From 1a3c7d0841ae24d28a15bbf87ee7d08614cec957 Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Sat, 11 Jun 2022 01:25:11 -0700 Subject: [PATCH 01/45] swiotlb: remove the unused swiotlb_force declaration The 'swiotlb_force' is removed since commit c6af2aa9ffc9 ("swiotlb: make the swiotlb_init interface more useful"). Signed-off-by: Dongli Zhang Signed-off-by: Christoph Hellwig --- include/linux/swiotlb.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 7ed35dd3de6e..bdc58a0e20b1 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -60,7 +60,6 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs); #ifdef CONFIG_SWIOTLB -extern enum swiotlb_force swiotlb_force; /** * struct io_tlb_mem - IO TLB Memory Pool Descriptor From 466298c65678e7a2bd7bd268fd3776de73e96a4b Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Sat, 11 Jun 2022 01:25:12 -0700 Subject: [PATCH 02/45] swiotlb: remove a useless return in swiotlb_init Both swiotlb_init_remap() and swiotlb_init() have return type void. Signed-off-by: Dongli Zhang Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index cb50f8d38360..fd21f4162f4b 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -282,7 +282,7 @@ retry: void __init swiotlb_init(bool addressing_limit, unsigned int flags) { - return swiotlb_init_remap(addressing_limit, flags, NULL); + swiotlb_init_remap(addressing_limit, flags, NULL); } /* From 04c14e8e38b06edf934e9bb0cc504afd94d593fb Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Sat, 11 Jun 2022 01:25:13 -0700 Subject: [PATCH 03/45] x86/swiotlb: fix param usage in boot-options.rst Fix the usage of swiotlb param in kernel doc. Signed-off-by: Dongli Zhang Signed-off-by: Christoph Hellwig --- Documentation/x86/x86_64/boot-options.rst | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/Documentation/x86/x86_64/boot-options.rst b/Documentation/x86/x86_64/boot-options.rst index 03ec9cf01181..cbd14124a667 100644 --- a/Documentation/x86/x86_64/boot-options.rst +++ b/Documentation/x86/x86_64/boot-options.rst @@ -287,11 +287,13 @@ iommu options only relevant to the AMD GART hardware IOMMU: iommu options only relevant to the software bounce buffering (SWIOTLB) IOMMU implementation: - swiotlb=[,force] - - Prereserve that many 128K pages for the software IO bounce buffering. + swiotlb=[,force,noforce] + + Prereserve that many 2K slots for the software IO bounce buffering. force Force all IO through the software TLB. + noforce + Do not initialize the software TLB. Miscellaneous From 0bf28fc40d89b1a3e00d1b79473bad4e9ca20ad1 Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Sat, 11 Jun 2022 01:25:14 -0700 Subject: [PATCH 04/45] swiotlb: panic if nslabs is too small Panic on purpose if nslabs is too small, in order to sync with the remap retry logic. In addition, print the number of bytes for tlb alloc failure. Signed-off-by: Dongli Zhang Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index fd21f4162f4b..1758b724c7a8 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -242,6 +242,9 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, if (swiotlb_force_disable) return; + if (nslabs < IO_TLB_MIN_SLABS) + panic("%s: nslabs = %lu too small\n", __func__, nslabs); + /* * By default allocate the bounce buffer memory from low memory, but * allow to pick a location everywhere for hypervisors with guest @@ -254,7 +257,8 @@ retry: else tlb = memblock_alloc_low(bytes, PAGE_SIZE); if (!tlb) { - pr_warn("%s: failed to allocate tlb structure\n", __func__); + pr_warn("%s: Failed to allocate %zu bytes tlb structure\n", + __func__, bytes); return; } From 9ba26f5cecd86c85551a5120529c2f548099100f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 3 Feb 2022 09:36:33 +0100 Subject: [PATCH 05/45] ARM: sa1100/assabet: move dmabounce hack to ohci driver The sa1111 platform is one of the two remaining users of the old Arm specific "dmabounce" code, which is an earlier implementation of the generic swiotlb. Linus Walleij submitted a patch that removes dmabounce support from the ixp4xx, and I had a look at the other user, which is the sa1111 companion chip. Looking at how dmabounce is used, I could narrow it down to one driver one three machines: - dmabounce is only initialized on assabet/neponset, jornada720 and badge4, which are the platforms that have an sa1111 and support DMA on it. - All three of these suffer from "erratum #7" that requires only doing DMA to half the memory sections based on one of the address lines, in addition, the neponset also can't DMA to the RAM that is connected to sa1111 itself. - the pxa lubbock machine also has sa1111, but does not support DMA on it and does not set dmabounce. - only the OHCI and audio devices on sa1111 support DMA, but as there is no audio driver for this hardware, only OHCI remains. In the OHCI code, I noticed that two other platforms already have a local bounce buffer support in the form of the "local_mem" allocator. Specifically, TMIO and SM501 use this on a few other ARM boards with 16KB or 128KB of local SRAM that can be accessed from the OHCI and from the CPU. While this is not the same problem as on sa1111, I could not find a reason why we can't re-use the existing implementation but replace the physical SRAM address mapping with a locally allocated DMA buffer. There are two main downsides: - rather than using a dynamically sized pool, this buffer needs to be allocated at probe time using a fixed size. Without having any idea of what it should be, I picked a size of 64KB, which is between what the other two OHCI front-ends use in their SRAM. If anyone has a better idea what that size is reasonable, this can be trivially changed. - Previously, only USB transfers to unaddressable memory needed to go through the bounce buffer, now all of them do, which may impact runtime performance for USB endpoints that do a lot of transfers. On the upside, the local_mem support uses write-combining buffers, which should be a bit faster for transfers to the device compared to normal uncached coherent memory as used in dmabounce. Cc: Linus Walleij Cc: Russell King Cc: Christoph Hellwig Cc: Laurentiu Tudor Cc: linux-usb@vger.kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Greg Kroah-Hartman Acked-by: Alan Stern Signed-off-by: Christoph Hellwig --- arch/arm/common/Kconfig | 2 +- arch/arm/common/sa1111.c | 64 ---------------------------------- drivers/usb/core/hcd.c | 17 +++++++-- drivers/usb/host/ohci-sa1111.c | 25 +++++++++++++ 4 files changed, 40 insertions(+), 68 deletions(-) diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig index c8e198631d41..bc158fd227e1 100644 --- a/arch/arm/common/Kconfig +++ b/arch/arm/common/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config SA1111 bool - select DMABOUNCE if !ARCH_PXA + select ZONE_DMA if ARCH_SA1100 config DMABOUNCE bool diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index 2343e2b6214d..f5e6990b8856 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -1389,70 +1389,9 @@ void sa1111_driver_unregister(struct sa1111_driver *driver) } EXPORT_SYMBOL(sa1111_driver_unregister); -#ifdef CONFIG_DMABOUNCE -/* - * According to the "Intel StrongARM SA-1111 Microprocessor Companion - * Chip Specification Update" (June 2000), erratum #7, there is a - * significant bug in the SA1111 SDRAM shared memory controller. If - * an access to a region of memory above 1MB relative to the bank base, - * it is important that address bit 10 _NOT_ be asserted. Depending - * on the configuration of the RAM, bit 10 may correspond to one - * of several different (processor-relative) address bits. - * - * This routine only identifies whether or not a given DMA address - * is susceptible to the bug. - * - * This should only get called for sa1111_device types due to the - * way we configure our device dma_masks. - */ -static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size) -{ - /* - * Section 4.6 of the "Intel StrongARM SA-1111 Development Module - * User's Guide" mentions that jumpers R51 and R52 control the - * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or - * SDRAM bank 1 on Neponset). The default configuration selects - * Assabet, so any address in bank 1 is necessarily invalid. - */ - return (machine_is_assabet() || machine_is_pfs168()) && - (addr >= 0xc8000000 || (addr + size) >= 0xc8000000); -} - -static int sa1111_notifier_call(struct notifier_block *n, unsigned long action, - void *data) -{ - struct sa1111_dev *dev = to_sa1111_device(data); - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - if (dev->dev.dma_mask && dev->dma_mask < 0xffffffffUL) { - int ret = dmabounce_register_dev(&dev->dev, 1024, 4096, - sa1111_needs_bounce); - if (ret) - dev_err(&dev->dev, "failed to register with dmabounce: %d\n", ret); - } - break; - - case BUS_NOTIFY_DEL_DEVICE: - if (dev->dev.dma_mask && dev->dma_mask < 0xffffffffUL) - dmabounce_unregister_dev(&dev->dev); - break; - } - return NOTIFY_OK; -} - -static struct notifier_block sa1111_bus_notifier = { - .notifier_call = sa1111_notifier_call, -}; -#endif - static int __init sa1111_init(void) { int ret = bus_register(&sa1111_bus_type); -#ifdef CONFIG_DMABOUNCE - if (ret == 0) - bus_register_notifier(&sa1111_bus_type, &sa1111_bus_notifier); -#endif if (ret == 0) platform_driver_register(&sa1111_device_driver); return ret; @@ -1461,9 +1400,6 @@ static int __init sa1111_init(void) static void __exit sa1111_exit(void) { platform_driver_unregister(&sa1111_device_driver); -#ifdef CONFIG_DMABOUNCE - bus_unregister_notifier(&sa1111_bus_type, &sa1111_bus_notifier); -#endif bus_unregister(&sa1111_bus_type); } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 06eea8848ccc..4db3add28b44 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1251,7 +1251,8 @@ void usb_hcd_unlink_urb_from_ep(struct usb_hcd *hcd, struct urb *urb) EXPORT_SYMBOL_GPL(usb_hcd_unlink_urb_from_ep); /* - * Some usb host controllers can only perform dma using a small SRAM area. + * Some usb host controllers can only perform dma using a small SRAM area, + * or have restrictions on addressable DRAM. * The usb core itself is however optimized for host controllers that can dma * using regular system memory - like pci devices doing bus mastering. * @@ -3117,8 +3118,18 @@ int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr, if (IS_ERR(hcd->localmem_pool)) return PTR_ERR(hcd->localmem_pool); - local_mem = devm_memremap(hcd->self.sysdev, phys_addr, - size, MEMREMAP_WC); + /* + * if a physical SRAM address was passed, map it, otherwise + * allocate system memory as a buffer. + */ + if (phys_addr) + local_mem = devm_memremap(hcd->self.sysdev, phys_addr, + size, MEMREMAP_WC); + else + local_mem = dmam_alloc_attrs(hcd->self.sysdev, size, &dma, + GFP_KERNEL, + DMA_ATTR_WRITE_COMBINE); + if (IS_ERR(local_mem)) return PTR_ERR(local_mem); diff --git a/drivers/usb/host/ohci-sa1111.c b/drivers/usb/host/ohci-sa1111.c index feca826d3f6a..75c2b28b3379 100644 --- a/drivers/usb/host/ohci-sa1111.c +++ b/drivers/usb/host/ohci-sa1111.c @@ -203,6 +203,31 @@ static int ohci_hcd_sa1111_probe(struct sa1111_dev *dev) goto err1; } + /* + * According to the "Intel StrongARM SA-1111 Microprocessor Companion + * Chip Specification Update" (June 2000), erratum #7, there is a + * significant bug in the SA1111 SDRAM shared memory controller. If + * an access to a region of memory above 1MB relative to the bank base, + * it is important that address bit 10 _NOT_ be asserted. Depending + * on the configuration of the RAM, bit 10 may correspond to one + * of several different (processor-relative) address bits. + * + * Section 4.6 of the "Intel StrongARM SA-1111 Development Module + * User's Guide" mentions that jumpers R51 and R52 control the + * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or + * SDRAM bank 1 on Neponset). The default configuration selects + * Assabet, so any address in bank 1 is necessarily invalid. + * + * As a workaround, use a bounce buffer in addressable memory + * as local_mem, relying on ZONE_DMA to provide an area that + * fits within the above constraints. + * + * SZ_64K is an estimate for what size this might need. + */ + ret = usb_hcd_setup_local_mem(hcd, 0, 0, SZ_64K); + if (ret) + goto err1; + if (!request_mem_region(hcd->rsrc_start, hcd->rsrc_len, hcd_name)) { dev_dbg(&dev->dev, "request_mem_region failed\n"); ret = -EBUSY; From e3217540c2710f42a2388fe7896f0f28695c00b2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Apr 2022 09:35:29 +0200 Subject: [PATCH 06/45] ARM/dma-mapping: remove dmabounce Remove the now unused dmabounce code. Signed-off-by: Christoph Hellwig Reviewed-by: Arnd Bergmann --- arch/arm/common/Kconfig | 4 - arch/arm/common/Makefile | 1 - arch/arm/common/dmabounce.c | 582 ----------------------------- arch/arm/include/asm/device.h | 3 - arch/arm/include/asm/dma-mapping.h | 29 -- 5 files changed, 619 deletions(-) delete mode 100644 arch/arm/common/dmabounce.c diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig index bc158fd227e1..d2fdb1796f48 100644 --- a/arch/arm/common/Kconfig +++ b/arch/arm/common/Kconfig @@ -3,10 +3,6 @@ config SA1111 bool select ZONE_DMA if ARCH_SA1100 -config DMABOUNCE - bool - select ZONE_DMA - config KRAIT_L2_ACCESSORS bool diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile index 8cd574be94cf..7bae8cbaafe7 100644 --- a/arch/arm/common/Makefile +++ b/arch/arm/common/Makefile @@ -6,7 +6,6 @@ obj-y += firmware.o obj-$(CONFIG_SA1111) += sa1111.o -obj-$(CONFIG_DMABOUNCE) += dmabounce.o obj-$(CONFIG_KRAIT_L2_ACCESSORS) += krait-l2-accessors.o obj-$(CONFIG_SHARP_LOCOMO) += locomo.o obj-$(CONFIG_SHARP_PARAM) += sharpsl_param.o diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c deleted file mode 100644 index 7996c04393d5..000000000000 --- a/arch/arm/common/dmabounce.c +++ /dev/null @@ -1,582 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/common/dmabounce.c - * - * Special dma_{map/unmap/dma_sync}_* routines for systems that have - * limited DMA windows. These functions utilize bounce buffers to - * copy data to/from buffers located outside the DMA region. This - * only works for systems in which DMA memory is at the bottom of - * RAM, the remainder of memory is at the top and the DMA memory - * can be marked as ZONE_DMA. Anything beyond that such as discontiguous - * DMA windows will require custom implementations that reserve memory - * areas at early bootup. - * - * Original version by Brad Parker (brad@heeltoe.com) - * Re-written by Christopher Hoover - * Made generic by Deepak Saxena - * - * Copyright (C) 2002 Hewlett Packard Company. - * Copyright (C) 2004 MontaVista Software, Inc. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#undef STATS - -#ifdef STATS -#define DO_STATS(X) do { X ; } while (0) -#else -#define DO_STATS(X) do { } while (0) -#endif - -/* ************************************************** */ - -struct safe_buffer { - struct list_head node; - - /* original request */ - void *ptr; - size_t size; - int direction; - - /* safe buffer info */ - struct dmabounce_pool *pool; - void *safe; - dma_addr_t safe_dma_addr; -}; - -struct dmabounce_pool { - unsigned long size; - struct dma_pool *pool; -#ifdef STATS - unsigned long allocs; -#endif -}; - -struct dmabounce_device_info { - struct device *dev; - struct list_head safe_buffers; -#ifdef STATS - unsigned long total_allocs; - unsigned long map_op_count; - unsigned long bounce_count; - int attr_res; -#endif - struct dmabounce_pool small; - struct dmabounce_pool large; - - rwlock_t lock; - - int (*needs_bounce)(struct device *, dma_addr_t, size_t); -}; - -#ifdef STATS -static ssize_t dmabounce_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct dmabounce_device_info *device_info = dev->archdata.dmabounce; - return sprintf(buf, "%lu %lu %lu %lu %lu %lu\n", - device_info->small.allocs, - device_info->large.allocs, - device_info->total_allocs - device_info->small.allocs - - device_info->large.allocs, - device_info->total_allocs, - device_info->map_op_count, - device_info->bounce_count); -} - -static DEVICE_ATTR(dmabounce_stats, 0400, dmabounce_show, NULL); -#endif - - -/* allocate a 'safe' buffer and keep track of it */ -static inline struct safe_buffer * -alloc_safe_buffer(struct dmabounce_device_info *device_info, void *ptr, - size_t size, enum dma_data_direction dir) -{ - struct safe_buffer *buf; - struct dmabounce_pool *pool; - struct device *dev = device_info->dev; - unsigned long flags; - - dev_dbg(dev, "%s(ptr=%p, size=%d, dir=%d)\n", - __func__, ptr, size, dir); - - if (size <= device_info->small.size) { - pool = &device_info->small; - } else if (size <= device_info->large.size) { - pool = &device_info->large; - } else { - pool = NULL; - } - - buf = kmalloc(sizeof(struct safe_buffer), GFP_ATOMIC); - if (buf == NULL) { - dev_warn(dev, "%s: kmalloc failed\n", __func__); - return NULL; - } - - buf->ptr = ptr; - buf->size = size; - buf->direction = dir; - buf->pool = pool; - - if (pool) { - buf->safe = dma_pool_alloc(pool->pool, GFP_ATOMIC, - &buf->safe_dma_addr); - } else { - buf->safe = dma_alloc_coherent(dev, size, &buf->safe_dma_addr, - GFP_ATOMIC); - } - - if (buf->safe == NULL) { - dev_warn(dev, - "%s: could not alloc dma memory (size=%d)\n", - __func__, size); - kfree(buf); - return NULL; - } - -#ifdef STATS - if (pool) - pool->allocs++; - device_info->total_allocs++; -#endif - - write_lock_irqsave(&device_info->lock, flags); - list_add(&buf->node, &device_info->safe_buffers); - write_unlock_irqrestore(&device_info->lock, flags); - - return buf; -} - -/* determine if a buffer is from our "safe" pool */ -static inline struct safe_buffer * -find_safe_buffer(struct dmabounce_device_info *device_info, dma_addr_t safe_dma_addr) -{ - struct safe_buffer *b, *rb = NULL; - unsigned long flags; - - read_lock_irqsave(&device_info->lock, flags); - - list_for_each_entry(b, &device_info->safe_buffers, node) - if (b->safe_dma_addr <= safe_dma_addr && - b->safe_dma_addr + b->size > safe_dma_addr) { - rb = b; - break; - } - - read_unlock_irqrestore(&device_info->lock, flags); - return rb; -} - -static inline void -free_safe_buffer(struct dmabounce_device_info *device_info, struct safe_buffer *buf) -{ - unsigned long flags; - - dev_dbg(device_info->dev, "%s(buf=%p)\n", __func__, buf); - - write_lock_irqsave(&device_info->lock, flags); - - list_del(&buf->node); - - write_unlock_irqrestore(&device_info->lock, flags); - - if (buf->pool) - dma_pool_free(buf->pool->pool, buf->safe, buf->safe_dma_addr); - else - dma_free_coherent(device_info->dev, buf->size, buf->safe, - buf->safe_dma_addr); - - kfree(buf); -} - -/* ************************************************** */ - -static struct safe_buffer *find_safe_buffer_dev(struct device *dev, - dma_addr_t dma_addr, const char *where) -{ - if (!dev || !dev->archdata.dmabounce) - return NULL; - if (dma_mapping_error(dev, dma_addr)) { - dev_err(dev, "Trying to %s invalid mapping\n", where); - return NULL; - } - return find_safe_buffer(dev->archdata.dmabounce, dma_addr); -} - -static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) -{ - if (!dev || !dev->archdata.dmabounce) - return 0; - - if (dev->dma_mask) { - unsigned long limit, mask = *dev->dma_mask; - - limit = (mask + 1) & ~mask; - if (limit && size > limit) { - dev_err(dev, "DMA mapping too big (requested %#x " - "mask %#Lx)\n", size, *dev->dma_mask); - return -E2BIG; - } - - /* Figure out if we need to bounce from the DMA mask. */ - if ((dma_addr | (dma_addr + size - 1)) & ~mask) - return 1; - } - - return !!dev->archdata.dmabounce->needs_bounce(dev, dma_addr, size); -} - -static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - struct dmabounce_device_info *device_info = dev->archdata.dmabounce; - struct safe_buffer *buf; - - if (device_info) - DO_STATS ( device_info->map_op_count++ ); - - buf = alloc_safe_buffer(device_info, ptr, size, dir); - if (buf == NULL) { - dev_err(dev, "%s: unable to map unsafe buffer %p!\n", - __func__, ptr); - return DMA_MAPPING_ERROR; - } - - dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n", - __func__, buf->ptr, virt_to_dma(dev, buf->ptr), - buf->safe, buf->safe_dma_addr); - - if ((dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) && - !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { - dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n", - __func__, ptr, buf->safe, size); - memcpy(buf->safe, ptr, size); - } - - return buf->safe_dma_addr; -} - -static inline void unmap_single(struct device *dev, struct safe_buffer *buf, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - BUG_ON(buf->size != size); - BUG_ON(buf->direction != dir); - - dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n", - __func__, buf->ptr, virt_to_dma(dev, buf->ptr), - buf->safe, buf->safe_dma_addr); - - DO_STATS(dev->archdata.dmabounce->bounce_count++); - - if ((dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) && - !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { - void *ptr = buf->ptr; - - dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n", - __func__, buf->safe, ptr, size); - memcpy(ptr, buf->safe, size); - - /* - * Since we may have written to a page cache page, - * we need to ensure that the data will be coherent - * with user mappings. - */ - __cpuc_flush_dcache_area(ptr, size); - } - free_safe_buffer(dev->archdata.dmabounce, buf); -} - -/* ************************************************** */ - -/* - * see if a buffer address is in an 'unsafe' range. if it is - * allocate a 'safe' buffer and copy the unsafe buffer into it. - * substitute the safe buffer for the unsafe one. - * (basically move the buffer from an unsafe area to a safe one) - */ -static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t dma_addr; - int ret; - - dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n", - __func__, page, offset, size, dir); - - dma_addr = pfn_to_dma(dev, page_to_pfn(page)) + offset; - - ret = needs_bounce(dev, dma_addr, size); - if (ret < 0) - return DMA_MAPPING_ERROR; - - if (ret == 0) { - arm_dma_ops.sync_single_for_device(dev, dma_addr, size, dir); - return dma_addr; - } - - if (PageHighMem(page)) { - dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n"); - return DMA_MAPPING_ERROR; - } - - return map_single(dev, page_address(page) + offset, size, dir, attrs); -} - -/* - * see if a mapped address was really a "safe" buffer and if so, copy - * the data from the safe buffer back to the unsafe buffer and free up - * the safe buffer. (basically return things back to the way they - * should be) - */ -static void dmabounce_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - struct safe_buffer *buf; - - dev_dbg(dev, "%s(dma=%#x,size=%d,dir=%x)\n", - __func__, dma_addr, size, dir); - - buf = find_safe_buffer_dev(dev, dma_addr, __func__); - if (!buf) { - arm_dma_ops.sync_single_for_cpu(dev, dma_addr, size, dir); - return; - } - - unmap_single(dev, buf, size, dir, attrs); -} - -static int __dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr, - size_t sz, enum dma_data_direction dir) -{ - struct safe_buffer *buf; - unsigned long off; - - dev_dbg(dev, "%s(dma=%#x,sz=%zx,dir=%x)\n", - __func__, addr, sz, dir); - - buf = find_safe_buffer_dev(dev, addr, __func__); - if (!buf) - return 1; - - off = addr - buf->safe_dma_addr; - - BUG_ON(buf->direction != dir); - - dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x off=%#lx) mapped to %p (dma=%#x)\n", - __func__, buf->ptr, virt_to_dma(dev, buf->ptr), off, - buf->safe, buf->safe_dma_addr); - - DO_STATS(dev->archdata.dmabounce->bounce_count++); - - if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) { - dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n", - __func__, buf->safe + off, buf->ptr + off, sz); - memcpy(buf->ptr + off, buf->safe + off, sz); - } - return 0; -} - -static void dmabounce_sync_for_cpu(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - if (!__dmabounce_sync_for_cpu(dev, handle, size, dir)) - return; - - arm_dma_ops.sync_single_for_cpu(dev, handle, size, dir); -} - -static int __dmabounce_sync_for_device(struct device *dev, dma_addr_t addr, - size_t sz, enum dma_data_direction dir) -{ - struct safe_buffer *buf; - unsigned long off; - - dev_dbg(dev, "%s(dma=%#x,sz=%zx,dir=%x)\n", - __func__, addr, sz, dir); - - buf = find_safe_buffer_dev(dev, addr, __func__); - if (!buf) - return 1; - - off = addr - buf->safe_dma_addr; - - BUG_ON(buf->direction != dir); - - dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x off=%#lx) mapped to %p (dma=%#x)\n", - __func__, buf->ptr, virt_to_dma(dev, buf->ptr), off, - buf->safe, buf->safe_dma_addr); - - DO_STATS(dev->archdata.dmabounce->bounce_count++); - - if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) { - dev_dbg(dev, "%s: copy out unsafe %p to safe %p, size %d\n", - __func__,buf->ptr + off, buf->safe + off, sz); - memcpy(buf->safe + off, buf->ptr + off, sz); - } - return 0; -} - -static void dmabounce_sync_for_device(struct device *dev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - if (!__dmabounce_sync_for_device(dev, handle, size, dir)) - return; - - arm_dma_ops.sync_single_for_device(dev, handle, size, dir); -} - -static int dmabounce_dma_supported(struct device *dev, u64 dma_mask) -{ - if (dev->archdata.dmabounce) - return 0; - - return arm_dma_ops.dma_supported(dev, dma_mask); -} - -static const struct dma_map_ops dmabounce_ops = { - .alloc = arm_dma_alloc, - .free = arm_dma_free, - .mmap = arm_dma_mmap, - .get_sgtable = arm_dma_get_sgtable, - .map_page = dmabounce_map_page, - .unmap_page = dmabounce_unmap_page, - .sync_single_for_cpu = dmabounce_sync_for_cpu, - .sync_single_for_device = dmabounce_sync_for_device, - .map_sg = arm_dma_map_sg, - .unmap_sg = arm_dma_unmap_sg, - .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu, - .sync_sg_for_device = arm_dma_sync_sg_for_device, - .dma_supported = dmabounce_dma_supported, -}; - -static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev, - const char *name, unsigned long size) -{ - pool->size = size; - DO_STATS(pool->allocs = 0); - pool->pool = dma_pool_create(name, dev, size, - 0 /* byte alignment */, - 0 /* no page-crossing issues */); - - return pool->pool ? 0 : -ENOMEM; -} - -int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size, - unsigned long large_buffer_size, - int (*needs_bounce_fn)(struct device *, dma_addr_t, size_t)) -{ - struct dmabounce_device_info *device_info; - int ret; - - device_info = kmalloc(sizeof(struct dmabounce_device_info), GFP_ATOMIC); - if (!device_info) { - dev_err(dev, - "Could not allocated dmabounce_device_info\n"); - return -ENOMEM; - } - - ret = dmabounce_init_pool(&device_info->small, dev, - "small_dmabounce_pool", small_buffer_size); - if (ret) { - dev_err(dev, - "dmabounce: could not allocate DMA pool for %ld byte objects\n", - small_buffer_size); - goto err_free; - } - - if (large_buffer_size) { - ret = dmabounce_init_pool(&device_info->large, dev, - "large_dmabounce_pool", - large_buffer_size); - if (ret) { - dev_err(dev, - "dmabounce: could not allocate DMA pool for %ld byte objects\n", - large_buffer_size); - goto err_destroy; - } - } - - device_info->dev = dev; - INIT_LIST_HEAD(&device_info->safe_buffers); - rwlock_init(&device_info->lock); - device_info->needs_bounce = needs_bounce_fn; - -#ifdef STATS - device_info->total_allocs = 0; - device_info->map_op_count = 0; - device_info->bounce_count = 0; - device_info->attr_res = device_create_file(dev, &dev_attr_dmabounce_stats); -#endif - - dev->archdata.dmabounce = device_info; - set_dma_ops(dev, &dmabounce_ops); - - dev_info(dev, "dmabounce: registered device\n"); - - return 0; - - err_destroy: - dma_pool_destroy(device_info->small.pool); - err_free: - kfree(device_info); - return ret; -} -EXPORT_SYMBOL(dmabounce_register_dev); - -void dmabounce_unregister_dev(struct device *dev) -{ - struct dmabounce_device_info *device_info = dev->archdata.dmabounce; - - dev->archdata.dmabounce = NULL; - set_dma_ops(dev, NULL); - - if (!device_info) { - dev_warn(dev, - "Never registered with dmabounce but attempting" - "to unregister!\n"); - return; - } - - if (!list_empty(&device_info->safe_buffers)) { - dev_err(dev, - "Removing from dmabounce with pending buffers!\n"); - BUG(); - } - - if (device_info->small.pool) - dma_pool_destroy(device_info->small.pool); - if (device_info->large.pool) - dma_pool_destroy(device_info->large.pool); - -#ifdef STATS - if (device_info->attr_res == 0) - device_remove_file(dev, &dev_attr_dmabounce_stats); -#endif - - kfree(device_info); - - dev_info(dev, "dmabounce: device unregistered\n"); -} -EXPORT_SYMBOL(dmabounce_unregister_dev); - -MODULE_AUTHOR("Christopher Hoover , Deepak Saxena "); -MODULE_DESCRIPTION("Special dma_{map/unmap/dma_sync}_* routines for systems with limited DMA windows"); -MODULE_LICENSE("GPL"); diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h index be666f58bf7a..8754c0f5fc90 100644 --- a/arch/arm/include/asm/device.h +++ b/arch/arm/include/asm/device.h @@ -6,9 +6,6 @@ #define ASMARM_DEVICE_H struct dev_archdata { -#ifdef CONFIG_DMABOUNCE - struct dmabounce_device_info *dmabounce; -#endif #ifdef CONFIG_ARM_DMA_USE_IOMMU struct dma_iommu_mapping *mapping; #endif diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 77082246a5e1..1e015a7ad86a 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -80,35 +80,6 @@ extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, * */ -/** - * dmabounce_register_dev - * - * @dev: valid struct device pointer - * @small_buf_size: size of buffers to use with small buffer pool - * @large_buf_size: size of buffers to use with large buffer pool (can be 0) - * @needs_bounce_fn: called to determine whether buffer needs bouncing - * - * This function should be called by low-level platform code to register - * a device as requireing DMA buffer bouncing. The function will allocate - * appropriate DMA pools for the device. - */ -extern int dmabounce_register_dev(struct device *, unsigned long, - unsigned long, int (*)(struct device *, dma_addr_t, size_t)); - -/** - * dmabounce_unregister_dev - * - * @dev: valid struct device pointer - * - * This function should be called by low-level platform code when device - * that was previously registered with dmabounce_register_dev is removed - * from the system. - * - */ -extern void dmabounce_unregister_dev(struct device *); - - - /* * The scatter list versions of the above methods. */ From 5ed390e5a9d4d84f220e012ee20ae97fc254a9d9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Apr 2022 09:40:17 +0200 Subject: [PATCH 07/45] ARM/dma-mapping: mark various dma-mapping routines static in dma-mapping.c With the dmabounce removal these aren't used outside of dma-mapping.c, so mark them static. Move the dma_map_ops declarations down a bit to avoid lots of forward declarations. Signed-off-by: Christoph Hellwig Reviewed-by: Arnd Bergmann Tested-by: Marc Zyngier --- arch/arm/include/asm/dma-mapping.h | 75 ---------------------- arch/arm/mm/dma-mapping.c | 100 +++++++++++++---------------- 2 files changed, 46 insertions(+), 129 deletions(-) diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 1e015a7ad86a..6427b934bd11 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -20,80 +20,5 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) return NULL; } -/** - * arm_dma_alloc - allocate consistent memory for DMA - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @size: required memory size - * @handle: bus-specific DMA address - * @attrs: optinal attributes that specific mapping properties - * - * Allocate some memory for a device for performing DMA. This function - * allocates pages, and will return the CPU-viewed address, and sets @handle - * to be the device-viewed address. - */ -extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, unsigned long attrs); - -/** - * arm_dma_free - free memory allocated by arm_dma_alloc - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @size: size of memory originally requested in dma_alloc_coherent - * @cpu_addr: CPU-view address returned from dma_alloc_coherent - * @handle: device-view address returned from dma_alloc_coherent - * @attrs: optinal attributes that specific mapping properties - * - * Free (and unmap) a DMA buffer previously allocated by - * arm_dma_alloc(). - * - * References to memory and mappings associated with cpu_addr/handle - * during and after this call executing are illegal. - */ -extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs); - -/** - * arm_dma_mmap - map a coherent DMA allocation into user space - * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices - * @vma: vm_area_struct describing requested user mapping - * @cpu_addr: kernel CPU-view address returned from dma_alloc_coherent - * @handle: device-view address returned from dma_alloc_coherent - * @size: size of memory originally requested in dma_alloc_coherent - * @attrs: optinal attributes that specific mapping properties - * - * Map a coherent DMA buffer previously allocated by dma_alloc_coherent - * into user space. The coherent DMA buffer must not be freed by the - * driver until the user space mapping has been released. - */ -extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); - -/* - * For SA-1111, IXP425, and ADI systems the dma-mapping functions are "magic" - * and utilize bounce buffers as needed to work around limited DMA windows. - * - * On the SA-1111, a bug limits DMA to only certain regions of RAM. - * On the IXP425, the PCI inbound window is 64MB (256MB total RAM) - * On some ADI engineering systems, PCI inbound window is 32MB (12MB total RAM) - * - * The following are helper functions used by the dmabounce subystem - * - */ - -/* - * The scatter list versions of the above methods. - */ -extern int arm_dma_map_sg(struct device *, struct scatterlist *, int, - enum dma_data_direction, unsigned long attrs); -extern void arm_dma_unmap_sg(struct device *, struct scatterlist *, int, - enum dma_data_direction, unsigned long attrs); -extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int, - enum dma_data_direction); -extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int, - enum dma_data_direction); -extern int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); - #endif /* __KERNEL__ */ #endif diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 059cce018570..90142183d104 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -193,50 +193,6 @@ static int arm_dma_supported(struct device *dev, u64 mask) return dma_to_pfn(dev, mask) >= max_dma_pfn; } -const struct dma_map_ops arm_dma_ops = { - .alloc = arm_dma_alloc, - .free = arm_dma_free, - .alloc_pages = dma_direct_alloc_pages, - .free_pages = dma_direct_free_pages, - .mmap = arm_dma_mmap, - .get_sgtable = arm_dma_get_sgtable, - .map_page = arm_dma_map_page, - .unmap_page = arm_dma_unmap_page, - .map_sg = arm_dma_map_sg, - .unmap_sg = arm_dma_unmap_sg, - .map_resource = dma_direct_map_resource, - .sync_single_for_cpu = arm_dma_sync_single_for_cpu, - .sync_single_for_device = arm_dma_sync_single_for_device, - .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu, - .sync_sg_for_device = arm_dma_sync_sg_for_device, - .dma_supported = arm_dma_supported, - .get_required_mask = dma_direct_get_required_mask, -}; -EXPORT_SYMBOL(arm_dma_ops); - -static void *arm_coherent_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, unsigned long attrs); -static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs); -static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); - -const struct dma_map_ops arm_coherent_dma_ops = { - .alloc = arm_coherent_dma_alloc, - .free = arm_coherent_dma_free, - .alloc_pages = dma_direct_alloc_pages, - .free_pages = dma_direct_free_pages, - .mmap = arm_coherent_dma_mmap, - .get_sgtable = arm_dma_get_sgtable, - .map_page = arm_coherent_dma_map_page, - .map_sg = arm_dma_map_sg, - .map_resource = dma_direct_map_resource, - .dma_supported = arm_dma_supported, - .get_required_mask = dma_direct_get_required_mask, -}; -EXPORT_SYMBOL(arm_coherent_dma_ops); - static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag) { /* @@ -742,7 +698,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, * Allocate DMA-coherent memory space and return both the kernel remapped * virtual and bus address for that space. */ -void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, +static void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); @@ -791,7 +747,7 @@ static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma, return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); } -int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, +static int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { @@ -824,7 +780,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, kfree(buf); } -void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, +static void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, unsigned long attrs) { __arm_dma_free(dev, size, cpu_addr, handle, attrs, false); @@ -836,7 +792,7 @@ static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_add __arm_dma_free(dev, size, cpu_addr, handle, attrs, true); } -int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, +static int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t handle, size_t size, unsigned long attrs) { @@ -977,7 +933,7 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, * Device ownership issues as mentioned for dma_map_single are the same * here. */ -int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +static int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -1013,8 +969,8 @@ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, * Unmap a set of streaming mode DMA translations. Again, CPU access * rules concerning calls here are the same as for dma_unmap_single(). */ -void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) +static void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; @@ -1032,7 +988,7 @@ void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, * @nents: number of buffers to map (returned from dma_map_sg) * @dir: DMA transfer direction (same as was passed to dma_map_sg) */ -void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, +static void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -1051,8 +1007,8 @@ void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, * @nents: number of buffers to map (returned from dma_map_sg) * @dir: DMA transfer direction (same as was passed to dma_map_sg) */ -void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) +static void arm_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nents, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; @@ -1063,6 +1019,42 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, dir); } +const struct dma_map_ops arm_dma_ops = { + .alloc = arm_dma_alloc, + .free = arm_dma_free, + .alloc_pages = dma_direct_alloc_pages, + .free_pages = dma_direct_free_pages, + .mmap = arm_dma_mmap, + .get_sgtable = arm_dma_get_sgtable, + .map_page = arm_dma_map_page, + .unmap_page = arm_dma_unmap_page, + .map_sg = arm_dma_map_sg, + .unmap_sg = arm_dma_unmap_sg, + .map_resource = dma_direct_map_resource, + .sync_single_for_cpu = arm_dma_sync_single_for_cpu, + .sync_single_for_device = arm_dma_sync_single_for_device, + .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu, + .sync_sg_for_device = arm_dma_sync_sg_for_device, + .dma_supported = arm_dma_supported, + .get_required_mask = dma_direct_get_required_mask, +}; +EXPORT_SYMBOL(arm_dma_ops); + +const struct dma_map_ops arm_coherent_dma_ops = { + .alloc = arm_coherent_dma_alloc, + .free = arm_coherent_dma_free, + .alloc_pages = dma_direct_alloc_pages, + .free_pages = dma_direct_free_pages, + .mmap = arm_coherent_dma_mmap, + .get_sgtable = arm_dma_get_sgtable, + .map_page = arm_coherent_dma_map_page, + .map_sg = arm_dma_map_sg, + .map_resource = dma_direct_map_resource, + .dma_supported = arm_dma_supported, + .get_required_mask = dma_direct_get_required_mask, +}; +EXPORT_SYMBOL(arm_coherent_dma_ops); + static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent) { /* From d6e2e92597ed2036206b084e94828403d7fb14a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Apr 2022 09:43:48 +0200 Subject: [PATCH 08/45] ARM/dma-mapping: remove the unused virt_to_dma helper virt_to_dma was only used by the now removed dmabounce code. Signed-off-by: Christoph Hellwig Reviewed-by: Arnd Bergmann Tested-by: Marc Zyngier --- arch/arm/include/asm/dma-direct.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h index 77fcb7ee5ec9..6fd52713b5d1 100644 --- a/arch/arm/include/asm/dma-direct.h +++ b/arch/arm/include/asm/dma-direct.h @@ -5,7 +5,7 @@ #include /* - * dma_to_pfn/pfn_to_dma/virt_to_dma are architecture private + * dma_to_pfn/pfn_to_dma are architecture private * functions used internally by the DMA-mapping API to provide DMA * addresses. They must not be used by drivers. */ @@ -25,14 +25,6 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr) return pfn; } -static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) -{ - if (dev) - return pfn_to_dma(dev, virt_to_pfn(addr)); - - return (dma_addr_t)__virt_to_bus((unsigned long)(addr)); -} - static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) { unsigned int offset = paddr & ~PAGE_MASK; From f9774cfd5062d69dc8ba522369638f919c35391e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Apr 2022 09:48:53 +0200 Subject: [PATCH 09/45] ARM/dma-mapping: use dma_to_phys/phys_to_dma in the dma-mapping code Use the helpers as expected by the dma-direct code in the old arm dma-mapping code to ease a gradual switch to the common DMA code. Signed-off-by: Christoph Hellwig Reviewed-by: Arnd Bergmann Tested-by: Marc Zyngier --- arch/arm/mm/dma-mapping.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 90142183d104..a09ce16c7ddb 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -128,14 +128,14 @@ static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, { if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_page_cpu_to_dev(page, offset, size, dir); - return pfn_to_dma(dev, page_to_pfn(page)) + offset; + return phys_to_dma(dev, page_to_phys(page) + offset); } static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { - return pfn_to_dma(dev, page_to_pfn(page)) + offset; + return phys_to_dma(dev, page_to_phys(page) + offset); } /** @@ -156,7 +156,7 @@ static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) - __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)), + __dma_page_dev_to_cpu(phys_to_page(dma_to_phys(dev, handle)), handle & ~PAGE_MASK, size, dir); } @@ -164,7 +164,7 @@ static void arm_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { unsigned int offset = handle & (PAGE_SIZE - 1); - struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); + struct page *page = phys_to_page(dma_to_phys(dev, handle-offset)); __dma_page_dev_to_cpu(page, offset, size, dir); } @@ -172,7 +172,7 @@ static void arm_dma_sync_single_for_device(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { unsigned int offset = handle & (PAGE_SIZE - 1); - struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset)); + struct page *page = phys_to_page(dma_to_phys(dev, handle-offset)); __dma_page_cpu_to_dev(page, offset, size, dir); } @@ -190,7 +190,7 @@ static int arm_dma_supported(struct device *dev, u64 mask) * Translate the device's DMA mask to a PFN limit. This * PFN number includes the page which we can DMA to. */ - return dma_to_pfn(dev, mask) >= max_dma_pfn; + return PHYS_PFN(dma_to_phys(dev, mask)) >= max_dma_pfn; } static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag) @@ -681,7 +681,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (page) { unsigned long flags; - *handle = pfn_to_dma(dev, page_to_pfn(page)); + *handle = phys_to_dma(dev, page_to_phys(page)); buf->virt = args.want_vaddr ? addr : page; spin_lock_irqsave(&arm_dma_bufs_lock, flags); @@ -721,7 +721,7 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, int ret = -ENXIO; unsigned long nr_vma_pages = vma_pages(vma); unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - unsigned long pfn = dma_to_pfn(dev, dma_addr); + unsigned long pfn = PHYS_PFN(dma_to_phys(dev, dma_addr)); unsigned long off = vma->vm_pgoff; if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) @@ -762,7 +762,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, unsigned long attrs, bool is_coherent) { - struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); + struct page *page = phys_to_page(dma_to_phys(dev, handle)); struct arm_dma_buffer *buf; struct arm_dma_free_args args = { .dev = dev, @@ -796,15 +796,15 @@ static int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t handle, size_t size, unsigned long attrs) { - unsigned long pfn = dma_to_pfn(dev, handle); + phys_addr_t paddr = dma_to_phys(dev, handle); struct page *page; int ret; /* If the PFN is not valid, we do not have a struct page */ - if (!pfn_valid(pfn)) + if (!pfn_valid(PHYS_PFN(paddr))) return -ENXIO; - page = pfn_to_page(pfn); + page = phys_to_page(paddr); ret = sg_alloc_table(sgt, 1, GFP_KERNEL); if (unlikely(ret)) From af6f23b88e9508f1cb8d0af008bb175019428f73 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Apr 2022 10:00:32 +0200 Subject: [PATCH 10/45] ARM/dma-mapping: use the generic versions of dma_to_phys/phys_to_dma by default Only the footbridge platforms provide their own DMA address translation helpers, so switch to the generic version for all other platforms, and consolidate the footbridge implementation to remove two levels of indirection. Signed-off-by: Christoph Hellwig Reviewed-by: Arnd Bergmann Tested-by: Marc Zyngier --- arch/arm/Kconfig | 1 - arch/arm/include/asm/dma-direct.h | 41 +------------------ arch/arm/include/asm/memory.h | 2 - arch/arm/mach-footbridge/Kconfig | 1 + arch/arm/mach-footbridge/common.c | 19 +++++---- .../mach-footbridge/include/mach/dma-direct.h | 8 ++++ .../arm/mach-footbridge/include/mach/memory.h | 4 -- 7 files changed, 21 insertions(+), 55 deletions(-) create mode 100644 arch/arm/mach-footbridge/include/mach/dma-direct.h diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 7630ba9cb6cc..cd67e359958c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -15,7 +15,6 @@ config ARM select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL if ARM_LPAE - select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_SETUP_DMA_OPS select ARCH_HAS_SET_MEMORY select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h index 6fd52713b5d1..4f7bcde03abb 100644 --- a/arch/arm/include/asm/dma-direct.h +++ b/arch/arm/include/asm/dma-direct.h @@ -1,40 +1 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ASM_ARM_DMA_DIRECT_H -#define ASM_ARM_DMA_DIRECT_H 1 - -#include - -/* - * dma_to_pfn/pfn_to_dma are architecture private - * functions used internally by the DMA-mapping API to provide DMA - * addresses. They must not be used by drivers. - */ -static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn) -{ - if (dev && dev->dma_range_map) - pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn))); - return (dma_addr_t)__pfn_to_bus(pfn); -} - -static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr) -{ - unsigned long pfn = __bus_to_pfn(addr); - - if (dev && dev->dma_range_map) - pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn))); - return pfn; -} - -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) -{ - unsigned int offset = paddr & ~PAGE_MASK; - return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset; -} - -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) -{ - unsigned int offset = dev_addr & ~PAGE_MASK; - return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset; -} - -#endif /* ASM_ARM_DMA_DIRECT_H */ +#include diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index f673e13e0f94..a55a9038abc8 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -378,8 +378,6 @@ static inline unsigned long __virt_to_idmap(unsigned long x) #ifndef __virt_to_bus #define __virt_to_bus __virt_to_phys #define __bus_to_virt __phys_to_virt -#define __pfn_to_bus(x) __pfn_to_phys(x) -#define __bus_to_pfn(x) __phys_to_pfn(x) #endif /* diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig index 728aff93fba9..b5bbdcf2e489 100644 --- a/arch/arm/mach-footbridge/Kconfig +++ b/arch/arm/mach-footbridge/Kconfig @@ -60,6 +60,7 @@ endmenu # Footbridge support config FOOTBRIDGE + select ARCH_HAS_PHYS_TO_DMA bool # Footbridge in host mode diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c index 322495df271d..5020eb96b025 100644 --- a/arch/arm/mach-footbridge/common.c +++ b/arch/arm/mach-footbridge/common.c @@ -12,6 +12,7 @@ #include #include #include +#include #include