summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/s390/Kconfig2
-rw-r--r--arch/s390/crypto/crypt_s390.h122
-rw-r--r--arch/s390/crypto/prng.c850
-rw-r--r--arch/s390/include/asm/kexec.h3
-rw-r--r--arch/s390/include/asm/mmu.h4
-rw-r--r--arch/s390/include/asm/mmu_context.h3
-rw-r--r--arch/s390/include/asm/pgalloc.h1
-rw-r--r--arch/s390/include/asm/pgtable.h167
-rw-r--r--arch/s390/mm/hugetlbpage.c66
-rw-r--r--arch/s390/mm/pgtable.c142
-rw-r--r--arch/tile/kernel/setup.c2
-rw-r--r--arch/x86/include/asm/pvclock.h1
-rw-r--r--arch/x86/kernel/pvclock.c44
-rw-r--r--arch/x86/kvm/x86.c33
-rw-r--r--arch/x86/vdso/vclock_gettime.c34
15 files changed, 1076 insertions, 398 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8e58c614c37d..b06dc3839268 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -115,7 +115,7 @@ config S390
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
- select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z9_109_FEATURES
+ select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
select HAVE_DEBUG_KMEMLEAK
diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h
index ba3b2aefddf5..d9c4c313fbc6 100644
--- a/arch/s390/crypto/crypt_s390.h
+++ b/arch/s390/crypto/crypt_s390.h
@@ -3,9 +3,10 @@
*
* Support for s390 cryptographic instructions.
*
- * Copyright IBM Corp. 2003, 2007
+ * Copyright IBM Corp. 2003, 2015
* Author(s): Thomas Spatzier
* Jan Glauber (jan.glauber@de.ibm.com)
+ * Harald Freudenberger (freude@de.ibm.com)
*
* 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
@@ -28,15 +29,17 @@
#define CRYPT_S390_MSA 0x1
#define CRYPT_S390_MSA3 0x2
#define CRYPT_S390_MSA4 0x4
+#define CRYPT_S390_MSA5 0x8
/* s390 cryptographic operations */
enum crypt_s390_operations {
- CRYPT_S390_KM = 0x0100,
- CRYPT_S390_KMC = 0x0200,
- CRYPT_S390_KIMD = 0x0300,
- CRYPT_S390_KLMD = 0x0400,
- CRYPT_S390_KMAC = 0x0500,
- CRYPT_S390_KMCTR = 0x0600
+ CRYPT_S390_KM = 0x0100,
+ CRYPT_S390_KMC = 0x0200,
+ CRYPT_S390_KIMD = 0x0300,
+ CRYPT_S390_KLMD = 0x0400,
+ CRYPT_S390_KMAC = 0x0500,
+ CRYPT_S390_KMCTR = 0x0600,
+ CRYPT_S390_PPNO = 0x0700
};
/*
@@ -138,6 +141,16 @@ enum crypt_s390_kmac_func {
KMAC_TDEA_192 = CRYPT_S390_KMAC | 3
};
+/*
+ * function codes for PPNO (PERFORM PSEUDORANDOM NUMBER
+ * OPERATION) instruction
+ */
+enum crypt_s390_ppno_func {
+ PPNO_QUERY = CRYPT_S390_PPNO | 0,
+ PPNO_SHA512_DRNG_GEN = CRYPT_S390_PPNO | 3,
+ PPNO_SHA512_DRNG_SEED = CRYPT_S390_PPNO | 0x83
+};
+
/**
* crypt_s390_km:
* @func: the function code passed to KM; see crypt_s390_km_func
@@ -162,11 +175,11 @@ static inline int crypt_s390_km(long func, void *param,
int ret;
asm volatile(
- "0: .insn rre,0xb92e0000,%3,%1 \n" /* KM opcode */
- "1: brc 1,0b \n" /* handle partial completion */
+ "0: .insn rre,0xb92e0000,%3,%1\n" /* KM opcode */
+ "1: brc 1,0b\n" /* handle partial completion */
" la %0,0\n"
"2:\n"
- EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
: "=d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest)
: "d" (__func), "a" (__param), "0" (-1) : "cc", "memory");
if (ret < 0)
@@ -198,11 +211,11 @@ static inline int crypt_s390_kmc(long func, void *param,
int ret;
asm volatile(
- "0: .insn rre,0xb92f0000,%3,%1 \n" /* KMC opcode */
- "1: brc 1,0b \n" /* handle partial completion */
+ "0: .insn rre,0xb92f0000,%3,%1\n" /* KMC opcode */
+ "1: brc 1,0b\n" /* handle partial completion */
" la %0,0\n"
"2:\n"
- EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
: "=d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest)
: "d" (__func), "a" (__param), "0" (-1) : "cc", "memory");
if (ret < 0)
@@ -233,11 +246,11 @@ static inline int crypt_s390_kimd(long func, void *param,
int ret;
asm volatile(
- "0: .insn rre,0xb93e0000,%1,%1 \n" /* KIMD opcode */
- "1: brc 1,0b \n" /* handle partial completion */
+ "0: .insn rre,0xb93e0000,%1,%1\n" /* KIMD opcode */
+ "1: brc 1,0b\n" /* handle partial completion */
" la %0,0\n"
"2:\n"
- EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
: "=d" (ret), "+a" (__src), "+d" (__src_len)
: "d" (__func), "a" (__param), "0" (-1) : "cc", "memory");
if (ret < 0)
@@ -267,11 +280,11 @@ static inline int crypt_s390_klmd(long func, void *param,
int ret;
asm volatile(
- "0: .insn rre,0xb93f0000,%1,%1 \n" /* KLMD opcode */
- "1: brc 1,0b \n" /* handle partial completion */
+ "0: .insn rre,0xb93f0000,%1,%1\n" /* KLMD opcode */
+ "1: brc 1,0b\n" /* handle partial completion */
" la %0,0\n"
"2:\n"
- EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
: "=d" (ret), "+a" (__src), "+d" (__src_len)
: "d" (__func), "a" (__param), "0" (-1) : "cc", "memory");
if (ret < 0)
@@ -302,11 +315,11 @@ static inline int crypt_s390_kmac(long func, void *param,
int ret;
asm volatile(
- "0: .insn rre,0xb91e0000,%1,%1 \n" /* KLAC opcode */
- "1: brc 1,0b \n" /* handle partial completion */
+ "0: .insn rre,0xb91e0000,%1,%1\n" /* KLAC opcode */
+ "1: brc 1,0b\n" /* handle partial completion */
" la %0,0\n"
"2:\n"
- EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
: "=d" (ret), "+a" (__src), "+d" (__src_len)
: "d" (__func), "a" (__param), "0" (-1) : "cc", "memory");
if (ret < 0)
@@ -340,11 +353,11 @@ static inline int crypt_s390_kmctr(long func, void *param, u8 *dest,
int ret = -1;
asm volatile(
- "0: .insn rrf,0xb92d0000,%3,%1,%4,0 \n" /* KMCTR opcode */
- "1: brc 1,0b \n" /* handle partial completion */
+ "0: .insn rrf,0xb92d0000,%3,%1,%4,0\n" /* KMCTR opcode */
+ "1: brc 1,0b\n" /* handle partial completion */
" la %0,0\n"
"2:\n"
- EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
: "+d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest),
"+a" (__ctr)
: "d" (__func), "a" (__param) : "cc", "memory");
@@ -354,6 +367,47 @@ static inline int crypt_s390_kmctr(long func, void *param, u8 *dest,
}
/**
+ * crypt_s390_ppno:
+ * @func: the function code passed to PPNO; see crypt_s390_ppno_func
+ * @param: address of parameter block; see POP for details on each func
+ * @dest: address of destination memory area
+ * @dest_len: size of destination memory area in bytes
+ * @seed: address of seed data
+ * @seed_len: size of seed data in bytes
+ *
+ * Executes the PPNO (PERFORM PSEUDORANDOM NUMBER OPERATION)
+ * operation of the CPU.
+ *
+ * Returns -1 for failure, 0 for the query func, number of random
+ * bytes stored in dest buffer for generate function
+ */
+static inline int crypt_s390_ppno(long func, void *param,
+ u8 *dest, long dest_len,
+ const u8 *seed, long seed_len)
+{
+ register long __func asm("0") = func & CRYPT_S390_FUNC_MASK;
+ register void *__param asm("1") = param; /* param block (240 bytes) */
+ register u8 *__dest asm("2") = dest; /* buf for recv random bytes */
+ register long __dest_len asm("3") = dest_len; /* requested random bytes */
+ register const u8 *__seed asm("4") = seed; /* buf with seed data */
+ register long __seed_len asm("5") = seed_len; /* bytes in seed buf */
+ int ret = -1;
+
+ asm volatile (
+ "0: .insn rre,0xb93c0000,%1,%5\n" /* PPNO opcode */
+ "1: brc 1,0b\n" /* handle partial completion */
+ " la %0,0\n"
+ "2:\n"
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+ : "+d" (ret), "+a"(__dest), "+d"(__dest_len)
+ : "d"(__func), "a"(__param), "a"(__seed), "d"(__seed_len)
+ : "cc", "memory");
+ if (ret < 0)
+ return ret;
+ return (func & CRYPT_S390_FUNC_MASK) ? dest_len - __dest_len : 0;
+}
+
+/**
* crypt_s390_func_available:
* @func: the function code of the specific function; 0 if op in general
*
@@ -373,6 +427,9 @@ static inline int crypt_s390_func_available(int func,
return 0;
if (facility_mask & CRYPT_S390_MSA4 && !test_facility(77))
return 0;
+ if (facility_mask & CRYPT_S390_MSA5 && !test_facility(57))
+ return 0;
+
switch (func & CRYPT_S390_OP_MASK) {
case CRYPT_S390_KM:
ret = crypt_s390_km(KM_QUERY, &status, NULL, NULL, 0);
@@ -390,8 +447,12 @@ static inline int crypt_s390_func_available(int func,
ret = crypt_s390_kmac(KMAC_QUERY, &status, NULL, 0);
break;
case CRYPT_S390_KMCTR:
- ret = crypt_s390_kmctr(KMCTR_QUERY, &status, NULL, NULL, 0,
- NULL);
+ ret = crypt_s390_kmctr(KMCTR_QUERY, &status,
+ NULL, NULL, 0, NULL);
+ break;
+ case CRYPT_S390_PPNO:
+ ret = crypt_s390_ppno(PPNO_QUERY, &status,
+ NULL, 0, NULL, 0);
break;
default:
return 0;
@@ -419,15 +480,14 @@ static inline int crypt_s390_pcc(long func, void *param)
int ret = -1;
asm volatile(
- "0: .insn rre,0xb92c0000,0,0 \n" /* PCC opcode */
- "1: brc 1,0b \n" /* handle partial completion */
+ "0: .insn rre,0xb92c0000,0,0\n" /* PCC opcode */
+ "1: brc 1,0b\n" /* handle partial completion */
" la %0,0\n"
"2:\n"
- EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
: "+d" (ret)
: "d" (__func), "a" (__param) : "cc", "memory");
return ret;
}
-
#endif /* _CRYPTO_ARCH_S390_CRYPT_S390_H */
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 94a35a4c1b48..1f374b39a4ec 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -1,106 +1,529 @@
/*
- * Copyright IBM Corp. 2006, 2007
+ * Copyright IBM Corp. 2006, 2015
* Author(s): Jan Glauber <jan.glauber@de.ibm.com>
+ * Harald Freudenberger <freude@de.ibm.com>
* Driver for the s390 pseudo random number generator
*/
+
+#define KMSG_COMPONENT "prng"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
#include <linux/fs.h>
+#include <linux/fips.h>
#include <linux/init.h>
#include <linux/kernel.h>
+#include <linux/device.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
+#include <linux/mutex.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <asm/debug.h>
#include <asm/uaccess.h>
+#include <asm/timex.h>
#include "crypt_s390.h"
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Jan Glauber <jan.glauber@de.ibm.com>");
+MODULE_AUTHOR("IBM Corporation");
MODULE_DESCRIPTION("s390 PRNG interface");
-static int prng_chunk_size = 256;
-module_param(prng_chunk_size, int, S_IRUSR | S_IRGRP | S_IROTH);
+
+#define PRNG_MODE_AUTO 0
+#define PRNG_MODE_TDES 1
+#define PRNG_MODE_SHA512 2
+
+static unsigned int prng_mode = PRNG_MODE_AUTO;
+module_param_named(mode, prng_mode, int, 0);
+MODULE_PARM_DESC(prng_mode, "PRNG mode: 0 - auto, 1 - TDES, 2 - SHA512");
+
+
+#define PRNG_CHUNKSIZE_TDES_MIN 8
+#define PRNG_CHUNKSIZE_TDES_MAX (64*1024)
+#define PRNG_CHUNKSIZE_SHA512_MIN 64
+#define PRNG_CHUNKSIZE_SHA512_MAX (64*1024)
+
+static unsigned int prng_chunk_size = 256;
+module_param_named(chunksize, prng_chunk_size, int, 0);
MODULE_PARM_DESC(prng_chunk_size, "PRNG read chunk size in bytes");
-static int prng_entropy_limit = 4096;
-module_param(prng_entropy_limit, int, S_IRUSR | S_IRGRP | S_IROTH | S_IWUSR);
-MODULE_PARM_DESC(prng_entropy_limit,
- "PRNG add entropy after that much bytes were produced");
+
+#define PRNG_RESEED_LIMIT_TDES 4096
+#define PRNG_RESEED_LIMIT_TDES_LOWER 4096
+#define PRNG_RESEED_LIMIT_SHA512 100000
+#define PRNG_RESEED_LIMIT_SHA512_LOWER 10000
+
+static unsigned int prng_reseed_limit;
+module_param_named(reseed_limit, prng_reseed_limit, int, 0);
+MODULE_PARM_DESC(prng_reseed_limit, "PRNG reseed limit");
+
/*
* Any one who considers arithmetical methods of producing random digits is,
* of course, in a state of sin. -- John von Neumann
*/
-struct s390_prng_data {
- unsigned long count; /* how many bytes were produced */
- char *buf;
+static int prng_errorflag;
+
+#define PRNG_GEN_ENTROPY_FAILED 1
+#define PRNG_SELFTEST_FAILED 2
+#define PRNG_INSTANTIATE_FAILED 3
+#define PRNG_SEED_FAILED 4
+#define PRNG_RESEED_FAILED 5
+#define PRNG_GEN_FAILED 6
+
+struct prng_ws_s {
+ u8 parm_block[32];
+ u32 reseed_counter;
+ u64 byte_counter;
};
-static struct s390_prng_data *p;
+struct ppno_ws_s {
+ u32 res;
+ u32 reseed_counter;
+ u64 stream_bytes;
+ u8 V[112];
+ u8 C[112];
+};
-/* copied from libica, use a non-zero initial parameter block */
-static unsigned char parm_block[32] = {
-0x0F,0x2B,0x8E,0x63,0x8C,0x8E,0xD2,0x52,0x64,0xB7,0xA0,0x7B,0x75,0x28,0xB8,0xF4,
-0x75,0x5F,0xD2,0xA6,0x8D,0x97,0x11,0xFF,0x49,0xD8,0x23,0xF3,0x7E,0x21,0xEC,0xA0,
+struct prng_data_s {
+ struct mutex mutex;
+ union {
+ struct prng_ws_s prngws;
+ struct ppno_ws_s ppnows;
+ };
+ u8 *buf;
+ u32 rest;
+ u8 *prev;
};
-static int prng_open(struct inode *inode, struct file *file)
+static struct prng_data_s *prng_data;
+
+/* initial parameter block for tdes mode, copied from libica */
+static const u8 initial_parm_block[32] __initconst = {
+ 0x0F, 0x2B, 0x8E, 0x63, 0x8C, 0x8E, 0xD2, 0x52,
+ 0x64, 0xB7, 0xA0, 0x7B, 0x75, 0x28, 0xB8, 0xF4,
+ 0x75, 0x5F, 0xD2, 0xA6, 0x8D, 0x97, 0x11, 0xFF,
+ 0x49, 0xD8, 0x23, 0xF3, 0x7E, 0x21, 0xEC, 0xA0 };
+
+
+/*** helper functions ***/
+
+static int generate_entropy(u8 *ebuf, size_t nbytes)
{
- return nonseekable_open(inode, file);
+ int n, ret = 0;
+ u8 *pg, *h, hash[32];
+
+ pg = (u8 *) __get_free_page(GFP_KERNEL);
+ if (!pg) {
+ prng_errorflag = PRNG_GEN_ENTROPY_FAILED;
+ return -ENOMEM;
+ }
+
+ while (nbytes) {
+ /* fill page with urandom bytes */
+ get_random_bytes(pg, PAGE_SIZE);
+ /* exor page with stckf values */
+ for (n = 0; n < sizeof(PAGE_SIZE/sizeof(u64)); n++) {
+ u64 *p = ((u64 *)pg) + n;
+ *p ^= get_tod_clock_fast();
+ }
+ n = (nbytes < sizeof(hash)) ? nbytes : sizeof(hash);
+ if (n < sizeof(hash))
+ h = hash;
+ else
+ h = ebuf;
+ /* generate sha256 from this page */
+ if (crypt_s390_kimd(KIMD_SHA_256, h,
+ pg, PAGE_SIZE) != PAGE_SIZE) {
+ prng_errorflag = PRNG_GEN_ENTROPY_FAILED;
+ ret = -EIO;
+ goto out;
+ }
+ if (n < sizeof(hash))
+ memcpy(ebuf, hash, n);
+ ret += n;
+ ebuf += n;
+ nbytes -= n;
+ }
+
+out:
+ free_page((unsigned long)pg);
+ return ret;
}
-static void prng_add_entropy(void)
+
+/*** tdes functions ***/
+
+static void prng_tdes_add_entropy(void)
{
__u64 entropy[4];
unsigned int i;
int ret;
for (i = 0; i < 16; i++) {
- ret = crypt_s390_kmc(KMC_PRNG, parm_block, (char *)entropy,
- (char *)entropy, sizeof(entropy));
+ ret = crypt_s390_kmc(KMC_PRNG, prng_data->prngws.parm_block,
+ (char *)entropy, (char *)entropy,
+ sizeof(entropy));
BUG_ON(ret < 0 || ret != sizeof(entropy));
- memcpy(parm_block, entropy, sizeof(entropy));
+ memcpy(prng_data->prngws.parm_block, entropy, sizeof(entropy));
}
}
-static void prng_seed(int nbytes)
+
+static void prng_tdes_seed(int nbytes)
{
char buf[16];
int i = 0;
- BUG_ON(nbytes > 16);
+ BUG_ON(nbytes > sizeof(buf));
+
get_random_bytes(buf, nbytes);
/* Add the entropy */
while (nbytes >= 8) {
- *((__u64 *)parm_block) ^= *((__u64 *)(buf+i));
- prng_add_entropy();
+ *((__u64 *)prng_data->prngws.parm_block) ^= *((__u64 *)(buf+i));
+ prng_tdes_add_entropy();
i += 8;
nbytes -= 8;
}
- prng_add_entropy();
+ prng_tdes_add_entropy();
+ prng_data->prngws.reseed_counter = 0;
+}
+
+
+static int __init prng_tdes_instantiate(void)
+{
+ int datalen;
+
+ pr_debug("prng runs in TDES mode with "
+ "chunksize=%d and reseed_limit=%u\n",
+ prng_chunk_size, prng_reseed_limit);
+
+ /* memory allocation, prng_data struct init, mutex init */
+ datalen = sizeof(struct prng_data_s) + prng_chunk_size;
+ prng_data = kzalloc(datalen, GFP_KERNEL);
+ if (!prng_data) {
+ prng_errorflag = PRNG_INSTANTIATE_FAILED;
+ return -ENOMEM;
+ }
+ mutex_init(&prng_data->mutex);
+ prng_data->buf = ((u8 *)prng_data) + sizeof(struct prng_data_s);
+ memcpy(prng_data->prngws.parm_block, initial_parm_block, 32);
+
+ /* initialize the PRNG, add 128 bits of entropy */
+ prng_tdes_seed(16);
+
+ return 0;
}
-static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes,
- loff_t *ppos)
+
+static void prng_tdes_deinstantiate(void)
+{
+ pr_debug("The prng module stopped "
+ "after running in triple DES mode\n");
+ kzfree(prng_data);
+}
+
+
+/*** sha512 functions ***/
+
+static int __init prng_sha512_selftest(void)
{
- int chunk, n;
+ /* NIST DRBG testvector for Hash Drbg, Sha-512, Count #0 */
+ static const u8 seed[] __initconst = {
+ 0x6b, 0x50, 0xa7, 0xd8, 0xf8, 0xa5, 0x5d, 0x7a,
+ 0x3d, 0xf8, 0xbb, 0x40, 0xbc, 0xc3, 0xb7, 0x22,
+ 0xd8, 0x70, 0x8d, 0xe6, 0x7f, 0xda, 0x01, 0x0b,
+ 0x03, 0xc4, 0xc8, 0x4d, 0x72, 0x09, 0x6f, 0x8c,
+ 0x3e, 0xc6, 0x49, 0xcc, 0x62, 0x56, 0xd9, 0xfa,
+ 0x31, 0xdb, 0x7a, 0x29, 0x04, 0xaa, 0xf0, 0x25 };
+ static const u8 V0[] __initconst = {
+ 0x00, 0xad, 0xe3, 0x6f, 0x9a, 0x01, 0xc7, 0x76,
+ 0x61, 0x34, 0x35, 0xf5, 0x4e, 0x24, 0x74, 0x22,
+ 0x21, 0x9a, 0x29, 0x89, 0xc7, 0x93, 0x2e, 0x60,
+ 0x1e, 0xe8, 0x14, 0x24, 0x8d, 0xd5, 0x03, 0xf1,
+ 0x65, 0x5d, 0x08, 0x22, 0x72, 0xd5, 0xad, 0x95,
+ 0xe1, 0x23, 0x1e, 0x8a, 0xa7, 0x13, 0xd9, 0x2b,
+ 0x5e, 0xbc, 0xbb, 0x80, 0xab, 0x8d, 0xe5, 0x79,
+ 0xab, 0x5b, 0x47, 0x4e, 0xdd, 0xee, 0x6b, 0x03,
+ 0x8f, 0x0f, 0x5c, 0x5e, 0xa9, 0x1a, 0x83, 0xdd,
+ 0xd3, 0x88, 0xb2, 0x75, 0x4b, 0xce, 0x83, 0x36,
+ 0x57, 0x4b, 0xf1, 0x5c, 0xca, 0x7e, 0x09, 0xc0,
+ 0xd3, 0x89, 0xc6, 0xe0, 0xda, 0xc4, 0x81, 0x7e,
+ 0x5b, 0xf9, 0xe1, 0x01, 0xc1, 0x92, 0x05, 0xea,
+ 0xf5, 0x2f, 0xc6, 0xc6, 0xc7, 0x8f, 0xbc, 0xf4 };
+ static const u8 C0[] __initconst = {
+ 0x00, 0xf4, 0xa3, 0xe5, 0xa0, 0x72, 0x63, 0x95,
+ 0xc6, 0x4f, 0x48, 0xd0, 0x8b, 0x5b, 0x5f, 0x8e,
+ 0x6b, 0x96, 0x1f, 0x16, 0xed, 0xbc, 0x66, 0x94,
+ 0x45, 0x31, 0xd7, 0x47, 0x73, 0x22, 0xa5, 0x86,
+ 0xce, 0xc0, 0x4c, 0xac, 0x63, 0xb8, 0x39, 0x50,
+ 0xbf, 0xe6, 0x59, 0x6c, 0x38, 0x58, 0x99, 0x1f,
+ 0x27, 0xa7, 0x9d, 0x71, 0x2a, 0xb3, 0x7b, 0xf9,
+ 0xfb, 0x17, 0x86, 0xaa, 0x99, 0x81, 0xaa, 0x43,
+ 0xe4, 0x37, 0xd3, 0x1e, 0x6e, 0xe5, 0xe6, 0xee,
+ 0xc2, 0xed, 0x95, 0x4f, 0x53, 0x0e, 0x46, 0x8a,
+ 0xcc, 0x45, 0xa5, 0xdb, 0x69, 0x0d, 0x81, 0xc9,
+ 0x32, 0x92, 0xbc, 0x8f, 0x33, 0xe6, 0xf6, 0x09,
+ 0x7c, 0x8e, 0x05, 0x19, 0x0d, 0xf1, 0xb6, 0xcc,
+ 0xf3, 0x02, 0x21, 0x90, 0x25, 0xec, 0xed, 0x0e };
+ static const u8 random[] __initconst = {
+ 0x95, 0xb7, 0xf1, 0x7e, 0x98, 0x02, 0xd3, 0x57,
+ 0x73, 0x92, 0xc6, 0xa9, 0xc0, 0x80, 0x83, 0xb6,
+ 0x7d, 0xd1, 0x29, 0x22, 0x65, 0xb5, 0xf4, 0x2d,
+ 0x23, 0x7f, 0x1c, 0x55, 0xbb, 0x9b, 0x10, 0xbf,
+ 0xcf, 0xd8, 0x2c, 0x77, 0xa3, 0x78, 0xb8, 0x26,
+ 0x6a, 0x00, 0x99, 0x14, 0x3b, 0x3c, 0x2d, 0x64,
+ 0x61, 0x1e, 0xee, 0xb6, 0x9a, 0xcd, 0xc0, 0x55,
+ 0x95, 0x7c, 0x13, 0x9e, 0x8b, 0x19, 0x0c, 0x7a,
+ 0x06, 0x95, 0x5f, 0x2c, 0x79, 0x7c, 0x27, 0x78,
+ 0xde, 0x94, 0x03, 0x96, 0xa5, 0x01, 0xf4, 0x0e,
+ 0x91, 0x39, 0x6a, 0xcf, 0x8d, 0x7e, 0x45, 0xeb,
+ 0xdb, 0xb5, 0x3b, 0xbf, 0x8c, 0x97, 0x52, 0x30,
+ 0xd2, 0xf0, 0xff, 0x91, 0x06, 0xc7, 0x61, 0x19,
+ 0xae, 0x49, 0x8e, 0x7f, 0xbc, 0x03, 0xd9, 0x0f,
+ 0x8e, 0x4c, 0x51, 0x62, 0x7a, 0xed, 0x5c, 0x8d,
+ 0x42, 0x63, 0xd5, 0xd2, 0xb9, 0x78, 0x87, 0x3a,
+ 0x0d, 0xe5, 0x96, 0xee, 0x6d, 0xc7, 0xf7, 0xc2,
+ 0x9e, 0x37, 0xee, 0xe8, 0xb3, 0x4c, 0x90, 0xdd,
+ 0x1c, 0xf6, 0xa9, 0xdd, 0xb2, 0x2b, 0x4c, 0xbd,
+ 0x08, 0x6b, 0x14, 0xb3, 0x5d, 0xe9, 0x3d, 0xa2,
+ 0xd5, 0xcb, 0x18, 0x06, 0x69, 0x8c, 0xbd, 0x7b,
+ 0xbb, 0x67, 0xbf, 0xe3, 0xd3, 0x1f, 0xd2, 0xd1,
+ 0xdb, 0xd2, 0xa1, 0xe0, 0x58, 0xa3, 0xeb, 0x99,
+ 0xd7, 0xe5, 0x1f, 0x1a, 0x93, 0x8e, 0xed, 0x5e,
+ 0x1c, 0x1d, 0xe2, 0x3a, 0x6b, 0x43, 0x45, 0xd3,
+ 0x19, 0x14, 0x09, 0xf9, 0x2f, 0x39, 0xb3, 0x67,
+ 0x0d, 0x8d, 0xbf, 0xb6, 0x35, 0xd8, 0xe6, 0xa3,
+ 0x69, 0x32, 0xd8, 0x10, 0x33, 0xd1, 0x44, 0x8d,
+ 0x63, 0xb4, 0x03, 0xdd, 0xf8, 0x8e, 0x12, 0x1b,
+ 0x6e, 0x81, 0x9a, 0xc3, 0x81, 0x22, 0x6c, 0x13,
+ 0x21, 0xe4, 0xb0, 0x86, 0x44, 0xf6, 0x72, 0x7c,
+ 0x36, 0x8c, 0x5a, 0x9f, 0x7a, 0x4b, 0x3e, 0xe2 };
+
int ret = 0;
- int tmp;
+ u8 buf[sizeof(random)];
+ struct ppno_ws_s ws;
+
+ memset(&ws, 0, sizeof(ws));
+
+ /* initial seed */
+ ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED,
+ &ws, NULL, 0,
+ seed, sizeof(seed));
+ if (ret < 0) {
+ pr_err("The prng self test seed operation for the "
+ "SHA-512 mode failed with rc=%d\n", ret);
+ prng_errorflag = PRNG_SELFTEST_FAILED;
+ return -EIO;
+ }
+
+ /* check working states V and C */
+ if (memcmp(ws.V, V0, sizeof(V0)) != 0
+ || memcmp(ws.C, C0, sizeof(C0)) != 0) {
+ pr_err("The prng self test state test "
+ "for the SHA-512 mode failed\n");
+ prng_errorflag = PRNG_SELFTEST_FAILED;
+ return -EIO;
+ }
+
+ /* generate random bytes */
+ ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN,
+ &ws, buf, sizeof(buf),
+ NULL, 0);
+ if (ret < 0) {
+ pr_err("The prng self test generate operation for "
+ "the SHA-512 mode failed with rc=%d\n", ret);
+ prng_errorflag = PRNG_SELFTEST_FAILED;
+ return -EIO;
+ }
+ ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN,
+ &ws, buf, sizeof(buf),
+ NULL, 0);
+ if (ret < 0) {
+ pr_err("The prng self test generate operation for "
+ "the SHA-512 mode failed with rc=%d\n", ret);
+ prng_errorflag = PRNG_SELFTEST_FAILED;
+ return -EIO;
+ }
+
+ /* check against expected data */
+ if (memcmp(buf, random, sizeof(random)) != 0) {
+ pr_err("The prng self test data test "
+ "for the SHA-512 mode failed\n");
+ prng_errorflag = PRNG_SELFTEST_FAILED;
+ return -EIO;
+ }
+
+ return 0;
+}
+
+
+static int __init prng_sha512_instantiate(void)
+{
+ int ret, datalen;
+ u8 seed[64];
+
+ pr_debug("prng runs in SHA-512 mode "
+ "with chunksize=%d and reseed_limit=%u\n",
+ prng_chunk_size, prng_reseed_limit);
+
+ /* memory allocation, prng_data struct init, mutex init */
+ datalen = sizeof(struct prng_data_s) + prng_chunk_size;
+ if (fips_enabled)
+ datalen += prng_chunk_size;
+ prng_data = kzalloc(datalen, GFP_KERNEL);
+ if (!prng_data) {
+ prng_errorflag = PRNG_INSTANTIATE_FAILED;
+ return -ENOMEM;
+ }
+ mutex_init(&prng_data->mutex);
+ prng_data->buf = ((u8 *)prng_data) + sizeof(struct prng_data_s);
+
+ /* selftest */
+ ret = prng_sha512_selftest();
+ if (ret)
+ goto outfree;
+
+ /* generate initial seed bytestring, first 48 bytes of entropy */
+ ret = generate_entropy(seed, 48);
+ if (ret != 48)
+ goto outfree;
+ /* followed by 16 bytes of unique nonce */
+ get_tod_clock_ext(seed + 48);
+
+ /* initial seed of the ppno drng */
+ ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED,
+ &prng_data->ppnows, NULL, 0,
+ seed, sizeof(seed));
+ if (ret < 0) {
+ prng_errorflag = PRNG_SEED_FAILED;
+ ret = -EIO;
+ goto outfree;
+ }
+
+ /* if fips mode is enabled, generate a first block of random
+ bytes for the FIPS 140-2 Conditional Self Test */
+ if (fips_enabled) {
+ prng_data->prev = prng_data->buf + prng_chunk_size;
+ ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN,
+ &prng_data->ppnows,
+ prng_data->prev,
+ prng_chunk_size,
+ NULL, 0);
+ if (ret < 0 || ret != prng_chunk_size) {
+ prng_errorflag = PRNG_GEN_FAILED;
+ ret = -EIO;
+ goto outfree;
+ }
+ }
+
+ return 0;
+
+outfree:
+ kfree(prng_data);
+ return ret;
+}
+
+
+static void prng_sha512_deinstantiate(void)
+{
+ pr_debug("The prng module stopped after running in SHA-512 mode\n");
+ kzfree(prng_data);
+}
+
+
+static int prng_sha512_reseed(void)
+{
+ int ret;
+ u8 seed[32];
+
+ /* generate 32 bytes of fresh entropy */
+ ret = generate_entropy(seed, sizeof(seed));
+ if (ret != sizeof(seed))
+ return ret;
+
+ /* do a reseed of the ppno drng with this bytestring */
+ ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED,
+ &prng_data->ppnows, NULL, 0,
+ seed, sizeof(seed));
+ if (ret) {
+ prng_errorflag = PRNG_RESEED_FAILED;
+ return -EIO;
+ }
+
+ return 0;
+}
+
+
+static int prng_sha512_generate(u8 *buf, size_t nbytes)
+{
+ int ret;
+
+ /* reseed needed ? */
+ if (prng_data->ppnows.reseed_counter > prng_reseed_limit) {
+ ret = prng_sha512_reseed();
+ if (ret)
+ return ret;
+ }
+
+ /* PPNO generate */
+ ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN,
+ &prng_data->ppnows, buf, nbytes,
+ NULL, 0);
+ if (ret < 0 || ret != nbytes) {
+ prng_errorflag = PRNG_GEN_FAILED;
+ return -EIO;
+ }
+
+ /* FIPS 140-2 Conditional Self Test */
+ if (fips_enabled) {
+ if (!memcmp(prng_data->prev, buf, nbytes)) {
+ prng_errorflag = PRNG_GEN_FAILED;
+ return -EILSEQ;
+ }
+ memcpy(prng_data->prev, buf, nbytes);
+ }
+
+ return ret;
+}
+
+
+/*** file io functions ***/
+
+static int prng_open(struct inode *inode, struct file *file)
+{
+ return nonseekable_open(inode, file);
+}
+
+
+static ssize_t prng_tdes_read(struct file *file, char __user *ubuf,
+ size_t nbytes, loff_t *ppos)
+{
+ int chunk, n, tmp, ret = 0;
+
+ /* lock prng_data struct */
+ if (mutex_lock_interruptible(&prng_data->mutex))
+ return -ERESTARTSYS;
- /* nbytes can be arbitrary length, we split it into chunks */
while (nbytes) {
- /* same as in extract_entropy_user in random.c */
if (need_resched()) {
if (signal_pending(current)) {
if (ret == 0)
ret = -ERESTARTSYS;
break;
}
+ /* give mutex free before calling schedule() */
+ mutex_unlock(&prng_data->mutex);
schedule();
+ /* occopy mutex again */
+ if (mutex_lock_interruptible(&prng_data->mutex)) {
+ if (ret == 0)
+ ret = -ERESTARTSYS;
+ return ret;
+ }
}
/*
@@ -112,12 +535,11 @@ static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes,
/* PRNG only likes multiples of 8 bytes */
n = (chunk + 7) & -8;
- if (p->count > prng_entropy_limit)
- prng_seed(8);
+ if (prng_data->prngws.reseed_counter > prng_reseed_limit)
+ prng_tdes_seed(8);
/* if the CPU supports PRNG stckf is present too */
- asm volatile(".insn s,0xb27c0000,%0"
- : "=m" (*((unsigned long long *)p->buf)) : : "cc");
+ *((unsigned long long *)prng_data->buf) = get_tod_clock_fast();
/*
* Beside the STCKF the input for the TDES-EDE is the output
@@ -132,35 +554,259 @@ static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes,
* Note: you can still get strict X9.17 conformity by setting
* prng_chunk_size to 8 bytes.
*/
- tmp = crypt_s390_kmc(KMC_PRNG, parm_block, p->buf, p->buf, n);
- BUG_ON((tmp < 0) || (tmp != n));
+ tmp = crypt_s390_kmc(KMC_PRNG, prng_data->prngws.parm_block,
+ prng_data->buf, prng_data->buf, n);
+ if (tmp < 0 || tmp != n) {
+ ret = -EIO;
+ break;
+ }
- p->count += n;
+ prng_data->prngws.byte_counter += n;
+ prng_data->prngws.reseed_counter += n;
- if (copy_to_user(ubuf, p->buf, chunk))
+ if (copy_to_user(ubuf, prng_data->buf, chunk))
return -EFAULT;
nbytes -= chunk;
ret += chunk;
ubuf += chunk;
}
+
+ /* unlock prng_data struct */
+ mutex_unlock(&prng_data->mutex);
+
return ret;
}
-static const struct file_operations prng_fops = {
+
+static ssize_t prng_sha512_read(struct file *file, char __user *ubuf,
+ size_t nbytes, loff_t *ppos)
+{
+ int n, ret = 0;
+ u8 *p;
+
+ /* if errorflag is set do nothing and return 'broken pipe' */
+ if (prng_errorflag)
+ return -EPIPE;
+
+ /* lock prng_data struct */
+ if (mutex_lock_interruptible(&prng_data->mutex))
+ return -ERESTARTSYS;
+
+ while (nbytes) {
+ if (need_resched()) {
+ if (signal_pending(current)) {
+ if (ret == 0)
+ ret = -ERESTARTSYS;
+ break;
+ }
+ /* give mutex free before calling schedule() */
+ mutex_unlock(&prng_data->mutex);
+ schedule();
+ /* occopy mutex again */
+ if (mutex_lock_interruptible(&prng_data->mutex)) {
+ if (ret == 0)
+ ret = -ERESTARTSYS;
+ return ret;
+ }
+ }
+ if (prng_data->rest) {
+ /* push left over random bytes from the previous read */
+ p = prng_data->buf + prng_chunk_size - prng_data->rest;
+ n = (nbytes < prng_data->rest) ?
+ nbytes : prng_data->rest;
+ prng_data->rest -= n;
+ } else {
+ /* generate one chunk of random bytes into read buf */
+ p = prng_data->buf;
+ n = prng_sha512_generate(p, prng_chunk_size);
+ if (n < 0) {
+ ret = n;
+ break;
+ }
+ if (nbytes < prng_chunk_size) {
+ n = nbytes;
+ prng_data->rest = prng_chunk_size - n;
+ } else {
+ n = prng_chunk_size;
+ prng_data->rest = 0;
+ }
+ }
+ if (copy_to_user(ubuf, p, n)) {
+ ret = -EFAULT;
+ break;
+ }
+ ubuf += n;
+ nbytes -= n;
+ ret += n;
+ }
+
+ /* unlock prng_data struct */
+ mutex_unlock(&prng_data->mutex);
+
+ return ret;
+}
+
+
+/*** sysfs stuff ***/
+
+static const struct file_operations prng_sha512_fops = {
+ .owner = THIS_MODULE,
+ .open = &prng_open,
+ .release = NULL,
+ .read = &prng_sha512_read,
+ .llseek = noop_llseek,
+};
+static const struct file_operations prng_tdes_fops = {
.owner = THIS_MODULE,
.open = &prng_open,
.release = NULL,
- .read = &prng_read,
+ .read = &prng_tdes_read,
.llseek = noop_llseek,
};
-static struct miscdevice prng_dev = {
+static struct miscdevice prng_sha512_dev = {
+ .name = "prandom",
+ .minor = MISC_DYNAMIC_MINOR,
+ .fops = &prng_sha512_fops,
+};
+static struct miscdevice prng_tdes_dev = {
.name = "prandom",
.minor = MISC_DYNAMIC_MINOR,
- .fops = &prng_fops,
+ .fops = &prng_tdes_fops,
};
+
+/* chunksize attribute (ro) */
+static ssize_t prng_chunksize_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size);
+}
+static DEVICE_ATTR(chunksize, 0444, prng_chunksize_show, NULL);
+
+/* counter attribute (ro) */
+static ssize_t prng_counter_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ u64 counter;
+
+ if (mutex_lock_interruptible(&prng_data->mutex))
+ return -ERESTARTSYS;
+ if (prng_mode == PRNG_MODE_SHA512)
+ counter = prng_data->ppnows.stream_bytes;
+ else
+ counter = prng_data->prngws.byte_counter;
+ mutex_unlock(&prng_data->mutex);
+
+ return snprintf(buf, PAGE_SIZE, "%llu\n", counter);
+}
+static DEVICE_ATTR(byte_counter, 0444, prng_counter_show, NULL);
+
+/* errorflag attribute (ro) */
+static ssize_t prng_errorflag_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag);
+}
+static DEVICE_ATTR(errorflag, 0444, prng_errorflag_show, NULL);
+
+/* mode attribute (ro) */
+static ssize_t prng_mode_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ if (prng_mode == PRNG_MODE_TDES)
+ return snprintf(buf, PAGE_SIZE, "TDES\n");
+ else
+ return snprintf(buf, PAGE_SIZE, "SHA512\n");
+}
+static DEVICE_ATTR(mode, 0444, prng_mode_show, NULL);
+
+/* reseed attribute (w) */
+static ssize_t prng_reseed_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ if (mutex_lock_interruptible(&prng_data->mutex))
+ return -ERESTARTSYS;
+ prng_sha512_reseed();
+ mutex_unlock(&prng_data->mutex);
+
+ return count;
+}
+static DEVICE_ATTR(reseed, 0200, NULL, prng_reseed_store);
+
+/* reseed limit attribute (rw) */
+static ssize_t prng_reseed_limit_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit);
+}
+static ssize_t prng_reseed_limit_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned limit;
+
+ if (sscanf(buf, "%u\n", &limit) != 1)
+ return -EINVAL;
+
+ if (prng_mode == PRNG_MODE_SHA512) {
+ if (limit < PRNG_RESEED_LIMIT_SHA512_LOWER)
+ return -EINVAL;
+ } else {
+ if (limit < PRNG_RESEED_LIMIT_TDES_LOWER)
+ return -EINVAL;
+ }
+
+ prng_reseed_limit = limit;
+
+ return count;
+}
+static DEVICE_ATTR(reseed_limit, 0644,
+ prng_reseed_limit_show, prng_reseed_limit_store);
+
+/* strength attribute (ro) */
+static ssize_t prng_strength_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "256\n");
+}
+static DEVICE_ATTR(strength, 0444, prng_strength_show, NULL);
+
+static struct attribute *prng_sha512_dev_attrs[] = {
+ &dev_attr_errorflag.attr,
+ &dev_attr_chunksize.attr,
+ &dev_attr_byte_counter.attr,
+ &dev_attr_mode.attr,
+ &dev_attr_reseed.attr,
+ &dev_attr_reseed_limit.attr,
+ &dev_attr_strength.attr,
+ NULL
+};
+static struct attribute *prng_tdes_dev_attrs[] = {
+ &dev_attr_chunksize.attr,
+ &dev_attr_byte_counter.attr,
+ &dev_attr_mode.attr,
+ NULL
+};
+
+static struct attribute_group prng_sha512_dev_attr_group = {
+ .attrs = prng_sha512_dev_attrs
+};
+static struct attribute_group prng_tdes_dev_attr_group = {
+ .attrs = prng_tdes_dev_attrs
+};
+
+
+/*** module init and exit ***/
+
static int __init prng_init(void)
{
int ret;
@@ -169,43 +815,105 @@ static int __init prng_init(void)
if (!crypt_s390_func_available(KMC_PRNG, CRYPT_S390_MSA))
return -EOPNOTSUPP;
- if (prng_chunk_size < 8)
- return -EINVAL;
+ /* choose prng mode */
+ if (prng_mode != PRNG_MODE_TDES) {
+ /* check for MSA5 support for PPNO operations */
+ if (!crypt_s390_func_available(PPNO_SHA512_DRNG_GEN,
+ CRYPT_S390_MSA5)) {
+ if (prng_mode == PRNG_MODE_SHA512) {
+ pr_err("The prng module cannot "
+ "start in SHA-512 mode\n");
+ return -EOPNOTSUPP;
+ }
+ prng_mode = PRNG_MODE_TDES;
+ } else
+ prng_mode = PRNG_MODE_SHA512;
+ }
- p = kmalloc(sizeof(struct s390_prng_data), GFP_KERNEL);
- if (!p)
- return -ENOMEM;
- p->count = 0;
+ if (prng_mode == PRNG_MODE_SHA512) {
- p->buf = kmalloc(prng_chunk_size, GFP_KERNEL);
- if (!p->buf) {
- ret = -ENOMEM;
- goto out_free;
- }
+ /* SHA512 mode */
- /* initialize the PRNG, add 128 bits of entropy */
- prng_seed(16);
+ if (prng_chunk_size < PRNG_CHUNKSIZE_SHA512_MIN
+ || prng_chunk_size > PRNG_CHUNKSIZE_SHA512_MAX)
+ return -EINVAL;
+ prng_chunk_size = (prng_chunk_size + 0x3f) & ~0x3f;
- ret = misc_register(&prng_dev);
- if (ret)
- goto out_buf;
- return 0;
+ if (prng_reseed_limit == 0)
+ prng_reseed_limit = PRNG_RESEED_LIMIT_SHA512;
+ else if (prng_reseed_limit < PRNG_RESEED_LIMIT_SHA512_LOWER)
+ return -EINVAL;
+
+ ret = prng_sha512_instantiate();
+ if (ret)
+ goto out;
+
+ ret = misc_register(&prng_sha512_dev);
+ if (ret) {
+ prng_sha512_deinstantiate();
+ goto out;
+ }
+ ret = sysfs_create_group(&prng_sha512_dev.this_device->kobj,
+ &prng_sha512_dev_attr_group);
+ if (ret) {
+ misc_deregister(&prng_sha512_dev);
+ prng_sha512_deinstantiate();
+ goto out;
+ }
-out_buf:
- kfree(p->buf);
-out_free:
- kfree(p);
+ } else {
+
+ /* TDES mode */
+
+ if (prng_chunk_size < PRNG_CHUNKSIZE_TDES_MIN
+ || prng_chunk_size > PRNG_CHUNKSIZE_TDES_MAX)
+ return -EINVAL;
+ prng_chunk_size = (prng_chunk_size + 0x07) & ~0x07;
+
+ if (prng_reseed_limit == 0)
+ prng_reseed_limit = PRNG_RESEED_LIMIT_TDES;
+ else if (prng_reseed_limit < PRNG_RESEED_LIMIT_TDES_LOWER)
+ return -EINVAL;
+
+ ret = prng_tdes_instantiate();
+ if (ret)
+ goto out;
+
+ ret = misc_register(&prng_tdes_dev);
+ if (ret) {
+ prng_tdes_deinstantiate();
+ goto out;
+ }
+ ret = sysfs_create_group(&prng_tdes_dev.this_device->kobj,
+ &prng_tdes_dev_attr_group);
+ if (ret) {
+ misc_deregister(&prng_tdes_dev);
+ prng_tdes_deinstantiate();
+ goto out;
+ }
+
+ }
+
+out:
return ret;
}
+
static void __exit prng_exit(void)
{
- /* wipe me */
- kzfree(p->buf);
- kfree(p);
-
- misc_deregister(&prng_dev);
+ if (prng_mode == PRNG_MODE_SHA512) {
+ sysfs_remove_group(&prng_sha512_dev.this_device->kobj,
+ &prng_sha512_dev_attr_group);
+ misc_deregister(&prng_sha512_dev);
+ prng_sha512_deinstantiate();
+ } else {
+ sysfs_remove_group(&prng_tdes_dev.this_device->kobj,
+ &prng_tdes_dev_attr_group);
+ misc_deregister(&prng_tdes_dev);
+ prng_tdes_deinstantiate();
+ }
}
+
module_init(prng_init);
module_exit(prng_exit);
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 694bcd6bd927..2f924bc30e35 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -26,6 +26,9 @@
/* Not more than 2GB */
#define KEXEC_CONTROL_MEMORY_LIMIT (1UL<<31)
+/* Allocate control page with GFP_DMA */
+#define KEXEC_CONTROL_MEMORY_GFP GFP_DMA
+
/* Maximum address we can use for the crash control pages */
#define KEXEC_CRASH_CONTROL_MEMORY_LIMIT (-1UL)
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index a5e656260a70..d29ad9545b41 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -14,7 +14,9 @@ typedef struct {
unsigned long asce_bits;
unsigned long asce_limit;
unsigned long vdso_base;
- /* The mmu context has extended page tables. */
+ /* The mmu context allocates 4K page tables. */
+ unsigned int alloc_pgste:1;
+ /* The mmu context uses extended page tables. */
unsigned int has_pgste:1;
/* The mmu context uses storage keys. */
unsigned int use_skey:1;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index d25d9ff10ba8..fb1b93ea3e3f 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -20,8 +20,11 @@ static inline int init_new_context(struct task_struct *tsk,
mm->context.flush_mm = 0;
mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
mm->context.asce_bits |= _ASCE_TYPE_REGION3;
+#ifdef CONFIG_PGSTE
+ mm->context.alloc_pgste = page_table_allocate_pgste;
mm->context.has_pgste = 0;
mm->context.use_skey = 0;
+#endif
mm->context.asce_limit = STACK_TOP_MAX;
crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
return 0;
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 51e7fb634ebc..7b7858f158b4 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -21,6 +21,7 @@ void crst_table_free(struct mm_struct *, unsigned long *);
unsigned long *page_table_alloc(struct mm_struct *);
void page_table_free(struct mm_struct *, unsigned long *);
void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
+extern int page_table_allocate_pgste;
int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
unsigned long key, bool nq);
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 989cfae9e202..fc642399b489 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -12,12 +12,9 @@
#define _ASM_S390_PGTABLE_H
/*
- * The Linux memory management assumes a three-level page table setup. For
- * s390 31 bit we "fold" the mid level into the top-level page table, so
- * that we physically have the same two-level page table as the s390 mmu
- * expects in 31 bit mode. For s390 64 bit we use three of the five levels
- * the hardware provides (region first and region second tables are not
- * used).
+ * The Linux memory management assumes a three-level page table setup.
+ * For s390 64 bit we use up to four of the five levels the hardware
+ * provides (region first tables are not used).
*
* The "pgd_xxx()" functions are trivial for a folded two-level
* setup: the pgd is never bad, and a pmd always exists (as it's folded
@@ -101,8 +98,8 @@ extern unsigned long zero_page_mask;
#ifndef __ASSEMBLY__
/*
- * The vmalloc and module area will always be on the topmost area of the kernel
- * mapping. We reserve 96MB (31bit) / 128GB (64bit) for vmalloc and modules.
+ * The vmalloc and module area will always be on the topmost area of the
+ * kernel mapping. We reserve 128GB (64bit) for vmalloc and modules.
* On 64 bit kernels we have a 2GB area at the top of the vmalloc area where
* modules will reside. That makes sure that inter module branches always
* happen without trampolines and in addition the placement within a 2GB frame
@@ -131,38 +128,6 @@ static inline int is_module_addr(void *addr)
}
/*
- * A 31 bit pagetable entry of S390 has following format:
- * | PFRA | | OS |
- * 0 0IP0
- * 00000000001111111111222222222233
- * 01234567890123456789012345678901
- *
- * I Page-Invalid Bit: Page is not available for address-translation
- * P Page-Protection Bit: Store access not possible for page
- *
- * A 31 bit segmenttable entry of S390 has following format:
- * | P-table origin | |PTL
- * 0 IC
- * 00000000001111111111222222222233
- * 01234567890123456789012345678901
- *
- * I Segment-Invalid Bit: Segment is not available for address-translation
- * C Common-Segment Bit: Segment is not private (PoP 3-30)
- * PTL Page-Table-Length: Page-table length (PTL+1*16 entries -> up to 256)
- *
- * The 31 bit segmenttable origin of S390 has following format:
- *
- * |S-table origin | | STL |
- * X **GPS
- * 00000000001111111111222222222233
- * 01234567890123456789012345678901
- *
- * X Space-Switch event:
- * G Segment-Invalid Bit: *
- * P Private-Space Bit: Segment is not private (PoP 3-30)
- * S Storage-Alteration:
- * STL Segment-Table-Length: Segment-table length (STL+1*16 entries -> up to 2048)
- *
* A 64 bit pagetable entry of S390 has following format:
* | PFRA |0IPC| OS |
* 0000000000111111111122222222223333333333444444444455555555556666
@@ -220,7 +185,6 @@ static inline int is_module_addr(void *addr)
/* Software bits in the page table entry */
#define _PAGE_PRESENT 0x001 /* SW pte present bit */
-#define _PAGE_TYPE 0x002 /* SW pte type bit */
#define _PAGE_YOUNG 0x004 /* SW pte young bit */
#define _PAGE_DIRTY 0x008 /* SW pte dirty bit */
#define _PAGE_READ 0x010 /* SW pte read bit */
@@ -240,31 +204,34 @@ static inline int is_module_addr(void *addr)
* table lock held.
*
* The following table gives the different possible bit combinations for
- * the pte hardware and software bits in the last 12 bits of a pte:
+ * the pte hardware and software bits in the last 12 bits of a pte
+ * (. unassigned bit, x don't care, t swap type):
*
* 842100000000
* 000084210000
* 000000008421
- * .IR...wrdytp
- * empty .10...000000
- * swap .10...xxxx10
- * file .11...xxxxx0
- * prot-none, clean, old .11...000001
- * prot-none, clean, young .11...000101
- * prot-none, dirty, old .10...001001
- * prot-none, dirty, young .10...001101
- * read-only, clean, old .11...010001
- * read-only, clean, young .01...010101
- * read-only, dirty, old .11...011001
- * read-only, dirty, young .01...011101
- * read-write, clean, old .11...110001
- * read-write, clean, young .01...110101
- * read-write, dirty, old .10...111001
- * read-write, dirty, young .00...111101
+ * .IR.uswrdy.p
+ * empty .10.00000000
+ * swap .11..ttttt.0
+ * prot-none, clean, old .11.xx0000.1
+ * prot-none, clean, young .11.xx0001.1
+ * prot-none, dirty, old .10.xx0010.1
+ * prot-none, dirty, young .10.xx0011.1
+ * read-only, clean, old .11.xx0100.1
+ * read-only, clean, young .01.xx0101.1
+ * read-only, dirty, old .11.xx0110.1
+ * read-only, dirty, young .01.xx0111.1
+ * read-write, clean, old .11.xx1100.1
+ * read-write, clean, young .01.xx1101.1
+ * read-write, dirty, old .10.xx1110.1
+ * read-write, dirty, young .00.xx1111.1
+ * HW-bits: R read-only, I invalid
+ * SW-bits: p present, y young, d dirty, r read, w write, s special,
+ * u unused, l large
*
- * pte_present is true for the bit pattern .xx...xxxxx1, (pte & 0x001) == 0x001
- * pte_none is true for the bit pattern .10...xxxx00, (pte & 0x603) == 0x400
- * pte_swap is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402
+ * pte_none is true for the bit pattern .10.00000000, pte == 0x400
+ * pte_swap is true for the bit pattern .11..ooooo.0, (pte & 0x201) == 0x200
+ * pte_present is true for the bit pattern .xx.xxxxxx.1, (pte & 0x001) == 0x001
*/
/* Bits in the segment/region table address-space-control-element */
@@ -335,6 +302,8 @@ static inline int is_module_addr(void *addr)
* read-write, dirty, young 11..0...0...11
* The segment table origin is used to distinguish empty (origin==0) from
* read-write, old segment table entries (origin!=0)
+ * HW-bits: R read-only, I invalid
+ * SW-bits: y young, d dirty, r read, w write
*/
#define _SEGMENT_ENTRY_SPLIT_BIT 11 /* THP splitting bit number */
@@ -423,6 +392,15 @@ static inline int mm_has_pgste(struct mm_struct *mm)
return 0;
}
+static inline int mm_alloc_pgste(struct mm_struct *mm)
+{
+#ifdef CONFIG_PGSTE
+ if (unlikely(mm->context.alloc_pgste))
+ return 1;
+#endif
+ return 0;
+}
+
/*
* In the case that a guest uses storage keys
* faults should no longer be backed by zero pages
@@ -582,10 +560,9 @@ static inline int pte_none(pte_t pte)
static inline int pte_swap(pte_t pte)
{
- /* Bit pattern: (pte & 0x603) == 0x402 */
- return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT |
- _PAGE_TYPE | _PAGE_PRESENT))
- == (_PAGE_INVALID | _PAGE_TYPE);
+ /* Bit pattern: (pte & 0x201) == 0x200 */
+ return (pte_val(pte) & (_PAGE_PROTECT | _PAGE_PRESENT))
+ == _PAGE_PROTECT;
}
static inline int pte_special(pte_t pte)
@@ -1586,51 +1563,51 @@ static inline int has_transparent_hugepage(void)
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * 31 bit swap entry format:
- * A page-table entry has some bits we have to treat in a special way.
- * Bits 0, 20 and bit 23 have to be zero, otherwise an specification
- * exception will occur instead of a page translation exception. The
- * specifiation exception has the bad habit not to store necessary
- * information in the lowcore.
- * Bits 21, 22, 30 and 31 are used to indicate the page type.
- * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402
- * This leaves the bits 1-19 and bits 24-29 to store type and offset.
- * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19
- * plus 24 for the offset.
- * 0| offset |0110|o|type |00|
- * 0 0000000001111111111 2222 2 22222 33
- * 0 1234567890123456789 0123 4 56789 01
- *
* 64 bit swap entry format:
* A page-table entry has some bits we have to treat in a special way.
* Bits 52 and bit 55 have to be zero, otherwise an specification
* exception will occur instead of a page translation exception. The
* specifiation exception has the bad habit not to store necessary
* information in the lowcore.
- * Bits 53, 54, 62 and 63 are used to indicate the page type.
- * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402
- * This leaves the bits 0-51 and bits 56-61 to store type and offset.
- * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51
- * plus 56 for the offset.
- * | offset |0110|o|type |00|
- * 0000000000111111111122222222223333333333444444444455 5555 5 55566 66
- * 0123456789012345678901234567890123456789012345678901 2345 6 78901 23
+ * Bits 54 and 63 are used to indicate the page type.
+ * A swap pte is indicated by bit pattern (pte & 0x201) == 0x200
+ * This leaves the bits 0-51 and bits 56-62 to store type and offset.
+ * We use the 5 bits from 57-61 for the type and the 52 bits from 0-51
+ * for the offset.
+ * | offset |01100|type |00|
+ * |0000000000111111111122222222223333333333444444444455|55555|55566|66|
+ * |0123456789012345678901234567890123456789012345678901|23456|78901|23|
*/
-#define __SWP_OFFSET_MASK (~0UL >> 11)
+#define __SWP_OFFSET_MASK ((1UL << 52) - 1)
+#define __SWP_OFFSET_SHIFT 12
+#define __SWP_TYPE_MASK ((1UL << 5) - 1)
+#define __SWP_TYPE_SHIFT 2
static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
{
pte_t pte;
- offset &= __SWP_OFFSET_MASK;
- pte_val(pte) = _PAGE_INVALID | _PAGE_TYPE | ((type & 0x1f) << 2) |
- ((offset & 1UL) << 7) | ((offset & ~1UL) << 11);
+
+ pte_val(pte) = _PAGE_INVALID | _PAGE_PROTECT;
+ pte_val(pte) |= (offset & __SWP_OFFSET_MASK) << __SWP_OFFSET_SHIFT;
+ pte_val(pte) |= (type & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT;
return pte;
}
-#define __swp_type(entry) (((entry).val >> 2) & 0x1f)
-#define __swp_offset(entry) (((entry).val >> 11) | (((entry).val >> 7) & 1))
-#define __swp_entry(type,offset) ((swp_entry_t) { pte_val(mk_swap_pte((type),(offset))) })
+static inline unsigned long __swp_type(swp_entry_t entry)
+{
+ return (entry.val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK;
+}
+
+static inline unsigned long __swp_offset(swp_entry_t entry)
+{
+ return (entry.val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK;
+}
+
+static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset)
+{
+ return (swp_entry_t) { pte_val(mk_swap_pte(type, offset)) };
+}
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 210ffede0153..e617e74b7be2 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -14,20 +14,23 @@ static inline pmd_t __pte_to_pmd(pte_t pte)
/*
* Convert encoding pte bits pmd bits
- * .IR...wrdytp dy..R...I...wr
- * empty .10...000000 -> 00..0...1...00
- * prot-none, clean, old .11...000001 -> 00..1...1...00
- * prot-none, clean, young .11...000101 -> 01..1...1...00
- * prot-none, dirty, old .10...001001 -> 10..1...1...00
- * prot-none, dirty, young .10...001101 -> 11..1...1...00
- * read-only, clean, old .11...010001 -> 00..1...1...01
- * read-only, clean, young .01...010101 -> 01..1...0...01
- * read-only, dirty, old .11...011001 -> 10..1...1...01
- * read-only, dirty, young .01...011101 -> 11..1...0...01
- * read-write, clean, old .11...110001 -> 00..0...1...11
- * read-write, clean, young .01...110101 -> 01..0...0...11
- * read-write, dirty, old .10...111001 -> 10..0...1...11
- * read-write, dirty, young .00...111101 -> 11..0...0...11
+ * lIR.uswrdy.p dy..R...I...wr
+ * empty 010.000000.0 -> 00..0...1...00
+ * prot-none, clean, old 111.000000.1 -> 00..1...1...00
+ * prot-none, clean, young 111.000001.1 -> 01..1...1...00
+ * prot-none, dirty, old 111.000010.1 -> 10..1...1...00
+ * prot-none, dirty, young 111.000011.1 -> 11..1...1...00
+ * read-only, clean, old 111.000100.1 -> 00..1...1...01
+ * read-only, clean, young 101.000101.1 -> 01..1...0...01
+ * read-only, dirty, old 111.000110.1 -> 10..1...1...01
+ * read-only, dirty, young 101.000111.1 -> 11..1...0...01
+ * read-write, clean, old 111.001100.1 -> 00..1...1...11
+ * read-write, clean, young 101.001101.1 -> 01..1...0...11
+ * read-write, dirty, old 110.001110.1 -> 10..0...1...11
+ * read-write, dirty, young 100.001111.1 -> 11..0...0...11
+ * HW-bits: R read-only, I invalid
+ * SW-bits: p present, y young, d dirty, r read, w write, s special,
+ * u unused, l large
*/
if (pte_present(pte)) {
pmd_val(pmd) = pte_val(pte) & PAGE_MASK;
@@ -48,20 +51,23 @@ static inline pte_t __pmd_to_pte(pmd_t pmd)
/*
* Convert encoding pmd bits pte bits
- * dy..R...I...wr .IR...wrdytp
- * empty 00..0...1...00 -> .10...001100
- * prot-none, clean, old 00..0...1...00 -> .10...000001
- * prot-none, clean, young 01..0...1...00 -> .10...000101
- * prot-none, dirty, old 10..0...1...00 -> .10...001001
- * prot-none, dirty, young 11..0...1...00 -> .10...001101
- * read-only, clean, old 00..1...1...01 -> .11...010001
- * read-only, clean, young 01..1...1...01 -> .11...010101
- * read-only, dirty, old 10..1...1...01 -> .11...011001
- * read-only, dirty, young 11..1...1...01 -> .11...011101
- * read-write, clean, old 00..0...1...11 -> .10...110001
- * read-write, clean, young 01..0...1...11 -> .10...110101
- * read-write, dirty, old 10..0...1...11 -> .10...111001
- * read-write, dirty, young 11..0...1...11 -> .10...111101
+ * dy..R...I...wr lIR.uswrdy.p
+ * empty 00..0...1...00 -> 010.000000.0
+ * prot-none, clean, old 00..1...1...00 -> 111.000000.1
+ * prot-none, clean, young 01..1...1...00 -> 111.000001.1
+ * prot-none, dirty, old 10..1...1...00 -> 111.000010.1
+ * prot-none, dirty, young 11..1...1...00 -> 111.000011.1
+ * read-only, clean, old 00..1...1...01 -> 111.000100.1
+ * read-only, clean, young 01..1...0...01 -> 101.000101.1
+ * read-only, dirty, old 10..1...1...01 -> 111.000110.1
+ * read-only, dirty, young 11..1...0...01 -> 101.000111.1
+ * read-write, clean, old 00..1...1...11 -> 111.001100.1
+ * read-write, clean, young 01..1...0...11 -> 101.001101.1
+ * read-write, dirty, old 10..0...1...11 -> 110.001110.1
+ * read-write, dirty, young 11..0...0...11 -> 100.001111.1
+ * HW-bits: R read-only, I invalid
+ * SW-bits: p present, y young, d dirty, r read, w write, s special,
+ * u unused, l large
*/
if (pmd_present(pmd)) {
pte_val(pte) = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN_LARGE;
@@ -70,8 +76,8 @@ static inline pte_t __pmd_to_pte(pmd_t pmd)
pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) << 4;
pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) << 5;
pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT);
- pmd_val(pmd) |= (pte_val(pte) & _PAGE_DIRTY) << 10;
- pmd_val(pmd) |= (pte_val(pte) & _PAGE_YOUNG) << 10;
+ pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) >> 10;
+ pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) >> 10;
} else
pte_val(pte) = _PAGE_INVALID;
return pte;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 33f589459113..b33f66110ca9 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -18,6 +18,7 @@
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/swapops.h>
+#include <linux/sysctl.h>
#include <linux/ksm.h>
#include <linux/mman.h>
@@ -920,6 +921,40 @@ unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
}
EXPORT_SYMBOL(get_guest_storage_key);
+static int page_table_allocate_pgste_min = 0;
+static int page_table_allocate_pgste_max = 1;
+int page_table_allocate_pgste = 0;
+EXPORT_SYMBOL(page_table_allocate_pgste);
+
+static struct ctl_table page_table_sysctl[] = {
+ {
+ .procname = "allocate_pgste",
+ .data = &page_table_allocate_pgste,
+ .maxlen = sizeof(int),
+ .mode = S_IRUGO | S_IWUSR,
+ .proc_handler = proc_dointvec,
+ .extra1 = &page_table_allocate_pgste_min,
+ .extra2 = &page_table_allocate_pgste_max,
+ },
+ { }
+};
+
+static struct ctl_table page_table_sysctl_dir[] = {
+ {
+ .procname = "vm",
+ .maxlen = 0,
+ .mode = 0555,
+ .child = page_table_sysctl,
+ },
+ { }
+};
+
+static int __init page_table_register_sysctl(void)
+{
+ return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM;
+}
+__initcall(page_table_register_sysctl);
+
#else /* CONFIG_PGSTE */
static inline int page_table_with_pgste(struct page *page)
@@ -963,7 +998,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
struct page *uninitialized_var(page);
unsigned int mask, bit;
- if (mm_has_pgste(mm))
+ if (mm_alloc_pgste(mm))
return page_table_alloc_pgste(mm);
/* Allocate fragments of a 4K page as 1K/2K page table */
spin_lock_bh(&mm->context.list_lock);
@@ -1165,116 +1200,25 @@ static inline void thp_split_mm(struct mm_struct *mm)
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb,
- struct mm_struct *mm, pud_t *pud,
- unsigned long addr, unsigned long end)
-{
- unsigned long next, *table, *new;
- struct page *page;
- spinlock_t *ptl;
- pmd_t *pmd;
-
- pmd = pmd_offset(pud, addr);
- do {
- next = pmd_addr_end(addr, end);
-again:
- if (pmd_none_or_clear_bad(pmd))
- continue;
- table = (unsigned long *) pmd_deref(*pmd);
- page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
- if (page_table_with_pgste(page))
- continue;
- /* Allocate new page table with pgstes */
- new = page_table_alloc_pgste(mm);
- if (!new)
- return -ENOMEM;
-
- ptl = pmd_lock(mm, pmd);
- if (likely((unsigned long *) pmd_deref(*pmd) == table)) {
- /* Nuke pmd entry pointing to the "short" page table */
- pmdp_flush_lazy(mm, addr, pmd);
- pmd_clear(pmd);
- /* Copy ptes from old table to new table */
- memcpy(new, table, PAGE_SIZE/2);
- clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
- /* Establish new table */
- pmd_populate(mm, pmd, (pte_t *) new);
- /* Free old table with rcu, there might be a walker! */
- page_table_free_rcu(tlb, table, addr);
- new = NULL;
- }
- spin_unlock(ptl);
- if (new) {
- page_table_free_pgste(new);
- goto again;
- }
- } while (pmd++, addr = next, addr != end);
-
- return addr;
-}
-
-static unsigned long page_table_realloc_pud(struct mmu_gather *tlb,
- struct mm_struct *mm, pgd_t *pgd,
- unsigned long addr, unsigned long end)
-{
- unsigned long next;
- pud_t *pud;
-
- pud = pud_offset(pgd, addr);
- do {
- next = pud_addr_end(addr, end);
- if (pud_none_or_clear_bad(pud))
- continue;
- next = page_table_realloc_pmd(tlb, mm, pud, addr, next);
- if (unlikely(IS_ERR_VALUE(next)))
- return next;
- } while (pud++, addr = next, addr != end);
-
- return addr;
-}
-
-static unsigned long page_table_realloc(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long addr, unsigned long end)
-{
- unsigned long next;
- pgd_t *pgd;
-
- pgd = pgd_offset(mm, addr);
- do {
- next = pgd_addr_end(addr, end);
- if (pgd_none_or_clear_bad(pgd))
- continue;
- next = page_table_realloc_pud(tlb, mm, pgd, addr, next);
- if (unlikely(IS_ERR_VALUE(next)))
- return next;
- } while (pgd++, addr = next, addr != end);
-
- return 0;
-}
-
/*
* switch on pgstes for its userspace process (for kvm)
*/
int s390_enable_sie(void)
{
- struct task_struct *tsk = current;
- struct mm_struct *mm = tsk->mm;
- struct mmu_gather tlb;
+ struct mm_struct *mm = current->mm;
/* Do we have pgstes? if yes, we are done */
- if (mm_has_pgste(tsk->mm))
+ if (mm_has_pgste(mm))
return 0;
-
+ /* Fail if the page tables are 2K */
+ if (!mm_alloc_pgste(mm))
+ return -EINVAL;
down_write(&mm->mmap_sem);
+ mm->context.has_pgste = 1;
/* split thp mappings and disable thp for future mappings */
thp_split_mm(mm);
- /* Reallocate the page tables with pgstes */
- tlb_gather_mmu(&tlb, mm, 0, TASK_SIZE);
- if (!page_table_realloc(&tlb, mm, 0, TASK_SIZE))
- mm->context.has_pgste = 1;
- tlb_finish_mmu(&tlb, 0, TASK_SIZE);
up_write(&mm->mmap_sem);
- return mm->context.has_pgste ? 0 : -ENOMEM;
+ return 0;
}
EXPORT_SYMBOL_GPL(s390_enable_sie);
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 6873f006f7d0..d366675e4bf8 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -774,7 +774,7 @@ static void __init zone_sizes_init(void)
* though, there'll be no lowmem, so we just alloc_bootmem
* the memmap. There will be no percpu memory either.
*/
- if (i != 0 && cpumask_test_cpu(i, &isolnodes)) {
+ if (i != 0 && node_isset(i, isolnodes)) {
node_memmap_pfn[i] =
alloc_bootmem_pfn(0, memmap_size, 0);
BUG_ON(node_percpu[i] != 0);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 25b1cc07d496..d6b078e9fa28 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -95,7 +95,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
struct pvclock_vsyscall_time_info {
struct pvclock_vcpu_time_info pvti;
- u32 migrate_count;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));
#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index e5ecd20e72dd..2f355d229a58 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -141,46 +141,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
}
-static struct pvclock_vsyscall_time_info *pvclock_vdso_info;
-
-static struct pvclock_vsyscall_time_info *
-pvclock_get_vsyscall_user_time_info(int cpu)
-{
- if (!pvclock_vdso_info) {
- BUG();
- return NULL;
- }
-
- return &pvclock_vdso_info[cpu];
-}
-
-struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
-{
- return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
-}
-
#ifdef CONFIG_X86_64
-static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l,
- void *v)
-{
- struct task_migration_notifier *mn = v;
- struct pvclock_vsyscall_time_info *pvti;
-
- pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu);
-
- /* this is NULL when pvclock vsyscall is not initialized */
- if (unlikely(pvti == NULL))
- return NOTIFY_DONE;
-
- pvti->migrate_count++;
-
- return NOTIFY_DONE;
-}
-
-static struct notifier_block pvclock_migrate = {
- .notifier_call = pvclock_task_migrate,
-};
-
/*
* Initialize the generic pvclock vsyscall state. This will allocate
* a/some page(s) for the per-vcpu pvclock information, set up a
@@ -194,17 +155,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
- pvclock_vdso_info = i;
-
for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
__pa(i) + (idx*PAGE_SIZE),
PAGE_KERNEL_VVAR);
}
-
- register_task_migration_notifier(&pvclock_migrate);
-
return 0;
}
#endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ed31c31b2485..c73efcd03e29 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1669,12 +1669,28 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
&guest_hv_clock, sizeof(guest_hv_clock))))
return 0;
- /*
- * The interface expects us to write an even number signaling that the
- * update is finished. Since the guest won't see the intermediate
- * state, we just increase by 2 at the end.
+ /* This VCPU is paused, but it's legal for a guest to read another
+ * VCPU's kvmclock, so we really have to follow the specification where
+ * it says that version is odd if data is being modified, and even after
+ * it is consistent.
+ *
+ * Version field updates must be kept separate. This is because
+ * kvm_write_guest_cached might use a "rep movs" instruction, and
+ * writes within a string instruction are weakly ordered. So there
+ * are three writes overall.
+ *
+ * As a small optimization, only write the version field in the first
+ * and third write. The vcpu->pv_time cache is still valid, because the
+ * version field is the first in the struct.
*/
- vcpu->hv_clock.version = guest_hv_clock.version + 2;
+ BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+
+ vcpu->hv_clock.version = guest_hv_clock.version + 1;
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
+
+ smp_wmb();
/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
@@ -1695,6 +1711,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
&vcpu->hv_clock,
sizeof(vcpu->hv_clock));
+
+ smp_wmb();
+
+ vcpu->hv_clock.version++;
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
return 0;
}
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 40d2473836c9..9793322751e0 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -82,15 +82,18 @@ static notrace cycle_t vread_pvclock(int *mode)
cycle_t ret;
u64 last;
u32 version;
- u32 migrate_count;
u8 flags;
unsigned cpu, cpu1;
/*
- * When looping to get a consistent (time-info, tsc) pair, we
- * also need to deal with the possibility we can switch vcpus,
- * so make sure we always re-fetch time-info for the current vcpu.
+ * Note: hypervisor must guarantee that:
+ * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
+ * 2. that per-CPU pvclock time info is updated if the
+ * underlying CPU changes.
+ * 3. that version is increased whenever underlying CPU
+ * changes.
+ *
*/
do {
cpu = __getcpu() & VGETCPU_CPU_MASK;
@@ -99,27 +102,20 @@ static notrace cycle_t vread_pvclock(int *mode)
* __getcpu() calls (Gleb).
*/
- /* Make sure migrate_count will change if we leave the VCPU. */
- do {
- pvti = get_pvti(cpu);
- migrate_count = pvti->migrate_count;
-
- cpu1 = cpu;
- cpu = __getcpu() & VGETCPU_CPU_MASK;
- } while (unlikely(cpu != cpu1));
+ pvti = get_pvti(cpu);
version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
/*
* Test we're still on the cpu as well as the version.
- * - We must read TSC of pvti's VCPU.
- * - KVM doesn't follow the versioning protocol, so data could
- * change before version if we left the VCPU.
+ * We could have been migrated just after the first
+ * vgetcpu but before fetching the version, so we
+ * wouldn't notice a version change.
*/
- smp_rmb();
- } while (unlikely((pvti->pvti.version & 1) ||
- pvti->pvti.version != version ||
- pvti->migrate_count != migrate_count));
+ cpu1 = __getcpu() & VGETCPU_CPU_MASK;
+ } while (unlikely(cpu != cpu1 ||
+ (pvti->pvti.version & 1) ||
+ pvti->pvti.version != version));
if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
*mode = VCLOCK_NONE;
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-14 10:07:59 +0000