diff options
46 files changed, 1118 insertions, 356 deletions
diff --git a/Documentation/devicetree/bindings/interrupt-controller/lsi,zevio-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/lsi,zevio-intc.txt new file mode 100644 index 000000000000..aee38e7c13e7 --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/lsi,zevio-intc.txt @@ -0,0 +1,18 @@ +TI-NSPIRE interrupt controller + +Required properties: +- compatible: Compatible property value should be "lsi,zevio-intc". + +- reg: Physical base address of the controller and length of memory mapped + region. + +- interrupt-controller : Identifies the node as an interrupt controller + +Example: + +interrupt-controller { + compatible = "lsi,zevio-intc"; + interrupt-controller; + reg = <0xDC000000 0x1000>; + #interrupt-cells = <1>; +}; diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h index afd45e0d552e..ae763d8bf55a 100644 --- a/arch/ia64/include/asm/unistd.h +++ b/arch/ia64/include/asm/unistd.h @@ -11,7 +11,7 @@ -#define NR_syscalls 312 /* length of syscall table */ +#define NR_syscalls 314 /* length of syscall table */ /* * The following defines stop scripts/checksyscalls.sh from complaining about diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h index 34fd6fe46da1..715e85f858de 100644 --- a/arch/ia64/include/uapi/asm/unistd.h +++ b/arch/ia64/include/uapi/asm/unistd.h @@ -325,5 +325,7 @@ #define __NR_process_vm_writev 1333 #define __NR_accept4 1334 #define __NR_finit_module 1335 +#define __NR_sched_setattr 1336 +#define __NR_sched_getattr 1337 #endif /* _UAPI_ASM_IA64_UNISTD_H */ diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index ddea607f948a..fa8d61a312a7 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1773,6 +1773,8 @@ sys_call_table: data8 sys_process_vm_writev data8 sys_accept4 data8 sys_finit_module // 1335 + data8 sys_sched_setattr + data8 sys_sched_getattr .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */ diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c index 88d0962de65a..2bedafea3d94 100644 --- a/arch/parisc/hpux/fs.c +++ b/arch/parisc/hpux/fs.c @@ -33,22 +33,9 @@ int hpux_execve(struct pt_regs *regs) { - int error; - struct filename *filename; - - filename = getname((const char __user *) regs->gr[26]); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - - error = do_execve(filename->name, + return do_execve(getname((const char __user *) regs->gr[26]), (const char __user *const __user *) regs->gr[25], (const char __user *const __user *) regs->gr[24]); - - putname(filename); - -out: - return error; } struct hpux_dirent { diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index b3feabd39f31..cf3c0089bef2 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -25,6 +25,7 @@ #include <linux/err.h> #include <linux/module.h> #include <linux/init.h> +#include <linux/spinlock.h> #include "crypt_s390.h" #define AES_KEYLEN_128 1 @@ -32,6 +33,7 @@ #define AES_KEYLEN_256 4 static u8 *ctrblk; +static DEFINE_SPINLOCK(ctrblk_lock); static char keylen_flag; struct s390_aes_ctx { @@ -758,43 +760,67 @@ static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, return aes_set_key(tfm, in_key, key_len); } +static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes) +{ + unsigned int i, n; + + /* only use complete blocks, max. PAGE_SIZE */ + n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1); + for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) { + memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE, + AES_BLOCK_SIZE); + crypto_inc(ctrptr + i, AES_BLOCK_SIZE); + } + return n; +} + static int ctr_aes_crypt(struct blkcipher_desc *desc, long func, struct s390_aes_ctx *sctx, struct blkcipher_walk *walk) { int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE); - unsigned int i, n, nbytes; - u8 buf[AES_BLOCK_SIZE]; - u8 *out, *in; + unsigned int n, nbytes; + u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE]; + u8 *out, *in, *ctrptr = ctrbuf; if (!walk->nbytes) return ret; - memcpy(ctrblk, walk->iv, AES_BLOCK_SIZE); + if (spin_trylock(&ctrblk_lock)) + ctrptr = ctrblk; + + memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE); while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) { out = walk->dst.virt.addr; in = walk->src.virt.addr; while (nbytes >= AES_BLOCK_SIZE) { - /* only use complete blocks, max. PAGE_SIZE */ - n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : - nbytes & ~(AES_BLOCK_SIZE - 1); - for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) { - memcpy(ctrblk + i, ctrblk + i - AES_BLOCK_SIZE, - AES_BLOCK_SIZE); - crypto_inc(ctrblk + i, AES_BLOCK_SIZE); - } - ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk); - if (ret < 0 || ret != n) + if (ctrptr == ctrblk) + n = __ctrblk_init(ctrptr, nbytes); + else + n = AES_BLOCK_SIZE; + ret = crypt_s390_kmctr(func, sctx->key, out, in, + n, ctrptr); + if (ret < 0 || ret != n) { + if (ctrptr == ctrblk) + spin_unlock(&ctrblk_lock); return -EIO; + } if (n > AES_BLOCK_SIZE) - memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE, + memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE, AES_BLOCK_SIZE); - crypto_inc(ctrblk, AES_BLOCK_SIZE); + crypto_inc(ctrptr, AES_BLOCK_SIZE); out += n; in += n; nbytes -= n; } ret = blkcipher_walk_done(desc, walk, nbytes); } + if (ctrptr == ctrblk) { + if (nbytes) + memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE); + else + memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE); + spin_unlock(&ctrblk_lock); + } /* * final block may be < AES_BLOCK_SIZE, copy only nbytes */ @@ -802,14 +828,15 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func, out = walk->dst.virt.addr; in = walk->src.virt.addr; ret = crypt_s390_kmctr(func, sctx->key, buf, in, - AES_BLOCK_SIZE, ctrblk); + AES_BLOCK_SIZE, ctrbuf); if (ret < 0 || ret != AES_BLOCK_SIZE) return -EIO; memcpy(out, buf, nbytes); - crypto_inc(ctrblk, AES_BLOCK_SIZE); + crypto_inc(ctrbuf, AES_BLOCK_SIZE); ret = blkcipher_walk_done(desc, walk, 0); + memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE); } - memcpy(walk->iv, ctrblk, AES_BLOCK_SIZE); + return ret; } diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 200f2a1b599d..0a5aac8a9412 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -25,6 +25,7 @@ #define DES3_KEY_SIZE (3 * DES_KEY_SIZE) static u8 *ctrblk; +static DEFINE_SPINLOCK(ctrblk_lock); struct s390_des_ctx { u8 iv[DES_BLOCK_SIZE]; @@ -105,29 +106,35 @@ static int ecb_desall_crypt(struct blkcipher_desc *desc, long func, } static int cbc_desall_crypt(struct blkcipher_desc *desc, long func, - u8 *iv, struct blkcipher_walk *walk) + struct blkcipher_walk *walk) { + struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); int ret = blkcipher_walk_virt(desc, walk); unsigned int nbytes = walk->nbytes; + struct { + u8 iv[DES_BLOCK_SIZE]; + u8 key[DES3_KEY_SIZE]; + } param; if (!nbytes) goto out; - memcpy(iv, walk->iv, DES_BLOCK_SIZE); + memcpy(param.iv, walk->iv, DES_BLOCK_SIZE); + memcpy(param.key, ctx->key, DES3_KEY_SIZE); do { /* only use complete blocks */ unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1); u8 *out = walk->dst.virt.addr; u8 *in = walk->src.virt.addr; - ret = crypt_s390_kmc(func, iv, out, in, n); + ret = crypt_s390_kmc(func, ¶m, out, in, n); if (ret < 0 || ret != n) return -EIO; nbytes &= DES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, walk, nbytes); } while ((nbytes = walk->nbytes)); - memcpy(walk->iv, iv, DES_BLOCK_SIZE); + memcpy(walk->iv, param.iv, DES_BLOCK_SIZE); out: return ret; @@ -179,22 +186,20 @@ static int cbc_des_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, ctx->iv, &walk); + return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, &walk); } static int cbc_des_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, ctx->iv, &walk); + return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, &walk); } static struct crypto_alg cbc_des_alg = { @@ -327,22 +332,20 @@ static int cbc_des3_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, ctx->iv, &walk); + return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, &walk); } static int cbc_des3_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); struct blkcipher_walk walk; blkcipher_walk_init(&walk, dst, src, nbytes); - return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, ctx->iv, &walk); + return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, &walk); } static struct crypto_alg cbc_des3_alg = { @@ -366,54 +369,80 @@ static struct crypto_alg cbc_des3_alg = { } }; +static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes) +{ + unsigned int i, n; + + /* align to block size, max. PAGE_SIZE */ + n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1); + for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) { + memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE); + crypto_inc(ctrptr + i, DES_BLOCK_SIZE); + } + return n; +} + static int ctr_desall_crypt(struct blkcipher_desc *desc, long func, - struct s390_des_ctx *ctx, struct blkcipher_walk *walk) + struct s390_des_ctx *ctx, + struct blkcipher_walk *walk) { int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE); - unsigned int i, n, nbytes; - u8 buf[DES_BLOCK_SIZE]; - u8 *out, *in; + unsigned int n, nbytes; + u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE]; + u8 *out, *in, *ctrptr = ctrbuf; + + if (!walk->nbytes) + return ret; - memcpy(ctrblk, walk->iv, DES_BLOCK_SIZE); + if (spin_trylock(&ctrblk_lock)) + ctrptr = ctrblk; + + memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE); while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) { out = walk->dst.virt.addr; in = walk->src.virt.addr; while (nbytes >= DES_BLOCK_SIZE) { - /* align to block size, max. PAGE_SIZE */ - n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : - nbytes & ~(DES_BLOCK_SIZE - 1); - for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) { - memcpy(ctrblk + i, ctrblk + i - DES_BLOCK_SIZE, - DES_BLOCK_SIZE); - crypto_inc(ctrblk + i, DES_BLOCK_SIZE); - } - ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk); - if (ret < 0 || ret != n) + if (ctrptr == ctrblk) + n = __ctrblk_init(ctrptr, nbytes); + else + n = DES_BLOCK_SIZE; + ret = crypt_s390_kmctr(func, ctx->key, out, in, + n, ctrptr); + if (ret < 0 || ret != n) { + if (ctrptr == ctrblk) + spin_unlock(&ctrblk_lock); return -EIO; + } if (n > DES_BLOCK_SIZE) - memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE, + memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE, DES_BLOCK_SIZE); - crypto_inc(ctrblk, DES_BLOCK_SIZE); + crypto_inc(ctrptr, DES_BLOCK_SIZE); out += n; in += n; nbytes -= n; } ret = blkcipher_walk_done(desc, walk, nbytes); } - + if (ctrptr == ctrblk) { + if (nbytes) + memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE); + else + memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE); + spin_unlock(&ctrblk_lock); + } /* final block may be < DES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { out = walk->dst.virt.addr; in = walk->src.virt.addr; ret = crypt_s390_kmctr(func, ctx->key, buf, in, - DES_BLOCK_SIZE, ctrblk); + DES_BLOCK_SIZE, ctrbuf); if (ret < 0 || ret != DES_BLOCK_SIZE) return -EIO; memcpy(out, buf, nbytes); - crypto_inc(ctrblk, DES_BLOCK_SIZE); + crypto_inc(ctrbuf, DES_BLOCK_SIZE); ret = blkcipher_walk_done(desc, walk, 0); + memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE); } - memcpy(walk->iv, ctrblk, DES_BLOCK_SIZE); return ret; } diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 0f3621ed1db6..321a52ccf63a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -184,6 +184,7 @@ config HAVE_MMIOTRACE_SUPPORT config X86_DECODER_SELFTEST bool "x86 instruction decoder selftest" depends on DEBUG_KERNEL && KPROBES + depends on !COMPILE_TEST ---help--- Perform x86 instruction decoder selftests at build time. This option is useful for checking the sanity of x86 instruction diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 787e1bb5aafc..3e276eb23d1b 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -52,8 +52,7 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s, extern int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op); extern int m2p_remove_override(struct page *page, - struct gnttab_map_grant_ref *kmap_op, - unsigned long mfn); + struct gnttab_map_grant_ref *kmap_op); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); @@ -122,7 +121,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) pfn = m2p_find_override_pfn(mfn, ~0); } - /* + /* * pfn is ~0 if there are no entries in the m2p for mfn or if the * entry doesn't map back to the mfn and m2p_override doesn't have a * valid entry for it. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a4d7b647867f..201d09a7c46b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1473,6 +1473,18 @@ static void xen_pvh_set_cr_flags(int cpu) * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */ write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM); + + if (!cpu) + return; + /* + * For BSP, PSE PGE are set in probe_page_size_mask(), for APs + * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init. + */ + if (cpu_has_pse) + set_in_cr4(X86_CR4_PSE); + + if (cpu_has_pge) + set_in_cr4(X86_CR4_PGE); } /* diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 8009acbe41e4..696c694986d0 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -899,6 +899,13 @@ int m2p_add_override(unsigned long mfn, struct page *page, "m2p_add_override: pfn %lx not mapped", pfn)) return -EINVAL; } + WARN_ON(PagePrivate(page)); + SetPagePrivate(page); + set_page_private(page, mfn); + page->index = pfn_to_mfn(pfn); + + if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) + return -ENOMEM; if (kmap_op != NULL) { if (!PageHighMem(page)) { @@ -937,16 +944,19 @@ int m2p_add_override(unsigned long mfn, struct page *page, } EXPORT_SYMBOL_GPL(m2p_add_override); int m2p_remove_override(struct page *page, - struct gnttab_map_grant_ref *kmap_op, - unsigned long mfn) + struct gnttab_map_grant_ref *kmap_op) { unsigned long flags; + unsigned long mfn; unsigned long pfn; unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; pfn = page_to_pfn(page); + mfn = get_phys_to_machine(pfn); + if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) + return -EINVAL; if (!PageHighMem(page)) { address = (unsigned long)__va(pfn << PAGE_SHIFT); @@ -960,7 +970,10 @@ int m2p_remove_override(struct page *page, spin_lock_irqsave(&m2p_override_lock, flags); list_del(&page->lru); spin_unlock_irqrestore(&m2p_override_lock, flags); + WARN_ON(!PagePrivate(page)); + ClearPagePrivate(page); + set_phys_to_machine(pfn, page->index); if (kmap_op != NULL) { if (!PageHighMem(page)) { struct multicall_space mcs; diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index 1f14ac403945..51824d1f23ea 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -46,7 +46,6 @@ #define NVME_Q_DEPTH 1024 #define SQ_SIZE(depth) (depth * sizeof(struct nvme_command)) #define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion)) -#define NVME_MINORS 64 #define ADMIN_TIMEOUT (60 * HZ) static int nvme_major; @@ -58,6 +57,17 @@ module_param(use_threaded_interrupts, int, 0); static DEFINE_SPINLOCK(dev_list_lock); static LIST_HEAD(dev_list); static struct task_struct *nvme_thread; +static struct workqueue_struct *nvme_workq; + +static void nvme_reset_failed_dev(struct work_struct *ws); + +struct async_cmd_info { + struct kthread_work work; + struct kthread_worker *worker; + u32 result; + int status; + void *ctx; +}; /* * An NVM Express queue. Each device has at least two (one for admin @@ -66,6 +76,7 @@ static struct task_struct *nvme_thread; struct nvme_queue { struct device *q_dmadev; struct nvme_dev *dev; + char irqname[24]; /* nvme4294967295-65535\0 */ spinlock_t q_lock; struct nvme_command *sq_cmds; volatile struct nvme_completion *cqes; @@ -80,9 +91,11 @@ struct nvme_queue { u16 sq_head; u16 sq_tail; u16 cq_head; + u16 qid; u8 cq_phase; u8 cqe_seen; u8 q_suspended; + struct async_cmd_info cmdinfo; unsigned long cmdid_data[]; }; @@ -97,6 +110,7 @@ static inline void _nvme_check_size(void) BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64); BUILD_BUG_ON(sizeof(struct nvme_features) != 64); BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64); BUILD_BUG_ON(sizeof(struct nvme_command) != 64); BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != 4096); BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096); @@ -111,6 +125,7 @@ struct nvme_cmd_info { nvme_completion_fn fn; void *ctx; unsigned long timeout; + int aborted; }; static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq) @@ -154,6 +169,7 @@ static int alloc_cmdid(struct nvme_queue *nvmeq, void *ctx, info[cmdid].fn = handler; info[cmdid].ctx = ctx; info[cmdid].timeout = jiffies + timeout; + info[cmdid].aborted = 0; return cmdid; } @@ -172,6 +188,7 @@ static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx, #define CMD_CTX_COMPLETED (0x310 + CMD_CTX_BASE) #define CMD_CTX_INVALID (0x314 + CMD_CTX_BASE) #define CMD_CTX_FLUSH (0x318 + CMD_CTX_BASE) +#define CMD_CTX_ABORT (0x31C + CMD_CTX_BASE) static void special_completion(struct nvme_dev *dev, void *ctx, struct nvme_completion *cqe) @@ -180,6 +197,10 @@ static void special_completion(struct nvme_dev *dev, void *ctx, return; if (ctx == CMD_CTX_FLUSH) return; + if (ctx == CMD_CTX_ABORT) { + ++dev->abort_limit; + return; + } if (ctx == CMD_CTX_COMPLETED) { dev_warn(&dev->pci_dev->dev, "completed id %d twice on queue %d\n", @@ -196,6 +217,15 @@ static void special_completion(struct nvme_dev *dev, void *ctx, dev_warn(&dev->pci_dev->dev, "Unknown special completion %p\n", ctx); } +static void async_completion(struct nvme_dev *dev, void *ctx, + struct nvme_completion *cqe) +{ + struct async_cmd_info *cmdinfo = ctx; + cmdinfo->result = le32_to_cpup(&cqe->result); + cmdinfo->status = le16_to_cpup(&cqe->status) >> 1; + queue_kthread_work(cmdinfo->worker, &cmdinfo->work); +} + /* * Called with local interrupts disabled and the q_lock held. May not sleep. */ @@ -693,7 +723,7 @@ static int nvme_process_cq(struct nvme_queue *nvmeq) if (head == nvmeq->cq_head && phase == nvmeq->cq_phase) return 0; - writel(head, nvmeq->q_db + (1 << nvmeq->dev->db_stride)); + writel(head, nvmeq->q_db + nvmeq->dev->db_stride); nvmeq->cq_head = head; nvmeq->cq_phase = phase; @@ -804,12 +834,34 @@ int nvme_submit_sync_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd, return cmdinfo.status; } +static int nvme_submit_async_cmd(struct nvme_queue *nvmeq, + struct nvme_command *cmd, + struct async_cmd_info *cmdinfo, unsigned timeout) +{ + int cmdid; + + cmdid = alloc_cmdid_killable(nvmeq, cmdinfo, async_completion, timeout); + if (cmdid < 0) + return cmdid; + cmdinfo->status = -EINTR; + cmd->common.command_id = cmdid; + nvme_submit_cmd(nvmeq, cmd); + return 0; +} + int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd, u32 *result) { return nvme_submit_sync_cmd(dev->queues[0], cmd, result, ADMIN_TIMEOUT); } +static int nvme_submit_admin_cmd_async(struct nvme_dev *dev, + struct nvme_command *cmd, struct async_cmd_info *cmdinfo) +{ + return nvme_submit_async_cmd(dev->queues[0], cmd, cmdinfo, + ADMIN_TIMEOUT); +} + static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id) { int status; @@ -920,6 +972,56 @@ int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11, } /** + * nvme_abort_cmd - Attempt aborting a command + * @cmdid: Command id of a timed out IO + * @queue: The queue with timed out IO + * + * Schedule controller reset if the command was already aborted once before and + * still hasn't been returned to the driver, or if this is the admin queue. + */ +static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq) +{ + int a_cmdid; + struct nvme_command cmd; + struct nvme_dev *dev = nvmeq->dev; + struct nvme_cmd_info *info = nvme_cmd_info(nvmeq); + + if (!nvmeq->qid || info[cmdid].aborted) { + if (work_busy(&dev->reset_work)) + return; + list_del_init(&dev->node); + dev_warn(&dev->pci_dev->dev, + "I/O %d QID %d timeout, reset controller\n", cmdid, + nvmeq->qid); + PREPARE_WORK(&dev->reset_work, nvme_reset_failed_dev); + queue_work(nvme_workq, &dev->reset_work); + return; + } + + if (!dev->abort_limit) + return; + + a_cmdid = alloc_cmdid(dev->queues[0], CMD_CTX_ABORT, special_completion, + ADMIN_TIMEOUT); + if (a_cmdid < 0) + return; + + memset(&cmd, 0, sizeof(cmd)); + cmd.abort.opcode = nvme_admin_abort_cmd; + cmd.abort.cid = cmdid; + cmd.abort.sqid = cpu_to_le16(nvmeq->qid); + cmd.abort.command_id = a_cmdid; + + --dev->abort_limit; + info[cmdid].aborted = 1; + info[cmdid].timeout = jiffies + ADMIN_TIMEOUT; + + dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", cmdid, + nvmeq->qid); + nvme_submit_cmd(dev->queues[0], &cmd); +} + +/** * nvme_cancel_ios - Cancel outstanding I/Os * @queue: The queue to cancel I/Os on * @timeout: True to only cancel I/Os which have timed out @@ -942,7 +1044,12 @@ static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout) continue; if (info[cmdid].ctx == CMD_CTX_CANCELLED) continue; - dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d\n", cmdid); + if (timeout && nvmeq->dev->initialized) { + nvme_abort_cmd(cmdid, nvmeq); + continue; + } + dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", cmdid, + nvmeq->qid); ctx = cancel_cmdid(nvmeq, cmdid, &fn); fn(nvmeq->dev, ctx, &cqe); } @@ -964,26 +1071,31 @@ static void nvme_free_queue(struct nvme_queue *nvmeq) kfree(nvmeq); } -static void nvme_free_queues(struct nvme_dev *dev) +static void nvme_free_queues(struct nvme_dev *dev, int lowest) { int i; - for (i = dev->queue_count - 1; i >= 0; i--) { + for (i = dev->queue_count - 1; i >= lowest; i--) { nvme_free_queue(dev->queues[i]); dev->queue_count--; dev->queues[i] = NULL; } } -static void nvme_disable_queue(struct nvme_dev *dev, int qid) +/** + * nvme_suspend_queue - put queue into suspended state + * @nvmeq - queue to suspend + * + * Returns 1 if already suspended, 0 otherwise. + */ +static int nvme_suspend_queue(struct nvme_queue *nvmeq) { - struct nvme_queue *nvmeq = dev->queues[qid]; - int vector = dev->entry[nvmeq->cq_vector].vector; + int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector; spin_lock_irq(&nvmeq->q_lock); if (nvmeq->q_suspended) { spin_unlock_irq(&nvmeq->q_lock); - return; + return 1; } nvmeq->q_suspended = 1; spin_unlock_irq(&nvmeq->q_lock); @@ -991,18 +1103,35 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid) irq_set_affinity_hint(vector, NULL); free_irq(vector, nvmeq); - /* Don't tell the adapter to delete the admin queue */ - if (qid) { - adapter_delete_sq(dev, qid); - adapter_delete_cq(dev, qid); - } + return 0; +} +static void nvme_clear_queue(struct nvme_queue *nvmeq) +{ spin_lock_irq(&nvmeq->q_lock); nvme_process_cq(nvmeq); nvme_cancel_ios(nvmeq, false); spin_unlock_irq(&nvmeq->q_lock); } +static void nvme_disable_queue(struct nvme_dev *dev, int qid) +{ + struct nvme_queue *nvmeq = dev->queues[qid]; + + if (!nvmeq) + return; + if (nvme_suspend_queue(nvmeq)) + return; + + /* Don't tell the adapter to delete the admin queue. + * Don't tell a removed adapter to delete IO queues. */ + if (qid && readl(&dev->bar->csts) != -1) { + adapter_delete_sq(dev, qid); + adapter_delete_cq(dev, qid); + } + nvme_clear_queue(nvmeq); +} + static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth, int vector) { @@ -1025,15 +1154,18 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid, nvmeq->q_dmadev = dmadev; nvmeq->dev = dev; + snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d", + dev->instance, qid); spin_lock_init(&nvmeq->q_lock); nvmeq->cq_head = 0; nvmeq->cq_phase = 1; init_waitqueue_head(&nvmeq->sq_full); init_waitqueue_entry(&nvmeq->sq_cong_wait, nvme_thread); bio_list_init(&nvmeq->sq_cong); - nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)]; + nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride]; nvmeq->q_depth = depth; nvmeq->cq_vector = vector; + nvmeq->qid = qid; nvmeq->q_suspended = 1; dev->queue_count++; @@ -1052,11 +1184,10 @@ static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq, { if (use_threaded_interrupts) return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector, - nvme_irq_check, nvme_irq, - IRQF_DISABLED | IRQF_SHARED, + nvme_irq_check, nvme_irq, IRQF_SHARED, name, nvmeq); return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq, - IRQF_DISABLED | IRQF_SHARED, name, nvmeq); + IRQF_SHARED, name, nvmeq); } static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid) @@ -1067,7 +1198,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid) nvmeq->sq_tail = 0; nvmeq->cq_head = 0; nvmeq->cq_phase = 1; - nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)]; + nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride]; memset(nvmeq->cmdid_data, 0, extra); memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth)); nvme_cancel_ios(nvmeq, false); @@ -1087,13 +1218,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) if (result < 0) goto release_cq; - result = queue_request_irq(dev, nvmeq, "nvme"); + result = queue_request_irq(dev, nvmeq, nvmeq->irqname); if (result < 0) goto release_sq; - spin_lock(&nvmeq->q_lock); + spin_lock_irq(&nvmeq->q_lock); nvme_init_queue(nvmeq, qid); - spin_unlock(&nvmeq->q_lock); + spin_unlock_irq(&nvmeq->q_lock); return result; @@ -1205,13 +1336,13 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) if (result) return result; - result = queue_request_irq(dev, nvmeq, "nvme admin"); + result = queue_request_irq(dev, nvmeq, nvmeq->irqname); if (result) return result; - spin_lock(&nvmeq->q_lock); + spin_lock_irq(&nvmeq->q_lock); nvme_init_queue(nvmeq, 0); - spin_unlock(&nvmeq->q_lock); + spin_unlock_irq(&nvmeq->q_lock); return result; } @@ -1487,10 +1618,47 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, } } +#ifdef CONFIG_COMPAT +static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + struct nvme_ns *ns = bdev->bd_disk->private_data; + + switch (cmd) { + case SG_IO: + return nvme_sg_io32(ns, arg); + } + return nvme_ioctl(bdev, mode, cmd, arg); +} +#else +#define nvme_compat_ioctl NULL +#endif + +static int nvme_open(struct block_device *bdev, fmode_t mode) +{ + struct nvme_ns *ns = bdev->bd_disk->private_data; + struct nvme_dev *dev = ns->dev; + + kref_get(&dev->kref); + return 0; +} + +static void nvme_free_dev(struct kref *kref); + +static void nvme_release(struct gendisk *disk, fmode_t mode) +{ + struct nvme_ns *ns = disk->private_data; + struct nvme_dev *dev = ns->dev; + + kref_put(&dev->kref, nvme_free_dev); +} + static const struct block_device_operations nvme_fops = { .owner = THIS_MODULE, .ioctl = nvme_ioctl, - .compat_ioctl = nvme_ioctl, + .compat_ioctl = nvme_compat_ioctl, + .open = nvme_open, + .release = nvme_release, }; static void nvme_resubmit_bios(struct nvme_queue *nvmeq) @@ -1514,13 +1682,25 @@ static void nvme_resubmit_bios(struct nvme_queue *nvmeq) static int nvme_kthread(void *data) { - struct nvme_dev *dev; + struct nvme_dev *dev, *next; while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); spin_lock(&dev_list_lock); - list_for_each_entry(dev, &dev_list, node) { + list_for_each_entry_safe(dev, next, &dev_list, node) { int i; + if (readl(&dev->bar->csts) & NVME_CSTS_CFS && + dev->initialized) { + if (work_busy(&dev->reset_work)) + continue; + list_del_init(&dev->node); + dev_warn(&dev->pci_dev->dev, + "Failed status, reset controller\n"); + PREPARE_WORK(&dev->reset_work, + nvme_reset_failed_dev); + queue_work(nvme_workq, &dev->reset_work); + continue; + } for (i = 0; i < dev->queue_count; i++) { struct nvme_queue *nvmeq = dev->queues[i]; if (!nvmeq) @@ -1541,33 +1721,6 @@ static int nvme_kthread(void *data) return 0; } -static DEFINE_IDA(nvme_index_ida); - -static int nvme_get_ns_idx(void) -{ - int index, error; - - do { - if (!ida_pre_get(&nvme_index_ida, GFP_KERNEL)) - return -1; - - spin_lock(&dev_list_lock); - error = ida_get_new(&nvme_index_ida, &index); - spin_unlock(&dev_list_lock); - } while (error == -EAGAIN); - - if (error) - index = -1; - return index; -} - -static void nvme_put_ns_idx(int index) -{ - spin_lock(&dev_list_lock); - ida_remove(&nvme_index_ida, index); - spin_unlock(&dev_list_lock); -} - static void nvme_config_discard(struct nvme_ns *ns) { u32 logical_block_size = queue_logical_block_size(ns->queue); @@ -1601,7 +1754,7 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid, ns->dev = dev; ns->queue->queuedata = ns; - disk = alloc_disk(NVME_MINORS); + disk = alloc_disk(0); if (!disk) goto out_free_queue; ns->ns_id = nsid; @@ -1614,12 +1767,12 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid, blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors); disk->major = nvme_major; - disk->minors = NVME_MINORS; - disk->first_minor = NVME_MINORS * nvme_get_ns_idx(); + disk->first_minor = 0; disk->fops = &nvme_fops; disk->private_data = ns; disk->queue = ns->queue; disk->driverfs_dev = &dev->pci_dev->dev; + disk->flags = GENHD_FL_EXT_DEVT; sprintf(disk->disk_name, "nvme%dn%d", dev->instance, nsid); set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9)); @@ -1635,15 +1788,6 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid, return NULL; } -static void nvme_ns_free(struct nvme_ns *ns) -{ - int index = ns->disk->first_minor / NVME_MINORS; - put_disk(ns->disk); - nvme_put_ns_idx(index); - blk_cleanup_queue(ns->queue); - kfree(ns); -} - static int set_queue_count(struct nvme_dev *dev, int count) { int status; @@ -1659,11 +1803,12 @@ static int set_queue_count(struct nvme_dev *dev, int count) static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues) { - return 4096 + ((nr_io_queues + 1) << (dev->db_stride + 3)); + return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride); } static int nvme_setup_io_queues(struct nvme_dev *dev) { + struct nvme_queue *adminq = dev->queues[0]; struct pci_dev *pdev = dev->pci_dev; int result, cpu, i, vecs, nr_io_queues, size, q_depth; @@ -1690,7 +1835,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) } /* Deregister the admin queue's interrupt */ - free_irq(dev->entry[0].vector, dev->queues[0]); + free_irq(dev->entry[0].vector, adminq); vecs = nr_io_queues; for (i = 0; i < vecs; i++) @@ -1728,9 +1873,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) */ nr_io_queues = vecs; - result = queue_request_irq(dev, dev->queues[0], "nvme admin"); + result = queue_request_irq(dev, adminq, adminq->irqname); if (result) { - dev->queues[0]->q_suspended = 1; + adminq->q_suspended = 1; goto free_queues; } @@ -1739,9 +1884,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) for (i = dev->queue_count - 1; i > nr_io_queues; i--) { struct nvme_queue *nvmeq = dev->queues[i]; - spin_lock(&nvmeq->q_lock); + spin_lock_irq(&nvmeq->q_lock); nvme_cancel_ios(nvmeq, false); - spin_unlock(&nvmeq->q_lock); + spin_unlock_irq(&nvmeq->q_lock); nvme_free_queue(nvmeq); dev->queue_count--; @@ -1782,7 +1927,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) return 0; free_queues: - nvme_free_queues(dev); + nvme_free_queues(dev, 1); return result; } @@ -1794,6 +1939,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) */ static int nvme_dev_add(struct nvme_dev *dev) { + struct pci_dev *pdev = dev->pci_dev; int res; unsigned nn, i; struct nvme_ns *ns; @@ -1803,8 +1949,7 @@ static int nvme_dev_add(struct nvme_dev *dev) dma_addr_t dma_addr; int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12; - mem = dma_alloc_coherent(&dev->pci_dev->dev, 8192, &dma_addr, - GFP_KERNEL); + mem = dma_alloc_coherent(&pdev->dev, 8192, &dma_addr, GFP_KERNEL); if (!mem) return -ENOMEM; @@ -1817,13 +1962,14 @@ static int nvme_dev_add(struct nvme_dev *dev) ctrl = mem; nn = le32_to_cpup(&ctrl->nn); dev->oncs = le16_to_cpup(&ctrl->oncs); + dev->abort_limit = ctrl->acl + 1; memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn)); memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn)); memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr)); if (ctrl->mdts) dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9); - if ((dev->pci_dev->vendor == PCI_VENDOR_ID_INTEL) && - (dev->pci_dev->device == 0x0953) && ctrl->vs[3]) + if ((pdev->vendor == PCI_VENDOR_ID_INTEL) && + (pdev->device == 0x0953) && ctrl->vs[3]) dev->stripe_size = 1 << (ctrl->vs[3] + shift); id_ns = mem; @@ -1871,16 +2017,21 @@ static int nvme_dev_map(struct nvme_dev *dev) dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) goto disable; - pci_set_drvdata(pdev, dev); dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); if (!dev->bar) goto disable; - - dev->db_stride = NVME_CAP_STRIDE(readq(&dev->bar->cap)); + if (readl(&dev->bar->csts) == -1) { + result = -ENODEV; + goto unmap; + } + dev->db_stride = 1 << NVME_CAP_STRIDE(readq(&dev->bar->cap)); dev->dbs = ((void __iomem *)dev->bar) + 4096; return 0; + unmap: + iounmap(dev->bar); + dev->bar = NULL; disable: pci_release_regions(pdev); disable_pci: @@ -1898,37 +2049,183 @@ static void nvme_dev_unmap(struct nvme_dev *dev) if (dev->bar) { iounmap(dev->bar); dev->bar = NULL; + pci_release_regions(dev->pci_dev); } - pci_release_regions(dev->pci_dev); if (pci_is_enabled(dev->pci_dev)) pci_disable_device(dev->pci_dev); } +struct nvme_delq_ctx { + struct task_struct *waiter; + struct kthread_worker *worker; + atomic_t refcount; +}; + +static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev) +{ + dq->waiter = current; + mb(); + + for (;;) { + set_current_state(TASK_KILLABLE); + if (!atomic_read(&dq->refcount)) + break; + if (!schedule_timeout(ADMIN_TIMEOUT) || + fatal_signal_pending(current)) { + set_current_state(TASK_RUNNING); + + nvme_disable_ctrl(dev, readq(&dev->bar->cap)); + nvme_disable_queue(dev, 0); + + send_sig(SIGKILL, dq->worker->task, 1); + flush_kthread_worker(dq->worker); + return; + } + } + set_current_state(TASK_RUNNING); +} + +static void nvme_put_dq(struct nvme_delq_ctx *dq) +{ + atomic_dec(&dq->refcount); + if (dq->waiter) + wake_up_process(dq->waiter); +} + +static struct nvme_delq_ctx *nvme_get_dq(struct nvme_delq_ctx *dq) +{ + atomic_inc(&dq->refcount); + return dq; +} + +static void nvme_del_queue_end(struct nvme_queue *nvmeq) +{ + struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx; + + nvme_clear_queue(nvmeq); + nvme_put_dq(dq); +} + +static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode, + kthread_work_func_t fn) +{ + struct nvme_command c; + + memset(&c, 0, sizeof(c)); + c.delete_queue.opcode = opcode; + c.delete_queue.qid = cpu_to_le16(nvmeq->qid); + + init_kthread_work(&nvmeq->cmdinfo.work, fn); + return nvme_submit_admin_cmd_async(nvmeq->dev, &c, &nvmeq->cmdinfo); +} + +static void nvme_del_cq_work_handler(struct kthread_work *work) +{ + struct nvme_queue *nvmeq = container_of(work, struct nvme_queue, + cmdinfo.work); + nvme_del_queue_end(nvmeq); +} + +static int nvme_delete_cq(struct nvme_queue *nvmeq) +{ + return adapter_async_del_queue(nvmeq, nvme_admin_delete_cq, + nvme_del_cq_work_handler); +} + +static void nvme_del_sq_work_handler(struct kthread_work *work) +{ + struct nvme_queue *nvmeq = container_of(work, struct nvme_queue, + cmdinfo.work); + int status = nvmeq->cmdinfo.status; + + if (!status) + status = nvme_delete_cq(nvmeq); + if (status) + nvme_del_queue_end(nvmeq); +} + +static int nvme_delete_sq(struct nvme_queue *nvmeq) +{ + return adapter_async_del_queue(nvmeq, nvme_admin_delete_sq, + nvme_del_sq_work_handler); +} + +static void nvme_del_queue_start(struct kthread_work *work) +{ + struct nvme_queue *nvmeq = container_of(work, struct nvme_queue, + cmdinfo.work); + allow_signal(SIGKILL); + if (nvme_delete_sq(nvmeq)) + nvme_del_queue_end(nvmeq); +} + +static void nvme_disable_io_queues(struct nvme_dev *dev) +{ + int i; + DEFINE_KTHREAD_WORKER_ONSTACK(worker); + struct nvme_delq_ctx dq; + struct task_struct *kworker_task = kthread_run(kthread_worker_fn, + &worker, "nvme%d", dev->instance); + + if (IS_ERR(kworker_task)) { + dev_err(&dev->pci_dev->dev, + "Failed to create queue del task\n"); + for (i = dev->queue_count - 1; i > 0; i--) + nvme_disable_queue(dev, i); + return; + } + + dq.waiter = NULL; + atomic_set(&dq.refcount, 0); + dq.worker = &worker; + for (i = dev->queue_count - 1; i > 0; i--) { + struct nvme_queue *nvmeq = dev->queues[i]; + + if (nvme_suspend_queue(nvmeq)) + continue; + nvmeq->cmdinfo.ctx = nvme_get_dq(&dq); + nvmeq->cmdinfo.worker = dq.worker; + init_kthread_work(&nvmeq->cmdinfo.work, nvme_del_queue_start); + queue_kthread_work(dq.worker, &nvmeq->cmdinfo.work); + } + nvme_wait_dq(&dq, dev); + kthread_stop(kworker_task); +} + static void nvme_dev_shutdown(struct nvme_dev *dev) { int i; - for (i = dev->queue_count - 1; i >= 0; i--) - nvme_disable_queue(dev, i); + dev->initialized = 0; spin_lock(&dev_list_lock); list_del_init(&dev->node); spin_unlock(&dev_list_lock); - if (dev->bar) + if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) { + for (i = dev->queue_count - 1; i >= 0; i--) { + struct nvme_queue *nvmeq = dev->queues[i]; + nvme_suspend_queue(nvmeq); + nvme_clear_queue(nvmeq); + } + } else { + nvme_disable_io_queues(dev); nvme_shutdown_ctrl(dev); + nvme_disable_queue(dev, 0); + } nvme_dev_unmap(dev); } static void nvme_dev_remove(struct nvme_dev *dev) { - struct nvme_ns *ns, *next; + struct nvme_ns *ns; - list_for_each_entry_safe(ns, next, &dev->namespaces, list) { - list_del(&ns->list); - del_gendisk(ns->disk); - nvme_ns_free(ns); + list_for_each_entry(ns, &dev->namespaces, list) { + if (ns->disk->flags & GENHD_FL_UP) + del_gendisk(ns->disk); + if (!blk_queue_dying(ns->queue)) + blk_cleanup_queue(ns->queue); } } @@ -1985,14 +2282,22 @@ static void nvme_release_instance(struct nvme_dev *dev) spin_unlock(&dev_list_lock); } +static void nvme_free_namespaces(struct nvme_dev *dev) +{ + struct nvme_ns *ns, *next; + + list_for_each_entry_safe(ns, next, &dev->namespaces, list) { + list_del(&ns->list); + put_disk(ns->disk); + kfree(ns); + } +} + static void nvme_free_dev(struct kref *kref) { struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref); - nvme_dev_remove(dev); - nvme_dev_shutdown(dev); - nvme_free_queues(dev); - nvme_release_instance(dev); - nvme_release_prp_pools(dev); + + nvme_free_namespaces(dev); kfree(dev->queues); kfree(dev->entry); kfree(dev); @@ -2056,6 +2361,7 @@ static int nvme_dev_start(struct nvme_dev *dev) return result; disable: + nvme_disable_queue(dev, 0); spin_lock(&dev_list_lock); list_del_init(&dev->node); spin_unlock(&dev_list_lock); @@ -2064,6 +2370,71 @@ static int nvme_dev_start(struct nvme_dev *dev) return result; } +static int nvme_remove_dead_ctrl(void *arg) +{ + struct nvme_dev *dev = (struct nvme_dev *)arg; + struct pci_dev *pdev = dev->pci_dev; + + if (pci_get_drvdata(pdev)) + pci_stop_and_remove_bus_device(pdev); + kref_put(&dev->kref, nvme_free_dev); + return 0; +} + +static void nvme_remove_disks(struct work_struct *ws) +{ + int i; + struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work); + + nvme_dev_remove(dev); + spin_lock(&dev_list_lock); + for (i = dev->queue_count - 1; i > 0; i--) { + BUG_ON(!dev->queues[i] || !dev->queues[i]->q_suspended); + nvme_free_queue(dev->queues[i]); + dev->queue_count--; + dev->queues[i] = NULL; + } + spin_unlock(&dev_list_lock); +} + +static int nvme_dev_resume(struct nvme_dev *dev) +{ + int ret; + + ret = nvme_dev_start(dev); + if (ret && ret != -EBUSY) + return ret; + if (ret == -EBUSY) { + spin_lock(&dev_list_lock); + PREPARE_WORK(&dev->reset_work, nvme_remove_disks); + queue_work(nvme_workq, &dev->reset_work); + spin_unlock(&dev_list_lock); + } + dev->initialized = 1; + return 0; +} + +static void nvme_dev_reset(struct nvme_dev *dev) +{ + nvme_dev_shutdown(dev); + if (nvme_dev_resume(dev)) { + dev_err(&dev->pci_dev->dev, "Device failed to resume\n"); + kref_get(&dev->kref); + if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d", + dev->instance))) { + dev_err(&dev->pci_dev->dev, + "Failed to start controller remove task\n"); + kref_put(&dev->kref, nvme_free_dev); + } + } +} + +static void nvme_reset_failed_dev(struct work_struct *ws) +{ + struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work); + nvme_dev_reset(dev); +} + static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int result = -ENOMEM; @@ -2082,8 +2453,9 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto free; INIT_LIST_HEAD(&dev->namespaces); + INIT_WORK(&dev->reset_work, nvme_reset_failed_dev); dev->pci_dev = pdev; - + pci_set_drvdata(pdev, dev); result = nvme_set_instance(dev); if (result) goto free; @@ -2099,6 +2471,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto release_pools; } + kref_init(&dev->kref); result = nvme_dev_add(dev); if (result) goto shutdown; @@ -2113,15 +2486,16 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (result) goto remove; - kref_init(&dev->kref); + dev->initialized = 1; return 0; remove: nvme_dev_remove(dev); + nvme_free_namespaces(dev); shutdown: nvme_dev_shutdown(dev); release_pools: - nvme_free_queues(dev); + nvme_free_queues(dev, 0); nvme_release_prp_pools(dev); release: nvme_release_instance(dev); @@ -2132,10 +2506,28 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) return result; } +static void nvme_shutdown(struct pci_dev *pdev) +{ + struct nvme_dev *dev = pci_get_drvdata(pdev); + nvme_dev_shutdown(dev); +} + static void nvme_remove(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); + + spin_lock(&dev_list_lock); + list_del_init(&dev->node); + spin_unlock(&dev_list_lock); + + pci_set_drvdata(pdev, NULL); + flush_work(&dev->reset_work); misc_deregister(&dev->miscdev); + nvme_dev_remove(dev); + nvme_dev_shutdown(dev); + nvme_free_queues(dev, 0); + nvme_release_instance(dev); + nvme_release_prp_pools(dev); kref_put(&dev->kref, nvme_free_dev); } @@ -2159,13 +2551,12 @@ static int nvme_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct nvme_dev *ndev = pci_get_drvdata(pdev); - int ret; - ret = nvme_dev_start(ndev); - /* XXX: should remove gendisks if resume fails */ - if (ret) - nvme_free_queues(ndev); - return ret; + if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) { + PREPARE_WORK(&ndev->reset_work, nvme_reset_failed_dev); + queue_work(nvme_workq, &ndev->reset_work); + } + return 0; } static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume); @@ -2192,6 +2583,7 @@ static struct pci_driver nvme_driver = { .id_table = nvme_id_table, .probe = nvme_probe, .remove = nvme_remove, + .shutdown = nvme_shutdown, .driver = { .pm = &nvme_dev_pm_ops, }, @@ -2206,9 +2598,14 @@ static int __init nvme_init(void) if (IS_ERR(nvme_thread)) return PTR_ERR(nvme_thread); + result = -ENOMEM; + nvme_workq = create_singlethread_workqueue("nvme"); + if (!nvme_workq) + goto kill_kthread; + result = register_blkdev(nvme_major, "nvme"); if (result < 0) - goto kill_kthread; + goto kill_workq; else if (result > 0) nvme_major = result; @@ -2219,6 +2616,8 @@ static int __init nvme_init(void) unregister_blkdev: unregister_blkdev(nvme_major, "nvme"); + kill_workq: + destroy_workqueue(nvme_workq); kill_kthread: kthread_stop(nvme_thread); return result; @@ -2228,6 +2627,7 @@ static void __exit nvme_exit(void) { pci_unregister_driver(&nvme_driver); unregister_blkdev(nvme_major, "nvme"); + destroy_workqueue(nvme_workq); kthread_stop(nvme_thread); } diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c index 4a4ff4eb8e23..4a0ceb64e269 100644 --- a/drivers/block/nvme-scsi.c +++ b/drivers/block/nvme-scsi.c @@ -25,6 +25,7 @@ #include <linux/bio.h> #include <linux/bitops.h> #include <linux/blkdev.h> +#include <linux/compat.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/fs.h> @@ -3038,6 +3039,152 @@ int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr) return retcode; } +#ifdef CONFIG_COMPAT +typedef struct sg_io_hdr32 { + compat_int_t interface_id; /* [i] 'S' for SCSI generic (required) */ + compat_int_t dxfer_direction; /* [i] data transfer direction */ + unsigned char cmd_len; /* [i] SCSI command length ( <= 16 bytes) */ + unsigned char mx_sb_len; /* [i] max length to write to sbp */ + unsigned short iovec_count; /* [i] 0 implies no scatter gather */ + compat_uint_t dxfer_len; /* [i] byte count of data transfer */ + compat_uint_t dxferp; /* [i], [*io] points to data transfer memory + or scatter gather list */ + compat_uptr_t cmdp; /* [i], [*i] points to command to perform */ + compat_uptr_t sbp; /* [i], [*o] points to sense_buffer memory */ + compat_uint_t timeout; /* [i] MAX_UINT->no timeout (unit: millisec) */ + compat_uint_t flags; /* [i] 0 -> default, see SG_FLAG... */ + compat_int_t pack_id; /* [i->o] unused internally (normally) */ + compat_uptr_t usr_ptr; /* [i->o] unused internally */ + unsigned char status; /* [o] scsi status */ + unsigned char masked_status; /* [o] shifted, masked scsi status */ + unsigned char msg_status; /* [o] messaging level data (optional) */ + unsigned char sb_len_wr; /* [o] byte count actually written to sbp */ + unsigned short host_status; /* [o] errors from host adapter */ + unsigned short driver_status; /* [o] errors from software driver */ + compat_int_t resid; /* [o] dxfer_len - actual_transferred */ + compat_uint_t duration; /* [o] time taken by cmd (unit: millisec) */ + compat_uint_t info; /* [o] auxiliary information */ +} sg_io_hdr32_t; /* 64 bytes long (on sparc32) */ + +typedef struct sg_iovec32 { + compat_uint_t iov_base; + compat_uint_t iov_len; +} sg_iovec32_t; + +static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iovec_count) +{ + sg_iovec_t __user *iov = (sg_iovec_t __user *) (sgio + 1); + sg_iovec32_t __user *iov32 = dxferp; + int i; + + for (i = 0; i < iovec_count; i++) { + u32 base, len; + + if (get_user(base, &iov32[i].iov_base) || + get_user(len, &iov32[i].iov_len) || + put_user(compat_ptr(base), &iov[i].iov_base) || + put_user(len, &iov[i].iov_len)) + return -EFAULT; + } + + if (put_user(iov, &sgio->dxferp)) + return -EFAULT; + return 0; +} + +int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg) +{ + sg_io_hdr32_t __user *sgio32 = (sg_io_hdr32_t __user *)arg; + sg_io_hdr_t __user *sgio; + u16 iovec_count; + u32 data; + void __user *dxferp; + int err; + int interface_id; + + if (get_user(interface_id, &sgio32->interface_id)) + return -EFAULT; + if (interface_id != 'S') + return -EINVAL; + + if (get_user(iovec_count, &sgio32->iovec_count)) + return -EFAULT; + + { + void __user *top = compat_alloc_user_space(0); + void __user *new = compat_alloc_user_space(sizeof(sg_io_hdr_t) + + (iovec_count * sizeof(sg_iovec_t))); + if (new > top) + return -EINVAL; + + sgio = new; + } + + /* Ok, now construct. */ + if (copy_in_user(&sgio->interface_id, &sgio32->interface_id, + (2 * sizeof(int)) + + (2 * sizeof(unsigned char)) + + (1 * sizeof(unsigned short)) + + (1 * sizeof(unsigned int)))) + return -EFAULT; + + if (get_user(data, &sgio32->dxferp)) + return -EFAULT; + dxferp = compat_ptr(data); + if (iovec_count) { + if (sg_build_iovec(sgio, dxferp, iovec_count)) + return -EFAULT; + } else { + if (put_user(dxferp, &sgio->dxferp)) + return -EFAULT; + } + + { + unsigned char __user *cmdp; + unsigned char __user *sbp; + + if (get_user(data, &sgio32->cmdp)) + return -EFAULT; + cmdp = compat_ptr(data); + + if (get_user(data, &sgio32->sbp)) + return -EFAULT; + sbp = compat_ptr(data); + + if (put_user(cmdp, &sgio->cmdp) || + put_user(sbp, &sgio->sbp)) + return -EFAULT; + } + + if (copy_in_user(&sgio->timeout, &sgio32->timeout, + 3 * sizeof(int))) + return -EFAULT; + + if (get_user(data, &sgio32->usr_ptr)) + return -EFAULT; + if (put_user(compat_ptr(data), &sgio->usr_ptr)) + return -EFAULT; + + err = nvme_sg_io(ns, sgio); + if (err >= 0) { + void __user *datap; + + if (copy_in_user(&sgio32->pack_id, &sgio->pack_id, + sizeof(int)) || + get_user(datap, &sgio->usr_ptr) || + put_user((u32)(unsigned long)datap, + &sgio32->usr_ptr) || + copy_in_user(&sgio32->status, &sgio->status, + (4 * sizeof(unsigned char)) + + (2 * sizeof(unsigned short)) + + (3 * sizeof(int)))) + err = -EFAULT; + } + + return err; +} +#endif + int nvme_sg_get_version_num(int __user *ip) { return put_user(sg_version_num, ip); diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index da18046d0e07..4b97b86da926 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -285,7 +285,8 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root, if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST || !rb_next(&persistent_gnt->node)) { - ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap); + ret = gnttab_unmap_refs(unmap, NULL, pages, + segs_to_unmap); BUG_ON(ret); put_free_pages(blkif, pages, segs_to_unmap); segs_to_unmap = 0; @@ -320,7 +321,8 @@ static void unmap_purged_grants(struct work_struct *work) pages[segs_to_unmap] = persistent_gnt->page; if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) { - ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap); + ret = gnttab_unmap_refs(unmap, NULL, pages, + segs_to_unmap); BUG_ON(ret); put_free_pages(blkif, pages, segs_to_unmap); segs_to_unmap = 0; @@ -328,7 +330,7 @@ static void unmap_purged_grants(struct work_struct *work) kfree(persistent_gnt); } if (segs_to_unmap > 0) { - ret = gnttab_unmap_refs(unmap, pages, segs_to_unmap); + ret = gnttab_unmap_refs(unmap, NULL, pages, segs_to_unmap); BUG_ON(ret); put_free_pages(blkif, pages, segs_to_unmap); } @@ -668,14 +670,15 @@ static void xen_blkbk_unmap(struct xen_blkif *blkif, GNTMAP_host_map, pages[i]->handle); pages[i]->handle = BLKBACK_INVALID_HANDLE; if (++invcount == BLKIF_MAX_SEGMENTS_PER_REQUEST) { - ret = gnttab_unmap_refs(unmap, unmap_pages, invcount); + ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, + invcount); BUG_ON(ret); put_free_pages(blkif, unmap_pages, invcount); invcount = 0; } } if (invcount) { - ret = gnttab_unmap_refs(unmap, unmap_pages, invcount); + ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount); BUG_ON(ret); put_free_pages(blkif, unmap_pages, invcount); } @@ -737,7 +740,7 @@ again: } if (segs_to_map) { - ret = gnttab_map_refs(map, pages_to_gnt, segs_to_map); + ret = gnttab_map_refs(map, NULL, pages_to_gnt, segs_to_map); BUG_ON(ret); } diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 86b484cb3ec2..5194afb39e78 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_SIRF_IRQ) += irq-sirfsoc.o obj-$(CONFIG_RENESAS_INTC_IRQPIN) += irq-renesas-intc-irqpin.o obj-$(CONFIG_RENESAS_IRQC) += irq-renesas-irqc.o obj-$(CONFIG_VERSATILE_FPGA_IRQ) += irq-versatile-fpga.o +obj-$(CONFIG_ARCH_NSPIRE) += irq-zevio.o obj-$(CONFIG_ARCH_VT8500) += irq-vt8500.o obj-$(CONFIG_TB10X_IRQC) += irq-tb10x.o obj-$(CONFIG_XTENSA) += irq-xtensa-pic.o diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 9300bc32784e..540956465ed2 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -381,7 +381,7 @@ armada_370_xp_handle_irq(struct pt_regs *regs) ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS) & PCI_MSI_DOORBELL_MASK; - writel(~PCI_MSI_DOORBELL_MASK, per_cpu_int_base + + writel(~msimask, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS); for (msinr = PCI_MSI_DOORBELL_START; @@ -407,7 +407,7 @@ armada_370_xp_handle_irq(struct pt_regs *regs) ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS) & IPI_DOORBELL_MASK; - writel(~IPI_DOORBELL_MASK, per_cpu_int_base + + writel(~ipimask, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS); /* Handle all pending doorbells */ diff --git a/drivers/irqchip/irq-zevio.c b/drivers/irqchip/irq-zevio.c new file mode 100644 index 000000000000..8ed04c4a43ee --- /dev/null +++ b/drivers/irqchip/irq-zevio.c @@ -0,0 +1,127 @@ +/* + * linux/drivers/irqchip/irq-zevio.c + * + * Copyright (C) 2013 Daniel Tang <[email protected]> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2, as + * published by the Free Software Foundation. + * + */ + +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> + +#include <asm/mach/irq.h> +#include <asm/exception.h> + +#include "irqchip.h" + +#define IO_STATUS 0x000 +#define IO_RAW_STATUS 0x004 +#define IO_ENABLE 0x008 +#define IO_DISABLE 0x00C +#define IO_CURRENT 0x020 +#define IO_RESET 0x028 +#define IO_MAX_PRIOTY 0x02C + +#define IO_IRQ_BASE 0x000 +#define IO_FIQ_BASE 0x100 + +#define IO_INVERT_SEL 0x200 +#define IO_STICKY_SEL 0x204 +#define IO_PRIORITY_SEL 0x300 + +#define MAX_INTRS 32 +#define FIQ_START MAX_INTRS + +static struct irq_domain *zevio_irq_domain; +static void __iomem *zevio_irq_io; + +static void zevio_irq_ack(struct irq_data *irqd) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(irqd); + struct irq_chip_regs *regs = + &container_of(irqd->chip, struct irq_chip_type, chip)->regs; + + readl(gc->reg_base + regs->ack); +} + +static asmlinkage void __exception_irq_entry zevio_handle_irq(struct pt_regs *regs) +{ + int irqnr; + + while (readl(zevio_irq_io + IO_STATUS)) { + irqnr = readl(zevio_irq_io + IO_CURRENT); + irqnr = irq_find_mapping(zevio_irq_domain, irqnr); + handle_IRQ(irqnr, regs); + }; +} + +static void __init zevio_init_irq_base(void __iomem *base) +{ + /* Disable all interrupts */ + writel(~0, base + IO_DISABLE); + + /* Accept interrupts of all priorities */ + writel(0xF, base + IO_MAX_PRIOTY); + + /* Reset existing interrupts */ + readl(base + IO_RESET); +} + +static int __init zevio_of_init(struct device_node *node, + struct device_node *parent) +{ + unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; + struct irq_chip_generic *gc; + int ret; + + if (WARN_ON(zevio_irq_io || zevio_irq_domain)) + return -EBUSY; + + zevio_irq_io = of_iomap(node, 0); + BUG_ON(!zevio_irq_io); + + /* Do not invert interrupt status bits */ + writel(~0, zevio_irq_io + IO_INVERT_SEL); + + /* Disable sticky interrupts */ + writel(0, zevio_irq_io + IO_STICKY_SEL); + + /* We don't use IRQ priorities. Set each IRQ to highest priority. */ + memset_io(zevio_irq_io + IO_PRIORITY_SEL, 0, MAX_INTRS * sizeof(u32)); + + /* Init IRQ and FIQ */ + zevio_init_irq_base(zevio_irq_io + IO_IRQ_BASE); + zevio_init_irq_base(zevio_irq_io + IO_FIQ_BASE); + + zevio_irq_domain = irq_domain_add_linear(node, MAX_INTRS, + &irq_generic_chip_ops, NULL); + BUG_ON(!zevio_irq_domain); + + ret = irq_alloc_domain_generic_chips(zevio_irq_domain, MAX_INTRS, 1, + "zevio_intc", handle_level_irq, + clr, 0, IRQ_GC_INIT_MASK_CACHE); + BUG_ON(ret); + + gc = irq_get_domain_generic_chip(zevio_irq_domain, 0); + gc->reg_base = zevio_irq_io; + gc->chip_types[0].chip.irq_ack = zevio_irq_ack; + gc->chip_types[0].chip.irq_mask = irq_gc_mask_disable_reg; + gc->chip_types[0].chip.irq_unmask = irq_gc_unmask_enable_reg; + gc->chip_types[0].regs.mask = IO_IRQ_BASE + IO_ENABLE; + gc->chip_types[0].regs.enable = IO_IRQ_BASE + IO_ENABLE; + gc->chip_types[0].regs.disable = IO_IRQ_BASE + IO_DISABLE; + gc->chip_types[0].regs.ack = IO_IRQ_BASE + IO_RESET; + + set_handle_irq(zevio_handle_irq); + + pr_info("TI-NSPIRE classic IRQ controller\n"); + return 0; +} + +IRQCHIP_DECLARE(zevio_irq, "lsi,zevio-intc", zevio_of_init); diff --git a/drivers/regulator/ab3100.c b/drivers/regulator/ab3100.c index 77b46d0b37a6..e10febe9ec34 100644 --- a/drivers/regulator/ab3100.c +++ b/drivers/regulator/ab3100.c @@ -498,7 +498,7 @@ static int ab3100_regulator_register(struct platform_device *pdev, struct ab3100_platform_data *plfdata, struct regulator_init_data *init_data, struct device_node *np, - int id) + unsigned long id) { struct regulator_desc *desc; struct ab3100_regulator *reg; @@ -646,7 +646,7 @@ ab3100_regulator_of_probe(struct platform_device *pdev, struct device_node *np) err = ab3100_regulator_register( pdev, NULL, ab3100_regulator_matches[i].init_data, ab3100_regulator_matches[i].of_node, - (int) ab3100_regulator_matches[i].driver_data); + (unsigned long)ab3100_regulator_matches[i].driver_data); if (err) { ab3100_regulators_remove(pdev); return err; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index b38a6b669e8c..16a309e5c024 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1272,6 +1272,8 @@ static struct regulator_dev *regulator_dev_lookup(struct device *dev, if (r->dev.parent && node == r->dev.of_node) return r; + *ret = -EPROBE_DEFER; + return NULL; } else { /* * If we couldn't even get the node then it's @@ -1312,7 +1314,7 @@ static struct regulator *_regulator_get(struct device *dev, const char *id, struct regulator_dev *rdev; struct regulator *regulator = ERR_PTR(-EPROBE_DEFER); const char *devname = NULL; - int ret = -EPROBE_DEFER; + int ret; if (id == NULL) { pr_err("get() with no identifier\n"); @@ -1322,6 +1324,11 @@ static struct regulator *_regulator_get(struct device *dev, const char *id, if (dev) devname = dev_name(dev); + if (have_full_constraints()) + ret = -ENODEV; + else + ret = -EPROBE_DEFER; + mutex_lock(®ulator_list_mutex); rdev = regulator_dev_lookup(dev, id, &ret); diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index d9e557990577..cd0b9e35a56d 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -441,6 +441,7 @@ common_reg: for (i = 0; i < S2MPS11_REGULATOR_MAX; i++) { if (!reg_np) { config.init_data = pdata->regulators[i].initdata; + config.of_node = pdata->regulators[i].reg_node; } else { config.init_data = rdata[i].init_data; config.of_node = rdata[i].of_node; diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 34a2704fbc88..073b4a19a8b0 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -284,10 +284,8 @@ static int map_grant_pages(struct grant_map *map) } pr_debug("map %d+%d\n", map->index, map->count); - err = gnttab_map_refs_userspace(map->map_ops, - use_ptemod ? map->kmap_ops : NULL, - map->pages, - map->count); + err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL, + map->pages, map->count); if (err) return err; @@ -317,10 +315,9 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages) } } - err = gnttab_unmap_refs_userspace(map->unmap_ops + offset, - use_ptemod ? map->kmap_ops + offset : NULL, - map->pages + offset, - pages); + err = gnttab_unmap_refs(map->unmap_ops + offset, + use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset, + pages); if (err) return err; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 8ee13e2e45e2..b84e3ab839aa 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -928,17 +928,15 @@ void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count) } EXPORT_SYMBOL_GPL(gnttab_batch_copy); -int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, +int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count, - bool m2p_override) + struct page **pages, unsigned int count) { int i, ret; bool lazy = false; pte_t *pte; - unsigned long mfn, pfn; + unsigned long mfn; - BUG_ON(kmap_ops && !m2p_override); ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count); if (ret) return ret; @@ -957,12 +955,10 @@ int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT, map_ops[i].dev_bus_addr >> PAGE_SHIFT); } - return 0; + return ret; } - if (m2p_override && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { + if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { arch_enter_lazy_mmu_mode(); lazy = true; } @@ -979,20 +975,8 @@ int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, } else { mfn = PFN_DOWN(map_ops[i].dev_bus_addr); } - pfn = page_to_pfn(pages[i]); - - WARN_ON(PagePrivate(pages[i])); - SetPagePrivate(pages[i]); - set_page_private(pages[i], mfn); - - pages[i]->index = pfn_to_mfn(pfn); - if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { - ret = -ENOMEM; - goto out; - } - if (m2p_override) - ret = m2p_add_override(mfn, pages[i], kmap_ops ? - &kmap_ops[i] : NULL); + ret = m2p_add_override(mfn, pages[i], kmap_ops ? + &kmap_ops[i] : NULL); if (ret) goto out; } @@ -1003,32 +987,15 @@ int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, return ret; } - -int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_map_refs(map_ops, NULL, pages, count, false); -} EXPORT_SYMBOL_GPL(gnttab_map_refs); -int gnttab_map_refs_userspace(struct gnttab_map_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_map_refs(map_ops, kmap_ops, pages, count, true); -} -EXPORT_SYMBOL_GPL(gnttab_map_refs_userspace); - -int __gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, +int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count, - bool m2p_override) + struct page **pages, unsigned int count) { int i, ret; bool lazy = false; - unsigned long pfn, mfn; - BUG_ON(kmap_ops && !m2p_override); ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count); if (ret) return ret; @@ -1039,33 +1006,17 @@ int __gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT, INVALID_P2M_ENTRY); } - return 0; + return ret; } - if (m2p_override && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { + if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { arch_enter_lazy_mmu_mode(); lazy = true; } for (i = 0; i < count; i++) { - pfn = page_to_pfn(pages[i]); - mfn = get_phys_to_machine(pfn); - if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) { - ret = -EINVAL; - goto out; - } - - set_page_private(pages[i], INVALID_P2M_ENTRY); - WARN_ON(!PagePrivate(pages[i])); - ClearPagePrivate(pages[i]); - set_phys_to_machine(pfn, pages[i]->index); - if (m2p_override) - ret = m2p_remove_override(pages[i], - kmap_ops ? - &kmap_ops[i] : NULL, - mfn); + ret = m2p_remove_override(pages[i], kmap_ops ? + &kmap_ops[i] : NULL); if (ret) goto out; } @@ -1076,22 +1027,8 @@ int __gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, return ret; } - -int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *map_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_unmap_refs(map_ops, NULL, pages, count, false); -} EXPORT_SYMBOL_GPL(gnttab_unmap_refs); -int gnttab_unmap_refs_userspace(struct gnttab_unmap_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_unmap_refs(map_ops, kmap_ops, pages, count, true); -} -EXPORT_SYMBOL_GPL(gnttab_unmap_refs_userspace); - static unsigned nr_status_frames(unsigned nr_grant_frames) { BUG_ON(grefs_per_grant_frame == 0); diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 49a62b4dda3b..0e8388e72d8d 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -92,11 +92,11 @@ #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/mutex.h> -#include <linux/crc32c.h> #include <linux/genhd.h> #include <linux/blkdev.h> #include "ctree.h" #include "disk-io.h" +#include "hash.h" #include "transaction.h" #include "extent_io.h" #include "volumes.h" @@ -1823,7 +1823,7 @@ static int btrfsic_test_for_metadata(struct btrfsic_state *state, size_t sublen = i ? PAGE_CACHE_SIZE : (PAGE_CACHE_SIZE - BTRFS_CSUM_SIZE); - crc = crc32c(crc, data, sublen); + crc = btrfs_crc32c(crc, data, sublen); } btrfs_csum_final(crc, csum); if (memcmp(csum, h->csum, state->csum_size)) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0e69295d0031..5215f04260b2 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -26,7 +26,6 @@ #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/freezer.h> -#include <linux/crc32c.h> #include <linux/slab.h> #include <linux/migrate.h> #include <linux/ratelimit.h> @@ -35,6 +34,7 @@ #include <asm/unaligned.h> #include "ctree.h" #include "disk-io.h" +#include "hash.h" #include "transaction.h" #include "btrfs_inode.h" #include "volumes.h" @@ -244,7 +244,7 @@ out: u32 btrfs_csum_data(char *data, u32 seed, size_t len) { - return crc32c(seed, data, len); + return btrfs_crc32c(seed, data, len); } void btrfs_csum_final(u32 crc, char *result) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5c4ab9c18940..184e9cb39647 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2629,7 +2629,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) EXTENT_DEFRAG, 1, cached_state); if (ret) { u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item); - if (last_snapshot >= BTRFS_I(inode)->generation) + if (0 && last_snapshot >= BTRFS_I(inode)->generation) /* the inode is shared */ new = record_old_file_extents(inode, ordered_extent); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 730dce395858..cf9107a64204 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -24,12 +24,12 @@ #include <linux/xattr.h> #include <linux/posix_acl_xattr.h> #include <linux/radix-tree.h> -#include <linux/crc32c.h> #include <linux/vmalloc.h> #include <linux/string.h> #include "send.h" #include "backref.h" +#include "hash.h" #include "locking.h" #include "disk-io.h" #include "btrfs_inode.h" @@ -620,7 +620,7 @@ static int send_cmd(struct send_ctx *sctx) hdr->len = cpu_to_le32(sctx->send_size - sizeof(*hdr)); hdr->crc = 0; - crc = crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size); + crc = btrfs_crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size); hdr->crc = cpu_to_le32(crc); ret = write_buf(sctx->send_filp, sctx->send_buf, sctx->send_size, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c02f63356895..97cc24198554 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1996,7 +1996,7 @@ static void __exit exit_btrfs_fs(void) btrfs_hash_exit(); } -module_init(init_btrfs_fs) +late_initcall(init_btrfs_fs); module_exit(exit_btrfs_fs) MODULE_LICENSE("GPL"); diff --git a/fs/exec.c b/fs/exec.c index e1529b4c79b1..3d78fccdd723 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -748,11 +748,10 @@ EXPORT_SYMBOL(setup_arg_pages); #endif /* CONFIG_MMU */ -struct file *open_exec(const char *name) +static struct file *do_open_exec(struct filename *name) { struct file *file; int err; - struct filename tmp = { .name = name }; static const struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC | MAY_OPEN, @@ -760,7 +759,7 @@ struct file *open_exec(const char *name) .lookup_flags = LOOKUP_FOLLOW, }; - file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags); + file = do_filp_open(AT_FDCWD, name, &open_exec_flags); if (IS_ERR(file)) goto out; @@ -784,6 +783,12 @@ exit: fput(file); return ERR_PTR(err); } + +struct file *open_exec(const char *name) +{ + struct filename tmp = { .name = name }; + return do_open_exec(&tmp); +} EXPORT_SYMBOL(open_exec); int kernel_read(struct file *file, loff_t offset, @@ -1162,7 +1167,7 @@ int prepare_bprm_creds(struct linux_binprm *bprm) return -ENOMEM; } -void free_bprm(struct linux_binprm *bprm) +static void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { @@ -1432,7 +1437,7 @@ static int exec_binprm(struct linux_binprm *bprm) /* * sys_execve() executes a new program. */ -static int do_execve_common(const char *filename, +static int do_execve_common(struct filename *filename, struct user_arg_ptr argv, struct user_arg_ptr envp) { @@ -1441,6 +1446,9 @@ static int do_execve_common(const char *filename, struct files_struct *displaced; int retval; + if (IS_ERR(filename)) + return PTR_ERR(filename); + /* * We move the actual failure in case of RLIMIT_NPROC excess from * set*uid() to execve() because too many poorly written programs @@ -1473,7 +1481,7 @@ static int do_execve_common(const char *filename, check_unsafe_exec(bprm); current->in_execve = 1; - file = open_exec(filename); + file = do_open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) goto out_unmark; @@ -1481,8 +1489,7 @@ static int do_execve_common(const char *filename, sched_exec(); bprm->file = file; - bprm->filename = filename; - bprm->interp = filename; + bprm->filename = bprm->interp = filename->name; retval = bprm_mm_init(bprm); if (retval) @@ -1523,6 +1530,7 @@ static int do_execve_common(const char *filename, acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); + putname(filename); if (displaced) put_files_struct(displaced); return retval; @@ -1544,10 +1552,11 @@ out_files: if (displaced) reset_files_struct(displaced); out_ret: + putname(filename); return retval; } -int do_execve(const char *filename, +int do_execve(struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp) { @@ -1557,7 +1566,7 @@ int do_execve(const char *filename, } #ifdef CONFIG_COMPAT -static int compat_do_execve(const char *filename, +static int compat_do_execve(struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp) { @@ -1607,25 +1616,13 @@ SYSCALL_DEFINE3(execve, const char __user *const __user *, argv, const char __user *const __user *, envp) { - struct filename *path = getname(filename); - int error = PTR_ERR(path); - if (!IS_ERR(path)) { - error = do_execve(path->name, argv, envp); - putname(path); - } - return error; + return do_execve(getname(filename), argv, envp); } #ifdef CONFIG_COMPAT asmlinkage long compat_sys_execve(const char __user * filename, const compat_uptr_t __user * argv, const compat_uptr_t __user * envp) { - struct filename *path = getname(filename); - int error = PTR_ERR(path); - if (!IS_ERR(path)) { - error = compat_do_execve(path->name, argv, envp); - putname(path); - } - return error; + return compat_do_execve(getname(filename), argv, envp); } #endif diff --git a/fs/namei.c b/fs/namei.c index d580df2e6804..385f7817bfcc 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -196,6 +196,7 @@ recopy: goto error; result->uptr = filename; + result->aname = NULL; audit_getname(result); return result; @@ -210,6 +211,35 @@ getname(const char __user * filename) return getname_flags(filename, 0, NULL); } +/* + * The "getname_kernel()" interface doesn't do pathnames longer + * than EMBEDDED_NAME_MAX. Deal with it - you're a kernel user. + */ +struct filename * +getname_kernel(const char * filename) +{ + struct filename *result; + char *kname; + int len; + + len = strlen(filename); + if (len >= EMBEDDED_NAME_MAX) + return ERR_PTR(-ENAMETOOLONG); + + result = __getname(); + if (unlikely(!result)) + return ERR_PTR(-ENOMEM); + + kname = (char *)result + sizeof(*result); + result->name = kname; + result->uptr = NULL; + result->aname = NULL; + result->separate = false; + + strlcpy(kname, filename, EMBEDDED_NAME_MAX); + return result; +} + #ifdef CONFIG_AUDITSYSCALL void putname(struct filename *name) { diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 9a5ca03fa539..871d6eda8dba 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -80,7 +80,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) } if (res.acl_access != NULL) { - if (posix_acl_equiv_mode(res.acl_access, NULL) || + if ((posix_acl_equiv_mode(res.acl_access, NULL) == 0) || res.acl_access->a_count == 0) { posix_acl_release(res.acl_access); res.acl_access = NULL; @@ -113,7 +113,7 @@ getout: return ERR_PTR(status); } -int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, +static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, struct posix_acl *dfacl) { struct nfs_server *server = NFS_SERVER(inode); @@ -198,6 +198,15 @@ out: return status; } +int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl) +{ + int ret; + ret = __nfs3_proc_setacls(inode, acl, dfacl); + return (ret == -EOPNOTSUPP) ? 0 : ret; + +} + int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type) { struct posix_acl *alloc = NULL, *dfacl = NULL; @@ -225,7 +234,7 @@ int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (IS_ERR(alloc)) goto fail; } - status = nfs3_proc_setacls(inode, acl, dfacl); + status = __nfs3_proc_setacls(inode, acl, dfacl); posix_acl_release(alloc); return status; @@ -233,25 +242,6 @@ fail: return PTR_ERR(alloc); } -int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - umode_t mode) -{ - struct posix_acl *default_acl, *acl; - int error; - - error = posix_acl_create(dir, &mode, &default_acl, &acl); - if (error) - return (error == -EOPNOTSUPP) ? 0 : error; - - error = nfs3_proc_setacls(inode, acl, default_acl); - - if (acl) - posix_acl_release(acl); - if (default_acl) - posix_acl_release(default_acl); - return error; -} - const struct xattr_handler *nfs3_xattr_handlers[] = { &posix_acl_access_xattr_handler, &posix_acl_default_xattr_handler, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index dbb3e1f30c68..860ad26a5590 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -170,7 +170,7 @@ void nfs41_shutdown_client(struct nfs_client *clp) void nfs40_shutdown_client(struct nfs_client *clp) { if (clp->cl_slot_tbl) { - nfs4_release_slot_table(clp->cl_slot_tbl); + nfs4_shutdown_slot_table(clp->cl_slot_tbl); kfree(clp->cl_slot_tbl); } } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 42da6af77587..2da6a698b8f7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1620,15 +1620,15 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata) { struct nfs4_opendata *data = calldata; - nfs40_setup_sequence(data->o_arg.server, &data->o_arg.seq_args, - &data->o_res.seq_res, task); + nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args, + &data->c_res.seq_res, task); } static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) { struct nfs4_opendata *data = calldata; - nfs40_sequence_done(task, &data->o_res.seq_res); + nfs40_sequence_done(task, &data->c_res.seq_res); data->rpc_status = task->tk_status; if (data->rpc_status == 0) { @@ -1686,7 +1686,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) }; int status; - nfs4_init_sequence(&data->o_arg.seq_args, &data->o_res.seq_res, 1); + nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1); kref_get(&data->kref); data->rpc_done = 0; data->rpc_status = 0; diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index cf883c7ae053..e799dc3c3b1d 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -231,14 +231,23 @@ out: return ret; } +/* + * nfs4_release_slot_table - release all slot table entries + */ +static void nfs4_release_slot_table(struct nfs4_slot_table *tbl) +{ + nfs4_shrink_slot_table(tbl, 0); +} + /** - * nfs4_release_slot_table - release resources attached to a slot table + * nfs4_shutdown_slot_table - release resources attached to a slot table * @tbl: slot table to shut down * */ -void nfs4_release_slot_table(struct nfs4_slot_table *tbl) +void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl) { - nfs4_shrink_slot_table(tbl, 0); + nfs4_release_slot_table(tbl); + rpc_destroy_wait_queue(&tbl->slot_tbl_waitq); } /** @@ -422,7 +431,7 @@ void nfs41_update_target_slotid(struct nfs4_slot_table *tbl, spin_unlock(&tbl->slot_tbl_lock); } -static void nfs4_destroy_session_slot_tables(struct nfs4_session *session) +static void nfs4_release_session_slot_tables(struct nfs4_session *session) { nfs4_release_slot_table(&session->fc_slot_table); nfs4_release_slot_table(&session->bc_slot_table); @@ -450,7 +459,7 @@ int nfs4_setup_session_slot_tables(struct nfs4_session *ses) if (status && tbl->slots == NULL) /* Fore and back channel share a connection so get * both slot tables or neither */ - nfs4_destroy_session_slot_tables(ses); + nfs4_release_session_slot_tables(ses); return status; } @@ -470,6 +479,12 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp) return session; } +static void nfs4_destroy_session_slot_tables(struct nfs4_session *session) +{ + nfs4_shutdown_slot_table(&session->fc_slot_table); + nfs4_shutdown_slot_table(&session->bc_slot_table); +} + void nfs4_destroy_session(struct nfs4_session *session) { struct rpc_xprt *xprt; diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 232306100651..b34ada9bc6a2 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -74,7 +74,7 @@ enum nfs4_session_state { extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, unsigned int max_reqs, const char *queue); -extern void nfs4_release_slot_table(struct nfs4_slot_table *tbl); +extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl); extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl); extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot); extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 38bae5a0ea25..11c54fd51e16 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -521,8 +521,11 @@ posix_acl_chmod(struct inode *inode, umode_t mode) return -EOPNOTSUPP; acl = get_acl(inode, ACL_TYPE_ACCESS); - if (IS_ERR_OR_NULL(acl)) + if (IS_ERR_OR_NULL(acl)) { + if (acl == ERR_PTR(-EOPNOTSUPP)) + return 0; return PTR_ERR(acl); + } ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) @@ -544,14 +547,15 @@ posix_acl_create(struct inode *dir, umode_t *mode, goto no_acl; p = get_acl(dir, ACL_TYPE_DEFAULT); - if (IS_ERR(p)) + if (IS_ERR(p)) { + if (p == ERR_PTR(-EOPNOTSUPP)) + goto apply_umask; return PTR_ERR(p); - - if (!p) { - *mode &= ~current_umask(); - goto no_acl; } + if (!p) + goto apply_umask; + *acl = posix_acl_clone(p, GFP_NOFS); if (!*acl) return -ENOMEM; @@ -575,6 +579,8 @@ posix_acl_create(struct inode *dir, umode_t *mode, } return 0; +apply_umask: + *mode &= ~current_umask(); no_acl: *default_acl = NULL; *acl = NULL; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index fd8bf3219ef7..b4a745d7d9a9 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -115,7 +115,6 @@ extern int copy_strings_kernel(int argc, const char *const *argv, extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); -extern void free_bprm(struct linux_binprm *); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); #endif /* _LINUX_BINFMTS_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 09f553c59813..d79678c188ad 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2079,6 +2079,7 @@ extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname(const char __user *); +extern struct filename *getname_kernel(const char *); enum { FILE_CREATED = 1, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 3ccfcecf8999..b2fb167b2e6d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -379,12 +379,14 @@ struct nfs_openres { * Arguments to the open_confirm call. */ struct nfs_open_confirmargs { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; nfs4_stateid * stateid; struct nfs_seqid * seqid; }; struct nfs_open_confirmres { + struct nfs4_sequence_res seq_res; nfs4_stateid stateid; struct nfs_seqid * seqid; }; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 26ebcf41c213..69ae03f6eb15 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -80,13 +80,14 @@ struct nvme_dev { struct dma_pool *prp_small_pool; int instance; int queue_count; - int db_stride; + u32 db_stride; u32 ctrl_config; struct msix_entry *entry; struct nvme_bar __iomem *bar; struct list_head namespaces; struct kref kref; struct miscdevice miscdev; + struct work_struct reset_work; char name[12]; char serial[20]; char model[40]; @@ -94,6 +95,8 @@ struct nvme_dev { u32 max_hw_sectors; u32 stripe_size; u16 oncs; + u16 abort_limit; + u8 initialized; }; /* @@ -165,6 +168,7 @@ int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11, struct sg_io_hdr; int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr); +int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg); int nvme_sg_get_version_num(int __user *ip); #endif /* _LINUX_NVME_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 68a0e84463a0..a781dec1cd0b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -128,6 +128,7 @@ struct bio_list; struct fs_struct; struct perf_event_context; struct blk_plug; +struct filename; /* * List of flags we want to share for kernel threads, @@ -2311,7 +2312,7 @@ extern void do_group_exit(int); extern int allow_signal(int); extern int disallow_signal(int); -extern int do_execve(const char *, +extern int do_execve(struct filename *, const char __user * const __user *, const char __user * const __user *); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h index 989c04e0c563..e5ab62201119 100644 --- a/include/uapi/linux/nvme.h +++ b/include/uapi/linux/nvme.h @@ -350,6 +350,16 @@ struct nvme_delete_queue { __u32 rsvd11[5]; }; +struct nvme_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 sqid; + __u16 cid; + __u32 rsvd11[5]; +}; + struct nvme_download_firmware { __u8 opcode; __u8 flags; @@ -384,6 +394,7 @@ struct nvme_command { struct nvme_download_firmware dlfw; struct nvme_format_cmd format; struct nvme_dsm_cmd dsm; + struct nvme_abort_cmd abort; }; }; diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 7ad033dbc845..a5af2a26d94f 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -191,15 +191,11 @@ void gnttab_free_auto_xlat_frames(void); #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count); -int gnttab_map_refs_userspace(struct gnttab_map_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count); int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_map_grant_ref *kunmap_ops, struct page **pages, unsigned int count); -int gnttab_unmap_refs_userspace(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kunmap_ops, - struct page **pages, unsigned int count); /* Perform a batch of grant map/copy operations. Retry every batch slot * for which the hypervisor returns GNTST_eagain. This is typically due diff --git a/init/main.c b/init/main.c index 2fd9cef70ee8..eb03090cdced 100644 --- a/init/main.c +++ b/init/main.c @@ -812,7 +812,7 @@ void __init load_default_modules(void) static int run_init_process(const char *init_filename) { argv_init[0] = init_filename; - return do_execve(init_filename, + return do_execve(getname_kernel(init_filename), (const char __user *const __user *)argv_init, (const char __user *const __user *)envp_init); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 10176cd5956a..7aef2f4b6c64 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1719,7 +1719,7 @@ void audit_putname(struct filename *name) struct audit_context *context = current->audit_context; BUG_ON(!context); - if (!context->in_syscall) { + if (!name->aname || !context->in_syscall) { #if AUDIT_DEBUG == 2 printk(KERN_ERR "%s:%d(:%d): final_putname(%p)\n", __FILE__, __LINE__, context->serial, name); diff --git a/kernel/kmod.c b/kernel/kmod.c index b086006c59e7..6b375af4958d 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -239,7 +239,7 @@ static int ____call_usermodehelper(void *data) commit_creds(new); - retval = do_execve(sub_info->path, + retval = do_execve(getname_kernel(sub_info->path), (const char __user *const __user *)sub_info->argv, (const char __user *const __user *)sub_info->envp); if (!retval) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index dbf94a7d25a8..a48abeac753f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -119,7 +119,7 @@ menu "Compile-time checks and compiler options" config DEBUG_INFO bool "Compile the kernel with debug info" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !COMPILE_TEST help If you say Y here the resulting kernel image will include debugging info resulting in a larger kernel image. |