X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=drivers%2Finfiniband%2Fhw%2Fipath%2Fipath_file_ops.c;h=7e025c8e01b6d9d1efe6bc0e787061159b1b1380;hb=d870ec7281d8429ab17d2e0324f4d8ca3f3de62d;hp=1272aaf2a78543f86fa9288e7cf85e2426ead2be;hpb=4f7a307dc6e4d8bfeb56f7cf7231b08cb845687c;p=linux-2.6 diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c index 1272aaf2a7..7e025c8e01 100644 --- a/drivers/infiniband/hw/ipath/ipath_file_ops.c +++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c @@ -169,7 +169,7 @@ static int ipath_get_base_info(struct file *fp, kinfo->spi_piocnt = dd->ipath_pbufsport; kinfo->spi_piobufbase = (u64) pd->port_piobufs; kinfo->__spi_uregbase = (u64) dd->ipath_uregbase + - dd->ipath_palign * pd->port_port; + dd->ipath_ureg_align * pd->port_port; } else if (master) { kinfo->spi_piocnt = (dd->ipath_pbufsport / subport_cnt) + (dd->ipath_pbufsport % subport_cnt); @@ -186,7 +186,7 @@ static int ipath_get_base_info(struct file *fp, } if (shared) { kinfo->spi_port_uregbase = (u64) dd->ipath_uregbase + - dd->ipath_palign * pd->port_port; + dd->ipath_ureg_align * pd->port_port; kinfo->spi_port_rcvegrbuf = kinfo->spi_rcv_egrbufs; kinfo->spi_port_rcvhdr_base = kinfo->spi_rcvhdr_base; kinfo->spi_port_rcvhdr_tailaddr = kinfo->spi_rcvhdr_tailaddr; @@ -396,7 +396,8 @@ static int ipath_tid_update(struct ipath_portdata *pd, struct file *fp, "TID %u, vaddr %lx, physaddr %llx pgp %p\n", tid, vaddr, (unsigned long long) physaddr, pagep[i]); - dd->ipath_f_put_tid(dd, &tidbase[tid], 1, physaddr); + dd->ipath_f_put_tid(dd, &tidbase[tid], RCVHQ_RCV_TYPE_EXPECTED, + physaddr); /* * don't check this tid in ipath_portshadow, since we * just filled it in; start with the next one. @@ -422,7 +423,8 @@ static int ipath_tid_update(struct ipath_portdata *pd, struct file *fp, if (dd->ipath_pageshadow[porttid + tid]) { ipath_cdbg(VERBOSE, "Freeing TID %u\n", tid); - dd->ipath_f_put_tid(dd, &tidbase[tid], 1, + dd->ipath_f_put_tid(dd, &tidbase[tid], + RCVHQ_RCV_TYPE_EXPECTED, dd->ipath_tidinvalid); pci_unmap_page(dd->pcidev, dd->ipath_physshadow[porttid + tid], @@ -536,16 +538,18 @@ static int ipath_tid_free(struct ipath_portdata *pd, unsigned subport, continue; cnt++; if (dd->ipath_pageshadow[porttid + tid]) { + struct page *p; + p = dd->ipath_pageshadow[porttid + tid]; + dd->ipath_pageshadow[porttid + tid] = NULL; ipath_cdbg(VERBOSE, "PID %u freeing TID %u\n", pd->port_pid, tid); - dd->ipath_f_put_tid(dd, &tidbase[tid], 1, + dd->ipath_f_put_tid(dd, &tidbase[tid], + RCVHQ_RCV_TYPE_EXPECTED, dd->ipath_tidinvalid); pci_unmap_page(dd->pcidev, dd->ipath_physshadow[porttid + tid], PAGE_SIZE, PCI_DMA_FROMDEVICE); - ipath_release_user_pages( - &dd->ipath_pageshadow[porttid + tid], 1); - dd->ipath_pageshadow[porttid + tid] = NULL; + ipath_release_user_pages(&p, 1); ipath_stats.sps_pageunlocks++; } else ipath_dbg("Unused tid %u, ignoring\n", tid); @@ -738,11 +742,12 @@ static int ipath_manage_rcvq(struct ipath_portdata *pd, unsigned subport, * updated and correct itself, even in the face of software * bugs. */ - *(volatile u64 *)pd->port_rcvhdrtail_kvaddr = 0; - set_bit(INFINIPATH_R_PORTENABLE_SHIFT + pd->port_port, + if (pd->port_rcvhdrtail_kvaddr) + ipath_clear_rcvhdrtail(pd); + set_bit(dd->ipath_r_portenable_shift + pd->port_port, &dd->ipath_rcvctrl); } else - clear_bit(INFINIPATH_R_PORTENABLE_SHIFT + pd->port_port, + clear_bit(dd->ipath_r_portenable_shift + pd->port_port, &dd->ipath_rcvctrl); ipath_write_kreg(dd, dd->ipath_kregs->kr_rcvctrl, dd->ipath_rcvctrl); @@ -877,7 +882,7 @@ static int ipath_create_user_egr(struct ipath_portdata *pd) egrcnt = dd->ipath_rcvegrcnt; /* TID number offset for this port */ - egroff = pd->port_port * egrcnt; + egroff = (pd->port_port - 1) * egrcnt + dd->ipath_p0_rcvegrcnt; egrsize = dd->ipath_rcvegrbufsize; ipath_cdbg(VERBOSE, "Allocating %d egr buffers, at egrtid " "offset %x, egrsize %u\n", egrcnt, egroff, egrsize); @@ -921,7 +926,8 @@ static int ipath_create_user_egr(struct ipath_portdata *pd) (u64 __iomem *) ((char __iomem *) dd->ipath_kregbase + - dd->ipath_rcvegrbase), 0, pa); + dd->ipath_rcvegrbase), + RCVHQ_RCV_TYPE_EAGER, pa); pa += egrsize; } cond_resched(); /* don't hog the cpu */ @@ -1044,11 +1050,6 @@ static int mmap_piobufs(struct vm_area_struct *vma, phys = dd->ipath_physaddr + piobufs; - /* - * Don't mark this as non-cached, or we don't get the - * write combining behavior we want on the PIO buffers! - */ - #if defined(__powerpc__) /* There isn't a generic way to specify writethrough mappings */ pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE; @@ -1115,33 +1116,24 @@ bail: } /* - * ipath_file_vma_nopage - handle a VMA page fault. + * ipath_file_vma_fault - handle a VMA page fault. */ -static struct page *ipath_file_vma_nopage(struct vm_area_struct *vma, - unsigned long address, int *type) +static int ipath_file_vma_fault(struct vm_area_struct *vma, + struct vm_fault *vmf) { - unsigned long offset = address - vma->vm_start; - struct page *page = NOPAGE_SIGBUS; - void *pageptr; + struct page *page; - /* - * Convert the vmalloc address into a struct page. - */ - pageptr = (void *)(offset + (vma->vm_pgoff << PAGE_SHIFT)); - page = vmalloc_to_page(pageptr); + page = vmalloc_to_page((void *)(vmf->pgoff << PAGE_SHIFT)); if (!page) - goto out; - - /* Increment the reference count. */ + return VM_FAULT_SIGBUS; get_page(page); - if (type) - *type = VM_FAULT_MINOR; -out: - return page; + vmf->page = page; + + return 0; } static struct vm_operations_struct ipath_file_vm_ops = { - .nopage = ipath_file_vma_nopage, + .fault = ipath_file_vma_fault, }; static int mmap_kvaddr(struct vm_area_struct *vma, u64 pgaddr, @@ -1279,7 +1271,7 @@ static int ipath_mmap(struct file *fp, struct vm_area_struct *vma) goto bail; } - ureg = dd->ipath_uregbase + dd->ipath_palign * pd->port_port; + ureg = dd->ipath_uregbase + dd->ipath_ureg_align * pd->port_port; if (!pd->port_subport_cnt) { /* port is not shared */ piocnt = dd->ipath_pbufsport; @@ -1337,68 +1329,143 @@ bail: return ret; } -static unsigned int ipath_poll(struct file *fp, - struct poll_table_struct *pt) +static unsigned ipath_poll_hdrqfull(struct ipath_portdata *pd) +{ + unsigned pollflag = 0; + + if ((pd->poll_type & IPATH_POLL_TYPE_OVERFLOW) && + pd->port_hdrqfull != pd->port_hdrqfull_poll) { + pollflag |= POLLIN | POLLRDNORM; + pd->port_hdrqfull_poll = pd->port_hdrqfull; + } + + return pollflag; +} + +static unsigned int ipath_poll_urgent(struct ipath_portdata *pd, + struct file *fp, + struct poll_table_struct *pt) { - struct ipath_portdata *pd; - u32 head, tail; - int bit; unsigned pollflag = 0; struct ipath_devdata *dd; - pd = port_fp(fp); - if (!pd) - goto bail; dd = pd->port_dd; - bit = pd->port_port + INFINIPATH_R_INTRAVAIL_SHIFT; - set_bit(bit, &dd->ipath_rcvctrl); + /* variable access in ipath_poll_hdrqfull() needs this */ + rmb(); + pollflag = ipath_poll_hdrqfull(pd); - /* - * Before blocking, make sure that head is still == tail, - * reading from the chip, so we can be sure the interrupt - * enable has made it to the chip. If not equal, disable - * interrupt again and return immediately. This avoids races, - * and the overhead of the chip read doesn't matter much at - * this point, since we are waiting for something anyway. - */ + if (pd->port_urgent != pd->port_urgent_poll) { + pollflag |= POLLIN | POLLRDNORM; + pd->port_urgent_poll = pd->port_urgent; + } - ipath_write_kreg(dd, dd->ipath_kregs->kr_rcvctrl, - dd->ipath_rcvctrl); + if (!pollflag) { + /* this saves a spin_lock/unlock in interrupt handler... */ + set_bit(IPATH_PORT_WAITING_URG, &pd->port_flag); + /* flush waiting flag so don't miss an event... */ + wmb(); + poll_wait(fp, &pd->port_wait, pt); + } + + return pollflag; +} + +static unsigned int ipath_poll_next(struct ipath_portdata *pd, + struct file *fp, + struct poll_table_struct *pt) +{ + u32 head; + u32 tail; + unsigned pollflag = 0; + struct ipath_devdata *dd; + + dd = pd->port_dd; + + /* variable access in ipath_poll_hdrqfull() needs this */ + rmb(); + pollflag = ipath_poll_hdrqfull(pd); head = ipath_read_ureg32(dd, ur_rcvhdrhead, pd->port_port); - tail = ipath_read_ureg32(dd, ur_rcvhdrtail, pd->port_port); + if (pd->port_rcvhdrtail_kvaddr) + tail = ipath_get_rcvhdrtail(pd); + else + tail = ipath_read_ureg32(dd, ur_rcvhdrtail, pd->port_port); - if (tail == head) { + if (head != tail) + pollflag |= POLLIN | POLLRDNORM; + else { + /* this saves a spin_lock/unlock in interrupt handler */ set_bit(IPATH_PORT_WAITING_RCV, &pd->port_flag); + /* flush waiting flag so we don't miss an event */ + wmb(); + + set_bit(pd->port_port + dd->ipath_r_intravail_shift, + &dd->ipath_rcvctrl); + + ipath_write_kreg(dd, dd->ipath_kregs->kr_rcvctrl, + dd->ipath_rcvctrl); + if (dd->ipath_rhdrhead_intr_off) /* arm rcv interrupt */ - (void)ipath_write_ureg(dd, ur_rcvhdrhead, - dd->ipath_rhdrhead_intr_off - | head, pd->port_port); - poll_wait(fp, &pd->port_wait, pt); + ipath_write_ureg(dd, ur_rcvhdrhead, + dd->ipath_rhdrhead_intr_off | head, + pd->port_port); - if (test_bit(IPATH_PORT_WAITING_RCV, &pd->port_flag)) { - /* timed out, no packets received */ - clear_bit(IPATH_PORT_WAITING_RCV, &pd->port_flag); - pd->port_rcvwait_to++; - } - else - pollflag = POLLIN | POLLRDNORM; - } - else { - /* it's already happened; don't do wait_event overhead */ - pollflag = POLLIN | POLLRDNORM; - pd->port_rcvnowait++; + poll_wait(fp, &pd->port_wait, pt); } - clear_bit(bit, &dd->ipath_rcvctrl); - ipath_write_kreg(dd, dd->ipath_kregs->kr_rcvctrl, - dd->ipath_rcvctrl); + return pollflag; +} + +static unsigned int ipath_poll(struct file *fp, + struct poll_table_struct *pt) +{ + struct ipath_portdata *pd; + unsigned pollflag; + + pd = port_fp(fp); + if (!pd) + pollflag = 0; + else if (pd->poll_type & IPATH_POLL_TYPE_URGENT) + pollflag = ipath_poll_urgent(pd, fp, pt); + else + pollflag = ipath_poll_next(pd, fp, pt); -bail: return pollflag; } +static int ipath_supports_subports(int user_swmajor, int user_swminor) +{ + /* no subport implementation prior to software version 1.3 */ + return (user_swmajor > 1) || (user_swminor >= 3); +} + +static int ipath_compatible_subports(int user_swmajor, int user_swminor) +{ + /* this code is written long-hand for clarity */ + if (IPATH_USER_SWMAJOR != user_swmajor) { + /* no promise of compatibility if major mismatch */ + return 0; + } + if (IPATH_USER_SWMAJOR == 1) { + switch (IPATH_USER_SWMINOR) { + case 0: + case 1: + case 2: + /* no subport implementation so cannot be compatible */ + return 0; + case 3: + /* 3 is only compatible with itself */ + return user_swminor == 3; + default: + /* >= 4 are compatible (or are expected to be) */ + return user_swminor >= 4; + } + } + /* make no promises yet for future major versions */ + return 0; +} + static int init_subports(struct ipath_devdata *dd, struct ipath_portdata *pd, const struct ipath_user_info *uinfo) @@ -1408,20 +1475,32 @@ static int init_subports(struct ipath_devdata *dd, size_t size; /* - * If the user is requesting zero or one port, + * If the user is requesting zero subports, * skip the subport allocation. */ - if (uinfo->spu_subport_cnt <= 1) + if (uinfo->spu_subport_cnt <= 0) + goto bail; + + /* Self-consistency check for ipath_compatible_subports() */ + if (ipath_supports_subports(IPATH_USER_SWMAJOR, IPATH_USER_SWMINOR) && + !ipath_compatible_subports(IPATH_USER_SWMAJOR, + IPATH_USER_SWMINOR)) { + dev_info(&dd->pcidev->dev, + "Inconsistent ipath_compatible_subports()\n"); goto bail; + } - /* Old user binaries don't know about new subport implementation */ - if ((uinfo->spu_userversion & 0xffff) != IPATH_USER_SWMINOR) { + /* Check for subport compatibility */ + if (!ipath_compatible_subports(uinfo->spu_userversion >> 16, + uinfo->spu_userversion & 0xffff)) { dev_info(&dd->pcidev->dev, - "Mismatched user minor version (%d) and driver " - "minor version (%d) while port sharing. Ensure " + "Mismatched user version (%d.%d) and driver " + "version (%d.%d) while port sharing. Ensure " "that driver and library are from the same " "release.\n", + (int) (uinfo->spu_userversion >> 16), (int) (uinfo->spu_userversion & 0xffff), + IPATH_USER_SWMAJOR, IPATH_USER_SWMINOR); goto bail; } @@ -1701,6 +1780,7 @@ static int find_shared_port(struct file *fp, } port_fp(fp) = pd; subport_fp(fp) = pd->port_cnt++; + pd->port_subpid[subport_fp(fp)] = current->pid; tidcursor_fp(fp) = 0; pd->active_slaves |= 1 << subport_fp(fp); ipath_cdbg(PROC, @@ -1725,14 +1805,13 @@ static int ipath_open(struct inode *in, struct file *fp) return fp->private_data ? 0 : -ENOMEM; } - /* Get port early, so can set affinity prior to memory allocation */ static int ipath_assign_port(struct file *fp, const struct ipath_user_info *uinfo) { int ret; int i_minor; - unsigned swminor; + unsigned swmajor, swminor; /* Check to be sure we haven't already initialized this file */ if (port_fp(fp)) { @@ -1741,7 +1820,8 @@ static int ipath_assign_port(struct file *fp, } /* for now, if major version is different, bail */ - if ((uinfo->spu_userversion >> 16) != IPATH_USER_SWMAJOR) { + swmajor = uinfo->spu_userversion >> 16; + if (swmajor != IPATH_USER_SWMAJOR) { ipath_dbg("User major version %d not same as driver " "major %d\n", uinfo->spu_userversion >> 16, IPATH_USER_SWMAJOR); @@ -1756,7 +1836,8 @@ static int ipath_assign_port(struct file *fp, mutex_lock(&ipath_mutex); - if (swminor == IPATH_USER_SWMINOR && uinfo->spu_subport_cnt && + if (ipath_compatible_subports(swmajor, swminor) && + uinfo->spu_subport_cnt && (ret = find_shared_port(fp, uinfo))) { mutex_unlock(&ipath_mutex); if (ret > 0) @@ -1830,11 +1911,16 @@ static int ipath_do_user_init(struct file *fp, */ head32 = ipath_read_ureg32(dd, ur_rcvegrindextail, pd->port_port); ipath_write_ureg(dd, ur_rcvegrindexhead, head32, pd->port_port); - dd->ipath_lastegrheads[pd->port_port] = -1; - dd->ipath_lastrcvhdrqtails[pd->port_port] = -1; + pd->port_lastrcvhdrqtail = -1; ipath_cdbg(VERBOSE, "Wrote port%d egrhead %x from tail regs\n", pd->port_port, head32); pd->port_tidcursor = 0; /* start at beginning after open */ + + /* initialize poll variables... */ + pd->port_urgent = 0; + pd->port_urgent_poll = 0; + pd->port_hdrqfull_poll = pd->port_hdrqfull; + /* * now enable the port; the tail registers will be written to memory * by the chip as soon as it sees the write to @@ -1845,11 +1931,13 @@ static int ipath_do_user_init(struct file *fp, * We explictly set the in-memory copy to 0 beforehand, so we don't * have to wait to be sure the DMA update has happened. */ - *(volatile u64 *)pd->port_rcvhdrtail_kvaddr = 0ULL; - set_bit(INFINIPATH_R_PORTENABLE_SHIFT + pd->port_port, + if (pd->port_rcvhdrtail_kvaddr) + ipath_clear_rcvhdrtail(pd); + set_bit(dd->ipath_r_portenable_shift + pd->port_port, &dd->ipath_rcvctrl); ipath_write_kreg(dd, dd->ipath_kregs->kr_rcvctrl, - dd->ipath_rcvctrl & ~INFINIPATH_R_TAILUPD); + dd->ipath_rcvctrl & + ~(1ULL << dd->ipath_r_tailupd_shift)); ipath_write_kreg(dd, dd->ipath_kregs->kr_rcvctrl, dd->ipath_rcvctrl); /* Notify any waiting slaves */ @@ -1926,6 +2014,7 @@ static int ipath_close(struct inode *in, struct file *fp) * the slave(s) don't wait for receive data forever. */ pd->active_slaves &= ~(1 << fd->subport); + pd->port_subpid[fd->subport] = 0; mutex_unlock(&ipath_mutex); goto bail; } @@ -1957,8 +2046,10 @@ static int ipath_close(struct inode *in, struct file *fp) if (dd->ipath_kregbase) { int i; - /* atomically clear receive enable port. */ - clear_bit(INFINIPATH_R_PORTENABLE_SHIFT + port, + /* atomically clear receive enable port and intr avail. */ + clear_bit(dd->ipath_r_portenable_shift + port, + &dd->ipath_rcvctrl); + clear_bit(pd->port_port + dd->ipath_r_intravail_shift, &dd->ipath_rcvctrl); ipath_write_kreg( dd, dd->ipath_kregs->kr_rcvctrl, dd->ipath_rcvctrl); @@ -2020,7 +2111,8 @@ static int ipath_port_info(struct ipath_portdata *pd, u16 subport, info.port = pd->port_port; info.subport = subport; /* Don't return new fields if old library opened the port. */ - if ((pd->userversion & 0xffff) == IPATH_USER_SWMINOR) { + if (ipath_supports_subports(pd->userversion >> 16, + pd->userversion & 0xffff)) { /* Number of user ports available for this device. */ info.num_ports = pd->port_dd->ipath_cfgports - 1; info.num_subports = pd->port_subport_cnt; @@ -2050,11 +2142,15 @@ static int ipath_get_slave_info(struct ipath_portdata *pd, static int ipath_force_pio_avail_update(struct ipath_devdata *dd) { - u64 reg = dd->ipath_sendctrl; + unsigned long flags; - clear_bit(IPATH_S_PIOBUFAVAILUPD, ®); - ipath_write_kreg(dd, dd->ipath_kregs->kr_sendctrl, reg); + spin_lock_irqsave(&dd->ipath_sendctrl_lock, flags); + ipath_write_kreg(dd, dd->ipath_kregs->kr_sendctrl, + dd->ipath_sendctrl & ~INFINIPATH_S_PIOBUFAVAILUPD); + ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); ipath_write_kreg(dd, dd->ipath_kregs->kr_sendctrl, dd->ipath_sendctrl); + ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); + spin_unlock_irqrestore(&dd->ipath_sendctrl_lock, flags); return 0; } @@ -2123,6 +2219,16 @@ static ssize_t ipath_write(struct file *fp, const char __user *data, src = NULL; dest = NULL; break; + case IPATH_CMD_POLL_TYPE: + copy = sizeof(cmd.cmd.poll_type); + dest = &cmd.cmd.poll_type; + src = &ucmd->cmd.poll_type; + break; + case IPATH_CMD_ARMLAUNCH_CTRL: + copy = sizeof(cmd.cmd.armlaunch_ctrl); + dest = &cmd.cmd.armlaunch_ctrl; + src = &ucmd->cmd.armlaunch_ctrl; + break; default: ret = -EINVAL; goto bail; @@ -2195,6 +2301,15 @@ static ssize_t ipath_write(struct file *fp, const char __user *data, case IPATH_CMD_PIOAVAILUPD: ret = ipath_force_pio_avail_update(pd->port_dd); break; + case IPATH_CMD_POLL_TYPE: + pd->poll_type = cmd.cmd.poll_type; + break; + case IPATH_CMD_ARMLAUNCH_CTRL: + if (cmd.cmd.armlaunch_ctrl) + ipath_enable_armlaunch(pd->port_dd); + else + ipath_disable_armlaunch(pd->port_dd); + break; } if (ret >= 0)