diff options
| -rw-r--r-- | Documentation/filesystems/spufs.txt | 521 | ||||
| -rw-r--r-- | arch/powerpc/Kconfig | 1 | ||||
| -rw-r--r-- | arch/powerpc/kernel/systbl.S | 2 | ||||
| -rw-r--r-- | arch/powerpc/mm/hash_utils_64.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/Kconfig | 13 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/Makefile | 3 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spu_base.c | 740 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spu_syscalls.c | 86 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spufs/Makefile | 3 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spufs/context.c | 67 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spufs/file.c | 596 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spufs/inode.c | 470 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spufs/spufs.h | 71 | ||||
| -rw-r--r-- | arch/powerpc/platforms/cell/spufs/syscalls.c | 106 | ||||
| -rw-r--r-- | arch/ppc/kernel/ppc_ksyms.c | 1 | ||||
| -rw-r--r-- | include/asm-powerpc/spu.h | 498 | ||||
| -rw-r--r-- | include/asm-powerpc/unistd.h | 2 | ||||
| -rw-r--r-- | include/linux/syscalls.h | 5 | ||||
| -rw-r--r-- | kernel/sys_ni.c | 2 | ||||
| -rw-r--r-- | mm/memory.c | 2 |
20 files changed, 3189 insertions, 1 deletions
diff --git a/Documentation/filesystems/spufs.txt b/Documentation/filesystems/spufs.txt new file mode 100644 index 000000000000..8edc3952eff4 --- /dev/null +++ b/Documentation/filesystems/spufs.txt @@ -0,0 +1,521 @@ +SPUFS(2) Linux Programmer's Manual SPUFS(2) + + + +NAME + spufs - the SPU file system + + +DESCRIPTION + The SPU file system is used on PowerPC machines that implement the Cell + Broadband Engine Architecture in order to access Synergistic Processor + Units (SPUs). + + The file system provides a name space similar to posix shared memory or + message queues. Users that have write permissions on the file system + can use spu_create(2) to establish SPU contexts in the spufs root. + + Every SPU context is represented by a directory containing a predefined + set of files. These files can be used for manipulating the state of the + logical SPU. Users can change permissions on those files, but not actu- + ally add or remove files. + + +MOUNT OPTIONS + uid=<uid> + set the user owning the mount point, the default is 0 (root). + + gid=<gid> + set the group owning the mount point, the default is 0 (root). + + +FILES + The files in spufs mostly follow the standard behavior for regular sys- + tem calls like read(2) or write(2), but often support only a subset of + the operations supported on regular file systems. This list details the + supported operations and the deviations from the behaviour in the + respective man pages. + + All files that support the read(2) operation also support readv(2) and + all files that support the write(2) operation also support writev(2). + All files support the access(2) and stat(2) family of operations, but + only the st_mode, st_nlink, st_uid and st_gid fields of struct stat + contain reliable information. + + All files support the chmod(2)/fchmod(2) and chown(2)/fchown(2) opera- + tions, but will not be able to grant permissions that contradict the + possible operations, e.g. read access on the wbox file. + + The current set of files is: + + + /mem + the contents of the local storage memory of the SPU. This can be + accessed like a regular shared memory file and contains both code and + data in the address space of the SPU. The possible operations on an + open mem file are: + + read(2), pread(2), write(2), pwrite(2), lseek(2) + These operate as documented, with the exception that seek(2), + write(2) and pwrite(2) are not supported beyond the end of the + file. The file size is the size of the local storage of the SPU, + which normally is 256 kilobytes. + + mmap(2) + Mapping mem into the process address space gives access to the + SPU local storage within the process address space. Only + MAP_SHARED mappings are allowed. + + + /mbox + The first SPU to CPU communication mailbox. This file is read-only and + can be read in units of 32 bits. The file can only be used in non- + blocking mode and it even poll() will not block on it. The possible + operations on an open mbox file are: + + read(2) + If a count smaller than four is requested, read returns -1 and + sets errno to EINVAL. If there is no data available in the mail + box, the return value is set to -1 and errno becomes EAGAIN. + When data has been read successfully, four bytes are placed in + the data buffer and the value four is returned. + + + /ibox + The second SPU to CPU communication mailbox. This file is similar to + the first mailbox file, but can be read in blocking I/O mode, and the + poll familiy of system calls can be used to wait for it. The possible + operations on an open ibox file are: + + read(2) + If a count smaller than four is requested, read returns -1 and + sets errno to EINVAL. If there is no data available in the mail + box and the file descriptor has been opened with O_NONBLOCK, the + return value is set to -1 and errno becomes EAGAIN. + + If there is no data available in the mail box and the file + descriptor has been opened without O_NONBLOCK, the call will + block until the SPU writes to its interrupt mailbox channel. + When data has been read successfully, four bytes are placed in + the data buffer and the value four is returned. + + poll(2) + Poll on the ibox file returns (POLLIN | POLLRDNORM) whenever + data is available for reading. + + + /wbox + The CPU to SPU communation mailbox. It is write-only can can be written + in units of 32 bits. If the mailbox is full, write() will block and + poll can be used to wait for it becoming empty again. The possible + operations on an open wbox file are: write(2) If a count smaller than + four is requested, write returns -1 and sets errno to EINVAL. If there + is no space available in the mail box and the file descriptor has been + opened with O_NONBLOCK, the return value is set to -1 and errno becomes + EAGAIN. + + If there is no space available in the mail box and the file descriptor + has been opened without O_NONBLOCK, the call will block until the SPU + reads from its PPE mailbox channel. When data has been read success- + fully, four bytes are placed in the data buffer and the value four is + returned. + + poll(2) + Poll on the ibox file returns (POLLOUT | POLLWRNORM) whenever + space is available for writing. + + + /mbox_stat + /ibox_stat + /wbox_stat + Read-only files that contain the length of the current queue, i.e. how + many words can be read from mbox or ibox or how many words can be + written to wbox without blocking. The files can be read only in 4-byte + units and return a big-endian binary integer number. The possible + operations on an open *box_stat file are: + + read(2) + If a count smaller than four is requested, read returns -1 and + sets errno to EINVAL. Otherwise, a four byte value is placed in + the data buffer, containing the number of elements that can be + read from (for mbox_stat and ibox_stat) or written to (for + wbox_stat) the respective mail box without blocking or resulting + in EAGAIN. + + + /npc + /decr + /decr_status + /spu_tag_mask + /event_mask + /srr0 + Internal registers of the SPU. The representation is an ASCII string + with the numeric value of the next instruction to be executed. These + can be used in read/write mode for debugging, but normal operation of + programs should not rely on them because access to any of them except + npc requires an SPU context save and is therefore very inefficient. + + The contents of these files are: + + npc Next Program Counter + + decr SPU Decrementer + + decr_status Decrementer Status + + spu_tag_mask MFC tag mask for SPU DMA + + event_mask Event mask for SPU interrupts + + srr0 Interrupt Return address register + + + The possible operations on an open npc, decr, decr_status, + spu_tag_mask, event_mask or srr0 file are: + + read(2) + When the count supplied to the read call is shorter than the + required length for the pointer value plus a newline character, + subsequent reads from the same file descriptor will result in + completing the string, regardless of changes to the register by + a running SPU task. When a complete string has been read, all + subsequent read operations will return zero bytes and a new file + descriptor needs to be opened to read the value again. + + write(2) + A write operation on the file results in setting the register to + the value given in the string. The string is parsed from the + beginning to the first non-numeric character or the end of the + buffer. Subsequent writes to the same file descriptor overwrite + the previous setting. + + + /fpcr + This file gives access to the Floating Point Status and Control Regis- + ter as a four byte long file. The operations on the fpcr file are: + + read(2) + If a count smaller than four is requested, read returns -1 and + sets errno to EINVAL. Otherwise, a four byte value is placed in + the data buffer, containing the current value of the fpcr regis- + ter. + + write(2) + If a count smaller than four is requested, write returns -1 and + sets errno to EINVAL. Otherwise, a four byte value is copied + from the data buffer, updating the value of the fpcr register. + + + /signal1 + /signal2 + The two signal notification channels of an SPU. These are read-write + files that operate on a 32 bit word. Writing to one of these files + triggers an interrupt on the SPU. The value writting to the signal + files can be read from the SPU through a channel read or from host user + space through the file. After the value has been read by the SPU, it + is reset to zero. The possible operations on an open signal1 or sig- + nal2 file are: + + read(2) + If a count smaller than four is requested, read returns -1 and + sets errno to EINVAL. Otherwise, a four byte value is placed in + the data buffer, containing the current value of the specified + signal notification register. + + write(2) + If a count smaller than four is requested, write returns -1 and + sets errno to EINVAL. Otherwise, a four byte value is copied + from the data buffer, updating the value of the specified signal + notification register. The signal notification register will + either be replaced with the input data or will be updated to the + bitwise OR or the old value and the input data, depending on the + contents of the signal1_type, or signal2_type respectively, + file. + + + /signal1_type + /signal2_type + These two files change the behavior of the signal1 and signal2 notifi- + cation files. The contain a numerical ASCII string which is read as + either "1" or "0". In mode 0 (overwrite), the hardware replaces the + contents of the signal channel with the data that is written to it. in + mode 1 (logical OR), the hardware accumulates the bits that are subse- + quently written to it. The possible operations on an open signal1_type + or signal2_type file are: + + read(2) + When the count supplied to the read call is shorter than the + required length for the digit plus a newline character, subse- + quent reads from the same file descriptor will result in com- + pleting the string. When a complete string has been read, all + subsequent read operations will return zero bytes and a new file + descriptor needs to be opened to read the value again. + + write(2) + A write operation on the file results in setting the register to + the value given in the string. The string is parsed from the + beginning to the first non-numeric character or the end of the + buffer. Subsequent writes to the same file descriptor overwrite + the previous setting. + + +EXAMPLES + /etc/fstab entry + none /spu spufs gid=spu 0 0 + + +AUTHORS + Arnd Bergmann <arndb@de.ibm.com>, Mark Nutter <mnutter@us.ibm.com>, + Ulrich Weigand <Ulrich.Weigand@de.ibm.com> + +SEE ALSO + capabilities(7), close(2), spu_create(2), spu_run(2), spufs(7) + + + +Linux 2005-09-28 SPUFS(2) + +------------------------------------------------------------------------------ + +SPU_RUN(2) Linux Programmer's Manual SPU_RUN(2) + + + +NAME + spu_run - execute an spu context + + +SYNOPSIS + #include <sys/spu.h> + + int spu_run(int fd, unsigned int *npc, unsigned int *event); + +DESCRIPTION + The spu_run system call is used on PowerPC machines that implement the + Cell Broadband Engine Architecture in order to access Synergistic Pro- + cessor Units (SPUs). It uses the fd that was returned from spu_cre- + ate(2) to address a specific SPU context. When the context gets sched- + uled to a physical SPU, it starts execution at the instruction pointer + passed in npc. + + Execution of SPU code happens synchronously, meaning that spu_run does + not return while the SPU is still running. If there is a need to exe- + cute SPU code in parallel with other code on either the main CPU or + other SPUs, you need to create a new thread of execution first, e.g. + using the pthread_create(3) call. + + When spu_run returns, the current value of the SPU instruction pointer + is written back to npc, so you can call spu_run again without updating + the pointers. + + event can be a NULL pointer or point to an extended status code that + gets filled when spu_run returns. It can be one of the following con- + stants: + + SPE_EVENT_DMA_ALIGNMENT + A DMA alignment error + + SPE_EVENT_SPE_DATA_SEGMENT + A DMA segmentation error + + SPE_EVENT_SPE_DATA_STORAGE + A DMA storage error + + If NULL is passed as the event argument, these errors will result in a + signal delivered to the calling process. + +RETURN VALUE + spu_run returns the value of the spu_status register or -1 to indicate + an error and set errno to one of the error codes listed below. The + spu_status register value contains a bit mask of status codes and + optionally a 14 bit code returned from the stop-and-signal instruction + on the SPU. The bit masks for the status codes are: + + 0x02 SPU was stopped by stop-and-signal. + + 0x04 SPU was stopped by halt. + + 0x08 SPU is waiting for a channel. + + 0x10 SPU is in single-step mode. + + 0x20 SPU has tried to execute an invalid instruction. + + 0x40 SPU has tried to access an invalid channel. + + 0x3fff0000 + The bits masked with this value contain the code returned from + stop-and-signal. + + There are always one or more of the lower eight bits set or an error + code is returned from spu_run. + +ERRORS + EAGAIN or EWOULDBLOCK + fd is in non-blocking mode and spu_run would block. + + EBADF fd is not a valid file descriptor. + + EFAULT npc is not a valid pointer or status is neither NULL nor a valid + pointer. + + EINTR A signal occured while spu_run was in progress. The npc value + has been updated to the new program counter value if necessary. + + EINVAL fd is not a file descriptor returned from spu_create(2). + + ENOMEM Insufficient memory was available to handle a page fault result- + ing from an MFC direct memory access. + + ENOSYS the functionality is not provided by the current system, because + either the hardware does not provide SPUs or the spufs module is + not loaded. + + +NOTES + spu_run is meant to be used from libraries that implement a more + abstract interface to SPUs, not to be used from regular applications. + See http://www.bsc.es/projects/deepcomputing/linuxoncell/ for the rec- + ommended libraries. + + +CONFORMING TO + This call is Linux specific and only implemented by the ppc64 architec- + ture. Programs using this system call are not portable. + + +BUGS + The code does not yet fully implement all features lined out here. + + +AUTHOR + Arnd Bergmann <arndb@de.ibm.com> + +SEE ALSO + capabilities(7), close(2), spu_create(2), spufs(7) + + + +Linux 2005-09-28 SPU_RUN(2) + +------------------------------------------------------------------------------ + +SPU_CREATE(2) Linux Programmer's Manual SPU_CREATE(2) + + + +NAME + spu_create - create a new spu context + + +SYNOPSIS + #include <sys/types.h> + #include <sys/spu.h> + + int spu_create(const char *pathname, int flags, mode_t mode); + +DESCRIPTION + The spu_create system call is used on PowerPC machines that implement + the Cell Broadband Engine Architecture in order to access Synergistic + Processor Units (SPUs). It creates a new logical context for an SPU in + pathname and returns a handle to associated with it. pathname must + point to a non-existing directory in the mount point of the SPU file + system (spufs). When spu_create is successful, a directory gets cre- + ated on pathname and it is populated with files. + + The returned file handle can only be passed to spu_run(2) or closed, + other operations are not defined on it. When it is closed, all associ- + ated directory entries in spufs are removed. When the last file handle + pointing either inside of the context directory or to this file + descriptor is closed, the logical SPU context is destroyed. + + The parameter flags can be zero or any bitwise or'd combination of the + following constants: + + SPU_RAWIO + Allow mapping of some of the hardware registers of the SPU into + user space. This flag requires the CAP_SYS_RAWIO capability, see + capabilities(7). + + The mode parameter specifies the permissions used for creating the new + directory in spufs. mode is modified with the user's umask(2) value + and then used for both the directory and the files contained in it. The + file permissions mask out some more bits of mode because they typically + support only read or write access. See stat(2) for a full list of the + possible mode values. + + +RETURN VALUE + spu_create returns a new file descriptor. It may return -1 to indicate + an error condition and set errno to one of the error codes listed + below. + + +ERRORS + EACCESS + The current user does not have write access on the spufs mount + point. + + EEXIST An SPU context already exists at the given path name. + + EFAULT pathname is not a valid string pointer in the current address + space. + + EINVAL pathname is not a directory in the spufs mount point. + + ELOOP Too many symlinks were found while resolving pathname. + + EMFILE The process has reached its maximum open file limit. + + ENAMETOOLONG + pathname was too long. + + ENFILE The system has reached the global open file limit. + + ENOENT Part of pathname could not be resolved. + + ENOMEM The kernel could not allocate all resources required. + + ENOSPC There are not enough SPU resources available to create a new + context or the user specific limit for the number of SPU con- + texts has been reached. + + ENOSYS the functionality is not provided by the current system, because + either the hardware does not provide SPUs or the spufs module is + not loaded. + + ENOTDIR + A part of pathname is not a directory. + + + +NOTES + spu_create is meant to be used from libraries that implement a more + abstract interface to SPUs, not to be used from regular applications. + See http://www.bsc.es/projects/deepcomputing/linuxoncell/ for the rec- + ommended libraries. + + +FILES + pathname must point to a location beneath the mount point of spufs. By + convention, it gets mounted in /spu. + + +CONFORMING TO + This call is Linux specific and only implemented by the ppc64 architec- + ture. Programs using this system call are not portable. + + +BUGS + The code does not yet fully implement all features lined out here. + + +AUTHOR + Arnd Bergmann <arndb@de.ibm.com> + +SEE ALSO + capabilities(7), close(2), spu_run(2), spufs(7) + + + +Linux 2005-09-28 SPU_CREATE(2) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 4d71aa3ecbb5..39ca7b9da369 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -482,6 +482,7 @@ source arch/powerpc/platforms/embedded6xx/Kconfig source arch/powerpc/platforms/4xx/Kconfig source arch/powerpc/platforms/85xx/Kconfig source arch/powerpc/platforms/8xx/Kconfig +source arch/powerpc/platforms/cell/Kconfig menu "Kernel options" diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 4bb3650420b4..989f6286991a 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -319,3 +319,5 @@ COMPAT_SYS(ioprio_get) SYSCALL(inotify_init) SYSCALL(inotify_add_watch) SYSCALL(inotify_rm_watch) +SYSCALL(spu_run) +SYSCALL(spu_create) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index a606504678bd..846a1894cf95 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -644,6 +644,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) DBG_LOW(" -> rc=%d\n", rc); return rc; } +EXPORT_SYMBOL_GPL(hash_page); void hash_preload(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap) diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig new file mode 100644 index 000000000000..3157071e241c --- /dev/null +++ b/arch/powerpc/platforms/cell/Kconfig @@ -0,0 +1,13 @@ +menu "Cell Broadband Engine options" + depends on PPC_CELL + +config SPU_FS + tristate "SPU file system" + default m + depends on PPC_CELL + help + The SPU file system is used to access Synergistic Processing + Units on machines implementing the Broadband Processor + Architecture. + +endmenu diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index 55e094b96bc0..74616cf13af9 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -1,2 +1,5 @@ obj-y += interrupt.o iommu.o setup.o spider-pic.o obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_SPU_FS) += spufs/ spu_base.o +builtin-spufs-$(CONFIG_SPU_FS) += spu_syscalls.o +obj-y += $(builtin-spufs-m) diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c new file mode 100644 index 000000000000..9e9096590a07 --- /dev/null +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -0,0 +1,740 @@ +/* + * Low-level SPU handling + * + * (C) Copyright IBM Deutschland Entwicklung GmbH 2005 + * + * Author: Arnd Bergmann <arndb@de.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#define DEBUG 1 + +#include <linux/interrupt.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/poll.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/wait.h> + +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/semaphore.h> +#include <asm/spu.h> +#include <asm/mmu_context.h> + +#include "interrupt.h" + +static int __spu_trap_invalid_dma(struct spu *spu) +{ + pr_debug("%s\n", __FUNCTION__); + force_sig(SIGBUS, /* info, */ current); + return 0; +} + +static int __spu_trap_dma_align(struct spu *spu) +{ + pr_debug("%s\n", __FUNCTION__); + force_sig(SIGBUS, /* info, */ current); + return 0; +} + +static int __spu_trap_error(struct spu *spu) +{ + pr_debug("%s\n", __FUNCTION__); + force_sig(SIGILL, /* info, */ current); + return 0; +} + +static void spu_restart_dma(struct spu *spu) +{ + struct spu_priv2 __iomem *priv2 = spu->priv2; + out_be64(&priv2->mfc_control_RW, MFC_CNTL_RESTART_DMA_COMMAND); +} + +static int __spu_trap_data_seg(struct spu *spu, unsigned long ea) +{ + struct spu_priv2 __iomem *priv2; + struct mm_struct *mm; + + pr_debug("%s\n", __FUNCTION__); + + if (REGION_ID(ea) != USER_REGION_ID) { + pr_debug("invalid region access at %016lx\n", ea); + return 1; + } + + priv2 = spu->priv2; + mm = spu->mm; + + if (spu->slb_replace >= 8) + spu->slb_replace = 0; + + out_be64(&priv2->slb_index_W, spu->slb_replace); + out_be64(&priv2->slb_vsid_RW, + (get_vsid(mm->context.id, ea) << SLB_VSID_SHIFT) + | SLB_VSID_USER); + out_be64(&priv2->slb_esid_RW, (ea & ESID_MASK) | SLB_ESID_V); + + spu_restart_dma(spu); + + pr_debug("set slb %d context %lx, ea %016lx, vsid %016lx, esid %016lx\n", + spu->slb_replace, mm->context.id, ea, + (get_vsid(mm->context.id, ea) << SLB_VSID_SHIFT)| SLB_VSID_USER, + (ea & ESID_MASK) | SLB_ESID_V); + return 0; +} + +static int __spu_trap_data_map(struct spu *spu, unsigned long ea) +{ + unsigned long dsisr; + struct spu_priv1 __iomem *priv1; + + pr_debug("%s\n", __FUNCTION__); + priv1 = spu->priv1; + dsisr = in_be64(&priv1->mfc_dsisr_RW); + + wake_up(&spu->stop_wq); + + return 0; +} + +static int __spu_trap_mailbox(struct spu *spu) +{ + wake_up_all(&spu->ibox_wq); + kill_fasync(&spu->ibox_fasync, SIGIO, POLLIN); + + /* atomically disable SPU mailbox interrupts */ + spin_lock(&spu->register_lock); + out_be64(&spu->priv1->int_mask_class2_RW, + in_be64(&spu->priv1->int_mask_class2_RW) & ~0x1); + spin_unlock(&spu->register_lock); + return 0; +} + +static int __spu_trap_stop(struct spu *spu) +{ + pr_debug("%s\n", __FUNCTION__); + spu->stop_code = in_be32(&spu->problem->spu_status_R); + wake_up(&spu->stop_wq); + return 0; +} + +static int __spu_trap_halt(struct spu *spu) +{ + pr_debug("%s\n", __FUNCTION__); + spu->stop_code = in_be32(&spu->problem->spu_status_R); + wake_up(&spu->stop_wq); + return 0; +} + +static int __spu_trap_tag_group(struct spu *spu) +{ + pr_debug("%s\n", __FUNCTION__); + /* wake_up(&spu->dma_wq); */ + return 0; +} + +static int __spu_trap_spubox(struct spu *spu) +{ + wake_up_all(&spu->wbox_wq); + kill_fasync(&spu->wbox_fasync, SIGIO, POLLOUT); + + /* atomically disable SPU mailbox interrupts */ + spin_lock(&spu->register_lock); + out_be64(&spu->priv1->int_mask_class2_RW, + in_be64(&spu->priv1->int_mask_class2_RW) & ~0x10); + spin_unlock(&spu->register_lock); + return 0; +} + +static irqreturn_t +spu_irq_class_0(int irq, void *data, struct pt_regs *regs) +{ + struct spu *spu; + + spu = data; + spu->class_0_pending = 1; + wake_up(&spu->stop_wq); + + return IRQ_HANDLED; +} + +static int +spu_irq_class_0_bottom(struct spu *spu) +{ + unsigned long stat; + + spu->class_0_pending = 0; + + stat = in_be64(&spu->priv1->int_stat_class0_RW); + + if (stat & 1) /* invalid MFC DMA */ + __spu_trap_invalid_dma(spu); + + if (stat & 2) /* invalid DMA alignment */ + __spu_trap_dma_align(spu); + + if (stat & 4) /* error on SPU */ + __spu_trap_error(spu); + + out_be64(&spu->priv1->int_stat_class0_RW, stat); + return 0; +} + +static irqreturn_t +spu_irq_class_1(int irq, void *data, struct pt_regs *regs) +{ + struct spu *spu; + unsigned long stat, dar; + + spu = data; + stat = in_be64(&spu->priv1->int_stat_class1_RW); + dar = in_be64(&spu->priv1->mfc_dar_RW); + + if (stat & 1) /* segment fault */ + __spu_trap_data_seg(spu, dar); + + if (stat & 2) { /* mapping fault */ + __spu_trap_data_map(spu, dar); + } + + if (stat & 4) /* ls compare & suspend on get */ + ; + + if (stat & 8) /* ls compare & suspend on put */ + ; + + out_be64(&spu->priv1->int_stat_class1_RW, stat); + return stat ? IRQ_HANDLED : IRQ_NONE; +} + +static irqreturn_t +spu_irq_class_2(int irq, void *data, struct pt_regs *regs) +{ + struct spu *spu; + unsigned long stat; + + spu = data; + stat = in_be64(&spu->priv1->int_stat_class2_RW); + + pr_debug("class 2 interrupt %d, %lx, %lx\n", irq, stat, + in_be64(&spu->priv1->int_mask_class2_RW)); + + + if (stat & 1) /* PPC core mailbox */ + __spu_trap_mailbox(spu); + + if (stat & 2) /* SPU stop-and-signal */ + __spu_trap_stop(spu); + + if (stat & 4) /* SPU halted */ + __spu_trap_halt(spu); + + if (stat & 8) /* DMA tag group complete */ + __spu_trap_tag_group(spu); + + if (stat & 0x10) /* SPU mailbox threshold */ + __spu_trap_spubox(spu); + + out_be64(&spu->priv1->int_stat_class2_RW, stat); + return stat ? IRQ_HANDLED : IRQ_NONE; +} + +static int +spu_request_irqs(struct spu *spu) +{ + int ret; + int irq_base; + + irq_base = IIC_NODE_STRIDE * spu->node + IIC_SPE_OFFSET; + + snprintf(spu->irq_c0, sizeof (spu->irq_c0), "spe%02d.0", spu->number); + ret = request_irq(irq_base + spu->isrc, + spu_irq_class_0, 0, spu->irq_c0, spu); + if (ret) + goto out; + out_be64(&spu->priv1->int_mask_class0_RW, 0x7); + + snprintf(spu->irq_c1, sizeof (spu->irq_c1), "spe%02d.1", spu->number); + ret = request_irq(irq_base + IIC_CLASS_STRIDE + spu->isrc, + spu_irq_class_1, 0, spu->irq_c1, spu); + if (ret) + goto out1; + out_be64(&spu->priv1->int_mask_class1_RW, 0x3); + + snprintf(spu->irq_c2, sizeof (spu->irq_c2), "spe%02d.2", spu->number); + ret = request_irq(irq_base + 2*IIC_CLASS_STRIDE + spu->isrc, + spu_irq_class_2, 0, spu->irq_c2, spu); + if (ret) + goto out2; + out_be64(&spu->priv1->int_mask_class2_RW, 0xe); + goto out; + +out2: + free_irq(irq_base + IIC_CLASS_STRIDE + spu->isrc, spu); +out1: + free_irq(irq_base + spu->isrc, spu); +out: + return ret; +} + +static void +spu_free_irqs(struct spu *spu) +{ + int irq_base; + + irq_base = IIC_NODE_STRIDE * spu->node + IIC_SPE_OFFSET; + + free_irq(irq_base + spu->isrc, spu); + free_irq(irq_base + IIC_CLASS_STRIDE + spu->isrc, spu); + free_irq(irq_base + 2*IIC_CLASS_STRIDE + spu->isrc, spu); +} + +static LIST_HEAD(spu_list); +static DECLARE_MUTEX(spu_mutex); + +static void spu_init_channels(struct spu *spu) +{ |