diff options
Diffstat (limited to 'drivers/usb/host/xhci-mem.c')
| -rw-r--r-- | drivers/usb/host/xhci-mem.c | 226 |
1 files changed, 164 insertions, 62 deletions
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 873c272b3ef..c089668308a 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -149,14 +149,140 @@ static void xhci_link_rings(struct xhci_hcd *xhci, struct xhci_ring *ring, } } +/* + * We need a radix tree for mapping physical addresses of TRBs to which stream + * ID they belong to. We need to do this because the host controller won't tell + * us which stream ring the TRB came from. We could store the stream ID in an + * event data TRB, but that doesn't help us for the cancellation case, since the + * endpoint may stop before it reaches that event data TRB. + * + * The radix tree maps the upper portion of the TRB DMA address to a ring + * segment that has the same upper portion of DMA addresses. For example, say I + * have segments of size 1KB, that are always 1KB aligned. A segment may + * start at 0x10c91000 and end at 0x10c913f0. If I use the upper 10 bits, the + * key to the stream ID is 0x43244. I can use the DMA address of the TRB to + * pass the radix tree a key to get the right stream ID: + * + * 0x10c90fff >> 10 = 0x43243 + * 0x10c912c0 >> 10 = 0x43244 + * 0x10c91400 >> 10 = 0x43245 + * + * Obviously, only those TRBs with DMA addresses that are within the segment + * will make the radix tree return the stream ID for that ring. + * + * Caveats for the radix tree: + * + * The radix tree uses an unsigned long as a key pair. On 32-bit systems, an + * unsigned long will be 32-bits; on a 64-bit system an unsigned long will be + * 64-bits. Since we only request 32-bit DMA addresses, we can use that as the + * key on 32-bit or 64-bit systems (it would also be fine if we asked for 64-bit + * PCI DMA addresses on a 64-bit system). There might be a problem on 32-bit + * extended systems (where the DMA address can be bigger than 32-bits), + * if we allow the PCI dma mask to be bigger than 32-bits. So don't do that. + */ +static int xhci_insert_segment_mapping(struct radix_tree_root *trb_address_map, + struct xhci_ring *ring, + struct xhci_segment *seg, + gfp_t mem_flags) +{ + unsigned long key; + int ret; + + key = (unsigned long)(seg->dma >> TRB_SEGMENT_SHIFT); + /* Skip any segments that were already added. */ + if (radix_tree_lookup(trb_address_map, key)) + return 0; + + ret = radix_tree_maybe_preload(mem_flags); + if (ret) + return ret; + ret = radix_tree_insert(trb_address_map, + key, ring); + radix_tree_preload_end(); + return ret; +} + +static void xhci_remove_segment_mapping(struct radix_tree_root *trb_address_map, + struct xhci_segment *seg) +{ + unsigned long key; + + key = (unsigned long)(seg->dma >> TRB_SEGMENT_SHIFT); + if (radix_tree_lookup(trb_address_map, key)) + radix_tree_delete(trb_address_map, key); +} + +static int xhci_update_stream_segment_mapping( + struct radix_tree_root *trb_address_map, + struct xhci_ring *ring, + struct xhci_segment *first_seg, + struct xhci_segment *last_seg, + gfp_t mem_flags) +{ + struct xhci_segment *seg; + struct xhci_segment *failed_seg; + int ret; + + if (WARN_ON_ONCE(trb_address_map == NULL)) + return 0; + + seg = first_seg; + do { + ret = xhci_insert_segment_mapping(trb_address_map, + ring, seg, mem_flags); + if (ret) + goto remove_streams; + if (seg == last_seg) + return 0; + seg = seg->next; + } while (seg != first_seg); + + return 0; + +remove_streams: + failed_seg = seg; + seg = first_seg; + do { + xhci_remove_segment_mapping(trb_address_map, seg); + if (seg == failed_seg) + return ret; + seg = seg->next; + } while (seg != first_seg); + + return ret; +} + +static void xhci_remove_stream_mapping(struct xhci_ring *ring) +{ + struct xhci_segment *seg; + + if (WARN_ON_ONCE(ring->trb_address_map == NULL)) + return; + + seg = ring->first_seg; + do { + xhci_remove_segment_mapping(ring->trb_address_map, seg); + seg = seg->next; + } while (seg != ring->first_seg); +} + +static int xhci_update_stream_mapping(struct xhci_ring *ring, gfp_t mem_flags) +{ + return xhci_update_stream_segment_mapping(ring->trb_address_map, ring, + ring->first_seg, ring->last_seg, mem_flags); +} + /* XXX: Do we need the hcd structure in all these functions? */ void xhci_ring_free(struct xhci_hcd *xhci, struct xhci_ring *ring) { if (!ring) return; - if (ring->first_seg) + if (ring->first_seg) { + if (ring->type == TYPE_STREAM) + xhci_remove_stream_mapping(ring); xhci_free_segments_for_ring(xhci, ring->first_seg); + } kfree(ring); } @@ -349,6 +475,21 @@ int xhci_ring_expansion(struct xhci_hcd *xhci, struct xhci_ring *ring, if (ret) return -ENOMEM; + if (ring->type == TYPE_STREAM) + ret = xhci_update_stream_segment_mapping(ring->trb_address_map, + ring, first, last, flags); + if (ret) { + struct xhci_segment *next; + do { + next = first->next; + xhci_segment_free(xhci, first); + if (first == last) + break; + first = next; + } while (true); + return ret; + } + xhci_link_rings(xhci, ring, first, last, num_segs); xhci_dbg_trace(xhci, trace_xhci_dbg_ring_expansion, "ring expansion succeed, now has %d segments", @@ -434,12 +575,12 @@ static void xhci_free_stream_ctx(struct xhci_hcd *xhci, struct xhci_stream_ctx *stream_ctx, dma_addr_t dma) { struct device *dev = xhci_to_hcd(xhci)->self.controller; + size_t size = sizeof(struct xhci_stream_ctx) * num_stream_ctxs; - if (num_stream_ctxs > MEDIUM_STREAM_ARRAY_SIZE) - dma_free_coherent(dev, - sizeof(struct xhci_stream_ctx)*num_stream_ctxs, + if (size > MEDIUM_STREAM_ARRAY_SIZE) + dma_free_coherent(dev, size, stream_ctx, dma); - else if (num_stream_ctxs <= SMALL_STREAM_ARRAY_SIZE) + else if (size <= SMALL_STREAM_ARRAY_SIZE) return dma_pool_free(xhci->small_streams_pool, stream_ctx, dma); else @@ -462,12 +603,12 @@ static struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci, gfp_t mem_flags) { struct device *dev = xhci_to_hcd(xhci)->self.controller; + size_t size = sizeof(struct xhci_stream_ctx) * num_stream_ctxs; - if (num_stream_ctxs > MEDIUM_STREAM_ARRAY_SIZE) - return dma_alloc_coherent(dev, - sizeof(struct xhci_stream_ctx)*num_stream_ctxs, + if (size > MEDIUM_STREAM_ARRAY_SIZE) + return dma_alloc_coherent(dev, size, dma, mem_flags); - else if (num_stream_ctxs <= SMALL_STREAM_ARRAY_SIZE) + else if (size <= SMALL_STREAM_ARRAY_SIZE) return dma_pool_alloc(xhci->small_streams_pool, mem_flags, dma); else @@ -510,36 +651,6 @@ struct xhci_ring *xhci_stream_id_to_ring( * The number of stream contexts in the stream context array may be bigger than * the number of streams the driver wants to use. This is because the number of * stream context array entries must be a power of two. - * - * We need a radix tree for mapping physical addresses of TRBs to which stream - * ID they belong to. We need to do this because the host controller won't tell - * us which stream ring the TRB came from. We could store the stream ID in an - * event data TRB, but that doesn't help us for the cancellation case, since the - * endpoint may stop before it reaches that event data TRB. - * - * The radix tree maps the upper portion of the TRB DMA address to a ring - * segment that has the same upper portion of DMA addresses. For example, say I - * have segments of size 1KB, that are always 64-byte aligned. A segment may - * start at 0x10c91000 and end at 0x10c913f0. If I use the upper 10 bits, the - * key to the stream ID is 0x43244. I can use the DMA address of the TRB to - * pass the radix tree a key to get the right stream ID: - * - * 0x10c90fff >> 10 = 0x43243 - * 0x10c912c0 >> 10 = 0x43244 - * 0x10c91400 >> 10 = 0x43245 - * - * Obviously, only those TRBs with DMA addresses that are within the segment - * will make the radix tree return the stream ID for that ring. - * - * Caveats for the radix tree: - * - * The radix tree uses an unsigned long as a key pair. On 32-bit systems, an - * unsigned long will be 32-bits; on a 64-bit system an unsigned long will be - * 64-bits. Since we only request 32-bit DMA addresses, we can use that as the - * key on 32-bit or 64-bit systems (it would also be fine if we asked for 64-bit - * PCI DMA addresses on a 64-bit system). There might be a problem on 32-bit - * extended systems (where the DMA address can be bigger than 32-bits), - * if we allow the PCI dma mask to be bigger than 32-bits. So don't do that. */ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci, unsigned int num_stream_ctxs, @@ -548,7 +659,6 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci, struct xhci_stream_info *stream_info; u32 cur_stream; struct xhci_ring *cur_ring; - unsigned long key; u64 addr; int ret; @@ -603,6 +713,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci, if (!cur_ring) goto cleanup_rings; cur_ring->stream_id = cur_stream; + cur_ring->trb_address_map = &stream_info->trb_address_map; /* Set deq ptr, cycle bit, and stream context type */ addr = cur_ring->first_seg->dma | SCT_FOR_CTX(SCT_PRI_TR) | @@ -612,10 +723,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci, xhci_dbg(xhci, "Setting stream %d ring ptr to 0x%08llx\n", cur_stream, (unsigned long long) addr); - key = (unsigned long) - (cur_ring->first_seg->dma >> TRB_SEGMENT_SHIFT); - ret = radix_tree_insert(&stream_info->trb_address_map, - key, cur_ring); + ret = xhci_update_stream_mapping(cur_ring, mem_flags); if (ret) { xhci_ring_free(xhci, cur_ring); stream_info->stream_rings[cur_stream] = NULL; @@ -635,9 +743,6 @@ cleanup_rings: for (cur_stream = 1; cur_stream < num_streams; cur_stream++) { cur_ring = stream_info->stream_rings[cur_stream]; if (cur_ring) { - addr = cur_ring->first_seg->dma; - radix_tree_delete(&stream_info->trb_address_map, - addr >> TRB_SEGMENT_SHIFT); xhci_ring_free(xhci, cur_ring); stream_info->stream_rings[cur_stream] = NULL; } @@ -698,7 +803,6 @@ void xhci_free_stream_info(struct xhci_hcd *xhci, { int cur_stream; struct xhci_ring *cur_ring; - dma_addr_t addr; if (!stream_info) return; @@ -707,9 +811,6 @@ void xhci_free_stream_info(struct xhci_hcd *xhci, cur_stream++) { cur_ring = stream_info->stream_rings[cur_stream]; if (cur_ring) { - addr = cur_ring->first_seg->dma; - radix_tree_delete(&stream_info->trb_address_map, - addr >> TRB_SEGMENT_SHIFT); xhci_ring_free(xhci, cur_ring); stream_info->stream_rings[cur_stream] = NULL; } @@ -1711,7 +1812,6 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) if (xhci->lpm_command) xhci_free_command(xhci, xhci->lpm_command); - xhci->cmd_ring_reserved_trbs = 0; if (xhci->cmd_ring) xhci_ring_free(xhci, xhci->cmd_ring); xhci->cmd_ring = NULL; @@ -1776,6 +1876,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci) } no_bw: + xhci->cmd_ring_reserved_trbs = 0; xhci->num_usb2_ports = 0; xhci->num_usb3_ports = 0; xhci->num_active_eps = 0; @@ -1958,7 +2059,7 @@ static void xhci_set_hc_event_deq(struct xhci_hcd *xhci) xhci_warn(xhci, "WARN something wrong with SW event ring " "dequeue ptr.\n"); /* Update HC event ring dequeue pointer */ - temp = readq(&xhci->ir_set->erst_dequeue); + temp = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue); temp &= ERST_PTR_MASK; /* Don't clear the EHB bit (which is RW1C) because * there might be more events to service. @@ -1967,7 +2068,7 @@ static void xhci_set_hc_event_deq(struct xhci_hcd *xhci) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Write event ring dequeue pointer, " "preserving EHB bit"); - writeq(((u64) deq & (u64) ~ERST_PTR_MASK) | temp, + xhci_write_64(xhci, ((u64) deq & (u64) ~ERST_PTR_MASK) | temp, &xhci->ir_set->erst_dequeue); } @@ -2269,16 +2370,17 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Device context base array address = 0x%llx (DMA), %p (virt)", (unsigned long long)xhci->dcbaa->dma, xhci->dcbaa); - writeq(dma, &xhci->op_regs->dcbaa_ptr); + xhci_write_64(xhci, dma, &xhci->op_regs->dcbaa_ptr); /* * Initialize the ring segment pool. The ring must be a contiguous * structure comprised of TRBs. The TRBs must be 16 byte aligned, - * however, the command ring segment needs 64-byte aligned segments, - * so we pick the greater alignment need. + * however, the command ring segment needs 64-byte aligned segments + * and our use of dma addresses in the trb_address_map radix tree needs + * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need. */ xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, - TRB_SEGMENT_SIZE, 64, xhci->page_size); + TRB_SEGMENT_SIZE, TRB_SEGMENT_SIZE, xhci->page_size); /* See Table 46 and Note on Figure 55 */ xhci->device_pool = dma_pool_create("xHCI input/output contexts", dev, @@ -2312,13 +2414,13 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) (unsigned long long)xhci->cmd_ring->first_seg->dma); /* Set the address in the Command Ring Control register */ - val_64 = readq(&xhci->op_regs->cmd_ring); + val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring); val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) | (xhci->cmd_ring->first_seg->dma & (u64) ~CMD_RING_RSVD_BITS) | xhci->cmd_ring->cycle_state; xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Setting command ring address to 0x%x", val); - writeq(val_64, &xhci->op_regs->cmd_ring); + xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring); xhci_dbg_cmd_ptrs(xhci); xhci->lpm_command = xhci_alloc_command(xhci, true, true, flags); @@ -2396,10 +2498,10 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Set ERST base address for ir_set 0 = 0x%llx", (unsigned long long)xhci->erst.erst_dma_addr); - val_64 = readq(&xhci->ir_set->erst_base); + val_64 = xhci_read_64(xhci, &xhci->ir_set->erst_base); val_64 &= ERST_PTR_MASK; val_64 |= (xhci->erst.erst_dma_addr & (u64) ~ERST_PTR_MASK); - writeq(val_64, &xhci->ir_set->erst_base); + xhci_write_64(xhci, val_64, &xhci->ir_set->erst_base); /* Set the event ring dequeue address */ xhci_set_hc_event_deq(xhci); |