3 files changed, 46 insertions, 314 deletions

diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 7e319951fa41..51738bdd834e 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -1,7 +1,5 @@
 /*
- * drivers/char/hw_random/omap-rng.c
- *
- * RNG driver for TI OMAP CPU family
+ * omap-rng.c - RNG driver for TI OMAP CPU family
  *
  * Author: Deepak Saxena <dsaxena@plexity.net>
  *
@@ -15,11 +13,6 @@
  * This file is licensed under  the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
- *
- * TODO:
- *
- * - Make status updated be interrupt driven so we don't poll
- *
  */
 
 #include <linux/module.h>
@@ -55,17 +48,16 @@ static void __iomem *rng_base;
 static struct clk *rng_ick;
 static struct platform_device *rng_dev;
 
-static u32 omap_rng_read_reg(int reg)
+static inline u32 omap_rng_read_reg(int reg)
 {
         return __raw_readl(rng_base + reg);
 }
 
-static void omap_rng_write_reg(int reg, u32 val)
+static inline void omap_rng_write_reg(int reg, u32 val)
 {
         __raw_writel(val, rng_base + reg);
 }
 
-/* REVISIT: Does the status bit really work on 16xx? */
 static int omap_rng_data_present(struct hwrng *rng, int wait)
 {
         int data, i;
@@ -74,6 +66,11 @@ static int omap_rng_data_present(struct hwrng *rng, int wait)
                 data = omap_rng_read_reg(RNG_STAT_REG) ? 0 : 1;
                 if (data || !wait)
                         break;
+                /* RNG produces data fast enough (2+ MBit/sec, even
+                 * during "rngtest" loads, that these delays don't
+                 * seem to trigger.  We *could* use the RNG IRQ, but
+                 * that'd be higher overhead ... so why bother?
+                 */
                 udelay(10);
         }
         return data;
@@ -101,7 +98,8 @@ static int __init omap_rng_probe(struct platform_device *pdev)
          * A bit ugly, and it will never actually happen but there can
          * be only one RNG and this catches any bork
          */
-        BUG_ON(rng_dev);
+        if (rng_dev)
+                return -EBUSY;
 
         if (cpu_is_omap24xx()) {
                 rng_ick = clk_get(NULL, "rng_ick");
@@ -124,7 +122,7 @@ static int __init omap_rng_probe(struct platform_device *pdev)
                 return -EBUSY;
 
         dev_set_drvdata(&pdev->dev, mem);
-        rng_base = (u32 __iomem *)io_p2v(res->start);
+        rng_base = (u32 __force __iomem *)io_p2v(res->start);
 
         ret = hwrng_register(&omap_rng_ops);
         if (ret) {
@@ -182,6 +180,8 @@ static int omap_rng_resume(struct platform_device *pdev)
 
 #endif
 
+/* work with hotplug and coldplug */
+MODULE_ALIAS("platform:omap_rng");
 
 static struct platform_driver omap_rng_driver = {
         .driver = {
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 6d2f0c8d419a..43b71b69daa5 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -27,6 +27,7 @@ config CRYPTO_DEV_PADLOCK_AES
         tristate "PadLock driver for AES algorithm"
         depends on CRYPTO_DEV_PADLOCK
         select CRYPTO_BLKCIPHER
+        select CRYPTO_AES
         help
           Use VIA PadLock for AES algorithm.
 
@@ -101,6 +102,19 @@ config CRYPTO_SHA256_S390
           This version of SHA implements a 256 bit hash with 128 bits of
           security against collision attacks.
 
+config CRYPTO_SHA512_S390
+        tristate "SHA384 and SHA512 digest algorithm"
+        depends on S390
+        select CRYPTO_ALGAPI
+        help
+          This is the s390 hardware accelerated implementation of the
+          SHA512 secure hash standard.
+
+          This version of SHA implements a 512 bit hash with 256 bits of
+          security against collision attacks. The code also includes SHA-384,
+          a 384 bit hash with 192 bits of security against collision attacks.
+
+
 config CRYPTO_DES_S390
         tristate "DES and Triple DES cipher algorithms"
         depends on S390
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 2f3ad3f7dfea..bb30eb9b93ef 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -5,42 +5,6 @@
  *
  * Copyright (c) 2004  Michal Ludvig <michal@logix.cz>
  *
- * Key expansion routine taken from crypto/aes_generic.c
- *
- * 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.
- *
- * ---------------------------------------------------------------------------
- * Copyright (c) 2002, Dr Brian Gladman <brg@gladman.me.uk>, Worcester, UK.
- * All rights reserved.
- *
- * LICENSE TERMS
- *
- * The free distribution and use of this software in both source and binary
- * form is allowed (with or without changes) provided that:
- *
- *   1. distributions of this source code include the above copyright
- *      notice, this list of conditions and the following disclaimer;
- *
- *   2. distributions in binary form include the above copyright
- *      notice, this list of conditions and the following disclaimer
- *      in the documentation and/or other associated materials;
- *
- *   3. the copyright holder's name is not used to endorse products
- *      built using this software without specific written permission.
- *
- * ALTERNATIVELY, provided that this notice is retained in full, this product
- * may be distributed under the terms of the GNU General Public License (GPL),
- * in which case the provisions of the GPL apply INSTEAD OF those given above.
- *
- * DISCLAIMER
- *
- * This software is provided 'as is' with no explicit or implied warranties
- * in respect of its properties, including, but not limited to, correctness
- * and/or fitness for purpose.
- * ---------------------------------------------------------------------------
  */
 
 #include <crypto/algapi.h>
@@ -54,9 +18,6 @@
 #include <asm/byteorder.h>
 #include "padlock.h"
 
-#define AES_EXTENDED_KEY_SIZE   64      /* in uint32_t units */
-#define AES_EXTENDED_KEY_SIZE_B (AES_EXTENDED_KEY_SIZE * sizeof(uint32_t))
-
 /* Control word. */
 struct cword {
         unsigned int __attribute__ ((__packed__))
@@ -70,218 +31,23 @@ struct cword {
 
 /* Whenever making any changes to the following
  * structure *make sure* you keep E, d_data
- * and cword aligned on 16 Bytes boundaries!!! */
+ * and cword aligned on 16 Bytes boundaries and
+ * the Hardware can access 16 * 16 bytes of E and d_data
+ * (only the first 15 * 16 bytes matter but the HW reads
+ * more).
+ */
 struct aes_ctx {
+        u32 E[AES_MAX_KEYLENGTH_U32]
+                __attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
+        u32 d_data[AES_MAX_KEYLENGTH_U32]
+                __attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
         struct {
                 struct cword encrypt;
                 struct cword decrypt;
         } cword;
         u32 *D;
-        int key_length;
-        u32 E[AES_EXTENDED_KEY_SIZE]
-                __attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
-        u32 d_data[AES_EXTENDED_KEY_SIZE]
-                __attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
 };
 
-/* ====== Key management routines ====== */
-
-static inline uint32_t
-generic_rotr32 (const uint32_t x, const unsigned bits)
-{
-        const unsigned n = bits % 32;
-        return (x >> n) | (x << (32 - n));
-}
-
-static inline uint32_t
-generic_rotl32 (const uint32_t x, const unsigned bits)
-{
-        const unsigned n = bits % 32;
-        return (x << n) | (x >> (32 - n));
-}
-
-#define rotl generic_rotl32
-#define rotr generic_rotr32
-
-/*
- * #define byte(x, nr) ((unsigned char)((x) >> (nr*8))) 
- */
-static inline uint8_t
-byte(const uint32_t x, const unsigned n)
-{
-        return x >> (n << 3);
-}
-
-#define E_KEY ctx->E
-#define D_KEY ctx->D
-
-static uint8_t pow_tab[256];
-static uint8_t log_tab[256];
-static uint8_t sbx_tab[256];
-static uint8_t isb_tab[256];
-static uint32_t rco_tab[10];
-static uint32_t ft_tab[4][256];
-static uint32_t it_tab[4][256];
-
-static uint32_t fl_tab[4][256];
-static uint32_t il_tab[4][256];
-
-static inline uint8_t
-f_mult (uint8_t a, uint8_t b)
-{
-        uint8_t aa = log_tab[a], cc = aa + log_tab[b];
-
-        return pow_tab[cc + (cc < aa ? 1 : 0)];
-}
-
-#define ff_mult(a,b)    (a && b ? f_mult(a, b) : 0)
-
-#define f_rn(bo, bi, n, k)                                      \
-    bo[n] =  ft_tab[0][byte(bi[n],0)] ^                         \
-             ft_tab[1][byte(bi[(n + 1) & 3],1)] ^               \
-             ft_tab[2][byte(bi[(n + 2) & 3],2)] ^               \
-             ft_tab[3][byte(bi[(n + 3) & 3],3)] ^ *(k + n)
-
-#define i_rn(bo, bi, n, k)                                      \
-    bo[n] =  it_tab[0][byte(bi[n],0)] ^                         \
-             it_tab[1][byte(bi[(n + 3) & 3],1)] ^               \
-             it_tab[2][byte(bi[(n + 2) & 3],2)] ^               \
-             it_tab[3][byte(bi[(n + 1) & 3],3)] ^ *(k + n)
-
-#define ls_box(x)                               \
-    ( fl_tab[0][byte(x, 0)] ^                   \
-      fl_tab[1][byte(x, 1)] ^                   \
-      fl_tab[2][byte(x, 2)] ^                   \
-      fl_tab[3][byte(x, 3)] )
-
-#define f_rl(bo, bi, n, k)                                      \
-    bo[n] =  fl_tab[0][byte(bi[n],0)] ^                         \
-             fl_tab[1][byte(bi[(n + 1) & 3],1)] ^               \
-             fl_tab[2][byte(bi[(n + 2) & 3],2)] ^               \
-             fl_tab[3][byte(bi[(n + 3) & 3],3)] ^ *(k + n)
-
-#define i_rl(bo, bi, n, k)                                      \
-    bo[n] =  il_tab[0][byte(bi[n],0)] ^                         \
-             il_tab[1][byte(bi[(n + 3) & 3],1)] ^               \
-             il_tab[2][byte(bi[(n + 2) & 3],2)] ^               \
-             il_tab[3][byte(bi[(n + 1) & 3],3)] ^ *(k + n)
-
-static void
-gen_tabs (void)
-{
-        uint32_t i, t;
-        uint8_t p, q;
-
-        /* log and power tables for GF(2**8) finite field with
-           0x011b as modular polynomial - the simplest prmitive
-           root is 0x03, used here to generate the tables */
-
-        for (i = 0, p = 1; i < 256; ++i) {
-                pow_tab[i] = (uint8_t) p;
-                log_tab[p] = (uint8_t) i;
-
-                p ^= (p << 1) ^ (p & 0x80 ? 0x01b : 0);
-        }
-
-        log_tab[1] = 0;
-
-        for (i = 0, p = 1; i < 10; ++i) {
-                rco_tab[i] = p;
-
-                p = (p << 1) ^ (p & 0x80 ? 0x01b : 0);
-        }
-
-        for (i = 0; i < 256; ++i) {
-                p = (i ? pow_tab[255 - log_tab[i]] : 0);
-                q = ((p >> 7) | (p << 1)) ^ ((p >> 6) | (p << 2));
-                p ^= 0x63 ^ q ^ ((q >> 6) | (q << 2));
-                sbx_tab[i] = p;
-                isb_tab[p] = (uint8_t) i;
-        }
-
-        for (i = 0; i < 256; ++i) {
-                p = sbx_tab[i];
-
-                t = p;
-                fl_tab[0][i] = t;
-                fl_tab[1][i] = rotl (t, 8);
-                fl_tab[2][i] = rotl (t, 16);
-                fl_tab[3][i] = rotl (t, 24);
-
-                t = ((uint32_t) ff_mult (2, p)) |
-                    ((uint32_t) p << 8) |
-                    ((uint32_t) p << 16) | ((uint32_t) ff_mult (3, p) << 24);
-
-                ft_tab[0][i] = t;
-                ft_tab[1][i] = rotl (t, 8);
-                ft_tab[2][i] = rotl (t, 16);
-                ft_tab[3][i] = rotl (t, 24);
-
-                p = isb_tab[i];
-
-                t = p;
-                il_tab[0][i] = t;
-                il_tab[1][i] = rotl (t, 8);
-                il_tab[2][i] = rotl (t, 16);
-                il_tab[3][i] = rotl (t, 24);
-
-                t = ((uint32_t) ff_mult (14, p)) |
-                    ((uint32_t) ff_mult (9, p) << 8) |
-                    ((uint32_t) ff_mult (13, p) << 16) |
-                    ((uint32_t) ff_mult (11, p) << 24);
-
-                it_tab[0][i] = t;
-                it_tab[1][i] = rotl (t, 8);
-                it_tab[2][i] = rotl (t, 16);
-                it_tab[3][i] = rotl (t, 24);
-        }
-}
-
-#define star_x(x) (((x) & 0x7f7f7f7f) << 1) ^ ((((x) & 0x80808080) >> 7) * 0x1b)
-
-#define imix_col(y,x)       \
-    u   = star_x(x);        \
-    v   = star_x(u);        \
-    w   = star_x(v);        \
-    t   = w ^ (x);          \
-   (y)  = u ^ v ^ w;        \
-   (y) ^= rotr(u ^ t,  8) ^ \
-          rotr(v ^ t, 16) ^ \
-          rotr(t,24)
-
-/* initialise the key schedule from the user supplied key */
-
-#define loop4(i)                                    \
-{   t = rotr(t,  8); t = ls_box(t) ^ rco_tab[i];    \
-    t ^= E_KEY[4 * i];     E_KEY[4 * i + 4] = t;    \
-    t ^= E_KEY[4 * i + 1]; E_KEY[4 * i + 5] = t;    \
-    t ^= E_KEY[4 * i + 2]; E_KEY[4 * i + 6] = t;    \
-    t ^= E_KEY[4 * i + 3]; E_KEY[4 * i + 7] = t;    \
-}
-
-#define loop6(i)                                    \
-{   t = rotr(t,  8); t = ls_box(t) ^ rco_tab[i];    \
-    t ^= E_KEY[6 * i];     E_KEY[6 * i + 6] = t;    \
-    t ^= E_KEY[6 * i + 1]; E_KEY[6 * i + 7] = t;    \
-    t ^= E_KEY[6 * i + 2]; E_KEY[6 * i + 8] = t;    \
-    t ^= E_KEY[6 * i + 3]; E_KEY[6 * i + 9] = t;    \
-    t ^= E_KEY[6 * i + 4]; E_KEY[6 * i + 10] = t;   \
-    t ^= E_KEY[6 * i + 5]; E_KEY[6 * i + 11] = t;   \
-}
-
-#define loop8(i)                                    \
-{   t = rotr(t,  8); ; t = ls_box(t) ^ rco_tab[i];  \
-    t ^= E_KEY[8 * i];     E_KEY[8 * i + 8] = t;    \
-    t ^= E_KEY[8 * i + 1]; E_KEY[8 * i + 9] = t;    \
-    t ^= E_KEY[8 * i + 2]; E_KEY[8 * i + 10] = t;   \
-    t ^= E_KEY[8 * i + 3]; E_KEY[8 * i + 11] = t;   \
-    t  = E_KEY[8 * i + 4] ^ ls_box(t);    \
-    E_KEY[8 * i + 12] = t;                \
-    t ^= E_KEY[8 * i + 5]; E_KEY[8 * i + 13] = t;   \
-    t ^= E_KEY[8 * i + 6]; E_KEY[8 * i + 14] = t;   \
-    t ^= E_KEY[8 * i + 7]; E_KEY[8 * i + 15] = t;   \
-}
-
 /* Tells whether the ACE is capable to generate
    the extended key for a given key_len. */
 static inline int
@@ -321,17 +87,13 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
         struct aes_ctx *ctx = aes_ctx(tfm);
         const __le32 *key = (const __le32 *)in_key;
         u32 *flags = &tfm->crt_flags;
-        uint32_t i, t, u, v, w;
-        uint32_t P[AES_EXTENDED_KEY_SIZE];
-        uint32_t rounds;
+        struct crypto_aes_ctx gen_aes;
 
         if (key_len % 8) {
                 *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
                 return -EINVAL;
         }
 
-        ctx->key_length = key_len;
-
         /*
          * If the hardware is capable of generating the extended key
          * itself we must supply the plain key for both encryption
@@ -339,10 +101,10 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
          */
         ctx->D = ctx->E;
 
-        E_KEY[0] = le32_to_cpu(key[0]);
-        E_KEY[1] = le32_to_cpu(key[1]);
-        E_KEY[2] = le32_to_cpu(key[2]);
-        E_KEY[3] = le32_to_cpu(key[3]);
+        ctx->E[0] = le32_to_cpu(key[0]);
+        ctx->E[1] = le32_to_cpu(key[1]);
+        ctx->E[2] = le32_to_cpu(key[2]);
+        ctx->E[3] = le32_to_cpu(key[3]);
 
         /* Prepare control words. */
         memset(&ctx->cword, 0, sizeof(ctx->cword));
@@ -361,56 +123,13 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
         ctx->cword.encrypt.keygen = 1;
         ctx->cword.decrypt.keygen = 1;
 
-        switch (key_len) {
-        case 16:
-                t = E_KEY[3];
-                for (i = 0; i < 10; ++i)
-                        loop4 (i);
-                break;
-
-        case 24:
-                E_KEY[4] = le32_to_cpu(key[4]);
-                t = E_KEY[5] = le32_to_cpu(key[5]);
-                for (i = 0; i < 8; ++i)
-                        loop6 (i);
-                break;
-
-        case 32:
-                E_KEY[4] = le32_to_cpu(key[4]);
-                E_KEY[5] = le32_to_cpu(key[5]);
-                E_KEY[6] = le32_to_cpu(key[6]);
-                t = E_KEY[7] = le32_to_cpu(key[7]);
-                for (i = 0; i < 7; ++i)
-                        loop8 (i);
-                break;
-        }
-
-        D_KEY[0] = E_KEY[0];
-        D_KEY[1] = E_KEY[1];
-        D_KEY[2] = E_KEY[2];
-        D_KEY[3] = E_KEY[3];
-
-        for (i = 4; i < key_len + 24; ++i) {
-                imix_col (D_KEY[i], E_KEY[i]);
-        }
-
-        /* PadLock needs a different format of the decryption key. */
-        rounds = 10 + (key_len - 16) / 4;
-
-        for (i = 0; i < rounds; i++) {
-                P[((i + 1) * 4) + 0] = D_KEY[((rounds - i - 1) * 4) + 0];
-                P[((i + 1) * 4) + 1] = D_KEY[((rounds - i - 1) * 4) + 1];
-                P[((i + 1) * 4) + 2] = D_KEY[((rounds - i - 1) * 4) + 2];
-                P[((i + 1) * 4) + 3] = D_KEY[((rounds - i - 1) * 4) + 3];
+        if (crypto_aes_expand_key(&gen_aes, in_key, key_len)) {
+                *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+                return -EINVAL;
         }
 
-        P[0] = E_KEY[(rounds * 4) + 0];
-        P[1] = E_KEY[(rounds * 4) + 1];
-        P[2] = E_KEY[(rounds * 4) + 2];
-        P[3] = E_KEY[(rounds * 4) + 3];
-
-        memcpy(D_KEY, P, AES_EXTENDED_KEY_SIZE_B);
-
+        memcpy(ctx->E, gen_aes.key_enc, AES_MAX_KEYLENGTH);
+        memcpy(ctx->D, gen_aes.key_dec, AES_MAX_KEYLENGTH);
         return 0;
 }
 
@@ -675,7 +394,6 @@ static int __init padlock_init(void)
                 return -ENODEV;
         }
 
-        gen_tabs();
         if ((ret = crypto_register_alg(&aes_alg)))
                 goto aes_err;