diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-12-28 14:12:21 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-12-28 14:12:21 -0800 |
commit | af7ddd8a627c62a835524b3f5b471edbbbcce025 (patch) | |
tree | af9777ddef6d394c7cc01fca599328b584ca2bc1 /kernel/dma | |
parent | fe2b0cdabcd9e6aeca66a104bc03576946e5fee2 (diff) | |
parent | 8b1cce9f5832a8eda17d37a3c49fb7dd2d650f46 (diff) |
Merge tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping
Pull DMA mapping updates from Christoph Hellwig:
"A huge update this time, but a lot of that is just consolidating or
removing code:
- provide a common DMA_MAPPING_ERROR definition and avoid indirect
calls for dma_map_* error checking
- use direct calls for the DMA direct mapping case, avoiding huge
retpoline overhead for high performance workloads
- merge the swiotlb dma_map_ops into dma-direct
- provide a generic remapping DMA consistent allocator for
architectures that have devices that perform DMA that is not cache
coherent. Based on the existing arm64 implementation and also used
for csky now.
- improve the dma-debug infrastructure, including dynamic allocation
of entries (Robin Murphy)
- default to providing chaining scatterlist everywhere, with opt-outs
for the few architectures (alpha, parisc, most arm32 variants) that
can't cope with it
- misc sparc32 dma-related cleanups
- remove the dma_mark_clean arch hook used by swiotlb on ia64 and
replace it with the generic noncoherent infrastructure
- fix the return type of dma_set_max_seg_size (Niklas Söderlund)
- move the dummy dma ops for not DMA capable devices from arm64 to
common code (Robin Murphy)
- ensure dma_alloc_coherent returns zeroed memory to avoid kernel
data leaks through userspace. We already did this for most common
architectures, but this ensures we do it everywhere.
dma_zalloc_coherent has been deprecated and can hopefully be
removed after -rc1 with a coccinelle script"
* tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping: (73 commits)
dma-mapping: fix inverted logic in dma_supported
dma-mapping: deprecate dma_zalloc_coherent
dma-mapping: zero memory returned from dma_alloc_*
sparc/iommu: fix ->map_sg return value
sparc/io-unit: fix ->map_sg return value
arm64: default to the direct mapping in get_arch_dma_ops
PCI: Remove unused attr variable in pci_dma_configure
ia64: only select ARCH_HAS_DMA_COHERENT_TO_PFN if swiotlb is enabled
dma-mapping: bypass indirect calls for dma-direct
vmd: use the proper dma_* APIs instead of direct methods calls
dma-direct: merge swiotlb_dma_ops into the dma_direct code
dma-direct: use dma_direct_map_page to implement dma_direct_map_sg
dma-direct: improve addressability error reporting
swiotlb: remove dma_mark_clean
swiotlb: remove SWIOTLB_MAP_ERROR
ACPI / scan: Refactor _CCA enforcement
dma-mapping: factor out dummy DMA ops
dma-mapping: always build the direct mapping code
dma-mapping: move dma_cache_sync out of line
dma-mapping: move various slow path functions out of line
...
Diffstat (limited to 'kernel/dma')
-rw-r--r-- | kernel/dma/Kconfig | 14 | ||||
-rw-r--r-- | kernel/dma/Makefile | 5 | ||||
-rw-r--r-- | kernel/dma/debug.c | 259 | ||||
-rw-r--r-- | kernel/dma/direct.c | 222 | ||||
-rw-r--r-- | kernel/dma/dummy.c | 39 | ||||
-rw-r--r-- | kernel/dma/mapping.c | 223 | ||||
-rw-r--r-- | kernel/dma/remap.c | 256 | ||||
-rw-r--r-- | kernel/dma/swiotlb.c | 253 | ||||
-rw-r--r-- | kernel/dma/virt.c | 2 |
9 files changed, 708 insertions, 565 deletions
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 645c7a2ecde8..ca88b867e7fe 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -35,13 +35,8 @@ config ARCH_HAS_DMA_COHERENT_TO_PFN config ARCH_HAS_DMA_MMAP_PGPROT bool -config DMA_DIRECT_OPS - bool - depends on HAS_DMA - config DMA_NONCOHERENT_CACHE_SYNC bool - depends on DMA_DIRECT_OPS config DMA_VIRT_OPS bool @@ -49,5 +44,12 @@ config DMA_VIRT_OPS config SWIOTLB bool - select DMA_DIRECT_OPS select NEED_DMA_MAP_STATE + +config DMA_REMAP + depends on MMU + bool + +config DMA_DIRECT_REMAP + bool + select DMA_REMAP diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index 7d581e4eea4a..72ff6e46aa86 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -1,10 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_HAS_DMA) += mapping.o +obj-$(CONFIG_HAS_DMA) += mapping.o direct.o dummy.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o -obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o obj-$(CONFIG_DMA_VIRT_OPS) += virt.o obj-$(CONFIG_DMA_API_DEBUG) += debug.o obj-$(CONFIG_SWIOTLB) += swiotlb.o - +obj-$(CONFIG_DMA_REMAP) += remap.o diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 231ca4628062..164706da2a73 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -17,6 +17,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#define pr_fmt(fmt) "DMA-API: " fmt + #include <linux/sched/task_stack.h> #include <linux/scatterlist.h> #include <linux/dma-mapping.h> @@ -41,10 +43,9 @@ #define HASH_FN_SHIFT 13 #define HASH_FN_MASK (HASH_SIZE - 1) -/* allow architectures to override this if absolutely required */ -#ifndef PREALLOC_DMA_DEBUG_ENTRIES #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) -#endif +/* If the pool runs out, add this many new entries at once */ +#define DMA_DEBUG_DYNAMIC_ENTRIES (PAGE_SIZE / sizeof(struct dma_debug_entry)) enum { dma_debug_single, @@ -142,6 +143,7 @@ static struct dentry *show_all_errors_dent __read_mostly; static struct dentry *show_num_errors_dent __read_mostly; static struct dentry *num_free_entries_dent __read_mostly; static struct dentry *min_free_entries_dent __read_mostly; +static struct dentry *nr_total_entries_dent __read_mostly; static struct dentry *filter_dent __read_mostly; /* per-driver filter related state */ @@ -234,7 +236,7 @@ static bool driver_filter(struct device *dev) error_count += 1; \ if (driver_filter(dev) && \ (show_all_errors || show_num_errors > 0)) { \ - WARN(1, "%s %s: " format, \ + WARN(1, pr_fmt("%s %s: ") format, \ dev ? dev_driver_string(dev) : "NULL", \ dev ? dev_name(dev) : "NULL", ## arg); \ dump_entry_trace(entry); \ @@ -519,7 +521,7 @@ static void active_cacheline_inc_overlap(phys_addr_t cln) * prematurely. */ WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP, - "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n", + pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"), ACTIVE_CACHELINE_MAX_OVERLAP, &cln); } @@ -614,7 +616,7 @@ void debug_dma_assert_idle(struct page *page) cln = to_cacheline_number(entry); err_printk(entry->dev, entry, - "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n", + "cpu touching an active dma mapped cacheline [cln=%pa]\n", &cln); } @@ -634,7 +636,7 @@ static void add_dma_entry(struct dma_debug_entry *entry) rc = active_cacheline_insert(entry); if (rc == -ENOMEM) { - pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n"); + pr_err("cacheline tracking ENOMEM, dma-debug disabled\n"); global_disable = true; } @@ -643,6 +645,24 @@ static void add_dma_entry(struct dma_debug_entry *entry) */ } +static int dma_debug_create_entries(gfp_t gfp) +{ + struct dma_debug_entry *entry; + int i; + + entry = (void *)get_zeroed_page(gfp); + if (!entry) + return -ENOMEM; + + for (i = 0; i < DMA_DEBUG_DYNAMIC_ENTRIES; i++) + list_add_tail(&entry[i].list, &free_entries); + + num_free_entries += DMA_DEBUG_DYNAMIC_ENTRIES; + nr_total_entries += DMA_DEBUG_DYNAMIC_ENTRIES; + + return 0; +} + static struct dma_debug_entry *__dma_entry_alloc(void) { struct dma_debug_entry *entry; @@ -658,6 +678,18 @@ static struct dma_debug_entry *__dma_entry_alloc(void) return entry; } +void __dma_entry_alloc_check_leak(void) +{ + u32 tmp = nr_total_entries % nr_prealloc_entries; + + /* Shout each time we tick over some multiple of the initial pool */ + if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) { + pr_info("dma_debug_entry pool grown to %u (%u00%%)\n", + nr_total_entries, + (nr_total_entries / nr_prealloc_entries)); + } +} + /* struct dma_entry allocator * * The next two functions implement the allocator for @@ -669,12 +701,14 @@ static struct dma_debug_entry *dma_entry_alloc(void) unsigned long flags; spin_lock_irqsave(&free_entries_lock, flags); - - if (list_empty(&free_entries)) { - global_disable = true; - spin_unlock_irqrestore(&free_entries_lock, flags); - pr_err("DMA-API: debugging out of memory - disabling\n"); - return NULL; + if (num_free_entries == 0) { + if (dma_debug_create_entries(GFP_ATOMIC)) { + global_disable = true; + spin_unlock_irqrestore(&free_entries_lock, flags); + pr_err("debugging out of memory - disabling\n"); + return NULL; + } + __dma_entry_alloc_check_leak(); } entry = __dma_entry_alloc(); @@ -707,52 +741,6 @@ static void dma_entry_free(struct dma_debug_entry *entry) spin_unlock_irqrestore(&free_entries_lock, flags); } -int dma_debug_resize_entries(u32 num_entries) -{ - int i, delta, ret = 0; - unsigned long flags; - struct dma_debug_entry *entry; - LIST_HEAD(tmp); - - spin_lock_irqsave(&free_entries_lock, flags); - - if (nr_total_entries < num_entries) { - delta = num_entries - nr_total_entries; - - spin_unlock_irqrestore(&free_entries_lock, flags); - - for (i = 0; i < delta; i++) { - entry = kzalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - break; - - list_add_tail(&entry->list, &tmp); - } - - spin_lock_irqsave(&free_entries_lock, flags); - - list_splice(&tmp, &free_entries); - nr_total_entries += i; - num_free_entries += i; - } else { - delta = nr_total_entries - num_entries; - - for (i = 0; i < delta && !list_empty(&free_entries); i++) { - entry = __dma_entry_alloc(); - kfree(entry); - } - - nr_total_entries -= i; - } - - if (nr_total_entries != num_entries) - ret = 1; - - spin_unlock_irqrestore(&free_entries_lock, flags); - - return ret; -} - /* * DMA-API debugging init code * @@ -761,36 +749,6 @@ int dma_debug_resize_entries(u32 num_entries) * 2. Preallocate a given number of dma_debug_entry structs */ -static int prealloc_memory(u32 num_entries) -{ - struct dma_debug_entry *entry, *next_entry; - int i; - - for (i = 0; i < num_entries; ++i) { - entry = kzalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - goto out_err; - - list_add_tail(&entry->list, &free_entries); - } - - num_free_entries = num_entries; - min_free_entries = num_entries; - - pr_info("DMA-API: preallocated %d debug entries\n", num_entries); - - return 0; - -out_err: - - list_for_each_entry_safe(entry, next_entry, &free_entries, list) { - list_del(&entry->list); - kfree(entry); - } - - return -ENOMEM; -} - static ssize_t filter_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -850,7 +808,7 @@ static ssize_t filter_write(struct file *file, const char __user *userbuf, * switched off. */ if (current_driver_name[0]) - pr_info("DMA-API: switching off dma-debug driver filter\n"); + pr_info("switching off dma-debug driver filter\n"); current_driver_name[0] = 0; current_driver = NULL; goto out_unlock; @@ -868,7 +826,7 @@ static ssize_t filter_write(struct file *file, const char __user *userbuf, current_driver_name[i] = 0; current_driver = NULL; - pr_info("DMA-API: enable driver filter for driver [%s]\n", + pr_info("enable driver filter for driver [%s]\n", current_driver_name); out_unlock: @@ -887,7 +845,7 @@ static int dma_debug_fs_init(void) { dma_debug_dent = debugfs_create_dir("dma-api", NULL); if (!dma_debug_dent) { - pr_err("DMA-API: can not create debugfs directory\n"); + pr_err("can not create debugfs directory\n"); return -ENOMEM; } @@ -926,6 +884,12 @@ static int dma_debug_fs_init(void) if (!min_free_entries_dent) goto out_err; + nr_total_entries_dent = debugfs_create_u32("nr_total_entries", 0444, + dma_debug_dent, + &nr_total_entries); + if (!nr_total_entries_dent) + goto out_err; + filter_dent = debugfs_create_file("driver_filter", 0644, dma_debug_dent, NULL, &filter_fops); if (!filter_dent) @@ -973,7 +937,7 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti count = device_dma_allocations(dev, &entry); if (count == 0) break; - err_printk(dev, entry, "DMA-API: device driver has pending " + err_printk(dev, entry, "device driver has pending " "DMA allocations while released from device " "[count=%d]\n" "One of leaked entries details: " @@ -1009,7 +973,7 @@ void dma_debug_add_bus(struct bus_type *bus) static int dma_debug_init(void) { - int i; + int i, nr_pages; /* Do not use dma_debug_initialized here, since we really want to be * called to set dma_debug_initialized @@ -1023,24 +987,31 @@ static int dma_debug_init(void) } if (dma_debug_fs_init() != 0) { - pr_err("DMA-API: error creating debugfs entries - disabling\n"); + pr_err("error creating debugfs entries - disabling\n"); global_disable = true; return 0; } - if (prealloc_memory(nr_prealloc_entries) != 0) { - pr_err("DMA-API: debugging out of memory error - disabled\n"); + nr_pages = DIV_ROUND_UP(nr_prealloc_entries, DMA_DEBUG_DYNAMIC_ENTRIES); + for (i = 0; i < nr_pages; ++i) + dma_debug_create_entries(GFP_KERNEL); + if (num_free_entries >= nr_prealloc_entries) { + pr_info("preallocated %d debug entries\n", nr_total_entries); + } else if (num_free_entries > 0) { + pr_warn("%d debug entries requested but only %d allocated\n", + nr_prealloc_entries, nr_total_entries); + } else { + pr_err("debugging out of memory error - disabled\n"); global_disable = true; return 0; } - - nr_total_entries = num_free_entries; + min_free_entries = num_free_entries; dma_debug_initialized = true; - pr_info("DMA-API: debugging enabled by kernel config\n"); + pr_info("debugging enabled by kernel config\n"); return 0; } core_initcall(dma_debug_init); @@ -1051,7 +1022,7 @@ static __init int dma_debug_cmdline(char *str) return -EINVAL; if (strncmp(str, "off", 3) == 0) { - pr_info("DMA-API: debugging disabled on kernel command line\n"); + pr_info("debugging disabled on kernel command line\n"); global_disable = true; } @@ -1085,11 +1056,11 @@ static void check_unmap(struct dma_debug_entry *ref) if (dma_mapping_error(ref->dev, ref->dev_addr)) { err_printk(ref->dev, NULL, - "DMA-API: device driver tries to free an " + "device driver tries to free an " "invalid DMA memory address\n"); } else { err_printk(ref->dev, NULL, - "DMA-API: device driver tries to free DMA " + "device driver tries to free DMA " "memory it has not allocated [device " "address=0x%016llx] [size=%llu bytes]\n", ref->dev_addr, ref->size); @@ -1098,7 +1069,7 @@ static void check_unmap(struct dma_debug_entry *ref) } if (ref->size != entry->size) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA memory with different size " "[device address=0x%016llx] [map size=%llu bytes] " "[unmap size=%llu bytes]\n", @@ -1106,7 +1077,7 @@ static void check_unmap(struct dma_debug_entry *ref) } if (ref->type != entry->type) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA memory with wrong function " "[device address=0x%016llx] [size=%llu bytes] " "[mapped as %s] [unmapped as %s]\n", @@ -1114,7 +1085,7 @@ static void check_unmap(struct dma_debug_entry *ref) type2name[entry->type], type2name[ref->type]); } else if ((entry->type == dma_debug_coherent) && (phys_addr(ref) != phys_addr(entry))) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA memory with different CPU address " "[device address=0x%016llx] [size=%llu bytes] " "[cpu alloc address=0x%016llx] " @@ -1126,7 +1097,7 @@ static void check_unmap(struct dma_debug_entry *ref) if (ref->sg_call_ents && ref->type == dma_debug_sg && ref->sg_call_ents != entry->sg_call_ents) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA sg list with different entry count " "[map count=%d] [unmap count=%d]\n", entry->sg_call_ents, ref->sg_call_ents); @@ -1137,7 +1108,7 @@ static void check_unmap(struct dma_debug_entry *ref) * DMA API don't handle this properly, so check for it here */ if (ref->direction != entry->direction) { - err_printk(ref->dev, entry, "DMA-API: device driver frees " + err_printk(ref->dev, entry, "device driver frees " "DMA memory with different direction " "[device address=0x%016llx] [size=%llu bytes] " "[mapped with %s] [unmapped with %s]\n", @@ -1153,7 +1124,7 @@ static void check_unmap(struct dma_debug_entry *ref) */ if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { err_printk(ref->dev, entry, - "DMA-API: device driver failed to check map error" + "device driver failed to check map error" "[device address=0x%016llx] [size=%llu bytes] " "[mapped as %s]", ref->dev_addr, ref->size, @@ -1178,7 +1149,7 @@ static void check_for_stack(struct device *dev, return; addr = page_address(page) + offset; if (object_is_on_stack(addr)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr); + err_printk(dev, NULL, "device driver maps memory from stack [addr=%p]\n", addr); } else { /* Stack is vmalloced. */ int i; @@ -1188,7 +1159,7 @@ static void check_for_stack(struct device *dev, continue; addr = (u8 *)current->stack + i * PAGE_SIZE + offset; - err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr); + err_printk(dev, NULL, "device driver maps memory from stack [probable addr=%p]\n", addr); break; } } @@ -1208,7 +1179,7 @@ static void check_for_illegal_area(struct device *dev, void *addr, unsigned long { if (overlap(addr, len, _stext, _etext) || overlap(addr, len, __start_rodata, __end_rodata)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); + err_printk(dev, NULL, "device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); } static void check_sync(struct device *dev, @@ -1224,7 +1195,7 @@ static void check_sync(struct device *dev, entry = bucket_find_contain(&bucket, ref, &flags); if (!entry) { - err_printk(dev, NULL, "DMA-API: device driver tries " + err_printk(dev, NULL, "device driver tries " "to sync DMA memory it has not allocated " "[device address=0x%016llx] [size=%llu bytes]\n", (unsigned long long)ref->dev_addr, ref->size); @@ -1232,7 +1203,7 @@ static void check_sync(struct device *dev, } if (ref->size > entry->size) { - err_printk(dev, entry, "DMA-API: device driver syncs" + err_printk(dev, entry, "device driver syncs" " DMA memory outside allocated range " "[device address=0x%016llx] " "[allocation size=%llu bytes] " @@ -1245,7 +1216,7 @@ static void check_sync(struct device *dev, goto out; if (ref->direction != entry->direction) { - err_printk(dev, entry, "DMA-API: device driver syncs " + err_printk(dev, entry, "device driver syncs " "DMA memory with different direction " "[device address=0x%016llx] [size=%llu bytes] " "[mapped with %s] [synced with %s]\n", @@ -1256,7 +1227,7 @@ static void check_sync(struct device *dev, if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) && !(ref->direction == DMA_TO_DEVICE)) - err_printk(dev, entry, "DMA-API: device driver syncs " + err_printk(dev, entry, "device driver syncs " "device read-only DMA memory for cpu " "[device address=0x%016llx] [size=%llu bytes] " "[mapped with %s] [synced with %s]\n", @@ -1266,7 +1237,7 @@ static void check_sync(struct device *dev, if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) && !(ref->direction == DMA_FROM_DEVICE)) - err_printk(dev, entry, "DMA-API: device driver syncs " + err_printk(dev, entry, "device driver syncs " "device write-only DMA memory to device " "[device address=0x%016llx] [size=%llu bytes] " "[mapped with %s] [synced with %s]\n", @@ -1276,7 +1247,7 @@ static void check_sync(struct device *dev, if (ref->sg_call_ents && ref->type == dma_debug_sg && ref->sg_call_ents != entry->sg_call_ents) { - err_printk(ref->dev, entry, "DMA-API: device driver syncs " + err_printk(ref->dev, entry, "device driver syncs " "DMA sg list with different entry count " "[map count=%d] [sync count=%d]\n", entry->sg_call_ents, ref->sg_call_ents); @@ -1297,7 +1268,7 @@ static void check_sg_segment(struct device *dev, struct scatterlist *sg) * whoever generated the list forgot to check them. */ if (sg->length > max_seg) - err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n", + err_printk(dev, NULL, "mapping sg segment longer than device claims to support [len=%u] [max=%u]\n", sg->length, max_seg); /* * In some cases this could potentially be the DMA API @@ -1307,7 +1278,7 @@ static void check_sg_segment(struct device *dev, struct scatterlist *sg) start = sg_dma_address(sg); end = start + sg_dma_len(sg) - 1; if ((start ^ end) & ~boundary) - err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n", + err_printk(dev, NULL, "mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n", start, end, boundary); #endif } @@ -1319,11 +1290,11 @@ void debug_dma_map_single(struct device *dev, const void *addr, return; if (!virt_addr_valid(addr)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from invalid area [addr=%p] [len=%lu]\n", + err_printk(dev, NULL, "device driver maps memory from invalid area [addr=%p] [len=%lu]\n", addr, len); if (is_vmalloc_addr(addr)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n", + err_printk(dev, NULL, "device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n", addr, len); } EXPORT_SYMBOL(debug_dma_map_single); @@ -1662,48 +1633,6 @@ void debug_dma_sync_single_for_device(struct device *dev, } EXPORT_SYMBOL(debug_dma_sync_single_for_device); -void debug_dma_sync_single_range_for_cpu(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, size_t size, - int direction) -{ - struct dma_debug_entry ref; - - if (unlikely(dma_debug_disabled())) - return; - - ref.type = dma_debug_single; - ref.dev = dev; - ref.dev_addr = dma_handle; - ref.size = offset + size; - ref.direction = direction; - ref.sg_call_ents = 0; - - check_sync(dev, &ref, true); -} -EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu); - -void debug_dma_sync_single_range_for_device(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, - size_t size, int direction) -{ - struct dma_debug_entry ref; - - if (unlikely(dma_debug_disabled())) - return; - - ref.type = dma_debug_single; - ref.dev = dev; - ref.dev_addr = dma_handle; - ref.size = offset + size; - ref.direction = direction; - ref.sg_call_ents = 0; - - check_sync(dev, &ref, false); -} -EXPORT_SYMBOL(debug_dma_sync_single_range_for_device); - void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, int direction) { @@ -1780,7 +1709,7 @@ static int __init dma_debug_driver_setup(char *str) } if (current_driver_name[0]) - pr_info("DMA-API: enable driver filter for driver [%s]\n", + pr_info("enable driver filter for driver [%s]\n", current_driver_name); diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 375c77e8d52f..355d16acee6d 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -13,6 +13,7 @@ #include <linux/dma-noncoherent.h> #include <linux/pfn.h> #include <linux/set_memory.h> +#include <linux/swiotlb.h> /* * Most architectures use ZONE_DMA for the first 16 Megabytes, but @@ -30,27 +31,16 @@ static inline bool force_dma_unencrypted(void) return sev_active(); } -static bool -check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, - const char *caller) +static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) { - if (unlikely(dev && !dma_capable(dev, dma_addr, size))) { - if (!dev->dma_mask) { - dev_err(dev, - "%s: call on device without dma_mask\n", - caller); - return false; - } - - if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) { - dev_err(dev, - "%s: overflow %pad+%zu of device mask %llx bus mask %llx\n", - caller, &dma_addr, size, - *dev->dma_mask, dev->bus_dma_mask); - } - return false; + if (!dev->dma_mask) { + dev_err_once(dev, "DMA map on device without dma_mask\n"); + } else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) { + dev_err_once(dev, + "overflow %pad+%zu of DMA mask %llx bus mask %llx\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_mask); } - return true; + WARN_ON_ONCE(1); } static inline dma_addr_t phys_to_dma_direct(struct device *dev, @@ -103,14 +93,13 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask); } -void *dma_direct_alloc_pages(struct device *dev, size_t size, +struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; int page_order = get_order(size); struct page *page = NULL; u64 phys_mask; - void *ret; if (attrs & DMA_ATTR_NO_WARN) gfp |= __GFP_NOWARN; @@ -150,11 +139,34 @@ again: } } + return page; +} + +void *dma_direct_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + struct page *page; + void *ret; + + page = __dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); if (!page) return NULL; + + if (PageHighMem(page)) { + /* + * Depending on the cma= arguments and per-arch setup + * dma_alloc_from_contiguous could return highmem pages. + * Without remapping there is no way to return them here, + * so log an error and fail. + */ + dev_info(dev, "Rejecting highmem page from CMA.\n"); + __dma_direct_free_pages(dev, size, page); + return NULL; + } + ret = page_address(page); if (force_dma_unencrypted()) { - set_memory_decrypted((unsigned long)ret, 1 << page_order); + set_memory_decrypted((unsigned long)ret, 1 << get_order(size)); *dma_handle = __phys_to_dma(dev, page_to_phys(page)); } else { *dma_handle = phys_to_dma(dev, page_to_phys(page)); @@ -163,20 +175,22 @@ again: return ret; } -/* - * NOTE: this function must never look at the dma_addr argument, because we want - * to be able to use it as a helper for iommu implementations as well. - */ +void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (!dma_release_from_contiguous(dev, page, count)) + __free_pages(page, get_order(size)); +} + void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned int page_order = get_order(size); if (force_dma_unencrypted()) set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order); - if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count)) - free_pages((unsigned long)cpu_addr, page_order); + __dma_direct_free_pages(dev, size, virt_to_page(cpu_addr)); } void *dma_direct_alloc(struct device *dev, size_t size, @@ -196,67 +210,111 @@ void dma_direct_free(struct device *dev, size_t size, dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); } -static void dma_direct_sync_single_for_device(struct device *dev, +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - if (dev_is_dma_coherent(dev)) - return; - arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); + + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(dev, paddr, size, dir); } +EXPORT_SYMBOL(dma_direct_sync_single_for_device); -static void dma_direct_sync_sg_for_device(struct device *dev, +void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { struct scatterlist *sg; int i; - if (dev_is_dma_coherent(dev)) - return; + for_each_sg(sgl, sg, nents, i) { + if (unlikely(is_swiotlb_buffer(sg_phys(sg)))) + swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, + dir, SYNC_FOR_DEVICE); - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, + dir); + } } +EXPORT_SYMBOL(dma_direct_sync_sg_for_device); +#endif #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) -static void dma_direct_sync_single_for_cpu(struct device *dev, + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - if (dev_is_dma_coherent(dev)) - return; - arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); - arch_sync_dma_for_cpu_all(dev); + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (!dev_is_dma_coherent(dev)) { + arch_sync_dma_for_cpu(dev, paddr, size, dir); + arch_sync_dma_for_cpu_all(dev); + } + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); } +EXPORT_SYMBOL(dma_direct_sync_single_for_cpu); -static void dma_direct_sync_sg_for_cpu(struct device *dev, +void dma_direct_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { struct scatterlist *sg; int i; - if (dev_is_dma_coherent(dev)) - return; + for_each_sg(sgl, sg, nents, i) { + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + + if (unlikely(is_swiotlb_buffer(sg_phys(sg)))) + swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir, + SYNC_FOR_CPU); + } - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); - arch_sync_dma_for_cpu_all(dev); + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_cpu_all(dev); } +EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu); -static void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, +void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { + phys_addr_t phys = dma_to_phys(dev, addr); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_direct_sync_single_for_cpu(dev, addr, size, dir); + + if (unlikely(is_swiotlb_buffer(phys))) + swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } +EXPORT_SYMBOL(dma_direct_unmap_page); -static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) { - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir); + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir, + attrs); } +EXPORT_SYMBOL(dma_direct_unmap_sg); #endif +static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, + size_t size) +{ + return swiotlb_force != SWIOTLB_FORCE && + (!dev || dma_capable(dev, dma_addr, size)); +} + dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -264,13 +322,17 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys); - if (!check_addr(dev, dma_addr, size, __func__)) - return DIRECT_MAPPING_ERROR; + if (unlikely(!dma_direct_possible(dev, dma_addr, size)) && + !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) { + report_addr(dev, dma_addr, size); + return DMA_MAPPING_ERROR; + } - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_single_for_device(dev, dma_addr, size, dir); + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(dev, phys, size, dir); return dma_addr; } +EXPORT_SYMBOL(dma_direct_map_page); int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) @@ -279,18 +341,20 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, struct scatterlist *sg; for_each_sg(sgl, sg, nents, i) { - BUG_ON(!sg_page(sg)); - - sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg)); - if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__)) - return 0; + sg->dma_address = dma_direct_map_page(dev, sg_page(sg), + sg->offset, sg->length, dir, attrs); + if (sg->dma_address == DMA_MAPPING_ERROR) + goto out_unmap; sg_dma_len(sg) = sg->length; } - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_direct_sync_sg_for_device(dev, sgl, nents, dir); return nents; + +out_unmap: + dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); + return 0; } +EXPORT_SYMBOL(dma_direct_map_sg); /* * Because 32-bit DMA masks are so common we expect every architecture to be @@ -316,31 +380,3 @@ int dma_direct_supported(struct device *dev, u64 ma |