Merge branch 'master' of git://www.denx.de/git/u-boot

6 files changed, 394 insertions, 65 deletions

diff --git a/lib_generic/Makefile b/lib_generic/Makefile
index dca3a6c..4f6ce73 100644
--- a/lib_generic/Makefile
+++ b/lib_generic/Makefile
@@ -38,6 +38,7 @@ COBJS-y += lmb.o
 COBJS-y += ldiv.o
 COBJS-$(CONFIG_MD5) += md5.o
 COBJS-y += sha1.o
+COBJS-$(CONFIG_SHA256) += sha256.o
 COBJS-y += string.o
 COBJS-y += vsprintf.o
 COBJS-y += zlib.o
diff --git a/lib_generic/display_options.c b/lib_generic/display_options.c
index 5ddd94f..2dc2567 100644
--- a/lib_generic/display_options.c
+++ b/lib_generic/display_options.c
@@ -39,27 +39,35 @@ int display_options (void)
 }
 
 /*
- * print sizes as "xxx kB", "xxx.y kB", "xxx MB" or "xxx.y MB" as needed;
- * allow for optional trailing string (like "\n")
+ * print sizes as "xxx kB", "xxx.y kB", "xxx MB", "xxx.y MB",
+ * xxx GB, or xxx.y GB as needed; allow for optional trailing string
+ * (like "\n")
  */
-void print_size (ulong size, const char *s)
+void print_size (phys_size_t size, const char *s)
 {
-	ulong m, n;
-	ulong d = 1 << 20;		/* 1 MB */
-	char  c = 'M';
-
-	if (size < d) {			/* print in kB */
-		c = 'k';
-		d = 1 << 10;
+	ulong m = 0, n;
+	phys_size_t d = 1 << 30;		/* 1 GB */
+	char  c = 'G';
+
+	if (size < d) {			/* try MB */
+		c = 'M';
+		d = 1 << 20;
+		if (size < d) {		/* print in kB */
+			c = 'k';
+			d = 1 << 10;
+		}
 	}
 
 	n = size / d;
 
-	m = (10 * (size - (n * d)) + (d / 2) ) / d;
+	/* If there's a remainder, deal with it */
+	if(size % d) {
+		m = (10 * (size - (n * d)) + (d / 2) ) / d;
 
-	if (m >= 10) {
-		m -= 10;
-		n += 1;
+		if (m >= 10) {
+			m -= 10;
+			n += 1;
+		}
 	}
 
 	printf ("%2ld", n);
diff --git a/lib_generic/lmb.c b/lib_generic/lmb.c
index 3b8c805..6b46fa8 100644
--- a/lib_generic/lmb.c
+++ b/lib_generic/lmb.c
@@ -22,33 +22,34 @@ void lmb_dump_all(struct lmb *lmb)
 
 	debug("lmb_dump_all:\n");
 	debug("    memory.cnt		   = 0x%lx\n", lmb->memory.cnt);
-	debug("    memory.size		   = 0x%08x\n", lmb->memory.size);
+	debug("    memory.size		   = 0x%llx\n",
+	      (unsigned long long)lmb->memory.size);
 	for (i=0; i < lmb->memory.cnt ;i++) {
-		debug("    memory.reg[0x%x].base   = 0x%08x\n", i,
+		debug("    memory.reg[0x%x].base   = 0x%llx\n", i,
 			lmb->memory.region[i].base);
-		debug("		   .size   = 0x%08x\n",
+		debug("		   .size   = 0x%llx\n",
 			lmb->memory.region[i].size);
 	}
 
 	debug("\n    reserved.cnt	   = 0x%lx\n", lmb->reserved.cnt);
-	debug("    reserved.size	   = 0x%08x\n", lmb->reserved.size);
+	debug("    reserved.size	   = 0x%llx\n", lmb->reserved.size);
 	for (i=0; i < lmb->reserved.cnt ;i++) {
-		debug("    reserved.reg[0x%x].base = 0x%08x\n", i,
+		debug("    reserved.reg[0x%x].base = 0x%llx\n", i,
 			lmb->reserved.region[i].base);
-		debug("		     .size = 0x%08x\n",
+		debug("		     .size = 0x%llx\n",
 			lmb->reserved.region[i].size);
 	}
 #endif /* DEBUG */
 }
 
-static unsigned long lmb_addrs_overlap(ulong base1,
-		ulong size1, ulong base2, ulong size2)
+static long lmb_addrs_overlap(phys_addr_t base1,
+		phys_size_t size1, phys_addr_t base2, phys_size_t size2)
 {
 	return ((base1 < (base2+size2)) && (base2 < (base1+size1)));
 }
 
-static long lmb_addrs_adjacent(ulong base1, ulong size1,
-		ulong base2, ulong size2)
+static long lmb_addrs_adjacent(phys_addr_t base1, phys_size_t size1,
+		phys_addr_t base2, phys_size_t size2)
 {
 	if (base2 == base1 + size1)
 		return 1;
@@ -61,10 +62,10 @@ static long lmb_addrs_adjacent(ulong base1, ulong size1,
 static long lmb_regions_adjacent(struct lmb_region *rgn,
 		unsigned long r1, unsigned long r2)
 {
-	ulong base1 = rgn->region[r1].base;
-	ulong size1 = rgn->region[r1].size;
-	ulong base2 = rgn->region[r2].base;
-	ulong size2 = rgn->region[r2].size;
+	phys_addr_t base1 = rgn->region[r1].base;
+	phys_size_t size1 = rgn->region[r1].size;
+	phys_addr_t base2 = rgn->region[r2].base;
+	phys_size_t size2 = rgn->region[r2].size;
 
 	return lmb_addrs_adjacent(base1, size1, base2, size2);
 }
@@ -106,7 +107,7 @@ void lmb_init(struct lmb *lmb)
 }
 
 /* This routine called with relocation disabled. */
-static long lmb_add_region(struct lmb_region *rgn, ulong base, ulong size)
+static long lmb_add_region(struct lmb_region *rgn, phys_addr_t base, phys_size_t size)
 {
 	unsigned long coalesced = 0;
 	long adjacent, i;
@@ -119,8 +120,8 @@ static long lmb_add_region(struct lmb_region *rgn, ulong base, ulong size)
 
 	/* First try and coalesce this LMB with another. */
 	for (i=0; i < rgn->cnt; i++) {
-		ulong rgnbase = rgn->region[i].base;
-		ulong rgnsize = rgn->region[i].size;
+		phys_addr_t rgnbase = rgn->region[i].base;
+		phys_size_t rgnsize = rgn->region[i].size;
 
 		if ((rgnbase == base) && (rgnsize == size))
 			/* Already have this region, so we're done */
@@ -173,28 +174,77 @@ static long lmb_add_region(struct lmb_region *rgn, ulong base, ulong size)
 }
 
 /* This routine may be called with relocation disabled. */
-long lmb_add(struct lmb *lmb, ulong base, ulong size)
+long lmb_add(struct lmb *lmb, phys_addr_t base, phys_size_t size)
 {
 	struct lmb_region *_rgn = &(lmb->memory);
 
 	return lmb_add_region(_rgn, base, size);
 }
 
-long lmb_reserve(struct lmb *lmb, ulong base, ulong size)
+long lmb_free(struct lmb *lmb, phys_addr_t base, phys_size_t size)
+{
+	struct lmb_region *rgn = &(lmb->reserved);
+	phys_addr_t rgnbegin, rgnend;
+	phys_addr_t end = base + size;
+	int i;
+
+	rgnbegin = rgnend = 0; /* supress gcc warnings */
+
+	/* Find the region where (base, size) belongs to */
+	for (i=0; i < rgn->cnt; i++) {
+		rgnbegin = rgn->region[i].base;
+		rgnend = rgnbegin + rgn->region[i].size;
+
+		if ((rgnbegin <= base) && (end <= rgnend))
+			break;
+	}
+
+	/* Didn't find the region */
+	if (i == rgn->cnt)
+		return -1;
+
+	/* Check to see if we are removing entire region */
+	if ((rgnbegin == base) && (rgnend == end)) {
+		lmb_remove_region(rgn, i);
+		return 0;
+	}
+
+	/* Check to see if region is matching at the front */
+	if (rgnbegin == base) {
+		rgn->region[i].base = end;
+		rgn->region[i].size -= size;
+		return 0;
+	}
+
+	/* Check to see if the region is matching at the end */
+	if (rgnend == end) {
+		rgn->region[i].size -= size;
+		return 0;
+	}
+
+	/*
+	 * We need to split the entry -  adjust the current one to the
+	 * beginging of the hole and add the region after hole.
+	 */
+	rgn->region[i].size = base - rgn->region[i].base;
+	return lmb_add_region(rgn, end, rgnend - end);
+}
+
+long lmb_reserve(struct lmb *lmb, phys_addr_t base, phys_size_t size)
 {
 	struct lmb_region *_rgn = &(lmb->reserved);
 
 	return lmb_add_region(_rgn, base, size);
 }
 
-long lmb_overlaps_region(struct lmb_region *rgn, ulong base,
-				ulong size)
+long lmb_overlaps_region(struct lmb_region *rgn, phys_addr_t base,
+				phys_size_t size)
 {
 	unsigned long i;
 
 	for (i=0; i < rgn->cnt; i++) {
-		ulong rgnbase = rgn->region[i].base;
-		ulong rgnsize = rgn->region[i].size;
+		phys_addr_t rgnbase = rgn->region[i].base;
+		phys_size_t rgnsize = rgn->region[i].size;
 		if ( lmb_addrs_overlap(base,size,rgnbase,rgnsize) ) {
 			break;
 		}
@@ -203,14 +253,14 @@ long lmb_overlaps_region(struct lmb_region *rgn, ulong base,
 	return (i < rgn->cnt) ? i : -1;
 }
 
-ulong lmb_alloc(struct lmb *lmb, ulong size, ulong align)
+phys_addr_t lmb_alloc(struct lmb *lmb, phys_size_t size, ulong align)
 {
 	return lmb_alloc_base(lmb, size, align, LMB_ALLOC_ANYWHERE);
 }
 
-ulong lmb_alloc_base(struct lmb *lmb, ulong size, ulong align, ulong max_addr)
+phys_addr_t lmb_alloc_base(struct lmb *lmb, phys_size_t size, ulong align, phys_addr_t max_addr)
 {
-	ulong alloc;
+	phys_addr_t alloc;
 
 	alloc = __lmb_alloc_base(lmb, size, align, max_addr);
 
@@ -221,25 +271,28 @@ ulong lmb_alloc_base(struct lmb *lmb, ulong size, ulong align, ulong max_addr)
 	return alloc;
 }
 
-static ulong lmb_align_down(ulong addr, ulong size)
+static phys_addr_t lmb_align_down(phys_addr_t addr, phys_size_t size)
 {
 	return addr & ~(size - 1);
 }
 
-static ulong lmb_align_up(ulong addr, ulong size)
+static phys_addr_t lmb_align_up(phys_addr_t addr, ulong size)
 {
 	return (addr + (size - 1)) & ~(size - 1);
 }
 
-ulong __lmb_alloc_base(struct lmb *lmb, ulong size, ulong align, ulong max_addr)
+phys_addr_t __lmb_alloc_base(struct lmb *lmb, phys_size_t size, ulong align, phys_addr_t max_addr)
 {
 	long i, j;
-	ulong base = 0;
+	phys_addr_t base = 0;
+	phys_addr_t res_base;
 
 	for (i = lmb->memory.cnt-1; i >= 0; i--) {
-		ulong lmbbase = lmb->memory.region[i].base;
-		ulong lmbsize = lmb->memory.region[i].size;
+		phys_addr_t lmbbase = lmb->memory.region[i].base;
+		phys_size_t lmbsize = lmb->memory.region[i].size;
 
+		if (lmbsize < size)
+			continue;
 		if (max_addr == LMB_ALLOC_ANYWHERE)
 			base = lmb_align_down(lmbbase + lmbsize - size, align);
 		else if (lmbbase < max_addr) {
@@ -248,30 +301,31 @@ ulong __lmb_alloc_base(struct lmb *lmb, ulong size, ulong align, ulong max_addr)
 		} else
 			continue;
 
-		while ((lmbbase <= base) &&
-		       ((j = lmb_overlaps_region(&(lmb->reserved), base, size)) >= 0) )
-			base = lmb_align_down(lmb->reserved.region[j].base - size,
-					      align);
-
-		if ((base != 0) && (lmbbase <= base))
-			break;
+		while (base && lmbbase <= base) {
+			j = lmb_overlaps_region(&lmb->reserved, base, size);
+			if (j < 0) {
+				/* This area isn't reserved, take it */
+				if (lmb_add_region(&lmb->reserved, base,
+							lmb_align_up(size,
+								align)) < 0)
+					return 0;
+				return base;
+			}
+			res_base = lmb->reserved.region[j].base;
+			if (res_base < size)
+				break;
+			base = lmb_align_down(res_base - size, align);
+		}
 	}
-
-	if (i < 0)
-		return 0;
-
-	if (lmb_add_region(&(lmb->reserved), base, lmb_align_up(size, align)) < 0)
-		return 0;
-
-	return base;
+	return 0;
 }
 
-int lmb_is_reserved(struct lmb *lmb, ulong addr)
+int lmb_is_reserved(struct lmb *lmb, phys_addr_t addr)
 {
 	int i;
 
 	for (i = 0; i < lmb->reserved.cnt; i++) {
-		ulong upper = lmb->reserved.region[i].base +
+		phys_addr_t upper = lmb->reserved.region[i].base +
 			lmb->reserved.region[i].size - 1;
 		if ((addr >= lmb->reserved.region[i].base) && (addr <= upper))
 			return 1;
diff --git a/lib_generic/md5.c b/lib_generic/md5.c
index 78ef475..9150510 100644
--- a/lib_generic/md5.c
+++ b/lib_generic/md5.c
@@ -27,10 +27,12 @@
 
 #ifndef USE_HOSTCC
 #include <common.h>
+#include <linux/string.h>
+#else
+#include <string.h>
 #endif /* USE_HOSTCC */
 #include <watchdog.h>
 #include <linux/types.h>
-#include <linux/string.h>
 #include <u-boot/md5.h>
 
 static void
diff --git a/lib_generic/sha1.c b/lib_generic/sha1.c
index c8ef4d2..da5bc16 100644
--- a/lib_generic/sha1.c
+++ b/lib_generic/sha1.c
@@ -31,9 +31,11 @@
 
 #ifndef USE_HOSTCC
 #include <common.h>
+#include <linux/string.h>
+#else
+#include <string.h>
 #endif /* USE_HOSTCC */
 #include <watchdog.h>
-#include <linux/string.h>
 #include "sha1.h"
 
 /*
diff --git a/lib_generic/sha256.c b/lib_generic/sha256.c
new file mode 100644
index 0000000..deb63a4
--- /dev/null
+++ b/lib_generic/sha256.c
@@ -0,0 +1,262 @@
+/*
+ * FIPS-180-2 compliant SHA-256 implementation
+ *
+ * Copyright (C) 2001-2003  Christophe Devine
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef USE_HOSTCC
+#include <common.h>
+#endif /* USE_HOSTCC */
+#include <watchdog.h>
+#include <linux/string.h>
+#include <sha256.h>
+
+/*
+ * 32-bit integer manipulation macros (big endian)
+ */
+#ifndef GET_UINT32_BE
+#define GET_UINT32_BE(n,b,i) {				\
+	(n) = ( (unsigned long) (b)[(i)    ] << 24 )	\
+	    | ( (unsigned long) (b)[(i) + 1] << 16 )	\
+	    | ( (unsigned long) (b)[(i) + 2] <<  8 )	\
+	    | ( (unsigned long) (b)[(i) + 3]       );	\
+}
+#endif
+#ifndef PUT_UINT32_BE
+#define PUT_UINT32_BE(n,b,i) {				\
+	(b)[(i)    ] = (unsigned char) ( (n) >> 24 );	\
+	(b)[(i) + 1] = (unsigned char) ( (n) >> 16 );	\
+	(b)[(i) + 2] = (unsigned char) ( (n) >>  8 );	\
+	(b)[(i) + 3] = (unsigned char) ( (n)       );	\
+}
+#endif
+
+void sha256_starts(sha256_context * ctx)
+{
+	ctx->total[0] = 0;
+	ctx->total[1] = 0;
+
+	ctx->state[0] = 0x6A09E667;
+	ctx->state[1] = 0xBB67AE85;
+	ctx->state[2] = 0x3C6EF372;
+	ctx->state[3] = 0xA54FF53A;
+	ctx->state[4] = 0x510E527F;
+	ctx->state[5] = 0x9B05688C;
+	ctx->state[6] = 0x1F83D9AB;
+	ctx->state[7] = 0x5BE0CD19;
+}
+
+void sha256_process(sha256_context * ctx, uint8_t data[64])
+{
+	uint32_t temp1, temp2;
+	uint32_t W[64];
+	uint32_t A, B, C, D, E, F, G, H;
+
+	GET_UINT32_BE(W[0], data, 0);
+	GET_UINT32_BE(W[1], data, 4);
+	GET_UINT32_BE(W[2], data, 8);
+	GET_UINT32_BE(W[3], data, 12);
+	GET_UINT32_BE(W[4], data, 16);
+	GET_UINT32_BE(W[5], data, 20);
+	GET_UINT32_BE(W[6], data, 24);
+	GET_UINT32_BE(W[7], data, 28);
+	GET_UINT32_BE(W[8], data, 32);
+	GET_UINT32_BE(W[9], data, 36);
+	GET_UINT32_BE(W[10], data, 40);
+	GET_UINT32_BE(W[11], data, 44);
+	GET_UINT32_BE(W[12], data, 48);
+	GET_UINT32_BE(W[13], data, 52);
+	GET_UINT32_BE(W[14], data, 56);
+	GET_UINT32_BE(W[15], data, 60);
+
+#define SHR(x,n) ((x & 0xFFFFFFFF) >> n)
+#define ROTR(x,n) (SHR(x,n) | (x << (32 - n)))
+
+#define S0(x) (ROTR(x, 7) ^ ROTR(x,18) ^ SHR(x, 3))
+#define S1(x) (ROTR(x,17) ^ ROTR(x,19) ^ SHR(x,10))
+
+#define S2(x) (ROTR(x, 2) ^ ROTR(x,13) ^ ROTR(x,22))
+#define S3(x) (ROTR(x, 6) ^ ROTR(x,11) ^ ROTR(x,25))
+
+#define F0(x,y,z) ((x & y) | (z & (x | y)))
+#define F1(x,y,z) (z ^ (x & (y ^ z)))
+
+#define R(t)					\
+(						\
+	W[t] = S1(W[t - 2]) + W[t - 7] +	\
+		S0(W[t - 15]) + W[t - 16]	\
+)
+
+#define P(a,b,c,d,e,f,g,h,x,K) {		\
+	temp1 = h + S3(e) + F1(e,f,g) + K + x;	\
+	temp2 = S2(a) + F0(a,b,c);		\
+	d += temp1; h = temp1 + temp2;		\
+}
+
+	A = ctx->state[0];
+	B = ctx->state[1];
+	C = ctx->state[2];
+	D = ctx->state[3];
+	E = ctx->state[4];
+	F = ctx->state[5];
+	G = ctx->state[6];
+	H = ctx->state[7];
+
+	P(A, B, C, D, E, F, G, H, W[0], 0x428A2F98);
+	P(H, A, B, C, D, E, F, G, W[1], 0x71374491);
+	P(G, H, A, B, C, D, E, F, W[2], 0xB5C0FBCF);
+	P(F, G, H, A, B, C, D, E, W[3], 0xE9B5DBA5);
+	P(E, F, G, H, A, B, C, D, W[4], 0x3956C25B);
+	P(D, E, F, G, H, A, B, C, W[5], 0x59F111F1);
+	P(C, D, E, F, G, H, A, B, W[6], 0x923F82A4);
+	P(B, C, D, E, F, G, H, A, W[7], 0xAB1C5ED5);
+	P(A, B, C, D, E, F, G, H, W[8], 0xD807AA98);
+	P(H, A, B, C, D, E, F, G, W[9], 0x12835B01);
+	P(G, H, A, B, C, D, E, F, W[10], 0x243185BE);
+	P(F, G, H, A, B, C, D, E, W[11], 0x550C7DC3);
+	P(E, F, G, H, A, B, C, D, W[12], 0x72BE5D74);
+	P(D, E, F, G, H, A, B, C, W[13], 0x80DEB1FE);
+	P(C, D, E, F, G, H, A, B, W[14], 0x9BDC06A7);
+	P(B, C, D, E, F, G, H, A, W[15], 0xC19BF174);
+	P(A, B, C, D, E, F, G, H, R(16), 0xE49B69C1);
+	P(H, A, B, C, D, E, F, G, R(17), 0xEFBE4786);
+	P(G, H, A, B, C, D, E, F, R(18), 0x0FC19DC6);
+	P(F, G, H, A, B, C, D, E, R(19), 0x240CA1CC);
+	P(E, F, G, H, A, B, C, D, R(20), 0x2DE92C6F);
+	P(D, E, F, G, H, A, B, C, R(21), 0x4A7484AA);
+	P(C, D, E, F, G, H, A, B, R(22), 0x5CB0A9DC);
+	P(B, C, D, E, F, G, H, A, R(23), 0x76F988DA);
+	P(A, B, C, D, E, F, G, H, R(24), 0x983E5152);
+	P(H, A, B, C, D, E, F, G, R(25), 0xA831C66D);
+	P(G, H, A, B, C, D, E, F, R(26), 0xB00327C8);
+	P(F, G, H, A, B, C, D, E, R(27), 0xBF597FC7);
+	P(E, F, G, H, A, B, C, D, R(28), 0xC6E00BF3);
+	P(D, E, F, G, H, A, B, C, R(29), 0xD5A79147);
+	P(C, D, E, F, G, H, A, B, R(30), 0x06CA6351);
+	P(B, C, D, E, F, G, H, A, R(31), 0x14292967);
+	P(A, B, C, D, E, F, G, H, R(32), 0x27B70A85);
+	P(H, A, B, C, D, E, F, G, R(33), 0x2E1B2138);
+	P(G, H, A, B, C, D, E, F, R(34), 0x4D2C6DFC);
+	P(F, G, H, A, B, C, D, E, R(35), 0x53380D13);
+	P(E, F, G, H, A, B, C, D, R(36), 0x650A7354);
+	P(D, E, F, G, H, A, B, C, R(37), 0x766A0ABB);
+	P(C, D, E, F, G, H, A, B, R(38), 0x81C2C92E);
+	P(B, C, D, E, F, G, H, A, R(39), 0x92722C85);
+	P(A, B, C, D, E, F, G, H, R(40), 0xA2BFE8A1);
+	P(H, A, B, C, D, E, F, G, R(41), 0xA81A664B);
+	P(G, H, A, B, C, D, E, F, R(42), 0xC24B8B70);
+	P(F, G, H, A, B, C, D, E, R(43), 0xC76C51A3);
+	P(E, F, G, H, A, B, C, D, R(44), 0xD192E819);
+	P(D, E, F, G, H, A, B, C, R(45), 0xD6990624);
+	P(C, D, E, F, G, H, A, B, R(46), 0xF40E3585);
+	P(B, C, D, E, F, G, H, A, R(47), 0x106AA070);
+	P(A, B, C, D, E, F, G, H, R(48), 0x19A4C116);
+	P(H, A, B, C, D, E, F, G, R(49), 0x1E376C08);
+	P(G, H, A, B, C, D, E, F, R(50), 0x2748774C);
+	P(F, G, H, A, B, C, D, E, R(51), 0x34B0BCB5);
+	P(E, F, G, H, A, B, C, D, R(52), 0x391C0CB3);
+	P(D, E, F, G, H, A, B, C, R(53), 0x4ED8AA4A);
+	P(C, D, E, F, G, H, A, B, R(54), 0x5B9CCA4F);
+	P(B, C, D, E, F, G, H, A, R(55), 0x682E6FF3);
+	P(A, B, C, D, E, F, G, H, R(56), 0x748F82EE);
+	P(H, A, B, C, D, E, F, G, R(57), 0x78A5636F);
+	P(G, H, A, B, C, D, E, F, R(58), 0x84C87814);
+	P(F, G, H, A, B, C, D, E, R(59), 0x8CC70208);
+	P(E, F, G, H, A, B, C, D, R(60), 0x90BEFFFA);
+	P(D, E, F, G, H, A, B, C, R(61), 0xA4506CEB);
+	P(C, D, E, F, G, H, A, B, R(62), 0xBEF9A3F7);
+	P(B, C, D, E, F, G, H, A, R(63), 0xC67178F2);
+
+	ctx->state[0] += A;
+	ctx->state[1] += B;
+	ctx->state[2] += C;
+	ctx->state[3] += D;
+	ctx->state[4] += E;
+	ctx->state[5] += F;
+	ctx->state[6] += G;
+	ctx->state[7] += H;
+}
+
+void sha256_update(sha256_context * ctx, uint8_t * input, uint32_t length)
+{
+	uint32_t left, fill;
+
+	if (!length)
+		return;
+
+	left = ctx->total[0] & 0x3F;
+	fill = 64 - left;
+
+	ctx->total[0] += length;
+	ctx->total[0] &= 0xFFFFFFFF;
+
+	if (ctx->total[0] < length)
+		ctx->total[1]++;
+
+	if (left && length >= fill) {
+		memcpy((void *) (ctx->buffer + left), (void *) input, fill);
+		sha256_process(ctx, ctx->buffer);
+		length -= fill;
+		input += fill;
+		left = 0;
+	}
+
+	while (length >= 64) {
+		sha256_process(ctx, input);
+		length -= 64;
+		input += 64;
+	}
+
+	if (length)
+		memcpy((void *) (ctx->buffer + left), (void *) input, length);
+}
+
+static uint8_t sha256_padding[64] = {
+	0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+
+void sha256_finish(sha256_context * ctx, uint8_t digest[32])
+{
+	uint32_t last, padn;
+	uint32_t high, low;
+	uint8_t msglen[8];
+
+	high = ((ctx->total[0] >> 29)
+		| (ctx->total[1] << 3));
+	low = (ctx->total[0] << 3);
+
+	PUT_UINT32_BE(high, msglen, 0);
+	PUT_UINT32_BE(low, msglen, 4);
+
+	last = ctx->total[0] & 0x3F;
+	padn = (last < 56) ? (56 - last) : (120 - last);
+
+	sha256_update(ctx, sha256_padding, padn);
+	sha256_update(ctx, msglen, 8);
+
+	PUT_UINT32_BE(ctx->state[0], digest, 0);
+	PUT_UINT32_BE(ctx->state[1], digest, 4);
+	PUT_UINT32_BE(ctx->state[2], digest, 8);
+	PUT_UINT32_BE(ctx->state[3], digest, 12);
+	PUT_UINT32_BE(ctx->state[4], digest, 16);
+	PUT_UINT32_BE(ctx->state[5], digest, 20);
+	PUT_UINT32_BE(ctx->state[6], digest, 24);
+	PUT_UINT32_BE(ctx->state[7], digest, 28);
+}