The Raspberry Pi Foundation released the new Compute Module 4 which we want to detect, so we can enable Ethernet on it and know the correct device tree file name.

Note that this sets the Ethernet option to true since the official CM4 IO board has an Ethernet port. But that might not be the case when using custom ones.

Signed-off-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Reviewed-by: Peter Robinson pbrobinson@gmail.com Tested-by: Peter Robinson pbrobinson@gmail.com --- board/raspberrypi/rpi/rpi.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/board/raspberrypi/rpi/rpi.c b/board/raspberrypi/rpi/rpi.c index b66698e4a9..abcf41a5a8 100644 --- a/board/raspberrypi/rpi/rpi.c +++ b/board/raspberrypi/rpi/rpi.c @@ -162,6 +162,11 @@ static const struct rpi_model rpi_models_new_scheme[] = { DTB_DIR "bcm2711-rpi-400.dtb", true, }, + [0x14] = { + "Compute Module 4", + DTB_DIR "bcm2711-rpi-cm4.dtb", + true, + }, };

static const struct rpi_model rpi_models_old_scheme[] = {

Add the following functions to get a specific device's DMA ranges: - dev_get_dma_range() - ofnode_get_dma_range() - of_get_dma_range() - fdt_get_dma_range() They are specially useful in oder to be able validate a physical address space range into a bus's and to convert addresses from and to address spaces.

Signed-off-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Reviewed-by: Simon Glass sjg@chromium.org Tested-by: Peter Robinson pbrobinson@gmail.com --- common/fdt_support.c | 73 +++++++++++++++++++++++++++++++++++++++ drivers/core/of_addr.c | 78 ++++++++++++++++++++++++++++++++++++++++++ drivers/core/ofnode.c | 9 +++++ drivers/core/read.c | 6 ++++ include/dm/of_addr.h | 17 +++++++++ include/dm/ofnode.h | 16 +++++++++ include/dm/read.h | 21 ++++++++++++ include/fdt_support.h | 14 ++++++++ 8 files changed, 234 insertions(+)

diff --git a/common/fdt_support.c b/common/fdt_support.c index 5ae75df3c6..bf855d26c8 100644 --- a/common/fdt_support.c +++ b/common/fdt_support.c @@ -1342,6 +1342,79 @@ u64 fdt_translate_dma_address(const void *blob, int node_offset, return __of_translate_address(blob, node_offset, in_addr, "dma-ranges"); }

+int fdt_get_dma_range(const void *blob, int node, phys_addr_t *cpu, + dma_addr_t *bus, u64 *size) +{ + bool found_dma_ranges = false; + struct of_bus *bus_node; + const fdt32_t *ranges; + int na, ns, pna, pns; + int parent = node; + int ret = 0; + int len; + + /* Find the closest dma-ranges property */ + while (parent >= 0) { + ranges = fdt_getprop(blob, parent, "dma-ranges", &len); + + /* Ignore empty ranges, they imply no translation required */ + if (ranges && len > 0) + break; + + /* Once we find 'dma-ranges', then a missing one is an error */ + if (found_dma_ranges && !ranges) { + ret = -EINVAL; + goto out; + } + + if (ranges) + found_dma_ranges = true; + + parent = fdt_parent_offset(blob, parent); + } + + if (!ranges || parent < 0) { + debug("no dma-ranges found for node %s\n", + fdt_get_name(blob, node, NULL)); + ret = -ENOENT; + goto out; + } + + /* switch to that node */ + node = parent; + parent = fdt_parent_offset(blob, node); + if (parent < 0) { + printf("Found dma-ranges in root node, shoudln't happen\n"); + ret = -EINVAL; + goto out; + } + + /* Get the address sizes both for the bus and its parent */ + bus_node = of_match_bus(blob, node); + bus_node->count_cells(blob, node, &na, &ns); + if (!OF_CHECK_COUNTS(na, ns)) { + printf("%s: Bad cell count for %s\n", __FUNCTION__, + fdt_get_name(blob, node, NULL)); + return -EINVAL; + goto out; + } + + bus_node = of_match_bus(blob, parent); + bus_node->count_cells(blob, parent, &pna, &pns); + if (!OF_CHECK_COUNTS(pna, pns)) { + printf("%s: Bad cell count for %s\n", __FUNCTION__, + fdt_get_name(blob, parent, NULL)); + return -EINVAL; + goto out; + } + + *bus = fdt_read_number(ranges, na); + *cpu = fdt_translate_dma_address(blob, node, ranges + na); + *size = fdt_read_number(ranges + na + pna, ns); +out: + return ret; +} + /** * fdt_node_offset_by_compat_reg: Find a node that matches compatiable and * who's reg property matches a physical cpu address diff --git a/drivers/core/of_addr.c b/drivers/core/of_addr.c index ca34d84922..703bc3e3f5 100644 --- a/drivers/core/of_addr.c +++ b/drivers/core/of_addr.c @@ -325,6 +325,84 @@ u64 of_translate_dma_address(const struct device_node *dev, const __be32 *in_add return __of_translate_address(dev, in_addr, "dma-ranges"); }

+int of_get_dma_range(const struct device_node *dev, phys_addr_t *cpu, + dma_addr_t *bus, u64 *size) +{ + bool found_dma_ranges = false; + struct device_node *parent; + struct of_bus *bus_node; + int na, ns, pna, pns; + const __be32 *ranges; + int ret = 0; + int len; + + /* Find the closest dma-ranges property */ + dev = of_node_get(dev); + while (dev) { + ranges = of_get_property(dev, "dma-ranges", &len); + + /* Ignore empty ranges, they imply no translation required */ + if (ranges && len > 0) + break; + + /* Once we find 'dma-ranges', then a missing one is an error */ + if (found_dma_ranges && !ranges) { + ret = -EINVAL; + goto out; + } + + if (ranges) + found_dma_ranges = true; + + parent = of_get_parent(dev); + of_node_put(dev); + dev = parent; + } + + if (!dev || !ranges) { + debug("no dma-ranges found for node %s\n", + of_node_full_name(dev)); + ret = -ENOENT; + goto out; + } + + /* switch to that node */ + parent = of_get_parent(dev); + if (!parent) { + printf("Found dma-ranges in root node, shoudln't happen\n"); + ret = -EINVAL; + goto out; + } + + /* Get the address sizes both for the bus and its parent */ + bus_node = of_match_bus((struct device_node*)dev); + bus_node->count_cells(dev, &na, &ns); + if (!OF_CHECK_COUNTS(na, ns)) { + printf("Bad cell count for %s\n", of_node_full_name(dev)); + return -EINVAL; + goto out_parent; + } + + bus_node = of_match_bus(parent); + bus_node->count_cells(parent, &pna, &pns); + if (!OF_CHECK_COUNTS(pna, pns)) { + printf("Bad cell count for %s\n", of_node_full_name(parent)); + return -EINVAL; + goto out_parent; + } + + *bus = of_read_number(ranges, na); + *cpu = of_translate_dma_address(dev, ranges + na); + *size = of_read_number(ranges + na + pna, ns); + +out_parent: + of_node_put(parent); +out: + of_node_put(dev); + return ret; +} + + static int __of_address_to_resource(const struct device_node *dev, const __be32 *addrp, u64 size, unsigned int flags, const char *name, struct resource *r) diff --git a/drivers/core/ofnode.c b/drivers/core/ofnode.c index 2a6e43ddc6..18bb375f19 100644 --- a/drivers/core/ofnode.c +++ b/drivers/core/ofnode.c @@ -923,6 +923,15 @@ u64 ofnode_translate_dma_address(ofnode node, const fdt32_t *in_addr) return fdt_translate_dma_address(gd->fdt_blob, ofnode_to_offset(node), in_addr); }

+int ofnode_get_dma_range(ofnode node, phys_addr_t *cpu, dma_addr_t *bus, u64 *size) +{ + if (ofnode_is_np(node)) + return of_get_dma_range(ofnode_to_np(node), cpu, bus, size); + else + return fdt_get_dma_range(gd->fdt_blob, ofnode_to_offset(node), + cpu, bus, size); +} + int ofnode_device_is_compatible(ofnode node, const char *compat) { if (ofnode_is_np(node)) diff --git a/drivers/core/read.c b/drivers/core/read.c index fc74d64814..e86c4b6740 100644 --- a/drivers/core/read.c +++ b/drivers/core/read.c @@ -340,6 +340,12 @@ u64 dev_translate_dma_address(const struct udevice *dev, const fdt32_t *in_addr) return ofnode_translate_dma_address(dev_ofnode(dev), in_addr); }

+int dev_get_dma_range(const struct udevice *dev, phys_addr_t *cpu, + dma_addr_t *bus, u64 *size) +{ + return ofnode_get_dma_range(dev_ofnode(dev), cpu, bus, size); +} + int dev_read_alias_highest_id(const char *stem) { if (of_live_active()) diff --git a/include/dm/of_addr.h b/include/dm/of_addr.h index 3fa1ffce81..ee21d5cf4f 100644 --- a/include/dm/of_addr.h +++ b/include/dm/of_addr.h @@ -44,6 +44,23 @@ u64 of_translate_address(const struct device_node *no, const __be32 *in_addr); */ u64 of_translate_dma_address(const struct device_node *no, const __be32 *in_addr);

+ +/** + * of_get_dma_range() - get dma-ranges for a specific DT node + * + * Get DMA ranges for a specifc node, this is useful to perform bus->cpu and + * cpu->bus address translations + * + * @param blob Pointer to device tree blob + * @param node_offset Node DT offset + * @param cpu Pointer to variable storing the range's cpu address + * @param bus Pointer to variable storing the range's bus address + * @param size Pointer to variable storing the range's size + * @return translated DMA address or OF_BAD_ADDR on error + */ +int of_get_dma_range(const struct device_node *dev, phys_addr_t *cpu, + dma_addr_t *bus, u64 *size); + /** * of_get_address() - obtain an address from a node * diff --git a/include/dm/ofnode.h b/include/dm/ofnode.h index 5b088650d3..c4680fbbaa 100644 --- a/include/dm/ofnode.h +++ b/include/dm/ofnode.h @@ -996,6 +996,22 @@ u64 ofnode_translate_address(ofnode node, const fdt32_t *in_addr); */ u64 ofnode_translate_dma_address(ofnode node, const fdt32_t *in_addr);

+/** + * ofnode_get_dma_range() - get dma-ranges for a specific DT node + * + * Get DMA ranges for a specifc node, this is useful to perform bus->cpu and + * cpu->bus address translations + * + * @param blob Pointer to device tree blob + * @param node_offset Node DT offset + * @param cpu Pointer to variable storing the range's cpu address + * @param bus Pointer to variable storing the range's bus address + * @param size Pointer to variable storing the range's size + * @return translated DMA address or OF_BAD_ADDR on error + */ +int ofnode_get_dma_range(ofnode node, phys_addr_t *cpu, dma_addr_t *bus, + u64 *size); + /** * ofnode_device_is_compatible() - check if the node is compatible with compat * diff --git a/include/dm/read.h b/include/dm/read.h index fc987f7759..e0e3da0bae 100644 --- a/include/dm/read.h +++ b/include/dm/read.h @@ -648,6 +648,21 @@ u64 dev_translate_address(const struct udevice *dev, const fdt32_t *in_addr); u64 dev_translate_dma_address(const struct udevice *dev, const fdt32_t *in_addr);

+/** + * dev_get_dma_range() - Get a device's DMA constraints + * + * Provide the address bases and size of the linear mapping between the CPU and + * a device's BUS address space. + * + * @dev: device giving the context in which to translate the DMA address + * @cpu: base address for CPU's view of memory + * @bus: base address for BUS's view of memory + * @size: size of the address space + * @return 0 if ok, negative on error + */ +int dev_get_dma_range(const struct udevice *dev, phys_addr_t *cpu, + dma_addr_t *bus, u64 *size); + /** * dev_read_alias_highest_id - Get highest alias id for the given stem * @stem: Alias stem to be examined @@ -988,6 +1003,12 @@ static inline u64 dev_translate_dma_address(const struct udevice *dev, return ofnode_translate_dma_address(dev_ofnode(dev), in_addr); }

+static inline int dev_get_dma_range(const struct udevice *dev, phys_addr_t *cpu, + dma_addr_t *bus, u64 *size) +{ + return ofnode_get_dma_range(dev_ofnode(dev), cpu, bus, size); +} + static inline int dev_read_alias_highest_id(const char *stem) { if (!CONFIG_IS_ENABLED(OF_LIBFDT)) diff --git a/include/fdt_support.h b/include/fdt_support.h index dbbac0fb6a..46eb1dbbb2 100644 --- a/include/fdt_support.h +++ b/include/fdt_support.h @@ -260,6 +260,20 @@ u64 fdt_translate_address(const void *blob, int node_offset, u64 fdt_translate_dma_address(const void *blob, int node_offset, const __be32 *in_addr);

+/** + * Get DMA ranges for a specifc node, this is useful to perform bus->cpu and + * cpu->bus address translations + * + * @param blob Pointer to device tree blob + * @param node_offset Node DT offset + * @param cpu Pointer to variable storing the range's cpu address + * @param bus Pointer to variable storing the range's bus address + * @param size Pointer to variable storing the range's size + * @return translated DMA address or OF_BAD_ADDR on error + */ +int fdt_get_dma_range(const void *blob, int node_offset, phys_addr_t *cpu, + dma_addr_t *bus, u64 *size); + int fdt_node_offset_by_compat_reg(void *blob, const char *compat, phys_addr_t compat_off); int fdt_alloc_phandle(void *blob);

Calculating the DMA offset between a bus address space and CPU's every time we call phys_to_bus() and bus_to_phys() isn't ideal performance wise, as it implies traversing the device tree from the device's node up to the root. Since this information is static and available before the device's initialization, parse it before the probe call an provide the DMA offset in 'struct udevice' for the address translation code to use it.

Signed-off-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Reviewed-by: Simon Glass sjg@chromium.org Tested-by: Peter Robinson pbrobinson@gmail.com ---

Changes since v5: - Use dev_has_ofnode()

drivers/core/Kconfig | 10 ++++++++++ drivers/core/device.c | 41 +++++++++++++++++++++++++++++++++++++++++ include/dm/device.h | 13 +++++++++++++ 3 files changed, 64 insertions(+)

diff --git a/drivers/core/Kconfig b/drivers/core/Kconfig index 65a503e76d..0932ee23a7 100644 --- a/drivers/core/Kconfig +++ b/drivers/core/Kconfig @@ -129,6 +129,16 @@ config TPL_DM_INLINE_OFNODE This applies to several ofnode functions (see ofnode.h) which are seldom used. Inlining them can help reduce code size.

+config DM_DMA + bool "Support per-device DMA constraints" + depends on DM + default n + help + Enable this to extract per-device DMA constraints, only supported on + device-tree systems for now. This is needed in order translate + addresses on systems where different buses have different views of + the physical address space. + config REGMAP bool "Support register maps" depends on DM diff --git a/drivers/core/device.c b/drivers/core/device.c index aeab3836ed..57424abf99 100644 --- a/drivers/core/device.c +++ b/drivers/core/device.c @@ -421,6 +421,43 @@ fail: return ret; }

+/** + * device_get_dma_constraints() - Populate device's DMA constraints + * + * Gets a device's DMA constraints from firmware. This information is later + * used by drivers to translate physcal addresses to the device's bus address + * space. For now only device-tree is supported. + * + * @dev: Pointer to target device + * Return: 0 if OK or if no DMA constraints were found, error otherwise + */ +static int device_get_dma_constraints(struct udevice *dev) +{ + struct udevice *parent = dev->parent; + phys_addr_t cpu = 0; + dma_addr_t bus = 0; + u64 size = 0; + int ret; + + if (!CONFIG_IS_ENABLED(DM_DMA) || !parent || !dev_has_ofnode(parent)) + return 0; + + /* + * We start parsing for dma-ranges from the device's bus node. This is + * specially important on nested buses. + */ + ret = dev_get_dma_range(parent, &cpu, &bus, &size); + /* Don't return an error if no 'dma-ranges' were found */ + if (ret && ret != -ENOENT) { + dm_warn("%s: failed to get DMA range, %d\n", dev->name, ret); + return ret; + } + + dev_set_dma_offset(dev, cpu - bus); + + return 0; +} + int device_probe(struct udevice *dev) { const struct driver *drv; @@ -474,6 +511,10 @@ int device_probe(struct udevice *dev) goto fail; }

+ ret = device_get_dma_constraints(dev); + if (ret) + goto fail; + ret = uclass_pre_probe_device(dev); if (ret) goto fail; diff --git a/include/dm/device.h b/include/dm/device.h index f5b4cd6876..9ac96fa28d 100644 --- a/include/dm/device.h +++ b/include/dm/device.h @@ -148,6 +148,8 @@ enum { * When CONFIG_DEVRES is enabled, devm_kmalloc() and friends will * add to this list. Memory so-allocated will be freed * automatically when the device is removed / unbound + * @dma_offset: Offset between the physical address space (CPU's) and the + * device's bus address space */ struct udevice { const struct driver *driver; @@ -172,6 +174,9 @@ struct udevice { #ifdef CONFIG_DEVRES struct list_head devres_head; #endif +#if CONFIG_IS_ENABLED(DM_DMA) + ulong dma_offset; +#endif };

/* Maximum sequence number supported */ @@ -213,6 +218,14 @@ static inline ofnode dev_ofnode(const struct udevice *dev) /* Returns non-zero if the device is active (probed and not removed) */ #define device_active(dev) (dev_get_flags(dev) & DM_FLAG_ACTIVATED)

+#if CONFIG_IS_ENABLED(DM_DMA) +#define dev_set_dma_offset(_dev, _offset) _dev->dma_offset = _offset +#define dev_get_dma_offset(_dev) _dev->dma_offset +#else +#define dev_set_dma_offset(_dev, _offset) +#define dev_get_dma_offset(_dev) 0 +#endif + static inline int dev_of_offset(const struct udevice *dev) { #if !CONFIG_IS_ENABLED(OF_PLATDATA)

These functions, instead of relying on hard-coded platform-specific address translations, make use of the DMA constraints provided by the DM core. This allows for per-device translations.

We can't yet get rid of the legacy phys_to_bus()/bus_to_phys() implementations as some of its users are not integrated into the device model.

Signed-off-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Reviewed-by: Simon Glass sjg@chromium.org Reviewed-by: Stefan Roese sr@denx.de Tested-by: Peter Robinson pbrobinson@gmail.com --- include/phys2bus.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)

diff --git a/include/phys2bus.h b/include/phys2bus.h index dc9b8e5a25..866b8b51a8 100644 --- a/include/phys2bus.h +++ b/include/phys2bus.h @@ -21,4 +21,21 @@ static inline unsigned long bus_to_phys(unsigned long bus) } #endif

+#if CONFIG_IS_ENABLED(DM) +#include <dm/device.h> + +static inline dma_addr_t dev_phys_to_bus(struct udevice *dev, phys_addr_t phys) +{ + return phys - dev_get_dma_offset(dev); +} + +static inline phys_addr_t dev_bus_to_phys(struct udevice *dev, dma_addr_t bus) +{ + return bus + dev_get_dma_offset(dev); +} +#else +#define dev_phys_to_bus(_, _addr) _addr +#define dev_bus_to_phys(_, _addr) _addr +#endif + #endif

So far we've been content with passing physical addresses when configuring memory addresses into XHCI controllers, but not all platforms have buses with transparent mappings. Specifically the Raspberry Pi 4 might introduce an offset to memory accesses incoming from its PCIe port.

Introduce xhci_virt_to_bus() and xhci_bus_to_virt() to cater with these limitations, and make sure we don't break non DM users.

Signed-off-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Reviewed-by: Simon Glass sjg@chromium.org Reviewed-by: Stefan Roese sr@denx.de Tested-by: Peter Robinson pbrobinson@gmail.com ---

Changes since v5: - Add missing address tranlation

drivers/usb/host/xhci-mem.c | 45 +++++++++++++++++++----------------- drivers/usb/host/xhci-ring.c | 13 +++++++---- drivers/usb/host/xhci.c | 4 ++-- include/usb/xhci.h | 20 +++++++++++++++- 4 files changed, 53 insertions(+), 29 deletions(-)

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index b002d6f166..83147d51b5 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -110,7 +110,7 @@ static void xhci_scratchpad_free(struct xhci_ctrl *ctrl)

ctrl->dcbaa->dev_context_ptrs[0] = 0;

- free((void *)(uintptr_t)le64_to_cpu(ctrl->scratchpad->sp_array[0])); + free(xhci_bus_to_virt(ctrl, le64_to_cpu(ctrl->scratchpad->sp_array[0]))); free(ctrl->scratchpad->sp_array); free(ctrl->scratchpad); ctrl->scratchpad = NULL; @@ -216,8 +216,8 @@ static void *xhci_malloc(unsigned int size) * @param link_trbs flag to indicate whether to link the trbs or NOT * @return none */ -static void xhci_link_segments(struct xhci_segment *prev, - struct xhci_segment *next, bool link_trbs) +static void xhci_link_segments(struct xhci_ctrl *ctrl, struct xhci_segment *prev, + struct xhci_segment *next, bool link_trbs) { u32 val; u64 val_64 = 0; @@ -226,7 +226,7 @@ static void xhci_link_segments(struct xhci_segment *prev, return; prev->next = next; if (link_trbs) { - val_64 = virt_to_phys(next->trbs); + val_64 = xhci_virt_to_bus(ctrl, next->trbs); prev->trbs[TRBS_PER_SEGMENT-1].link.segment_ptr = cpu_to_le64(val_64);

@@ -304,7 +304,8 @@ static struct xhci_segment *xhci_segment_alloc(void) * @param link_trbs flag to indicate whether to link the trbs or NOT * @return pointer to the newly created RING */ -struct xhci_ring *xhci_ring_alloc(unsigned int num_segs, bool link_trbs) +struct xhci_ring *xhci_ring_alloc(struct xhci_ctrl *ctrl, unsigned int num_segs, + bool link_trbs) { struct xhci_ring *ring; struct xhci_segment *prev; @@ -327,12 +328,12 @@ struct xhci_ring *xhci_ring_alloc(unsigned int num_segs, bool link_trbs) next = xhci_segment_alloc(); BUG_ON(!next);

- xhci_link_segments(prev, next, link_trbs); + xhci_link_segments(ctrl, prev, next, link_trbs);

prev = next; num_segs--; } - xhci_link_segments(prev, ring->first_seg, link_trbs); + xhci_link_segments(ctrl, prev, ring->first_seg, link_trbs); if (link_trbs) { /* See section 4.9.2.1 and 6.4.4.1 */ prev->trbs[TRBS_PER_SEGMENT-1].link.control |= @@ -354,6 +355,7 @@ static int xhci_scratchpad_alloc(struct xhci_ctrl *ctrl) struct xhci_hccr *hccr = ctrl->hccr; struct xhci_hcor *hcor = ctrl->hcor; struct xhci_scratchpad *scratchpad; + uint64_t val_64; int num_sp; uint32_t page_size; void *buf; @@ -371,8 +373,9 @@ static int xhci_scratchpad_alloc(struct xhci_ctrl *ctrl) scratchpad->sp_array = xhci_malloc(num_sp * sizeof(u64)); if (!scratchpad->sp_array) goto fail_sp2; - ctrl->dcbaa->dev_context_ptrs[0] = - cpu_to_le64((uintptr_t)scratchpad->sp_array); + + val_64 = xhci_virt_to_bus(ctrl, scratchpad->sp_array); + ctrl->dcbaa->dev_context_ptrs[0] = cpu_to_le64(val_64);

xhci_flush_cache((uintptr_t)&ctrl->dcbaa->dev_context_ptrs[0], sizeof(ctrl->dcbaa->dev_context_ptrs[0])); @@ -393,8 +396,8 @@ static int xhci_scratchpad_alloc(struct xhci_ctrl *ctrl) xhci_flush_cache((uintptr_t)buf, num_sp * page_size);

for (i = 0; i < num_sp; i++) { - uintptr_t ptr = (uintptr_t)buf + i * page_size; - scratchpad->sp_array[i] = cpu_to_le64(ptr); + val_64 = xhci_virt_to_bus(ctrl, buf + i * page_size); + scratchpad->sp_array[i] = cpu_to_le64(val_64); }

xhci_flush_cache((uintptr_t)scratchpad->sp_array, @@ -484,9 +487,9 @@ int xhci_alloc_virt_device(struct xhci_ctrl *ctrl, unsigned int slot_id) }

/* Allocate endpoint 0 ring */ - virt_dev->eps[0].ring = xhci_ring_alloc(1, true); + virt_dev->eps[0].ring = xhci_ring_alloc(ctrl, 1, true);

- byte_64 = virt_to_phys(virt_dev->out_ctx->bytes); + byte_64 = xhci_virt_to_bus(ctrl, virt_dev->out_ctx->bytes);

/* Point to output device context in dcbaa. */ ctrl->dcbaa->dev_context_ptrs[slot_id] = cpu_to_le64(byte_64); @@ -522,15 +525,15 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr, return -ENOMEM; }

- val_64 = virt_to_phys(ctrl->dcbaa); + val_64 = xhci_virt_to_bus(ctrl, ctrl->dcbaa); /* Set the pointer in DCBAA register */ xhci_writeq(&hcor->or_dcbaap, val_64);

/* Command ring control pointer register initialization */ - ctrl->cmd_ring = xhci_ring_alloc(1, true); + ctrl->cmd_ring = xhci_ring_alloc(ctrl, 1, true);

/* Set the address in the Command Ring Control register */ - trb_64 = virt_to_phys(ctrl->cmd_ring->first_seg->trbs); + trb_64 = xhci_virt_to_bus(ctrl, ctrl->cmd_ring->first_seg->trbs); val_64 = xhci_readq(&hcor->or_crcr); val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) | (trb_64 & (u64) ~CMD_RING_RSVD_BITS) | @@ -551,7 +554,7 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr, ctrl->ir_set = &ctrl->run_regs->ir_set[0];

/* Event ring does not maintain link TRB */ - ctrl->event_ring = xhci_ring_alloc(ERST_NUM_SEGS, false); + ctrl->event_ring = xhci_ring_alloc(ctrl, ERST_NUM_SEGS, false); ctrl->erst.entries = xhci_malloc(sizeof(struct xhci_erst_entry) * ERST_NUM_SEGS);

@@ -560,8 +563,8 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr, for (val = 0, seg = ctrl->event_ring->first_seg; val < ERST_NUM_SEGS; val++) { - trb_64 = virt_to_phys(seg->trbs); struct xhci_erst_entry *entry = &ctrl->erst.entries[val]; + trb_64 = xhci_virt_to_bus(ctrl, seg->trbs); entry->seg_addr = cpu_to_le64(trb_64); entry->seg_size = cpu_to_le32(TRBS_PER_SEGMENT); entry->rsvd = 0; @@ -570,7 +573,7 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr, xhci_flush_cache((uintptr_t)ctrl->erst.entries, ERST_NUM_SEGS * sizeof(struct xhci_erst_entry));

- deq = virt_to_phys(ctrl->event_ring->dequeue); + deq = xhci_virt_to_bus(ctrl, ctrl->event_ring->dequeue);

/* Update HC event ring dequeue pointer */ xhci_writeq(&ctrl->ir_set->erst_dequeue, @@ -585,7 +588,7 @@ int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr, /* this is the event ring segment table pointer */ val_64 = xhci_readq(&ctrl->ir_set->erst_base); val_64 &= ERST_PTR_MASK; - val_64 |= virt_to_phys(ctrl->erst.entries) & ~ERST_PTR_MASK; + val_64 |= xhci_virt_to_bus(ctrl, ctrl->erst.entries) & ~ERST_PTR_MASK;

xhci_writeq(&ctrl->ir_set->erst_base, val_64);

@@ -848,7 +851,7 @@ void xhci_setup_addressable_virt_dev(struct xhci_ctrl *ctrl, /* EP 0 can handle "burst" sizes of 1, so Max Burst Size field is 0 */ ep0_ctx->ep_info2 |= cpu_to_le32(MAX_BURST(0) | ERROR_COUNT(3));

- trb_64 = virt_to_phys(virt_dev->eps[0].ring->first_seg->trbs); + trb_64 = xhci_virt_to_bus(ctrl, virt_dev->eps[0].ring->first_seg->trbs); ep0_ctx->deq = cpu_to_le64(trb_64 | virt_dev->eps[0].ring->cycle_state);

/* diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index d708fc928b..6b31ad4398 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -275,10 +275,13 @@ void xhci_queue_command(struct xhci_ctrl *ctrl, u8 *ptr, u32 slot_id, u32 ep_index, trb_type cmd) { u32 fields[4]; - u64 val_64 = virt_to_phys(ptr); + u64 val_64 = 0;

BUG_ON(prepare_ring(ctrl, ctrl->cmd_ring, EP_STATE_RUNNING));

+ if (ptr) + val_64 = xhci_virt_to_bus(ctrl, ptr); + fields[0] = lower_32_bits(val_64); fields[1] = upper_32_bits(val_64); fields[2] = 0; @@ -401,7 +404,7 @@ void xhci_acknowledge_event(struct xhci_ctrl *ctrl)

/* Inform the hardware */ xhci_writeq(&ctrl->ir_set->erst_dequeue, - virt_to_phys(ctrl->event_ring->dequeue) | ERST_EHB); + xhci_virt_to_bus(ctrl, ctrl->event_ring->dequeue) | ERST_EHB); }

/** @@ -579,7 +582,7 @@ int xhci_bulk_tx(struct usb_device *udev, unsigned long pipe, u64 addr; int ret; u32 trb_fields[4]; - u64 val_64 = virt_to_phys(buffer); + u64 val_64 = xhci_virt_to_bus(ctrl, buffer); void *last_transfer_trb_addr; int available_length;

@@ -723,7 +726,7 @@ again: return -ETIMEDOUT; }

- if ((uintptr_t)(le64_to_cpu(event->trans_event.buffer)) + if ((uintptr_t)(le64_to_cpu(xhci_bus_to_virt(ctrl, event->trans_event.buffer))) != (uintptr_t)last_transfer_trb_addr) { available_length -= (int)EVENT_TRB_LEN(le32_to_cpu(event->trans_event.transfer_len)); @@ -884,7 +887,7 @@ int xhci_ctrl_tx(struct usb_device *udev, unsigned long pipe, if (length > 0) { if (req->requesttype & USB_DIR_IN) field |= TRB_DIR_IN; - buf_64 = virt_to_phys(buffer); + buf_64 = xhci_virt_to_bus(ctrl, buffer);

trb_fields[0] = lower_32_bits(buf_64); trb_fields[1] = upper_32_bits(buf_64); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 7080f8fabe..d27ac01c83 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -604,7 +604,7 @@ static int xhci_set_configuration(struct usb_device *udev) ep_ctx[ep_index] = xhci_get_ep_ctx(ctrl, in_ctx, ep_index);

/* Allocate the ep rings */ - virt_dev->eps[ep_index].ring = xhci_ring_alloc(1, true); + virt_dev->eps[ep_index].ring = xhci_ring_alloc(ctrl, 1, true); if (!virt_dev->eps[ep_index].ring) return -ENOMEM;

@@ -628,7 +628,7 @@ static int xhci_set_configuration(struct usb_device *udev) cpu_to_le32(MAX_BURST(max_burst) | ERROR_COUNT(err_count));

- trb_64 = virt_to_phys(virt_dev->eps[ep_index].ring->enqueue); + trb_64 = xhci_virt_to_bus(ctrl, virt_dev->eps[ep_index].ring->enqueue); ep_ctx[ep_index]->deq = cpu_to_le64(trb_64 | virt_dev->eps[ep_index].ring->cycle_state);

diff --git a/include/usb/xhci.h b/include/usb/xhci.h index e1d382369a..8d95e213b0 100644 --- a/include/usb/xhci.h +++ b/include/usb/xhci.h @@ -16,6 +16,7 @@ #ifndef HOST_XHCI_H_ #define HOST_XHCI_H_

+#include <phys2bus.h> #include <reset.h> #include <asm/types.h> #include <asm/cache.h> @@ -1221,6 +1222,12 @@ struct xhci_ctrl { #define XHCI_MTK_HOST BIT(0) };

+#if CONFIG_IS_ENABLED(DM_USB) +#define xhci_to_dev(_ctrl) _ctrl->dev +#else +#define xhci_to_dev(_ctrl) NULL +#endif + unsigned long trb_addr(struct xhci_segment *seg, union xhci_trb *trb); struct xhci_input_control_ctx *xhci_get_input_control_ctx(struct xhci_container_ctx *ctx); @@ -1250,7 +1257,8 @@ int xhci_check_maxpacket(struct usb_device *udev); void xhci_flush_cache(uintptr_t addr, u32 type_len); void xhci_inval_cache(uintptr_t addr, u32 type_len); void xhci_cleanup(struct xhci_ctrl *ctrl); -struct xhci_ring *xhci_ring_alloc(unsigned int num_segs, bool link_trbs); +struct xhci_ring *xhci_ring_alloc(struct xhci_ctrl *ctrl, unsigned int num_segs, + bool link_trbs); int xhci_alloc_virt_device(struct xhci_ctrl *ctrl, unsigned int slot_id); int xhci_mem_init(struct xhci_ctrl *ctrl, struct xhci_hccr *hccr, struct xhci_hcor *hcor); @@ -1278,4 +1286,14 @@ extern struct dm_usb_ops xhci_usb_ops;

struct xhci_ctrl *xhci_get_ctrl(struct usb_device *udev);

+static inline dma_addr_t xhci_virt_to_bus(struct xhci_ctrl *ctrl, void *addr) +{ + return dev_phys_to_bus(xhci_to_dev(ctrl), virt_to_phys(addr)); +} + +static inline void *xhci_bus_to_virt(struct xhci_ctrl *ctrl, dma_addr_t addr) +{ + return phys_to_virt(dev_bus_to_phys(xhci_to_dev(ctrl), addr)); +} + #endif /* HOST_XHCI_H_ */

The DM_DMA option is needed in order to translate physical address into bus addresses on a per-device basis.

Signed-off-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Reviewed-by: Simon Glass sjg@chromium.org Tested-by: Peter Robinson pbrobinson@gmail.com --- configs/rpi_4_32b_defconfig | 1 + configs/rpi_4_defconfig | 1 + configs/rpi_arm64_defconfig | 1 + 3 files changed, 3 insertions(+)

diff --git a/configs/rpi_4_32b_defconfig b/configs/rpi_4_32b_defconfig index 5ddd838fd5..0a5d3ff8cd 100644 --- a/configs/rpi_4_32b_defconfig +++ b/configs/rpi_4_32b_defconfig @@ -22,6 +22,7 @@ CONFIG_OF_BOARD=y CONFIG_ENV_FAT_DEVICE_AND_PART="0:1" CONFIG_SYS_RELOC_GD_ENV_ADDR=y CONFIG_ENV_VARS_UBOOT_RUNTIME_CONFIG=y +CONFIG_DM_DMA=y CONFIG_DFU_MMC=y CONFIG_DM_KEYBOARD=y CONFIG_DM_MMC=y diff --git a/configs/rpi_4_defconfig b/configs/rpi_4_defconfig index 2590d0a696..b61cdc05f1 100644 --- a/configs/rpi_4_defconfig +++ b/configs/rpi_4_defconfig @@ -22,6 +22,7 @@ CONFIG_OF_BOARD=y CONFIG_ENV_FAT_DEVICE_AND_PART="0:1" CONFIG_SYS_RELOC_GD_ENV_ADDR=y CONFIG_ENV_VARS_UBOOT_RUNTIME_CONFIG=y +CONFIG_DM_DMA=y CONFIG_DFU_MMC=y CONFIG_DM_KEYBOARD=y CONFIG_DM_MMC=y diff --git a/configs/rpi_arm64_defconfig b/configs/rpi_arm64_defconfig index 2639219a1a..4125a1feba 100644 --- a/configs/rpi_arm64_defconfig +++ b/configs/rpi_arm64_defconfig @@ -20,6 +20,7 @@ CONFIG_CMD_FS_UUID=y CONFIG_OF_BOARD=y CONFIG_ENV_FAT_DEVICE_AND_PART="0:1" CONFIG_ENV_VARS_UBOOT_RUNTIME_CONFIG=y +CONFIG_DM_DMA=y CONFIG_DM_KEYBOARD=y CONFIG_DM_MMC=y CONFIG_MMC_SDHCI=y