_xmm2 ",0x01    \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x02    \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x04    \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x08    \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x10    \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x20    \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x40    \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x80    \ncall 1b   \n"
+         "2:                            \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x01    \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x02    \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x04    \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x08    \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x10    \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x20    \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x40    \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x80    \n\tcall 1b \n\t"
 
          :
          : "r" (rk), "r" (key)
@@ -380,12 +380,12 @@
 static void aesni_setkey_enc_256( unsigned char *rk,
                                   const unsigned char *key )
 {
-    asm( "movdqu (%1), %%xmm0           \n"
-         "movdqu %%xmm0, (%0)           \n"
-         "add $16, %0                   \n"
-         "movdqu 16(%1), %%xmm1         \n"
-         "movdqu %%xmm1, (%0)           \n"
-         "jmp 2f                        \n" // skip auxiliary routine
+    asm( "movdqu (%1), %%xmm0           \n\t"
+         "movdqu %%xmm0, (%0)           \n\t"
+         "add $16, %0                   \n\t"
+         "movdqu 16(%1), %%xmm1         \n\t"
+         "movdqu %%xmm1, (%0)           \n\t"
+         "jmp 2f                        \n\t" // skip auxiliary routine
 
          /*
           * Finish generating the next two round keys.
@@ -396,45 +396,45 @@
           * On exit, xmm0 is r11:r10:r9:r8 and xmm1 is r15:r14:r13:r12
           * and those have been written to the output buffer.
           */
-         "1:                                \n"
-         "pshufd $0xff, %%xmm2, %%xmm2      \n"
-         "pxor %%xmm0, %%xmm2               \n"
-         "pslldq $4, %%xmm0                 \n"
-         "pxor %%xmm0, %%xmm2               \n"
-         "pslldq $4, %%xmm0                 \n"
-         "pxor %%xmm0, %%xmm2               \n"
-         "pslldq $4, %%xmm0                 \n"
-         "pxor %%xmm2, %%xmm0               \n"
-         "add $16, %0                       \n"
-         "movdqu %%xmm0, (%0)               \n"
+         "1:                                \n\t"
+         "pshufd $0xff, %%xmm2, %%xmm2      \n\t"
+         "pxor %%xmm0, %%xmm2               \n\t"
+         "pslldq $4, %%xmm0                 \n\t"
+         "pxor %%xmm0, %%xmm2               \n\t"
+         "pslldq $4, %%xmm0                 \n\t"
+         "pxor %%xmm0, %%xmm2               \n\t"
+         "pslldq $4, %%xmm0                 \n\t"
+         "pxor %%xmm2, %%xmm0               \n\t"
+         "add $16, %0                       \n\t"
+         "movdqu %%xmm0, (%0)               \n\t"
 
          /* Set xmm2 to stuff:Y:stuff:stuff with Y = subword( r11 )
           * and proceed to generate next round key from there */
-         AESKEYGENA xmm0_xmm2 ",0x00        \n"
-         "pshufd $0xaa, %%xmm2, %%xmm2      \n"
-         "pxor %%xmm1, %%xmm2               \n"
-         "pslldq $4, %%xmm1                 \n"
-         "pxor %%xmm1, %%xmm2               \n"
-         "pslldq $4, %%xmm1                 \n"
-         "pxor %%xmm1, %%xmm2               \n"
-         "pslldq $4, %%xmm1                 \n"
-         "pxor %%xmm2, %%xmm1               \n"
-         "add $16, %0                       \n"
-         "movdqu %%xmm1, (%0)               \n"
-         "ret                               \n"
+         AESKEYGENA xmm0_xmm2 ",0x00        \n\t"
+         "pshufd $0xaa, %%xmm2, %%xmm2      \n\t"
+         "pxor %%xmm1, %%xmm2               \n\t"
+         "pslldq $4, %%xmm1                 \n\t"
+         "pxor %%xmm1, %%xmm2               \n\t"
+         "pslldq $4, %%xmm1                 \n\t"
+         "pxor %%xmm1, %%xmm2               \n\t"
+         "pslldq $4, %%xmm1                 \n\t"
+         "pxor %%xmm2, %%xmm1               \n\t"
+         "add $16, %0                       \n\t"
+         "movdqu %%xmm1, (%0)               \n\t"
+         "ret                               \n\t"
 
          /*
           * Main "loop" - Generating one more key than necessary,
           * see definition of aes_context.buf
           */
-         "2:                                \n"
-         AESKEYGENA xmm1_xmm2 ",0x01        \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x02        \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x04        \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x08        \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x10        \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x20        \ncall 1b   \n"
-         AESKEYGENA xmm1_xmm2 ",0x40        \ncall 1b   \n"
+         "2:                                \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x01        \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x02        \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x04        \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x08        \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x10        \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x20        \n\tcall 1b \n\t"
+         AESKEYGENA xmm1_xmm2 ",0x40        \n\tcall 1b \n\t"
          :
          : "r" (rk), "r" (key)
          : "memory", "cc", "0" );
diff --git a/library/gcm.c b/library/gcm.c
index 4e40fbf..d4c68ae 100644
--- a/library/gcm.c
+++ b/library/gcm.c
@@ -266,6 +266,13 @@
     const unsigned char *p;
     size_t use_len, olen = 0;
 
+    /* IV and AD are limited to 2^64 bits, so 2^61 bytes */
+    if( ( (uint64_t) iv_len  ) >> 61 != 0 ||
+        ( (uint64_t) add_len ) >> 61 != 0 )
+    {
+        return( POLARSSL_ERR_GCM_BAD_INPUT );
+    }
+
     memset( ctx->y, 0x00, sizeof(ctx->y) );
     memset( ctx->buf, 0x00, sizeof(ctx->buf) );
 
@@ -342,6 +349,14 @@
     if( output > input && (size_t) ( output - input ) < length )
         return( POLARSSL_ERR_GCM_BAD_INPUT );
 
+    /* Total length is restricted to 2^39 - 256 bits, ie 2^36 - 2^5 bytes
+     * Also check for possible overflow */
+    if( ctx->len + length < ctx->len ||
+        (uint64_t) ctx->len + length > 0x03FFFFE0llu )
+    {
+        return( POLARSSL_ERR_GCM_BAD_INPUT );
+    }
+
     ctx->len += length;
 
     p = input;
@@ -387,7 +402,7 @@
     uint64_t orig_len = ctx->len * 8;
     uint64_t orig_add_len = ctx->add_len * 8;
 
-    if( tag_len > 16 )
+    if( tag_len > 16 || tag_len < 4 )
         return( POLARSSL_ERR_GCM_BAD_INPUT );
 
     if( tag_len != 0 )
diff --git a/library/padlock.c b/library/padlock.c
index d277ccf..5d06390 100644
--- a/library/padlock.c
+++ b/library/padlock.c
@@ -51,17 +51,17 @@
 
     if( flags == -1 )
     {
-        asm( "movl  %%ebx, %0           \n"     \
-             "movl  $0xC0000000, %%eax  \n"     \
-             "cpuid                     \n"     \
-             "cmpl  $0xC0000001, %%eax  \n"     \
-             "movl  $0, %%edx           \n"     \
-             "jb    unsupported         \n"     \
-             "movl  $0xC0000001, %%eax  \n"     \
-             "cpuid                     \n"     \
-             "unsupported:              \n"     \
-             "movl  %%edx, %1           \n"     \
-             "movl  %2, %%ebx           \n"
+        asm( "movl  %%ebx, %0           \n\t"
+             "movl  $0xC0000000, %%eax  \n\t"
+             "cpuid                     \n\t"
+             "cmpl  $0xC0000001, %%eax  \n\t"
+             "movl  $0, %%edx           \n\t"
+             "jb    unsupported         \n\t"
+             "movl  $0xC0000001, %%eax  \n\t"
+             "cpuid                     \n\t"
+             "unsupported:              \n\t"
+             "movl  %%edx, %1           \n\t"
+             "movl  %2, %%ebx           \n\t"
              : "=m" (ebx), "=m" (edx)
              :  "m" (ebx)
              : "eax", "ecx", "edx" );
@@ -93,15 +93,16 @@
      ctrl = blk + 4;
     *ctrl = 0x80 | ctx->nr | ( ( ctx->nr + ( mode^1 ) - 10 ) << 9 );
 
-    asm( "pushfl; popfl         \n"     \
-         "movl    %%ebx, %0     \n"     \
-         "movl    $1, %%ecx     \n"     \
-         "movl    %2, %%edx     \n"     \
-         "movl    %3, %%ebx     \n"     \
-         "movl    %4, %%esi     \n"     \
-         "movl    %4, %%edi     \n"     \
-         ".byte  0xf3,0x0f,0xa7,0xc8\n" \
-         "movl    %1, %%ebx     \n"
+    asm( "pushfl                        \n\t"
+         "popfl                         \n\t"
+         "movl    %%ebx, %0             \n\t"
+         "movl    $1, %%ecx             \n\t"
+         "movl    %2, %%edx             \n\t"
+         "movl    %3, %%ebx             \n\t"
+         "movl    %4, %%esi             \n\t"
+         "movl    %4, %%edi             \n\t"
+         ".byte  0xf3,0x0f,0xa7,0xc8    \n\t"
+         "movl    %1, %%ebx             \n\t"
          : "=m" (ebx)
          :  "m" (ebx), "m" (ctrl), "m" (rk), "m" (blk)
          : "ecx", "edx", "esi", "edi" );
@@ -141,16 +142,17 @@
 
     count = ( length + 15 ) >> 4;
 
-    asm( "pushfl; popfl         \n"     \
-         "movl    %%ebx, %0     \n"     \
-         "movl    %2, %%ecx     \n"     \
-         "movl    %3, %%edx     \n"     \
-         "movl    %4, %%ebx     \n"     \
-         "movl    %5, %%esi     \n"     \
-         "movl    %6, %%edi     \n"     \
-         "movl    %7, %%eax     \n"     \
-         ".byte  0xf3,0x0f,0xa7,0xd0\n" \
-         "movl    %1, %%ebx     \n"
+    asm( "pushfl                        \n\t"
+         "popfl                         \n\t"
+         "movl    %%ebx, %0             \n\t"
+         "movl    %2, %%ecx             \n\t"
+         "movl    %3, %%edx             \n\t"
+         "movl    %4, %%ebx             \n\t"
+         "movl    %5, %%esi             \n\t"
+         "movl    %6, %%edi             \n\t"
+         "movl    %7, %%eax             \n\t"
+         ".byte  0xf3,0x0f,0xa7,0xd0    \n\t"
+         "movl    %1, %%ebx             \n\t"
          : "=m" (ebx)
          :  "m" (ebx), "m" (count), "m" (ctrl),
             "m"  (rk), "m" (input), "m" (output), "m" (iw)
diff --git a/library/ssl_ciphersuites.c b/library/ssl_ciphersuites.c
index a74e324..7463353 100644
--- a/library/ssl_ciphersuites.c
+++ b/library/ssl_ciphersuites.c
@@ -51,18 +51,18 @@
  *    Forward-secure non-PSK > forward-secure PSK > other non-PSK > other PSK
  * 2. By key length and cipher:
  *    AES-256 > Camellia-256 > AES-128 > Camellia-128 > 3DES
- * 3. By cipher mode when relevant CCM > GCM > CBC > CCM_8
+ * 3. By cipher mode when relevant GCM > CCM > CBC > CCM_8
  * 4. By hash function used when relevant
  * 5. By key exchange/auth again: EC > non-EC
  */
 static const int ciphersuite_preference[] =
 {
     /* All AES-256 ephemeral suites */
-    TLS_ECDHE_ECDSA_WITH_AES_256_CCM,
-    TLS_DHE_RSA_WITH_AES_256_CCM,
     TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,
     TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,
     TLS_DHE_RSA_WITH_AES_256_GCM_SHA384,
+    TLS_ECDHE_ECDSA_WITH_AES_256_CCM,
+    TLS_DHE_RSA_WITH_AES_256_CCM,
     TLS_ECDHE_ECDSA_WITH_AES_256_CBC_SHA384,
     TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384,
     TLS_DHE_RSA_WITH_AES_256_CBC_SHA256,
@@ -82,11 +82,11 @@
     TLS_DHE_RSA_WITH_CAMELLIA_256_CBC_SHA,
 
     /* All AES-128 ephemeral suites */
-    TLS_ECDHE_ECDSA_WITH_AES_128_CCM,
-    TLS_DHE_RSA_WITH_AES_128_CCM,
     TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,
     TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,
     TLS_DHE_RSA_WITH_AES_128_GCM_SHA256,
+    TLS_ECDHE_ECDSA_WITH_AES_128_CCM,
+    TLS_DHE_RSA_WITH_AES_128_CCM,
     TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,
     TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256,
     TLS_DHE_RSA_WITH_AES_128_CBC_SHA256,
@@ -111,8 +111,8 @@
     TLS_DHE_RSA_WITH_3DES_EDE_CBC_SHA,
 
     /* The PSK ephemeral suites */
-    TLS_DHE_PSK_WITH_AES_256_CCM,
     TLS_DHE_PSK_WITH_AES_256_GCM_SHA384,
+    TLS_DHE_PSK_WITH_AES_256_CCM,
     TLS_ECDHE_PSK_WITH_AES_256_CBC_SHA384,
     TLS_DHE_PSK_WITH_AES_256_CBC_SHA384,
     TLS_ECDHE_PSK_WITH_AES_256_CBC_SHA,
@@ -122,8 +122,8 @@
     TLS_DHE_PSK_WITH_CAMELLIA_256_CBC_SHA384,
     TLS_DHE_PSK_WITH_AES_256_CCM_8,
 
-    TLS_DHE_PSK_WITH_AES_128_CCM,
     TLS_DHE_PSK_WITH_AES_128_GCM_SHA256,
+    TLS_DHE_PSK_WITH_AES_128_CCM,
     TLS_ECDHE_PSK_WITH_AES_128_CBC_SHA256,
     TLS_DHE_PSK_WITH_AES_128_CBC_SHA256,
     TLS_ECDHE_PSK_WITH_AES_128_CBC_SHA,
@@ -137,8 +137,8 @@
     TLS_DHE_PSK_WITH_3DES_EDE_CBC_SHA,
 
     /* All AES-256 suites */
-    TLS_RSA_WITH_AES_256_CCM,
     TLS_RSA_WITH_AES_256_GCM_SHA384,
+    TLS_RSA_WITH_AES_256_CCM,
     TLS_RSA_WITH_AES_256_CBC_SHA256,
     TLS_RSA_WITH_AES_256_CBC_SHA,
     TLS_ECDH_RSA_WITH_AES_256_GCM_SHA384,
@@ -159,8 +159,8 @@
     TLS_ECDH_ECDSA_WITH_CAMELLIA_256_CBC_SHA384,
 
     /* All AES-128 suites */
-    TLS_RSA_WITH_AES_128_CCM,
     TLS_RSA_WITH_AES_128_GCM_SHA256,
+    TLS_RSA_WITH_AES_128_CCM,
     TLS_RSA_WITH_AES_128_CBC_SHA256,
     TLS_RSA_WITH_AES_128_CBC_SHA,
     TLS_ECDH_RSA_WITH_AES_128_GCM_SHA256,
@@ -201,16 +201,16 @@
     TLS_RSA_PSK_WITH_3DES_EDE_CBC_SHA,
 
     /* The PSK suites */
-    TLS_PSK_WITH_AES_256_CCM,
     TLS_PSK_WITH_AES_256_GCM_SHA384,
+    TLS_PSK_WITH_AES_256_CCM,
     TLS_PSK_WITH_AES_256_CBC_SHA384,
     TLS_PSK_WITH_AES_256_CBC_SHA,
     TLS_PSK_WITH_CAMELLIA_256_GCM_SHA384,
     TLS_PSK_WITH_CAMELLIA_256_CBC_SHA384,
     TLS_PSK_WITH_AES_256_CCM_8,
 
-    TLS_PSK_WITH_AES_128_CCM,
     TLS_PSK_WITH_AES_128_GCM_SHA256,
+    TLS_PSK_WITH_AES_128_CCM,
     TLS_PSK_WITH_AES_128_CBC_SHA256,
     TLS_PSK_WITH_AES_128_CBC_SHA,
     TLS_PSK_WITH_CAMELLIA_128_GCM_SHA256,
diff --git a/library/ssl_cli.c b/library/ssl_cli.c
index 9903954..035cf39 100644
--- a/library/ssl_cli.c
+++ b/library/ssl_cli.c
@@ -803,7 +803,7 @@
         return( POLARSSL_ERR_SSL_BAD_HS_SERVER_HELLO );
     }
 
-    p = buf + 2;
+    p = buf + 1;
     while( list_size > 0 )
     {
         if( p[0] == POLARSSL_ECP_PF_UNCOMPRESSED ||
@@ -818,7 +818,8 @@
         p++;
     }
 
-    return( 0 );
+    SSL_DEBUG_MSG( 1, ( "no point format in common" ) );
+    return( POLARSSL_ERR_SSL_BAD_HS_SERVER_HELLO );
 }
 #endif /* POLARSSL_ECDH_C || POLARSSL_ECDSA_C */
 
@@ -2056,7 +2057,7 @@
         SSL_DEBUG_MPI( 3, "DHM: X ", &ssl->handshake->dhm_ctx.X  );
         SSL_DEBUG_MPI( 3, "DHM: GX", &ssl->handshake->dhm_ctx.GX );
 
-        ssl->handshake->pmslen = ssl->handshake->dhm_ctx.len;
+        ssl->handshake->pmslen = POLARSSL_PREMASTER_SIZE;
 
         if( ( ret = dhm_calc_secret( &ssl->handshake->dhm_ctx,
                                       ssl->handshake->premaster,
diff --git a/library/ssl_srv.c b/library/ssl_srv.c
index 7a5f462..a8e4f41 100644
--- a/library/ssl_srv.c
+++ b/library/ssl_srv.c
@@ -2743,7 +2743,7 @@
             return( POLARSSL_ERR_SSL_BAD_HS_CLIENT_KEY_EXCHANGE );
         }
 
-        ssl->handshake->pmslen = ssl->handshake->dhm_ctx.len;
+        ssl->handshake->pmslen = POLARSSL_PREMASTER_SIZE;
 
         if( ( ret = dhm_calc_secret( &ssl->handshake->dhm_ctx,
                                       ssl->handshake->premaster,
diff --git a/library/ssl_tls.c b/library/ssl_tls.c
index ce6730d..a1428dc 100644
--- a/library/ssl_tls.c
+++ b/library/ssl_tls.c
@@ -511,58 +511,81 @@
      * Determine the appropriate key, IV and MAC length.
      */
 
+    transform->keylen = cipher_info->key_length / 8;
+
     if( cipher_info->mode == POLARSSL_MODE_GCM ||
         cipher_info->mode == POLARSSL_MODE_CCM )
     {
-        transform->keylen = cipher_info->key_length;
-        transform->keylen /= 8;
-        transform->minlen = 1;
+        transform->maclen = 0;
+
         transform->ivlen = 12;
         transform->fixed_ivlen = 4;
-        transform->maclen = 0;
+
+        /* Minimum length is expicit IV + tag */
+        transform->minlen = transform->ivlen - transform->fixed_ivlen
+                            + ( transform->ciphersuite_info->flags &
+                                POLARSSL_CIPHERSUITE_SHORT_TAG ? 8 : 16 );
     }
     else
     {
-        if( md_info->type != POLARSSL_MD_NONE )
+        int ret;
+
+        /* Initialize HMAC contexts */
+        if( ( ret = md_init_ctx( &transform->md_ctx_enc, md_info ) ) != 0 ||
+            ( ret = md_init_ctx( &transform->md_ctx_dec, md_info ) ) != 0 )
         {
-            int ret;
-
-            if( ( ret = md_init_ctx( &transform->md_ctx_enc, md_info ) ) != 0 )
-            {
-                SSL_DEBUG_RET( 1, "md_init_ctx", ret );
-                return( ret );
-            }
-
-            if( ( ret = md_init_ctx( &transform->md_ctx_dec, md_info ) ) != 0 )
-            {
-                SSL_DEBUG_RET( 1, "md_init_ctx", ret );
-                return( ret );
-            }
-
-            transform->maclen = md_get_size( md_info );
-
-#if defined(POLARSSL_SSL_TRUNCATED_HMAC)
-            /*
-             * If HMAC is to be truncated, we shall keep the leftmost bytes,
-             * (rfc 6066 page 13 or rfc 2104 section 4),
-             * so we only need to adjust the length here.
-             */
-            if( session->trunc_hmac == SSL_TRUNC_HMAC_ENABLED )
-                transform->maclen = SSL_TRUNCATED_HMAC_LEN;
-#endif /* POLARSSL_SSL_TRUNCATED_HMAC */
+            SSL_DEBUG_RET( 1, "md_init_ctx", ret );
+            return( ret );
         }
 
-        transform->keylen = cipher_info->key_length;
-        transform->keylen /= 8;
+        /* Get MAC length */
+        transform->maclen = md_get_size( md_info );
+
+#if defined(POLARSSL_SSL_TRUNCATED_HMAC)
+        /*
+         * If HMAC is to be truncated, we shall keep the leftmost bytes,
+         * (rfc 6066 page 13 or rfc 2104 section 4),
+         * so we only need to adjust the length here.
+         */
+        if( session->trunc_hmac == SSL_TRUNC_HMAC_ENABLED )
+            transform->maclen = SSL_TRUNCATED_HMAC_LEN;
+#endif /* POLARSSL_SSL_TRUNCATED_HMAC */
+
+        /* IV length */
         transform->ivlen = cipher_info->iv_size;
 
-        transform->minlen = transform->keylen;
-        if( transform->minlen < transform->maclen )
+        /* Minimum length */
+        if( cipher_info->mode == POLARSSL_MODE_STREAM )
+            transform->minlen = transform->maclen;
+        else
         {
-            if( cipher_info->mode == POLARSSL_MODE_STREAM )
-                transform->minlen = transform->maclen;
+            /*
+             * GenericBlockCipher:
+             * first multiple of blocklen greater than maclen
+             * + IV except for SSL3 and TLS 1.0
+             */
+            transform->minlen = transform->maclen
+                                + cipher_info->block_size
+                                - transform->maclen % cipher_info->block_size;
+
+#if defined(POLARSSL_SSL_PROTO_SSL3) || defined(POLARSSL_SSL_PROTO_TLS1)
+            if( ssl->minor_ver == SSL_MINOR_VERSION_0 ||
+                ssl->minor_ver == SSL_MINOR_VERSION_1 )
+                ; /* No need to adjust minlen */
             else
-                transform->minlen += transform->keylen;
+#endif
+#if defined(POLARSSL_SSL_PROTO_TLS1_1) || defined(POLARSSL_SSL_PROTO_TLS1_2)
+            if( ssl->minor_ver == SSL_MINOR_VERSION_2 ||
+                ssl->minor_ver == SSL_MINOR_VERSION_3 )
+            {
+                transform->minlen += transform->ivlen;
+            }
+            else
+#endif
+            {
+                SSL_DEBUG_MSG( 1, ( "should never happen" ) );
+                return( POLARSSL_ERR_SSL_INTERNAL_ERROR );
+            }
         }
     }
 
@@ -885,19 +908,18 @@
     if( key_ex == POLARSSL_KEY_EXCHANGE_DHE_PSK )
     {
         int ret;
-        size_t len = ssl->handshake->dhm_ctx.len;
+        size_t len = end - ( p + 2 );
 
-        if( end - p < 2 + (int) len )
-            return( POLARSSL_ERR_SSL_BAD_INPUT_DATA );
-
-        *(p++) = (unsigned char)( len >> 8 );
-        *(p++) = (unsigned char)( len );
+        /* Write length only when we know the actual value */
         if( ( ret = dhm_calc_secret( &ssl->handshake->dhm_ctx,
-                                      p, &len, ssl->f_rng, ssl->p_rng ) ) != 0 )
+                                      p + 2, &len,
+                                      ssl->f_rng, ssl->p_rng ) ) != 0 )
         {
             SSL_DEBUG_RET( 1, "dhm_calc_secret", ret );
             return( ret );
         }
+        *(p++) = (unsigned char)( len >> 8 );
+        *(p++) = (unsigned char)( len );
         p += len;
 
         SSL_DEBUG_MPI( 3, "DHM: K ", &ssl->handshake->dhm_ctx.K  );
@@ -1327,10 +1349,18 @@
         unsigned char add_data[13];
         unsigned char taglen = ssl->transform_in->ciphersuite_info->flags &
                                POLARSSL_CIPHERSUITE_SHORT_TAG ? 8 : 16;
+        unsigned char explicit_iv_len =  ssl->transform_in->ivlen -
+                                         ssl->transform_in->fixed_ivlen;
 
-        dec_msglen = ssl->in_msglen - ( ssl->transform_in->ivlen -
-                                        ssl->transform_in->fixed_ivlen );
-        dec_msglen -= taglen;
+        if( ssl->in_msglen < explicit_iv_len + taglen )
+        {
+            SSL_DEBUG_MSG( 1, ( "msglen (%d) < explicit_iv_len (%d) "
+                                "+ taglen (%d)", ssl->in_msglen,
+                                explicit_iv_len, taglen ) );
+            return( POLARSSL_ERR_SSL_INVALID_MAC );
+        }
+        dec_msglen = ssl->in_msglen - explicit_iv_len - taglen;
+
         dec_msg = ssl->in_msg;
         dec_msg_result = ssl->in_msg;
         ssl->in_msglen = dec_msglen;
@@ -1943,9 +1973,6 @@
 
     SSL_DEBUG_MSG( 2, ( "=> read record" ) );
 
-    SSL_DEBUG_BUF( 4, "input record from network",
-                   ssl->in_hdr, 5 + ssl->in_msglen );
-
     if( ssl->in_hslen != 0 &&
         ssl->in_hslen < ssl->in_msglen )
     {
diff --git a/library/x509_crt.c b/library/x509_crt.c
index c5f7f70..03cdda8 100644
--- a/library/x509_crt.c
+++ b/library/x509_crt.c
@@ -1587,22 +1587,48 @@
 /*
  * Check if 'parent' is a suitable parent (signing CA) for 'child'.
  * Return 0 if yes, -1 if not.
+ *
+ * top means parent is a locally-trusted certificate
+ * bottom means child is the end entity cert
  */
 static int x509_crt_check_parent( const x509_crt *child,
-                                  const x509_crt *parent )
+                                  const x509_crt *parent,
+                                  int top, int bottom )
 {
-    if( parent->version == 0 ||
-        parent->ca_istrue == 0 ||
-        child->issuer_raw.len != parent->subject_raw.len ||
+    int need_ca_bit;
+
+    /* Parent must be the issuer */
+    if( child->issuer_raw.len != parent->subject_raw.len ||
         memcmp( child->issuer_raw.p, parent->subject_raw.p,
                 child->issuer_raw.len ) != 0 )
     {
         return( -1 );
     }
 
-#if defined(POLARSSL_X509_CHECK_KEY_USAGE)
-    if( x509_crt_check_key_usage( parent, KU_KEY_CERT_SIGN ) != 0 )
+    /* Parent must have the basicConstraints CA bit set as a general rule */
+    need_ca_bit = 1;
+
+    /* Exception: v1/v2 certificates that are locally trusted. */
+    if( top && parent->version < 3 )
+        need_ca_bit = 0;
+
+    /* Exception: self-signed end-entity certs that are locally trusted. */
+    if( top && bottom &&
+        child->raw.len == parent->raw.len &&
+        memcmp( child->raw.p, parent->raw.p, child->raw.len ) == 0 )
+    {
+        need_ca_bit = 0;
+    }
+
+    if( need_ca_bit && ! parent->ca_istrue )
         return( -1 );
+
+#if defined(POLARSSL_X509_CHECK_KEY_USAGE)
+    if( need_ca_bit &&
+        x509_crt_check_key_usage( parent, KU_KEY_CERT_SIGN ) != 0 )
+    {
+        return( -1 );
+    }
 #endif
 
     return( 0 );
@@ -1643,7 +1669,7 @@
 
     for( /* trust_ca */ ; trust_ca != NULL; trust_ca = trust_ca->next )
     {
-        if( x509_crt_check_parent( child, trust_ca ) != 0 )
+        if( x509_crt_check_parent( child, trust_ca, 1, path_cnt == 0 ) != 0 )
             continue;
 
         /*
@@ -1770,7 +1796,8 @@
          grandparent != NULL;
          grandparent = grandparent->next )
     {
-        if( x509_crt_check_parent( parent, grandparent ) == 0 )
+        if( x509_crt_check_parent( parent, grandparent,
+                                   0, path_cnt == 0 ) == 0 )
             break;
     }
 
@@ -1872,7 +1899,7 @@
     /* Look for a parent upwards the chain */
     for( parent = crt->next; parent != NULL; parent = parent->next )
     {
-        if( x509_crt_check_parent( crt, parent ) == 0 )
+        if( x509_crt_check_parent( crt, parent, 0, pathlen == 0 ) == 0 )
             break;
     }
 
diff --git a/programs/ssl/ssl_client2.c b/programs/ssl/ssl_client2.c
index 2b1c03a..3af54f9 100644
--- a/programs/ssl/ssl_client2.c
+++ b/programs/ssl/ssl_client2.c
@@ -72,7 +72,7 @@
 #define DFL_SERVER_ADDR         NULL
 #define DFL_SERVER_PORT         4433
 #define DFL_REQUEST_PAGE        "/"
-#define DFL_REQUEST_SIZE        0
+#define DFL_REQUEST_SIZE        -1
 #define DFL_DEBUG_LEVEL         0
 #define DFL_NBIO                0
 #define DFL_CA_FILE             ""
@@ -288,8 +288,8 @@
     "    server_addr=%%s      default: given by name\n"     \
     "    server_port=%%d      default: 4433\n"              \
     "    request_page=%%s     default: \".\"\n"             \
-    "    request_size=%%d     default: 0 (no extra padding)\n" \
-    "                        (minimum: 16, max: " ")\n" \
+    "    request_size=%%d     default: about 34 (basic request)\n" \
+    "                        (minimum: 0, max: 16384)\n" \
     "    debug_level=%%d      default: 0 (disabled)\n"      \
     "    nbio=%%d             default: 0 (blocking I/O)\n"  \
     "                        options: 1 (non-blocking), 2 (added delays)\n" \
@@ -1035,9 +1035,9 @@
         len = snprintf( (char *) buf, sizeof(buf) - 1, GET_REQUEST,
                         opt.request_page );
 
-        // Add padding to GET request to reach opt.request_size in length
-        //
-        if( len + tail_len < (size_t) opt.request_size )
+        /* Add padding to GET request to reach opt.request_size in length */
+        if( opt.request_size != DFL_REQUEST_SIZE &&
+            len + tail_len < (size_t) opt.request_size )
         {
             memset( buf + len, 'A', opt.request_size - len - tail_len );
             len += opt.request_size - len - tail_len;
@@ -1047,6 +1047,17 @@
         len += tail_len;
     }
 
+    /* Truncate if request size is smaller than the "natural" size */
+    if( opt.request_size != DFL_REQUEST_SIZE &&
+        len > opt.request_size )
+    {
+        len = opt.request_size;
+
+        /* Still end with \r\n unless that's really not possible */
+        if( len >= 2 ) buf[len - 2] = '\r';
+        if( len >= 1 ) buf[len - 1] = '\n';
+    }
+
     for( written = 0, frags = 0; written < len; written += ret, frags++ )
     {
         while( ( ret = ssl_write( &ssl, buf + written, len - written ) ) <= 0 )
diff --git a/programs/ssl/ssl_server2.c b/programs/ssl/ssl_server2.c
index 3b8f234..d5f01bc 100644
--- a/programs/ssl/ssl_server2.c
+++ b/programs/ssl/ssl_server2.c
@@ -1507,7 +1507,8 @@
 
             larger_buf[ori_len + extra_len] = '\0';
             printf( " %u bytes read (%u + %u)\n\n%s\n",
-                    ori_len + extra_len, ori_len, extra_len, (char *) buf );
+                    ori_len + extra_len, ori_len, extra_len,
+                    (char *) larger_buf );
 
             polarssl_free( larger_buf );
         }
diff --git a/tests/data_files/server1-v1.crt b/tests/data_files/server1-v1.crt
new file mode 100644
index 0000000..47f1fff
--- /dev/null
+++ b/tests/data_files/server1-v1.crt
@@ -0,0 +1,19 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
diff --git a/tests/data_files/server2-v1-chain.crt b/tests/data_files/server2-v1-chain.crt
new file mode 100644
index 0000000..84bb6b2
--- /dev/null
+++ b/tests/data_files/server2-v1-chain.crt
@@ -0,0 +1,38 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
diff --git a/tests/data_files/server2-v1.crt b/tests/data_files/server2-v1.crt
new file mode 100644
index 0000000..7ef7968
--- /dev/null
+++ b/tests/data_files/server2-v1.crt
@@ -0,0 +1,19 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
diff --git a/tests/data_files/server5-selfsigned.crt b/tests/data_files/server5-selfsigned.crt
new file mode 100644
index 0000000..cb55647
--- /dev/null
+++ b/tests/data_files/server5-selfsigned.crt
@@ -0,0 +1,12 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
diff --git a/tests/data_files/server6-ss-child.crt b/tests/data_files/server6-ss-child.crt
new file mode 100644
index 0000000..3c6fd4d
--- /dev/null
+++ b/tests/data_files/server6-ss-child.crt
@@ -0,0 +1,13 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
diff --git a/tests/data_files/test-ca-v1.crt b/tests/data_files/test-ca-v1.crt
new file mode 100644
index 0000000..e5a3b1c
--- /dev/null
+++ b/tests/data_files/test-ca-v1.crt
@@ -0,0 +1,19 @@
+-----BEGIN CERTIFICATE-----
+MIIDIzCCAgsCDFOito4FQA5VXJOV5TANBgkqhkiG9w0BAQsFADBQMRwwGgYDVQQD
+ExNQb2xhclNTTCBUZXN0IENBIHYxMRAwDgYDVQQLEwd0ZXN0aW5nMREwDwYDVQQK
+EwhQb2xhclNTTDELMAkGA1UEBhMCTkwwIhgPMjAxNDA2MTkxMDA4MTRaGA8yMDI0
+MDYxODEwMDgxNFowUDEcMBoGA1UEAxMTUG9sYXJTU0wgVGVzdCBDQSB2MTEQMA4G
+A1UECxMHdGVzdGluZzERMA8GA1UEChMIUG9sYXJTU0wxCzAJBgNVBAYTAk5MMIIB
+IjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwN83/Be74JadP4beljJ9RKUW
+oM0h8ZnU7OrLfBhYCJSl7JvFi98aHpk4mYcee8CNOd84XXB4B9Oe2ZPouXJRxc6j
+MFKp8udAcBTLRKJyC8LlQPk+5aYOs/nsSmPAuCkAdJxXO6ilBJBx8b2D2T/WpeI8
+Ko/vJ2DDxp/LuuxgfbfmhDK+T/tYJiIDW9S01fv145YucMDkLr38Lu7iQVXANC59
+JHJpy0exFECDfWf0hvYxq/F5pLK1LhL5hBfwYm8nPhNYsVQNIZpzN6Ewz2+S3Pbp
+/KzbLijRfgJLI6AV8jhlZAnqDG6OGxegccizm8mr6cPyz4eWj4ACMp6ZWG+i1QID
+AQABMA0GCSqGSIb3DQEBCwUAA4IBAQBoXC5AlXI5azyOPvmNse2qHhO7BrXOEjH+
+9g5P/VsrVADhsUGv6x0A2oLoWXtOjGDIWWH53BWHkCUCu4T5D5C6+I47rXWl4pAr
+J+h+tQVZo6J0AJxfPse/NnrjsboUSWhunmo/iTrU6S4KJBguIKP6T1DZoD/8EYgU
+x+fXDmvRO+MTesWDiY+p+FHEzsu3b9EBtG9dUiR/zzXi/ktFCfrgstKGSuW6+j7m
+lcduTxsogi6Uc3tWKtn6qpSGR0uBoCz6emFO7Smmy/tIyVA88lH0+3UnxOvu4TAK
+uvjYkOcZqhprDiMfhxBB7pxbfiviEANTbgSfCtZewSNz2RUJ9ocy
+-----END CERTIFICATE-----
diff --git a/tests/ssl-opt.sh b/tests/ssl-opt.sh
index f43f1eb..102a5b5 100755
--- a/tests/ssl-opt.sh
+++ b/tests/ssl-opt.sh
@@ -176,7 +176,7 @@
         # psk is useful when server only has bad certs
         $P_CLI request_page=SERVERQUIT tickets=0 auth_mode=none psk=abc123 \
             crt_file=data_files/cli2.crt key_file=data_files/cli2.key \
-            >/dev/null
+            >/dev/null 2>&1
 
         wait $SRV_PID
         kill $WATCHDOG_PID
@@ -1422,6 +1422,244 @@
             0 \
             -s "Read from client: 500 bytes read (.*+.*)"
 
+# Tests for small packets
+
+run_test    "Small packet SSLv3 BlockCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=ssl3 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet SSLv3 StreamCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=ssl3 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.0 BlockCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.0 BlockCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.0 StreamCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.1 BlockCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_1 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.1 StreamCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_1 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.1 BlockCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_1 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.1 StreamCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_1 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.2 BlockCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.2 BlockCipher larger MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_2 force_ciphersuite=TLS-ECDHE-RSA-WITH-AES-256-CBC-SHA384" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.2 BlockCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.2 StreamCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.2 StreamCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.2 AEAD" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CCM" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+run_test    "Small packet TLS 1.2 AEAD shorter tag" \
+            "$P_SRV" \
+            "$P_CLI request_size=1 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CCM-8" \
+            0 \
+            -s "Read from client: 1 bytes read"
+
+# Test for large packets
+
+run_test    "Large packet SSLv3 BlockCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=ssl3 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet SSLv3 StreamCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=ssl3 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.0 BlockCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.0 BlockCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.0 StreamCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.1 BlockCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_1 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.1 StreamCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_1 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.1 BlockCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_1 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.1 StreamCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_1 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.2 BlockCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.2 BlockCipher larger MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_2 force_ciphersuite=TLS-ECDHE-RSA-WITH-AES-256-CBC-SHA384" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.2 BlockCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CBC-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.2 StreamCipher" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.2 StreamCipher truncated MAC" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-RC4-128-SHA \
+             trunc_hmac=1" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.2 AEAD" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CCM" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
+run_test    "Large packet TLS 1.2 AEAD shorter tag" \
+            "$P_SRV" \
+            "$P_CLI request_size=16384 force_version=tls1_2 \
+             force_ciphersuite=TLS-RSA-WITH-AES-256-CCM-8" \
+            0 \
+            -s "Read from client: 16384 bytes read"
+
 # Final report
 
 echo "------------------------------------------------------------------------"
diff --git a/tests/suites/test_suite_x509parse.data b/tests/suites/test_suite_x509parse.data
index 54ef202..a22741e 100644
--- a/tests/suites/test_suite_x509parse.data
+++ b/tests/suites/test_suite_x509parse.data
@@ -622,6 +622,26 @@
 depends_on:POLARSSL_PEM_PARSE_C:POLARSSL_X509_RSASSA_PSS_SUPPORT:POLARSSL_SHA256_C
 x509_verify:"data_files/server9-bad-mgfhash.crt":"data_files/test-ca.crt":"data_files/crl.pem":"NULL":POLARSSL_ERR_X509_CERT_VERIFY_FAILED:BADCERT_NOT_TRUSTED:"NULL"
 
+X509 Certificate verification #70 (v1 trusted CA)
+depends_on:POLARSSL_PEM_PARSE_C:POLARSSL_RSA_C:POLARSSL_PKCS1_V15:POLARSSL_SHA256_C
+x509_verify:"data_files/server1-v1.crt":"data_files/test-ca-v1.crt":"data_files/crl.pem":"NULL":0:0:"NULL"
+
+X509 Certificate verification #71 (v1 trusted CA, other)
+depends_on:POLARSSL_PEM_PARSE_C:POLARSSL_RSA_C:POLARSSL_PKCS1_V15:POLARSSL_SHA256_C
+x509_verify:"data_files/server2-v1.crt":"data_files/server1-v1.crt":"data_files/crl.pem":"NULL":0:0:"NULL"
+
+X509 Certificate verification #72 (v1 chain)
+depends_on:POLARSSL_PEM_PARSE_C:POLARSSL_RSA_C:POLARSSL_PKCS1_V15:POLARSSL_SHA256_C
+x509_verify:"data_files/server2-v1-chain.crt":"data_files/test-ca-v1.crt":"data_files/crl.pem":"NULL":POLARSSL_ERR_X509_CERT_VERIFY_FAILED:BADCERT_NOT_TRUSTED:"NULL"
+
+X509 Certificate verification #73 (selfsigned trusted without CA bit)
+depends_on:POLARSSL_PEM_PARSE_C:POLARSSL_ECDSA_C:POLARSSL_SHA256_C
+x509_verify:"data_files/server5-selfsigned.crt":"data_files/server5-selfsigned.crt":"data_files/crl.pem":"NULL":0:0:"NULL"
+
+X509 Certificate verification #74 (signed by selfsigned trusted without CA bit)
+depends_on:POLARSSL_PEM_PARSE_C:POLARSSL_ECDSA_C:POLARSSL_SHA256_C
+x509_verify:"data_files/server6-ss-child.crt":"data_files/server5-selfsigned.crt":"data_files/crl.pem":"NULL":POLARSSL_ERR_X509_CERT_VERIFY_FAILED:BADCERT_NOT_TRUSTED:"NULL"
+
 X509 Parse Selftest
 depends_on:POLARSSL_SHA1_C:POLARSSL_PEM_PARSE_C:POLARSSL_CERTS_C
 x509_selftest: