From 2dd14934c9138c562d93c501e88c6d6f061eb8ba Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 23 Mar 2006 00:00:09 +0100 Subject: [PATCH] spufs: allow SPU code to do syscalls An SPU does not have a way to implement system calls itself, but it can create intercepts to the kernel. This patch uses the method defined by the JSRE interface for C99 host library calls from an SPU to implement Linux system calls. It uses the reserved SPU stop code 0x2104 for this, using the structure layout and syscall numbers for ppc64-linux. I'm still undecided wether it is better to have a list of allowed syscalls or a list of forbidden syscalls, since we can't allow an SPU to call all syscalls that are defined for ppc64-linux. This patch implements the easier choice of them, with a blacklist that only prevents an SPU from calling anything that interacts with its own execution, e.g fork, execve, clone, vfork, exit, spu_run and spu_create and everything that deals with signals. Signed-off-by: Arnd Bergmann Signed-off-by: Paul Mackerras --- include/asm-powerpc/spu.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/asm-powerpc/spu.h') diff --git a/include/asm-powerpc/spu.h b/include/asm-powerpc/spu.h index 38bacf2f6e0c..b5c90d6fdceb 100644 --- a/include/asm-powerpc/spu.h +++ b/include/asm-powerpc/spu.h @@ -149,6 +149,14 @@ int spu_irq_class_0_bottom(struct spu *spu); int spu_irq_class_1_bottom(struct spu *spu); void spu_irq_setaffinity(struct spu *spu, int cpu); +/* system callbacks from the SPU */ +struct spu_syscall_block { + u64 nr_ret; + u64 parm[6]; +}; +extern long spu_sys_callback(struct spu_syscall_block *s); + +/* syscalls implemented in spufs */ extern struct spufs_calls { asmlinkage long (*create_thread)(const char __user *name, unsigned int flags, mode_t mode); @@ -399,7 +407,6 @@ struct spu_priv1 { #define SPU_GET_REVISION_BITS(vr) (vr & SPU_REVISION_BITS) u8 pad_0x28_0x100[0x100 - 0x28]; /* 0x28 */ - /* Interrupt Area */ u64 int_mask_RW[3]; /* 0x100 */ #define CLASS0_ENABLE_DMA_ALIGNMENT_INTR 0x1L -- cgit v1.2.3 From a33a7d7309d79656bc19a0e96fc4547a1633283e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 23 Mar 2006 00:00:11 +0100 Subject: [PATCH] spufs: implement mfc access for PPE-side DMA This patch adds a new file called 'mfc' to each spufs directory. The file accepts DMA commands that are a subset of what would be legal DMA commands for problem state register access. Upon reading the file, a bitmask is returned with the completed tag groups set. The file is meant to be used from an abstraction in libspe that is added by a different patch. From the kernel perspective, this means a process can now offload a memory copy from or into an SPE local store without having to run code on the SPE itself. The transfer will only be performed while the SPE is owned by one thread that is waiting in the spu_run system call and the data will be transferred into that thread's address space, independent of which thread started the transfer. Signed-off-by: Arnd Bergmann Signed-off-by: Paul Mackerras --- arch/powerpc/platforms/cell/spu_base.c | 7 +- arch/powerpc/platforms/cell/spufs/backing_ops.c | 47 ++++ arch/powerpc/platforms/cell/spufs/context.c | 5 +- arch/powerpc/platforms/cell/spufs/file.c | 294 ++++++++++++++++++++++++ arch/powerpc/platforms/cell/spufs/hw_ops.c | 57 +++++ arch/powerpc/platforms/cell/spufs/sched.c | 2 + arch/powerpc/platforms/cell/spufs/spufs.h | 20 ++ arch/powerpc/platforms/cell/spufs/switch.c | 3 +- include/asm-powerpc/spu.h | 1 + 9 files changed, 431 insertions(+), 5 deletions(-) (limited to 'include/asm-powerpc/spu.h') diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index a8fa1eeeb174..162b6cfa8a43 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -111,7 +111,7 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea) extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); //XXX static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr) { - pr_debug("%s\n", __FUNCTION__); + pr_debug("%s, %lx, %lx\n", __FUNCTION__, dsisr, ea); /* Handle kernel space hash faults immediately. User hash faults need to be deferred to process context. */ @@ -168,7 +168,7 @@ static int __spu_trap_halt(struct spu *spu) static int __spu_trap_tag_group(struct spu *spu) { pr_debug("%s\n", __FUNCTION__); - /* wake_up(&spu->dma_wq); */ + spu->mfc_callback(spu); return 0; } @@ -242,6 +242,8 @@ spu_irq_class_1(int irq, void *data, struct pt_regs *regs) spu_mfc_dsisr_set(spu, 0ul); spu_int_stat_clear(spu, 1, stat); spin_unlock(&spu->register_lock); + pr_debug("%s: %lx %lx %lx %lx\n", __FUNCTION__, mask, stat, + dar, dsisr); if (stat & 1) /* segment fault */ __spu_trap_data_seg(spu, dar); @@ -632,6 +634,7 @@ static int __init create_spu(struct device_node *spe) spu->ibox_callback = NULL; spu->wbox_callback = NULL; spu->stop_callback = NULL; + spu->mfc_callback = NULL; mutex_lock(&spu_mutex); spu->number = number++; diff --git a/arch/powerpc/platforms/cell/spufs/backing_ops.c b/arch/powerpc/platforms/cell/spufs/backing_ops.c index a5c489a53c61..f1d35ddc9df3 100644 --- a/arch/powerpc/platforms/cell/spufs/backing_ops.c +++ b/arch/powerpc/platforms/cell/spufs/backing_ops.c @@ -285,6 +285,49 @@ static void spu_backing_runcntl_stop(struct spu_context *ctx) spu_backing_runcntl_write(ctx, SPU_RUNCNTL_STOP); } +static int spu_backing_set_mfc_query(struct spu_context * ctx, u32 mask, + u32 mode) +{ + struct spu_problem_collapsed *prob = &ctx->csa.prob; + int ret; + + spin_lock(&ctx->csa.register_lock); + ret = -EAGAIN; + if (prob->dma_querytype_RW) + goto out; + ret = 0; + /* FIXME: what are the side-effects of this? */ + prob->dma_querymask_RW = mask; + prob->dma_querytype_RW = mode; +out: + spin_unlock(&ctx->csa.register_lock); + + return ret; +} + +static u32 spu_backing_read_mfc_tagstatus(struct spu_context * ctx) +{ + return ctx->csa.prob.dma_tagstatus_R; +} + +static u32 spu_backing_get_mfc_free_elements(struct spu_context *ctx) +{ + return ctx->csa.prob.dma_qstatus_R; +} + +static int spu_backing_send_mfc_command(struct spu_context *ctx, + struct mfc_dma_command *cmd) +{ + int ret; + + spin_lock(&ctx->csa.register_lock); + ret = -EAGAIN; + /* FIXME: set up priv2->puq */ + spin_unlock(&ctx->csa.register_lock); + + return ret; +} + struct spu_context_ops spu_backing_ops = { .mbox_read = spu_backing_mbox_read, .mbox_stat_read = spu_backing_mbox_stat_read, @@ -305,4 +348,8 @@ struct spu_context_ops spu_backing_ops = { .get_ls = spu_backing_get_ls, .runcntl_write = spu_backing_runcntl_write, .runcntl_stop = spu_backing_runcntl_stop, + .set_mfc_query = spu_backing_set_mfc_query, + .read_mfc_tagstatus = spu_backing_read_mfc_tagstatus, + .get_mfc_free_elements = spu_backing_get_mfc_free_elements, + .send_mfc_command = spu_backing_send_mfc_command, }; diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c index 336f238102fd..7e016b9eab21 100644 --- a/arch/powerpc/platforms/cell/spufs/context.c +++ b/arch/powerpc/platforms/cell/spufs/context.c @@ -47,8 +47,11 @@ struct spu_context *alloc_spu_context(struct address_space *local_store) init_waitqueue_head(&ctx->ibox_wq); init_waitqueue_head(&ctx->wbox_wq); init_waitqueue_head(&ctx->stop_wq); + init_waitqueue_head(&ctx->mfc_wq); ctx->ibox_fasync = NULL; ctx->wbox_fasync = NULL; + ctx->mfc_fasync = NULL; + ctx->tagwait = 0; ctx->state = SPU_STATE_SAVED; ctx->local_store = local_store; ctx->spu = NULL; @@ -68,8 +71,6 @@ void destroy_spu_context(struct kref *kref) ctx = container_of(kref, struct spu_context, kref); down_write(&ctx->state_sema); spu_deactivate(ctx); - ctx->ibox_fasync = NULL; - ctx->wbox_fasync = NULL; up_write(&ctx->state_sema); spu_fini_csa(&ctx->csa); kfree(ctx); diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index dfa649c9b956..62fe9941ccee 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -20,6 +20,8 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#undef DEBUG + #include #include #include @@ -641,6 +643,297 @@ static u64 spufs_signal2_type_get(void *data) DEFINE_SIMPLE_ATTRIBUTE(spufs_signal2_type, spufs_signal2_type_get, spufs_signal2_type_set, "%llu"); + +static int spufs_mfc_open(struct inode *inode, struct file *file) +{ + struct spufs_inode_info *i = SPUFS_I(inode); + struct spu_context *ctx = i->i_ctx; + + /* we don't want to deal with DMA into other processes */ + if (ctx->owner != current->mm) + return -EINVAL; + + if (atomic_read(&inode->i_count) != 1) + return -EBUSY; + + file->private_data = ctx; + return nonseekable_open(inode, file); +} + +/* interrupt-level mfc callback function. */ +void spufs_mfc_callback(struct spu *spu) +{ + struct spu_context *ctx = spu->ctx; + + wake_up_all(&ctx->mfc_wq); + + pr_debug("%s %s\n", __FUNCTION__, spu->name); + if (ctx->mfc_fasync) { + u32 free_elements, tagstatus; + unsigned int mask; + + /* no need for spu_acquire in interrupt context */ + free_elements = ctx->ops->get_mfc_free_elements(ctx); + tagstatus = ctx->ops->read_mfc_tagstatus(ctx); + + mask = 0; + if (free_elements & 0xffff) + mask |= POLLOUT; + if (tagstatus & ctx->tagwait) + mask |= POLLIN; + + kill_fasync(&ctx->mfc_fasync, SIGIO, mask); + } +} + +static int spufs_read_mfc_tagstatus(struct spu_context *ctx, u32 *status) +{ + /* See if there is one tag group is complete */ + /* FIXME we need locking around tagwait */ + *status = ctx->ops->read_mfc_tagstatus(ctx) & ctx->tagwait; + ctx->tagwait &= ~*status; + if (*status) + return 1; + + /* enable interrupt waiting for any tag group, + may silently fail if interrupts are already enabled */ + ctx->ops->set_mfc_query(ctx, ctx->tagwait, 1); + return 0; +} + +static ssize_t spufs_mfc_read(struct file *file, char __user *buffer, + size_t size, loff_t *pos) +{ + struct spu_context *ctx = file->private_data; + int ret = -EINVAL; + u32 status; + + if (size != 4) + goto out; + + spu_acquire(ctx); + if (file->f_flags & O_NONBLOCK) { + status = ctx->ops->read_mfc_tagstatus(ctx); + if (!(status & ctx->tagwait)) + ret = -EAGAIN; + else + ctx->tagwait &= ~status; + } else { + ret = spufs_wait(ctx->mfc_wq, + spufs_read_mfc_tagstatus(ctx, &status)); + } + spu_release(ctx); + + if (ret) + goto out; + + ret = 4; + if (copy_to_user(buffer, &status, 4)) + ret = -EFAULT; + +out: + return ret; +} + +static int spufs_check_valid_dma(struct mfc_dma_command *cmd) +{ + pr_debug("queueing DMA %x %lx %x %x %x\n", cmd->lsa, + cmd->ea, cmd->size, cmd->tag, cmd->cmd); + + switch (cmd->cmd) { + case MFC_PUT_CMD: + case MFC_PUTF_CMD: + case MFC_PUTB_CMD: + case MFC_GET_CMD: + case MFC_GETF_CMD: + case MFC_GETB_CMD: + break; + default: + pr_debug("invalid DMA opcode %x\n", cmd->cmd); + return -EIO; + } + + if ((cmd->lsa & 0xf) != (cmd->ea &0xf)) { + pr_debug("invalid DMA alignment, ea %lx lsa %x\n", + cmd->ea, cmd->lsa); + return -EIO; + } + + switch (cmd->size & 0xf) { + case 1: + break; + case 2: + if (cmd->lsa & 1) + goto error; + break; + case 4: + if (cmd->lsa & 3) + goto error; + break; + case 8: + if (cmd->lsa & 7) + goto error; + break; + case 0: + if (cmd->lsa & 15) + goto error; + break; + error: + default: + pr_debug("invalid DMA alignment %x for size %x\n", + cmd->lsa & 0xf, cmd->size); + return -EIO; + } + + if (cmd->size > 16 * 1024) { + pr_debug("invalid DMA size %x\n", cmd->size); + return -EIO; + } + + if (cmd->tag & 0xfff0) { + /* we reserve the higher tag numbers for kernel use */ + pr_debug("invalid DMA tag\n"); + return -EIO; + } + + if (cmd->class) { + /* not supported in this version */ + pr_debug("invalid DMA class\n"); + return -EIO; + } + + return 0; +} + +static int spu_send_mfc_command(struct spu_context *ctx, + struct mfc_dma_command cmd, + int *error) +{ + *error = ctx->ops->send_mfc_command(ctx, &cmd); + if (*error == -EAGAIN) { + /* wait for any tag group to complete + so we have space for the new command */ + ctx->ops->set_mfc_query(ctx, ctx->tagwait, 1); + /* try again, because the queue might be + empty again */ + *error = ctx->ops->send_mfc_command(ctx, &cmd); + if (*error == -EAGAIN) + return 0; + } + return 1; +} + +static ssize_t spufs_mfc_write(struct file *file, const char __user *buffer, + size_t size, loff_t *pos) +{ + struct spu_context *ctx = file->private_data; + struct mfc_dma_command cmd; + int ret = -EINVAL; + + if (size != sizeof cmd) + goto out; + + ret = -EFAULT; + if (copy_from_user(&cmd, buffer, sizeof cmd)) + goto out; + + ret = spufs_check_valid_dma(&cmd); + if (ret) + goto out; + + spu_acquire_runnable(ctx); + if (file->f_flags & O_NONBLOCK) { + ret = ctx->ops->send_mfc_command(ctx, &cmd); + } else { + int status; + ret = spufs_wait(ctx->mfc_wq, + spu_send_mfc_command(ctx, cmd, &status)); + if (status) + ret = status; + } + spu_release(ctx); + + if (ret) + goto out; + + ctx->tagwait |= 1 << cmd.tag; + +out: + return ret; +} + +static unsigned int spufs_mfc_poll(struct file *file,poll_table *wait) +{ + struct spu_context *ctx = file->private_data; + u32 free_elements, tagstatus; + unsigned int mask; + + spu_acquire(ctx); + ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2); + free_elements = ctx->ops->get_mfc_free_elements(ctx); + tagstatus = ctx->ops->read_mfc_tagstatus(ctx); + spu_release(ctx); + + poll_wait(file, &ctx->mfc_wq, wait); + + mask = 0; + if (free_elements & 0xffff) + mask |= POLLOUT | POLLWRNORM; + if (tagstatus & ctx->tagwait) + mask |= POLLIN | POLLRDNORM; + + pr_debug("%s: free %d tagstatus %d tagwait %d\n", __FUNCTION__, + free_elements, tagstatus, ctx->tagwait); + + return mask; +} + +static int spufs_mfc_flush(struct file *file) +{ + struct spu_context *ctx = file->private_data; + int ret; + + spu_acquire(ctx); +#if 0 +/* this currently hangs */ + ret = spufs_wait(ctx->mfc_wq, + ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2)); + if (ret) + goto out; + ret = spufs_wait(ctx->mfc_wq, + ctx->ops->read_mfc_tagstatus(ctx) == ctx->tagwait); +out: +#else + ret = 0; +#endif + spu_release(ctx); + + return ret; +} + +static int spufs_mfc_fsync(struct file *file, struct dentry *dentry, + int datasync) +{ + return spufs_mfc_flush(file); +} + +static int spufs_mfc_fasync(int fd, struct file *file, int on) +{ + struct spu_context *ctx = file->private_data; + + return fasync_helper(fd, file, on, &ctx->mfc_fasync); +} + +static struct file_operations spufs_mfc_fops = { + .open = spufs_mfc_open, + .read = spufs_mfc_read, + .write = spufs_mfc_write, + .poll = spufs_mfc_poll, + .flush = spufs_mfc_flush, + .fsync = spufs_mfc_fsync, + .fasync = spufs_mfc_fasync, +}; + static void spufs_npc_set(void *data, u64 val) { struct spu_context *ctx = data; @@ -783,6 +1076,7 @@ struct tree_descr spufs_dir_contents[] = { { "signal2", &spufs_signal2_fops, 0666, }, { "signal1_type", &spufs_signal1_type, 0666, }, { "signal2_type", &spufs_signal2_type, 0666, }, + { "mfc", &spufs_mfc_fops, 0666, }, { "npc", &spufs_npc_ops, 0666, }, { "fpcr", &spufs_fpcr_fops, 0666, }, { "decr", &spufs_decr_ops, 0666, }, diff --git a/arch/powerpc/platforms/cell/spufs/hw_ops.c b/arch/powerpc/platforms/cell/spufs/hw_ops.c index 5445719bff79..a13a8b5a014d 100644 --- a/arch/powerpc/platforms/cell/spufs/hw_ops.c +++ b/arch/powerpc/platforms/cell/spufs/hw_ops.c @@ -232,6 +232,59 @@ static void spu_hw_runcntl_stop(struct spu_context *ctx) spin_unlock_irq(&ctx->spu->register_lock); } +static int spu_hw_set_mfc_query(struct spu_context * ctx, u32 mask, u32 mode) +{ + struct spu_problem *prob = ctx->spu->problem; + int ret; + + spin_lock_irq(&ctx->spu->register_lock); + ret = -EAGAIN; + if (in_be32(&prob->dma_querytype_RW)) + goto out; + ret = 0; + out_be32(&prob->dma_querymask_RW, mask); + out_be32(&prob->dma_querytype_RW, mode); +out: + spin_unlock_irq(&ctx->spu->register_lock); + return ret; +} + +static u32 spu_hw_read_mfc_tagstatus(struct spu_context * ctx) +{ + return in_be32(&ctx->spu->problem->dma_tagstatus_R); +} + +static u32 spu_hw_get_mfc_free_elements(struct spu_context *ctx) +{ + return in_be32(&ctx->spu->problem->dma_qstatus_R); +} + +static int spu_hw_send_mfc_command(struct spu_context *ctx, + struct mfc_dma_command *cmd) +{ + u32 status; + struct spu_problem *prob = ctx->spu->problem; + + spin_lock_irq(&ctx->spu->register_lock); + out_be32(&prob->mfc_lsa_W, cmd->lsa); + out_be64(&prob->mfc_ea_W, cmd->ea); + out_be32(&prob->mfc_union_W.by32.mfc_size_tag32, + cmd->size << 16 | cmd->tag); + out_be32(&prob->mfc_union_W.by32.mfc_class_cmd32, + cmd->class << 16 | cmd->cmd); + status = in_be32(&prob->mfc_union_W.by32.mfc_class_cmd32); + spin_unlock_irq(&ctx->spu->register_lock); + + switch (status & 0xffff) { + case 0: + return 0; + case 2: + return -EAGAIN; + default: + return -EINVAL; + } +} + struct spu_context_ops spu_hw_ops = { .mbox_read = spu_hw_mbox_read, .mbox_stat_read = spu_hw_mbox_stat_read, @@ -252,4 +305,8 @@ struct spu_context_ops spu_hw_ops = { .get_ls = spu_hw_get_ls, .runcntl_write = spu_hw_runcntl_write, .runcntl_stop = spu_hw_runcntl_stop, + .set_mfc_query = spu_hw_set_mfc_query, + .read_mfc_tagstatus = spu_hw_read_mfc_tagstatus, + .get_mfc_free_elements = spu_hw_get_mfc_free_elements, + .send_mfc_command = spu_hw_send_mfc_command, }; diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 963182fbd1aa..bf652cd77000 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -180,6 +180,7 @@ static inline void bind_context(struct spu *spu, struct spu_context *ctx) spu->ibox_callback = spufs_ibox_callback; spu->wbox_callback = spufs_wbox_callback; spu->stop_callback = spufs_stop_callback; + spu->mfc_callback = spufs_mfc_callback; mb(); spu_unmap_mappings(ctx); spu_restore(&ctx->csa, spu); @@ -197,6 +198,7 @@ static inline void unbind_context(struct spu *spu, struct spu_context *ctx) spu->ibox_callback = NULL; spu->wbox_callback = NULL; spu->stop_callback = NULL; + spu->mfc_callback = NULL; spu->mm = NULL; spu->pid = 0; spu->prio = MAX_PRIO; diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index db2601f0abd5..57d687ca3f03 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -55,13 +55,27 @@ struct spu_context { wait_queue_head_t ibox_wq; wait_queue_head_t wbox_wq; wait_queue_head_t stop_wq; + wait_queue_head_t mfc_wq; struct fasync_struct *ibox_fasync; struct fasync_struct *wbox_fasync; + struct fasync_struct *mfc_fasync; + u32 tagwait; struct spu_context_ops *ops; struct work_struct reap_work; u64 flags; }; +struct mfc_dma_command { + int32_t pad; /* reserved */ + uint32_t lsa; /* local storage address */ + uint64_t ea; /* effective address */ + uint16_t size; /* transfer size */ + uint16_t tag; /* command tag */ + uint16_t class; /* class ID */ + uint16_t cmd; /* command opcode */ +}; + + /* SPU context query/set operations. */ struct spu_context_ops { int (*mbox_read) (struct spu_context * ctx, u32 * data); @@ -84,6 +98,11 @@ struct spu_context_ops { char*(*get_ls) (struct spu_context * ctx); void (*runcntl_write) (struct spu_context * ctx, u32 data); void (*runcntl_stop) (struct spu_context * ctx); + int (*set_mfc_query)(struct spu_context * ctx, u32 mask, u32 mode); + u32 (*read_mfc_tagstatus)(struct spu_context * ctx); + u32 (*get_mfc_free_elements)(struct spu_context *ctx); + int (*send_mfc_command)(struct spu_context *ctx, + struct mfc_dma_command *cmd); }; extern struct spu_context_ops spu_hw_ops; @@ -159,5 +178,6 @@ size_t spu_ibox_read(struct spu_context *ctx, u32 *data); void spufs_ibox_callback(struct spu *spu); void spufs_wbox_callback(struct spu *spu); void spufs_stop_callback(struct spu *spu); +void spufs_mfc_callback(struct spu *spu); #endif diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c index 212db28531fa..97898d5d34e5 100644 --- a/arch/powerpc/platforms/cell/spufs/switch.c +++ b/arch/powerpc/platforms/cell/spufs/switch.c @@ -2145,7 +2145,8 @@ static void init_priv1(struct spu_state *csa) csa->priv1.int_mask_class1_RW = CLASS1_ENABLE_SEGMENT_FAULT_INTR | CLASS1_ENABLE_STORAGE_FAULT_INTR; csa->priv1.int_mask_class2_RW = CLASS2_ENABLE_SPU_STOP_INTR | - CLASS2_ENABLE_SPU_HALT_INTR; + CLASS2_ENABLE_SPU_HALT_INTR | + CLASS2_ENABLE_SPU_DMA_TAG_GROUP_COMPLETE_INTR; } static void init_priv2(struct spu_state *csa) diff --git a/include/asm-powerpc/spu.h b/include/asm-powerpc/spu.h index b5c90d6fdceb..8564b8234069 100644 --- a/include/asm-powerpc/spu.h +++ b/include/asm-powerpc/spu.h @@ -137,6 +137,7 @@ struct spu { void (* wbox_callback)(struct spu *spu); void (* ibox_callback)(struct spu *spu); void (* stop_callback)(struct spu *spu); + void (* mfc_callback)(struct spu *spu); char irq_c0[8]; char irq_c1[8]; -- cgit v1.2.3 From 6df10a82f8de89c66eb91c371d62d76e87b2cbba Mon Sep 17 00:00:00 2001 From: Mark Nutter Date: Thu, 23 Mar 2006 00:00:12 +0100 Subject: [PATCH] spufs: enable SPE problem state MMIO access. This patch is layered on top of CONFIG_SPARSEMEM and is patterned after direct mapping of LS. This patch allows mmap() of the following regions: "mfc", which represents the area from [0x3000 - 0x3fff]; "cntl", which represents the area from [0x4000 - 0x4fff]; "signal1" which begins at offset 0x14000; "signal2" which begins at offset 0x1c000. The signal1 & signal2 files may be mmap()'d by regular user processes. The cntl and mfc file, on the other hand, may only be accessed if the owning process has CAP_SYS_RAWIO, because they have the potential to confuse the kernel with regard to parallel access to the same files with regular file operations: the kernel always holds a spinlock when accessing registers in these areas to serialize them, which can not be guaranteed with user mmaps, Signed-off-by: Arnd Bergmann Signed-off-by: Paul Mackerras --- arch/powerpc/platforms/cell/Kconfig | 5 + arch/powerpc/platforms/cell/spu_base.c | 5 + arch/powerpc/platforms/cell/spufs/context.c | 18 ++- arch/powerpc/platforms/cell/spufs/file.c | 229 +++++++++++++++++++++++++++- arch/powerpc/platforms/cell/spufs/inode.c | 2 +- arch/powerpc/platforms/cell/spufs/spufs.h | 8 +- include/asm-powerpc/spu.h | 1 + 7 files changed, 256 insertions(+), 12 deletions(-) (limited to 'include/asm-powerpc/spu.h') diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 3157071e241c..c2a3db8edb0c 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -10,4 +10,9 @@ config SPU_FS Units on machines implementing the Broadband Processor Architecture. +config SPUFS_MMAP + bool + depends on SPU_FS && SPARSEMEM && !PPC_64K_PAGES + default y + endmenu diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index 162b6cfa8a43..d152a3fbdb83 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -570,6 +570,11 @@ static int __init spu_map_device(struct spu *spu, struct device_node *spe) if (!spu->local_store) goto out; + prop = get_property(spe, "problem", NULL); + if (!prop) + goto out_unmap; + spu->problem_phys = *(unsigned long *)prop; + spu->problem= map_spe_prop(spe, "problem"); if (!spu->problem) goto out_unmap; diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c index 7e016b9eab21..3f75c1e7adea 100644 --- a/arch/powerpc/platforms/cell/spufs/context.c +++ b/arch/powerpc/platforms/cell/spufs/context.c @@ -27,7 +27,7 @@ #include #include "spufs.h" -struct spu_context *alloc_spu_context(struct address_space *local_store) +struct spu_context *alloc_spu_context(void) { struct spu_context *ctx; ctx = kmalloc(sizeof *ctx, GFP_KERNEL); @@ -53,7 +53,10 @@ struct spu_context *alloc_spu_context(struct address_space *local_store) ctx->mfc_fasync = NULL; ctx->tagwait = 0; ctx->state = SPU_STATE_SAVED; - ctx->local_store = local_store; + ctx->local_store = NULL; + ctx->cntl = NULL; + ctx->signal1 = NULL; + ctx->signal2 = NULL; ctx->spu = NULL; ctx->ops = &spu_backing_ops; ctx->owner = get_task_mm(current); @@ -110,7 +113,16 @@ void spu_release(struct spu_context *ctx) void spu_unmap_mappings(struct spu_context *ctx) { - unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1); + if (ctx->local_store) + unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1); + if (ctx->mfc) + unmap_mapping_range(ctx->mfc, 0, 0x4000, 1); + if (ctx->cntl) + unmap_mapping_range(ctx->cntl, 0, 0x4000, 1); + if (ctx->signal1) + unmap_mapping_range(ctx->signal1, 0, 0x4000, 1); + if (ctx->signal2) + unmap_mapping_range(ctx->signal2, 0, 0x4000, 1); } int spu_acquire_runnable(struct spu_context *ctx) diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 62fe9941ccee..366185e92667 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -41,8 +41,10 @@ static int spufs_mem_open(struct inode *inode, struct file *file) { struct spufs_inode_info *i = SPUFS_I(inode); - file->private_data = i->i_ctx; - file->f_mapping = i->i_ctx->local_store; + struct spu_context *ctx = i->i_ctx; + file->private_data = ctx; + file->f_mapping = inode->i_mapping; + ctx->local_store = inode->i_mapping; return 0; } @@ -86,7 +88,7 @@ spufs_mem_write(struct file *file, const char __user *buffer, return ret; } -#ifdef CONFIG_SPARSEMEM +#ifdef CONFIG_SPUFS_MMAP static struct page * spufs_mem_mmap_nopage(struct vm_area_struct *vma, unsigned long address, int *type) @@ -138,11 +140,113 @@ static struct file_operations spufs_mem_fops = { .read = spufs_mem_read, .write = spufs_mem_write, .llseek = generic_file_llseek, -#ifdef CONFIG_SPARSEMEM +#ifdef CONFIG_SPUFS_MMAP .mmap = spufs_mem_mmap, #endif }; +#ifdef CONFIG_SPUFS_MMAP +static struct page *spufs_ps_nopage(struct vm_area_struct *vma, + unsigned long address, + int *type, unsigned long ps_offs) +{ + struct page *page = NOPAGE_SIGBUS; + int fault_type = VM_FAULT_SIGBUS; + struct spu_context *ctx = vma->vm_file->private_data; + unsigned long offset = address - vma->vm_start; + unsigned long area; + int ret; + + offset += vma->vm_pgoff << PAGE_SHIFT; + if (offset >= 0x4000) + goto out; + + ret = spu_acquire_runnable(ctx); + if (ret) + goto out; + + area = ctx->spu->problem_phys + ps_offs; + page = pfn_to_page((area + offset) >> PAGE_SHIFT); + fault_type = VM_FAULT_MINOR; + page_cache_get(page); + + spu_release(ctx); + + out: + if (type) + *type = fault_type; + + return page; +} + +static struct page *spufs_cntl_mmap_nopage(struct vm_area_struct *vma, + unsigned long address, int *type) +{ + return spufs_ps_nopage(vma, address, type, 0x4000); +} + +static struct vm_operations_struct spufs_cntl_mmap_vmops = { + .nopage = spufs_cntl_mmap_nopage, +}; + +/* + * mmap support for problem state control area [0x4000 - 0x4fff]. + * Mapping this area requires that the application have CAP_SYS_RAWIO, + * as these registers require special care when read/writing. + */ +static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + vma->vm_flags |= VM_RESERVED; + vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) + | _PAGE_NO_CACHE); + + vma->vm_ops = &spufs_cntl_mmap_vmops; + return 0; +} +#endif + +static int spufs_cntl_open(struct inode *inode, struct file *file) +{ + struct spufs_inode_info *i = SPUFS_I(inode); + struct spu_context *ctx = i->i_ctx; + + file->private_data = ctx; + file->f_mapping = inode->i_mapping; + ctx->cntl = inode->i_mapping; + return 0; +} + +static ssize_t +spufs_cntl_read(struct file *file, char __user *buffer, + size_t size, loff_t *pos) +{ + /* FIXME: read from spu status */ + return -EINVAL; +} + +static ssize_t +spufs_cntl_write(struct file *file, const char __user *buffer, + size_t size, loff_t *pos) +{ + /* FIXME: write to runctl bit */ + return -EINVAL; +} + +static struct file_operations spufs_cntl_fops = { + .open = spufs_cntl_open, + .read = spufs_cntl_read, + .write = spufs_cntl_write, +#ifdef CONFIG_SPUFS_MMAP + .mmap = spufs_cntl_mmap, +#endif +}; + static int spufs_regs_open(struct inode *inode, struct file *file) { @@ -503,6 +607,16 @@ static struct file_operations spufs_wbox_stat_fops = { .read = spufs_wbox_stat_read, }; +static int spufs_signal1_open(struct inode *inode, struct file *file) +{ + struct spufs_inode_info *i = SPUFS_I(inode); + struct spu_context *ctx = i->i_ctx; + file->private_data = ctx; + file->f_mapping = inode->i_mapping; + ctx->signal1 = inode->i_mapping; + return nonseekable_open(inode, file); +} + static ssize_t spufs_signal1_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { @@ -543,12 +657,50 @@ static ssize_t spufs_signal1_write(struct file *file, const char __user *buf, return 4; } +#ifdef CONFIG_SPUFS_MMAP +static struct page *spufs_signal1_mmap_nopage(struct vm_area_struct *vma, + unsigned long address, int *type) +{ + return spufs_ps_nopage(vma, address, type, 0x14000); +} + +static struct vm_operations_struct spufs_signal1_mmap_vmops = { + .nopage = spufs_signal1_mmap_nopage, +}; + +static int spufs_signal1_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + + vma->vm_flags |= VM_RESERVED; + vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) + | _PAGE_NO_CACHE); + + vma->vm_ops = &spufs_signal1_mmap_vmops; + return 0; +} +#endif + static struct file_operations spufs_signal1_fops = { - .open = spufs_pipe_open, + .open = spufs_signal1_open, .read = spufs_signal1_read, .write = spufs_signal1_write, +#ifdef CONFIG_SPUFS_MMAP + .mmap = spufs_signal1_mmap, +#endif }; +static int spufs_signal2_open(struct inode *inode, struct file *file) +{ + struct spufs_inode_info *i = SPUFS_I(inode); + struct spu_context *ctx = i->i_ctx; + file->private_data = ctx; + file->f_mapping = inode->i_mapping; + ctx->signal2 = inode->i_mapping; + return nonseekable_open(inode, file); +} + static ssize_t spufs_signal2_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { @@ -591,10 +743,39 @@ static ssize_t spufs_signal2_write(struct file *file, const char __user *buf, return 4; } +#ifdef CONFIG_SPUFS_MMAP +static struct page *spufs_signal2_mmap_nopage(struct vm_area_struct *vma, + unsigned long address, int *type) +{ + return spufs_ps_nopage(vma, address, type, 0x1c000); +} + +static struct vm_operations_struct spufs_signal2_mmap_vmops = { + .nopage = spufs_signal2_mmap_nopage, +}; + +static int spufs_signal2_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + + /* FIXME: */ + vma->vm_flags |= VM_RESERVED; + vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) + | _PAGE_NO_CACHE); + + vma->vm_ops = &spufs_signal2_mmap_vmops; + return 0; +} +#endif + static struct file_operations spufs_signal2_fops = { - .open = spufs_pipe_open, + .open = spufs_signal2_open, .read = spufs_signal2_read, .write = spufs_signal2_write, +#ifdef CONFIG_SPUFS_MMAP + .mmap = spufs_signal2_mmap, +#endif }; static void spufs_signal1_type_set(void *data, u64 val) @@ -643,6 +824,38 @@ static u64 spufs_signal2_type_get(void *data) DEFINE_SIMPLE_ATTRIBUTE(spufs_signal2_type, spufs_signal2_type_get, spufs_signal2_type_set, "%llu"); +#ifdef CONFIG_SPUFS_MMAP +static struct page *spufs_mfc_mmap_nopage(struct vm_area_struct *vma, + unsigned long address, int *type) +{ + return spufs_ps_nopage(vma, address, type, 0x3000); +} + +static struct vm_operations_struct spufs_mfc_mmap_vmops = { + .nopage = spufs_mfc_mmap_nopage, +}; + +/* + * mmap support for problem state MFC DMA area [0x0000 - 0x0fff]. + * Mapping this area requires that the application have CAP_SYS_RAWIO, + * as these registers require special care when read/writing. + */ +static int spufs_mfc_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + vma->vm_flags |= VM_RESERVED; + vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) + | _PAGE_NO_CACHE); + + vma->vm_ops = &spufs_mfc_mmap_vmops; + return 0; +} +#endif static int spufs_mfc_open(struct inode *inode, struct file *file) { @@ -932,6 +1145,9 @@ static struct file_operations spufs_mfc_fops = { .flush = spufs_mfc_flush, .fsync = spufs_mfc_fsync, .fasync = spufs_mfc_fasync, +#ifdef CONFIG_SPUFS_MMAP + .mmap = spufs_mfc_mmap, +#endif }; static void spufs_npc_set(void *data, u64 val) @@ -1077,6 +1293,7 @@ struct tree_descr spufs_dir_contents[] = { { "signal1_type", &spufs_signal1_type, 0666, }, { "signal2_type", &spufs_signal2_type, 0666, }, { "mfc", &spufs_mfc_fops, 0666, }, + { "cntl", &spufs_cntl_fops, 0666, }, { "npc", &spufs_npc_ops, 0666, }, { "fpcr", &spufs_fpcr_fops, 0666, }, { "decr", &spufs_decr_ops, 0666, }, diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index b3962c3a0348..dc06305eecf5 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -241,7 +241,7 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, int mode) inode->i_gid = dir->i_gid; inode->i_mode &= S_ISGID; } - ctx = alloc_spu_context(inode->i_mapping); + ctx = alloc_spu_context(); SPUFS_I(inode)->i_ctx = ctx; if (!ctx) goto out_iput; diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index 57d687ca3f03..4485738e2102 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -43,7 +43,11 @@ struct spu_context { struct spu *spu; /* pointer to a physical SPU */ struct spu_state csa; /* SPU context save area. */ spinlock_t mmio_lock; /* protects mmio access */ - struct address_space *local_store;/* local store backing store */ + struct address_space *local_store; /* local store mapping. */ + struct address_space *mfc; /* 'mfc' area mappings. */ + struct address_space *cntl; /* 'control' area mappings. */ + struct address_space *signal1; /* 'signal1' area mappings. */ + struct address_space *signal2; /* 'signal2' area mappings. */ enum { SPU_STATE_RUNNABLE, SPU_STATE_SAVED } state; struct rw_semaphore state_sema; @@ -125,7 +129,7 @@ long spufs_create_thread(struct nameidata *nd, extern struct file_operations spufs_context_fops; /* context management */ -struct spu_context * alloc_spu_context(struct address_space *local_store); +struct spu_context * alloc_spu_context(void); void destroy_spu_context(struct kref *kref); struct spu_context * get_spu_context(struct spu_context *ctx); int put_spu_context(struct spu_context *ctx); diff --git a/include/asm-powerpc/spu.h b/include/asm-powerpc/spu.h index 8564b8234069..f431d8b0b651 100644 --- a/include/asm-powerpc/spu.h +++ b/include/asm-powerpc/spu.h @@ -110,6 +110,7 @@ struct spu { char *name; unsigned long local_store_phys; u8 *local_store; + unsigned long problem_phys; struct spu_problem __iomem *problem; struct spu_priv1 __iomem *priv1; struct spu_priv2 __iomem *priv2; -- cgit v1.2.3