diff options
author | Tushar Dave <tushar.n.dave@oracle.com> | 2016-10-28 19:12:44 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2016-11-18 20:17:00 +0100 |
commit | f08978b0fdbf37d3c91efb60a20bdee3ba8f59c6 (patch) | |
tree | 61a2039e1611d9898c0c23b13e9d95b70430087a | |
parent | sparc64: Bind PCIe devices to use IOMMU v2 service (diff) | |
download | linux-f08978b0fdbf37d3c91efb60a20bdee3ba8f59c6.tar.xz linux-f08978b0fdbf37d3c91efb60a20bdee3ba8f59c6.zip |
sparc64: Enable sun4v dma ops to use IOMMU v2 APIs
Add Hypervisor IOMMU v2 APIs pci_iotsb_map(), pci_iotsb_demap() and
enable sun4v dma ops to use IOMMU v2 API for all PCIe devices with
64bit DMA mask.
Signed-off-by: Tushar Dave <tushar.n.dave@oracle.com>
Reviewed-by: chris hyser <chris.hyser@oracle.com>
Acked-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r-- | arch/sparc/include/asm/hypervisor.h | 6 | ||||
-rw-r--r-- | arch/sparc/kernel/pci_sun4v.c | 216 | ||||
-rw-r--r-- | arch/sparc/kernel/pci_sun4v.h | 11 | ||||
-rw-r--r-- | arch/sparc/kernel/pci_sun4v_asm.S | 36 |
4 files changed, 211 insertions, 58 deletions
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index 7b15df8be008..73cb8978df58 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2377,6 +2377,12 @@ unsigned long sun4v_vintr_set_target(unsigned long dev_handle, * iotsb_index Zero-based IOTTE number within an IOTSB. */ +/* The index_count argument consists of two fields: + * bits 63:48 #iottes and bits 47:0 iotsb_index + */ +#define HV_PCI_IOTSB_INDEX_COUNT(__iottes, __iotsb_index) \ + (((u64)(__iottes) << 48UL) | ((u64)(__iotsb_index))) + /* pci_iotsb_conf() * TRAP: HV_FAST_TRAP * FUNCTION: HV_FAST_PCI_IOTSB_CONF diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index d4208aa93383..06981cc716b6 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -72,34 +72,57 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns } /* Interrupts must be disabled. */ -static long iommu_batch_flush(struct iommu_batch *p) +static long iommu_batch_flush(struct iommu_batch *p, u64 mask) { struct pci_pbm_info *pbm = p->dev->archdata.host_controller; + u64 *pglist = p->pglist; + u64 index_count; unsigned long devhandle = pbm->devhandle; unsigned long prot = p->prot; unsigned long entry = p->entry; - u64 *pglist = p->pglist; unsigned long npages = p->npages; + unsigned long iotsb_num; + unsigned long ret; + long num; /* VPCI maj=1, min=[0,1] only supports read and write */ if (vpci_major < 2) prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE); while (npages != 0) { - long num; - - num = pci_sun4v_iommu_map(devhandle, HV_PCI_TSBID(0, entry), - npages, prot, __pa(pglist)); - if (unlikely(num < 0)) { - if (printk_ratelimit()) - printk("iommu_batch_flush: IOMMU map of " - "[%08lx:%08llx:%lx:%lx:%lx] failed with " - "status %ld\n", - devhandle, HV_PCI_TSBID(0, entry), - npages, prot, __pa(pglist), num); - return -1; + if (mask <= DMA_BIT_MASK(32)) { + num = pci_sun4v_iommu_map(devhandle, + HV_PCI_TSBID(0, entry), + npages, + prot, + __pa(pglist)); + if (unlikely(num < 0)) { + pr_err_ratelimited("%s: IOMMU map of [%08lx:%08llx:%lx:%lx:%lx] failed with status %ld\n", + __func__, + devhandle, + HV_PCI_TSBID(0, entry), + npages, prot, __pa(pglist), + num); + return -1; + } + } else { + index_count = HV_PCI_IOTSB_INDEX_COUNT(npages, entry), + iotsb_num = pbm->iommu->atu->iotsb->iotsb_num; + ret = pci_sun4v_iotsb_map(devhandle, + iotsb_num, + index_count, + prot, + __pa(pglist), + &num); + if (unlikely(ret != HV_EOK)) { + pr_err_ratelimited("%s: ATU map of [%08lx:%lx:%llx:%lx:%lx] failed with status %ld\n", + __func__, + devhandle, iotsb_num, + index_count, prot, + __pa(pglist), ret); + return -1; + } } - entry += num; npages -= num; pglist += num; @@ -111,19 +134,19 @@ static long iommu_batch_flush(struct iommu_batch *p) return 0; } -static inline void iommu_batch_new_entry(unsigned long entry) +static inline void iommu_batch_new_entry(unsigned long entry, u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); if (p->entry + p->npages == entry) return; if (p->entry != ~0UL) - iommu_batch_flush(p); + iommu_batch_flush(p, mask); p->entry = entry; } /* Interrupts must be disabled. */ -static inline long iommu_batch_add(u64 phys_page) +static inline long iommu_batch_add(u64 phys_page, u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); @@ -131,28 +154,31 @@ static inline long iommu_batch_add(u64 phys_page) p->pglist[p->npages++] = phys_page; if (p->npages == PGLIST_NENTS) - return iommu_batch_flush(p); + return iommu_batch_flush(p, mask); return 0; } /* Interrupts must be disabled. */ -static inline long iommu_batch_end(void) +static inline long iommu_batch_end(u64 mask) { struct iommu_batch *p = this_cpu_ptr(&iommu_batch); BUG_ON(p->npages >= PGLIST_NENTS); - return iommu_batch_flush(p); + return iommu_batch_flush(p, mask); } static void *dma_4v_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addrp, gfp_t gfp, unsigned long attrs) { + u64 mask; unsigned long flags, order, first_page, npages, n; unsigned long prot = 0; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; struct page *page; void *ret; long entry; @@ -177,14 +203,21 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, memset((char *)first_page, 0, PAGE_SIZE << order); iommu = dev->archdata.iommu; + atu = iommu->atu; + + mask = dev->coherent_dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL, + entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL, (unsigned long)(-1), 0); if (unlikely(entry == IOMMU_ERROR_CODE)) goto range_alloc_fail; - *dma_addrp = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT)); + *dma_addrp = (tbl->table_map_base + (entry << IO_PAGE_SHIFT)); ret = (void *) first_page; first_page = __pa(first_page); @@ -196,12 +229,12 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, entry); for (n = 0; n < npages; n++) { - long err = iommu_batch_add(first_page + (n * PAGE_SIZE)); + long err = iommu_batch_add(first_page + (n * PAGE_SIZE), mask); if (unlikely(err < 0L)) goto iommu_map_fail; } - if (unlikely(iommu_batch_end() < 0L)) + if (unlikely(iommu_batch_end(mask) < 0L)) goto iommu_map_fail; local_irq_restore(flags); @@ -209,7 +242,7 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, return ret; iommu_map_fail: - iommu_tbl_range_free(&iommu->tbl, *dma_addrp, npages, IOMMU_ERROR_CODE); + iommu_tbl_range_free(tbl, *dma_addrp, npages, IOMMU_ERROR_CODE); range_alloc_fail: free_pages(first_page, order); @@ -253,18 +286,27 @@ unsigned long dma_4v_iotsb_bind(unsigned long devhandle, return 0; } -static void dma_4v_iommu_demap(void *demap_arg, unsigned long entry, - unsigned long npages) +static void dma_4v_iommu_demap(struct device *dev, unsigned long devhandle, + dma_addr_t dvma, unsigned long iotsb_num, + unsigned long entry, unsigned long npages) { - u32 devhandle = *(u32 *)demap_arg; unsigned long num, flags; + unsigned long ret; local_irq_save(flags); do { - num = pci_sun4v_iommu_demap(devhandle, - HV_PCI_TSBID(0, entry), - npages); - + if (dvma <= DMA_BIT_MASK(32)) { + num = pci_sun4v_iommu_demap(devhandle, + HV_PCI_TSBID(0, entry), + npages); + } else { + ret = pci_sun4v_iotsb_demap(devhandle, iotsb_num, + entry, npages, &num); + if (unlikely(ret != HV_EOK)) { + pr_err_ratelimited("pci_iotsb_demap() failed with error: %ld\n", + ret); + } + } entry += num; npages -= num; } while (npages != 0); @@ -276,16 +318,28 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu, { struct pci_pbm_info *pbm; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; unsigned long order, npages, entry; + unsigned long iotsb_num; u32 devhandle; npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT; iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; - entry = ((dvma - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT); - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, dvma, npages, IOMMU_ERROR_CODE); + + if (dvma <= DMA_BIT_MASK(32)) { + tbl = &iommu->tbl; + iotsb_num = 0; /* we don't care for legacy iommu */ + } else { + tbl = &atu->tbl; + iotsb_num = atu->iotsb->iotsb_num; + } + entry = ((dvma - tbl->table_map_base) >> IO_PAGE_SHIFT); + dma_4v_iommu_demap(dev, devhandle, dvma, iotsb_num, entry, npages); + iommu_tbl_range_free(tbl, dvma, npages, IOMMU_ERROR_CODE); order = get_order(size); if (order < 10) free_pages((unsigned long)cpu, order); @@ -297,13 +351,17 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, unsigned long attrs) { struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; + u64 mask; unsigned long flags, npages, oaddr; unsigned long i, base_paddr; - u32 bus_addr, ret; unsigned long prot; + dma_addr_t bus_addr, ret; long entry; iommu = dev->archdata.iommu; + atu = iommu->atu; if (unlikely(direction == DMA_NONE)) goto bad; @@ -312,13 +370,19 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK); npages >>= IO_PAGE_SHIFT; - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL, + mask = *dev->dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; + + entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL, (unsigned long)(-1), 0); if (unlikely(entry == IOMMU_ERROR_CODE)) goto bad; - bus_addr = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT)); + bus_addr = (tbl->table_map_base + (entry << IO_PAGE_SHIFT)); ret = bus_addr | (oaddr & ~IO_PAGE_MASK); base_paddr = __pa(oaddr & IO_PAGE_MASK); prot = HV_PCI_MAP_ATTR_READ; @@ -333,11 +397,11 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, iommu_batch_start(dev, prot, entry); for (i = 0; i < npages; i++, base_paddr += IO_PAGE_SIZE) { - long err = iommu_batch_add(base_paddr); + long err = iommu_batch_add(base_paddr, mask); if (unlikely(err < 0L)) goto iommu_map_fail; } - if (unlikely(iommu_batch_end() < 0L)) + if (unlikely(iommu_batch_end(mask) < 0L)) goto iommu_map_fail; local_irq_restore(flags); @@ -350,7 +414,7 @@ bad: return DMA_ERROR_CODE; iommu_map_fail: - iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE); + iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE); return DMA_ERROR_CODE; } @@ -360,7 +424,10 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, { struct pci_pbm_info *pbm; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; unsigned long npages; + unsigned long iotsb_num; long entry; u32 devhandle; @@ -372,14 +439,23 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; npages = IO_PAGE_ALIGN(bus_addr + sz) - (bus_addr & IO_PAGE_MASK); npages >>= IO_PAGE_SHIFT; bus_addr &= IO_PAGE_MASK; - entry = (bus_addr - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT; - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE); + + if (bus_addr <= DMA_BIT_MASK(32)) { + iotsb_num = 0; /* we don't care for legacy iommu */ + tbl = &iommu->tbl; + } else { + iotsb_num = atu->iotsb->iotsb_num; + tbl = &atu->tbl; + } + entry = (bus_addr - tbl->table_map_base) >> IO_PAGE_SHIFT; + dma_4v_iommu_demap(dev, devhandle, bus_addr, iotsb_num, entry, npages); + iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE); } static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, @@ -393,12 +469,17 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, unsigned long seg_boundary_size; int outcount, incount, i; struct iommu *iommu; + struct atu *atu; + struct iommu_map_table *tbl; + u64 mask; unsigned long base_shift; long err; BUG_ON(direction == DMA_NONE); iommu = dev->archdata.iommu; + atu = iommu->atu; + if (nelems == 0 || !iommu) return 0; @@ -424,7 +505,15 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, max_seg_size = dma_get_max_seg_size(dev); seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, IO_PAGE_SIZE) >> IO_PAGE_SHIFT; - base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT; + + mask = *dev->dma_mask; + if (mask <= DMA_BIT_MASK(32)) + tbl = &iommu->tbl; + else + tbl = &atu->tbl; + + base_shift = tbl->table_map_base >> IO_PAGE_SHIFT; + for_each_sg(sglist, s, nelems, i) { unsigned long paddr, npages, entry, out_entry = 0, slen; @@ -437,27 +526,26 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, /* Allocate iommu entries for that segment */ paddr = (unsigned long) SG_ENT_PHYS_ADDRESS(s); npages = iommu_num_pages(paddr, slen, IO_PAGE_SIZE); - entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, + entry = iommu_tbl_range_alloc(dev, tbl, npages, &handle, (unsigned long)(-1), 0); /* Handle failure */ if (unlikely(entry == IOMMU_ERROR_CODE)) { - if (printk_ratelimit()) - printk(KERN_INFO "iommu_alloc failed, iommu %p paddr %lx" - " npages %lx\n", iommu, paddr, npages); + pr_err_ratelimited("iommu_alloc failed, iommu %p paddr %lx npages %lx\n", + tbl, paddr, npages); goto iommu_map_failed; } - iommu_batch_new_entry(entry); + iommu_batch_new_entry(entry, mask); /* Convert entry to a dma_addr_t */ - dma_addr = iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT); + dma_addr = tbl->table_map_base + (entry << IO_PAGE_SHIFT); dma_addr |= (s->offset & ~IO_PAGE_MASK); /* Insert into HW table */ paddr &= IO_PAGE_MASK; while (npages--) { - err = iommu_batch_add(paddr); + err = iommu_batch_add(paddr, mask); if (unlikely(err < 0L)) goto iommu_map_failed; paddr += IO_PAGE_SIZE; @@ -492,7 +580,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, dma_next = dma_addr + slen; } - err = iommu_batch_end(); + err = iommu_batch_end(mask); if (unlikely(err < 0L)) goto iommu_map_failed; @@ -515,7 +603,7 @@ iommu_map_failed: vaddr = s->dma_address & IO_PAGE_MASK; npages = iommu_num_pages(s->dma_address, s->dma_length, IO_PAGE_SIZE); - iommu_tbl_range_free(&iommu->tbl, vaddr, npages, + iommu_tbl_range_free(tbl, vaddr, npages, IOMMU_ERROR_CODE); /* XXX demap? XXX */ s->dma_address = DMA_ERROR_CODE; @@ -536,13 +624,16 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, struct pci_pbm_info *pbm; struct scatterlist *sg; struct iommu *iommu; + struct atu *atu; unsigned long flags, entry; + unsigned long iotsb_num; u32 devhandle; BUG_ON(direction == DMA_NONE); iommu = dev->archdata.iommu; pbm = dev->archdata.host_controller; + atu = iommu->atu; devhandle = pbm->devhandle; local_irq_save(flags); @@ -552,15 +643,24 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, dma_addr_t dma_handle = sg->dma_address; unsigned int len = sg->dma_length; unsigned long npages; - struct iommu_map_table *tbl = &iommu->tbl; + struct iommu_map_table *tbl; unsigned long shift = IO_PAGE_SHIFT; if (!len) break; npages = iommu_num_pages(dma_handle, len, IO_PAGE_SIZE); + + if (dma_handle <= DMA_BIT_MASK(32)) { + iotsb_num = 0; /* we don't care for legacy iommu */ + tbl = &iommu->tbl; + } else { + iotsb_num = atu->iotsb->iotsb_num; + tbl = &atu->tbl; + } entry = ((dma_handle - tbl->table_map_base) >> shift); - dma_4v_iommu_demap(&devhandle, entry, npages); - iommu_tbl_range_free(&iommu->tbl, dma_handle, npages, + dma_4v_iommu_demap(dev, devhandle, dma_handle, iotsb_num, + entry, npages); + iommu_tbl_range_free(tbl, dma_handle, npages, IOMMU_ERROR_CODE); sg = sg_next(sg); } diff --git a/arch/sparc/kernel/pci_sun4v.h b/arch/sparc/kernel/pci_sun4v.h index 1019e0fe6e9d..22603a4e48bf 100644 --- a/arch/sparc/kernel/pci_sun4v.h +++ b/arch/sparc/kernel/pci_sun4v.h @@ -99,4 +99,15 @@ unsigned long pci_sun4v_iotsb_conf(unsigned long devhandle, unsigned long pci_sun4v_iotsb_bind(unsigned long devhandle, unsigned long iotsb_num, unsigned int pci_device); +unsigned long pci_sun4v_iotsb_map(unsigned long devhandle, + unsigned long iotsb_num, + unsigned long iotsb_index_iottes, + unsigned long io_attributes, + unsigned long io_page_list_pa, + long *mapped); +unsigned long pci_sun4v_iotsb_demap(unsigned long devhandle, + unsigned long iotsb_num, + unsigned long iotsb_index, + unsigned long iottes, + unsigned long *demapped); #endif /* !(_PCI_SUN4V_H) */ diff --git a/arch/sparc/kernel/pci_sun4v_asm.S b/arch/sparc/kernel/pci_sun4v_asm.S index 22024a96c317..578f09657916 100644 --- a/arch/sparc/kernel/pci_sun4v_asm.S +++ b/arch/sparc/kernel/pci_sun4v_asm.S @@ -392,3 +392,39 @@ ENTRY(pci_sun4v_iotsb_bind) retl nop ENDPROC(pci_sun4v_iotsb_bind) + + /* + * %o0: devhandle + * %o1: iotsb_num/iotsb_handle + * %o2: index_count + * %o3: iotte_attributes + * %o4: io_page_list_p + * %o5: &mapped + * + * returns %o0: status + * %o1: #mapped + */ +ENTRY(pci_sun4v_iotsb_map) + mov %o5, %g1 + mov HV_FAST_PCI_IOTSB_MAP, %o5 + ta HV_FAST_TRAP + retl + stx %o1, [%g1] +ENDPROC(pci_sun4v_iotsb_map) + + /* + * %o0: devhandle + * %o1: iotsb_num/iotsb_handle + * %o2: iotsb_index + * %o3: #iottes + * %o4: &demapped + * + * returns %o0: status + * %o1: #demapped + */ +ENTRY(pci_sun4v_iotsb_demap) + mov HV_FAST_PCI_IOTSB_DEMAP, %o5 + ta HV_FAST_TRAP + retl + stx %o1, [%o4] +ENDPROC(pci_sun4v_iotsb_demap) |