diff options
Diffstat (limited to 'arch/s390')
63 files changed, 4378 insertions, 1091 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 1831833c430e..29a7940f284f 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -3,6 +3,10 @@ # see Documentation/kbuild/kconfig-language.txt. # +config SCHED_MC + def_bool y + depends on SMP + config MMU def_bool y @@ -39,6 +43,9 @@ config GENERIC_HWEIGHT config GENERIC_TIME def_bool y +config GENERIC_CLOCKEVENTS + def_bool y + config GENERIC_BUG bool depends on BUG @@ -55,6 +62,10 @@ config GENERIC_LOCKBREAK default y depends on SMP && PREEMPT +config PGSTE + bool + default y if KVM + mainmenu "Linux Kernel Configuration" config S390 @@ -62,6 +73,7 @@ config S390 select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES + select HAVE_KVM if 64BIT source "init/Kconfig" @@ -69,6 +81,8 @@ menu "Base setup" comment "Processor type and features" +source "kernel/time/Kconfig" + config 64BIT bool "64 bit kernel" help @@ -286,6 +300,14 @@ comment "Kernel preemption" source "kernel/Kconfig.preempt" +config ARCH_SPARSEMEM_ENABLE + def_bool y + select SPARSEMEM_VMEMMAP_ENABLE + select SPARSEMEM_VMEMMAP + +config ARCH_SPARSEMEM_DEFAULT + def_bool y + source "mm/Kconfig" comment "I/O subsystem configuration" @@ -301,10 +323,7 @@ config QDIO tristate "QDIO support" ---help--- This driver provides the Queued Direct I/O base support for - IBM mainframes. - - For details please refer to the documentation provided by IBM at - <http://www10.software.ibm.com/developerworks/opensource/linux390> + IBM System z. To compile this driver as a module, choose M here: the module will be called qdio. @@ -486,25 +505,6 @@ config APPLDATA_NET_SUM source kernel/Kconfig.hz -config NO_IDLE_HZ - bool "No HZ timer ticks in idle" - help - Switches the regular HZ timer off when the system is going idle. - This helps z/VM to detect that the Linux system is idle. VM can - then "swap-out" this guest which reduces memory usage. It also - reduces the overhead of idle systems. - - The HZ timer can be switched on/off via /proc/sys/kernel/hz_timer. - hz_timer=0 means HZ timer is disabled. hz_timer=1 means HZ - timer is active. - -config NO_IDLE_HZ_INIT - bool "HZ timer in idle off by default" - depends on NO_IDLE_HZ - help - The HZ timer is switched off in idle by default. That means the - HZ timer is already disabled at boot time. - config S390_HYPFS_FS bool "s390 hypervisor file system support" select SYS_HYPERVISOR @@ -528,6 +528,13 @@ config ZFCPDUMP Select this option if you want to build an zfcpdump enabled kernel. Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this. +config S390_GUEST +bool "s390 guest support (EXPERIMENTAL)" + depends on 64BIT && EXPERIMENTAL + select VIRTIO + select VIRTIO_RING + help + Select this option if you want to run the kernel under s390 linux endmenu source "net/Kconfig" @@ -549,3 +556,5 @@ source "security/Kconfig" source "crypto/Kconfig" source "lib/Kconfig" + +source "arch/s390/kvm/Kconfig" diff --git a/arch/s390/Makefile b/arch/s390/Makefile index f708be367b03..792a4e7743ce 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -87,7 +87,7 @@ LDFLAGS_vmlinux := -e start head-y := arch/s390/kernel/head.o arch/s390/kernel/init_task.o core-y += arch/s390/mm/ arch/s390/kernel/ arch/s390/crypto/ \ - arch/s390/appldata/ arch/s390/hypfs/ + arch/s390/appldata/ arch/s390/hypfs/ arch/s390/kvm/ libs-y += arch/s390/lib/ drivers-y += drivers/s390/ drivers-$(CONFIG_MATHEMU) += arch/s390/math-emu/ diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile index 14e552c5cc43..6a1157fa4f98 100644 --- a/arch/s390/crypto/Makefile +++ b/arch/s390/crypto/Makefile @@ -2,8 +2,9 @@ # Cryptographic API # -obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o -obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o +obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o sha_common.o +obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o sha_common.o +obj-$(CONFIG_CRYPTO_SHA512_S390) += sha512_s390.o sha_common.o obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o des_check_key.o obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o obj-$(CONFIG_S390_PRNG) += prng.o diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index a3f67f8b5427..e33f32b54c08 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -499,7 +499,7 @@ static struct crypto_alg cbc_aes_alg = { } }; -static int __init aes_init(void) +static int __init aes_s390_init(void) { int ret; @@ -542,15 +542,15 @@ aes_err: goto out; } -static void __exit aes_fini(void) +static void __exit aes_s390_fini(void) { crypto_unregister_alg(&cbc_aes_alg); crypto_unregister_alg(&ecb_aes_alg); crypto_unregister_alg(&aes_alg); } -module_init(aes_init); -module_exit(aes_fini); +module_init(aes_s390_init); +module_exit(aes_s390_fini); MODULE_ALIAS("aes"); diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h index 95f5160df27f..9992f95ef992 100644 --- a/arch/s390/crypto/crypt_s390.h +++ b/arch/s390/crypto/crypt_s390.h @@ -82,6 +82,7 @@ enum crypt_s390_kimd_func { KIMD_QUERY = CRYPT_S390_KIMD | 0, KIMD_SHA_1 = CRYPT_S390_KIMD | 1, KIMD_SHA_256 = CRYPT_S390_KIMD | 2, + KIMD_SHA_512 = CRYPT_S390_KIMD | 3, }; /* @@ -92,6 +93,7 @@ enum crypt_s390_klmd_func { KLMD_QUERY = CRYPT_S390_KLMD | 0, KLMD_SHA_1 = CRYPT_S390_KLMD | 1, KLMD_SHA_256 = CRYPT_S390_KLMD | 2, + KLMD_SHA_512 = CRYPT_S390_KLMD | 3, }; /* diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index ea22707f435f..4aba83b31596 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -550,7 +550,7 @@ static struct crypto_alg cbc_des3_192_alg = { } }; -static int init(void) +static int des_s390_init(void) { int ret = 0; @@ -612,7 +612,7 @@ des_err: goto out; } -static void __exit fini(void) +static void __exit des_s390_fini(void) { crypto_unregister_alg(&cbc_des3_192_alg); crypto_unregister_alg(&ecb_des3_192_alg); @@ -625,8 +625,8 @@ static void __exit fini(void) crypto_unregister_alg(&des_alg); } -module_init(init); -module_exit(fini); +module_init(des_s390_init); +module_exit(des_s390_fini); MODULE_ALIAS("des"); MODULE_ALIAS("des3_ede"); diff --git a/arch/s390/crypto/sha.h b/arch/s390/crypto/sha.h new file mode 100644 index 000000000000..1ceafa571eab --- /dev/null +++ b/arch/s390/crypto/sha.h @@ -0,0 +1,35 @@ +/* + * Cryptographic API. + * + * s390 generic implementation of the SHA Secure Hash Algorithms. + * + * Copyright IBM Corp. 2007 + * Author(s): Jan Glauber (jang@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 + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#ifndef _CRYPTO_ARCH_S390_SHA_H +#define _CRYPTO_ARCH_S390_SHA_H + +#include <linux/crypto.h> +#include <crypto/sha.h> + +/* must be big enough for the largest SHA variant */ +#define SHA_MAX_STATE_SIZE 16 +#define SHA_MAX_BLOCK_SIZE SHA512_BLOCK_SIZE + +struct s390_sha_ctx { + u64 count; /* message length in bytes */ + u32 state[SHA_MAX_STATE_SIZE]; + u8 buf[2 * SHA_MAX_BLOCK_SIZE]; + int func; /* KIMD function to use */ +}; + +void s390_sha_update(struct crypto_tfm *tfm, const u8 *data, unsigned int len); +void s390_sha_final(struct crypto_tfm *tfm, u8 *out); + +#endif diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index 5a834f6578ab..b3cb5a89b00d 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -29,16 +29,11 @@ #include <crypto/sha.h> #include "crypt_s390.h" - -struct s390_sha1_ctx { - u64 count; /* message length */ - u32 state[5]; - u8 buf[2 * SHA1_BLOCK_SIZE]; -}; +#include "sha.h" static void sha1_init(struct crypto_tfm *tfm) { - struct s390_sha1_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_sha_ctx *sctx = crypto_tfm_ctx(tfm); sctx->state[0] = SHA1_H0; sctx->state[1] = SHA1_H1; @@ -46,79 +41,7 @@ static void sha1_init(struct crypto_tfm *tfm) sctx->state[3] = SHA1_H3; sctx->state[4] = SHA1_H4; sctx->count = 0; -} - -static void sha1_update(struct crypto_tfm *tfm, const u8 *data, - unsigned int len) -{ - struct s390_sha1_ctx *sctx = crypto_tfm_ctx(tfm); - unsigned int index; - int ret; - - /* how much is already in the buffer? */ - index = sctx->count & 0x3f; - - sctx->count += len; - - if (index + len < SHA1_BLOCK_SIZE) - goto store; - - /* process one stored block */ - if (index) { - memcpy(sctx->buf + index, data, SHA1_BLOCK_SIZE - index); - ret = crypt_s390_kimd(KIMD_SHA_1, sctx->state, sctx->buf, - SHA1_BLOCK_SIZE); - BUG_ON(ret != SHA1_BLOCK_SIZE); - data += SHA1_BLOCK_SIZE - index; - len -= SHA1_BLOCK_SIZE - index; - } - - /* process as many blocks as possible */ - if (len >= SHA1_BLOCK_SIZE) { - ret = crypt_s390_kimd(KIMD_SHA_1, sctx->state, data, - len & ~(SHA1_BLOCK_SIZE - 1)); - BUG_ON(ret != (len & ~(SHA1_BLOCK_SIZE - 1))); - data += ret; - len -= ret; - } - -store: - /* anything left? */ - if (len) - memcpy(sctx->buf + index , data, len); -} - -/* Add padding and return the message digest. */ -static void sha1_final(struct crypto_tfm *tfm, u8 *out) -{ - struct s390_sha1_ctx *sctx = crypto_tfm_ctx(tfm); - u64 bits; - unsigned int index, end; - int ret; - - /* must perform manual padding */ - index = sctx->count & 0x3f; - end = (index < 56) ? SHA1_BLOCK_SIZE : (2 * SHA1_BLOCK_SIZE); - - /* start pad with 1 */ - sctx->buf[index] = 0x80; - - /* pad with zeros */ - index++; - memset(sctx->buf + index, 0x00, end - index - 8); - - /* append message length */ - bits = sctx->count * 8; - memcpy(sctx->buf + end - 8, &bits, sizeof(bits)); - - ret = crypt_s390_kimd(KIMD_SHA_1, sctx->state, sctx->buf, end); - BUG_ON(ret != end); - - /* copy digest to out */ - memcpy(out, sctx->state, SHA1_DIGEST_SIZE); - - /* wipe context */ - memset(sctx, 0, sizeof *sctx); + sctx->func = KIMD_SHA_1; } static struct crypto_alg alg = { @@ -127,33 +50,31 @@ static struct crypto_alg alg = { .cra_priority = CRYPT_S390_PRIORITY, .cra_flags = CRYPTO_ALG_TYPE_DIGEST, .cra_blocksize = SHA1_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_sha1_ctx), + .cra_ctxsize = sizeof(struct s390_sha_ctx), .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT(alg.cra_list), .cra_u = { .digest = { .dia_digestsize = SHA1_DIGEST_SIZE, .dia_init = sha1_init, - .dia_update = sha1_update, - .dia_final = sha1_final } } + .dia_update = s390_sha_update, + .dia_final = s390_sha_final } } }; -static int __init init(void) +static int __init sha1_s390_init(void) { if (!crypt_s390_func_available(KIMD_SHA_1)) return -EOPNOTSUPP; - return crypto_register_alg(&alg); } -static void __exit fini(void) +static void __exit sha1_s390_fini(void) { crypto_unregister_alg(&alg); } -module_init(init); -module_exit(fini); +module_init(sha1_s390_init); +module_exit(sha1_s390_fini); MODULE_ALIAS("sha1"); - MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index ccf8633c4f65..19c03fb6ba7e 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -22,16 +22,11 @@ #include <crypto/sha.h> #include "crypt_s390.h" - -struct s390_sha256_ctx { - u64 count; /* message length */ - u32 state[8]; - u8 buf[2 * SHA256_BLOCK_SIZE]; -}; +#include "sha.h" static void sha256_init(struct crypto_tfm *tfm) { - struct s390_sha256_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_sha_ctx *sctx = crypto_tfm_ctx(tfm); sctx->state[0] = SHA256_H0; sctx->state[1] = SHA256_H1; @@ -42,79 +37,7 @@ static void sha256_init(struct crypto_tfm *tfm) sctx->state[6] = SHA256_H6; sctx->state[7] = SHA256_H7; sctx->count = 0; -} - -static void sha256_update(struct crypto_tfm *tfm, const u8 *data, - unsigned int len) -{ - struct s390_sha256_ctx *sctx = crypto_tfm_ctx(tfm); - unsigned int index; - int ret; - - /* how much is already in the buffer? */ - index = sctx->count & 0x3f; - - sctx->count += len; - - if ((index + len) < SHA256_BLOCK_SIZE) - goto store; - - /* process one stored block */ - if (index) { - memcpy(sctx->buf + index, data, SHA256_BLOCK_SIZE - index); - ret = crypt_s390_kimd(KIMD_SHA_256, sctx->state, sctx->buf, - SHA256_BLOCK_SIZE); - BUG_ON(ret != SHA256_BLOCK_SIZE); - data += SHA256_BLOCK_SIZE - index; - len -= SHA256_BLOCK_SIZE - index; - } - - /* process as many blocks as possible */ - if (len >= SHA256_BLOCK_SIZE) { - ret = crypt_s390_kimd(KIMD_SHA_256, sctx->state, data, - len & ~(SHA256_BLOCK_SIZE - 1)); - BUG_ON(ret != (len & ~(SHA256_BLOCK_SIZE - 1))); - data += ret; - len -= ret; - } - -store: - /* anything left? */ - if (len) - memcpy(sctx->buf + index , data, len); -} - -/* Add padding and return the message digest */ -static void sha256_final(struct crypto_tfm *tfm, u8 *out) -{ - struct s390_sha256_ctx *sctx = crypto_tfm_ctx(tfm); - u64 bits; - unsigned int index, end; - int ret; - - /* must perform manual padding */ - index = sctx->count & 0x3f; - end = (index < 56) ? SHA256_BLOCK_SIZE : (2 * SHA256_BLOCK_SIZE); - - /* start pad with 1 */ - sctx->buf[index] = 0x80; - - /* pad with zeros */ - index++; - memset(sctx->buf + index, 0x00, end - index - 8); - - /* append message length */ - bits = sctx->count * 8; - memcpy(sctx->buf + end - 8, &bits, sizeof(bits)); - - ret = crypt_s390_kimd(KIMD_SHA_256, sctx->state, sctx->buf, end); - BUG_ON(ret != end); - - /* copy digest to out */ - memcpy(out, sctx->state, SHA256_DIGEST_SIZE); - - /* wipe context */ - memset(sctx, 0, sizeof *sctx); + sctx->func = KIMD_SHA_256; } static struct crypto_alg alg = { @@ -123,17 +46,17 @@ static struct crypto_alg alg = { .cra_priority = CRYPT_S390_PRIORITY, .cra_flags = CRYPTO_ALG_TYPE_DIGEST, .cra_blocksize = SHA256_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct s390_sha256_ctx), + .cra_ctxsize = sizeof(struct s390_sha_ctx), .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT(alg.cra_list), .cra_u = { .digest = { .dia_digestsize = SHA256_DIGEST_SIZE, .dia_init = sha256_init, - .dia_update = sha256_update, - .dia_final = sha256_final } } + .dia_update = s390_sha_update, + .dia_final = s390_sha_final } } }; -static int init(void) +static int sha256_s390_init(void) { if (!crypt_s390_func_available(KIMD_SHA_256)) return -EOPNOTSUPP; @@ -141,15 +64,14 @@ static int init(void) return crypto_register_alg(&alg); } -static void __exit fini(void) +static void __exit sha256_s390_fini(void) { crypto_unregister_alg(&alg); } -module_init(init); -module_exit(fini); +module_init(sha256_s390_init); +module_exit(sha256_s390_fini); MODULE_ALIAS("sha256"); - MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c new file mode 100644 index 000000000000..23c7861f6aeb --- /dev/null +++ b/arch/s390/crypto/sha512_s390.c @@ -0,0 +1,114 @@ +/* + * Cryptographic API. + * + * s390 implementation of the SHA512 and SHA38 Secure Hash Algorithm. + * + * Copyright IBM Corp. 2007 + * Author(s): Jan Glauber (jang@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 + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#include <linux/init.h> +#include <linux/module.h> +#include <linux/crypto.h> + +#include "sha.h" +#include "crypt_s390.h" + +static void sha512_init(struct crypto_tfm *tfm) +{ + struct s390_sha_ctx *ctx = crypto_tfm_ctx(tfm); + + *(__u64 *)&ctx->state[0] = 0x6a09e667f3bcc908ULL; + *(__u64 *)&ctx->state[2] = 0xbb67ae8584caa73bULL; + *(__u64 *)&ctx->state[4] = 0x3c6ef372fe94f82bULL; + *(__u64 *)&ctx->state[6] = 0xa54ff53a5f1d36f1ULL; + *(__u64 *)&ctx->state[8] = 0x510e527fade682d1ULL; + *(__u64 *)&ctx->state[10] = 0x9b05688c2b3e6c1fULL; + *(__u64 *)&ctx->state[12] = 0x1f83d9abfb41bd6bULL; + *(__u64 *)&ctx->state[14] = 0x5be0cd19137e2179ULL; + ctx->count = 0; + ctx->func = KIMD_SHA_512; +} + +static struct crypto_alg sha512_alg = { + .cra_name = "sha512", + .cra_driver_name = "sha512-s390", + .cra_priority = CRYPT_S390_PRIORITY, + .cra_flags = CRYPTO_ALG_TYPE_DIGEST, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct s390_sha_ctx), + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(sha512_alg.cra_list), + .cra_u = { .digest = { + .dia_digestsize = SHA512_DIGEST_SIZE, + .dia_init = sha512_init, + .dia_update = s390_sha_update, + .dia_final = s390_sha_final } } +}; + +MODULE_ALIAS("sha512"); + +static void sha384_init(struct crypto_tfm *tfm) +{ + struct s390_sha_ctx *ctx = crypto_tfm_ctx(tfm); + + *(__u64 *)&ctx->state[0] = 0xcbbb9d5dc1059ed8ULL; + *(__u64 *)&ctx->state[2] = 0x629a292a367cd507ULL; + *(__u64 *)&ctx->state[4] = 0x9159015a3070dd17ULL; + *(__u64 *)&ctx->state[6] = 0x152fecd8f70e5939ULL; + *(__u64 *)&ctx->state[8] = 0x67332667ffc00b31ULL; + *(__u64 *)&ctx->state[10] = 0x8eb44a8768581511ULL; + *(__u64 *)&ctx->state[12] = 0xdb0c2e0d64f98fa7ULL; + *(__u64 *)&ctx->state[14] = 0x47b5481dbefa4fa4ULL; + ctx->count = 0; + ctx->func = KIMD_SHA_512; +} + +static struct crypto_alg sha384_alg = { + .cra_name = "sha384", + .cra_driver_name = "sha384-s390", + .cra_priority = CRYPT_S390_PRIORITY, + .cra_flags = CRYPTO_ALG_TYPE_DIGEST, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct s390_sha_ctx), + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(sha384_alg.cra_list), + .cra_u = { .digest = { + .dia_digestsize = SHA384_DIGEST_SIZE, + .dia_init = sha384_init, + .dia_update = s390_sha_update, + .dia_final = s390_sha_final } } +}; + +MODULE_ALIAS("sha384"); + +static int __init init(void) +{ + int ret; + + if (!crypt_s390_func_available(KIMD_SHA_512)) + return -EOPNOTSUPP; + if ((ret = crypto_register_alg(&sha512_alg)) < 0) + goto out; + if ((ret = crypto_register_alg(&sha384_alg)) < 0) + crypto_unregister_alg(&sha512_alg); +out: + return ret; +} + +static void __exit fini(void) +{ + crypto_unregister_alg(&sha512_alg); + crypto_unregister_alg(&sha384_alg); +} + +module_init(init); +module_exit(fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SHA512 and SHA-384 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c new file mode 100644 index 000000000000..9d6eb8c3d37e --- /dev/null +++ b/arch/s390/crypto/sha_common.c @@ -0,0 +1,97 @@ +/* + * Cryptographic API. + * + * s390 generic implementation of the SHA Secure Hash Algorithms. + * + * Copyright IBM Corp. 2007 + * Author(s): Jan Glauber (jang@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 + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#include <linux/crypto.h> +#include "sha.h" +#include "crypt_s390.h" + +void s390_sha_update(struct crypto_tfm *tfm, const u8 *data, unsigned int len) +{ + struct s390_sha_ctx *ctx = crypto_tfm_ctx(tfm); + unsigned int bsize = crypto_tfm_alg_blocksize(tfm); + unsigned int index; + int ret; + + /* how much is already in the buffer? */ + index = ctx->count & (bsize - 1); + ctx->count += len; + + if ((index + len) < bsize) + goto store; + + /* process one stored block */ + if (index) { + memcpy(ctx->buf + index, data, bsize - index); + ret = crypt_s390_kimd(ctx->func, ctx->state, ctx->buf, bsize); + BUG_ON(ret != bsize); + data += bsize - index; + len -= bsize - index; + } + + /* process as many blocks as possible */ + if (len >= bsize) { + ret = crypt_s390_kimd(ctx->func, ctx->state, data, + len & ~(bsize - 1)); + BUG_ON(ret != (len & ~(bsize - 1))); + data += ret; + len -= ret; + } +store: + if (len) + memcpy(ctx->buf + index , data, len); +} +EXPORT_SYMBOL_GPL(s390_sha_update); + +void s390_sha_final(struct crypto_tfm *tfm, u8 *out) +{ + struct s390_sha_ctx *ctx = crypto_tfm_ctx(tfm); + unsigned int bsize = crypto_tfm_alg_blocksize(tfm); + u64 bits; + unsigned int index, end, plen; + int ret; + + /* SHA-512 uses 128 bit padding length */ + plen = (bsize > SHA256_BLOCK_SIZE) ? 16 : 8; + + /* must perform manual padding */ + index = ctx->count & (bsize - 1); + end = (index < bsize - plen) ? bsize : (2 * bsize); + + /* start pad with 1 */ + ctx->buf[index] = 0x80; + index++; + + /* pad with zeros */ + memset(ctx->buf + index, 0x00, end - index - 8); + + /* + * Append message length. Well, SHA-512 wants a 128 bit lenght value, + * nevertheless we use u64, should be enough for now... + */ + bits = ctx->count * 8; + memcpy(ctx->buf + end - 8, &bits, sizeof(bits)); + + ret = crypt_s390_kimd(ctx->func, ctx->state, ctx->buf, end); + BUG_ON(ret != end); + + /* copy digest to out */ + memcpy(out, ctx->state, crypto_hash_digestsize(crypto_hash_cast(tfm))); + /* wipe context */ + memset(ctx, 0, sizeof *ctx); +} +EXPORT_SYMBOL_GPL(s390_sha_final); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("s390 SHA cipher common functions"); diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 62f6b5a606dd..aa341d0ea1e6 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,8 +1,9 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.25-rc4 -# Wed Mar 5 11:22:59 2008 +# Linux kernel version: 2.6.25 +# Wed Apr 30 11:07:45 2008 # +CONFIG_SCHED_MC=y CONFIG_MMU=y CONFIG_ZONE_DMA=y CONFIG_LOCKDEP_SUPPORT=y @@ -13,10 +14,12 @@ CONFIG_RWSEM_XCHGADD_ALGORITHM=y # CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_GENERIC_BUG=y CONFIG_NO_IOMEM=y CONFIG_NO_DMA=y CONFIG_GENERIC_LOCKBREAK=y +CONFIG_PGSTE=y CONFIG_S390=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" @@ -42,6 +45,7 @@ CONFIG_LOG_BUF_SHIFT=17 CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set CONFIG_CGROUP_NS=y +# CONFIG_CGROUP_DEVICE is not set # CONFIG_CPUSETS is not set CONFIG_GROUP_SCHED=y CONFIG_FAIR_GROUP_SCHED=y @@ -64,6 +68,7 @@ CONFIG_INITRAMFS_SOURCE="" CONFIG_SYSCTL=y # CONFIG_EMBEDDED is not set CONFIG_SYSCTL_SYSCALL=y +CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_KALLSYMS=y # CONFIG_KALLSYMS_ALL is not set # CONFIG_KALLSYMS_EXTRA_PASS is not set @@ -91,6 +96,7 @@ CONFIG_KPROBES=y CONFIG_KRETPROBES=y CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y +# CONFIG_HAVE_DMA_ATTRS is not set CONFIG_PROC_PAGE_MONITOR=y CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y @@ -120,8 +126,8 @@ CONFIG_DEFAULT_DEADLINE=y # CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="deadline" +CONFIG_PREEMPT_NOTIFIERS=y CONFIG_CLASSIC_RCU=y -# CONFIG_PREEMPT_RCU is not set # # Base setup @@ -130,6 +136,10 @@ CONFIG_CLASSIC_RCU=y # # Processor type and features # +CONFIG_TICK_ONESHOT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_GENERIC_CLOCKEVENTS_BUILD=y CONFIG_64BIT=y CONFIG_SMP=y CONFIG_NR_CPUS=32 @@ -160,15 +170,20 @@ CONFIG_ARCH_POPULATES_NODE_MAP=y # CONFIG_PREEMPT_NONE is not set # CONFIG_PREEMPT_VOLUNTARY is not set CONFIG_PREEMPT=y -# CONFIG_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU is not set +CONFIG_ARCH_SPARSEMEM_ENABLE=y +CONFIG_ARCH_SPARSEMEM_DEFAULT=y CONFIG_SELECT_MEMORY_MODEL=y -CONFIG_FLATMEM_MANUAL=y +# CONFIG_FLATMEM_MANUAL is not set # CONFIG_DISCONTIGMEM_MANUAL is not set -# CONFIG_SPARSEMEM_MANUAL is not set -CONFIG_FLATMEM=y -CONFIG_FLAT_NODE_MEM_MAP=y +CONFIG_SPARSEMEM_MANUAL=y +CONFIG_SPARSEMEM=y +CONFIG_HAVE_MEMORY_PRESENT=y # CONFIG_SPARSEMEM_STATIC is not set -# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set +CONFIG_SPARSEMEM_EXTREME=y +CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y +CONFIG_SPARSEMEM_VMEMMAP=y +CONFIG_PAGEFLAGS_EXTENDED=y CONFIG_SPLIT_PTLOCK_CPUS=4 CONFIG_RESOURCES_64BIT=y CONFIG_ZONE_DMA_FLAG=1 @@ -204,11 +219,10 @@ CONFIG_HZ_100=y # CONFIG_HZ_1000 is not set CONFIG_HZ=100 # CONFIG_SCHED_HRTICK is not set -CONFIG_NO_IDLE_HZ=y -CONFIG_NO_IDLE_HZ_INIT=y CONFIG_S390_HYPFS_FS=y CONFIG_KEXEC=y # CONFIG_ZFCPDUMP is not set +CONFIG_S390_GUEST=y # # Networking @@ -271,8 +285,10 @@ CONFIG_INET6_XFRM_MODE_TUNNEL=y CONFIG_INET6_XFRM_MODE_BEET=y # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set CONFIG_IPV6_SIT=y +CONFIG_IPV6_NDISC_NODETYPE=y # CONFIG_IPV6_TUNNEL is not set # CONFIG_IPV6_MULTIPLE_TABLES is not set +# CONFIG_IPV6_MROUTE is not set # CONFIG_NETWORK_SECMARK is not set CONFIG_NETFILTER=y # CONFIG_NETFILTER_DEBUG is not set @@ -288,6 +304,7 @@ CONFIG_NF_CONNTRACK=m # CONFIG_NF_CT_ACCT is not set # CONFIG_NF_CONNTRACK_MARK is not set # CONFIG_NF_CONNTRACK_EVENTS is not set +# CONFIG_NF_CT_PROTO_DCCP is not set # CONFIG_NF_CT_PROTO_SCTP is not set # CONFIG_NF_CT_PROTO_UDPLITE is not set # CONFIG_NF_CONNTRACK_AMANDA is not set @@ -438,6 +455,7 @@ CONFIG_DASD_ECKD=y CONFIG_DASD_FBA=y CONFIG_DASD_DIAG=y CONFIG_DASD_EER=y +CONFIG_VIRTIO_BLK=m CONFIG_MISC_DEVICES=y # CONFIG_EEPROM_93CX6 is not set # CONFIG_ENCLOSURE_SERVICES is not set @@ -532,26 +550,26 @@ CONFIG_NETDEV_10000=y # S/390 network device drivers # CONFIG_LCS=m -CONFIG_CTC=m +CONFIG_CTCM=m # CONFIG_NETIUCV is not set # CONFIG_SMSGIUCV is not set # CONFIG_CLAW is not set CONFIG_QETH=y - -# -# Gigabit Ethernet default settings -# -# CONFIG_QETH_IPV6 is not set +CONFIG_QETH_L2=y +CONFIG_QETH_L3=y +CONFIG_QETH_IPV6=y CONFIG_CCWGROUP=y # CONFIG_PPP is not set # CONFIG_SLIP is not set # CONFIG_NETCONSOLE is not set # CONFIG_NETPOLL is not set # CONFIG_NET_POLL_CONTROLLER is not set +CONFIG_VIRTIO_NET=m # # Character devices # +CONFIG_DEVKMEM=y CONFIG_UNIX98_PTYS=y CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 @@ -601,6 +619,7 @@ CONFIG_S390_VMUR=m # Sonics Silicon Backplane # # CONFIG_MEMSTICK is not set +# CONFIG_NEW_LEDS is not set # # File systems @@ -653,6 +672,7 @@ CONFIG_PROC_SYSCTL=y CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +# CONFIG_HUGETLBFS is not set # CONFIG_HUGETLB_PAGE is not set CONFIG_CONFIGFS_FS=m @@ -679,12 +699,10 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3=y # CONFIG_NFS_V3_ACL is not set # CONFIG_NFS_V4 is not set -# CONFIG_NFS_DIRECTIO is not set CONFIG_NFSD=y CONFIG_NFSD_V3=y # CONFIG_NFSD_V3_ACL is not set # CONFIG_NFSD_V4 is not set -CONFIG_NFSD_TCP=y CONFIG_LOCKD=y CONFIG_LOCKD_V4=y CONFIG_EXPORTFS=y @@ -732,6 +750,7 @@ CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set CONFIG_ENABLE_WARN_DEPRECATED=y CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_WARN=2048 CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set CONFIG_DEBUG_FS=y @@ -755,6 +774,7 @@ CONFIG_DEBUG_SPINLOCK_SLEEP=y CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_INFO is not set # CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set # CONFIG_DEBUG_LIST is not set # CONFIG_DEBUG_SG is not set # CONFIG_FRAME_POINTER is not set @@ -776,58 +796,88 @@ CONFIG_SAMPLES=y # CONFIG_SECURITY is not set # CONFIG_SECURITY_FILE_CAPABILITIES is not set CONFIG_CRYPTO=y + +# +# Crypto core or helper +# CONFIG_CRYPTO_ALGAPI=y CONFIG_CRYPTO_AEAD=m CONFIG_CRYPTO_BLKCIPHER=y -CONFIG_CRYPTO_SEQIV=m CONFIG_CRYPTO_HASH=m CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_GF128MUL=m +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_CRYPTD is not set +CONFIG_CRYPTO_AUTHENC=m +# CONFIG_CRYPTO_TEST is not set + +# +# Authenticated Encryption with Associated Data +# +CONFIG_CRYPTO_CCM=m +CONFIG_CRYPTO_GCM=m +CONFIG_CRYPTO_SEQIV=m + +# +# Block modes +# +CONFIG_CRYPTO_CBC=y +CONFIG_CRYPTO_CTR=m +CONFIG_CRYPTO_CTS=m +CONFIG_CRYPTO_ECB=m +# CONFIG_CRYPTO_LRW is not set +CONFIG_CRYPTO_PCBC=m +# CONFIG_CRYPTO_XTS is not set + +# +# Hash modes +# CONFIG_CRYPTO_HMAC=m # CONFIG_CRYPTO_XCBC is not set -# CONFIG_CRYPTO_NULL is not set + +# +# Digest +# +# CONFIG_CRYPTO_CRC32C is not set # CONFIG_CRYPTO_MD4 is not set CONFIG_CRYPTO_MD5=m +# CONFIG_CRYPTO_MICHAEL_MIC is not set CONFIG_CRYPTO_SHA1=m # CONFIG_CRYPTO_SHA256 is not set # CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_WP512 is not set # CONFIG_CRYPTO_TGR192 is not set -CONFIG_CRYPTO_GF128MUL=m -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_CBC=y -CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_LRW is not set -# CONFIG_CRYPTO_XTS is not set -CONFIG_CRYPTO_CTR=m -CONFIG_CRYPTO_GCM=m -CONFIG_CRYPTO_CCM=m -# CONFIG_CRYPTO_CRYPTD is not set -# CONFIG_CRYPTO_DES is not set -CONFIG_CRYPTO_FCRYPT=m -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_TWOFISH is not set -# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_WP512 is not set + +# +# Ciphers +# # CONFIG_CRYPTO_AES is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_BLOWFISH is not set +CONFIG_CRYPTO_CAMELLIA=m # CONFIG_CRYPTO_CAST5 is not set # CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_TEA is not set -# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_DES is not set +CONFIG_CRYPTO_FCRYPT=m # CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_ANUBIS is not set -CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SEED=m +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_TWOFISH is not set + +# +# Compression +# # CONFIG_CRYPTO_DEFLATE is not set -# CONFIG_CRYPTO_MICHAEL_MIC is not set -# CONFIG_CRYPTO_CRC32C is not set -CONFIG_CRYPTO_CAMELLIA=m -# CONFIG_CRYPTO_TEST is not set -CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_HW=y CONFIG_ZCRYPT=m # CONFIG_ZCRYPT_MONOLITHIC is not set # CONFIG_CRYPTO_SHA1_S390 is not set # CONFIG_CRYPTO_SHA256_S390 is not set +CONFIG_CRYPTO_SHA512_S390=m # CONFIG_CRYPTO_DES_S390 is not set # CONFIG_CRYPTO_AES_S390 is not set CONFIG_S390_PRNG=m @@ -836,6 +886,8 @@ CONFIG_S390_PRNG=m # Library routines # CONFIG_BITREVERSE=m +# CONFIG_GENERIC_FIND_FIRST_BIT is not set +# CONFIG_GENERIC_FIND_NEXT_BIT is not set # CONFIG_CRC_CCITT is not set # CONFIG_CRC16 is not set # CONFIG_CRC_ITU_T is not set @@ -845,3 +897,9 @@ CONFIG_LIBCRC32C=m CONFIG_LZO_COMPRESS=m CONFIG_LZO_DECOMPRESS=m CONFIG_PLIST=y +CONFIG_HAVE_KVM=y +CONFIG_VIRTUALIZATION=y +CONFIG_KVM=m +CONFIG_VIRTIO=y +CONFIG_VIRTIO_RING=y +CONFIG_VIRTIO_BALLOON=m diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 4d3e38392cb1..6302f5082588 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -2,8 +2,6 @@ # Makefile for the linux kernel. # -EXTRA_AFLAGS := -traditional - # # Passing null pointers is ok for smp code, since we access the lowcore here. # @@ -11,7 +9,7 @@ CFLAGS_smp.o := -Wno-nonnull obj-y := bitmap.o traps.o time.o process.o base.o early.o \ setup.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \ - semaphore.o s390_ext.o debug.o irq.o ipl.o dis.o diag.o + s390_ext.o debug.o irq.o ipl.o dis.o diag.o obj-y += $(if $(CONFIG_64BIT),entry64.o,entry.o) obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) @@ -19,7 +17,7 @@ obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) extra-y += head.o init_task.o vmlinux.lds obj-$(CONFIG_MODULES) += s390_ksyms.o module.o -obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_SMP) += smp.o topology.o obj-$(CONFIG_AUDIT) += audit.o compat-obj-$(CONFIG_AUDIT) += compat_audit.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 1375f8a4469e..fa28ecae636b 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -5,44 +5,38 @@ */ #include <linux/sched.h> - -/* Use marker if you need to separate the values later */ - -#define DEFINE(sym, val, marker) \ - asm volatile("\n->" #sym " %0 " #val " " #marker : : "i" (val)) - -#define BLANK() asm volatile("\n->" : : ) +#include <linux/kbuild.h> int main(void) { - DEFINE(__THREAD_info, offsetof(struct task_struct, stack),); - DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp),); - DEFINE(__THREAD_per, offsetof(struct task_struct, thread.per_info),); + DEFINE(__THREAD_info, offsetof(struct task_struct, stack)); + DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp)); + DEFINE(__THREAD_per, offsetof(struct task_struct, thread.per_info)); DEFINE(__THREAD_mm_segment, - offsetof(struct task_struct, thread.mm_segment),); + offsetof(struct task_struct, thread.mm_segment)); BLANK(); - DEFINE(__TASK_pid, offsetof(struct task_struct, pid),); + DEFINE(__TASK_pid, offsetof(struct task_struct, pid)); BLANK(); - DEFINE(__PER_atmid, offsetof(per_struct, lowcore.words.perc_atmid),); - DEFINE(__PER_address, offsetof(per_struct, lowcore.words.address),); - DEFINE(__PER_access_id, offsetof(per_struct, lowcore.words.access_id),); + DEFINE(__PER_atmid, offsetof(per_struct, lowcore.words.perc_atmid)); + DEFINE(__PER_address, offsetof(per_struct, lowcore.words.address)); + DEFINE(__PER_access_id, offsetof(per_struct, lowcore.words.access_id)); BLANK(); - DEFINE(__TI_task, offsetof(struct thread_info, task),); - DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain),); - DEFINE(__TI_flags, offsetof(struct thread_info, flags),); - DEFINE(__TI_cpu, offsetof(struct thread_info, cpu),); - DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count),); + DEFINE(__TI_task, offsetof(struct thread_info, task)); + DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain)); + DEFINE(__TI_flags, offsetof(struct thread_info, flags)); + DEFINE(__TI_cpu, offsetof(struct thread_info, cpu)); + DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count)); BLANK(); - DEFINE(__PT_ARGS, offsetof(struct pt_regs, args),); - DEFINE(__PT_PSW, offsetof(struct pt_regs, psw),); - DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs),); - DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2),); - DEFINE(__PT_ILC, offsetof(struct pt_regs, ilc),); - DEFINE(__PT_TRAP, offsetof(struct pt_regs, trap),); - DEFINE(__PT_SIZE, sizeof(struct pt_regs),); + DEFINE(__PT_ARGS, offsetof(struct pt_regs, args)); + DEFINE(__PT_PSW, offsetof(struct pt_regs, psw)); + DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs)); + DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2)); + DEFINE(__PT_ILC, offsetof(struct pt_regs, ilc)); + DEFINE(__PT_TRAP, offsetof(struct pt_regs, trap)); + DEFINE(__PT_SIZE, sizeof(struct pt_regs)); BLANK(); - DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain),); - DEFINE(__SF_GPRS, offsetof(struct stack_frame, gprs),); - DEFINE(__SF_EMPTY, offsetof(struct stack_frame, empty1),); + DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain)); + DEFINE(__SF_GPRS, offsetof(struct stack_frame, gprs)); + DEFINE(__SF_EMPTY, offsetof(struct stack_frame, empty1)); return 0; } diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 50b85d07ddd2..d7f22226fc4e 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -62,7 +62,6 @@ #include <asm/types.h> #include <asm/uaccess.h> -#include <asm/semaphore.h> #include <net/scm.h> #include <net/sock.h> diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index e89f8c0c42a0..20723a062017 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -162,4 +162,77 @@ struct ucontext32 { compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; +struct __sysctl_args32; +struct stat64_emu31; +struct mmap_arg_struct_emu31; +struct fadvise64_64_args; +struct old_sigaction32; +struct old_sigaction32; + +long sys32_chown16(const char __user * filename, u16 user, u16 group); +long sys32_lchown16(const char __user * filename, u16 user, u16 group); +long sys32_fchown16(unsigned int fd, u16 user, u16 group); +long sys32_setregid16(u16 rgid, u16 egid); +long sys32_setgid16(u16 gid); +long sys32_setreuid16(u16 ruid, u16 euid); +long sys32_setuid16(u16 uid); +long sys32_setresuid16(u16 ruid, u16 euid, u16 suid); +long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid); +long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid); +long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid); +long sys32_setfsuid16(u16 uid); +long sys32_setfsgid16(u16 gid); +long sys32_getgroups16(int gidsetsize, u16 __user *grouplist); +long sys32_setgroups16(int gidsetsize, u16 __user *grouplist); +long sys32_getuid16(void); +long sys32_geteuid16(void); +long sys32_getgid16(void); +long sys32_getegid16(void); +long sys32_ipc(u32 call, int first, int second, int third, u32 ptr); +long sys32_truncate64(const char __user * path, unsigned long high, + unsigned long low); +long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low); +long sys32_sched_rr_get_interval(compat_pid_t pid, + struct compat_timespec __user *interval); +long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, + compat_sigset_t __user *oset, size_t sigsetsize); +long sys32_rt_sigpending(compat_sigset_t __user *set, size_t sigsetsize); +long sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo); +long sys32_execve(void); +long sys32_init_module(void __user *umod, unsigned long len, + const char __user *uargs); +long sys32_delete_module(const char __user *name_user, unsigned int flags); +long sys32_gettimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz); +long sys32_settimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz); +long sys32_pause(void); +long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count, + u32 poshi, u32 poslo); +long sys32_pwrite64(unsigned int fd, const char __user *ubuf, + size_t count, u32 poshi, u32 poslo); +compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count); +long sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, + size_t count); +long sys32_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, + s32 count); +long sys32_sysctl(struct __sysctl_args32 __user *args); +long sys32_stat64(char __user * filename, struct stat64_emu31 __user * statbuf); +long sys32_lstat64(char __user * filename, + struct stat64_emu31 __user * statbuf); +long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf); +long sys32_fstatat64(unsigned int dfd, char __user *filename, + struct stat64_emu31 __user* statbuf, int flag); +unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg); +long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg); +long sys32_read(unsigned int fd, char __user * buf, size_t count); +long sys32_write(unsigned int fd, char __user * buf, size_t count); +long sys32_clone(void); +long sys32_fadvise64(int fd, loff_t offset, size_t len, int advise); +long sys32_fadvise64_64(struct fadvise64_64_args __user *args); +long sys32_sigaction(int sig, const struct old_sigaction32 __user *act, + struct old_sigaction32 __user *oact); +long sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, + struct sigaction32 __user *oact, size_t sigsetsize); +long sys32_sigaltstack(const stack_t32 __user *uss, stack_t32 __user *uoss); #endif /* _ASM_S390X_S390_H */ diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index a5692c460bad..c7f02e777af2 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -29,6 +29,7 @@ #include <asm/lowcore.h> #include "compat_linux.h" #include "compat_ptrace.h" +#include "entry.h" #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -428,6 +429,10 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) /* Default to using normal stack */ sp = (unsigned long) A(regs->gprs[15]); + /* Overflow on alternate signal stack gives SIGSEGV. */ + if (on_sig_stack(sp) && !on_sig_stack((sp - frame_size) & -8UL)) + return (void __user *) -1UL; + /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { if (! sas_ss_flags(sp)) @@ -461,6 +466,9 @@ static int setup_frame32(int sig, struct k_sigaction *ka, if (!access_ok(VERIFY_WRITE, frame, sizeof(sigframe32))) goto give_sigsegv; + if (frame == (void __user *) -1UL) + goto give_sigsegv; + if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32)) goto give_sigsegv; @@ -514,6 +522,9 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, if (!access_ok(VERIFY_WRITE, frame, sizeof(rt_sigframe32))) goto give_sigsegv; + if (frame == (void __user *) -1UL) + goto give_sigsegv; + if (copy_siginfo_to_user32(&frame->info, info)) goto give_sigsegv; diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 1b2f5ce45320..dff0568e67ec 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -17,7 +17,6 @@ #include <linux/ctype.h> #include <linux/sysctl.h> #include <asm/uaccess.h> -#include <asm/semaphore.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> @@ -73,7 +72,7 @@ static ssize_t debug_input(struct file *file, const char __user *user_buf, static int debug_open(struct inode *inode, struct file *file); static int debug_close(struct inode *inode, struct file *file); static debug_info_t* debug_info_create(char *name, int pages_per_area, - int nr_areas, int buf_size); + int nr_areas, int buf_size, mode_t mode); static void debug_info_get(debug_info_t *); static void debug_info_put(debug_info_t *); static int debug_prolog_level_fn(debug_info_t * id, @@ -157,7 +156,7 @@ struct debug_view debug_sprintf_view = { }; /* used by dump analysis tools to determine version of debug feature */ -unsigned int debug_feature_version = __DEBUG_FEATURE_VERSION; +static unsigned int __used debug_feature_version = __DEBUG_FEATURE_VERSION; /* static globals */ @@ -327,7 +326,8 @@ debug_info_free(debug_info_t* db_info){ */ static debug_info_t* -debug_info_create(char *name, int pages_per_area, int nr_areas, int buf_size) +debug_info_create(char *name, int pages_per_area, int nr_areas, int buf_size, + mode_t mode) { debug_info_t* rc; @@ -336,6 +336,8 @@ debug_info_create(char *name, int pages_per_area, int nr_areas, int buf_size) if(!rc) goto out; + rc->mode = mode & ~S_IFMT; + /* create root directory */ rc->debugfs_root_entry = debugfs_create_dir(rc->name, debug_debugfs_root_entry); @@ -676,23 +678,30 @@ debug_close(struct inode *inode, struct file *file) } /* - * debug_register: - * - creates and initializes debug area for the caller - * - returns handle for debug area + * debug_register_mode: + * - Creates and initializes debug area for the caller + * The mode parameter allows to specify access rights for the s390dbf files + * - Returns handle for debug area */ -debug_info_t* -debug_register (char *name, int pages_per_area, int nr_areas, int buf_size) +debug_info_t *debug_register_mode(char *name, int pages_per_area, int nr_areas, + int buf_size, mode_t mode, uid_t uid, + gid_t gid) { debug_info_t *rc = NULL; + /* Since debugfs currently does not support uid/gid other than root, */ + /* we do not allow gid/uid != 0 until we get support for that. */ + if ((uid != 0) || (gid != 0)) + printk(KERN_WARNING "debug: Warning - Currently only uid/gid " + "= 0 are supported. Using root as owner now!"); if (!initialized) BUG(); mutex_lock(&debug_mutex); /* create new debug_info */ - rc = debug_info_create(name, pages_per_area, nr_areas, buf_size); + rc = debug_info_create(name, pages_per_area, nr_areas, buf_size, mode); if(!rc) goto out; debug_register_view(rc, &debug_level_view); @@ -705,6 +714,20 @@ out: mutex_unlock(&debug_mutex); return rc; } +EXPORT_SYMBOL(debug_register_mode); + +/* + * debug_register: + * - creates and initializes debug area for the caller + * - returns handle for debug area + */ + +debug_info_t *debug_register(char *name, int pages_per_area, int nr_areas, + int buf_size) +{ + return debug_register_mode(name, pages_per_area, nr_areas, buf_size, + S_IRUSR | S_IWUSR, 0, 0); +} /* * debug_unregister: @@ -1073,15 +1096,16 @@ debug_register_view(debug_info_t * id, struct debug_view *view) int rc = 0; int i; unsigned long flags; - mode_t mode = S_IFREG; + mode_t mode; struct dentry *pde; if (!id) goto out; - if (view->prolog_proc || view->format_proc || view->header_proc) - mode |= S_IRUSR; - if (view->input_proc) - mode |= S_IWUSR; + mode = (id->mode | S_IFREG) & ~S_IXUGO; + if (!(view->prolog_proc || view->format_proc || view->header_proc)) + mode &= ~(S_IRUSR | S_IRGRP | S_IROTH); + if (!view->input_proc) + mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); pde = debugfs_create_file(view->name, mode, id->debugfs_root_entry, id , &debug_file_ops); if (!pde){ diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 01832c440636..d0e09684b9ce 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -21,6 +21,7 @@ #include <asm/setup.h> #include <asm/cpcmd.h> #include <asm/sclp.h> +#include "entry.h" /* * Create a Kernel NSS if the SAVESYS= parameter is defined @@ -138,11 +139,15 @@ static noinline __init void detect_machine_type(void) /* Running under z/VM ? */ if (cpuinfo->cpu_id.version == 0xff) - machine_flags |= 1; + machine_flags |= MACHINE_FLAG_VM; /* Running on a P/390 ? */ if (cpuinfo->cpu_id.machine == 0x7490) - machine_flags |= 4; + machine_flags |= MACHINE_FLAG_P390; + + /* Running under KVM ? */ + if (cpuinfo->cpu_id.version == 0xfe) + machine_flags |= MACHINE_FLAG_KVM; } #ifdef CONFIG_64BIT @@ -263,6 +268,118 @@ static noinline __init void setup_lowcore_early(void) s390_base_pgm_handler_fn = early_pgm_check_handler; } +static noinline __init void setup_hpage(void) +{ +#ifndef CONFIG_DEBUG_PAGEALLOC + unsigned int facilities; + + facilities = stfl(); + if (!(facilities & (1UL << 23)) || !(facilities & (1UL << 29))) + return; + machine_flags |= MACHINE_FLAG_HPAGE; + __ctl_set_bit(0, 23); +#endif +} + +static __init void detect_mvpg(void) +{ +#ifndef CONFIG_64BIT + int rc; + + asm volatile( + " la 0,0\n" + " mvpg %2,%2\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "0" (-EOPNOTSUPP), "a" (0) : "memory", "cc", "0"); + if (!rc) + machine_flags |= MACHINE_FLAG_MVPG; +#endif +} + +static __init void detect_ieee(void) +{ +#ifndef CONFIG_64BIT + int rc, tmp; + + asm volatile( + " efpc %1,0\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc), "=d" (tmp): "0" (-EOPNOTSUPP) : "cc"); + if (!rc) + machine_flags |= MACHINE_FLAG_IEEE; +#endif +} + +static __init void detect_csp(void) +{ +#ifndef CONFIG_64BIT + int rc; + + asm volatile( + " la 0,0\n" + " la 1,0\n" + " la 2,4\n" + " csp 0,2\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc", "0", "1", "2"); + if (!rc) + machine_flags |= MACHINE_FLAG_CSP; +#endif +} + +static __init void detect_diag9c(void) +{ + unsigned int cpu_address; + int rc; + + cpu_address = stap(); + asm volatile( + " diag %2,0,0x9c\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "0" (-EOPNOTSUPP), "d" (cpu_address) : "cc"); + if (!rc) + machine_flags |= MACHINE_FLAG_DIAG9C; +} + +static __init void detect_diag44(void) +{ +#ifdef CONFIG_64BIT + int rc; + + asm volatile( + " diag 0,0,0x44\n" + "0: la %0,0\n" + "1:\n" + EX_TABLE(0b,1b) + : "=d" (rc) : "0" (-EOPNOTSUPP) : "cc"); + if (!rc) + machine_flags |= MACHINE_FLAG_DIAG44; +#endif +} + +static __init void detect_machine_facilities(void) +{ +#ifdef CONFIG_64BIT + unsigned int facilities; + + facilities = stfl(); + if (facilities & (1 << 28)) + machine_flags |= MACHINE_FLAG_IDTE; + if (facilities & (1 << 23)) + machine_flags |= MACHINE_FLAG_PFMF; + if (facilities & (1 << 4)) + machine_flags |= MACHINE_FLAG_MVCOS; +#endif +} + /* * Save ipl parameters, clear bss memory, initialize storage keys * and create a kernel NSS at startup if the SAVESYS= parm is defined @@ -280,6 +397,13 @@ void __init startup_init(void) create_kernel_nss(); sort_main_extable(); setup_lowcore_early(); + detect_mvpg(); + detect_ieee(); + detect_csp(); + detect_diag9c(); + detect_diag44(); + detect_machine_facilities(); + setup_hpage(); sclp_read_info_early(); sclp_facilities_detect(); memsize = sclp_memory_detect(); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 6766e37fe8ea..bdbb3bcd78a5 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -49,9 +49,9 @@ SP_ILC = STACK_FRAME_OVERHEAD + __PT_ILC SP_TRAP = STACK_FRAME_OVERHEAD + __PT_TRAP SP_SIZE = STACK_FRAME_OVERHEAD + __PT_SIZE -_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK | _TIF_NEED_RESCHED | \ +_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_SINGLE_STEP ) -_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK | _TIF_NEED_RESCHED | \ +_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER @@ -316,7 +316,7 @@ sysc_work: bo BASED(sysc_mcck_pending) tm __TI_flags+3(%r9),_TIF_NEED_RESCHED bo BASED(sysc_reschedule) - tm __TI_flags+3(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK) + tm __TI_flags+3(%r9),_TIF_SIGPENDING bnz BASED(sysc_sigpending) tm __TI_flags+3(%r9),_TIF_RESTART_SVC bo BASED(sysc_restart) @@ -342,7 +342,7 @@ sysc_mcck_pending: br %r1 # TIF bit will be cleared by handler # -# _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal +# _TIF_SIGPENDING is set, call do_signal # sysc_sigpending: ni __TI_flags+3(%r9),255-_TIF_SINGLE_STEP # clear TIF_SINGLE_STEP @@ -657,7 +657,7 @@ io_work: lr %r15,%r1 # # One of the work bits is on. Find out which one. -# Checked are: _TIF_SIGPENDING, _TIF_RESTORE_SIGMASK, _TIF_NEED_RESCHED +# Checked are: _TIF_SIGPENDING, _TIF_NEED_RESCHED # and _TIF_MCCK_PENDING # io_work_loop: @@ -665,7 +665,7 @@ io_work_loop: bo BASED(io_mcck_pending) tm __TI_flags+3(%r9),_TIF_NEED_RESCHED bo BASED(io_reschedule) - tm __TI_flags+3(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK) + tm __TI_flags+3(%r9),_TIF_SIGPENDING bnz BASED(io_sigpending) b BASED(io_restore) io_work_done: @@ -693,7 +693,7 @@ io_reschedule: b BASED(io_work_loop) # -# _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal +# _TIF_SIGPENDING is set, call do_signal # io_sigpending: TRACE_IRQS_ON diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h new file mode 100644 index 000000000000..6b1896345eda --- /dev/null +++ b/arch/s390/kernel/entry.h @@ -0,0 +1,60 @@ +#ifndef _ENTRY_H +#define _ENTRY_H + +#include <linux/types.h> +#include <linux/signal.h> +#include <asm/ptrace.h> + +typedef void pgm_check_handler_t(struct pt_regs *, long); +extern pgm_check_handler_t *pgm_check_table[128]; +pgm_check_handler_t do_protection_exception; +pgm_check_handler_t do_dat_exception; + +extern int sysctl_userprocess_debug; + +void do_single_step(struct pt_regs *regs); +void syscall_trace(struct pt_regs *regs, int entryexit); +void kernel_stack_overflow(struct pt_regs * regs); +void do_signal(struct pt_regs *regs); +int handle_signal32(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, struct pt_regs *regs); + +void do_extint(struct pt_regs *regs, unsigned short code); +int __cpuinit start_secondary(void *cpuvoid); +void __init startup_init(void); +void die(const char * str, struct pt_regs * regs, long err); + +struct new_utsname; +struct mmap_arg_struct; +struct fadvise64_64_args; +struct old_sigaction; +struct sel_arg_struct; + +long sys_pipe(unsigned long __user *fildes); +long sys_mmap2(struct mmap_arg_struct __user *arg); +long old_mmap(struct mmap_arg_struct __user *arg); +long sys_ipc(uint call, int first, unsigned long second, + unsigned long third, void __user *ptr); +long s390x_newuname(struct new_utsname __user *name); +long s390x_personality(unsigned long personality); +long s390_fadvise64(int fd, u32 offset_high, u32 offset_low, + size_t len, int advice); +long s390_fadvise64_64(struct fadvise64_64_args __user *args); +long s390_fallocate(int fd, int mode, loff_t offset, u32 len_high, u32 len_low); +long sys_fork(void); +long sys_clone(void); +long sys_vfork(void); +void execve_tail(void); +long sys_execve(void); +int sys_sigsuspend(int history0, int history1, old_sigset_t mask); +long sys_sigaction(int sig, const struct old_sigaction __user *act, + struct old_sigaction __user *oact); +long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss); +long sys_sigreturn(void); +long sys_rt_sigreturn(void); +long sys32_sigreturn(void); +long sys32_rt_sigreturn(void); +long old_select(struct sel_arg_struct __user *arg); +long sys_ptrace(long request, long pid, long addr, long data); + +#endif /* _ENTRY_H */ diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index efde6e178f6c..5a4a7bcd2bba 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -52,9 +52,9 @@ SP_SIZE = STACK_FRAME_OVERHEAD + __PT_SIZE STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT -_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK | _TIF_NEED_RESCHED | \ +_TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_SINGLE_STEP ) -_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK | _TIF_NEED_RESCHED | \ +_TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) #define BASED(name) name-system_call(%r13) @@ -308,7 +308,7 @@ sysc_work: jo sysc_mcck_pending tm __TI_flags+7(%r9),_TIF_NEED_RESCHED jo sysc_reschedule - tm __TI_flags+7(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK) + tm __TI_flags+7(%r9),_TIF_SIGPENDING jnz sysc_sigpending tm __TI_flags+7(%r9),_TIF_RESTART_SVC jo sysc_restart @@ -332,7 +332,7 @@ sysc_mcck_pending: jg s390_handle_mcck # TIF bit will be cleared by handler # -# _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal +# _TIF_SIGPENDING is set, call do_signal # sysc_sigpending: ni __TI_flags+7(%r9),255-_TIF_SINGLE_STEP # clear TIF_SINGLE_STEP @@ -475,6 +475,7 @@ pgm_check_handler: pgm_no_vtime: #endif lg %r9,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_ARGS(8,%r15),__LC_LAST_BREAK TRACE_IRQS_OFF lgf %r3,__LC_PGM_ILC # load program interruption code lghi %r8,0x7f @@ -647,7 +648,7 @@ io_work_loop: jo io_mcck_pending tm __TI_flags+7(%r9),_TIF_NEED_RESCHED jo io_reschedule - tm __TI_flags+7(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK) + tm __TI_flags+7(%r9),_TIF_SIGPENDING jnz io_sigpending j io_restore io_work_done: @@ -673,7 +674,7 @@ io_reschedule: j io_work_loop # -# _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal +# _TIF_SIGPENDING or is set, call do_signal # io_sigpending: TRACE_IRQS_ON @@ -847,6 +848,7 @@ stack_overflow: je 0f la %r1,__LC_SAVE_AREA+32 0: mvc SP_R12(32,%r15),0(%r1) # move %r12-%r15 to stack + mvc SP_ARGS(8,%r15),__LC_LAST_BREAK xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) # clear back chain la %r2,SP_PTREGS(%r15) # load pt_regs jg kernel_stack_overflow diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index dc364c1419af..a816e2de32b9 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -57,61 +57,6 @@ startup_continue: # l %r14,.Lstartup_init-.LPG1(%r13) basr %r14,%r14 - - l %r12,.Lmflags-.LPG1(%r13) # get address of machine_flags -# -# find out if we have an IEEE fpu -# - mvc __LC_PGM_NEW_PSW(8),.Lpcfpu-.LPG1(%r13) - efpc %r0,0 # test IEEE extract fpc instruction - oi 3(%r12),2 # set IEEE fpu flag -.Lchkfpu: - -# -# find out if we have the CSP instruction -# - mvc __LC_PGM_NEW_PSW(8),.Lpccsp-.LPG1(%r13) - la %r0,0 - lr %r1,%r0 - la %r2,4 - csp %r0,%r2 # Test CSP instruction - oi 3(%r12),8 # set CSP flag -.Lchkcsp: - -# -# find out if we have the MVPG instruction -# - mvc __LC_PGM_NEW_PSW(8),.Lpcmvpg-.LPG1(%r13) - sr %r0,%r0 - la %r1,0 - la %r2,0 - mvpg %r1,%r2 # Test CSP instruction - oi 3(%r12),16 # set MVPG flag -.Lchkmvpg: - -# -# find out if we have the IDTE instruction -# - mvc __LC_PGM_NEW_PSW(8),.Lpcidte-.LPG1(%r13) - .long 0xb2b10000 # store facility list - tm 0xc8,0x08 # check bit for clearing-by-ASCE - bno .Lchkidte-.LPG1(%r13) - lhi %r1,2094 - lhi %r2,0 - .long 0xb98e2001 - oi 3(%r12),0x80 # set IDTE flag -.Lchkidte: - -# -# find out if the diag 0x9c is available -# - mvc __LC_PGM_NEW_PSW(8),.Lpcdiag9c-.LPG1(%r13) - stap __LC_CPUID+4 # store cpu address - lh %r1,__LC_CPUID+4 - diag %r1,0,0x9c # test diag 0x9c - oi 2(%r12),1 # set diag9c flag -.Lchkdiag9c: - lpsw .Lentry-.LPG1(13) # jump to _stext in primary-space, # virtual and never return ... .align 8 @@ -132,13 +77,7 @@ startup_continue: .long 0 # cr13: home space segment table .long 0xc0000000 # cr14: machine check handling off .long 0 # cr15: linkage stack operations -.Lpcfpu:.long 0x00080000,0x80000000 + .Lchkfpu -.Lpccsp:.long 0x00080000,0x80000000 + .Lchkcsp -.Lpcmvpg:.long 0x00080000,0x80000000 + .Lchkmvpg -.Lpcidte:.long 0x00080000,0x80000000 + .Lchkidte -.Lpcdiag9c:.long 0x00080000,0x80000000 + .Lchkdiag9c .Lmchunk:.long memory_chunk -.Lmflags:.long machine_flags .Lbss_bgn: .long __bss_start .Lbss_end: .long _end .Lparmaddr: .long PARMAREA diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 79dccd206a6e..1d06961e87b3 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -125,73 +125,11 @@ startup_continue: # and create a kernel NSS if the SAVESYS= parm is defined # brasl %r14,startup_init - # set program check new psw mask - mvc __LC_PGM_NEW_PSW(8),.Lpcmsk-.LPG1(%r13) - larl %r12,machine_flags -# -# find out if we have the MVPG instruction -# - la %r1,0f-.LPG1(%r13) # set program check address - stg %r1,__LC_PGM_NEW_PSW+8 - sgr %r0,%r0 - lghi %r1,0 - lghi %r2,0 - mvpg %r1,%r2 # test MVPG instruction - oi 7(%r12),16 # set MVPG flag -0: - -# -# find out if the diag 0x44 works in 64 bit mode -# - la %r1,0f-.LPG1(%r13) # set program check address - stg %r1,__LC_PGM_NEW_PSW+8 - diag 0,0,0x44 # test diag 0x44 - oi 7(%r12),32 # set diag44 flag -0: - -# -# find out if we have the IDTE instruction -# - la %r1,0f-.LPG1(%r13) # set program check address - stg %r1,__LC_PGM_NEW_PSW+8 - .long 0xb2b10000 # store facility list - tm 0xc8,0x08 # check bit for clearing-by-ASCE - bno 0f-.LPG1(%r13) - lhi %r1,2048 - lhi %r2,0 - .long 0xb98e2001 - oi 7(%r12),0x80 # set IDTE flag -0: - -# -# find out if the diag 0x9c is available -# - la %r1,0f-.LPG1(%r13) # set program check address - stg %r1,__LC_PGM_NEW_PSW+8 - stap __LC_CPUID+4 # store cpu address - lh %r1,__LC_CPUID+4 - diag %r1,0,0x9c # test diag 0x9c - oi 6(%r12),1 # set diag9c flag -0: - -# -# find out if we have the MVCOS instruction -# - la %r1,0f-.LPG1(%r13) # set program check address - stg %r1,__LC_PGM_NEW_PSW+8 - .short 0xc800 # mvcos 0(%r0),0(%r0),%r0 - .short 0x0000 - .short 0x0000 -0: tm 0x8f,0x13 # special-operation exception? - bno 1f-.LPG1(%r13) # if yes, MVCOS is present - oi 6(%r12),2 # set MVCOS flag -1: - lpswe .Lentry-.LPG1(13) # jump to _stext in primary-space, # virtual and never return ... .align 16 .Lentry:.quad 0x0000000180000000,_stext -.Lctl: .quad 0x04b50002 # cr0: various things +.Lctl: .quad 0x04350002 # cr0: various things .quad 0 # cr1: primary space segment table .quad .Lduct # cr2: dispatchable unit control table .quad 0 # cr3: instruction authorization diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 375232c46c7a..532542447d66 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -655,7 +655,7 @@ static struct kobj_attribute reipl_type_attr = static struct kset *reipl_kset; -void reipl_run(struct shutdown_trigger *trigger) +static void reipl_run(struct shutdown_trigger *trigger) { struct ccw_dev_id devid; static char buf[100]; diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index c36d8123ca14..c59a86dca584 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -60,8 +60,6 @@ init_IRQ(void) /* * Switch to the asynchronous interrupt stack for softirq execution. */ -extern void __do_softirq(void); - asmlinkage void do_softirq(void) { unsigned long flags, old, new; diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index c5549a206284..ed04d1372d5d 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -360,7 +360,7 @@ no_kprobe: * - When the probed function returns, this probe * causes the handlers to fire */ -void kretprobe_trampoline_holder(void) +static void __used kretprobe_trampoline_holder(void) { asm volatile(".global kretprobe_trampoline\n" "kretprobe_trampoline: bcr 0,0\n"); diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index ce203154d8ce..7920861109d2 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -36,6 +36,8 @@ #include <linux/module.h> #include <linux/notifier.h> #include <linux/utsname.h> +#include <linux/tick.h> +#include <linux/elfcore.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -44,6 +46,7 @@ #include <asm/irq.h> #include <asm/timer.h> #include <asm/cpu.h> +#include "entry.h" asmlinkage void ret_from_fork(void) asm ("ret_from_fork"); @@ -76,6 +79,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk) * Need to know about CPUs going idle? */ static ATOMIC_NOTIFIER_HEAD(idle_chain); +DEFINE_PER_CPU(struct s390_idle_data, s390_idle); int register_idle_notifier(struct notifier_block *nb) { @@ -89,9 +93,33 @@ int unregister_idle_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_idle_notifier); -void do_monitor_call(struct pt_regs *regs, long interruption_code) +static int s390_idle_enter(void) +{ + struct s390_idle_data *idle; + int nr_calls = 0; + void *hcpu; + int rc; + + hcpu = (void *)(long)smp_processor_id(); + rc = __atomic_notifier_call_chain(&idle_chain, S390_CPU_IDLE, hcpu, -1, + &nr_calls); + if (rc == NOTIFY_BAD) { + nr_calls--; + __atomic_notifier_call_chain(&idle_chain, S390_CPU_NOT_IDLE, + hcpu, nr_calls, NULL); + return rc; + } + idle = &__get_cpu_var(s390_idle); + spin_lock(&idle->lock); + idle->idle_count++; + idle->in_idle = 1; + idle->idle_enter = get_clock(); + spin_unlock(&idle->lock); + return NOTIFY_OK; +} + +void s390_idle_leave(void) { -#ifdef CONFIG_SMP struct s390_idle_data *idle; idle = &__get_cpu_var(s390_idle); @@ -99,10 +127,6 @@ void do_monitor_call(struct pt_regs *regs, long interruption_code) idle->idle_time += get_clock() - idle->idle_enter; idle->in_idle = 0; spin_unlock(&idle->lock); -#endif - /* disable monitor call class 0 */ - __ctl_clear_bit(8, 15); - atomic_notifier_call_chain(&idle_chain, S390_CPU_NOT_IDLE, (void *)(long) smp_processor_id()); } @@ -113,61 +137,30 @@ extern void s390_handle_mcck(void); */ static void default_idle(void) { - int cpu, rc; - int nr_calls = 0; - void *hcpu; -#ifdef CONFIG_SMP - struct s390_idle_data *idle; -#endif - /* CPU is going idle. */ - cpu = smp_processor_id(); - hcpu = (void *)(long)cpu; local_irq_disable(); if (need_resched()) { local_irq_enable(); return; } - - rc = __atomic_notifier_call_chain(&idle_chain, S390_CPU_IDLE, hcpu, -1, - &nr_calls); - if (rc == NOTIFY_BAD) { - nr_calls--; - __atomic_notifier_call_chain(&idle_chain, S390_CPU_NOT_IDLE, - hcpu, nr_calls, NULL); + if (s390_idle_enter() == NOTIFY_BAD) { local_irq_enable(); return; } - - /* enable monitor call class 0 */ - __ctl_set_bit(8, 15); - #ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(cpu)) { + if (cpu_is_offline(smp_processor_id())) { preempt_enable_no_resched(); cpu_die(); } #endif - local_mcck_disable(); if (test_thread_flag(TIF_MCCK_PENDING)) { local_mcck_enable(); - /* disable monitor call class 0 */ - __ctl_clear_bit(8, 15); - atomic_notifier_call_chain(&idle_chain, S390_CPU_NOT_IDLE, - hcpu); + s390_idle_leave(); local_irq_enable(); s390_handle_mcck(); return; } -#ifdef CONFIG_SMP - idle = &__get_cpu_var(s390_idle); - spin_lock(&idle->lock); - idle->idle_count++; - idle->in_idle = 1; - idle->idle_enter = get_clock(); - spin_unlock(&idle->lock); -#endif trace_hardirqs_on(); /* Wait for external, I/O or machine check interrupt. */ __load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT | @@ -177,32 +170,16 @@ static void default_idle(void) void cpu_idle(void) { for (;;) { + tick_nohz_stop_sched_tick(); while (!need_resched()) default_idle(); - + tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); schedule(); preempt_disable(); } } -void show_regs(struct pt_regs *regs) -{ - print_modules(); - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); - show_registers(regs); - /* Show stack backtrace if pt_regs is from kernel mode */ - if (!(regs->psw.mask & PSW_MASK_PSTATE)) - show_trace(NULL, (unsigned long *) regs->gprs[15]); -} - extern void kernel_thread_starter(void); asm( diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 6e036bae9875..7f4270163744 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -41,6 +41,7 @@ #include <asm/system.h> #include <asm/uaccess.h> #include <asm/unistd.h> +#include "entry.h" #ifdef CONFIG_COMPAT #include "compat_ptrace.h" @@ -606,38 +607,8 @@ do_ptrace_emu31(struct task_struct *child, long request, long addr, long data) } #endif -#define PT32_IEEE_IP 0x13c - -static int -do_ptrace(struct task_struct *child, long request, long addr, long data) +long arch_ptrace(struct task_struct *child, long request, long addr, long data) { - int ret; - - if (request == PTRACE_ATTACH) - return ptrace_attach(child); - - /* - * Special cases to get/store the ieee instructions pointer. - */ - if (child == current) { - if (request == PTRACE_PEEKUSR && addr == PT_IEEE_IP) - return peek_user(child, addr, data); - if (request == PTRACE_POKEUSR && addr == PT_IEEE_IP) - return poke_user(child, addr, data); -#ifdef CONFIG_COMPAT - if (request == PTRACE_PEEKUSR && - addr == PT32_IEEE_IP && test_thread_flag(TIF_31BIT)) - return peek_user_emu31(child, addr, data); - if (request == PTRACE_POKEUSR && - addr == PT32_IEEE_IP && test_thread_flag(TIF_31BIT)) - return poke_user_emu31(child, addr, data); -#endif - } - - ret = ptrace_check_attach(child, request == PTRACE_KILL); - if (ret < 0) - return ret; - switch (request) { case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */ @@ -692,31 +663,6 @@ do_ptrace(struct task_struct *child, long request, long addr, long data) return -EIO; } -asmlinkage long -sys_ptrace(long request, long pid, long addr, long data) -{ - struct task_struct *child; - int ret; - - lock_kernel(); - if (request == PTRACE_TRACEME) { - ret = ptrace_traceme(); - goto out; - } - - child = ptrace_get_task_struct(pid); - if (IS_ERR(child)) { - ret = PTR_ERR(child); - goto out; - } - - ret = do_ptrace(child, request, addr, data); - put_task_struct(child); -out: - unlock_kernel(); - return ret; -} - asmlinkage void syscall_trace(struct pt_regs *regs, int entryexit) { diff --git a/arch/s390/kernel/s390_ext.c b/arch/s390/kernel/s390_ext.c index acf93dba7727..e019b419efc6 100644 --- a/arch/s390/kernel/s390_ext.c +++ b/arch/s390/kernel/s390_ext.c @@ -13,11 +13,12 @@ #include <linux/errno.h> #include <linux/kernel_stat.h> #include <linux/interrupt.h> - +#include <asm/cpu.h> #include <asm/lowcore.h> #include <asm/s390_ext.h> #include <asm/irq_regs.h> #include <asm/irq.h> +#include "entry.h" /* * ext_int_hash[index] is the start of the list for all external interrupts @@ -119,13 +120,10 @@ void do_extint(struct pt_regs *regs, unsigned short code) old_regs = set_irq_regs(regs); irq_enter(); - asm volatile ("mc 0,0"); - if (S390_lowcore.int_clock >= S390_lowcore.jiffy_timer) - /** - * Make sure that the i/o interrupt did not "overtake" - * the last HZ timer interrupt. - */ - account_ticks(S390_lowcore.int_clock); + s390_idle_check(); + if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) + /* Serve timer interrupts first. */ + clock_comparator_work(); kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++; index = ext_hash(code); for (p = ext_int_hash[index]; p; p = p->next) { diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c index 7234c737f825..48238a114ce9 100644 --- a/arch/s390/kernel/s390_ksyms.c +++ b/arch/s390/kernel/s390_ksyms.c @@ -27,13 +27,6 @@ EXPORT_SYMBOL(_zb_findmap); EXPORT_SYMBOL(_sb_findmap); /* - * semaphore ops - */ -EXPORT_SYMBOL(__up); -EXPORT_SYMBOL(__down); -EXPORT_SYMBOL(__down_interruptible); - -/* * binfmt_elf loader */ extern int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs); diff --git a/arch/s390/kernel/semaphore.c b/arch/s390/kernel/semaphore.c deleted file mode 100644 index 191303f6c1d8..000000000000 --- a/arch/s390/kernel/semaphore.c +++ /dev/null @@ -1,108 +0,0 @@ -/* - * linux/arch/s390/kernel/semaphore.c - * - * S390 version - * Copyright (C) 1998-2000 IBM Corporation - * Author(s): Martin Schwidefsky - * - * Derived from "linux/arch/i386/kernel/semaphore.c - * Copyright (C) 1999, Linus Torvalds - * - */ -#include <linux/sched.h> -#include <linux/errno.h> -#include <linux/init.h> - -#include <asm/semaphore.h> - -/* - * Atomically update sem->count. Equivalent to: - * old_val = sem->count.counter; - * new_val = ((old_val >= 0) ? old_val : 0) + incr; - * sem->count.counter = new_val; - * return old_val; - */ -static inline int __sem_update_count(struct semaphore *sem, int incr) -{ - int old_val, new_val; - - asm volatile( - " l %0,0(%3)\n" - "0: ltr %1,%0\n" - " jhe 1f\n" - " lhi %1,0\n" - "1: ar %1,%4\n" - " cs %0,%1,0(%3)\n" - " jl 0b\n" - : "=&d" (old_val), "=&d" (new_val), "=m" (sem->count) - : "a" (&sem->count), "d" (incr), "m" (sem->count) - : "cc"); - return old_val; -} - -/* - * The inline function up() incremented count but the result - * was <= 0. This indicates that some process is waiting on - * the semaphore. The semaphore is free and we'll wake the - * first sleeping process, so we set count to 1 unless some - * other cpu has called up in the meantime in which case - * we just increment count by 1. - */ -void __up(struct semaphore *sem) -{ - __sem_update_count(sem, 1); - wake_up(&sem->wait); -} - -/* - * The inline function down() decremented count and the result - * was < 0. The wait loop will atomically test and update the - * semaphore counter following the rules: - * count > 0: decrement count, wake up queue and exit. - * count <= 0: set count to -1, go to sleep. - */ -void __sched __down(struct semaphore * sem) -{ - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - - __set_task_state(tsk, TASK_UNINTERRUPTIBLE); - add_wait_queue_exclusive(&sem->wait, &wait); - while (__sem_update_count(sem, -1) <= 0) { - schedule(); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); - } - remove_wait_queue(&sem->wait, &wait); - __set_task_state(tsk, TASK_RUNNING); - wake_up(&sem->wait); -} - -/* - * Same as __down() with an additional test for signals. - * If a signal is pending the count is updated as follows: - * count > 0: wake up queue and exit. - * count <= 0: set count to 0, wake up queue and exit. - */ -int __sched __down_interruptible(struct semaphore * sem) -{ - int retval = 0; - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - - __set_task_state(tsk, TASK_INTERRUPTIBLE); - add_wait_queue_exclusive(&sem->wait, &wait); - while (__sem_update_count(sem, -1) <= 0) { - if (signal_pending(current)) { - __sem_update_count(sem, 0); - retval = -EINTR; - break; - } - schedule(); - set_task_state(tsk, TASK_INTERRUPTIBLE); - } - remove_wait_queue(&sem->wait, &wait); - __set_task_state(tsk, TASK_RUNNING); - wake_up(&sem->wait); - return retval; -} - diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 290e504061a3..2bc70b6e876a 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -39,6 +39,7 @@ #include <linux/pfn.h> #include <linux/ctype.h> #include <linux/reboot.h> +#include <linux/topology.h> #include <asm/ipl.h> #include <asm/uaccess.h> @@ -72,7 +73,7 @@ EXPORT_SYMBOL(uaccess); unsigned int console_mode = 0; unsigned int console_devno = -1; unsigned int console_irq = -1; -unsigned long machine_flags = 0; +unsigned long machine_flags; unsigned long elf_hwcap = 0; char elf_platform[ELF_PLATFORM_SIZE]; @@ -315,7 +316,11 @@ static int __init early_parse_ipldelay(char *p) early_param("ipldelay", early_parse_ipldelay); #ifdef CONFIG_S390_SWITCH_AMODE +#ifdef CONFIG_PGSTE +unsigned int switch_amode = 1; +#else unsigned int switch_amode = 0; +#endif EXPORT_SYMBOL_GPL(switch_amode); static void set_amode_and_uaccess(unsigned long user_amode, @@ -427,7 +432,7 @@ setup_lowcore(void) lc->io_new_psw.mask = psw_kernel_bits; lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; lc->ipl_device = S390_lowcore.ipl_device; - lc->jiffy_timer = -1LL; + lc->clock_comparator = -1ULL; lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE; lc->async_stack = (unsigned long) __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0) + ASYNC_SIZE; @@ -678,16 +683,7 @@ setup_memory(void) #endif } -static __init unsigned int stfl(void) -{ - asm volatile( - " .insn s,0xb2b10000,0(0)\n" /* stfl */ - "0:\n" - EX_TABLE(0b,0b)); - return S390_lowcore.stfl_fac_list; -} - -static __init int stfle(unsigned long long *list, int doublewords) +static int __init __stfle(unsigned long long *list, int doublewords) { typedef struct { unsigned long long _[doublewords]; } addrtype; register unsigned long __nr asm("0") = doublewords - 1; @@ -697,6 +693,13 @@ static __init int stfle(unsigned long long *list, int doublewords) return __nr + 1; } +int __init stfle(unsigned long long *list, int doublewords) +{ + if (!(stfl() & (1UL << 24))) + return -EOPNOTSUPP; + return __stfle(list, doublewords); +} + /* * Setup hardware capabilities. */ @@ -741,11 +744,14 @@ static void __init setup_hwcaps(void) * HWCAP_S390_DFP bit 6. */ if ((elf_hwcap & (1UL << 2)) && - stfle(&facility_list_extended, 1) > 0) { + __stfle(&facility_list_extended, 1) > 0) { if (facility_list_extended & (1ULL << (64 - 43))) elf_hwcap |= 1UL << 6; } + if (MACHINE_HAS_HPAGE) + elf_hwcap |= 1UL << 7; + switch (cpuinfo->cpu_id.machine) { case 0x9672: #if !defined(CONFIG_64BIT) @@ -789,9 +795,13 @@ setup_arch(char **cmdline_p) "This machine has an IEEE fpu\n" : "This machine has no IEEE fpu\n"); #else /* CONFIG_64BIT */ - printk((MACHINE_IS_VM) ? - "We are running under VM (64 bit mode)\n" : - "We are running native (64 bit mode)\n"); + if (MACHINE_IS_VM) + printk("We are running under VM (64 bit mode)\n"); + else if (MACHINE_IS_KVM) { + printk("We are running under KVM (64 bit mode)\n"); + add_preferred_console("ttyS", 1, NULL); + } else + printk("We are running native (64 bit mode)\n"); #endif /* CONFIG_64BIT */ /* Save unparsed command line copy for /proc/cmdline */ @@ -823,6 +833,7 @@ setup_arch(char **cmdline_p) cpu_init(); __cpu_logical_map[0] = S390_lowcore.cpu_data.cpu_addr; + s390_init_cpu_topology(); /* * Setup capabilities (ELF_HWCAP & ELF_PLATFORM). @@ -864,8 +875,9 @@ void __cpuinit print_cpu_info(struct cpuinfo_S390 *cpuinfo) static int show_cpuinfo(struct seq_file *m, void *v) { - static const char *hwcap_str[7] = { - "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp" + static const char *hwcap_str[8] = { + "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", + "edat" }; struct cpuinfo_S390 *cpuinfo; unsigned long n = (unsigned long) v - 1; @@ -880,7 +892,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) num_online_cpus(), loops_per_jiffy/(500000/HZ), (loops_per_jiffy/(5000/HZ))%100); seq_puts(m, "features\t: "); - for (i = 0; i < 7; i++) + for (i = 0; i < 8; i++) if (hwcap_str[i] && (elf_hwcap & (1UL << i))) seq_printf(m, "%s ", hwcap_str[i]); seq_puts(m, "\n"); diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 4449bf32cbf1..b97682040215 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -27,6 +27,7 @@ #include <asm/ucontext.h> #include <asm/uaccess.h> #include <asm/lowcore.h> +#include "entry.h" #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -235,6 +236,10 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) /* Default to using normal stack */ sp = regs->gprs[15]; + /* Overflow on alternate signal stack gives SIGSEGV. */ + if (on_sig_stack(sp) && !on_sig_stack((sp - frame_size) & -8UL)) + return (void __user *) -1UL; + /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { if (! sas_ss_flags(sp)) @@ -270,6 +275,9 @@ static int setup_frame(int sig, struct k_sigaction *ka, if (!access_ok(VERIFY_WRITE, frame, sizeof(sigframe))) goto give_sigsegv; + if (frame == (void __user *) -1UL) + goto give_sigsegv; + if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE)) goto give_sigsegv; @@ -327,6 +335,9 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, if (!access_ok(VERIFY_WRITE, frame, sizeof(rt_sigframe))) goto give_sigsegv; + if (frame == (void __user *) -1UL) + goto give_sigsegv; + if (copy_siginfo_to_user(&frame->info, info)) goto give_sigsegv; @@ -474,11 +485,6 @@ void do_signal(struct pt_regs *regs) int ret; #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_31BIT)) { - extern int handle_signal32(unsigned long sig, - struct k_sigaction *ka, - siginfo_t *info, - sigset_t *oldset, - struct pt_regs *regs); ret = handle_signal32(signr, &ka, &info, oldset, regs); } else diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 8f894d380a62..0aeb290060d9 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -44,6 +44,7 @@ #include <asm/lowcore.h> #include <asm/sclp.h> #include <asm/cpu.h> +#include "entry.h" /* * An array with a pointer the lowcore of every CPU. @@ -67,13 +68,12 @@ enum s390_cpu_state { CPU_STATE_CONFIGURED, }; -#ifdef CONFIG_HOTPLUG_CPU -static DEFINE_MUTEX(smp_cpu_state_mutex); -#endif +DEFINE_MUTEX(smp_cpu_state_mutex); +int smp_cpu_polarization[NR_CPUS]; static int smp_cpu_state[NR_CPUS]; +static int cpu_management; static DEFINE_PER_CPU(struct cpu, cpu_devices); -DEFINE_PER_CPU(struct s390_idle_data, s390_idle); static void smp_ext_bitcall(int, ec_bit_sig); @@ -298,7 +298,7 @@ static void smp_ext_bitcall(int cpu, ec_bit_sig sig) /* * this function sends a 'purge tlb' signal to another CPU. */ -void smp_ptlb_callback(void *info) +static void smp_ptlb_callback(void *info) { __tlb_flush_local(); } @@ -456,6 +456,7 @@ static int smp_rescan_cpus_sigp(cpumask_t avail) if (cpu_known(cpu_id)) continue; __cpu_logical_map[logical_cpu] = cpu_id; + smp_cpu_polarization[logical_cpu] = POLARIZATION_UNKNWN; if (!cpu_stopped(logical_cpu)) continue; cpu_set(logical_cpu, cpu_present_map); @@ -489,6 +490,7 @@ static int smp_rescan_cpus_sclp(cpumask_t avail) if (cpu_known(cpu_id)) continue; __cpu_logical_map[logical_cpu] = cpu_id; + smp_cpu_polarization[logical_cpu] = POLARIZATION_UNKNWN; cpu_set(logical_cpu, cpu_present_map); if (cpu >= info->configured) smp_cpu_state[logical_cpu] = CPU_STATE_STANDBY; @@ -503,7 +505,7 @@ out: return rc; } -static int smp_rescan_cpus(void) +static int __smp_rescan_cpus(void) { cpumask_t avail; @@ -568,7 +570,7 @@ out: kfree(info); printk(KERN_INFO "CPUs: %d configured, %d standby\n", c_cpus, s_cpus); get_online_cpus(); - smp_rescan_cpus(); + __smp_rescan_cpus(); put_online_cpus(); } @@ -846,6 +848,7 @@ void __init smp_prepare_boot_cpu(void) S390_lowcore.percpu_offset = __per_cpu_offset[0]; current_set[0] = current; smp_cpu_state[0] = CPU_STATE_CONFIGURED; + smp_cpu_polarization[0] = POLARIZATION_UNKNWN; spin_lock_init(&(&__get_cpu_var(s390_idle))->lock); } @@ -887,8 +890,8 @@ static ssize_t cpu_configure_store(struct sys_device *dev, const char *buf, if (val != 0 && val != 1) return -EINVAL; - mutex_lock(&smp_cpu_state_mutex); get_online_cpus(); + mutex_lock(&smp_cpu_state_mutex); rc = -EBUSY; if (cpu_online(cpu)) goto out; @@ -897,28 +900,60 @@ static ssize_t cpu_configure_store(struct sys_device *dev, const char *buf, case 0: if (smp_cpu_state[cpu] == CPU_STATE_CONFIGURED) { rc = sclp_cpu_deconfigure(__cpu_logical_map[cpu]); - if (!rc) + if (!rc) { smp_cpu_state[cpu] = CPU_STATE_STANDBY; + smp_cpu_polarization[cpu] = POLARIZATION_UNKNWN; + } } break; case 1: if (smp_cpu_state[cpu] == CPU_STATE_STANDBY) { rc = sclp_cpu_configure(__cpu_logical_map[cpu]); - if (!rc) + if (!rc) { smp_cpu_state[cpu] = CPU_STATE_CONFIGURED; + smp_cpu_polarization[cpu] = POLARIZATION_UNKNWN; + } } break; default: break; } out: - put_online_cpus(); mutex_unlock(&smp_cpu_state_mutex); + put_online_cpus(); return rc ? rc : count; } static SYSDEV_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store); #endif /* CONFIG_HOTPLUG_CPU */ +static ssize_t cpu_polarization_show(struct sys_device *dev, char *buf) +{ + int cpu = dev->id; + ssize_t count; + + mutex_lock(&smp_cpu_state_mutex); + switch (smp_cpu_polarization[cpu]) { + case POLARIZATION_HRZ: + count = sprintf(buf, "horizontal\n"); + break; + case POLARIZATION_VL: + count = sprintf(buf, "vertical:low\n"); + break; + case POLARIZATION_VM: + count = sprintf(buf, "vertical:medium\n"); + break; + case POLARIZATION_VH: + count = sprintf(buf, "vertical:high\n"); + break; + default: + count = sprintf(buf, "unknown\n"); + break; + } + mutex_unlock(&smp_cpu_state_mutex); + return count; +} +static SYSDEV_ATTR(polarization, 0444, cpu_polarization_show, NULL); + static ssize_t show_cpu_address(struct sys_device *dev, char *buf) { return sprintf(buf, "%d\n", __cpu_logical_map[dev->id]); @@ -931,6 +966,7 @@ static struct attribute *cpu_common_attrs[] = { &attr_configure.attr, #endif &attr_address.attr, + &attr_polarization.attr, NULL, }; @@ -1052,17 +1088,17 @@ out: } #ifdef CONFIG_HOTPLUG_CPU -static ssize_t __ref rescan_store(struct sys_device *dev, - const char *buf, size_t count) + +int smp_rescan_cpus(void) { cpumask_t newcpus; int cpu; int rc; - mutex_lock(&smp_cpu_state_mutex); get_online_cpus(); + mutex_lock(&smp_cpu_state_mutex); newcpus = cpu_present_map; - rc = smp_rescan_cpus(); + rc = __smp_rescan_cpus(); if (rc) goto out; cpus_andnot(newcpus, cpu_present_map, newcpus); @@ -1073,13 +1109,59 @@ static ssize_t __ref rescan_store(struct sys_device *dev, } rc = 0; out: - put_online_cpus(); mutex_unlock(&smp_cpu_state_mutex); + put_online_cpus(); + if (!cpus_empty(newcpus)) + topology_schedule_update(); + return rc; +} + +static ssize_t __ref rescan_store(struct sys_device *dev, const char *buf, + size_t count) +{ + int rc; + + rc = smp_rescan_cpus(); return rc ? rc : count; } static SYSDEV_ATTR(rescan, 0200, NULL, rescan_store); #endif /* CONFIG_HOTPLUG_CPU */ +static ssize_t dispatching_show(struct sys_device *dev, char *buf) +{ + ssize_t count; + + mutex_lock(&smp_cpu_state_mutex); + count = sprintf(buf, "%d\n", cpu_management); + mutex_unlock(&smp_cpu_state_mutex); + return count; +} + +static ssize_t dispatching_store(struct sys_device *dev, const char *buf, + size_t count) +{ + int val, rc; + char delim; + + if (sscanf(buf, "%d %c", &val, &delim) != 1) + return -EINVAL; + if (val != 0 && val != 1) + return -EINVAL; + rc = 0; + get_online_cpus(); + mutex_lock(&smp_cpu_state_mutex); + if (cpu_management == val) + goto out; + rc = topology_set_cpu_management(val); + if (!rc) + cpu_management = val; +out: + mutex_unlock(&smp_cpu_state_mutex); + put_online_cpus(); + return rc ? rc : count; +} +static SYSDEV_ATTR(dispatching, 0644, dispatching_show, dispatching_store); + static int __init topology_init(void) { int cpu; @@ -1093,6 +1175,10 @@ static int __init topology_init(void) if (rc) return rc; #endif + rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj, + &attr_dispatching.attr); + if (rc) + return rc; for_each_present_cpu(cpu) { rc = smp_add_present_cpu(cpu); if (rc) diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index fefee99f28aa..988d0d64c2c8 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -29,8 +29,8 @@ #include <linux/personality.h> #include <linux/unistd.h> #include <linux/ipc.h> - #include <asm/uaccess.h> +#include "entry.h" /* * sys_pipe() is the normal C calling standard for creating diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index cb232c155360..7aec676fefd5 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -30,7 +30,7 @@ #include <linux/timex.h> #include <linux/notifier.h> #include <linux/clocksource.h> - +#include <linux/clockchips.h> #include <asm/uaccess.h> #include <asm/delay.h> #include <asm/s390_ext.h> @@ -39,6 +39,7 @@ #include <asm/irq_regs.h> #include <asm/timer.h> #include <asm/etr.h> +#include <asm/cio.h> /* change this if you have some constant time drift */ #define USECS_PER_JIFFY ((unsigned long) 1000000/HZ) @@ -57,16 +58,16 @@ static ext_int_info_t ext_int_info_cc; static ext_int_info_t ext_int_etr_cc; -static u64 init_timer_cc; static u64 jiffies_timer_cc; -static u64 xtime_cc; + +static DEFINE_PER_CPU(struct clock_event_device, comparators); /* * Scheduler clock - returns current time in nanosec units. */ unsigned long long sched_clock(void) { - return ((get_clock() - jiffies_timer_cc) * 125) >> 9; + return ((get_clock_xt() - jiffies_timer_cc) * 125) >> 9; } /* @@ -95,162 +96,40 @@ void tod_to_timeval(__u64 todval, struct timespec *xtime) #define s390_do_profile() do { ; } while(0) #endif /* CONFIG_PROFILING */ -/* - * Advance the per cpu tick counter up to the time given with the - * "time" argument. The per cpu update consists of accounting - * the virtual cpu time, calling update_process_times and calling - * the profiling hook. If xtime is before time it is advanced as well. - */ -void account_ticks(u64 time) +void clock_comparator_work(void) { - __u32 ticks; - __u64 tmp; - - /* Calculate how many ticks have passed. */ - if (time < S390_lowcore.jiffy_timer) - return; - tmp = time - S390_lowcore.jiffy_timer; - if (tmp >= 2*CLK_TICKS_PER_JIFFY) { /* more than two ticks ? */ - ticks = __div(tmp, CLK_TICKS_PER_JIFFY) + 1; - S390_lowcore.jiffy_timer += - CLK_TICKS_PER_JIFFY * (__u64) ticks; - } else if (tmp >= CLK_TICKS_PER_JIFFY) { - ticks = 2; - S390_lowcore.jiffy_timer += 2*CLK_TICKS_PER_JIFFY; - } else { - ticks = 1; - S390_lowcore.jiffy_timer += CLK_TICKS_PER_JIFFY; - } - -#ifdef CONFIG_SMP - /* - * Do not rely on the boot cpu to do the calls to do_timer. - * Spread it over all cpus instead. - */ - write_seqlock(&xtime_lock); - if (S390_lowcore.jiffy_timer > xtime_cc) { - __u32 xticks; - tmp = S390_lowcore.jiffy_timer - xtime_cc; - if (tmp >= 2*CLK_TICKS_PER_JIFFY) { - xticks = __div(tmp, CLK_TICKS_PER_JIFFY); - xtime_cc += (__u64) xticks * CLK_TICKS_PER_JIFFY; - } else { - xticks = 1; - xtime_cc += CLK_TICKS_PER_JIFFY; - } - do_timer(xticks); - } - write_sequnlock(&xtime_lock); -#else - do_timer(ticks); -#endif - - while (ticks--) - update_process_times(user_mode(get_irq_regs())); + struct clock_event_device *cd; + S390_lowcore.clock_comparator = -1ULL; + set_clock_comparator(S390_lowcore.clock_comparator); + cd = &__get_cpu_var(comparators); + cd->event_handler(cd); s390_do_profile(); } -#ifdef CONFIG_NO_IDLE_HZ - -#ifdef CONFIG_NO_IDLE_HZ_INIT -int sysctl_hz_timer = 0; -#else -int sysctl_hz_timer = 1; -#endif - -/* - * Stop the HZ tick on the current CPU. - * Only cpu_idle may call this function. - */ -static void stop_hz_timer(void) -{ - unsigned long flags; - unsigned long seq, next; - __u64 timer, todval; - int cpu = smp_processor_id(); - - if (sysctl_hz_timer != 0) - return; - - cpu_set(cpu, nohz_cpu_mask); - - /* - * Leave the clock comparator set up for the next timer - * tick if either rcu or a softirq is pending. - */ - if (rcu_needs_cpu(cpu) || local_softirq_pending()) { - cpu_clear(cpu, nohz_cpu_mask); - return; - } - - /* - * This cpu is going really idle. Set up the clock comparator - * for the next event. - */ - next = next_timer_interrupt(); - do { - seq = read_seqbegin_irqsave(&xtime_lock, flags); - timer = ((__u64) next) - ((__u64) jiffies) + jiffies_64; - } while (read_seqretry_irqrestore(&xtime_lock, seq, flags)); - todval = -1ULL; - /* Be careful about overflows. */ - if (timer < (-1ULL / CLK_TICKS_PER_JIFFY)) { - timer = jiffies_timer_cc + timer * CLK_TICKS_PER_JIFFY; - if (timer >= jiffies_timer_cc) - todval = timer; - } - set_clock_comparator(todval); -} - /* - * Start the HZ tick on the current CPU. - * Only cpu_idle may call this function. + * Fixup the clock comparator. */ -static void start_hz_timer(void) +static void fixup_clock_comparator(unsigned long long delta) { - if (!cpu_isset(smp_processor_id(), nohz_cpu_mask)) + /* If nobody is waiting there's nothing to fix. */ + if (S390_lowcore.clock_comparator == -1ULL) return; - account_ticks(get_clock()); - set_clock_comparator(S390_lowcore.jiffy_timer + CPU_DEVIATION); - cpu_clear(smp_processor_id(), nohz_cpu_mask); -} - -static int nohz_idle_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - switch (action) { - case S390_CPU_IDLE: - stop_hz_timer(); - break; - case S390_CPU_NOT_IDLE: - start_hz_timer(); - break; - } - return NOTIFY_OK; + S390_lowcore.clock_comparator += delta; + set_clock_comparator(S390_lowcore.clock_comparator); } -static struct notifier_block nohz_idle_nb = { - .notifier_call = nohz_idle_notify, -}; - -static void __init nohz_init(void) +static int s390_next_event(unsigned long delta, + struct clock_event_device *evt) { - if (register_idle_notifier(&nohz_idle_nb)) - panic("Couldn't register idle notifier"); + S390_lowcore.clock_comparator = get_clock() + delta; + set_clock_comparator(S390_lowcore.clock_comparator); + return 0; } -#endif - -/* - * Set up per cpu jiffy timer and set the clock comparator. - */ -static void setup_jiffy_timer(void) +static void s390_set_mode(enum clock_event_mode mode, + struct clock_event_device *evt) { - /* Set up clock comparator to next jiffy. */ - S390_lowcore.jiffy_timer = - jiffies_timer_cc + (jiffies_64 + 1) * CLK_TICKS_PER_JIFFY; - set_clock_comparator(S390_lowcore.jiffy_timer + CPU_DEVIATION); } /* @@ -259,7 +138,26 @@ static void setup_jiffy_timer(void) */ void init_cpu_timer(void) { - setup_jiffy_timer(); + struct clock_event_device *cd; + int cpu; + + S390_lowcore.clock_comparator = -1ULL; + set_clock_comparator(S390_lowcore.clock_comparator); + + cpu = smp_processor_id(); + cd = &per_cpu(comparators, cpu); + cd->name = "comparator"; + cd->features = CLOCK_EVT_FEAT_ONESHOT; + cd->mult = 16777; + cd->shift = 12; + cd->min_delta_ns = 1; + cd->max_delta_ns = LONG_MAX; + cd->rating = 400; + cd->cpumask = cpumask_of_cpu(cpu); + cd->set_next_event = s390_next_event; + cd->set_mode = s390_set_mode; + + clockevents_register_device(cd); /* Enable clock comparator timer interrupt. */ __ctl_set_bit(0,11); @@ -270,8 +168,6 @@ void init_cpu_timer(void) static void clock_comparator_interrupt(__u16 code) { - /* set clock comparator for next tick */ - set_clock_comparator(S390_lowcore.jiffy_timer + CPU_DEVIATION); } static void etr_reset(void); @@ -316,8 +212,9 @@ static struct clocksource clocksource_tod = { */ void __init time_init(void) { + u64 init_timer_cc; + init_timer_cc = reset_tod_clock(); - xtime_cc = init_timer_cc + CLK_TICKS_PER_JIFFY; jiffies_timer_cc = init_timer_cc - jiffies_64 * CLK_TICKS_PER_JIFFY; /* set xtime */ @@ -342,10 +239,6 @@ void __init time_init(void) /* Enable TOD clock interrupts on the boot cpu. */ init_cpu_timer(); -#ifdef CONFIG_NO_IDLE_HZ - nohz_init(); -#endif - #ifdef CONFIG_VIRT_TIMER vtime_init(); #endif @@ -699,53 +592,49 @@ static int etr_aib_follows(struct etr_aib *a1, struct etr_aib *a2, int p) } /* - * The time is "clock". xtime is what we think the time is. + * The time is "clock". old is what we think the time is. * Adjust the value by a multiple of jiffies and add the delta to ntp. * "delay" is an approximation how long the synchronization took. If * the time correction is positive, then "delay" is subtracted from * the time difference and only the remaining part is passed to ntp. */ -static void etr_adjust_time(unsigned long long clock, unsigned long long delay) +static unsigned long long etr_adjust_time(unsigned long long old, + unsigned long long clock, + unsigned long long delay) { unsigned long long delta, ticks; struct timex adjust; - /* - * We don't have to take the xtime lock because the cpu - * executing etr_adjust_time is running disabled in - * tasklet context and all other cpus are looping in - * etr_sync_cpu_start. - */ - if (clock > xtime_cc) { + if (clock > old) { /* It is later than we thought. */ - delta = ticks = clock - xtime_cc; + delta = ticks = clock - old; delta = ticks = (delta < delay) ? 0 : delta - delay; delta -= do_div(ticks, CLK_TICKS_PER_JIFFY); - init_timer_cc = init_timer_cc + delta; - jiffies_timer_cc = jiffies_timer_cc + delta; - xtime_cc = xtime_cc + delta; adjust.offset = ticks * (1000000 / HZ); } else { /* It is earlier than we thought. */ - delta = ticks = xtime_cc - clock; + delta = ticks = old - clock; delta -= do_div(ticks, CLK_TICKS_PER_JIFFY); - init_timer_cc = init_timer_cc - delta; - jiffies_timer_cc = jiffies_timer_cc - delta; - xtime_cc = xtime_cc - delta; + delta = -delta; adjust.offset = -ticks * (1000000 / HZ); } + jiffies_timer_cc += delta; if (adjust.offset != 0) { printk(KERN_NOTICE "etr: time adjusted by %li micro-seconds\n", adjust.offset); adjust.modes = ADJ_OFFSET_SINGLESHOT; do_adjtimex(&adjust); } + return delta; } +static struct { + int in_sync; + unsigned long long fixup_cc; +} etr_sync; + static void etr_sync_cpu_start(void *dummy) { - int *in_sync = dummy; - etr_enable_sync_clock(); /* * This looks like a busy wait loop but it isn't. etr_sync_cpus @@ -753,7 +642,7 @@ static void etr_sync_cpu_start(void *dummy) * __udelay will stop the cpu on an enabled wait psw until the * TOD is running again. */ - while (*in_sync == 0) { + while (etr_sync.in_sync == 0) { __udelay(1); /* * A different cpu changes *in_sync. Therefore use @@ -761,14 +650,14 @@ static void etr_sync_cpu_start(void *dummy) */ barrier(); } - if (*in_sync != 1) + if (etr_sync.in_sync != 1) /* Didn't work. Clear per-cpu in sync bit again. */ etr_disable_sync_clock(NULL); /* * This round of TOD syncing is done. Set the clock comparator * to the next tick and let the processor continue. */ - setup_jiffy_timer(); + fixup_clock_comparator(etr_sync.fixup_cc); } static void etr_sync_cpu_end(void *dummy) @@ -783,8 +672,8 @@ static void etr_sync_cpu_end(void *dummy) static int etr_sync_clock(struct etr_aib *aib, int port) { struct etr_aib *sync_port; - unsigned long long clock, delay; - int in_sync, follows; + unsigned long long clock, old_clock, delay, delta; + int follows; int rc; /* Check if the current aib is adjacent to the sync port aib. */ @@ -799,9 +688,9 @@ static int etr_sync_clock(struct etr_aib *aib, int port) * successfully synced the clock. smp_call_function will * return after all other cpus are in etr_sync_cpu_start. */ - in_sync = 0; + memset(&etr_sync, 0, sizeof(etr_sync)); preempt_disable(); - smp_call_function(etr_sync_cpu_start,&in_sync,0,0); + smp_call_function(etr_sync_cpu_start, NULL, 0, 0); local_irq_disable(); etr_enable_sync_clock(); @@ -809,6 +698,7 @@ static int etr_sync_clock(struct etr_aib *aib, int port) __ctl_set_bit(14, 21); __ctl_set_bit(0, 29); clock = ((unsigned long long) (aib->edf2.etv + 1)) << 32; + old_clock = get_clock(); if (set_clock(clock) == 0) { __udelay(1); /* Wait for the clock to start. */ __ctl_clear_bit(0, 29); @@ -817,16 +707,17 @@ static int etr_sync_clock(struct etr_aib *aib, int port) /* Adjust Linux timing variables. */ delay = (unsigned long long) (aib->edf2.etv - sync_port->edf2.etv) << 32; - etr_adjust_time(clock, delay); - setup_jiffy_timer(); + delta = etr_adjust_time(old_clock, clock, delay); + etr_sync.fixup_cc = delta; + fixup_clock_comparator(delta); /* Verify that the clock is properly set. */ if (!etr_aib_follows(sync_port, aib, port)) { /* Didn't work. */ etr_disable_sync_clock(NULL); - in_sync = -EAGAIN; + etr_sync.in_sync = -EAGAIN; rc = -EAGAIN; } else { - in_sync = 1; + etr_sync.in_sync = 1; rc = 0; } } else { @@ -834,7 +725,7 @@ static int etr_sync_clock(struct etr_aib *aib, int port) __ctl_clear_bit(0, 29); __ctl_clear_bit(14, 21); etr_disable_sync_clock(NULL); - in_sync = -EAGAIN; + etr_sync.in_sync = -EAGAIN; rc = -EAGAIN; } local_irq_enable(); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c new file mode 100644 index 000000000000..661a07217057 --- /dev/null +++ b/arch/s390/kernel/topology.c @@ -0,0 +1,341 @@ +/* + * Copyright IBM Corp. 2007 + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/init.h> +#include <linux/device.h> +#include <linux/bootmem.h> +#include <linux/sched.h> +#include <linux/kthread.h> +#include <linux/workqueue.h> +#include <linux/cpu.h> +#include <linux/smp.h> +#include <asm/delay.h> +#include <asm/s390_ext.h> +#include <asm/sysinfo.h> + +#define CPU_BITS 64 +#define NR_MAG 6 + +#define PTF_HORIZONTAL (0UL) +#define PTF_VERTICAL (1UL) +#define PTF_CHECK (2UL) + +struct tl_cpu { + unsigned char reserved0[4]; + unsigned char :6; + unsigned char pp:2; + unsigned char reserved1; + unsigned short origin; + unsigned long mask[CPU_BITS / BITS_PER_LONG]; +}; + +struct tl_container { + unsigned char reserved[8]; +}; + +union tl_entry { + unsigned char nl; + struct tl_cpu cpu; + struct tl_container container; +}; + +struct tl_info { + unsigned char reserved0[2]; + unsigned short length; + unsigned char mag[NR_MAG]; + unsigned char reserved1; + unsigned char mnest; + unsigned char reserved2[4]; + union tl_entry tle[0]; +}; + +struct core_info { + struct core_info *next; + cpumask_t mask; +}; + +static void topology_work_fn(struct work_struct *work); +static struct tl_info *tl_info; +static struct core_info core_info; +static int machine_has_topology; +static int machine_has_topology_irq; +static struct timer_list topology_timer; +static void set_topology_timer(void); +static DECLARE_WORK(topology_work, topology_work_fn); + +cpumask_t cpu_core_map[NR_CPUS]; + +cpumask_t cpu_coregroup_map(unsigned int cpu) +{ + struct core_info *core = &core_info; + cpumask_t mask; + + cpus_clear(mask); + if (!machine_has_topology) + return cpu_present_map; + mutex_lock(&smp_cpu_state_mutex); + while (core) { + if (cpu_isset(cpu, core->mask)) { + mask = core->mask; + break; + } + core = core->next; + } + mutex_unlock(&smp_cpu_state_mutex); + if (cpus_empty(mask)) + mask = cpumask_of_cpu(cpu); + return mask; +} + +static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core) +{ + unsigned int cpu; + + for (cpu = find_first_bit(&tl_cpu->mask[0], CPU_BITS); + cpu < CPU_BITS; + cpu = find_next_bit(&tl_cpu->mask[0], CPU_BITS, cpu + 1)) + { + unsigned int rcpu, lcpu; + + rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin; + for_each_present_cpu(lcpu) { + if (__cpu_logical_map[lcpu] == rcpu) { + cpu_set(lcpu, core->mask); + smp_cpu_polarization[lcpu] = tl_cpu->pp; + } + } + } +} + +static void clear_cores(void) +{ + struct core_info *core = &core_info; + + while (core) { + cpus_clear(core->mask); + core = core->next; + } +} + +static union tl_entry *next_tle(union tl_entry *tle) +{ + if (tle->nl) + return (union tl_entry *)((struct tl_container *)tle + 1); + else + return (union tl_entry *)((struct tl_cpu *)tle + 1); +} + +static void tl_to_cores(struct tl_info *info) +{ + union tl_entry *tle, *end; + struct core_info *core = &core_info; + + mutex_lock(&smp_cpu_state_mutex); + clear_cores(); + tle = info->tle; + end = (union tl_entry *)((unsigned long)info + info->length); + while (tle < end) { + switch (tle->nl) { + case 5: + case 4: + case 3: + case 2: + break; + case 1: + core = core->next; + break; + case 0: + add_cpus_to_core(&tle->cpu, core); + break; + default: + clear_cores(); + machine_has_topology = 0; + return; + } + tle = next_tle(tle); + } + mutex_unlock(&smp_cpu_state_mutex); +} + +static void topology_update_polarization_simple(void) +{ + int cpu; + + mutex_lock(&smp_cpu_state_mutex); + for_each_present_cpu(cpu) + smp_cpu_polarization[cpu] = POLARIZATION_HRZ; + mutex_unlock(&smp_cpu_state_mutex); +} + +static int ptf(unsigned long fc) +{ + int rc; + + asm volatile( + " .insn rre,0xb9a20000,%1,%1\n" + " ipm %0\n" + " srl %0,28\n" + : "=d" (rc) + : "d" (fc) : "cc"); + return rc; +} + +int topology_set_cpu_management(int fc) +{ + int cpu; + int rc; + + if (!machine_has_topology) + return -EOPNOTSUPP; + if (fc) + rc = ptf(PTF_VERTICAL); + else + rc = ptf(PTF_HORIZONTAL); + if (rc) + return -EBUSY; + for_each_present_cpu(cpu) + smp_cpu_polarization[cpu] = POLARIZATION_UNKNWN; + return rc; +} + +static void update_cpu_core_map(void) +{ + int cpu; + + for_each_present_cpu(cpu) + cpu_core_map[cpu] = cpu_coregroup_map(cpu); +} + +void arch_update_cpu_topology(void) +{ + struct tl_info *info = tl_info; + struct sys_device *sysdev; + int cpu; + + if (!machine_has_topology) { + update_cpu_core_map(); + topology_update_polarization_simple(); + return; + } + stsi(info, 15, 1, 2); + tl_to_cores(info); + update_cpu_core_map(); + for_each_online_cpu(cpu) { + sysdev = get_cpu_sysdev(cpu); + kobject_uevent(&sysdev->kobj, KOBJ_CHANGE); + } +} + +static int topology_kthread(void *data) +{ + arch_reinit_sched_domains(); + return 0; +} + +static void topology_work_fn(struct work_struct *work) +{ + /* We can't call arch_reinit_sched_domains() from a multi-threaded + * workqueue context since it may deadlock in case of cpu hotplug. + * So we have to create a kernel thread in order to call + * arch_reinit_sched_domains(). + */ + kthread_run(topology_kthread, NULL, "topology_update"); +} + +void topology_schedule_update(void) +{ + schedule_work(&topology_work); +} + +static void topology_timer_fn(unsigned long ignored) +{ + if (ptf(PTF_CHECK)) + topology_schedule_update(); + set_topology_timer(); +} + +static void set_topology_timer(void) +{ + topology_timer.function = topology_timer_fn; + topology_timer.data = 0; + topology_timer.expires = jiffies + 60 * HZ; + add_timer(&topology_timer); +} + +static void topology_interrupt(__u16 code) +{ + schedule_work(&topology_work); +} + +static int __init init_topology_update(void) +{ + int rc; + + rc = 0; + if (!machine_has_topology) { + topology_update_polarization_simple(); + goto out; + } + init_timer_deferrable(&topology_timer); + if (machine_has_topology_irq) { + rc = register_external_interrupt(0x2005, topology_interrupt); + if (rc) + goto out; + ctl_set_bit(0, 8); + } + else + set_topology_timer(); +out: + update_cpu_core_map(); + return rc; +} +__initcall(init_topology_update); + +void __init s390_init_cpu_topology(void) +{ + unsigned long long facility_bits; + struct tl_info *info; + struct core_info *core; + int nr_cores; + int i; + + if (stfle(&facility_bits, 1) <= 0) + return; + if (!(facility_bits & (1ULL << 52)) || !(facility_bits & (1ULL << 61))) + return; + machine_has_topology = 1; + + if (facility_bits & (1ULL << 51)) + machine_has_topology_irq = 1; + + tl_info = alloc_bootmem_pages(PAGE_SIZE); + if (!tl_info) + goto error; + info = tl_info; + stsi(info, 15, 1, 2); + + nr_cores = info->mag[NR_MAG - 2]; + for (i = 0; i < info->mnest - 2; i++) + nr_cores *= info->mag[NR_MAG - 3 - i]; + + printk(KERN_INFO "CPU topology:"); + for (i = 0; i < NR_MAG; i++) + printk(" %d", info->mag[i]); + printk(" / %d\n", info->mnest); + + core = &core_info; + for (i = 0; i < nr_cores; i++) { + core->next = alloc_bootmem(sizeof(struct core_info)); + core = core->next; + if (!core) + goto error; + } + return; +error: + machine_has_topology = 0; + machine_has_topology_irq = 0; +} diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 60f728aeaf12..4584d81984c0 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -42,11 +42,8 @@ #include <asm/s390_ext.h> #include <asm/lowcore.h> #include <asm/debug.h> +#include "entry.h" -/* Called from entry.S only */ -extern void handle_per_exception(struct pt_regs *regs); - -typedef void pgm_check_handler_t(struct pt_regs *, long); pgm_check_handler_t *pgm_check_table[128]; #ifdef CONFIG_SYSCTL @@ -59,7 +56,6 @@ int sysctl_userprocess_debug = 0; extern pgm_check_handler_t do_protection_exception; extern pgm_check_handler_t do_dat_exception; -extern pgm_check_handler_t do_monitor_call; extern pgm_check_handler_t do_asce_exception; #define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; }) @@ -117,7 +113,7 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high) } } -void show_trace(struct task_struct *task, unsigned long *stack) +static void show_trace(struct task_struct *task, unsigned long *stack) { register unsigned long __r15 asm ("15"); unsigned long sp; @@ -138,7 +134,6 @@ void show_trace(struct task_struct *task, unsigned long *stack) else __show_trace(sp, S390_lowcore.thread_info, S390_lowcore.thread_info + THREAD_SIZE); - printk("\n"); if (!task) task = current; debug_show_held_locks(task); @@ -166,6 +161,15 @@ void show_stack(struct task_struct *task, unsigned long *sp) show_trace(task, sp); } +static void show_last_breaking_event(struct pt_regs *regs) +{ +#ifdef CONFIG_64BIT + printk("Last Breaking-Event-Address:\n"); + printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN); + print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN); +#endif +} + /* * The architecture-independent dump_stack generator */ @@ -219,6 +223,24 @@ void show_registers(struct pt_regs *regs) show_code(regs); } +void show_regs(struct pt_regs *regs) +{ + print_modules(); + printk("CPU: %d %s %s %.*s\n", + task_thread_info(current)->cpu, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + printk("Process %s (pid: %d, task: %p, ksp: %p)\n", + current->comm, current->pid, current, + (void *) current->thread.ksp); + show_registers(regs); + /* Show stack backtrace if pt_regs is from kernel mode */ + if (!(regs->psw.mask & PSW_MASK_PSTATE)) + show_trace(NULL, (unsigned long *) regs->gprs[15]); + show_last_breaking_event(regs); +} + /* This is called from fs/proc/array.c */ void task_show_regs(struct seq_file *m, struct task_struct *task) { @@ -739,6 +761,5 @@ void __init trap_init(void) pgm_check_table[0x15] = &operand_exception; pgm_check_table[0x1C] = &space_switch_exception; pgm_check_table[0x1D] = &hfp_sqrt_exception; - pgm_check_table[0x40] = &do_monitor_call; pfault_irq_init(); } diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index c5f05b3fb2c3..ca90ee3f930e 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -110,6 +110,7 @@ void account_system_vtime(struct task_struct *tsk) S390_lowcore.steal_clock -= cputime << 12; account_system_time(tsk, 0, cputime); } +EXPORT_SYMBOL_GPL(account_system_vtime); static inline void set_vtimer(__u64 expires) { diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig new file mode 100644 index 000000000000..1761b74d639b --- /dev/null +++ b/arch/s390/kvm/Kconfig @@ -0,0 +1,46 @@ +# +# KVM configuration +# +config HAVE_KVM + bool + +menuconfig VIRTUALIZATION + bool "Virtualization" + default y + ---help--- + Say Y here to get to see options for using your Linux host to run other + operating systems inside virtual machines (guests). + This option alone does not add any kernel code. + + If you say N, all options in this submenu will be skipped and disabled. + +if VIRTUALIZATION + +config KVM + tristate "Kernel-based Virtual Machine (KVM) support" + depends on HAVE_KVM && EXPERIMENTAL + select PREEMPT_NOTIFIERS + select ANON_INODES + select S390_SWITCH_AMODE + select PREEMPT + ---help--- + Support hosting paravirtualized guest machines using the SIE + virtualization capability on the mainframe. This should work + on any 64bit machine. + + This module provides access to the hardware capabilities through + a character device node named /dev/kvm. + + To compile this as a module, choose M here: the module + will be called kvm. + + If unsure, say N. + +config KVM_TRACE + bool + +# OK, it's a little counter-intuitive to do this, but it puts it neatly under +# the virtualization menu. +source drivers/virtio/Kconfig + +endif # VIRTUALIZATION diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile new file mode 100644 index 000000000000..e5221ec0b8e3 --- /dev/null +++ b/arch/s390/kvm/Makefile @@ -0,0 +1,14 @@ +# Makefile for kernel virtual machines on s390 +# +# Copyright IBM Corp. 2008 +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License (version 2 only) +# as published by the Free Software Foundation. + +common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o) + +EXTRA_CFLAGS += -Ivirt/kvm -Iarch/s390/kvm + +kvm-objs := $(common-objs) kvm-s390.o sie64a.o intercept.o interrupt.o priv.o sigp.o diag.o +obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c new file mode 100644 index 000000000000..f639a152869f --- /dev/null +++ b/arch/s390/kvm/diag.c @@ -0,0 +1,67 @@ +/* + * diag.c - handling diagnose instructions + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include "kvm-s390.h" + +static int __diag_time_slice_end(struct kvm_vcpu *vcpu) +{ + VCPU_EVENT(vcpu, 5, "%s", "diag time slice end"); + vcpu->stat.diagnose_44++; + vcpu_put(vcpu); + schedule(); + vcpu_load(vcpu); + return 0; +} + +static int __diag_ipl_functions(struct kvm_vcpu *vcpu) +{ + unsigned int reg = vcpu->arch.sie_block->ipa & 0xf; + unsigned long subcode = vcpu->arch.guest_gprs[reg] & 0xffff; + + VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode); + switch (subcode) { + case 3: + vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR; + break; + case 4: + vcpu->run->s390_reset_flags = 0; + break; + default: + return -ENOTSUPP; + } + + atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM; + vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL; + vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT; + vcpu->run->exit_reason = KVM_EXIT_S390_RESET; + VCPU_EVENT(vcpu, 3, "requesting userspace resets %lx", + vcpu->run->s390_reset_flags); + return -EREMOTE; +} + +int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) +{ + int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16; + + switch (code) { + case 0x44: + return __diag_time_slice_end(vcpu); + case 0x308: + return __diag_ipl_functions(vcpu); + default: + return -ENOTSUPP; + } +} diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h new file mode 100644 index 000000000000..4e0633c413f3 --- /dev/null +++ b/arch/s390/kvm/gaccess.h @@ -0,0 +1,274 @@ +/* + * gaccess.h - access guest memory + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + */ + +#ifndef __KVM_S390_GACCESS_H +#define __KVM_S390_GACCESS_H + +#include <linux/compiler.h> +#include <linux/kvm_host.h> +#include <asm/uaccess.h> + +static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu, + u64 guestaddr) +{ + u64 prefix = vcpu->arch.sie_block->prefix; + u64 origin = vcpu->kvm->arch.guest_origin; + u64 memsize = vcpu->kvm->arch.guest_memsize; + + if (guestaddr < 2 * PAGE_SIZE) + guestaddr += prefix; + else if ((guestaddr >= prefix) && (guestaddr < prefix + 2 * PAGE_SIZE)) + guestaddr -= prefix; + + if (guestaddr > memsize) + return (void __user __force *) ERR_PTR(-EFAULT); + + guestaddr += origin; + + return (void __user *) guestaddr; +} + +static inline int get_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr, + u64 *result) +{ + void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); + + BUG_ON(guestaddr & 7); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + return get_user(*result, (u64 __user *) uptr); +} + +static inline int get_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr, + u32 *result) +{ + void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); + + BUG_ON(guestaddr & 3); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + return get_user(*result, (u32 __user *) uptr); +} + +static inline int get_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr, + u16 *result) +{ + void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); + + BUG_ON(guestaddr & 1); + + if (IS_ERR(uptr)) + return PTR_ERR(uptr); + + return get_user(*result, (u16 __user *) uptr); +} + +static inline int get_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr, + u8 *result) +{ + void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + return get_user(*result, (u8 __user *) uptr); +} + +static inline int put_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr, + u64 value) +{ + void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); + + BUG_ON(guestaddr & 7); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + return put_user(value, (u64 __user *) uptr); +} + +static inline int put_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr, + u32 value) +{ + void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); + + BUG_ON(guestaddr & 3); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + return put_user(value, (u32 __user *) uptr); +} + +static inline int put_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr, + u16 value) +{ + void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); + + BUG_ON(guestaddr & 1); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + return put_user(value, (u16 __user *) uptr); +} + +static inline int put_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr, + u8 value) +{ + void __user *uptr = __guestaddr_to_user(vcpu, guestaddr); + + if (IS_ERR((void __force *) uptr)) + return PTR_ERR((void __force *) uptr); + + return put_user(value, (u8 __user *) uptr); +} + + +static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, u64 guestdest, + const void *from, unsigned long n) +{ + int rc; + unsigned long i; + const u8 *data = from; + + for (i = 0; i < n; i++) { + rc = put_guest_u8(vcpu, guestdest++, *(data++)); + if (rc < 0) + return rc; + } + return 0; +} + +static inline int copy_to_guest(struct kvm_vcpu *vcpu, u64 guestdest, + const void *from, unsigned long n) +{ + u64 prefix = vcpu->arch.sie_block->prefix; + u64 origin = vcpu->kvm->arch.guest_origin; + u64 memsize = vcpu->kvm->arch.guest_memsize; + + if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE)) + goto slowpath; + + if ((guestdest < prefix) && (guestdest + n > prefix)) + goto slowpath; + + if ((guestdest < prefix + 2 * PAGE_SIZE) + && (guestdest + n > prefix + 2 * PAGE_SIZE)) + goto slowpath; + + if (guestdest < 2 * PAGE_SIZE) + guestdest += prefix; + else if ((guestdest >= prefix) && (guestdest < prefix + 2 * PAGE_SIZE)) + guestdest -= prefix; + + if (guestdest + n > memsize) + return -EFAULT; + + if (guestdest + n < guestdest) + return -EFAULT; + + guestdest += origin; + + return copy_to_user((void __user *) guestdest, from, n); +slowpath: + return __copy_to_guest_slow(vcpu, guestdest, from, n); +} + +static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to, + u64 guestsrc, unsigned long n) +{ + int rc; + unsigned long i; + u8 *data = to; + + for (i = 0; i < n; i++) { + rc = get_guest_u8(vcpu, guestsrc++, data++); + if (rc < 0) + return rc; + } + return 0; +} + +static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to, + u64 guestsrc, unsigned long n) +{ + u64 prefix = vcpu->arch.sie_block->prefix; + u64 origin = vcpu->kvm->arch.guest_origin; + u64 memsize = vcpu->kvm->arch.guest_memsize; + + if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE)) + goto slowpath; + + if ((guestsrc < prefix) && (guestsrc + n > prefix)) + goto slowpath; + + if ((guestsrc < prefix + 2 * PAGE_SIZE) + && (guestsrc + n > prefix + 2 * PAGE_SIZE)) + goto slowpath; + + if (guestsrc < 2 * PAGE_SIZE) + guestsrc += prefix; + else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE)) + guestsrc -= prefix; + + if (guestsrc + n > memsize) + return -EFAULT; + + if (guestsrc + n < guestsrc) + return -EFAULT; + + guestsrc += origin; + + return copy_from_user(to, (void __user *) guestsrc, n); +slowpath: + return __copy_from_guest_slow(vcpu, to, guestsrc, n); +} + +static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, u64 guestdest, + const void *from, unsigned long n) +{ + u64 origin = vcpu->kvm->arch.guest_origin; + u64 memsize = vcpu->kvm->arch.guest_memsize; + + if (guestdest + n > memsize) + return -EFAULT; + + if (guestdest + n < guestdest) + return -EFAULT; + + guestdest += origin; + + return copy_to_user((void __user *) guestdest, from, n); +} + +static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to, + u64 guestsrc, unsigned long n) +{ + u64 origin = vcpu->kvm->arch.guest_origin; + u64 memsize = vcpu->kvm->arch.guest_memsize; + + if (guestsrc + n > memsize) + return -EFAULT; + + if (guestsrc + n < guestsrc) + return -EFAULT; + + guestsrc += origin; + + return copy_from_user(to, (void __user *) guestsrc, n); +} +#endif diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c new file mode 100644 index 000000000000..349581a26103 --- /dev/null +++ b/arch/s390/kvm/intercept.c @@ -0,0 +1,216 @@ +/* + * intercept.c - in-kernel handling for sie intercepts + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#include <linux/kvm_host.h> +#include <linux/errno.h> +#include <linux/pagemap.h> + +#include <asm/kvm_host.h> + +#include "kvm-s390.h" +#include "gaccess.h" + +static int handle_lctg(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + int base2 = vcpu->arch.sie_block->ipb >> 28; + int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + + ((vcpu->arch.sie_block->ipb & 0xff00) << 4); + u64 useraddr; + int reg, rc; + + vcpu->stat.instruction_lctg++; + if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f) + return -ENOTSUPP; + + useraddr = disp2; + if (base2) + useraddr += vcpu->arch.guest_gprs[base2]; + + reg = reg1; + + VCPU_EVENT(vcpu, 5, "lctg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2, + disp2); + + do { + rc = get_guest_u64(vcpu, useraddr, + &vcpu->arch.sie_block->gcr[reg]); + if (rc == -EFAULT) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + break; + } + useraddr += 8; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + return 0; +} + +static int handle_lctl(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + int base2 = vcpu->arch.sie_block->ipb >> 28; + int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + u64 useraddr; + u32 val = 0; + int reg, rc; + + vcpu->stat.instruction_lctl++; + + useraddr = disp2; + if (base2) + useraddr += vcpu->arch.guest_gprs[base2]; + + VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2, + disp2); + + reg = reg1; + do { + rc = get_guest_u32(vcpu, useraddr, &val); + if (rc == -EFAULT) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + break; + } + vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul; + vcpu->arch.sie_block->gcr[reg] |= val; + useraddr += 4; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + return 0; +} + +static intercept_handler_t instruction_handlers[256] = { + [0x83] = kvm_s390_handle_diag, + [0xae] = kvm_s390_handle_sigp, + [0xb2] = kvm_s390_handle_priv, + [0xb7] = handle_lctl, + [0xeb] = handle_lctg, +}; + +static int handle_noop(struct kvm_vcpu *vcpu) +{ + switch (vcpu->arch.sie_block->icptcode) { + case 0x10: + vcpu->stat.exit_external_request++; + break; + case 0x14: + vcpu->stat.exit_external_interrupt++; + break; + default: + break; /* nothing */ + } + return 0; +} + +static int handle_stop(struct kvm_vcpu *vcpu) +{ + int rc; + + vcpu->stat.exit_stop_request++; + atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + spin_lock_bh(&vcpu->arch.local_int.lock); + if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) { + vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP; + rc = __kvm_s390_vcpu_store_status(vcpu, + KVM_S390_STORE_STATUS_NOADDR); + if (rc >= 0) + rc = -ENOTSUPP; + } + + if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) { + vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP; + VCPU_EVENT(vcpu, 3, "%s", "cpu stopped"); + rc = -ENOTSUPP; + } else + rc = 0; + spin_unlock_bh(&vcpu->arch.local_int.lock); + return rc; +} + +static int handle_validity(struct kvm_vcpu *vcpu) +{ + int viwhy = vcpu->arch.sie_block->ipb >> 16; + vcpu->stat.exit_validity++; + if (viwhy == 0x37) { + fault_in_pages_writeable((char __user *) + vcpu->kvm->arch.guest_origin + + vcpu->arch.sie_block->prefix, + PAGE_SIZE); + return 0; + } + VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d", + viwhy); + return -ENOTSUPP; +} + +static int handle_instruction(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + vcpu->stat.exit_instruction++; + handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8]; + if (handler) + return handler(vcpu); + return -ENOTSUPP; +} + +static int handle_prog(struct kvm_vcpu *vcpu) +{ + vcpu->stat.exit_program_interruption++; + return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc); +} + +static int handle_instruction_and_prog(struct kvm_vcpu *vcpu) +{ + int rc, rc2; + + vcpu->stat.exit_instr_and_program++; + rc = handle_instruction(vcpu); + rc2 = handle_prog(vcpu); + + if (rc == -ENOTSUPP) + vcpu->arch.sie_block->icptcode = 0x04; + if (rc) + return rc; + return rc2; +} + +static const intercept_handler_t intercept_funcs[0x48 >> 2] = { + [0x00 >> 2] = handle_noop, + [0x04 >> 2] = handle_instruction, + [0x08 >> 2] = handle_prog, + [0x0C >> 2] = handle_instruction_and_prog, + [0x10 >> 2] = handle_noop, + [0x14 >> 2] = handle_noop, + [0x1C >> 2] = kvm_s390_handle_wait, + [0x20 >> 2] = handle_validity, + [0x28 >> 2] = handle_stop, +}; + +int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) +{ + intercept_handler_t func; + u8 code = vcpu->arch.sie_block->icptcode; + + if (code & 3 || code > 0x48) + return -ENOTSUPP; + func = intercept_funcs[code >> 2]; + if (func) + return func(vcpu); + return -ENOTSUPP; +} diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c new file mode 100644 index 000000000000..fcd1ed8015c1 --- /dev/null +++ b/arch/s390/kvm/interrupt.c @@ -0,0 +1,592 @@ +/* + * interrupt.c - handling kvm guest interrupts + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + */ + +#include <asm/lowcore.h> +#include <asm/uaccess.h> +#include <linux/kvm_host.h> +#include "kvm-s390.h" +#include "gaccess.h" + +static int psw_extint_disabled(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT); +} + +static int psw_interrupts_disabled(struct kvm_vcpu *vcpu) +{ + if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) || + (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO) || + (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT)) + return 0; + return 1; +} + +static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, + struct interrupt_info *inti) +{ + switch (inti->type) { + case KVM_S390_INT_EMERGENCY: + if (psw_extint_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[0] & 0x4000ul) + return 1; + return 0; + case KVM_S390_INT_SERVICE: + if (psw_extint_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[0] & 0x200ul) + return 1; + return 0; + case KVM_S390_INT_VIRTIO: + if (psw_extint_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[0] & 0x200ul) + return 1; + return 0; + case KVM_S390_PROGRAM_INT: + case KVM_S390_SIGP_STOP: + case KVM_S390_SIGP_SET_PREFIX: + case KVM_S390_RESTART: + return 1; + default: + BUG(); + } + return 0; +} + +static void __set_cpu_idle(struct kvm_vcpu *vcpu) +{ + BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1); + atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); + set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask); +} + +static void __unset_cpu_idle(struct kvm_vcpu *vcpu) +{ + BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1); + atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); + clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask); +} + +static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) +{ + atomic_clear_mask(CPUSTAT_ECALL_PEND | + CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT, + &vcpu->arch.sie_block->cpuflags); + vcpu->arch.sie_block->lctl = 0x0000; +} + +static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) +{ + atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags); +} + +static void __set_intercept_indicator(struct kvm_vcpu *vcpu, + struct interrupt_info *inti) +{ + switch (inti->type) { + case KVM_S390_INT_EMERGENCY: + case KVM_S390_INT_SERVICE: + case KVM_S390_INT_VIRTIO: + if (psw_extint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_EXT_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR0; + break; + case KVM_S390_SIGP_STOP: + __set_cpuflag(vcpu, CPUSTAT_STOP_INT); + break; + default: + BUG(); + } +} + +static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, + struct interrupt_info *inti) +{ + const unsigned short table[] = { 2, 4, 4, 6 }; + int rc, exception = 0; + + switch (inti->type) { + case KVM_S390_INT_EMERGENCY: + VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg"); + vcpu->stat.deliver_emergency_signal++; + rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1201); + if (rc == -EFAULT) + exception = 1; + + rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_EXT_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + break; + + case KVM_S390_INT_SERVICE: + VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", + inti->ext.ext_params); + vcpu->stat.deliver_service_signal++; + rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2401); + if (rc == -EFAULT) + exception = 1; + + rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_EXT_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params); + if (rc == -EFAULT) + exception = 1; + break; + + case KVM_S390_INT_VIRTIO: + VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%lx", + inti->ext.ext_params, inti->ext.ext_params2); + vcpu->stat.deliver_virtio_interrupt++; + rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2603); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, 0x0d00); + if (rc == -EFAULT) + exception = 1; + + rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_EXT_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u64(vcpu, __LC_PFAULT_INTPARM, + inti->ext.ext_params2); + if (rc == -EFAULT) + exception = 1; + break; + + case KVM_S390_SIGP_STOP: + VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop"); + vcpu->stat.deliver_stop_signal++; + __set_intercept_indicator(vcpu, inti); + break; + + case KVM_S390_SIGP_SET_PREFIX: + VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", + inti->prefix.address); + vcpu->stat.deliver_prefix_signal++; + vcpu->arch.sie_block->prefix = inti->prefix.address; + vcpu->arch.sie_block->ihcpu = 0xffff; + break; + + case KVM_S390_RESTART: + VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart"); + vcpu->stat.deliver_restart_signal++; + rc = copy_to_guest(vcpu, offsetof(struct _lowcore, + restart_old_psw), &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + offsetof(struct _lowcore, restart_psw), sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + break; + + case KVM_S390_PROGRAM_INT: + VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x", + inti->pgm.code, + table[vcpu->arch.sie_block->ipa >> 14]); + vcpu->stat.deliver_program_int++; + rc = put_guest_u16(vcpu, __LC_PGM_INT_CODE, inti->pgm.code); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u16(vcpu, __LC_PGM_ILC, + table[vcpu->arch.sie_block->ipa >> 14]); + if (rc == -EFAULT) + exception = 1; + + rc = copy_to_guest(vcpu, __LC_PGM_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_PGM_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + break; + + default: + BUG(); + } + + if (exception) { + VCPU_EVENT(vcpu, 1, "%s", "program exception while delivering" + " interrupt"); + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (inti->type == KVM_S390_PROGRAM_INT) { + printk(KERN_WARNING "kvm: recursive program check\n"); + BUG(); + } + } +} + +static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu) +{ + int rc, exception = 0; + + if (psw_extint_disabled(vcpu)) + return 0; + if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul)) + return 0; + rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1004); + if (rc == -EFAULT) + exception = 1; + rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_EXT_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + if (exception) { + VCPU_EVENT(vcpu, 1, "%s", "program exception while delivering" \ + " ckc interrupt"); + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + return 0; + } + + return 1; +} + +int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct local_interrupt *li = &vcpu->arch.local_int; + struct float_interrupt *fi = vcpu->arch.local_int.float_int; + struct interrupt_info *inti; + int rc = 0; + + if (atomic_read(&li->active)) { + spin_lock_bh(&li->lock); + list_for_each_entry(inti, &li->list, list) + if (__interrupt_is_deliverable(vcpu, inti)) { + rc = 1; + break; + } + spin_unlock_bh(&li->lock); + } + + if ((!rc) && atomic_read(&fi->active)) { + spin_lock_bh(&fi->lock); + list_for_each_entry(inti, &fi->list, list) + if (__interrupt_is_deliverable(vcpu, inti)) { + rc = 1; + break; + } + spin_unlock_bh(&fi->lock); + } + + if ((!rc) && (vcpu->arch.sie_block->ckc < + get_clock() + vcpu->arch.sie_block->epoch)) { + if ((!psw_extint_disabled(vcpu)) && + (vcpu->arch.sie_block->gcr[0] & 0x800ul)) + rc = 1; + } + + return rc; +} + +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) +{ + return 0; +} + +int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) +{ + u64 now, sltime; + DECLARE_WAITQUEUE(wait, current); + + vcpu->stat.exit_wait_state++; + if (kvm_cpu_has_interrupt(vcpu)) + return 0; + + if (psw_interrupts_disabled(vcpu)) { + VCPU_EVENT(vcpu, 3, "%s", "disabled wait"); + __unset_cpu_idle(vcpu); + return -ENOTSUPP; /* disabled wait */ + } + + if (psw_extint_disabled(vcpu) || + (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))) { + VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer"); + goto no_timer; + } + + now = get_clock() + vcpu->arch.sie_block->epoch; + if (vcpu->arch.sie_block->ckc < now) { + __unset_cpu_idle(vcpu); + return 0; + } + + sltime = (vcpu->arch.sie_block->ckc - now) / (0xf4240000ul / HZ) + 1; + + vcpu->arch.ckc_timer.expires = jiffies + sltime; + + add_timer(&vcpu->arch.ckc_timer); + VCPU_EVENT(vcpu, 5, "enabled wait timer:%lx jiffies", sltime); +no_timer: + spin_lock_bh(&vcpu->arch.local_int.float_int->lock); + spin_lock_bh(&vcpu->arch.local_int.lock); + __set_cpu_idle(vcpu); + vcpu->arch.local_int.timer_due = 0; + add_wait_queue(&vcpu->arch.local_int.wq, &wait); + while (list_empty(&vcpu->arch.local_int.list) && + list_empty(&vcpu->arch.local_int.float_int->list) && + (!vcpu->arch.local_int.timer_due) && + !signal_pending(current)) { + set_current_state(TASK_INTERRUPTIBLE); + spin_unlock_bh(&vcpu->arch.local_int.lock); + spin_unlock_bh(&vcpu->arch.local_int.float_int->lock); + vcpu_put(vcpu); + schedule(); + vcpu_load(vcpu); + spin_lock_bh(&vcpu->arch.local_int.float_int->lock); + spin_lock_bh(&vcpu->arch.local_int.lock); + } + __unset_cpu_idle(vcpu); + __set_current_state(TASK_RUNNING); + remove_wait_queue(&vcpu->wq, &wait); + spin_unlock_bh(&vcpu->arch.local_int.lock); + spin_unlock_bh(&vcpu->arch.local_int.float_int->lock); + del_timer(&vcpu->arch.ckc_timer); + return 0; +} + +void kvm_s390_idle_wakeup(unsigned long data) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; + + spin_lock_bh(&vcpu->arch.local_int.lock); + vcpu->arch.local_int.timer_due = 1; + if (waitqueue_active(&vcpu->arch.local_int.wq)) + wake_up_interruptible(&vcpu->arch.local_int.wq); + spin_unlock_bh(&vcpu->arch.local_int.lock); +} + + +void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) +{ + struct local_interrupt *li = &vcpu->arch.local_int; + struct float_interrupt *fi = vcpu->arch.local_int.float_int; + struct interrupt_info *n, *inti = NULL; + int deliver; + + __reset_intercept_indicators(vcpu); + if (atomic_read(&li->active)) { + do { + deliver = 0; + spin_lock_bh(&li->lock); + list_for_each_entry_safe(inti, n, &li->list, list) { + if (__interrupt_is_deliverable(vcpu, inti)) { + list_del(&inti->list); + deliver = 1; + break; + } + __set_intercept_indicator(vcpu, inti); + } + if (list_empty(&li->list)) + atomic_set(&li->active, 0); + spin_unlock_bh(&li->lock); + if (deliver) { + __do_deliver_interrupt(vcpu, inti); + kfree(inti); + } + } while (deliver); + } + + if ((vcpu->arch.sie_block->ckc < + get_clock() + vcpu->arch.sie_block->epoch)) + __try_deliver_ckc_interrupt(vcpu); + + if (atomic_read(&fi->active)) { + do { + deliver = 0; + spin_lock_bh(&fi->lock); + list_for_each_entry_safe(inti, n, &fi->list, list) { + if (__interrupt_is_deliverable(vcpu, inti)) { + list_del(&inti->list); + deliver = 1; + break; + } + __set_intercept_indicator(vcpu, inti); + } + if (list_empty(&fi->list)) + atomic_set(&fi->active, 0); + spin_unlock_bh(&fi->lock); + if (deliver) { + __do_deliver_interrupt(vcpu, inti); + kfree(inti); + } + } while (deliver); + } +} + +int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) +{ + struct local_interrupt *li = &vcpu->arch.local_int; + struct interrupt_info *inti; + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + inti->type = KVM_S390_PROGRAM_INT;; + inti->pgm.code = code; + + VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code); + spin_lock_bh(&li->lock); + list_add(&inti->list, &li->list); + atomic_set(&li->active, 1); + BUG_ON(waitqueue_active(&li->wq)); + spin_unlock_bh(&li->lock); + return 0; +} + +int kvm_s390_inject_vm(struct kvm *kvm, + struct kvm_s390_interrupt *s390int) +{ + struct local_interrupt *li; + struct float_interrupt *fi; + struct interrupt_info *inti; + int sigcpu; + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + switch (s390int->type) { + case KVM_S390_INT_VIRTIO: + VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%lx", + s390int->parm, s390int->parm64); + inti->type = s390int->type; + inti->ext.ext_params = s390int->parm; + inti->ext.ext_params2 = s390int->parm64; + break; + case KVM_S390_INT_SERVICE: + VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm); + inti->type = s390int->type; + inti->ext.ext_params = s390int->parm; + break; + case KVM_S390_PROGRAM_INT: + case KVM_S390_SIGP_STOP: + case KVM_S390_INT_EMERGENCY: + default: + kfree(inti); + return -EINVAL; + } + + mutex_lock(&kvm->lock); + fi = &kvm->arch.float_int; + spin_lock_bh(&fi->lock); + list_add_tail(&inti->list, &fi->list); + atomic_set(&fi->active, 1); + sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); + if (sigcpu == KVM_MAX_VCPUS) { + do { + sigcpu = fi->next_rr_cpu++; + if (sigcpu == KVM_MAX_VCPUS) + sigcpu = fi->next_rr_cpu = 0; + } while (fi->local_int[sigcpu] == NULL); + } + li = fi->local_int[sigcpu]; + spin_lock_bh(&li->lock); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + if (waitqueue_active(&li->wq)) + wake_up_interruptible(&li->wq); + spin_unlock_bh(&li->lock); + spin_unlock_bh(&fi->lock); + mutex_unlock(&kvm->lock); + return 0; +} + +int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, + struct kvm_s390_interrupt *s390int) +{ + struct local_interrupt *li; + struct interrupt_info *inti; + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + switch (s390int->type) { + case KVM_S390_PROGRAM_INT: + if (s390int->parm & 0xffff0000) { + kfree(inti); + return -EINVAL; + } + inti->type = s390int->type; + inti->pgm.code = s390int->parm; + VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)", + s390int->parm); + break; + case KVM_S390_SIGP_STOP: + case KVM_S390_RESTART: + case KVM_S390_SIGP_SET_PREFIX: + case KVM_S390_INT_EMERGENCY: + VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type); + inti->type = s390int->type; + break; + case KVM_S390_INT_VIRTIO: + case KVM_S390_INT_SERVICE: + default: + kfree(inti); + return -EINVAL; + } + + mutex_lock(&vcpu->kvm->lock); + li = &vcpu->arch.local_int; + spin_lock_bh(&li->lock); + if (inti->type == KVM_S390_PROGRAM_INT) + list_add(&inti->list, &li->list); + else + list_add_tail(&inti->list, &li->list); + atomic_set(&li->active, 1); + if (inti->type == KVM_S390_SIGP_STOP) + li->action_bits |= ACTION_STOP_ON_STOP; + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + if (waitqueue_active(&li->wq)) + wake_up_interruptible(&vcpu->arch.local_int.wq); + spin_unlock_bh(&li->lock); + mutex_unlock(&vcpu->kvm->lock); + return 0; +} diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c new file mode 100644 index 000000000000..98d1e73e01f1 --- /dev/null +++ b/arch/s390/kvm/kvm-s390.c @@ -0,0 +1,685 @@ +/* + * s390host.c -- hosting zSeries kernel virtual machines + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + * Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/compiler.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <asm/lowcore.h> +#include <asm/pgtable.h> + +#include "kvm-s390.h" +#include "gaccess.h" + +#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU + +struct kvm_stats_debugfs_item debugfs_entries[] = { + { "userspace_handled", VCPU_STAT(exit_userspace) }, + { "exit_validity", VCPU_STAT(exit_validity) }, + { "exit_stop_request", VCPU_STAT(exit_stop_request) }, + { "exit_external_request", VCPU_STAT(exit_external_request) }, + { "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) }, + { "exit_instruction", VCPU_STAT(exit_instruction) }, + { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, + { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, + { "instruction_lctg", VCPU_STAT(instruction_lctg) }, + { "instruction_lctl", VCPU_STAT(instruction_lctl) }, + { "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) }, + { "deliver_service_signal", VCPU_STAT(deliver_service_signal) }, + { "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) }, + { "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) }, + { "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) }, + { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, + { "deliver_program_interruption", VCPU_STAT(deliver_program_int) }, + { "exit_wait_state", VCPU_STAT(exit_wait_state) }, + { "instruction_stidp", VCPU_STAT(instruction_stidp) }, + { "instruction_spx", VCPU_STAT(instruction_spx) }, + { "instruction_stpx", VCPU_STAT(instruction_stpx) }, + { "instruction_stap", VCPU_STAT(instruction_stap) }, + { "instruction_storage_key", VCPU_STAT(instruction_storage_key) }, + { "instruction_stsch", VCPU_STAT(instruction_stsch) }, + { "instruction_chsc", VCPU_STAT(instruction_chsc) }, + { "instruction_stsi", VCPU_STAT(instruction_stsi) }, + { "instruction_stfl", VCPU_STAT(instruction_stfl) }, + { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) }, + { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) }, + { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) }, + { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) }, + { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) }, + { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, + { "diagnose_44", VCPU_STAT(diagnose_44) }, + { NULL } +}; + + +/* Section: not file related */ +void kvm_arch_hardware_enable(void *garbage) +{ + /* every s390 is virtualization enabled ;-) */ +} + +void kvm_arch_hardware_disable(void *garbage) +{ +} + +void decache_vcpus_on_cpu(int cpu) +{ +} + +int kvm_arch_hardware_setup(void) +{ + return 0; +} + +void kvm_arch_hardware_unsetup(void) +{ +} + +void kvm_arch_check_processor_compat(void *rtn) +{ +} + +int kvm_arch_init(void *opaque) +{ + return 0; +} + +void kvm_arch_exit(void) +{ +} + +/* Section: device related */ +long kvm_arch_dev_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + if (ioctl == KVM_S390_ENABLE_SIE) + return s390_enable_sie(); + return -EINVAL; +} + +int kvm_dev_ioctl_check_extension(long ext) +{ + return 0; +} + +/* Section: vm related */ +/* + * Get (and clear) the dirty memory log for a memory slot. + */ +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log) +{ + return 0; +} + +long kvm_arch_vm_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + void __user *argp = (void __user *)arg; + int r; + + switch (ioctl) { + case KVM_S390_INTERRUPT: { + struct kvm_s390_interrupt s390int; + + r = -EFAULT; + if (copy_from_user(&s390int, argp, sizeof(s390int))) + break; + r = kvm_s390_inject_vm(kvm, &s390int); + break; + } + default: + r = -EINVAL; + } + + return r; +} + +struct kvm *kvm_arch_create_vm(void) +{ + struct kvm *kvm; + int rc; + char debug_name[16]; + + rc = s390_enable_sie(); + if (rc) + goto out_nokvm; + + rc = -ENOMEM; + kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + if (!kvm) + goto out_nokvm; + + kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL); + if (!kvm->arch.sca) + goto out_nosca; + + sprintf(debug_name, "kvm-%u", current->pid); + + kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long)); + if (!kvm->arch.dbf) + goto out_nodbf; + + spin_lock_init(&kvm->arch.float_int.lock); + INIT_LIST_HEAD(&kvm->arch.float_int.list); + + debug_register_view(kvm->arch.dbf, &debug_sprintf_view); + VM_EVENT(kvm, 3, "%s", "vm created"); + + try_module_get(THIS_MODULE); + + return kvm; +out_nodbf: + free_page((unsigned long)(kvm->arch.sca)); +out_nosca: + kfree(kvm); +out_nokvm: + return ERR_PTR(rc); +} + +void kvm_arch_destroy_vm(struct kvm *kvm) +{ + debug_unregister(kvm->arch.dbf); + free_page((unsigned long)(kvm->arch.sca)); + kfree(kvm); + module_put(THIS_MODULE); +} + +/* Section: vcpu related */ +int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) +{ + return 0; +} + +void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) +{ + /* kvm common code refers to this, but does'nt call it */ + BUG(); +} + +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + save_fp_regs(&vcpu->arch.host_fpregs); + save_access_regs(vcpu->arch.host_acrs); + vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK; + restore_fp_regs(&vcpu->arch.guest_fpregs); + restore_access_regs(vcpu->arch.guest_acrs); + + if (signal_pending(current)) + atomic_set_mask(CPUSTAT_STOP_INT, + &vcpu->arch.sie_block->cpuflags); +} + +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) +{ + save_fp_regs(&vcpu->arch.guest_fpregs); + save_access_regs(vcpu->arch.guest_acrs); + restore_fp_regs(&vcpu->arch.host_fpregs); + restore_access_regs(vcpu->arch.host_acrs); +} + +static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) +{ + /* this equals initial cpu reset in pop, but we don't switch to ESA */ + vcpu->arch.sie_block->gpsw.mask = 0UL; + vcpu->arch.sie_block->gpsw.addr = 0UL; + vcpu->arch.sie_block->prefix = 0UL; + vcpu->arch.sie_block->ihcpu = 0xffff; + vcpu->arch.sie_block->cputm = 0UL; + vcpu->arch.sie_block->ckc = 0UL; + vcpu->arch.sie_block->todpr = 0; + memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64)); + vcpu->arch.sie_block->gcr[0] = 0xE0UL; + vcpu->arch.sie_block->gcr[14] = 0xC2000000UL; + vcpu->arch.guest_fpregs.fpc = 0; + asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); + vcpu->arch.sie_block->gbea = 1; +} + +int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) +{ + atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH); + vcpu->arch.sie_block->gmslm = 0xffffffffffUL; + vcpu->arch.sie_block->gmsor = 0x000000000000; + vcpu->arch.sie_block->ecb = 2; + vcpu->arch.sie_block->eca = 0xC1002001U; + setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup, + (unsigned long) vcpu); + get_cpu_id(&vcpu->arch.cpu_id); + vcpu->arch.cpu_id.version = 0xfe; + return 0; +} + +struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, + unsigned int id) +{ + struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); + int rc = -ENOMEM; + + if (!vcpu) + goto out_nomem; + + vcpu->arch.sie_block = (struct sie_block *) get_zeroed_page(GFP_KERNEL); + + if (!vcpu->arch.sie_block) + goto out_free_cpu; + + vcpu->arch.sie_block->icpua = id; + BUG_ON(!kvm->arch.sca); + BUG_ON(kvm->arch.sca->cpu[id].sda); + kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block; + vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32); + vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca; + + spin_lock_init(&vcpu->arch.local_int.lock); + INIT_LIST_HEAD(&vcpu->arch.local_int.list); + vcpu->arch.local_int.float_int = &kvm->arch.float_int; + spin_lock_bh(&kvm->arch.float_int.lock); + kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int; + init_waitqueue_head(&vcpu->arch.local_int.wq); + vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; + spin_unlock_bh(&kvm->arch.float_int.lock); + + rc = kvm_vcpu_init(vcpu, kvm, id); + if (rc) + goto out_free_cpu; + VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu, + vcpu->arch.sie_block); + + try_module_get(THIS_MODULE); + + return vcpu; +out_free_cpu: + kfree(vcpu); +out_nomem: + return ERR_PTR(rc); +} + +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + VCPU_EVENT(vcpu, 3, "%s", "destroy cpu"); + free_page((unsigned long)(vcpu->arch.sie_block)); + kfree(vcpu); + module_put(THIS_MODULE); +} + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + /* kvm common code refers to this, but never calls it */ + BUG(); + return 0; +} + +static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) +{ + vcpu_load(vcpu); + kvm_s390_vcpu_initial_reset(vcpu); + vcpu_put(vcpu); + return 0; +} + +int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_load(vcpu); + memcpy(&vcpu->arch.guest_gprs, ®s->gprs, sizeof(regs->gprs)); + vcpu_put(vcpu); + return 0; +} + +int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_load(vcpu); + memcpy(®s->gprs, &vcpu->arch.guest_gprs, sizeof(regs->gprs)); + vcpu_put(vcpu); + return 0; +} + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + vcpu_load(vcpu); + memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs)); + memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs)); + vcpu_put(vcpu); + return 0; +} + +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + vcpu_load(vcpu); + memcpy(&sregs->acrs, &vcpu->arch.guest_acrs, sizeof(sregs->acrs)); + memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs)); + vcpu_put(vcpu); + return 0; +} + +int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + vcpu_load(vcpu); + memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); + vcpu->arch.guest_fpregs.fpc = fpu->fpc; + vcpu_put(vcpu); + return 0; +} + +int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + vcpu_load(vcpu); + memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs)); + fpu->fpc = vcpu->arch.guest_fpregs.fpc; + vcpu_put(vcpu); + return 0; +} + +static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw) +{ + int rc = 0; + + vcpu_load(vcpu); + if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING) + rc = -EBUSY; + else + vcpu->arch.sie_block->gpsw = psw; + vcpu_put(vcpu); + return rc; +} + +int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, + struct kvm_translation *tr) +{ + return -EINVAL; /* not implemented yet */ +} + +int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, + struct kvm_debug_guest *dbg) +{ + return -EINVAL; /* not implemented yet */ +} + +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + return -EINVAL; /* not implemented yet */ +} + +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + return -EINVAL; /* not implemented yet */ +} + +static void __vcpu_run(struct kvm_vcpu *vcpu) +{ + memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16); + + if (need_resched()) + schedule(); + + vcpu->arch.sie_block->icptcode = 0; + local_irq_disable(); + kvm_guest_enter(); + local_irq_enable(); + VCPU_EVENT(vcpu, 6, "entering sie flags %x", + atomic_read(&vcpu->arch.sie_block->cpuflags)); + sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs); + VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", + vcpu->arch.sie_block->icptcode); + local_irq_disable(); + kvm_guest_exit(); + local_irq_enable(); + + memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16); +} + +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + int rc; + sigset_t sigsaved; + + vcpu_load(vcpu); + + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); + + atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + + BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL); + + switch (kvm_run->exit_reason) { + case KVM_EXIT_S390_SIEIC: + vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask; + vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr; + break; + case KVM_EXIT_UNKNOWN: + case KVM_EXIT_S390_RESET: + break; + default: + BUG(); + } + + might_sleep(); + + do { + kvm_s390_deliver_pending_interrupts(vcpu); + __vcpu_run(vcpu); + rc = kvm_handle_sie_intercept(vcpu); + } while (!signal_pending(current) && !rc); + + if (signal_pending(current) && !rc) + rc = -EINTR; + + if (rc == -ENOTSUPP) { + /* intercept cannot be handled in-kernel, prepare kvm-run */ + kvm_run->exit_reason = KVM_EXIT_S390_SIEIC; + kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode; + kvm_run->s390_sieic.mask = vcpu->arch.sie_block->gpsw.mask; + kvm_run->s390_sieic.addr = vcpu->arch.sie_block->gpsw.addr; + kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa; + kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb; + rc = 0; + } + + if (rc == -EREMOTE) { + /* intercept was handled, but userspace support is needed + * kvm_run has been prepared by the handler */ + rc = 0; + } + + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + vcpu_put(vcpu); + + vcpu->stat.exit_userspace++; + return rc; +} + +static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from, + unsigned long n, int prefix) +{ + if (prefix) + return copy_to_guest(vcpu, guestdest, from, n); + else + return copy_to_guest_absolute(vcpu, guestdest, from, n); +} + +/* + * store status at address + * we use have two special cases: + * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit + * KVM_S390_STORE_STATUS_PREFIXED: -> prefix + */ +int __kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) +{ + const unsigned char archmode = 1; + int prefix; + + if (addr == KVM_S390_STORE_STATUS_NOADDR) { + if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1)) + return -EFAULT; + addr = SAVE_AREA_BASE; + prefix = 0; + } else if (addr == KVM_S390_STORE_STATUS_PREFIXED) { + if (copy_to_guest(vcpu, 163ul, &archmode, 1)) + return -EFAULT; + addr = SAVE_AREA_BASE; + prefix = 1; + } else + prefix = 0; + + if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, fp_regs), + vcpu->arch.guest_fpregs.fprs, 128, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, gp_regs), + vcpu->arch.guest_gprs, 128, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, psw), + &vcpu->arch.sie_block->gpsw, 16, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, pref_reg), + &vcpu->arch.sie_block->prefix, 4, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, + addr + offsetof(struct save_area_s390x, fp_ctrl_reg), + &vcpu->arch.guest_fpregs.fpc, 4, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, tod_reg), + &vcpu->arch.sie_block->todpr, 4, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, timer), + &vcpu->arch.sie_block->cputm, 8, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, clk_cmp), + &vcpu->arch.sie_block->ckc, 8, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, acc_regs), + &vcpu->arch.guest_acrs, 64, prefix)) + return -EFAULT; + + if (__guestcopy(vcpu, + addr + offsetof(struct save_area_s390x, ctrl_regs), + &vcpu->arch.sie_block->gcr, 128, prefix)) + return -EFAULT; + return 0; +} + +static int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) +{ + int rc; + + vcpu_load(vcpu); + rc = __kvm_s390_vcpu_store_status(vcpu, addr); + vcpu_put(vcpu); + return rc; +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + + switch (ioctl) { + case KVM_S390_INTERRUPT: { + struct kvm_s390_interrupt s390int; + + if (copy_from_user(&s390int, argp, sizeof(s390int))) + return -EFAULT; + return kvm_s390_inject_vcpu(vcpu, &s390int); + } + case KVM_S390_STORE_STATUS: + return kvm_s390_vcpu_store_status(vcpu, arg); + case KVM_S390_SET_INITIAL_PSW: { + psw_t psw; + + if (copy_from_user(&psw, argp, sizeof(psw))) + return -EFAULT; + return kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw); + } + case KVM_S390_INITIAL_RESET: + return kvm_arch_vcpu_ioctl_initial_reset(vcpu); + default: + ; + } + return -EINVAL; +} + +/* Section: memory related */ +int kvm_arch_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc) +{ + /* A few sanity checks. We can have exactly one memory slot which has + to start at guest virtual zero and which has to be located at a + page boundary in userland and which has to end at a page boundary. + The memory in userland is ok to be fragmented into various different + vmas. It is okay to mmap() and munmap() stuff in this slot after + doing this call at any time */ + + if (mem->slot) + return -EINVAL; + + if (mem->guest_phys_addr) + return -EINVAL; + + if (mem->userspace_addr & (PAGE_SIZE - 1)) + return -EINVAL; + + if (mem->memory_size & (PAGE_SIZE - 1)) + return -EINVAL; + + kvm->arch.guest_origin = mem->userspace_addr; + kvm->arch.guest_memsize = mem->memory_size; + + /* FIXME: we do want to interrupt running CPUs and update their memory + configuration now to avoid race conditions. But hey, changing the + memory layout while virtual CPUs are running is usually bad + programming practice. */ + + return 0; +} + +gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) +{ + return gfn; +} + +static int __init kvm_s390_init(void) +{ + return kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE); +} + +static void __exit kvm_s390_exit(void) +{ + kvm_exit(); +} + +module_init(kvm_s390_init); +module_exit(kvm_s390_exit); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h new file mode 100644 index 000000000000..3893cf12eacf --- /dev/null +++ b/arch/s390/kvm/kvm-s390.h @@ -0,0 +1,64 @@ +/* + * kvm_s390.h - definition for kvm on s390 + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#ifndef ARCH_S390_KVM_S390_H +#define ARCH_S390_KVM_S390_H + +#include <linux/kvm.h> +#include <linux/kvm_host.h> + +typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); + +int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu); + +#define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\ +do { \ + debug_sprintf_event(d_kvm->arch.dbf, d_loglevel, d_string "\n", \ + d_args); \ +} while (0) + +#define VCPU_EVENT(d_vcpu, d_loglevel, d_string, d_args...)\ +do { \ + debug_sprintf_event(d_vcpu->kvm->arch.dbf, d_loglevel, \ + "%02d[%016lx-%016lx]: " d_string "\n", d_vcpu->vcpu_id, \ + d_vcpu->arch.sie_block->gpsw.mask, d_vcpu->arch.sie_block->gpsw.addr,\ + d_args); \ +} while (0) + +static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu) +{ + return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT; +} + +int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); +void kvm_s390_idle_wakeup(unsigned long data); +void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu); +int kvm_s390_inject_vm(struct kvm *kvm, + struct kvm_s390_interrupt *s390int); +int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, + struct kvm_s390_interrupt *s390int); +int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); + +/* implemented in priv.c */ +int kvm_s390_handle_priv(struct kvm_vcpu *vcpu); + +/* implemented in sigp.c */ +int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); + +/* implemented in kvm-s390.c */ +int __kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, + unsigned long addr); +/* implemented in diag.c */ +int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c new file mode 100644 index 000000000000..c02286c6a931 --- /dev/null +++ b/arch/s390/kvm/priv.c @@ -0,0 +1,314 @@ +/* + * priv.c - handling privileged instructions + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#include <linux/kvm.h> +#include <linux/errno.h> +#include <asm/current.h> +#include <asm/debug.h> +#include <asm/ebcdic.h> +#include <asm/sysinfo.h> +#include "gaccess.h" +#include "kvm-s390.h" + +static int handle_set_prefix(struct kvm_vcpu *vcpu) +{ + int base2 = vcpu->arch.sie_block->ipb >> 28; + int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + u64 operand2; + u32 address = 0; + u8 tmp; + + vcpu->stat.instruction_spx++; + + operand2 = disp2; + if (base2) + operand2 += vcpu->arch.guest_gprs[base2]; + + /* must be word boundary */ + if (operand2 & 3) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + /* get the value */ + if (get_guest_u32(vcpu, operand2, &address)) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + goto out; + } + + address = address & 0x7fffe000u; + + /* make sure that the new value is valid memory */ + if (copy_from_guest_absolute(vcpu, &tmp, address, 1) || + (copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1))) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + goto out; + } + + vcpu->arch.sie_block->prefix = address; + vcpu->arch.sie_block->ihcpu = 0xffff; + + VCPU_EVENT(vcpu, 5, "setting prefix to %x", address); +out: + return 0; +} + +static int handle_store_prefix(struct kvm_vcpu *vcpu) +{ + int base2 = vcpu->arch.sie_block->ipb >> 28; + int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + u64 operand2; + u32 address; + + vcpu->stat.instruction_stpx++; + operand2 = disp2; + if (base2) + operand2 += vcpu->arch.guest_gprs[base2]; + + /* must be word boundary */ + if (operand2 & 3) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + address = vcpu->arch.sie_block->prefix; + address = address & 0x7fffe000u; + + /* get the value */ + if (put_guest_u32(vcpu, operand2, address)) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + goto out; + } + + VCPU_EVENT(vcpu, 5, "storing prefix to %x", address); +out: + return 0; +} + +static int handle_store_cpu_address(struct kvm_vcpu *vcpu) +{ + int base2 = vcpu->arch.sie_block->ipb >> 28; + int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + u64 useraddr; + int rc; + + vcpu->stat.instruction_stap++; + useraddr = disp2; + if (base2) + useraddr += vcpu->arch.guest_gprs[base2]; + + if (useraddr & 1) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + rc = put_guest_u16(vcpu, useraddr, vcpu->vcpu_id); + if (rc == -EFAULT) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + goto out; + } + + VCPU_EVENT(vcpu, 5, "storing cpu address to %lx", useraddr); +out: + return 0; +} + +static int handle_skey(struct kvm_vcpu *vcpu) +{ + vcpu->stat.instruction_storage_key++; + vcpu->arch.sie_block->gpsw.addr -= 4; + VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation"); + return 0; +} + +static int handle_stsch(struct kvm_vcpu *vcpu) +{ + vcpu->stat.instruction_stsch++; + VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3"); + /* condition code 3 */ + vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + return 0; +} + +static int handle_chsc(struct kvm_vcpu *vcpu) +{ + vcpu->stat.instruction_chsc++; + VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3"); + /* condition code 3 */ + vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + return 0; +} + +static int handle_stfl(struct kvm_vcpu *vcpu) +{ + unsigned int facility_list = stfl(); + int rc; + + vcpu->stat.instruction_stfl++; + facility_list &= ~(1UL<<24); /* no stfle */ + + rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list), + &facility_list, sizeof(facility_list)); + if (rc == -EFAULT) + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + else + VCPU_EVENT(vcpu, 5, "store facility list value %x", + facility_list); + return 0; +} + +static int handle_stidp(struct kvm_vcpu *vcpu) +{ + int base2 = vcpu->arch.sie_block->ipb >> 28; + int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + u64 operand2; + int rc; + + vcpu->stat.instruction_stidp++; + operand2 = disp2; + if (base2) + operand2 += vcpu->arch.guest_gprs[base2]; + + if (operand2 & 7) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + rc = put_guest_u64(vcpu, operand2, vcpu->arch.stidp_data); + if (rc == -EFAULT) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + goto out; + } + + VCPU_EVENT(vcpu, 5, "%s", "store cpu id"); +out: + return 0; +} + +static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) +{ + struct float_interrupt *fi = &vcpu->kvm->arch.float_int; + int cpus = 0; + int n; + + spin_lock_bh(&fi->lock); + for (n = 0; n < KVM_MAX_VCPUS; n++) + if (fi->local_int[n]) + cpus++; + spin_unlock_bh(&fi->lock); + + /* deal with other level 3 hypervisors */ + if (stsi(mem, 3, 2, 2) == -ENOSYS) + mem->count = 0; + if (mem->count < 8) + mem->count++; + for (n = mem->count - 1; n > 0 ; n--) + memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0])); + + mem->vm[0].cpus_total = cpus; + mem->vm[0].cpus_configured = cpus; + mem->vm[0].cpus_standby = 0; + mem->vm[0].cpus_reserved = 0; + mem->vm[0].caf = 1000; + memcpy(mem->vm[0].name, "KVMguest", 8); + ASCEBC(mem->vm[0].name, 8); + memcpy(mem->vm[0].cpi, "KVM/Linux ", 16); + ASCEBC(mem->vm[0].cpi, 16); +} + +static int handle_stsi(struct kvm_vcpu *vcpu) +{ + int fc = (vcpu->arch.guest_gprs[0] & 0xf0000000) >> 28; + int sel1 = vcpu->arch.guest_gprs[0] & 0xff; + int sel2 = vcpu->arch.guest_gprs[1] & 0xffff; + int base2 = vcpu->arch.sie_block->ipb >> 28; + int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + u64 operand2; + unsigned long mem; + + vcpu->stat.instruction_stsi++; + VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2); + + operand2 = disp2; + if (base2) + operand2 += vcpu->arch.guest_gprs[base2]; + + if (operand2 & 0xfff && fc > 0) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + switch (fc) { + case 0: + vcpu->arch.guest_gprs[0] = 3 << 28; + vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + return 0; + case 1: /* same handling for 1 and 2 */ + case 2: + mem = get_zeroed_page(GFP_KERNEL); + if (!mem) + goto out_fail; + if (stsi((void *) mem, fc, sel1, sel2) == -ENOSYS) + goto out_mem; + break; + case 3: + if (sel1 != 2 || sel2 != 2) + goto out_fail; + mem = get_zeroed_page(GFP_KERNEL); + if (!mem) + goto out_fail; + handle_stsi_3_2_2(vcpu, (void *) mem); + break; + default: + goto out_fail; + } + + if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + goto out_mem; + } + free_page(mem); + vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + vcpu->arch.guest_gprs[0] = 0; + return 0; +out_mem: + free_page(mem); +out_fail: + /* condition code 3 */ + vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; + return 0; +} + +static intercept_handler_t priv_handlers[256] = { + [0x02] = handle_stidp, + [0x10] = handle_set_prefix, + [0x11] = handle_store_prefix, + [0x12] = handle_store_cpu_address, + [0x29] = handle_skey, + [0x2a] = handle_skey, + [0x2b] = handle_skey, + [0x34] = handle_stsch, + [0x5f] = handle_chsc, + [0x7d] = handle_stsi, + [0xb1] = handle_stfl, +}; + +int kvm_s390_handle_priv(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; + if (handler) + return handler(vcpu); + return -ENOTSUPP; +} diff --git a/arch/s390/kvm/sie64a.S b/arch/s390/kvm/sie64a.S new file mode 100644 index 000000000000..934fd6a885f6 --- /dev/null +++ b/arch/s390/kvm/sie64a.S @@ -0,0 +1,47 @@ +/* + * sie64a.S - low level sie call + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/errno.h> +#include <asm/asm-offsets.h> + +SP_R5 = 5 * 8 # offset into stackframe +SP_R6 = 6 * 8 + +/* + * sie64a calling convention: + * %r2 pointer to sie control block + * %r3 guest register save area + */ + .globl sie64a +sie64a: + lgr %r5,%r3 + stmg %r5,%r14,SP_R5(%r15) # save register on entry + lgr %r14,%r2 # pointer to sie control block + lmg %r0,%r13,0(%r3) # load guest gprs 0-13 +sie_inst: + sie 0(%r14) + lg %r14,SP_R5(%r15) + stmg %r0,%r13,0(%r14) # save guest gprs 0-13 + lghi %r2,0 + lmg %r6,%r14,SP_R6(%r15) + br %r14 + +sie_err: + lg %r14,SP_R5(%r15) + stmg %r0,%r13,0(%r14) # save guest gprs 0-13 + lghi %r2,-EFAULT + lmg %r6,%r14,SP_R6(%r15) + br %r14 + + .section __ex_table,"a" + .quad sie_inst,sie_err + .previous diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c new file mode 100644 index 000000000000..0a236acfb5f6 --- /dev/null +++ b/arch/s390/kvm/sigp.c @@ -0,0 +1,288 @@ +/* + * sigp.c - handlinge interprocessor communication + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include "gaccess.h" +#include "kvm-s390.h" + +/* sigp order codes */ +#define SIGP_SENSE 0x01 +#define SIGP_EXTERNAL_CALL 0x02 +#define SIGP_EMERGENCY 0x03 +#define SIGP_START 0x04 +#define SIGP_STOP 0x05 +#define SIGP_RESTART 0x06 +#define SIGP_STOP_STORE_STATUS 0x09 +#define SIGP_INITIAL_CPU_RESET 0x0b +#define SIGP_CPU_RESET 0x0c +#define SIGP_SET_PREFIX 0x0d +#define SIGP_STORE_STATUS_ADDR 0x0e +#define SIGP_SET_ARCH 0x12 + +/* cpu status bits */ +#define SIGP_STAT_EQUIPMENT_CHECK 0x80000000UL +#define SIGP_STAT_INCORRECT_STATE 0x00000200UL +#define SIGP_STAT_INVALID_PARAMETER 0x00000100UL +#define SIGP_STAT_EXT_CALL_PENDING 0x00000080UL +#define SIGP_STAT_STOPPED 0x00000040UL +#define SIGP_STAT_OPERATOR_INTERV 0x00000020UL +#define SIGP_STAT_CHECK_STOP 0x00000010UL +#define SIGP_STAT_INOPERATIVE 0x00000004UL +#define SIGP_STAT_INVALID_ORDER 0x00000002UL +#define SIGP_STAT_RECEIVER_CHECK 0x00000001UL + + +static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, u64 *reg) +{ + struct float_interrupt *fi = &vcpu->kvm->arch.float_int; + int rc; + + if (cpu_addr >= KVM_MAX_VCPUS) + return 3; /* not operational */ + + spin_lock_bh(&fi->lock); + if (fi->local_int[cpu_addr] == NULL) + rc = 3; /* not operational */ + else if (atomic_read(fi->local_int[cpu_addr]->cpuflags) + & CPUSTAT_RUNNING) { + *reg &= 0xffffffff00000000UL; + rc = 1; /* status stored */ + } else { + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STAT_STOPPED; + rc = 1; /* status stored */ + } + spin_unlock_bh(&fi->lock); + + VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc); + return rc; +} + +static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) +{ + struct float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct local_interrupt *li; + struct interrupt_info *inti; + int rc; + + if (cpu_addr >= KVM_MAX_VCPUS) + return 3; /* not operational */ + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + inti->type = KVM_S390_INT_EMERGENCY; + + spin_lock_bh(&fi->lock); + li = fi->local_int[cpu_addr]; + if (li == NULL) { + rc = 3; /* not operational */ + kfree(inti); + goto unlock; + } + spin_lock_bh(&li->lock); + list_add_tail(&inti->list, &li->list); + atomic_set(&li->active, 1); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + if (waitqueue_active(&li->wq)) + wake_up_interruptible(&li->wq); + spin_unlock_bh(&li->lock); + rc = 0; /* order accepted */ +unlock: + spin_unlock_bh(&fi->lock); + VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); + return rc; +} + +static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store) +{ + struct float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct local_interrupt *li; + struct interrupt_info *inti; + int rc; + + if (cpu_addr >= KVM_MAX_VCPUS) + return 3; /* not operational */ + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + inti->type = KVM_S390_SIGP_STOP; + + spin_lock_bh(&fi->lock); + li = fi->local_int[cpu_addr]; + if (li == NULL) { + rc = 3; /* not operational */ + kfree(inti); + goto unlock; + } + spin_lock_bh(&li->lock); + list_add_tail(&inti->list, &li->list); + atomic_set(&li->active, 1); + atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); + if (store) + li->action_bits |= ACTION_STORE_ON_STOP; + li->action_bits |= ACTION_STOP_ON_STOP; + if (waitqueue_active(&li->wq)) + wake_up_interruptible(&li->wq); + spin_unlock_bh(&li->lock); + rc = 0; /* order accepted */ +unlock: + spin_unlock_bh(&fi->lock); + VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr); + return rc; +} + +static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) +{ + int rc; + + switch (parameter & 0xff) { + case 0: + printk(KERN_WARNING "kvm: request to switch to ESA/390 mode" + " not supported"); + rc = 3; /* not operational */ + break; + case 1: + case 2: + rc = 0; /* order accepted */ + break; + default: + rc = -ENOTSUPP; + } + return rc; +} + +static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, + u64 *reg) +{ + struct float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct local_interrupt *li; + struct interrupt_info *inti; + int rc; + u8 tmp; + + /* make sure that the new value is valid memory */ + address = address & 0x7fffe000u; + if ((copy_from_guest(vcpu, &tmp, + (u64) (address + vcpu->kvm->arch.guest_origin) , 1)) || + (copy_from_guest(vcpu, &tmp, (u64) (address + + vcpu->kvm->arch.guest_origin + PAGE_SIZE), 1))) { + *reg |= SIGP_STAT_INVALID_PARAMETER; + return 1; /* invalid parameter */ + } + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return 2; /* busy */ + + spin_lock_bh(&fi->lock); + li = fi->local_int[cpu_addr]; + + if ((cpu_addr >= KVM_MAX_VCPUS) || (li == NULL)) { + rc = 1; /* incorrect state */ + *reg &= SIGP_STAT_INCORRECT_STATE; + kfree(inti); + goto out_fi; + } + + spin_lock_bh(&li->lock); + /* cpu must be in stopped state */ + if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) { + rc = 1; /* incorrect state */ + *reg &= SIGP_STAT_INCORRECT_STATE; + kfree(inti); + goto out_li; + } + + inti->type = KVM_S390_SIGP_SET_PREFIX; + inti->prefix.address = address; + + list_add_tail(&inti->list, &li->list); + atomic_set(&li->active, 1); + if (waitqueue_active(&li->wq)) + wake_up_interruptible(&li->wq); + rc = 0; /* order accepted */ + + VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address); +out_li: + spin_unlock_bh(&li->lock); +out_fi: + spin_unlock_bh(&fi->lock); + return rc; +} + +int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) +{ + int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int r3 = vcpu->arch.sie_block->ipa & 0x000f; + int base2 = vcpu->arch.sie_block->ipb >> 28; + int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + u32 parameter; + u16 cpu_addr = vcpu->arch.guest_gprs[r3]; + u8 order_code; + int rc; + + order_code = disp2; + if (base2) + order_code += vcpu->arch.guest_gprs[base2]; + + if (r1 % 2) + parameter = vcpu->arch.guest_gprs[r1]; + else + parameter = vcpu->arch.guest_gprs[r1 + 1]; + + switch (order_code) { + case SIGP_SENSE: + vcpu->stat.instruction_sigp_sense++; + rc = __sigp_sense(vcpu, cpu_addr, + &vcpu->arch.guest_gprs[r1]); + break; + case SIGP_EMERGENCY: + vcpu->stat.instruction_sigp_emergency++; + rc = __sigp_emergency(vcpu, cpu_addr); + break; + case SIGP_STOP: + vcpu->stat.instruction_sigp_stop++; + rc = __sigp_stop(vcpu, cpu_addr, 0); + break; + case SIGP_STOP_STORE_STATUS: + vcpu->stat.instruction_sigp_stop++; + rc = __sigp_stop(vcpu, cpu_addr, 1); + break; + case SIGP_SET_ARCH: + vcpu->stat.instruction_sigp_arch++; + rc = __sigp_set_arch(vcpu, parameter); + break; + case SIGP_SET_PREFIX: + vcpu->stat.instruction_sigp_prefix++; + rc = __sigp_set_prefix(vcpu, cpu_addr, parameter, + &vcpu->arch.guest_gprs[r1]); + break; + case SIGP_RESTART: + vcpu->stat.instruction_sigp_restart++; + /* user space must know about restart */ + default: + return -ENOTSUPP; + } + + if (rc < 0) + return rc; + + vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + vcpu->arch.sie_block->gpsw.mask |= (rc & 3ul) << 44; + return 0; +} diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 52084436ab69..ab6735df2d21 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -2,8 +2,6 @@ # Makefile for s390-specific library files.. # -EXTRA_AFLAGS := -traditional - lib-y += delay.o string.o uaccess_std.o uaccess_pt.o obj-$(CONFIG_32BIT) += div64.o qrnnd.o lib-$(CONFIG_64BIT) += uaccess_mvcos.o diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 70f2a862b670..eae21a8ac72d 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -34,7 +34,7 @@ void __delay(unsigned long loops) */ void __udelay(unsigned long usecs) { - u64 end, time, jiffy_timer = 0; + u64 end, time, old_cc = 0; unsigned long flags, cr0, mask, dummy; int irq_context; @@ -43,8 +43,8 @@ void __udelay(unsigned long usecs) local_bh_disable(); local_irq_save(flags); if (raw_irqs_disabled_flags(flags)) { - jiffy_timer = S390_lowcore.jiffy_timer; - S390_lowcore.jiffy_timer = -1ULL - (4096 << 12); + old_cc = S390_lowcore.clock_comparator; + S390_lowcore.clock_comparator = -1ULL; __ctl_store(cr0, 0, 0); dummy = (cr0 & 0xffff00e0) | 0x00000800; __ctl_load(dummy , 0, 0); @@ -55,8 +55,8 @@ void __udelay(unsigned long usecs) end = get_clock() + ((u64) usecs << 12); do { - time = end < S390_lowcore.jiffy_timer ? - end : S390_lowcore.jiffy_timer; + time = end < S390_lowcore.clock_comparator ? + end : S390_lowcore.clock_comparator; set_clock_comparator(time); trace_hardirqs_on(); __load_psw_mask(mask); @@ -65,10 +65,10 @@ void __udelay(unsigned long usecs) if (raw_irqs_disabled_flags(flags)) { __ctl_load(cr0, 0, 0); - S390_lowcore.jiffy_timer = jiffy_timer; + S390_lowcore.clock_comparator = old_cc; } if (!irq_context) _local_bh_enable(); - set_clock_comparator(S390_lowcore.jiffy_timer); + set_clock_comparator(S390_lowcore.clock_comparator); local_irq_restore(flags); } diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c index 6d8772339d76..3f15aaf54855 100644 --- a/arch/s390/lib/uaccess_mvcos.c +++ b/arch/s390/lib/uaccess_mvcos.c @@ -162,6 +162,7 @@ static size_t clear_user_mvcos(size_t size, void __user *to) return size; } +#ifdef CONFIG_S390_SWITCH_AMODE static size_t strnlen_user_mvcos(size_t count, const char __user *src) { char buf[256]; @@ -199,6 +200,7 @@ static size_t strncpy_from_user_mvcos(size_t count, const char __user *src, } while ((len_str == len) && (done < count)); return done; } +#endif /* CONFIG_S390_SWITCH_AMODE */ struct uaccess_ops uaccess_mvcos = { .copy_from_user = copy_from_user_mvcos_check, diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 5efdfe9f5e76..d66215b0fde9 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -302,6 +302,10 @@ static size_t copy_in_user_pt(size_t n, void __user *to, pte_t *pte_from, *pte_to; int write_user; + if (segment_eq(get_fs(), KERNEL_DS)) { + memcpy((void __force *) to, (void __force *) from, n); + return 0; + } done = 0; retry: spin_lock(&mm->page_table_lock); @@ -361,18 +365,10 @@ fault: : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \ "m" (*uaddr) : "cc" ); -int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old) +static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old) { int oldval = 0, newval, ret; - spin_lock(¤t->mm->page_table_lock); - uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr); - if (!uaddr) { - spin_unlock(¤t->mm->page_table_lock); - return -EFAULT; - } - get_page(virt_to_page(uaddr)); - spin_unlock(¤t->mm->page_table_lock); switch (op) { case FUTEX_OP_SET: __futex_atomic_op("lr %2,%5\n", @@ -397,17 +393,17 @@ int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old) default: ret = -ENOSYS; } - put_page(virt_to_page(uaddr)); - *old = oldval; + if (ret == 0) + *old = oldval; return ret; } -int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval) +int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old) { int ret; - if (!current->mm) - return -EFAULT; + if (segment_eq(get_fs(), KERNEL_DS)) + return __futex_atomic_op_pt(op, uaddr, oparg, old); spin_lock(¤t->mm->page_table_lock); uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr); if (!uaddr) { @@ -416,13 +412,40 @@ int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval) } get_page(virt_to_page(uaddr)); spin_unlock(¤t->mm->page_table_lock); - asm volatile(" cs %1,%4,0(%5)\n" - "0: lr %0,%1\n" - "1:\n" - EX_TABLE(0b,1b) + ret = __futex_atomic_op_pt(op, uaddr, oparg, old); + put_page(virt_to_page(uaddr)); + return ret; +} + +static int __futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval) +{ + int ret; + + asm volatile("0: cs %1,%4,0(%5)\n" + "1: lr %0,%1\n" + "2:\n" + EX_TABLE(0b,2b) EX_TABLE(1b,2b) : "=d" (ret), "+d" (oldval), "=m" (*uaddr) : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr) : "cc", "memory" ); + return ret; +} + +int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval) +{ + int ret; + + if (segment_eq(get_fs(), KERNEL_DS)) + return __futex_atomic_cmpxchg_pt(uaddr, oldval, newval); + spin_lock(¤t->mm->page_table_lock); + uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr); + if (!uaddr) { + spin_unlock(¤t->mm->page_table_lock); + return -EFAULT; + } + get_page(virt_to_page(uaddr)); + spin_unlock(¤t->mm->page_table_lock); + ret = __futex_atomic_cmpxchg_pt(uaddr, oldval, newval); put_page(virt_to_page(uaddr)); return ret; } diff --git a/arch/s390/math-emu/Makefile b/arch/s390/math-emu/Makefile index 73b3e72efc46..c84890341052 100644 --- a/arch/s390/math-emu/Makefile +++ b/arch/s390/math-emu/Makefile @@ -5,4 +5,3 @@ obj-$(CONFIG_MATHEMU) := math.o EXTRA_CFLAGS := -I$(src) -Iinclude/math-emu -w -EXTRA_AFLAGS := -traditional diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index 66401930f83e..fb988a48a754 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -4,4 +4,4 @@ obj-y := init.o fault.o extmem.o mmap.o vmem.o pgtable.o obj-$(CONFIG_CMM) += cmm.o - +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 880b0ebf894b..f231f5ec74b6 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -287,24 +287,10 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long if (rc < 0) goto out_free; - rc = add_shared_memory(seg->start_addr, seg->end - seg->start_addr + 1); + rc = vmem_add_mapping(seg->start_addr, seg->end - seg->start_addr + 1); - switch (rc) { - case 0: - break; - case -ENOSPC: - PRINT_WARN("segment_load: not loading segment %s - overlaps " - "storage/segment\n", name); - goto out_free; - case -ERANGE: - PRINT_WARN("segment_load: not loading segment %s - exceeds " - "kernel mapping range\n", name); - goto out_free; - default: - PRINT_WARN("segment_load: not loading segment %s (rc: %d)\n", - name, rc); + if (rc) goto out_free; - } seg->res = kzalloc(sizeof(struct resource), GFP_KERNEL); if (seg->res == NULL) { @@ -365,7 +351,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long release_resource(seg->res); kfree(seg->res); out_shared: - remove_shared_memory(seg->start_addr, seg->end - seg->start_addr + 1); + vmem_remove_mapping(seg->start_addr, seg->end - seg->start_addr + 1); out_free: kfree(seg); out: @@ -488,7 +474,7 @@ segment_modify_shared (char *name, int do_nonshared) rc = 0; goto out_unlock; out_del: - remove_shared_memory(seg->start_addr, seg->end - seg->start_addr + 1); + vmem_remove_mapping(seg->start_addr, seg->end - seg->start_addr + 1); list_del(&seg->list); dcss_diag(DCSS_PURGESEG, seg->dcss_name, &dummy, &dummy); kfree(seg); @@ -522,7 +508,7 @@ segment_unload(char *name) goto out_unlock; release_resource(seg->res); kfree(seg->res); - remove_shared_memory(seg->start_addr, seg->end - seg->start_addr + 1); + vmem_remove_mapping(seg->start_addr, seg->end - seg->start_addr + 1); list_del(&seg->list); dcss_diag(DCSS_PURGESEG, seg->dcss_name, &dummy, &dummy); kfree(seg); @@ -582,8 +568,59 @@ out: mutex_unlock(&dcss_lock); } +/* + * print appropriate error message for segment_load()/segment_type() + * return code + */ +void segment_warning(int rc, char *seg_name) +{ + switch (rc) { + case -ENOENT: + PRINT_WARN("cannot load/query segment %s, " + "does not exist\n", seg_name); + break; + case -ENOSYS: + PRINT_WARN("cannot load/query segment %s, " + "not running on VM\n", seg_name); + break; + case -EIO: + PRINT_WARN("cannot load/query segment %s, " + "hardware error\n", seg_name); + break; + case -ENOTSUPP: + PRINT_WARN("cannot load/query segment %s, " + "is a multi-part segment\n", seg_name); + break; + case -ENOSPC: + PRINT_WARN("cannot load/query segment %s, " + "overlaps with storage\n", seg_name); + break; + case -EBUSY: + PRINT_WARN("cannot load/query segment %s, " + "overlaps with already loaded dcss\n", seg_name); + break; + case -EPERM: + PRINT_WARN("cannot load/query segment %s, " + "already loaded in incompatible mode\n", seg_name); + break; + case -ENOMEM: + PRINT_WARN("cannot load/query segment %s, " + "out of memory\n", seg_name); + break; + case -ERANGE: + PRINT_WARN("cannot load/query segment %s, " + "exceeds kernel mapping range\n", seg_name); + break; + default: + PRINT_WARN("cannot load/query segment %s, " + "return value %i\n", seg_name, rc); + break; + } +} + EXPORT_SYMBOL(segment_load); EXPORT_SYMBOL(segment_unload); EXPORT_SYMBOL(segment_save); EXPORT_SYMBOL(segment_type); EXPORT_SYMBOL(segment_modify_shared); +EXPORT_SYMBOL(segment_warning); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index ed13d429a487..4d537205e83c 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -28,11 +28,12 @@ #include <linux/hardirq.h> #include <linux/kprobes.h> #include <linux/uaccess.h> - +#include <linux/hugetlb.h> #include <asm/system.h> #include <asm/pgtable.h> #include <asm/s390_ext.h> #include <asm/mmu_context.h> +#include "../kernel/entry.h" #ifndef CONFIG_64BIT #define __FAIL_ADDR_MASK 0x7ffff000 @@ -50,8 +51,6 @@ extern int sysctl_userprocess_debug; #endif -extern void die(const char *,struct pt_regs *,long); - #ifdef CONFIG_KPROBES static inline int notify_page_fault(struct pt_regs *regs, long err) { @@ -245,11 +244,6 @@ static void do_sigbus(struct pt_regs *regs, unsigned long error_code, } #ifdef CONFIG_S390_EXEC_PROTECT -extern long sys_sigreturn(struct pt_regs *regs); -extern long sys_rt_sigreturn(struct pt_regs *regs); -extern long sys32_sigreturn(struct pt_regs *regs); -extern long sys32_rt_sigreturn(struct pt_regs *regs); - static int signal_return(struct mm_struct *mm, struct pt_regs *regs, unsigned long address, unsigned long error_code) { @@ -270,15 +264,15 @@ static int signal_return(struct mm_struct *mm, struct pt_regs *regs, #ifdef CONFIG_COMPAT compat = test_tsk_thread_flag(current, TIF_31BIT); if (compat && instruction == 0x0a77) - sys32_sigreturn(regs); + sys32_sigreturn(); else if (compat && instruction == 0x0aad) - sys32_rt_sigreturn(regs); + sys32_rt_sigreturn(); else #endif if (instruction == 0x0a77) - sys_sigreturn(regs); + sys_sigreturn(); else if (instruction == 0x0aad) - sys_rt_sigreturn(regs); + sys_rt_sigreturn(); else { current->thread.prot_addr = address; current->thread.trap_no = error_code; @@ -374,6 +368,8 @@ good_area: } survive: + if (is_vm_hugetlb_page(vma)) + address &= HPAGE_MASK; /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo @@ -424,7 +420,7 @@ no_context: } void __kprobes do_protection_exception(struct pt_regs *regs, - unsigned long error_code) + long error_code) { /* Protection exception is supressing, decrement psw address. */ regs->psw.addr -= (error_code >> 16); @@ -440,7 +436,7 @@ void __kprobes do_protection_exception(struct pt_regs *regs, do_exception(regs, 4, 1); } -void __kprobes do_dat_exception(struct pt_regs *regs, unsigned long error_code) +void __kprobes do_dat_exception(struct pt_regs *regs, long error_code) { do_exception(regs, error_code & 0xff, 0); } diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c new file mode 100644 index 000000000000..f4b6124fdb75 --- /dev/null +++ b/arch/s390/mm/hugetlbpage.c @@ -0,0 +1,134 @@ +/* + * IBM System z Huge TLB Page Support for Kernel. + * + * Copyright 2007 IBM Corp. + * Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com> + */ + +#include <linux/mm.h> +#include <linux/hugetlb.h> + + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *pteptr, pte_t pteval) +{ + pmd_t *pmdp = (pmd_t *) pteptr; + pte_t shadow_pteval = pteval; + unsigned long mask; + + if (!MACHINE_HAS_HPAGE) { + pteptr = (pte_t *) pte_page(pteval)[1].index; + mask = pte_val(pteval) & + (_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO); + pte_val(pteval) = (_SEGMENT_ENTRY + __pa(pteptr)) | mask; + if (mm->context.noexec) { + pteptr += PTRS_PER_PTE; + pte_val(shadow_pteval) = + (_SEGMENT_ENTRY + __pa(pteptr)) | mask; + } + } + + pmd_val(*pmdp) = pte_val(pteval); + if (mm->context.noexec) { + pmdp = get_shadow_table(pmdp); + pmd_val(*pmdp) = pte_val(shadow_pteval); + } +} + +int arch_prepare_hugepage(struct page *page) +{ + unsigned long addr = page_to_phys(page); + pte_t pte; + pte_t *ptep; + int i; + + if (MACHINE_HAS_HPAGE) + return 0; + + ptep = (pte_t *) pte_alloc_one(&init_mm, address); + if (!ptep) + return -ENOMEM; + + pte = mk_pte(page, PAGE_RW); + for (i = 0; i < PTRS_PER_PTE; i++) { + set_pte_at(&init_mm, addr + i * PAGE_SIZE, ptep + i, pte); + pte_val(pte) += PAGE_SIZE; + } + page[1].index = (unsigned long) ptep; + return 0; +} + +void arch_release_hugepage(struct page *page) +{ + pte_t *ptep; + + if (MACHINE_HAS_HPAGE) + return; + + ptep = (pte_t *) page[1].index; + if (!ptep) + return; + pte_free(&init_mm, ptep); + page[1].index = 0; +} + +pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp = NULL; + + pgdp = pgd_offset(mm, addr); + pudp = pud_alloc(mm, pgdp, addr); + if (pudp) + pmdp = pmd_alloc(mm, pudp, addr); + return (pte_t *) pmdp; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp = NULL; + + pgdp = pgd_offset(mm, addr); + if (pgd_present(*pgdp)) { + pudp = pud_offset(pgdp, addr); + if (pud_present(*pudp)) + pmdp = pmd_offset(pudp, addr); + } + return (pte_t *) pmdp; +} + +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + return 0; +} + +struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, + int write) +{ + return ERR_PTR(-EINVAL); +} + +int pmd_huge(pmd_t pmd) +{ + if (!MACHINE_HAS_HPAGE) + return 0; + + return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE); +} + +struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, + pmd_t *pmdp, int write) +{ + struct page *page; + + if (!MACHINE_HAS_HPAGE) + return NULL; + + page = pmd_page(*pmdp); + if (page) + page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT); + return page; +} diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 8053245fe259..fa31de6ae97a 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -50,7 +50,6 @@ void show_mem(void) printk("Mem-info:\n"); show_free_areas(); - printk("Free swap: %6ldkB\n", nr_swap_pages << (PAGE_SHIFT - 10)); i = max_mapnr; while (i-- > 0) { if (!pfn_valid(i)) @@ -78,28 +77,6 @@ void show_mem(void) printk("%lu pages pagetables\n", global_page_state(NR_PAGETABLE)); } -static void __init setup_ro_region(void) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - pte_t new_pte; - unsigned long address, end; - - address = ((unsigned long)&_stext) & PAGE_MASK; - end = PFN_ALIGN((unsigned long)&_eshared); - - for (; address < end; address += PAGE_SIZE) { - pgd = pgd_offset_k(address); - pud = pud_offset(pgd, address); - pmd = pmd_offset(pud, address); - pte = pte_offset_kernel(pmd, address); - new_pte = mk_pte_phys(address, __pgprot(_PAGE_RO)); - *pte = new_pte; - } -} - /* * paging_init() sets up the page tables */ @@ -122,7 +99,6 @@ void __init paging_init(void) clear_table((unsigned long *) init_mm.pgd, pgd_type, sizeof(unsigned long)*2048); vmem_map_init(); - setup_ro_region(); /* enable virtual mapping in kernel mode */ __ctl_load(S390_lowcore.kernel_asce, 1, 1); @@ -130,6 +106,8 @@ void __init paging_init(void) __ctl_load(S390_lowcore.kernel_asce, 13, 13); __raw_local_irq_ssm(ssm_mask); + sparse_memory_present_with_active_regions(MAX_NUMNODES); + sparse_init(); memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index fd072013f88c..5c1aea97cd12 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -30,11 +30,27 @@ #define TABLES_PER_PAGE 4 #define FRAG_MASK 15UL #define SECOND_HALVES 10UL + +void clear_table_pgstes(unsigned long *table) +{ + clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/4); + memset(table + 256, 0, PAGE_SIZE/4); + clear_table(table + 512, _PAGE_TYPE_EMPTY, PAGE_SIZE/4); + memset(table + 768, 0, PAGE_SIZE/4); +} + #else #define ALLOC_ORDER 2 #define TABLES_PER_PAGE 2 #define FRAG_MASK 3UL #define SECOND_HALVES 2UL + +void clear_table_pgstes(unsigned long *table) +{ + clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2); + memset(table + 256, 0, PAGE_SIZE/2); +} + #endif unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec) @@ -153,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) unsigned long *table; unsigned long bits; - bits = mm->context.noexec ? 3UL : 1UL; + bits = (mm->context.noexec || mm->context.pgstes) ? 3UL : 1UL; spin_lock(&mm->page_table_lock); page = NULL; if (!list_empty(&mm->context.pgtable_list)) { @@ -170,7 +186,10 @@ unsigned long *page_table_alloc(struct mm_struct *mm) pgtable_page_ctor(page); page->flags &= ~FRAG_MASK; table = (unsigned long *) page_to_phys(page); - clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE); + if (mm->context.pgstes) + clear_table_pgstes(table); + else + clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE); spin_lock(&mm->page_table_lock); list_add(&page->lru, &mm->context.pgtable_list); } @@ -191,7 +210,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) struct page *page; unsigned long bits; - bits = mm->context.noexec ? 3UL : 1UL; + bits = (mm->context.noexec || mm->context.pgstes) ? 3UL : 1UL; bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long); page = pfn_to_page(__pa(table) >> PAGE_SHIFT); spin_lock(&mm->page_table_lock); @@ -228,3 +247,43 @@ void disable_noexec(struct mm_struct *mm, struct task_struct *tsk) mm->context.noexec = 0; update_mm(mm, tsk); } + +/* + * switch on pgstes for its userspace process (for kvm) + */ +int s390_enable_sie(void) +{ + struct task_struct *tsk = current; + struct mm_struct *mm; + int rc; + + task_lock(tsk); + + rc = 0; + if (tsk->mm->context.pgstes) + goto unlock; + + rc = -EINVAL; + if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || + tsk->mm != tsk->active_mm || tsk->mm->ioctx_list) + goto unlock; + + tsk->mm->context.pgstes = 1; /* dirty little tricks .. */ + mm = dup_mm(tsk); + tsk->mm->context.pgstes = 0; + + rc = -ENOMEM; + if (!mm) + goto unlock; + mmput(tsk->mm); + tsk->mm = tsk->active_mm = mm; + preempt_disable(); + update_mm(mm, tsk); + cpu_set(smp_processor_id(), mm->cpu_vm_mask); + preempt_enable(); + rc = 0; +unlock: + task_unlock(tsk); + return rc; +} +EXPORT_SYMBOL_GPL(s390_enable_sie); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 35d90a4720fd..beccacf907f3 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -10,10 +10,12 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/list.h> +#include <linux/hugetlb.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> #include <asm/setup.h> #include <asm/tlbflush.h> +#include <asm/sections.h> static DEFINE_MUTEX(vmem_mutex); @@ -25,43 +27,6 @@ struct memory_segment { static LIST_HEAD(mem_segs); -void __meminit memmap_init(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn) -{ - struct page *start, *end; - struct page *map_start, *map_end; - int i; - - start = pfn_to_page(start_pfn); - end = start + size; - - for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { - unsigned long cstart, cend; - - cstart = PFN_DOWN(memory_chunk[i].addr); - cend = cstart + PFN_DOWN(memory_chunk[i].size); - - map_start = mem_map + cstart; - map_end = mem_map + cend; - - if (map_start < start) - map_start = start; - if (map_end > end) - map_end = end; - - map_start -= ((unsigned long) map_start & (PAGE_SIZE - 1)) - / sizeof(struct page); - map_end += ((PFN_ALIGN((unsigned long) map_end) - - (unsigned long) map_end) - / sizeof(struct page)); - - if (map_start < map_end) - memmap_init_zone((unsigned long)(map_end - map_start), - nid, zone, page_to_pfn(map_start), - MEMMAP_EARLY); - } -} - static void __ref *vmem_alloc_pages(unsigned int order) { if (slab_is_available()) @@ -77,8 +42,7 @@ static inline pud_t *vmem_pud_alloc(void) pud = vmem_alloc_pages(2); if (!pud) return NULL; - pud_val(*pud) = _REGION3_ENTRY_EMPTY; - memcpy(pud + 1, pud, (PTRS_PER_PUD - 1)*sizeof(pud_t)); + clear_table((unsigned long *) pud, _REGION3_ENTRY_EMPTY, PAGE_SIZE * 4); #endif return pud; } @@ -91,7 +55,7 @@ static inline pmd_t *vmem_pmd_alloc(void) pmd = vmem_alloc_pages(2); if (!pmd) return NULL; - clear_table((unsigned long *) pmd, _SEGMENT_ENTRY_EMPTY, PAGE_SIZE*4); + clear_table((unsigned long *) pmd, _SEGMENT_ENTRY_EMPTY, PAGE_SIZE * 4); #endif return pmd; } @@ -114,7 +78,7 @@ static pte_t __init_refok *vmem_pte_alloc(void) /* * Add a physical memory range to the 1:1 mapping. */ -static int vmem_add_range(unsigned long start, unsigned long size) +static int vmem_add_mem(unsigned long start, unsigned long size, int ro) { unsigned long address; pgd_t *pg_dir; @@ -141,7 +105,19 @@ static int vmem_add_range(unsigned long start, unsigned long size) pud_populate_kernel(&init_mm, pu_dir, pm_dir); } + pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0)); pm_dir = pmd_offset(pu_dir, address); + +#ifdef __s390x__ + if (MACHINE_HAS_HPAGE && !(address & ~HPAGE_MASK) && + (address + HPAGE_SIZE <= start + size) && + (address >= HPAGE_SIZE)) { + pte_val(pte) |= _SEGMENT_ENTRY_LARGE; + pmd_val(*pm_dir) = pte_val(pte); + address += HPAGE_SIZE - PAGE_SIZE; + continue; + } +#endif if (pmd_none(*pm_dir)) { pt_dir = vmem_pte_alloc(); if (!pt_dir) @@ -150,7 +126,6 @@ static int vmem_add_range(unsigned long start, unsigned long size) } pt_dir = pte_offset_kernel(pm_dir, address); - pte = pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL); *pt_dir = pte; } ret = 0; @@ -181,6 +156,13 @@ static void vmem_remove_range(unsigned long start, unsigned long size) pm_dir = pmd_offset(pu_dir, address); if (pmd_none(*pm_dir)) continue; + + if (pmd_huge(*pm_dir)) { + pmd_clear_kernel(pm_dir); + address += HPAGE_SIZE - PAGE_SIZE; + continue; + } + pt_dir = pte_offset_kernel(pm_dir, address); *pt_dir = pte; } @@ -190,10 +172,9 @@ static void vmem_remove_range(unsigned long start, unsigned long size) /* * Add a backed mem_map array to the virtual mem_map array. */ -static int vmem_add_mem_map(unsigned long start, unsigned long size) +int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) { unsigned long address, start_addr, end_addr; - struct page *map_start, *map_end; pgd_t *pg_dir; pud_t *pu_dir; pmd_t *pm_dir; @@ -201,11 +182,8 @@ static int vmem_add_mem_map(unsigned long start, unsigned long size) pte_t pte; int ret = -ENOMEM; - map_start = VMEM_MAP + PFN_DOWN(start); - map_end = VMEM_MAP + PFN_DOWN(start + size); - - start_addr = (unsigned long) map_start & PAGE_MASK; - end_addr = PFN_ALIGN((unsigned long) map_end); + start_addr = (unsigned long) start; + end_addr = (unsigned long) (start + nr); for (address = start_addr; address < end_addr; address += PAGE_SIZE) { pg_dir = pgd_offset_k(address); @@ -249,16 +227,6 @@ out: return ret; } -static int vmem_add_mem(unsigned long start, unsigned long size) -{ - int ret; - - ret = vmem_add_mem_map(start, size); - if (ret) - return ret; - return vmem_add_range(start, size); -} - /* * Add memory segment to the segment list if it doesn't overlap with * an already present segment. @@ -296,7 +264,7 @@ static void __remove_shared_memory(struct memory_segment *seg) vmem_remove_range(seg->start, seg->size); } -int remove_shared_memory(unsigned long start, unsigned long size) +int vmem_remove_mapping(unsigned long start, unsigned long size) { struct memory_segment *seg; int ret; @@ -320,11 +288,9 @@ out: return ret; } -int add_shared_memory(unsigned long start, unsigned long size) +int vmem_add_mapping(unsigned long start, unsigned long size) { struct memory_segment *seg; - struct page *page; - unsigned long pfn, num_pfn, end_pfn; int ret; mutex_lock(&vmem_mutex); @@ -339,24 +305,9 @@ int add_shared_memory(unsigned long start, unsigned long size) if (ret) goto out_free; - ret = vmem_add_mem(start, size); + ret = vmem_add_mem(start, size, 0); if (ret) goto out_remove; - - pfn = PFN_DOWN(start); - num_pfn = PFN_DOWN(size); - end_pfn = pfn + num_pfn; - - page = pfn_to_page(pfn); - memset(page, 0, num_pfn * sizeof(struct page)); - - for (; pfn < end_pfn; pfn++) { - page = pfn_to_page(pfn); - init_page_count(page); - reset_page_mapcount(page); - SetPageReserved(page); - INIT_LIST_HEAD(&page->lru); - } goto out; out_remove: @@ -375,14 +326,34 @@ out: */ void __init vmem_map_init(void) { + unsigned long ro_start, ro_end; + unsigned long start, end; int i; INIT_LIST_HEAD(&init_mm.context.crst_list); INIT_LIST_HEAD(&init_mm.context.pgtable_list); init_mm.context.noexec = 0; - NODE_DATA(0)->node_mem_map = VMEM_MAP; - for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) - vmem_add_mem(memory_chunk[i].addr, memory_chunk[i].size); + ro_start = ((unsigned long)&_stext) & PAGE_MASK; + ro_end = PFN_ALIGN((unsigned long)&_eshared); + for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { + start = memory_chunk[i].addr; + end = memory_chunk[i].addr + memory_chunk[i].size; + if (start >= ro_end || end <= ro_start) + vmem_add_mem(start, end - start, 0); + else if (start >= ro_start && end <= ro_end) + vmem_add_mem(start, end - start, 1); + else if (start >= ro_start) { + vmem_add_mem(start, ro_end - start, 1); + vmem_add_mem(ro_end, end - ro_end, 0); + } else if (end < ro_end) { + vmem_add_mem(start, ro_start - start, 0); + vmem_add_mem(ro_start, end - ro_start, 1); + } else { + vmem_add_mem(start, ro_start - start, 0); + vmem_add_mem(ro_start, ro_end - ro_start, 1); + vmem_add_mem(ro_end, end - ro_end, 0); + } + } } /* |