[Tarantool-patches] [PATCH v2 2/2] base64: Improve decoder performance

[Sergey Nikiforov]

Unnecessary checks were removed from internal loops.
Benchmark shows that performance is now ~1.15 times higher
(release build, Intel Core I7-9700K, only one thread).
---

Branch: https://github.com/tarantool/tarantool/tree/void234/gh-3069-fix-base64-memory-overrun-v2

 third_party/base64.c | 36 +++++++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/third_party/base64.c b/third_party/base64.c
index 3350a98ff..f4fbbf477 100644
--- a/third_party/base64.c
+++ b/third_party/base64.c
@@ -257,7 +257,7 @@ base64_decode_block(const char *in_base64, int in_len,
 		{
 	case step_a:
 			do {
-				if (in_pos == in_end || out_pos >= out_end)
+				if (in_pos >= in_end)
 				{
 					state->step = step_a;
 					state->result = curr_byte;
@@ -268,7 +268,7 @@ base64_decode_block(const char *in_base64, int in_len,
 			curr_byte = (fragment & 0x03f) << 2;
 	case step_b:
 			do {
-				if (in_pos == in_end || out_pos >= out_end)
+				if (in_pos >= in_end)
 				{
 					state->step = step_b;
 					state->result = curr_byte;
@@ -277,13 +277,17 @@ base64_decode_block(const char *in_base64, int in_len,
 				fragment = base64_decode_value(*in_pos++);
 			} while (fragment < 0);
 			curr_byte |= (fragment & 0x030) >> 4;
-			*out_pos++ = curr_byte;
+			*out_pos = curr_byte;
 			curr_byte = (fragment & 0x00f) << 4;
-			if (out_pos < out_end)
-				*out_pos = curr_byte;
+			if (++out_pos >= out_end)
+			{
+				state->step = step_c;
+				state->result = curr_byte;
+				return out_pos - out_bin;
+			}
 	case step_c:
 			do {
-				if (in_pos == in_end || out_pos >= out_end)
+				if (in_pos >= in_end)
 				{
 					state->step = step_c;
 					state->result = curr_byte;
@@ -292,13 +296,17 @@ base64_decode_block(const char *in_base64, int in_len,
 				fragment = base64_decode_value(*in_pos++);
 			} while (fragment < 0);
 			curr_byte |= (fragment & 0x03c) >> 2;
-			*out_pos++ = curr_byte;
+			*out_pos = curr_byte;
 			curr_byte = (fragment & 0x003) << 6;
-			if (out_pos < out_end)
-				*out_pos = curr_byte;
+			if (++out_pos >= out_end)
+			{
+				state->step = step_d;
+				state->result = curr_byte;
+				return out_pos - out_bin;
+			}
 	case step_d:
 			do {
-				if (in_pos == in_end || out_pos >= out_end)
+				if (in_pos >= in_end)
 				{
 					state->step = step_d;
 					state->result = curr_byte;
@@ -307,7 +315,13 @@ base64_decode_block(const char *in_base64, int in_len,
 				fragment = base64_decode_value(*in_pos++);
 			} while (fragment < 0);
 			curr_byte |= (fragment & 0x03f);
-			*out_pos++ = curr_byte;
+			*out_pos = curr_byte;
+			if (++out_pos >= out_end)
+			{
+				state->step = step_a;
+				state->result = curr_byte;
+				return out_pos - out_bin;
+			}
 		}
 	}
 	/* control should not reach here */
-- 
2.25.1