| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-id: <1455870164-25337-3-git-send-email-m.szyprowski@samsung.com>
Date: Fri, 19 Feb 2016 09:22:43 +0100
From: Marek Szyprowski <m.szyprowski@...sung.com>
To: iommu@...ts.linux-foundation.org,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org
Cc: Marek Szyprowski <m.szyprowski@...sung.com>,
linaro-mm-sig@...ts.linaro.org, dri-devel@...ts.freedesktop.org,
Arnd Bergmann <arnd@...db.de>,
Will Deacon <will.deacon@....com>,
Catalin Marinas <catalin.marinas@....com>,
Robin Murphy <robin.murphy@....com>,
Russell King - ARM Linux <linux@....linux.org.uk>,
Joerg Roedel <joro@...tes.org>,
Laurent Pinchart <laurent.pinchart@...asonboard.com>,
Sakari Ailus <sakari.ailus@....fi>,
Mark Yao <mark.yao@...k-chips.com>,
Heiko Stuebner <heiko@...ech.de>,
Tomasz Figa <tfiga@...omium.org>,
Inki Dae <inki.dae@...sung.com>,
Bartlomiej Zolnierkiewicz <b.zolnierkie@...sung.com>,
Krzysztof Kozlowski <k.kozlowski@...sung.com>
Subject: [RFC 2/3] iommu: dma-iommu: move IOMMU/DMA-mapping code from ARM64
arch to drivers
This patch moves all the IOMMU-based DMA-mapping code from arch/arm64/mm
to drivers/iommu/dma-iommu-ops.c. This way it can be easily shared with
ARM architecture, which will also use them.
Signed-off-by: Marek Szyprowski <m.szyprowski@...sung.com>
---
arch/arm64/include/asm/dma-mapping.h | 39 ++-
arch/arm64/mm/dma-mapping.c | 491 ++---------------------------------
drivers/iommu/Makefile | 2 +-
drivers/iommu/dma-iommu-ops.c | 471 +++++++++++++++++++++++++++++++++
include/linux/dma-iommu.h | 14 +
5 files changed, 538 insertions(+), 479 deletions(-)
create mode 100644 drivers/iommu/dma-iommu-ops.c
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index ba437f090a74..3a582d820717 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -22,6 +22,7 @@
#include <linux/vmalloc.h>
#include <xen/xen.h>
+#include <asm/cacheflush.h>
#include <asm/xen/hypervisor.h>
#define DMA_ERROR_CODE (~(dma_addr_t)0)
@@ -47,14 +48,17 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
return __generic_dma_ops(dev);
}
+static inline void arch_set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+ dev->archdata.dma_ops = ops;
+}
+
void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
struct iommu_ops *iommu, bool coherent);
#define arch_setup_dma_ops arch_setup_dma_ops
-#ifdef CONFIG_IOMMU_DMA
void arch_teardown_dma_ops(struct device *dev);
#define arch_teardown_dma_ops arch_teardown_dma_ops
-#endif
/* do not use this function in a driver */
static inline bool is_device_dma_coherent(struct device *dev)
@@ -86,5 +90,36 @@ static inline void dma_mark_clean(void *addr, size_t size)
{
}
+static inline void arch_flush_page(struct device *dev, const void *virt,
+ phys_addr_t phys)
+{
+ __dma_flush_range(virt, virt + PAGE_SIZE);
+}
+
+static inline void arch_dma_map_area(phys_addr_t phys, size_t size,
+ enum dma_data_direction dir)
+{
+ __dma_map_area(phys_to_virt(phys), size, dir);
+}
+
+static inline void arch_dma_unmap_area(phys_addr_t phys, size_t size,
+ enum dma_data_direction dir)
+{
+ __dma_unmap_area(phys_to_virt(phys), size, dir);
+}
+
+static inline pgprot_t arch_get_dma_pgprot(struct dma_attrs *attrs,
+ pgprot_t prot, bool coherent)
+{
+ if (!coherent || dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+ return pgprot_writecombine(prot);
+ return prot;
+}
+
+extern void *arch_alloc_from_atomic_pool(size_t size, struct page **ret_page,
+ gfp_t flags);
+extern bool arch_in_atomic_pool(void *start, size_t size);
+extern int arch_free_from_atomic_pool(void *start, size_t size);
+
#endif /* __KERNEL__ */
#endif /* __ASM_DMA_MAPPING_H */
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index a6e757cbab77..d8cb8552bbff 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -24,19 +24,12 @@
#include <linux/genalloc.h>
#include <linux/dma-mapping.h>
#include <linux/dma-contiguous.h>
+#include <linux/dma-iommu.h>
#include <linux/vmalloc.h>
#include <linux/swiotlb.h>
#include <asm/cacheflush.h>
-static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
- bool coherent)
-{
- if (!coherent || dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
- return pgprot_writecombine(prot);
- return prot;
-}
-
static struct gen_pool *atomic_pool;
#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
@@ -49,7 +42,7 @@ static int __init early_coherent_pool(char *p)
}
early_param("coherent_pool", early_coherent_pool);
-static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
+void *arch_alloc_from_atomic_pool(size_t size, struct page **ret_page, gfp_t flags)
{
unsigned long val;
void *ptr = NULL;
@@ -71,14 +64,14 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
return ptr;
}
-static bool __in_atomic_pool(void *start, size_t size)
+bool arch_in_atomic_pool(void *start, size_t size)
{
return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
}
-static int __free_from_pool(void *start, size_t size)
+int arch_free_from_atomic_pool(void *start, size_t size)
{
- if (!__in_atomic_pool(start, size))
+ if (!arch_in_atomic_pool(start, size))
return 0;
gen_pool_free(atomic_pool, (unsigned long)start, size);
@@ -142,13 +135,13 @@ static void *__dma_alloc(struct device *dev, size_t size,
struct page *page;
void *ptr, *coherent_ptr;
bool coherent = is_device_dma_coherent(dev);
- pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false);
+ pgprot_t prot = arch_get_dma_pgprot(attrs, PAGE_KERNEL, false);
size = PAGE_ALIGN(size);
if (!coherent && !gfpflags_allow_blocking(flags)) {
struct page *page = NULL;
- void *addr = __alloc_from_pool(size, &page, flags);
+ void *addr = arch_alloc_from_atomic_pool(size, &page, flags);
if (addr)
*dma_handle = phys_to_dma(dev, page_to_phys(page));
@@ -192,7 +185,7 @@ static void __dma_free(struct device *dev, size_t size,
size = PAGE_ALIGN(size);
if (!is_device_dma_coherent(dev)) {
- if (__free_from_pool(vaddr, size))
+ if (arch_free_from_atomic_pool(vaddr, size))
return;
vunmap(vaddr);
}
@@ -312,7 +305,7 @@ static int __swiotlb_mmap(struct device *dev,
unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
- vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+ vma->vm_page_prot = arch_get_dma_pgprot(attrs, vma->vm_page_prot,
is_device_dma_coherent(dev));
if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
@@ -526,470 +519,16 @@ static int __init dma_debug_do_init(void)
}
fs_initcall(dma_debug_do_init);
-
-#ifdef CONFIG_IOMMU_DMA
-#include <linux/dma-iommu.h>
-#include <linux/platform_device.h>
-#include <linux/amba/bus.h>
-
-/* Thankfully, all cache ops are by VA so we can ignore phys here */
-static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
-{
- __dma_flush_range(virt, virt + PAGE_SIZE);
-}
-
-static void *__iommu_alloc_attrs(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp,
- struct dma_attrs *attrs)
-{
- bool coherent = is_device_dma_coherent(dev);
- int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
- size_t iosize = size;
- void *addr;
-
- if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
- return NULL;
-
- size = PAGE_ALIGN(size);
-
- /*
- * Some drivers rely on this, and we probably don't want the
- * possibility of stale kernel data being read by devices anyway.
- */
- gfp |= __GFP_ZERO;
-
- if (gfpflags_allow_blocking(gfp)) {
- struct page **pages;
- pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
-
- pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle,
- flush_page);
- if (!pages)
- return NULL;
-
- addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
- __builtin_return_address(0));
- if (!addr)
- iommu_dma_free(dev, pages, iosize, handle);
- } else {
- struct page *page;
- /*
- * In atomic context we can't remap anything, so we'll only
- * get the virtually contiguous buffer we need by way of a
- * physically contiguous allocation.
- */
- if (coherent) {
- page = alloc_pages(gfp, get_order(size));
- addr = page ? page_address(page) : NULL;
- } else {
- addr = __alloc_from_pool(size, &page, gfp);
- }
- if (!addr)
- return NULL;
-
- *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
- if (iommu_dma_mapping_error(dev, *handle)) {
- if (coherent)
- __free_pages(page, get_order(size));
- else
- __free_from_pool(addr, size);
- addr = NULL;
- }
- }
- return addr;
-}
-
-static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
- dma_addr_t handle, struct dma_attrs *attrs)
-{
- size_t iosize = size;
-
- size = PAGE_ALIGN(size);
- /*
- * @cpu_addr will be one of 3 things depending on how it was allocated:
- * - A remapped array of pages from iommu_dma_alloc(), for all
- * non-atomic allocations.
- * - A non-cacheable alias from the atomic pool, for atomic
- * allocations by non-coherent devices.
- * - A normal lowmem address, for atomic allocations by
- * coherent devices.
- * Hence how dodgy the below logic looks...
- */
- if (__in_atomic_pool(cpu_addr, size)) {
- iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
- __free_from_pool(cpu_addr, size);
- } else if (is_vmalloc_addr(cpu_addr)){
- struct vm_struct *area = find_vm_area(cpu_addr);
-
- if (WARN_ON(!area || !area->pages))
- return;
- iommu_dma_free(dev, area->pages, iosize, &handle);
- dma_common_free_remap(cpu_addr, size, VM_USERMAP);
- } else {
- iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
- __free_pages(virt_to_page(cpu_addr), get_order(size));
- }
-}
-
-static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size,
- struct dma_attrs *attrs)
-{
- struct vm_struct *area;
- int ret;
-
- vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
- is_device_dma_coherent(dev));
-
- if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
- return ret;
-
- area = find_vm_area(cpu_addr);
- if (WARN_ON(!area || !area->pages))
- return -ENXIO;
-
- return iommu_dma_mmap(area->pages, size, vma);
-}
-
-static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t dma_addr,
- size_t size, struct dma_attrs *attrs)
-{
- unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- struct vm_struct *area = find_vm_area(cpu_addr);
-
- if (WARN_ON(!area || !area->pages))
- return -ENXIO;
-
- return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
- GFP_KERNEL);
-}
-
-static void __iommu_sync_single_for_cpu(struct device *dev,
- dma_addr_t dev_addr, size_t size,
- enum dma_data_direction dir)
-{
- phys_addr_t phys;
-
- if (is_device_dma_coherent(dev))
- return;
-
- phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
- __dma_unmap_area(phys_to_virt(phys), size, dir);
-}
-
-static void __iommu_sync_single_for_device(struct device *dev,
- dma_addr_t dev_addr, size_t size,
- enum dma_data_direction dir)
-{
- phys_addr_t phys;
-
- if (is_device_dma_coherent(dev))
- return;
-
- phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
- __dma_map_area(phys_to_virt(phys), size, dir);
-}
-
-static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
-{
- bool coherent = is_device_dma_coherent(dev);
- int prot = dma_direction_to_prot(dir, coherent);
- dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
-
- if (!iommu_dma_mapping_error(dev, dev_addr) &&
- !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
- __iommu_sync_single_for_device(dev, dev_addr, size, dir);
-
- return dev_addr;
-}
-
-static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- struct dma_attrs *attrs)
-{
- if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
- __iommu_sync_single_for_cpu(dev, dev_addr, size, dir);
-
- iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs);
-}
-
-static void __iommu_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir)
-{
- struct scatterlist *sg;
- int i;
-
- if (is_device_dma_coherent(dev))
- return;
-
- for_each_sg(sgl, sg, nelems, i)
- __dma_unmap_area(sg_virt(sg), sg->length, dir);
-}
-
-static void __iommu_sync_sg_for_device(struct device *dev,
- struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir)
-{
- struct scatterlist *sg;
- int i;
-
- if (is_device_dma_coherent(dev))
- return;
-
- for_each_sg(sgl, sg, nelems, i)
- __dma_map_area(sg_virt(sg), sg->length, dir);
-}
-
-static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
- int nelems, enum dma_data_direction dir,
- struct dma_attrs *attrs)
-{
- bool coherent = is_device_dma_coherent(dev);
-
- if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
- __iommu_sync_sg_for_device(dev, sgl, nelems, dir);
-
- return iommu_dma_map_sg(dev, sgl, nelems,
- dma_direction_to_prot(dir, coherent));
-}
-
-static void __iommu_unmap_sg_attrs(struct device *dev,
- struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
-{
- if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
- __iommu_sync_sg_for_cpu(dev, sgl, nelems, dir);
-
- iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs);
-}
-
-static struct dma_map_ops iommu_dma_ops = {
- .alloc = __iommu_alloc_attrs,
- .free = __iommu_free_attrs,
- .mmap = __iommu_mmap_attrs,
- .get_sgtable = __iommu_get_sgtable,
- .map_page = __iommu_map_page,
- .unmap_page = __iommu_unmap_page,
- .map_sg = __iommu_map_sg_attrs,
- .unmap_sg = __iommu_unmap_sg_attrs,
- .sync_single_for_cpu = __iommu_sync_single_for_cpu,
- .sync_single_for_device = __iommu_sync_single_for_device,
- .sync_sg_for_cpu = __iommu_sync_sg_for_cpu,
- .sync_sg_for_device = __iommu_sync_sg_for_device,
- .dma_supported = iommu_dma_supported,
- .mapping_error = iommu_dma_mapping_error,
-};
-
-/*
- * TODO: Right now __iommu_setup_dma_ops() gets called too early to do
- * everything it needs to - the device is only partially created and the
- * IOMMU driver hasn't seen it yet, so it can't have a group. Thus we
- * need this delayed attachment dance. Once IOMMU probe ordering is sorted
- * to move the arch_setup_dma_ops() call later, all the notifier bits below
- * become unnecessary, and will go away.
- */
-struct iommu_dma_notifier_data {
- struct list_head list;
- struct device *dev;
- const struct iommu_ops *ops;
- u64 dma_base;
- u64 size;
-};
-static LIST_HEAD(iommu_dma_masters);
-static DEFINE_MUTEX(iommu_dma_notifier_lock);
-
-/*
- * Temporarily "borrow" a domain feature flag to to tell if we had to resort
- * to creating our own domain here, in case we need to clean it up again.
- */
-#define __IOMMU_DOMAIN_FAKE_DEFAULT (1U << 31)
-
-static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
- u64 dma_base, u64 size)
-{
- struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-
- /*
- * Best case: The device is either part of a group which was
- * already attached to a domain in a previous call, or it's
- * been put in a default DMA domain by the IOMMU core.
- */
- if (!domain) {
- /*
- * Urgh. The IOMMU core isn't going to do default domains
- * for non-PCI devices anyway, until it has some means of
- * abstracting the entirely implementation-specific
- * sideband data/SoC topology/unicorn dust that may or
- * may not differentiate upstream masters.
- * So until then, HORRIBLE HACKS!
- */
- domain = ops->domain_alloc(IOMMU_DOMAIN_DMA);
- if (!domain)
- goto out_no_domain;
-
- domain->ops = ops;
- domain->type = IOMMU_DOMAIN_DMA | __IOMMU_DOMAIN_FAKE_DEFAULT;
-
- if (iommu_attach_device(domain, dev))
- goto out_put_domain;
- }
-
- if (iommu_dma_init_domain(domain, dma_base, size))
- goto out_detach;
-
- dev->archdata.dma_ops = &iommu_dma_ops;
- return true;
-
-out_detach:
- iommu_detach_device(domain, dev);
-out_put_domain:
- if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT)
- iommu_domain_free(domain);
-out_no_domain:
- pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
- dev_name(dev));
- return false;
-}
-
-static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops,
- u64 dma_base, u64 size)
-{
- struct iommu_dma_notifier_data *iommudata;
-
- iommudata = kzalloc(sizeof(*iommudata), GFP_KERNEL);
- if (!iommudata)
- return;
-
- iommudata->dev = dev;
- iommudata->ops = ops;
- iommudata->dma_base = dma_base;
- iommudata->size = size;
-
- mutex_lock(&iommu_dma_notifier_lock);
- list_add(&iommudata->list, &iommu_dma_masters);
- mutex_unlock(&iommu_dma_notifier_lock);
-}
-
-static int __iommu_attach_notifier(struct notifier_block *nb,
- unsigned long action, void *data)
-{
- struct iommu_dma_notifier_data *master, *tmp;
-
- if (action != BUS_NOTIFY_ADD_DEVICE)
- return 0;
-
- mutex_lock(&iommu_dma_notifier_lock);
- list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) {
- if (do_iommu_attach(master->dev, master->ops,
- master->dma_base, master->size)) {
- list_del(&master->list);
- kfree(master);
- }
- }
- mutex_unlock(&iommu_dma_notifier_lock);
- return 0;
-}
-
-static int __init register_iommu_dma_ops_notifier(struct bus_type *bus)
-{
- struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL);
- int ret;
-
- if (!nb)
- return -ENOMEM;
- /*
- * The device must be attached to a domain before the driver probe
- * routine gets a chance to start allocating DMA buffers. However,
- * the IOMMU driver also needs a chance to configure the iommu_group
- * via its add_device callback first, so we need to make the attach
- * happen between those two points. Since the IOMMU core uses a bus
- * notifier with default priority for add_device, do the same but
- * with a lower priority to ensure the appropriate ordering.
- */
- nb->notifier_call = __iommu_attach_notifier;
- nb->priority = -100;
-
- ret = bus_register_notifier(bus, nb);
- if (ret) {
- pr_warn("Failed to register DMA domain notifier; IOMMU DMA ops unavailable on bus '%s'\n",
- bus->name);
- kfree(nb);
- }
- return ret;
-}
-
-static int __init __iommu_dma_init(void)
-{
- int ret;
-
- ret = iommu_dma_init();
- if (!ret)
- ret = register_iommu_dma_ops_notifier(&platform_bus_type);
- if (!ret)
- ret = register_iommu_dma_ops_notifier(&amba_bustype);
-
- /* handle devices queued before this arch_initcall */
- if (!ret)
- __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL);
- return ret;
-}
-arch_initcall(__iommu_dma_init);
-
-static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
- const struct iommu_ops *ops)
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ struct iommu_ops *iommu, bool coherent)
{
- struct iommu_group *group;
+ dev->archdata.dma_coherent = coherent;
- if (!ops)
- return;
- /*
- * TODO: As a concession to the future, we're ready to handle being
- * called both early and late (i.e. after bus_add_device). Once all
- * the platform bus code is reworked to call us late and the notifier
- * junk above goes away, move the body of do_iommu_attach here.
- */
- group = iommu_group_get(dev);
- if (group) {
- do_iommu_attach(dev, ops, dma_base, size);
- iommu_group_put(group);
- } else {
- queue_iommu_attach(dev, ops, dma_base, size);
- }
+ if (!common_iommu_setup_dma_ops(dev, dma_base, size, iommu))
+ arch_set_dma_ops(dev, &swiotlb_dma_ops);
}
void arch_teardown_dma_ops(struct device *dev)
{
- struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-
- if (domain) {
- iommu_detach_device(domain, dev);
- if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT)
- iommu_domain_free(domain);
- }
-
- dev->archdata.dma_ops = NULL;
-}
-
-#else
-
-static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
- struct iommu_ops *iommu)
-{ }
-
-#endif /* CONFIG_IOMMU_DMA */
-
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
- struct iommu_ops *iommu, bool coherent)
-{
- if (!dev->archdata.dma_ops)
- dev->archdata.dma_ops = &swiotlb_dma_ops;
-
- dev->archdata.dma_coherent = coherent;
- __iommu_setup_dma_ops(dev, dma_base, size, iommu);
+ common_iommu_teardown_dma_ops(dev);
}
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 42fc0c25cf1a..c0dbf765bf45 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -1,7 +1,7 @@
obj-$(CONFIG_IOMMU_API) += iommu.o
obj-$(CONFIG_IOMMU_API) += iommu-traces.o
obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o
-obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o
+obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o dma-iommu-ops.o
obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
obj-$(CONFIG_IOMMU_IOVA) += iova.o
diff --git a/drivers/iommu/dma-iommu-ops.c b/drivers/iommu/dma-iommu-ops.c
new file mode 100644
index 000000000000..047c47e3c0ab
--- /dev/null
+++ b/drivers/iommu/dma-iommu-ops.c
@@ -0,0 +1,471 @@
+/*
+ * A common IOMMU based DMA-API implementation for ARM and ARM64 architecutes.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/device.h>
+#include <linux/dma-iommu.h>
+#include <linux/gfp.h>
+#include <linux/huge_mm.h>
+#include <linux/iommu.h>
+#include <linux/iova.h>
+#include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/vmalloc.h>
+
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+
+#include <asm/dma-mapping.h>
+
+static void *__iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp,
+ struct dma_attrs *attrs)
+{
+ bool coherent = is_device_dma_coherent(dev);
+ int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
+ size_t iosize = size;
+ void *addr;
+
+ if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
+ return NULL;
+
+ size = PAGE_ALIGN(size);
+
+ /*
+ * Some drivers rely on this, and we probably don't want the
+ * possibility of stale kernel data being read by devices anyway.
+ */
+ gfp |= __GFP_ZERO;
+
+ if (gfpflags_allow_blocking(gfp)) {
+ struct page **pages;
+ pgprot_t prot = arch_get_dma_pgprot(attrs, PAGE_KERNEL,
+ coherent);
+
+ pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle,
+ arch_flush_page);
+ if (!pages)
+ return NULL;
+
+ addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
+ __builtin_return_address(0));
+ if (!addr)
+ iommu_dma_free(dev, pages, iosize, handle);
+ } else {
+ struct page *page;
+ /*
+ * In atomic context we can't remap anything, so we'll only
+ * get the virtually contiguous buffer we need by way of a
+ * physically contiguous allocation.
+ */
+ if (coherent) {
+ page = alloc_pages(gfp, get_order(size));
+ addr = page ? page_address(page) : NULL;
+ } else {
+ addr = arch_alloc_from_atomic_pool(size, &page, gfp);
+ }
+ if (!addr)
+ return NULL;
+
+ *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
+ if (iommu_dma_mapping_error(dev, *handle)) {
+ if (coherent)
+ __free_pages(page, get_order(size));
+ else
+ arch_free_from_atomic_pool(addr, size);
+ addr = NULL;
+ }
+ }
+ return addr;
+}
+
+static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t handle, struct dma_attrs *attrs)
+{
+ size_t iosize = size;
+
+ size = PAGE_ALIGN(size);
+ /*
+ * @cpu_addr will be one of 3 things depending on how it was allocated:
+ * - A remapped array of pages from iommu_dma_alloc(), for all
+ * non-atomic allocations.
+ * - A non-cacheable alias from the atomic pool, for atomic
+ * allocations by non-coherent devices.
+ * - A normal lowmem address, for atomic allocations by
+ * coherent devices.
+ * Hence how dodgy the below logic looks...
+ */
+ if (arch_in_atomic_pool(cpu_addr, size)) {
+ iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
+ arch_free_from_atomic_pool(cpu_addr, size);
+ } else if (is_vmalloc_addr(cpu_addr)){
+ struct vm_struct *area = find_vm_area(cpu_addr);
+
+ if (WARN_ON(!area || !area->pages))
+ return;
+ iommu_dma_free(dev, area->pages, iosize, &handle);
+ dma_common_free_remap(cpu_addr, size, VM_USERMAP);
+ } else {
+ iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
+ __free_pages(virt_to_page(cpu_addr), get_order(size));
+ }
+}
+
+static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ struct dma_attrs *attrs)
+{
+ struct vm_struct *area;
+ int ret;
+
+ vma->vm_page_prot = arch_get_dma_pgprot(attrs, vma->vm_page_prot,
+ is_device_dma_coherent(dev));
+
+ if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ area = find_vm_area(cpu_addr);
+ if (WARN_ON(!area || !area->pages))
+ return -ENXIO;
+
+ return iommu_dma_mmap(area->pages, size, vma);
+}
+
+static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t dma_addr,
+ size_t size, struct dma_attrs *attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ struct vm_struct *area = find_vm_area(cpu_addr);
+
+ if (WARN_ON(!area || !area->pages))
+ return -ENXIO;
+
+ return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
+ GFP_KERNEL);
+}
+
+static void __iommu_sync_single_for_cpu(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+ phys_addr_t phys;
+
+ if (is_device_dma_coherent(dev))
+ return;
+
+ phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+ arch_dma_unmap_area(phys, size, dir);
+}
+
+static void __iommu_sync_single_for_device(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+ phys_addr_t phys;
+
+ if (is_device_dma_coherent(dev))
+ return;
+
+ phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+ arch_dma_map_area(phys, size, dir);
+}
+
+static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ bool coherent = is_device_dma_coherent(dev);
+ int prot = dma_direction_to_prot(dir, coherent);
+ dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
+
+ if (!iommu_dma_mapping_error(dev, dev_addr) &&
+ !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+ __iommu_sync_single_for_device(dev, dev_addr, size, dir);
+
+ return dev_addr;
+}
+
+static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+ __iommu_sync_single_for_cpu(dev, dev_addr, size, dir);
+
+ iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static void __iommu_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ if (is_device_dma_coherent(dev))
+ return;
+
+ for_each_sg(sgl, sg, nelems, i)
+ arch_dma_unmap_area(sg_phys(sg), sg->length, dir);
+}
+
+static void __iommu_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ if (is_device_dma_coherent(dev))
+ return;
+
+ for_each_sg(sgl, sg, nelems, i)
+ arch_dma_map_area(sg_phys(sg), sg->length, dir);
+}
+
+static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ bool coherent = is_device_dma_coherent(dev);
+
+ if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+ __iommu_sync_sg_for_device(dev, sgl, nelems, dir);
+
+ return iommu_dma_map_sg(dev, sgl, nelems,
+ dma_direction_to_prot(dir, coherent));
+}
+
+static void __iommu_unmap_sg_attrs(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+ __iommu_sync_sg_for_cpu(dev, sgl, nelems, dir);
+
+ iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs);
+}
+
+static struct dma_map_ops iommu_dma_ops = {
+ .alloc = __iommu_alloc_attrs,
+ .free = __iommu_free_attrs,
+ .mmap = __iommu_mmap_attrs,
+ .get_sgtable = __iommu_get_sgtable,
+ .map_page = __iommu_map_page,
+ .unmap_page = __iommu_unmap_page,
+ .map_sg = __iommu_map_sg_attrs,
+ .unmap_sg = __iommu_unmap_sg_attrs,
+ .sync_single_for_cpu = __iommu_sync_single_for_cpu,
+ .sync_single_for_device = __iommu_sync_single_for_device,
+ .sync_sg_for_cpu = __iommu_sync_sg_for_cpu,
+ .sync_sg_for_device = __iommu_sync_sg_for_device,
+ .dma_supported = iommu_dma_supported,
+ .mapping_error = iommu_dma_mapping_error,
+};
+
+/*
+ * TODO: Right now __iommu_setup_dma_ops() gets called too early to do
+ * everything it needs to - the device is only partially created and the
+ * IOMMU driver hasn't seen it yet, so it can't have a group. Thus we
+ * need this delayed attachment dance. Once IOMMU probe ordering is sorted
+ * to move the arch_setup_dma_ops() call later, all the notifier bits below
+ * become unnecessary, and will go away.
+ */
+struct iommu_dma_notifier_data {
+ struct list_head list;
+ struct device *dev;
+ const struct iommu_ops *ops;
+ u64 dma_base;
+ u64 size;
+};
+static LIST_HEAD(iommu_dma_masters);
+static DEFINE_MUTEX(iommu_dma_notifier_lock);
+
+/*
+ * Temporarily "borrow" a domain feature flag to to tell if we had to resort
+ * to creating our own domain here, in case we need to clean it up again.
+ */
+#define __IOMMU_DOMAIN_FAKE_DEFAULT (1U << 31)
+
+static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
+ u64 dma_base, u64 size)
+{
+ struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+ /*
+ * Best case: The device is either part of a group which was
+ * already attached to a domain in a previous call, or it's
+ * been put in a default DMA domain by the IOMMU core.
+ */
+ if (!domain) {
+ /*
+ * Urgh. The IOMMU core isn't going to do default domains
+ * for non-PCI devices anyway, until it has some means of
+ * abstracting the entirely implementation-specific
+ * sideband data/SoC topology/unicorn dust that may or
+ * may not differentiate upstream masters.
+ * So until then, HORRIBLE HACKS!
+ */
+ domain = ops->domain_alloc(IOMMU_DOMAIN_DMA);
+ if (!domain)
+ goto out_no_domain;
+
+ domain->ops = ops;
+ domain->type = IOMMU_DOMAIN_DMA | __IOMMU_DOMAIN_FAKE_DEFAULT;
+
+ if (iommu_attach_device(domain, dev))
+ goto out_put_domain;
+ }
+
+ if (iommu_dma_init_domain(domain, dma_base, size))
+ goto out_detach;
+
+ arch_set_dma_ops(dev, &iommu_dma_ops);
+ return true;
+
+out_detach:
+ iommu_detach_device(domain, dev);
+out_put_domain:
+ if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT)
+ iommu_domain_free(domain);
+out_no_domain:
+ pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+ dev_name(dev));
+ return false;
+}
+
+static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops,
+ u64 dma_base, u64 size)
+{
+ struct iommu_dma_notifier_data *iommudata;
+
+ iommudata = kzalloc(sizeof(*iommudata), GFP_KERNEL);
+ if (!iommudata)
+ return;
+
+ iommudata->dev = dev;
+ iommudata->ops = ops;
+ iommudata->dma_base = dma_base;
+ iommudata->size = size;
+
+ mutex_lock(&iommu_dma_notifier_lock);
+ list_add(&iommudata->list, &iommu_dma_masters);
+ mutex_unlock(&iommu_dma_notifier_lock);
+}
+
+static int __iommu_attach_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct iommu_dma_notifier_data *master, *tmp;
+
+ if (action != BUS_NOTIFY_ADD_DEVICE)
+ return 0;
+
+ mutex_lock(&iommu_dma_notifier_lock);
+ list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) {
+ if (do_iommu_attach(master->dev, master->ops,
+ master->dma_base, master->size)) {
+ list_del(&master->list);
+ kfree(master);
+ }
+ }
+ mutex_unlock(&iommu_dma_notifier_lock);
+ return 0;
+}
+
+static int __init register_iommu_dma_ops_notifier(struct bus_type *bus)
+{
+ struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL);
+ int ret;
+
+ if (!nb)
+ return -ENOMEM;
+ /*
+ * The device must be attached to a domain before the driver probe
+ * routine gets a chance to start allocating DMA buffers. However,
+ * the IOMMU driver also needs a chance to configure the iommu_group
+ * via its add_device callback first, so we need to make the attach
+ * happen between those two points. Since the IOMMU core uses a bus
+ * notifier with default priority for add_device, do the same but
+ * with a lower priority to ensure the appropriate ordering.
+ */
+ nb->notifier_call = __iommu_attach_notifier;
+ nb->priority = -100;
+
+ ret = bus_register_notifier(bus, nb);
+ if (ret) {
+ pr_warn("Failed to register DMA domain notifier; IOMMU DMA ops unavailable on bus '%s'\n",
+ bus->name);
+ kfree(nb);
+ }
+ return ret;
+}
+
+static int __init __iommu_dma_init(void)
+{
+ int ret;
+
+ ret = iommu_dma_init();
+ if (!ret)
+ ret = register_iommu_dma_ops_notifier(&platform_bus_type);
+ if (!ret)
+ ret = register_iommu_dma_ops_notifier(&amba_bustype);
+
+ /* handle devices queued before this arch_initcall */
+ if (!ret)
+ __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL);
+ return ret;
+}
+arch_initcall(__iommu_dma_init);
+
+bool common_iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ const struct iommu_ops *ops)
+{
+ struct iommu_group *group;
+
+ if (!ops)
+ return false;
+ /*
+ * TODO: As a concession to the future, we're ready to handle being
+ * called both early and late (i.e. after bus_add_device). Once all
+ * the platform bus code is reworked to call us late and the notifier
+ * junk above goes away, move the body of do_iommu_attach here.
+ */
+ group = iommu_group_get(dev);
+ if (group) {
+ do_iommu_attach(dev, ops, dma_base, size);
+ iommu_group_put(group);
+ } else {
+ queue_iommu_attach(dev, ops, dma_base, size);
+ }
+
+ return true;
+}
+
+void common_iommu_teardown_dma_ops(struct device *dev)
+{
+ struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+ if (domain) {
+ iommu_detach_device(domain, dev);
+ if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT)
+ iommu_domain_free(domain);
+ }
+
+ arch_set_dma_ops(dev, NULL);
+}
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index fc481037478a..01a836c43dc3 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -62,6 +62,10 @@ void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
int iommu_dma_supported(struct device *dev, u64 mask);
int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
+bool common_iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ const struct iommu_ops *ops);
+void common_iommu_teardown_dma_ops(struct device *dev);
+
#else
struct iommu_domain;
@@ -80,6 +84,16 @@ static inline void iommu_put_dma_cookie(struct iommu_domain *domain)
{
}
+static inline bool common_iommu_setup_dma_ops(struct device *dev, u64 dma_base,
+ u64 size, const struct iommu_ops *ops)
+{
+ return false;
+}
+
+static inline void common_iommu_teardown_dma_ops(struct device *dev)
+{
+}
+
#endif /* CONFIG_IOMMU_DMA */
#endif /* __KERNEL__ */
#endif /* __DMA_IOMMU_H */
--
1.9.2
Powered by blists - more mailing lists