diff options
Diffstat (limited to 'arch/powerpc')
23 files changed, 434 insertions, 147 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b94d4502a47..cf030b00441 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -256,6 +256,9 @@ config IOMMU_VMERGE Most drivers don't have this problem; it is safe to say Y here. +config IOMMU_HELPER + def_bool PPC64 + config HOTPLUG_CPU bool "Support for enabling/disabling CPUs" depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index ed083feaf6f..e6e49289f78 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -22,6 +22,7 @@ #include <linux/mman.h> #include <linux/mm.h> #include <linux/suspend.h> +#include <linux/hrtimer.h> #ifdef CONFIG_PPC64 #include <linux/time.h> #include <linux/hardirq.h> @@ -312,7 +313,7 @@ int main(void) DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); - DEFINE(CLOCK_REALTIME_RES, TICK_NSEC); + DEFINE(CLOCK_REALTIME_RES, (KTIME_MONOTONIC_RES).tv64); #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c index 84239076a5b..3a317cb0636 100644 --- a/arch/powerpc/kernel/dma_64.c +++ b/arch/powerpc/kernel/dma_64.c @@ -31,8 +31,8 @@ static inline unsigned long device_to_mask(struct device *dev) static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { - return iommu_alloc_coherent(dev->archdata.dma_data, size, dma_handle, - device_to_mask(dev), flag, + return iommu_alloc_coherent(dev, dev->archdata.dma_data, size, + dma_handle, device_to_mask(dev), flag, dev->archdata.numa_node); } @@ -52,7 +52,7 @@ static dma_addr_t dma_iommu_map_single(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction) { - return iommu_map_single(dev->archdata.dma_data, vaddr, size, + return iommu_map_single(dev, dev->archdata.dma_data, vaddr, size, device_to_mask(dev), direction); } @@ -68,7 +68,7 @@ static void dma_iommu_unmap_single(struct device *dev, dma_addr_t dma_handle, static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction) { - return iommu_map_sg(dev->archdata.dma_data, sglist, nelems, + return iommu_map_sg(dev, sglist, nelems, device_to_mask(dev), direction); } diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index a3c406aca66..8f1f4e539c4 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -31,6 +31,7 @@ #include <linux/string.h> #include <linux/dma-mapping.h> #include <linux/bitops.h> +#include <linux/iommu-helper.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/iommu.h> @@ -81,17 +82,19 @@ static int __init setup_iommu(char *str) __setup("protect4gb=", setup_protect4gb); __setup("iommu=", setup_iommu); -static unsigned long iommu_range_alloc(struct iommu_table *tbl, +static unsigned long iommu_range_alloc(struct device *dev, + struct iommu_table *tbl, unsigned long npages, unsigned long *handle, unsigned long mask, unsigned int align_order) { - unsigned long n, end, i, start; + unsigned long n, end, start; unsigned long limit; int largealloc = npages > 15; int pass = 0; unsigned long align_mask; + unsigned long boundary_size; align_mask = 0xffffffffffffffffl >> (64 - align_order); @@ -136,14 +139,17 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl, start &= mask; } - n = find_next_zero_bit(tbl->it_map, limit, start); - - /* Align allocation */ - n = (n + align_mask) & ~align_mask; - - end = n + npages; + if (dev) + boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, + 1 << IOMMU_PAGE_SHIFT); + else + boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT); + /* 4GB boundary for iseries_hv_alloc and iseries_hv_map */ - if (unlikely(end >= limit)) { + n = iommu_area_alloc(tbl->it_map, limit, start, npages, + tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT, + align_mask); + if (n == -1) { if (likely(pass < 2)) { /* First failure, just rescan the half of the table. * Second failure, rescan the other half of the table. @@ -158,14 +164,7 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl, } } - for (i = n; i < end; i++) - if (test_bit(i, tbl->it_map)) { - start = i+1; - goto again; - } - - for (i = n; i < end; i++) - __set_bit(i, tbl->it_map); + end = n + npages; /* Bump the hint to a new block for small allocs. */ if (largealloc) { @@ -184,16 +183,17 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl, return n; } -static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *page, - unsigned int npages, enum dma_data_direction direction, - unsigned long mask, unsigned int align_order) +static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, + void *page, unsigned int npages, + enum dma_data_direction direction, + unsigned long mask, unsigned int align_order) { unsigned long entry, flags; dma_addr_t ret = DMA_ERROR_CODE; spin_lock_irqsave(&(tbl->it_lock), flags); - entry = iommu_range_alloc(tbl, npages, NULL, mask, align_order); + entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order); if (unlikely(entry == DMA_ERROR_CODE)) { spin_unlock_irqrestore(&(tbl->it_lock), flags); @@ -224,7 +224,6 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned int npages) { unsigned long entry, free_entry; - unsigned long i; entry = dma_addr >> IOMMU_PAGE_SHIFT; free_entry = entry - tbl->it_offset; @@ -246,9 +245,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, } ppc_md.tce_free(tbl, entry, npages); - - for (i = 0; i < npages; i++) - __clear_bit(free_entry+i, tbl->it_map); + iommu_area_free(tbl->it_map, free_entry, npages); } static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, @@ -270,16 +267,18 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, spin_unlock_irqrestore(&(tbl->it_lock), flags); } -int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, +int iommu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, unsigned long mask, enum dma_data_direction direction) { + struct iommu_table *tbl = dev->archdata.dma_data; dma_addr_t dma_next = 0, dma_addr; unsigned long flags; struct scatterlist *s, *outs, *segstart; int outcount, incount, i; unsigned int align; unsigned long handle; + unsigned int max_seg_size; BUG_ON(direction == DMA_NONE); @@ -298,6 +297,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, spin_lock_irqsave(&(tbl->it_lock), flags); + max_seg_size = dma_get_max_seg_size(dev); for_each_sg(sglist, s, nelems, i) { unsigned long vaddr, npages, entry, slen; @@ -314,7 +314,7 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE && (vaddr & ~PAGE_MASK) == 0) align = PAGE_SHIFT - IOMMU_PAGE_SHIFT; - entry = iommu_range_alloc(tbl, npages, &handle, + entry = iommu_range_alloc(dev, tbl, npages, &handle, mask >> IOMMU_PAGE_SHIFT, align); DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen); @@ -344,7 +344,8 @@ int iommu_map_sg(struct iommu_table *tbl, struct scatterlist *sglist, /* We cannot merge if: * - allocated dma_addr isn't contiguous to previous allocation */ - if (novmerge || (dma_addr != dma_next)) { + if (novmerge || (dma_addr != dma_next) || + (outs->dma_length + s->length > max_seg_size)) { /* Can't merge: create a new segment */ segstart = s; outcount++; @@ -452,9 +453,6 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) { unsigned long sz; - unsigned long start_index, end_index; - unsigned long entries_per_4g; - unsigned long index; static int welcomed = 0; struct page *page; @@ -476,6 +474,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) #ifdef CONFIG_CRASH_DUMP if (ppc_md.tce_get) { + unsigned long index; unsigned long tceval; unsigned long tcecount = 0; @@ -506,23 +505,6 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size); #endif - /* - * DMA cannot cross 4 GB boundary. Mark last entry of each 4 - * GB chunk as reserved. - */ - if (protect4gb) { - entries_per_4g = 0x100000000l >> IOMMU_PAGE_SHIFT; - - /* Mark the last bit before a 4GB boundary as used */ - start_index = tbl->it_offset | (entries_per_4g - 1); - start_index -= tbl->it_offset; - - end_index = tbl->it_size; - - for (index = start_index; index < end_index - 1; index += entries_per_4g) - __set_bit(index, tbl->it_map); - } - if (!welcomed) { printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n", novmerge ? "disabled" : "enabled"); @@ -570,9 +552,9 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name) * need not be page aligned, the dma_addr_t returned will point to the same * byte within the page as vaddr. */ -dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr, - size_t size, unsigned long mask, - enum dma_data_direction direction) +dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl, + void *vaddr, size_t size, unsigned long mask, + enum dma_data_direction direction) { dma_addr_t dma_handle = DMA_ERROR_CODE; unsigned long uaddr; @@ -589,7 +571,7 @@ dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr, ((unsigned long)vaddr & ~PAGE_MASK) == 0) align = PAGE_SHIFT - IOMMU_PAGE_SHIFT; - dma_handle = iommu_alloc(tbl, vaddr, npages, direction, + dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction, mask >> IOMMU_PAGE_SHIFT, align); if (dma_handle == DMA_ERROR_CODE) { if (printk_ratelimit()) { @@ -621,8 +603,9 @@ void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle, * Returns the virtual address of the buffer and sets dma_handle * to the dma address (mapping) of the first page. */ -void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size, - dma_addr_t *dma_handle, unsigned long mask, gfp_t flag, int node) +void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, + size_t size, dma_addr_t *dma_handle, + unsigned long mask, gfp_t flag, int node) { void *ret = NULL; dma_addr_t mapping; @@ -656,7 +639,7 @@ void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size, /* Set up tces to cover the allocated range */ nio_pages = size >> IOMMU_PAGE_SHIFT; io_order = get_iommu_order(size); - mapping = iommu_alloc(tbl, ret, nio_pages, DMA_BIDIRECTIONAL, + mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> IOMMU_PAGE_SHIFT, io_order); if (mapping == DMA_ERROR_CODE) { free_pages((unsigned long)ret, order); diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 76b862bd1fe..61dd17449dd 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -36,7 +36,8 @@ static struct legacy_serial_info { static struct __initdata of_device_id parents[] = { {.type = "soc",}, {.type = "tsi-bridge",}, - {.type = "opb", .compatible = "ibm,opb",}, + {.type = "opb", }, + {.compatible = "ibm,opb",}, {.compatible = "simple-bus",}, {.compatible = "wrs,epld-localbus",}, }; diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index f0bad7070fb..f98867252ee 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -176,7 +176,7 @@ static void __devinit vio_dev_release(struct device *dev) * Returns a pointer to the created vio_dev or NULL if node has * NULL device_type or compatible fields. */ -struct vio_dev * __devinit vio_register_device_node(struct device_node *of_node) +struct vio_dev *vio_register_device_node(struct device_node *of_node) { struct vio_dev *viodev; const unsigned int *unit_address; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index e8122447f01..c7d7bd43a25 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -483,7 +483,12 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, */ _tlbie(address, 0 /* 8xx doesn't care about PID */); #endif - if (!PageReserved(page) + /* The _PAGE_USER test should really be _PAGE_EXEC, but + * older glibc versions execute some code from no-exec + * pages, which for now we are supporting. If exec-only + * pages are ever implemented, this will have to change. + */ + if (!PageReserved(page) && (pte_val(pte) & _PAGE_USER) && !test_bit(PG_arch_1, &page->flags)) { if (vma->vm_mm == current->active_mm) { __flush_dcache_icache((void *) address); diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 64488723162..f80f90c4d58 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -86,7 +86,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) return ret; } -void pgd_free(pgd_t *pgd) +void pgd_free(struct mm_struct *mm, pgd_t *pgd) { free_pages((unsigned long)pgd, PGDIR_ORDER); } @@ -123,7 +123,7 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) return ptepage; } -void pte_free_kernel(pte_t *pte) +void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { #ifdef CONFIG_SMP hash_page_sync(); @@ -131,7 +131,7 @@ void pte_free_kernel(pte_t *pte) free_page((unsigned long)pte); } -void pte_free(struct page *ptepage) +void pte_free(struct mm_struct *mm, struct page *ptepage) { #ifdef CONFIG_SMP hash_page_sync(); diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c index 3fce6b375db..7d301875198 100644 --- a/arch/powerpc/platforms/82xx/mpc8272_ads.c +++ b/arch/powerpc/platforms/82xx/mpc8272_ads.c @@ -134,13 +134,12 @@ static void __init mpc8272_ads_setup_arch(void) } bcsr = of_iomap(np, 0); + of_node_put(np); if (!bcsr) { printk(KERN_ERR "Cannot map BCSR registers\n"); return; } - of_node_put(np); - clrbits32(&bcsr[1], BCSR1_RS232_EN1 | BCSR1_RS232_EN2 | BCSR1_FETHIEN); setbits32(&bcsr[1], BCSR1_FETH_RST); diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c index 68196e34999..e1dceeec499 100644 --- a/arch/powerpc/platforms/82xx/pq2fads.c +++ b/arch/powerpc/platforms/82xx/pq2fads.c @@ -130,13 +130,12 @@ static void __init pq2fads_setup_arch(void) } bcsr = of_iomap(np, 0); + of_node_put(np); if (!bcsr) { printk(KERN_ERR "Cannot map BCSR registers\n"); return; } - of_node_put(np); - /* Enable the serial and ethernet ports */ clrbits32(&bcsr[1], BCSR1_RS232_EN1 | BCSR1_RS232_EN2 | BCSR1_FETHIEN); diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 3a963b4a9be..2f169991896 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -54,6 +54,13 @@ config SPU_FS_64K_LS uses 4K pages. This can improve performances of applications using multiple SPEs by lowering the TLB pressure on them. +config SPU_TRACE + tristate "SPU event tracing support" + depends on SPU_FS && MARKERS + help + This option allows reading a trace of spu-related events through + the sputrace file in procfs. + config SPU_BASE bool default n diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 095988f13bf..d95e71dee91 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -13,7 +13,7 @@ #include <linux/kernel.h> #include <linux/pci.h> #include <linux/msi.h> -#include <linux/reboot.h> +#include <linux/of_platform.h> #include <asm/dcr.h> #include <asm/machdep.h> @@ -65,14 +65,12 @@ struct axon_msic { struct irq_host *irq_host; - __le32 *fifo; + __le32 *fifo_virt; + dma_addr_t fifo_phys; dcr_host_t dcr_host; - struct list_head list; u32 read_offset; }; -static LIST_HEAD(axon_msic_list); - static void msic_dcr_write(struct axon_msic *msic, unsigned int dcr_n, u32 val) { pr_debug("axon_msi: dcr_write(0x%x, 0x%x)\n", val, dcr_n); @@ -94,7 +92,7 @@ static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc) while (msic->read_offset != write_offset) { idx = msic->read_offset / sizeof(__le32); - msi = le32_to_cpu(msic->fifo[idx]); + msi = le32_to_cpu(msic->fifo_virt[idx]); msi &= 0xFFFF; pr_debug("axon_msi: woff %x roff %x msi %x\n", @@ -139,6 +137,7 @@ static struct axon_msic *find_msi_translator(struct pci_dev *dev) tmp = dn; dn = of_find_node_by_phandle(*ph); + of_node_put(tmp); if (!dn) { dev_dbg(&dev->dev, "axon_msi: msi-translator doesn't point to a node\n"); @@ -156,7 +155,6 @@ static struct axon_msic *find_msi_translator(struct pci_dev *dev) out_error: of_node_put(dn); - of_node_put(tmp); return msic; } @@ -292,30 +290,24 @@ static struct irq_host_ops msic_host_ops = { .map = msic_host_map, }; -static int axon_msi_notify_reboot(struct notifier_block *nb, - unsigned long code, void *data) +static int axon_msi_shutdown(struct of_device *device) { - struct axon_msic *msic; + struct axon_msic *msic = device->dev.platform_data; u32 tmp; - list_for_each_entry(msic, &axon_msic_list, list) { - pr_debug("axon_msi: disabling %s\n", - msic->irq_host->of_node->full_name); - tmp = dcr_read(msic->dcr_host, MSIC_CTRL_REG); - tmp &= ~MSIC_CTRL_ENABLE & ~MSIC_CTRL_IRQ_ENABLE; - msic_dcr_write(msic, MSIC_CTRL_REG, tmp); - } + pr_debug("axon_msi: disabling %s\n", + msic->irq_host->of_node->full_name); + tmp = dcr_read(msic->dcr_host, MSIC_CTRL_REG); + tmp &= ~MSIC_CTRL_ENABLE & ~MSIC_CTRL_IRQ_ENABLE; + msic_dcr_write(msic, MSIC_CTRL_REG, tmp); return 0; } -static struct notifier_block axon_msi_reboot_notifier = { - .notifier_call = axon_msi_notify_reboot -}; - -static int axon_msi_setup_one(struct device_node *dn) +static int axon_msi_probe(struct of_device *device, + const struct of_device_id *device_id) { - struct page *page; + struct device_node *dn = device->node; struct axon_msic *msic; unsigned int virq; int dcr_base, dcr_len; @@ -346,16 +338,14 @@ static int axon_msi_setup_one(struct device_node *dn) goto out_free_msic; } - page = alloc_pages_node(of_node_to_nid(dn), GFP_KERNEL, - get_order(MSIC_FIFO_SIZE_BYTES)); - if (!page) { + msic->fifo_virt = dma_alloc_coherent(&device->dev, MSIC_FIFO_SIZE_BYTES, + &msic->fifo_phys, GFP_KERNEL); + if (!msic->fifo_virt) { printk(KERN_ERR "axon_msi: couldn't allocate fifo for %s\n", dn->full_name); goto out_free_msic; } - msic->fifo = page_address(page); - msic->irq_host = irq_alloc_host(of_node_get(dn), IRQ_HOST_MAP_NOMAP, NR_IRQS, &msic_host_ops, 0); if (!msic->irq_host) { @@ -378,14 +368,18 @@ static int axon_msi_setup_one(struct device_node *dn) pr_debug("axon_msi: irq 0x%x setup for axon_msi\n", virq); /* Enable the MSIC hardware */ - msic_dcr_write(msic, MSIC_BASE_ADDR_HI_REG, (u64)msic->fifo >> 32); + msic_dcr_write(msic, MSIC_BASE_ADDR_HI_REG, msic->fifo_phys >> 32); msic_dcr_write(msic, MSIC_BASE_ADDR_LO_REG, - (u64)msic->fifo & 0xFFFFFFFF); + msic->fifo_phys & 0xFFFFFFFF); msic_dcr_write(msic, MSIC_CTRL_REG, MSIC_CTRL_IRQ_ENABLE | MSIC_CTRL_ENABLE | MSIC_CTRL_FIFO_SIZE); - list_add(&msic->list, &axon_msic_list); + device->dev.platform_data = msic; + + ppc_md.setup_msi_irqs = axon_msi_setup_msi_irqs; + ppc_md.teardown_msi_irqs = axon_msi_teardown_msi_irqs; + ppc_md.msi_check_device = axon_msi_check_device; printk(KERN_DEBUG "axon_msi: setup MSIC on %s\n", dn->full_name); @@ -394,7 +388,8 @@ static int axon_msi_setup_one(struct device_node *dn) out_free_host: kfree(msic->irq_host); out_free_fifo: - __free_pages(virt_to_page(msic->fifo), get_order(MSIC_FIFO_SIZE_BYTES)); + dma_free_coherent(&device->dev, MSIC_FIFO_SIZE_BYTES, msic->fifo_virt, + msic->fifo_phys); out_free_msic: kfree(msic); out: @@ -402,28 +397,24 @@ out: return -1; } -static int axon_msi_init(void) -{ - struct device_node *dn; - int found = 0; - - pr_debug("axon_msi: initialising ...\n"); - - for_each_compatible_node(dn, NULL, "ibm,axon-msic") { - if (axon_msi_setup_one(dn) == 0) - found++; - } - - if (found) { - ppc_md.setup_msi_irqs = axon_msi_setup_msi_irqs; - ppc_md.teardown_msi_irqs = axon_msi_teardown_msi_irqs; - ppc_md.msi_check_device = axon_msi_check_device; - - register_reboot_notifier(&axon_msi_reboot_notifier); +static const struct of_device_id axon_msi_device_id[] = { + { + .compatible = "ibm,axon-msic" + }, + {} +}; - pr_debug("axon_msi: registered callbacks!\n"); - } +static struct of_platform_driver axon_msi_driver = { + .match_table = axon_msi_device_id, + .probe = axon_msi_probe, + .shutdown = axon_msi_shutdown, + .driver = { + .name = "axon-msi" + }, +}; - return 0; +static int __init axon_msi_init(void) +{ + return of_register_platform_driver(&axon_msi_driver); } -arch_initcall(axon_msi_init); +subsys_initcall(axon_msi_init); diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index e6534b519c9..a7f609b3b87 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -98,7 +98,7 @@ static int __init cell_publish_devices(void) } return 0; } -machine_device_initcall(cell, cell_publish_devices); +machine_subsys_initcall(cell, cell_publish_devices); static void cell_mpic_cascade(unsigned int irq, struct irq_desc *desc) { diff --git a/arch/powerpc/platforms/cell/spufs/Makefile b/arch/powerpc/platforms/cell/spufs/Makefile index d3a349fb42e..99610a6361f 100644 --- a/arch/powerpc/platforms/cell/spufs/Makefile +++ b/arch/powerpc/platforms/cell/spufs/Makefile @@ -4,6 +4,8 @@ spufs-y += inode.o file.o context.o syscalls.o coredump.o spufs-y += sched.o backing_ops.o hw_ops.o run.o gang.o spufs-y += switch.o fault.o lscsa_alloc.o +obj-$(CONFIG_SPU_TRACE) += sputrace.o + # Rules to build switch.o with the help of SPU tool chain SPU_CROSS := spu- SPU_CC := $(SPU_CROSS)gcc diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 3fcd06418b0..1018acd1746 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -29,6 +29,7 @@ #include <linux/poll.h> #include <linux/ptrace.h> #include <linux/seq_file.h> +#include <linux/marker.h> #include <asm/io.h> #include <asm/semaphore.h> @@ -358,6 +359,8 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma, struct spu_context *ctx = vma->vm_file->private_data; unsigned long area, offset = address - vma->vm_start; + spu_context_nospu_trace(spufs_ps_nopfn__enter, ctx); + offset += vma->vm_pgoff << PAGE_SHIFT; if (offset >= ps_size) return NOPFN_SIGBUS; @@ -375,11 +378,14 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma, if (ctx->state == SPU_STATE_SAVED) { up_read(¤t->mm->mmap_sem); + spu_context_nospu_trace(spufs_ps_nopfn__sleep, ctx); spufs_wait(ctx->run_wq, ctx->state == SPU_STATE_RUNNABLE); + spu_context_trace(spufs_ps_nopfn__wake, ctx, ctx->spu); down_read(¤t->mm->mmap_sem); } else { area = ctx->spu->problem_phys + ps_offs; vm_insert_pfn(vma, address, (area + offset) >> PAGE_SHIFT); + spu_context_trace(spufs_ps_nopfn__insert, ctx, ctx->spu); } spu_release(ctx); diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index c0e968a4c21..90784c029f2 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -322,7 +322,7 @@ static struct spu_context * spufs_assert_affinity(unsigned int flags, struct spu_gang *gang, struct file *filp) { - struct spu_context *tmp, *neighbor; + struct spu_context *tmp, *neighbor, *err; int count, node; int aff_supp; @@ -354,11 +354,15 @@ spufs_assert_affinity(unsigned int flags, struct spu_gang *gang, if (!list_empty(&neighbor->aff_list) && !(neighbor->aff_head) && !list_is_last(&neighbor->aff_list, &gang->aff_list_head) && !list_entry(neighbor->aff_list.next, struct spu_context, - aff_list)->aff_head) - return ERR_PTR(-EEXIST); + aff_list)->aff_head) { + err = ERR_PTR(-EEXIST); + goto out_put_neighbor; + } - if (gang != neighbor->gang) - return ERR_PTR(-EINVAL); + if (gang != neighbor->gang) { + err = ERR_PTR(-EINVAL); + goto out_put_neighbor; + } count = 1; list_for_each_entry(tmp, &gang->aff_list_head, aff_list) @@ -372,11 +376,17 @@ spufs_assert_affinity(unsigned int flags, struct spu_gang *gang, break; } - if (node == MAX_NUMNODES) - return ERR_PTR(-EEXIST); + if (node == MAX_NUMNODES) { + err = ERR_PTR(-EEXIST); + goto out_put_neighbor; + } } return neighbor; + +out_put_neighbor: + put_spu_context(neighbor); + return err; } static void @@ -454,9 +464,12 @@ spufs_create_context(struct inode *inode, struct dentry *dentry, if (ret) goto out_aff_unlock; - if (affinity) + if (affinity) { spufs_set_affinity(flags, SPUFS_I(dentry->d_inode)->i_ctx, neighbor); + if (neighbor) + put_spu_context(neighbor); + } /* * get references for dget and mntget, will be released diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c index c01a09da1e5..b4814c740d8 100644 --- a/arch/powerpc/platforms/cell/spufs/run.c +++ b/arch/powerpc/platforms/cell/spufs/run.c @@ -410,8 +410,11 @@ long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *event) * since we have TIF_SINGLESTEP set, thus the kernel will do * it upon return from the syscall anyawy */ - if ((status & SPU_STATUS_STOPPED_BY_STOP) - && (status >> SPU_STOP_STATUS_SHIFT) == 0x3fff) { + if (unlikely(status & SPU_STATUS_SINGLE_STEP)) + ret = -ERESTARTSYS; + + else if (unlikely((status & SPU_STATUS_STOPPED_BY_STOP) + && (status >> SPU_STOP_STATUS_SHIFT) == 0x3fff)) { force_sig(SIGTRAP, current); ret = -ERESTARTSYS; } diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 00d914232af..5915343e259 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -39,6 +39,7 @@ #include <linux/pid_namespace.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/marker.h> #include <asm/io.h> #include <asm/mmu_context.h> @@ -216,8 +217,8 @@ void do_notify_spus_active(void) */ static void spu_bind_context(struct spu *spu, struct spu_context *ctx) { - pr_debug("%s: pid=%d SPU=%d NODE=%d\n", __FUNCTION__, current->pid, - spu->number, spu->node); + spu_context_trace(spu_bind_context__enter, ctx, spu); + spuctx_switch_state(ctx, SPU_UTIL_SYSTEM); if (ctx->flags & SPU_CREATE_NOSCHED) @@ -399,8 +400,8 @@ static int has_affinity(struct spu_context *ctx) */ static void spu_unbind_context(struct spu *spu, struct spu_context *ctx) { - pr_debug("%s: unbind pid=%d SPU=%d NODE=%d\n", __FUNCTION__, - spu->pid, spu->number, spu->node); + spu_context_trace(spu_unbind_context__enter, ctx, spu); + spuctx_switch_state(ctx, SPU_UTIL_SYSTEM); if (spu->ctx->flags & SPU_CREATE_NOSCHED) @@ -528,6 +529,8 @@ static struct spu *spu_get_idle(struct spu_context *ctx) struct spu *spu, *aff_ref_spu; int node, n; + spu_context_nospu_trace(spu_get_idle__enter, ctx); + if (ctx->gang) { mutex_lock(&ctx->gang->aff_mutex); if (has_affinity(ctx)) { @@ -546,8 +549,7 @@ static struct spu *spu_get_idle(struct spu_context *ctx) if (atomic_dec_and_test(&ctx->gang->aff_sched_count)) ctx->gang->aff_ref_spu = NULL; mutex_unlock(&ctx->gang->aff_mutex); - - return NULL; + goto not_found; } mutex_unlock(&ctx->gang->aff_mutex); } @@ -565,12 +567,14 @@ static struct spu *spu_get_idle(struct spu_context *ctx) mutex_unlock(&cbe_spu_info[node].list_mutex); } + not_found: + spu_context_nospu_trace(spu_get_idle__not_found, ctx); return NULL; found: spu->alloc_state = SPU_USED; mutex_unlock(&cbe_spu_info[node].list_mutex); - pr_debug("Got SPU %d %d\n", spu->number, spu->node); + spu_context_trace(spu_get_idle__found, ctx, spu); spu_init_channels(spu); return spu; } @@ -587,6 +591,8 @@ static struct spu *find_victim(struct spu_context *ctx) struct spu *spu; int node, n; + spu_context_nospu_trace(spu_find_vitim__enter, ctx); + /* * Look for a possible preemption candidate on the local node first. * If there is no candidate look at the other nodes. This isn't @@ -640,6 +646,8 @@ static struct spu *find_victim(struct spu_context *ctx) goto restart; } + spu_context_trace(__spu_deactivate__unload, ctx, spu); + mutex_lock(&cbe_spu_info[node].list_mutex); cbe_spu_info[node].nr_active--; spu_unbind_context(spu, victim); @@ -822,6 +830,7 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio) */ void spu_deactivate(struct spu_context *ctx) { + spu_context_nospu_trace(spu_deactivate__enter, ctx); __spu_deactivate(ctx, 1, MAX_PRIO); } @@ -835,6 +844,7 @@ void spu_deactivate(struct spu_context *ctx) */ void spu_yield(struct spu_context *ctx) { + spu_context_nospu_trace(spu_yield__enter, ctx); if (!(ctx->flags & SPU_CREATE_NOSCHED)) { mutex_lock(&ctx->state_mutex); __spu_deactivate(ctx, 0, MAX_PRIO); @@ -864,11 +874,15 @@ static noinline void spusched_tick(struct spu_context *ctx) goto out; spu = ctx->spu; + + spu_context_trace(spusched_tick__preempt, ctx, spu); + new = grab_runnable_context(ctx->prio + 1, spu->node); if (new) { spu_unschedule(spu, ctx); spu_add_to_rq(ctx); } else { + spu_context_nospu_trace(spusched_tick__newslice, ctx); ctx->time_slice++; } out: diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index 0e114038ea6..795a1b52538 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -325,4 +325,9 @@ extern void spu_free_lscsa(struct spu_state *csa); extern void spuctx_switch_state(struct spu_context *ctx, enum spu_utilization_state new_state); +#define spu_context_trace(name, ctx, spu) \ + trace_mark(name, "%p %p", ctx, spu); +#define spu_context_nospu_trace(name, ctx) \ + trace_mark(name, "%p", ctx); + #endif diff --git a/arch/powerpc/platforms/cell/spufs/sputrace.c b/arch/powerpc/platforms/cell/spufs/sputrace.c new file mode 100644 index 00000000000..2b1953f6f12 --- /dev/null +++ b/arch/powerpc/platforms/cell/spufs/sputrace.c @@ -0,0 +1,250 @@ +/* + * Copyright (C) 2007 IBM Deutschland Entwicklung GmbH + * Released under GPL v2. + * + * Partially based on net/ipv4/tcp_probe.c. + * + * Simple tracing facility for spu contexts. + */ +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/marker.h> +#include <linux/proc_fs.h> +#include <linux/wait.h> +#include <asm/atomic.h> +#include <asm/uaccess.h> +#include "spufs.h" + +struct spu_probe { + const char *name; + const char *format; + marker_probe_func *probe_func; +}; + +struct sputrace { + ktime_t tstamp; + int owner_tid; /* owner */ + int curr_tid; + const char *name; + int number; +}; + +static int bufsize __read_mostly = 16384; +MODULE_PARM_DESC(bufsize, "Log buffer size (number of records)"); +module_param(bufsize, int, 0); + + +static DEFINE_SPINLOCK(sputrace_lock); +static DECLARE_WAIT_QUEUE_HEAD(sputrace_wait); +static ktime_t sputrace_start; +static unsigned long sputrace_head, sputrace_tail; +static struct sputrace *sputrace_log; + +static int sputrace_used(void) +{ + return (sputrace_head - sputrace_tail) % bufsize; +} + +static inline int sputrace_avail(void) +{ + return bufsize - sputrace_used(); +} + +static int sputrace_sprint(char *tbuf, int n) +{ + const struct sputrace *t = sputrace_log + sputrace_tail % bufsize; + struct timespec tv = + ktime_to_timespec(ktime_sub(t->tstamp, sputrace_start)); + + return snprintf(tbuf, n, + "[%lu.%09lu] %d: %s (thread = %d, spu = %d)\n", + (unsigned long) tv.tv_sec, + (unsigned long) tv.tv_nsec, + t->owner_tid, + t->name, + t->curr_tid, + t->number); +} + +static ssize_t sputrace_read(struct file *file, char __user *buf, + size_t len, loff_t *ppos) +{ + int error = 0, cnt = 0; + + if (!buf || len < 0) + return -EINVAL; + + while (cnt < len) { + char tbuf[128]; + int width; + + error = wait_event_interruptible(sputrace_wait, + sputrace_used() > 0); + if (error) + break; + + spin_lock(&sputrace_lock); + if (sputrace_head == sputrace_tail) { + spin_unlock(&sputrace_lock); + continue; + } + + width = sputrace_sprint(tbuf, sizeof(tbuf)); + if (width < len) + sputrace_tail = (sputrace_tail + 1) % bufsize; + spin_unlock(&sputrace_lock); + + if (width >= len) + break; + + error = copy_to_user(buf + cnt, tbuf, width); + if (error) + break; + cnt += width; + } + + return cnt == 0 ? error : cnt; +} + +static int sputrace_open(struct inode *inode, struct file *file) +{ + spin_lock(&sputrace_lock); + sputrace_head = sputrace_tail = 0; + sputrace_start = ktime_get(); + spin_unlock(&sputrace_lock); + + return 0; +} + +static const struct file_operations sputrace_fops = { + .owner = THIS_MODULE, + .open = sputrace_open, + .read = sputrace_read, +}; + +static void sputrace_log_item(const char *name, struct spu_context *ctx, + struct spu *spu) +{ + spin_lock(&sputrace_lock); + if (sputrace_avail() > 1) { + struct sputrace *t = sputrace_log + sputrace_head; + + t->tstamp = ktime_get(); + t->owner_tid = ctx->tid; + t->name = name; + t->curr_tid = current->pid; + t->number = spu ? spu->number : -1; + + sputrace_head = (sputrace_head + 1) % bufsize; + } else { + printk(KERN_WARNING + "sputrace: lost samples due to full buffer.\n"); + } + spin_unlock(&sputrace_lock); + + wake_up(&sputrace_wait); +} + +static void spu_context_event(const struct marker *mdata, + void *private, const char *format, ...) +{ + struct spu_probe *p = mdata->private; + va_list ap; + struct spu_context *ctx; + struct spu *spu; + + va_start(ap, format); + ctx = va_arg(ap, struct spu_context *); + spu = va_arg(ap, struct spu *); + + sputrace_log_item(p->name, ctx, spu); + va_end(ap); +} + +static void spu_context_nospu_event(const struct marker *mdata, + void *private, const char *format, ...) +{ + struct spu_probe *p = mdata->private; + va_list ap; + struct spu_context *ctx; + + va_start(ap, format); + ctx = va_arg(ap, struct spu_context *); + + sputrace_log_item(p->name, ctx, NULL); + va_end(ap); +} + +struct spu_probe spu_probes[] = { + { "spu_bind_context__enter", "%p %p", spu_context_event }, + { "spu_unbind_context__enter", "%p %p", spu_context_event }, + { "spu_get_idle__enter", "%p", spu_context_nospu_event }, + { "spu_get_idle__found", "%p %p", spu_context_event }, + { "spu_get_idle__not_found", "%p", spu_context_nospu_event }, + { "spu_find_victim__enter", "%p", spu_context_nospu_event }, + { "spusched_tick__preempt", "%p %p", spu_context_event }, + { "spusched_tick__newslice", "%p", spu_context_nospu_event }, + { "spu_yield__enter", "%p", spu_context_nospu_event }, + { "spu_deactivate__enter", "%p", spu_context_nospu_event }, + { "__spu_deactivate__unload", "%p %p", spu_context_event }, + { "spufs_ps_nopfn__enter", "%p", spu_context_nospu_event }, + { "spufs_ps_nopfn__sleep", "%p", spu_context_nospu_event }, + { "spufs_ps_nopfn__wake", "%p %p", spu_context_event }, + { "spufs_ps_nopfn__insert", "%p %p", spu_context_event }, + { "spu_acquire_saved__enter", "%p", spu_context_nospu_event }, + { "destroy_spu_context__enter", "%p", spu_context_nospu_event }, +}; + +static int __init sputrace_init(void) +{ + struct proc_dir_entry *entry; + int i, error = -ENOMEM; + + sputrace_log = kcalloc(sizeof(struct sputrace), + bufsize, GFP_KERNEL); + if (!sputrace_log) + goto out; + + entry = create_proc_entry("sputrace", S_IRUSR, NULL); + if (!entry) + goto out_free_log; + entry->proc_fops = &sputrace_fops; + + for (i = 0; i < ARRAY_SIZE(spu_probes); i++) { + struct spu_probe *p = &spu_probes[i]; + + error = marker_probe_register(p->name, p->format, + p->probe_func, p); + if (error) + printk(KERN_INFO "Unable to register probe %s\n", + p->name); + + error = marker_arm(p->name); + if (error) + printk(KERN_INFO "Unable to arm probe %s\n", p->name); + } + + return 0; + +out_free_log: + kfree(sputrace_log); +out: + return -ENOMEM; +} + +static void __exit sputrace_exit(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(spu_probes); i++) + marker_probe_unregister(spu_probes[i].name); + + remove_proc_entry("sputrace", NULL); + kfree(sputrace_log); +} + +module_init(sputrace_init); +module_exit(sputrace_exit); + +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c index 6a0c6f6675c..11fa3c772ed 100644 --- a/arch/powerpc/platforms/iseries/iommu.c +++ b/arch/powerpc/platforms/iseries/iommu.c @@ -199,7 +199,7 @@ static struct iommu_table vio_iommu_table; void *iseries_hv_alloc(size_t size, dma_addr_t *dma_handle, gfp_t flag) { - return iommu_alloc_coherent(&vio_iommu_table, size, dma_handle, + return iommu_alloc_coherent(NULL, &vio_iommu_table, size, dma_handle, DMA_32BIT_MASK, flag, -1); } EXPORT_SYMBOL_GPL(iseries_hv_alloc); @@ -213,7 +213,7 @@ EXPORT_SYMBOL_GPL(iseries_hv_free); dma_addr_t iseries_hv_map(void *vaddr, size_t size, enum dma_data_direction direction) { - return iommu_map_single(&vio_iommu_table, vaddr, size, + return iommu_map_single(NULL, &vio_iommu_table, vaddr, size, DMA_32BIT_MASK, direction); } diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index c02f8742c54..2800fced8c7 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -167,6 +167,7 @@ static int pSeries_reconfig_remove_node(struct device_node *np) if ((child = of_get_next_child(np, NULL))) { of_node_put(child); + of_node_put(parent); return -EBUSY; } diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c index 0e74a4bd982..5d2d5522ef4 100644 --- a/arch/powerpc/sysdev/mpc8xx_pic.c +++ b/arch/powerpc/sysdev/mpc8xx_pic.c @@ -174,15 +174,19 @@ int mpc8xx_pic_init(void) goto out; siu_reg = ioremap(res.start, res.end - res.start + 1); - if (siu_reg == NULL) - return -EINVAL; + if (siu_reg == NULL) { + ret = -EINVAL; + goto out; + } - mpc8xx_pic_host = irq_alloc_host(of_node_get(np), IRQ_HOST_MAP_LINEAR, + mpc8xx_pic_host = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR, 64, &mpc8xx_pic_host_ops, 64); if (mpc8xx_pic_host == NULL) { printk(KERN_ERR "MPC8xx PIC: failed to allocate irq host!\n"); ret = -ENOMEM; + goto out; } + return 0; out: of_node_put(np); |