summaryrefslogtreecommitdiff
path: root/drivers/iommu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu')
-rw-r--r--drivers/iommu/amd_iommu.c396
-rw-r--r--drivers/iommu/amd_iommu_types.h40
-rw-r--r--drivers/iommu/amd_iommu_v2.c56
-rw-r--r--drivers/iommu/arm-smmu-v3.c210
-rw-r--r--drivers/iommu/arm-smmu.c23
-rw-r--r--drivers/iommu/dma-iommu.c11
-rw-r--r--drivers/iommu/dmar.c12
-rw-r--r--drivers/iommu/intel-iommu.c4
-rw-r--r--drivers/iommu/intel-svm.c20
-rw-r--r--drivers/iommu/io-pgtable-arm.c49
-rw-r--r--drivers/iommu/io-pgtable.h6
-rw-r--r--drivers/iommu/iommu.c2
-rw-r--r--drivers/iommu/ipmmu-vmsa.c6
-rw-r--r--drivers/iommu/msm_iommu_dev.c25
-rw-r--r--drivers/iommu/s390-iommu.c4
15 files changed, 450 insertions, 414 deletions
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 8b2be1e7714f..539b0dea8034 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -35,6 +35,7 @@
#include <linux/msi.h>
#include <linux/dma-contiguous.h>
#include <linux/irqdomain.h>
+#include <linux/percpu.h>
#include <asm/irq_remapping.h>
#include <asm/io_apic.h>
#include <asm/apic.h>
@@ -114,6 +115,45 @@ struct kmem_cache *amd_iommu_irq_cache;
static void update_domain(struct protection_domain *domain);
static int protection_domain_init(struct protection_domain *domain);
+/*
+ * For dynamic growth the aperture size is split into ranges of 128MB of
+ * DMA address space each. This struct represents one such range.
+ */
+struct aperture_range {
+
+ spinlock_t bitmap_lock;
+
+ /* address allocation bitmap */
+ unsigned long *bitmap;
+ unsigned long offset;
+ unsigned long next_bit;
+
+ /*
+ * Array of PTE pages for the aperture. In this array we save all the
+ * leaf pages of the domain page table used for the aperture. This way
+ * we don't need to walk the page table to find a specific PTE. We can
+ * just calculate its address in constant time.
+ */
+ u64 *pte_pages[64];
+};
+
+/*
+ * Data container for a dma_ops specific protection domain
+ */
+struct dma_ops_domain {
+ /* generic protection domain information */
+ struct protection_domain domain;
+
+ /* size of the aperture for the mappings */
+ unsigned long aperture_size;
+
+ /* aperture index we start searching for free addresses */
+ u32 __percpu *next_index;
+
+ /* address space relevant data */
+ struct aperture_range *aperture[APERTURE_MAX_RANGES];
+};
+
/****************************************************************************
*
* Helper functions
@@ -1167,11 +1207,21 @@ static u64 *alloc_pte(struct protection_domain *domain,
end_lvl = PAGE_SIZE_LEVEL(page_size);
while (level > end_lvl) {
- if (!IOMMU_PTE_PRESENT(*pte)) {
+ u64 __pte, __npte;
+
+ __pte = *pte;
+
+ if (!IOMMU_PTE_PRESENT(__pte)) {
page = (u64 *)get_zeroed_page(gfp);
if (!page)
return NULL;
- *pte = PM_LEVEL_PDE(level, virt_to_phys(page));
+
+ __npte = PM_LEVEL_PDE(level, virt_to_phys(page));
+
+ if (cmpxchg64(pte, __pte, __npte)) {
+ free_page((unsigned long)page);
+ continue;
+ }
}
/* No level skipping support yet */
@@ -1376,8 +1426,10 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
bool populate, gfp_t gfp)
{
int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
- struct amd_iommu *iommu;
unsigned long i, old_size, pte_pgsize;
+ struct aperture_range *range;
+ struct amd_iommu *iommu;
+ unsigned long flags;
#ifdef CONFIG_IOMMU_STRESS
populate = false;
@@ -1386,15 +1438,17 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
if (index >= APERTURE_MAX_RANGES)
return -ENOMEM;
- dma_dom->aperture[index] = kzalloc(sizeof(struct aperture_range), gfp);
- if (!dma_dom->aperture[index])
+ range = kzalloc(sizeof(struct aperture_range), gfp);
+ if (!range)
return -ENOMEM;
- dma_dom->aperture[index]->bitmap = (void *)get_zeroed_page(gfp);
- if (!dma_dom->aperture[index]->bitmap)
+ range->bitmap = (void *)get_zeroed_page(gfp);
+ if (!range->bitmap)
goto out_free;
- dma_dom->aperture[index]->offset = dma_dom->aperture_size;
+ range->offset = dma_dom->aperture_size;
+
+ spin_lock_init(&range->bitmap_lock);
if (populate) {
unsigned long address = dma_dom->aperture_size;
@@ -1407,14 +1461,20 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
if (!pte)
goto out_free;
- dma_dom->aperture[index]->pte_pages[i] = pte_page;
+ range->pte_pages[i] = pte_page;
address += APERTURE_RANGE_SIZE / 64;
}
}
- old_size = dma_dom->aperture_size;
- dma_dom->aperture_size += APERTURE_RANGE_SIZE;
+ spin_lock_irqsave(&dma_dom->domain.lock, flags);
+
+ /* First take the bitmap_lock and then publish the range */
+ spin_lock(&range->bitmap_lock);
+
+ old_size = dma_dom->aperture_size;
+ dma_dom->aperture[index] = range;
+ dma_dom->aperture_size += APERTURE_RANGE_SIZE;
/* Reserve address range used for MSI messages */
if (old_size < MSI_ADDR_BASE_LO &&
@@ -1461,62 +1521,123 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
update_domain(&dma_dom->domain);
+ spin_unlock(&range->bitmap_lock);
+
+ spin_unlock_irqrestore(&dma_dom->domain.lock, flags);
+
return 0;
out_free:
update_domain(&dma_dom->domain);
- free_page((unsigned long)dma_dom->aperture[index]->bitmap);
+ free_page((unsigned long)range->bitmap);
- kfree(dma_dom->aperture[index]);
- dma_dom->aperture[index] = NULL;
+ kfree(range);
return -ENOMEM;
}
+static dma_addr_t dma_ops_aperture_alloc(struct dma_ops_domain *dom,
+ struct aperture_range *range,
+ unsigned long pages,
+ unsigned long dma_mask,
+ unsigned long boundary_size,
+ unsigned long align_mask,
+ bool trylock)
+{
+ unsigned long offset, limit, flags;
+ dma_addr_t address;
+ bool flush = false;
+
+ offset = range->offset >> PAGE_SHIFT;
+ limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset,
+ dma_mask >> PAGE_SHIFT);
+
+ if (trylock) {
+ if (!spin_trylock_irqsave(&range->bitmap_lock, flags))
+ return -1;
+ } else {
+ spin_lock_irqsave(&range->bitmap_lock, flags);
+ }
+
+ address = iommu_area_alloc(range->bitmap, limit, range->next_bit,
+ pages, offset, boundary_size, align_mask);
+ if (address == -1) {
+ /* Nothing found, retry one time */
+ address = iommu_area_alloc(range->bitmap, limit,
+ 0, pages, offset, boundary_size,
+ align_mask);
+ flush = true;
+ }
+
+ if (address != -1)
+ range->next_bit = address + pages;
+
+ spin_unlock_irqrestore(&range->bitmap_lock, flags);
+
+ if (flush) {
+ domain_flush_tlb(&dom->domain);
+ domain_flush_complete(&dom->domain);
+ }
+
+ return address;
+}
+
static unsigned long dma_ops_area_alloc(struct device *dev,
struct dma_ops_domain *dom,
unsigned int pages,
unsigned long align_mask,
- u64 dma_mask,
- unsigned long start)
+ u64 dma_mask)
{
- unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE;
- int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT;
- int i = start >> APERTURE_RANGE_SHIFT;
unsigned long boundary_size, mask;
unsigned long address = -1;
- unsigned long limit;
+ bool first = true;
+ u32 start, i;
- next_bit >>= PAGE_SHIFT;
+ preempt_disable();
mask = dma_get_seg_boundary(dev);
+again:
+ start = this_cpu_read(*dom->next_index);
+
+ /* Sanity check - is it really necessary? */
+ if (unlikely(start > APERTURE_MAX_RANGES)) {
+ start = 0;
+ this_cpu_write(*dom->next_index, 0);
+ }
+
boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT :
1UL << (BITS_PER_LONG - PAGE_SHIFT);
- for (;i < max_index; ++i) {
- unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT;
+ for (i = 0; i < APERTURE_MAX_RANGES; ++i) {
+ struct aperture_range *range;
+ int index;
- if (dom->aperture[i]->offset >= dma_mask)
- break;
+ index = (start + i) % APERTURE_MAX_RANGES;
- limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset,
- dma_mask >> PAGE_SHIFT);
+ range = dom->aperture[index];
- address = iommu_area_alloc(dom->aperture[i]->bitmap,
- limit, next_bit, pages, 0,
- boundary_size, align_mask);
+ if (!range || range->offset >= dma_mask)
+ continue;
+
+ address = dma_ops_aperture_alloc(dom, range, pages,
+ dma_mask, boundary_size,
+ align_mask, first);
if (address != -1) {
- address = dom->aperture[i]->offset +
- (address << PAGE_SHIFT);
- dom->next_address = address + (pages << PAGE_SHIFT);
+ address = range->offset + (address << PAGE_SHIFT);
+ this_cpu_write(*dom->next_index, index);
break;
}
+ }
- next_bit = 0;
+ if (address == -1 && first) {
+ first = false;
+ goto again;
}
+ preempt_enable();
+
return address;
}
@@ -1526,21 +1647,14 @@ static unsigned long dma_ops_alloc_addresses(struct device *dev,
unsigned long align_mask,
u64 dma_mask)
{
- unsigned long address;
-
-#ifdef CONFIG_IOMMU_STRESS
- dom->next_address = 0;
- dom->need_flush = true;
-#endif
+ unsigned long address = -1;
- address = dma_ops_area_alloc(dev, dom, pages, align_mask,
- dma_mask, dom->next_address);
+ while (address == -1) {
+ address = dma_ops_area_alloc(dev, dom, pages,
+ align_mask, dma_mask);
- if (address == -1) {
- dom->next_address = 0;
- address = dma_ops_area_alloc(dev, dom, pages, align_mask,
- dma_mask, 0);
- dom->need_flush = true;
+ if (address == -1 && alloc_new_range(dom, false, GFP_ATOMIC))
+ break;
}
if (unlikely(address == -1))
@@ -1562,6 +1676,7 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
{
unsigned i = address >> APERTURE_RANGE_SHIFT;
struct aperture_range *range = dom->aperture[i];
+ unsigned long flags;
BUG_ON(i >= APERTURE_MAX_RANGES || range == NULL);
@@ -1570,12 +1685,18 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
return;
#endif
- if (address >= dom->next_address)
- dom->need_flush = true;
+ if (amd_iommu_unmap_flush) {
+ domain_flush_tlb(&dom->domain);
+ domain_flush_complete(&dom->domain);
+ }
address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT;
+ spin_lock_irqsave(&range->bitmap_lock, flags);
+ if (address + pages > range->next_bit)
+ range->next_bit = address + pages;
bitmap_clear(range->bitmap, address, pages);
+ spin_unlock_irqrestore(&range->bitmap_lock, flags);
}
@@ -1755,6 +1876,8 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
if (!dom)
return;
+ free_percpu(dom->next_index);
+
del_domain_from_list(&dom->domain);
free_pagetable(&dom->domain);
@@ -1769,6 +1892,23 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
kfree(dom);
}
+static int dma_ops_domain_alloc_apertures(struct dma_ops_domain *dma_dom,
+ int max_apertures)
+{
+ int ret, i, apertures;
+
+ apertures = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
+ ret = 0;
+
+ for (i = apertures; i < max_apertures; ++i) {
+ ret = alloc_new_range(dma_dom, false, GFP_KERNEL);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
/*
* Allocates a new protection domain usable for the dma_ops functions.
* It also initializes the page table and the address allocator data
@@ -1777,6 +1917,7 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
static struct dma_ops_domain *dma_ops_domain_alloc(void)
{
struct dma_ops_domain *dma_dom;
+ int cpu;
dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL);
if (!dma_dom)
@@ -1785,6 +1926,10 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
if (protection_domain_init(&dma_dom->domain))
goto free_dma_dom;
+ dma_dom->next_index = alloc_percpu(u32);
+ if (!dma_dom->next_index)
+ goto free_dma_dom;
+
dma_dom->domain.mode = PAGE_MODE_2_LEVEL;
dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL);
dma_dom->domain.flags = PD_DMA_OPS_MASK;
@@ -1792,8 +1937,6 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
if (!dma_dom->domain.pt_root)
goto free_dma_dom;
- dma_dom->need_flush = false;
-
add_domain_to_list(&dma_dom->domain);
if (alloc_new_range(dma_dom, true, GFP_KERNEL))
@@ -1804,8 +1947,9 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
* a valid dma-address. So we can use 0 as error value
*/
dma_dom->aperture[0]->bitmap[0] = 1;
- dma_dom->next_address = 0;
+ for_each_possible_cpu(cpu)
+ *per_cpu_ptr(dma_dom->next_index, cpu) = 0;
return dma_dom;
@@ -2328,7 +2472,7 @@ static dma_addr_t dma_ops_domain_map(struct dma_ops_domain *dom,
else if (direction == DMA_BIDIRECTIONAL)
__pte |= IOMMU_PTE_IR | IOMMU_PTE_IW;
- WARN_ON(*pte);
+ WARN_ON_ONCE(*pte);
*pte = __pte;
@@ -2357,7 +2501,7 @@ static void dma_ops_domain_unmap(struct dma_ops_domain *dom,
pte += PM_LEVEL_INDEX(0, address);
- WARN_ON(!*pte);
+ WARN_ON_ONCE(!*pte);
*pte = 0ULL;
}
@@ -2393,26 +2537,11 @@ static dma_addr_t __map_single(struct device *dev,
if (align)
align_mask = (1UL << get_order(size)) - 1;
-retry:
address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask,
dma_mask);
- if (unlikely(address == DMA_ERROR_CODE)) {
- /*
- * setting next_address here will let the address
- * allocator only scan the new allocated range in the
- * first run. This is a small optimization.
- */
- dma_dom->next_address = dma_dom->aperture_size;
- if (alloc_new_range(dma_dom, false, GFP_ATOMIC))
- goto out;
-
- /*
- * aperture was successfully enlarged by 128 MB, try
- * allocation again
- */
- goto retry;
- }
+ if (address == DMA_ERROR_CODE)
+ goto out;
start = address;
for (i = 0; i < pages; ++i) {
@@ -2427,11 +2556,10 @@ retry:
ADD_STATS_COUNTER(alloced_io_mem, size);
- if (unlikely(dma_dom->need_flush && !amd_iommu_unmap_flush)) {
- domain_flush_tlb(&dma_dom->domain);
- dma_dom->need_flush = false;
- } else if (unlikely(amd_iommu_np_cache))
+ if (unlikely(amd_iommu_np_cache)) {
domain_flush_pages(&dma_dom->domain, address, size);
+ domain_flush_complete(&dma_dom->domain);
+ }
out:
return address;
@@ -2478,11 +2606,6 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
SUB_STATS_COUNTER(alloced_io_mem, size);
dma_ops_free_addresses(dma_dom, dma_addr, pages);
-
- if (amd_iommu_unmap_flush || dma_dom->need_flush) {
- domain_flush_pages(&dma_dom->domain, flush_addr, size);
- dma_dom->need_flush = false;
- }
}
/*
@@ -2493,11 +2616,9 @@ static dma_addr_t map_page(struct device *dev, struct page *page,
enum dma_data_direction dir,
struct dma_attrs *attrs)
{
- unsigned long flags;
+ phys_addr_t paddr = page_to_phys(page) + offset;
struct protection_domain *domain;
- dma_addr_t addr;
u64 dma_mask;
- phys_addr_t paddr = page_to_phys(page) + offset;
INC_STATS_COUNTER(cnt_map_single);
@@ -2509,19 +2630,8 @@ static dma_addr_t map_page(struct device *dev, struct page *page,
dma_mask = *dev->dma_mask;
- spin_lock_irqsave(&domain->lock, flags);
-
- addr = __map_single(dev, domain->priv, paddr, size, dir, false,
+ return __map_single(dev, domain->priv, paddr, size, dir, false,
dma_mask);
- if (addr == DMA_ERROR_CODE)
- goto out;
-
- domain_flush_complete(domain);
-
-out:
- spin_unlock_irqrestore(&domain->lock, flags);
-
- return addr;
}
/*
@@ -2530,7 +2640,6 @@ out:
static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
enum dma_data_direction dir, struct dma_attrs *attrs)
{
- unsigned long flags;
struct protection_domain *domain;
INC_STATS_COUNTER(cnt_unmap_single);
@@ -2539,13 +2648,7 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
if (IS_ERR(domain))
return;
- spin_lock_irqsave(&domain->lock, flags);
-
__unmap_single(domain->priv, dma_addr, size, dir);
-
- domain_flush_complete(domain);
-
- spin_unlock_irqrestore(&domain->lock, flags);
}
/*
@@ -2556,7 +2659,6 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
int nelems, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
- unsigned long flags;
struct protection_domain *domain;
int i;
struct scatterlist *s;
@@ -2572,8 +2674,6 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
dma_mask = *dev->dma_mask;
- spin_lock_irqsave(&domain->lock, flags);
-
for_each_sg(sglist, s, nelems, i) {
paddr = sg_phys(s);
@@ -2588,12 +2688,8 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
goto unmap;
}
- domain_flush_complete(domain);
-
-out:
- spin_unlock_irqrestore(&domain->lock, flags);
-
return mapped_elems;
+
unmap:
for_each_sg(sglist, s, mapped_elems, i) {
if (s->dma_address)
@@ -2602,9 +2698,7 @@ unmap:
s->dma_address = s->dma_length = 0;
}
- mapped_elems = 0;
-
- goto out;
+ return 0;
}
/*
@@ -2615,7 +2709,6 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
int nelems, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
- unsigned long flags;
struct protection_domain *domain;
struct scatterlist *s;
int i;
@@ -2626,17 +2719,11 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
if (IS_ERR(domain))
return;
- spin_lock_irqsave(&domain->lock, flags);
-
for_each_sg(sglist, s, nelems, i) {
__unmap_single(domain->priv, s->dma_address,
s->dma_length, dir);
s->dma_address = s->dma_length = 0;
}
-
- domain_flush_complete(domain);
-
- spin_unlock_irqrestore(&domain->lock, flags);
}
/*
@@ -2648,7 +2735,6 @@ static void *alloc_coherent(struct device *dev, size_t size,
{
u64 dma_mask = dev->coherent_dma_mask;
struct protection_domain *domain;
- unsigned long flags;
struct page *page;
INC_STATS_COUNTER(cnt_alloc_coherent);
@@ -2680,19 +2766,11 @@ static void *alloc_coherent(struct device *dev, size_t size,
if (!dma_mask)
dma_mask = *dev->dma_mask;
- spin_lock_irqsave(&domain->lock, flags);
-
*dma_addr = __map_single(dev, domain->priv, page_to_phys(page),
size, DMA_BIDIRECTIONAL, true, dma_mask);
- if (*dma_addr == DMA_ERROR_CODE) {
- spin_unlock_irqrestore(&domain->lock, flags);
+ if (*dma_addr == DMA_ERROR_CODE)
goto out_free;
- }
-
- domain_flush_complete(domain);
-
- spin_unlock_irqrestore(&domain->lock, flags);
return page_address(page);
@@ -2712,7 +2790,6 @@ static void free_coherent(struct device *dev, size_t size,
struct dma_attrs *attrs)
{
struct protection_domain *domain;
- unsigned long flags;
struct page *page;
INC_STATS_COUNTER(cnt_free_coherent);
@@ -2724,14 +2801,8 @@ static void free_coherent(struct device *dev, size_t size,
if (IS_ERR(domain))
goto free_mem;
- spin_lock_irqsave(&domain->lock, flags);
-
__unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
- domain_flush_complete(domain);
-
- spin_unlock_irqrestore(&domain->lock, flags);
-
free_mem:
if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
__free_pages(page, get_order(size));
@@ -2746,14 +2817,43 @@ static int amd_iommu_dma_supported(struct device *dev, u64 mask)
return check_device(dev);
}
+static int set_dma_mask(struct device *dev, u64 mask)
+{
+ struct protection_domain *domain;
+ int max_apertures = 1;
+
+ domain = get_domain(dev);
+ if (IS_ERR(domain))
+ return PTR_ERR(domain);
+
+ if (mask == DMA_BIT_MASK(64))
+ max_apertures = 8;
+ else if (mask > DMA_BIT_MASK(32))
+ max_apertures = 4;
+
+ /*
+ * To prevent lock contention it doesn't make sense to allocate more
+ * apertures than online cpus
+ */
+ if (max_apertures > num_online_cpus())
+ max_apertures = num_online_cpus();
+
+ if (dma_ops_domain_alloc_apertures(domain->priv, max_apertures))
+ dev_err(dev, "Can't allocate %d iommu apertures\n",
+ max_apertures);
+
+ return 0;
+}
+
static struct dma_map_ops amd_iommu_dma_ops = {
- .alloc = alloc_coherent,
- .free = free_coherent,
- .map_page = map_page,
- .unmap_page = unmap_page,
- .map_sg = map_sg,
- .unmap_sg = unmap_sg,
- .dma_supported = amd_iommu_dma_supported,
+ .alloc = alloc_coherent,
+ .free = free_coherent,
+ .map_page = map_page,
+ .unmap_page = unmap_page,
+ .map_sg = map_sg,
+ .unmap_sg = unmap_sg,
+ .dma_supported = amd_iommu_dma_supported,
+ .set_dma_mask = set_dma_mask,
};
int __init amd_iommu_init_api(void)
@@ -3757,11 +3857,9 @@ static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
case X86_IRQ_ALLOC_TYPE_MSI:
case X86_IRQ_ALLOC_TYPE_MSIX:
devid = get_device_id(&info->msi_dev->dev);
- if (devid >= 0) {
- iommu = amd_iommu_rlookup_table[devid];
- if (iommu)
- return iommu->msi_domain;
- }
+ iommu = amd_iommu_rlookup_table[devid];
+ if (iommu)
+ return iommu->msi_domain;
break;
default:
break;
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index b08cf57bf455..9d32b20a5e9a 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -425,46 +425,6 @@ struct protection_domain {
};
/*
- * For dynamic growth the aperture size is split into ranges of 128MB of
- * DMA address space each. This struct represents one such range.
- */
-struct aperture_range {
-
- /* address allocation bitmap */
- unsigned long *bitmap;
-
- /*
- * Array of PTE pages for the aperture. In this array we save all the
- * leaf pages of the domain page table used for the aperture. This way
- * we don't need to walk the page table to find a specific PTE. We can
- * just calculate its address in constant time.
- */
- u64 *pte_pages[64];
-
- unsigned long offset;
-};
-
-/*
- * Data container for a dma_ops specific protection domain
- */
-struct dma_ops_domain {
- /* generic protection domain information */
- struct protection_domain domain;
-
- /* size of the aperture for the mappings */
- unsigned long aperture_size;
-
- /* address we start to search for free addresses */
- unsigned long next_address;
-
- /* address space relevant data */
- struct aperture_range *aperture[APERTURE_MAX_RANGES];
-
- /* This will be set to true when TLB needs to be flushed */
- bool need_flush;
-};
-
-/*
* Structure where we save information about one hardware AMD IOMMU in the
* system.
*/
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index d21d4edf7236..c865737326e1 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -432,7 +432,7 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
unbind_pasid(pasid_state);
}
-static struct mmu_notifier_ops iommu_mn = {
+static const struct mmu_notifier_ops iommu_mn = {
.release = mn_release,
.clear_flush_young = mn_clear_flush_young,
.invalidate_page = mn_invalidate_page,
@@ -494,46 +494,58 @@ static void handle_fault_error(struct fault *fault)
}
}
+static bool access_error(struct vm_area_struct *vma, struct fault *fault)
+{
+ unsigned long requested = 0;
+
+ if (fault->flags & PPR_FAULT_EXEC)
+ requested |= VM_EXEC;
+
+ if (fault->flags & PPR_FAULT_READ)
+ requested |= VM_READ;
+
+ if (fault->flags & PPR_FAULT_WRITE)
+ requested |= VM_WRITE;
+
+ return (requested & ~vma->vm_flags) != 0;
+}
+
static void do_fault(struct work_struct *work)
{
struct fault *fault = container_of(work, struct fault, work);
- struct mm_struct *mm;
struct vm_area_struct *vma;
+ int ret = VM_FAULT_ERROR;
+ unsigned int flags = 0;
+ struct mm_struct *mm;
u64 address;
- int ret, write;
-
- write = !!(fault->flags & PPR_FAULT_WRITE);
mm = fault->state->mm;
address = fault->address;
+ if (fault->flags & PPR_FAULT_USER)
+ flags |= FAULT_FLAG_USER;
+ if (fault->flags & PPR_FAULT_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
down_read(&mm->mmap_sem);
vma = find_extend_vma(mm, address);
- if (!vma || address < vma->vm_start) {
+ if (!vma || address < vma->vm_start)
/* failed to get a vma in the right range */
- up_read(&mm->mmap_sem);
- handle_fault_error(fault);
goto out;
- }
- if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) {
- /* handle_mm_fault would BUG_ON() */
- up_read(&mm->mmap_sem);
- handle_fault_error(fault);
+ /* Check if we have the right permissions on the vma */
+ if (access_error(vma, fault))
goto out;
- }
- ret = handle_mm_fault(mm, vma, address, write);
- if (ret & VM_FAULT_ERROR) {
- /* failed to service fault */
- up_read(&mm->mmap_sem);
- handle_fault_error(fault);
- goto out;
- }
+ ret = handle_mm_fault(mm, vma, address, flags);
+out:
up_read(&mm->mmap_sem);
-out:
+ if (ret & VM_FAULT_ERROR)
+ /* failed to service fault */
+ handle_fault_error(fault);
+
finish_pri_tag(fault->dev_state, fault->state, fault->tag);
put_pasid_state(fault->state);
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 4e5118a4cd30..20875341c865 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -40,7 +40,10 @@
#define IDR0_ST_LVL_SHIFT 27
#define IDR0_ST_LVL_MASK 0x3
#define IDR0_ST_LVL_2LVL (1 << IDR0_ST_LVL_SHIFT)
-#define IDR0_STALL_MODEL (3 << 24)
+#define IDR0_STALL_MODEL_SHIFT 24
+#define IDR0_STALL_MODEL_MASK 0x3
+#define IDR0_STALL_MODEL_STALL (0 << IDR0_STALL_MODEL_SHIFT)
+#define IDR0_STALL_MODEL_FORCE (2 << IDR0_STALL_MODEL_SHIFT)
#define IDR0_TTENDIAN_SHIFT 21
#define IDR0_TTENDIAN_MASK 0x3
#define IDR0_TTENDIAN_LE (2 << IDR0_TTENDIAN_SHIFT)
@@ -253,6 +256,9 @@
#define STRTAB_STE_1_STRW_EL2 2UL
#define STRTAB_STE_1_STRW_SHIFT 30
+#define STRTAB_STE_1_SHCFG_INCOMING 1UL
+#define STRTAB_STE_1_SHCFG_SHIFT 44
+
#define STRTAB_STE_2_S2VMID_SHIFT 0
#define STRTAB_STE_2_S2VMID_MASK 0xffffUL
#define STRTAB_STE_2_VTCR_SHIFT 32
@@ -378,7 +384,6 @@
#define PRIQ_0_SID_MASK 0xffffffffUL
#define PRIQ_0_SSID_SHIFT 32
#define PRIQ_0_SSID_MASK 0xfffffUL
-#define PRIQ_0_OF (1UL << 57)
#define PRIQ_0_PERM_PRIV (1UL << 58)
#define PRIQ_0_PERM_EXEC (1UL << 59)
#define PRIQ_0_PERM_READ (1UL << 60)
@@ -855,15 +860,17 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
};
dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons,
- cerror_str[idx]);
+ idx < ARRAY_SIZE(cerror_str) ? cerror_str[idx] : "Unknown");
switch (idx) {
- case CMDQ_ERR_CERROR_ILL_IDX:
- break;
case CMDQ_ERR_CERROR_ABT_IDX:
dev_err(smmu->dev, "retrying command fetch\n");
case CMDQ_ERR_CERROR_NONE_IDX:
return;
+ case CMDQ_ERR_CERROR_ILL_IDX:
+ /* Fallthrough */
+ default:
+ break;
}
/*
@@ -1042,6 +1049,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
: STRTAB_STE_0_CFG_BYPASS;
dst[0] = cpu_to_le64(val);
+ dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING
+ << STRTAB_STE_1_SHCFG_SHIFT);
dst[2] = 0; /* Nuke the VMID */
if (ste_live)
arm_smmu_sync_ste_for_sid(smmu, sid);
@@ -1056,12 +1065,14 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
STRTAB_STE_1_S1C_CACHE_WBRA
<< STRTAB_STE_1_S1COR_SHIFT |
STRTAB_STE_1_S1C_SH_ISH << STRTAB_STE_1_S1CSH_SHIFT |
- STRTAB_STE_1_S1STALLD |
#ifdef CONFIG_PCI_ATS
STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT |
#endif
STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);
+ if (smmu->features & ARM_SMMU_FEAT_STALLS)
+ dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
+
val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
<< STRTAB_STE_0_S1CTXPTR_SHIFT) |
STRTAB_STE_0_CFG_S1_TRANS;
@@ -1123,8 +1134,8 @@ static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
strtab = &cfg->strtab[(sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS];
desc->span = STRTAB_SPLIT + 1;
- desc->l2ptr = dma_zalloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
- GFP_KERNEL);
+ desc->l2ptr = dmam_alloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
+ GFP_KERNEL | __GFP_ZERO);
if (!desc->l2ptr) {
dev_err(smmu->dev,
"failed to allocate l2 stream table for SID %u\n",
@@ -1250,50 +1261,50 @@ static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
{
- u32 gerror, gerrorn;
+ u32 gerror, gerrorn, active;
struct arm_smmu_device *smmu = dev;
gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
- gerror ^= gerrorn;
- if (!(gerror & GERROR_ERR_MASK))
+ active = gerror ^ gerrorn;
+ if (!(active & GERROR_ERR_MASK))
return IRQ_NONE; /* No errors pending */
dev_warn(smmu->dev,
"unexpected global error reported (0x%08x), this could be serious\n",
- gerror);
+ active);
- if (gerror & GERROR_SFM_ERR) {
+ if (active & GERROR_SFM_ERR) {
dev_err(smmu->dev, "device has entered Service Failure Mode!\n");
arm_smmu_device_disable(smmu);
}
- if (gerror & GERROR_MSI_GERROR_ABT_ERR)
+ if (active & GERROR_MSI_GERROR_ABT_ERR)
dev_warn(smmu->dev, "GERROR MSI write aborted\n");
- if (gerror & GERROR_MSI_PRIQ_ABT_ERR) {
+ if (active & GERROR_MSI_PRIQ_ABT_ERR) {
dev_warn(smmu->dev, "PRIQ MSI write aborted\n");
arm_smmu_priq_handler(irq, smmu->dev);
}
- if (gerror & GERROR_MSI_EVTQ_ABT_ERR) {
+ if (active & GERROR_MSI_EVTQ_ABT_ERR) {
dev_warn(smmu->dev, "EVTQ MSI write aborted\n");
arm_smmu_evtq_handler(irq, smmu->dev);
}
- if (gerror & GERROR_MSI_CMDQ_ABT_ERR) {
+ if (active & GERROR_MSI_CMDQ_ABT_ERR) {
dev_warn(smmu->dev, "CMDQ MSI write aborted\n");
arm_smmu_cmdq_sync_handler(irq, smmu->dev);
}
- if (gerror & GERROR_PRIQ_ABT_ERR)
+ if (active & GERROR_PRIQ_ABT_ERR)
dev_err(smmu->dev, "PRIQ write aborted -- events may have been lost\n");
- if (gerror & GERROR_EVTQ_ABT_ERR)
+ if (active & GERROR_EVTQ_ABT_ERR)
dev_err(smmu->dev, "EVTQ write aborted -- events may have been lost\n");
- if (gerror & GERROR_CMDQ_ERR)
+ if (active & GERROR_CMDQ_ERR)
arm_smmu_cmdq_skip_err(smmu);
writel(gerror, smmu->base + ARM_SMMU_GERRORN);
@@ -1335,7 +1346,7 @@ static void arm_smmu_tlb_inv_context(void *cookie)
}
static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
- bool leaf, void *cookie)
+ size_t granule, bool leaf, void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
struct arm_smmu_device *smmu = smmu_domain->smmu;
@@ -1354,7 +1365,10 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid;
}
- arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+ do {
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+ cmd.tlbi.addr += granule;
+ } while (size -= granule);
}
static struct iommu_gather_ops arm_smmu_gather_ops = {
@@ -1429,10 +1443,10 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
if (cfg->cdptr) {
- dma_free_coherent(smmu_domain->smmu->dev,
- CTXDESC_CD_DWORDS << 3,
- cfg->cdptr,
- cfg->cdptr_dma);
+ dmam_free_coherent(smmu_domain->smmu->dev,
+ CTXDESC_CD_DWORDS << 3,
+ cfg->cdptr,
+ cfg->cdptr_dma);
arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid);
}
@@ -1457,8 +1471,9 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
if (IS_ERR_VALUE(asid))
return asid;
- cfg->cdptr = dma_zalloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
- &cfg->cdptr_dma, GFP_KERNEL);
+ cfg->cdptr = dmam_alloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
+ &cfg->cdptr_dma,
+ GFP_KERNEL | __GFP_ZERO);
if (!cfg->cdptr) {
dev_warn(smmu->dev, "failed to allocate context descriptor\n");
ret = -ENOMEM;
@@ -1804,13 +1819,13 @@ static int arm_smmu_add_device(struct device *dev)
smmu = arm_smmu_get_for_pci_dev(pdev);
if (!smmu) {
ret = -ENOENT;
- goto out_put_group;
+ goto out_remove_dev;
}
smmu_group = kzalloc(sizeof(*smmu_group), GFP_KERNEL);
if (!smmu_group) {
ret = -ENOMEM;
- goto out_put_group;
+ goto out_remove_dev;
}
smmu_group->ste.valid = true;
@@ -1826,20 +1841,20 @@ static int arm_smmu_add_device(struct device *dev)
for (i = 0; i < smmu_group->num_sids; ++i) {
/* If we already know about this SID, then we're done */
if (smmu_group->sids[i] == sid)
- return 0;
+ goto out_put_group;
}
/* Check the SID is in range of the SMMU and our stream table */
if (!arm_smmu_sid_in_range(smmu, sid)) {
ret = -ERANGE;
- goto out_put_group;
+ goto out_remove_dev;
}
/* Ensure l2 strtab is initialised */
if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
ret = arm_smmu_init_l2_strtab(smmu, sid);
if (ret)
- goto out_put_group;
+ goto out_remove_dev;
}
/* Resize the SID array for the group */
@@ -1849,16 +1864,20 @@ static int arm_smmu_add_device(struct device *dev)
if (!sids) {
smmu_group->num_sids--;
ret = -ENOMEM;
- goto out_put_group;
+ goto out_remove_dev;
}
/* Add the new SID */
sids[smmu_group->num_sids - 1] = sid;
smmu_group->sids = sids;
- return 0;
out_put_group:
iommu_group_put(group);
+ return 0;
+
+out_remove_dev:
+ iommu_group_remove_device(dev);
+ iommu_group_put(group);
return ret;
}
@@ -1937,7 +1956,7 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
{
size_t qsz = ((1 << q->max_n_shift) * dwords) << 3;
- q->base = dma_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL);
+ q->base = dmam_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL);
if (!q->base) {
dev_err(smmu->dev, "failed to allocate queue (0x%zx bytes)\n",
qsz);
@@ -1957,23 +1976,6 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
return 0;
}
-static void arm_smmu_free_one_queue(struct arm_smmu_device *smmu,
- struct arm_smmu_queue *q)
-{
- size_t qsz = ((1 << q->max_n_shift) * q->ent_dwords) << 3;
-
- dma_free_coherent(smmu->dev, qsz, q->base, q->base_dma);
-}
-
-static void arm_smmu_free_queues(struct arm_smmu_device *smmu)
-{
- arm_smmu_free_one_queue(smmu, &smmu->cmdq.q);
- arm_smmu_free_one_queue(smmu, &smmu->evtq.q);
-
- if (smmu->features & ARM_SMMU_FEAT_PRI)
- arm_smmu_free_one_queue(smmu, &smmu->priq.q);
-}
-
static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
{
int ret;
@@ -1983,49 +1985,20 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS);
if (ret)
- goto out;
+ return ret;
/* evtq */
ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD,
ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS);
if (ret)
- goto out_free_cmdq;
+ return ret;
/* priq */
if (!(smmu->features & ARM_SMMU_FEAT_PRI))
return 0;
- ret = arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
- ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS);
- if (ret)
- goto out_free_evtq;
-
- return 0;
-
-out_free_evtq:
- arm_smmu_free_one_queue(smmu, &smmu->evtq.q);
-out_free_cmdq:
- arm_smmu_free_one_queue(smmu, &smmu->cmdq.q);
-out:
- return ret;
-}
-
-static void arm_smmu_free_l2_strtab(struct arm_smmu_device *smmu)
-{
- int i;
- size_t size;
- struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
-
- size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
- for (i = 0; i < cfg->num_l1_ents; ++i) {
- struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[i];
-
- if (!desc->l2ptr)
- continue;
-
- dma_free_coherent(smmu->dev, size, desc->l2ptr,
- desc->l2ptr_dma);
- }
+ return arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
+ ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS);
}
static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
@@ -2054,7 +2027,6 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
void *strtab;
u64 reg;
u32 size, l1size;
- int ret;
struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
/*
@@ -2077,8 +2049,8 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
size, smmu->sid_bits);
l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
- strtab = dma_zalloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
- GFP_KERNEL);
+ strtab = dmam_alloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
+ GFP_KERNEL | __GFP_ZERO);
if (!strtab) {
dev_err(smmu->dev,
"failed to allocate l1 stream table (%u bytes)\n",
@@ -2095,13 +2067,7 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
<< STRTAB_BASE_CFG_SPLIT_SHIFT;
cfg->strtab_base_cfg = reg;
- ret = arm_smmu_init_l1_strtab(smmu);
- if (ret)
- dma_free_coherent(smmu->dev,
- l1size,
- strtab,
- cfg->strtab_dma);
- return ret;
+ return arm_smmu_init_l1_strtab(smmu);
}
static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
@@ -2112,8 +2078,8 @@ static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
size = (1 << smmu->sid_bits) * (STRTAB_STE_DWORDS << 3);
- strtab = dma_zalloc_coherent(smmu->dev, size, &cfg->strtab_dma,
- GFP_KERNEL);
+ strtab = dmam_alloc_coherent(smmu->dev, size, &cfg->strtab_dma,
+ GFP_KERNEL | __GFP_ZERO);
if (!strtab) {
dev_err(smmu->dev,
"failed to allocate linear stream table (%u bytes)\n",
@@ -2157,21 +2123,6 @@ static int arm_smmu_init_strtab(struct arm_smmu_device *smmu)
return 0;
}
-static void arm_smmu_free_strtab(struct arm_smmu_device *smmu)
-{
- struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
- u32 size = cfg->num_l1_ents;
-
- if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
- arm_smmu_free_l2_strtab(smmu);
- size *= STRTAB_L1_DESC_DWORDS << 3;
- } else {
- size *= STRTAB_STE_DWORDS * 3;
- }
-
- dma_free_coherent(smmu->dev, size, cfg->strtab, cfg->strtab_dma);
-}
-
static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
{
int ret;
@@ -2180,21 +2131,7 @@ static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
if (ret)
return ret;
- ret = arm_smmu_init_strtab(smmu);
- if (ret)
- goto out_free_queues;
-
- return 0;
-
-out_free_queues:
- arm_smmu_free_queues(smmu);
- return ret;
-}
-
-static void arm_smmu_free_structures(struct arm_smmu_device *smmu)
-{
- arm_smmu_free_strtab(smmu);
- arm_smmu_free_queues(smmu);
+ return arm_smmu_init_strtab(smmu);
}
static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
@@ -2532,8 +2469,12 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
dev_warn(smmu->dev, "IDR0.COHACC overridden by dma-coherent property (%s)\n",
coherent ? "true" : "false");
- if (reg & IDR0_STALL_MODEL)
+ switch (reg & IDR0_STALL_MODEL_MASK << IDR0_STALL_MODEL_SHIFT) {
+ case IDR0_STALL_MODEL_STALL:
+ /* Fallthrough */
+ case IDR0_STALL_MODEL_FORCE:
smmu->features |= ARM_SMMU_FEAT_STALLS;
+ }
if (reg & IDR0_S1P)
smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
@@ -2699,15 +2640,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, smmu);
/* Reset the device */
- ret = arm_smmu_device_reset(smmu);
- if (ret)
- goto out_free_structures;
-
- return 0;
-
-out_free_structures:
- arm_smmu_free_structures(smmu);
- return ret;
+ return arm_smmu_device_reset(smmu);
}
static int arm_smmu_device_remove(struct platform_device *pdev)
@@ -2715,7 +2648,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
arm_smmu_device_disable(smmu);
- arm_smmu_free_structures(smmu);
return 0;
}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 47dc7a793f5c..59ee4b8a3236 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -582,7 +582,7 @@ static void arm_smmu_tlb_inv_context(void *cookie)
}
static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
- bool leaf, void *cookie)
+ size_t granule, bool leaf, void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
@@ -597,12 +597,18 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
if (!IS_ENABLED(CONFIG_64BIT) || smmu->version == ARM_SMMU_V1) {
iova &= ~12UL;
iova |= ARM_SMMU_CB_ASID(cfg);
- writel_relaxed(iova, reg);
+ do {
+ writel_relaxed(iova, reg);
+ iova += granule;
+ } while (size -= granule);
#ifdef CONFIG_64BIT
} else {
iova >>= 12;
iova |= (u64)ARM_SMMU_CB_ASID(cfg) << 48;
- writeq_relaxed(iova, reg);
+ do {
+ writeq_relaxed(iova, reg);
+ iova += granule >> 12;
+ } while (size -= granule);
#endif
}
#ifdef CONFIG_64BIT
@@ -610,7 +616,11 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
reg += leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L :
ARM_SMMU_CB_S2_TLBIIPAS2;
- writeq_relaxed(iova >> 12, reg);
+ iova >>= 12;
+ do {
+ writeq_relaxed(iova, reg);
+ iova += granule >> 12;
+ } while (size -= granule);
#endif
} else {
reg = ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_TLBIVMID;
@@ -945,9 +955,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
free_irq(irq, domain);
}
- if (smmu_domain->pgtbl_ops)
- free_io_pgtable_ops(smmu_domain->pgtbl_ops);
-
+ free_io_pgtable_ops(smmu_domain->pgtbl_ops);
__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
}
@@ -1357,6 +1365,7 @@ static int arm_smmu_add_device(struct device *dev)
if (IS_ERR(group))
return PTR_ERR(group);
+ iommu_group_put(group);
return 0;
}
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 3a20db4f8604..72d6182666cb 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -21,10 +21,13 @@
#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>
int iommu_dma_init(void)
{
@@ -191,6 +194,7 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp)
{
struct page **pages;
unsigned int i = 0, array_size = count * sizeof(*pages);
+ unsigned int order = MAX_ORDER;
if (array_size <= PAGE_SIZE)
pages = kzalloc(array_size, GFP_KERNEL);
@@ -204,14 +208,15 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp)
while (count) {
struct page *page = NULL;
- int j, order = __fls(count);
+ int j;
/*
* Higher-order allocations are a convenience rather
* than a necessity, hence using __GFP_NORETRY until
* falling back to single-page allocations.
*/
- for (order = min(order, MAX_ORDER); order > 0; order--) {
+ for (order = min_t(unsigned int, order, __fls(count));
+ order > 0; order--) {
page = alloc_pages(gfp | __GFP_NORETRY, order);
if (!page)
continue;
@@ -453,7 +458,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
size_t s_offset = iova_offset(iovad, s->offset);
size_t s_length = s->length;
- sg_dma_address(s) = s->offset;
+ sg_dma_address(s) = s_offset;
sg_dma_len(s) = s_length;
s->offset -= s_offset;
s_length = iova_align(iovad, s_length + s_offset);
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 80e3c176008e..62a400c5ba06 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1063,13 +1063,19 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
raw_spin_lock_init(&iommu->register_lock);
- drhd->iommu = iommu;
-
- if (intel_iommu_enabled)
+ if (intel_iommu_enabled) {
iommu->iommu_dev = iommu_device_create(NULL, iommu,
intel_iommu_groups,
"%s", iommu->name);
+ if (IS_ERR(iommu->iommu_dev)) {
+ err = PTR_ERR(iommu->iommu_dev);
+ goto err_unmap;
+ }
+ }
+
+ drhd->iommu = iommu;
+
return 0;
err_unmap:
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index f1042daef9ad..ac7387686ddc 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2159,7 +2159,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
sg_res = aligned_nrpages(sg->offset, sg->length);
sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset;
sg->dma_length = sg->length;
- pteval = (sg_phys(sg) & PAGE_MASK) | prot;
+ pteval = page_to_phys(sg_page(sg)) | prot;
phys_pfn = pteval >> VTD_PAGE_SHIFT;
}
@@ -3704,7 +3704,7 @@ static int intel_nontranslate_map_sg(struct device *hddev,
for_each_sg(sglist, sg, nelems, i) {
BUG_ON(!sg_page(sg));
- sg->dma_address = sg_phys(sg);
+ sg->dma_address = page_to_phys(sg_page(sg)) + sg->offset;
sg->dma_length = sg->length;
}
return nelems;
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index c69e3f9ec958..50464833d0b8 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -484,6 +484,23 @@ struct page_req_dsc {
};
#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x10)
+
+static bool access_error(struct vm_area_struct *vma, struct page_req_dsc *req)
+{
+ unsigned long requested = 0;
+
+ if (req->exe_req)
+ requested |= VM_EXEC;
+
+ if (req->rd_req)
+ requested |= VM_READ;
+
+ if (req->wr_req)
+ requested |= VM_WRITE;
+
+ return (requested & ~vma->vm_flags) != 0;
+}
+
static irqreturn_t prq_event_thread(int irq, void *d)
{
struct intel_iommu *iommu = d;
@@ -539,6 +556,9 @@ static irqreturn_t prq_event_thread(int irq, void *d)
if (!vma || address < vma->vm_start)
goto invalid;
+ if (access_error(vma, req))
+ goto invalid;
+
ret = handle_mm_fault(svm->mm, vma, address,
req->wr_req ? FAULT_FLAG_WRITE : 0);
if (ret & VM_FAULT_ERROR)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 7df97777662d..8bbcbfe7695c 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -38,9 +38,6 @@
#define io_pgtable_to_data(x) \
container_of((x), struct arm_lpae_io_pgtable, iop)
-#define io_pgtable_ops_to_pgtable(x) \
- container_of((x), struct io_pgtable, ops)
-
#define io_pgtable_ops_to_data(x) \
io_pgtable_to_data(io_pgtable_ops_to_pgtable(x))
@@ -58,8 +55,10 @@
((((d)->levels - ((l) - ARM_LPAE_START_LVL(d) + 1)) \
* (d)->bits_per_level) + (d)->pg_shift)
+#define ARM_LPAE_GRANULE(d) (1UL << (d)->pg_shift)
+
#define ARM_LPAE_PAGES_PER_PGD(d) \
- DIV_ROUND_UP((d)->pgd_size, 1UL << (d)->pg_shift)
+ DIV_ROUND_UP((d)->pgd_size, ARM_LPAE_GRANULE(d))
/*
* Calculate the index at level l used to map virtual address a using the
@@ -169,7 +168,7 @@
/* IOPTE accessors */
#define iopte_deref(pte,d) \
(__va((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1) \
- & ~((1ULL << (d)->pg_shift) - 1)))
+ & ~(ARM_LPAE_GRANULE(d) - 1ULL)))
#define iopte_type(pte,l) \
(((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK)
@@ -326,7 +325,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
/* Grab a pointer to the next level */
pte = *ptep;
if (!pte) {
- cptep = __arm_lpae_alloc_pages(1UL << data->pg_shift,
+ cptep = __arm_lpae_alloc_pages(ARM_LPAE_GRANULE(data),
GFP_ATOMIC, cfg);
if (!cptep)
return -ENOMEM;
@@ -405,17 +404,18 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
arm_lpae_iopte *start, *end;
unsigned long table_size;
- /* Only leaf entries at the last level */
- if (lvl == ARM_LPAE_MAX_LEVELS - 1)
- return;
-
if (lvl == ARM_LPAE_START_LVL(data))
table_size = data->pgd_size;
else
- table_size = 1UL << data->pg_shift;
+ table_size = ARM_LPAE_GRANULE(data);
start = ptep;
- end = (void *)ptep + table_size;
+
+ /* Only leaf entries at the last level */
+ if (lvl == ARM_LPAE_MAX_LEVELS - 1)
+ end = ptep;
+ else
+ end = (void *)ptep + table_size;
while (ptep != end) {
arm_lpae_iopte pte = *ptep++;
@@ -473,7 +473,7 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
__arm_lpae_set_pte(ptep, table, cfg);
iova &= ~(blk_size - 1);
- cfg->tlb->tlb_add_flush(iova, blk_size, true, data->iop.cookie);
+ cfg->tlb->tlb_add_flush(iova, blk_size, blk_size, true, data->iop.cookie);
return size;
}
@@ -486,11 +486,13 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
void *cookie = data->iop.cookie;
size_t blk_size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+ /* Something went horribly wrong and we ran out of page table */
+ if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
+ return 0;
+
ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
pte = *ptep;
-
- /* Something went horribly wrong and we ran out of page table */
- if (WARN_ON(!pte || (lvl == ARM_LPAE_MAX_LEVELS)))
+ if (WARN_ON(!pte))
return 0;
/* If the size matches this level, we're in the right place */
@@ -499,12 +501,13 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
if (!iopte_leaf(pte, lvl)) {
/* Also flush any partial walks */
- tlb->tlb_add_flush(iova, size, false, cookie);
+ tlb->tlb_add_flush(iova, size, ARM_LPAE_GRANULE(data),
+ false, cookie);
tlb->tlb_sync(cookie);
ptep = iopte_deref(pte, data);
__arm_lpae_free_pgtable(data, lvl + 1, ptep);
} else {
- tlb->tlb_add_flush(iova, size, true, cookie);
+ tlb->tlb_add_flush(iova, size, size, true, cookie);
}
return size;
@@ -570,7 +573,7 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
return 0;
found_translation:
- iova &= ((1 << data->pg_shift) - 1);
+ iova &= (ARM_LPAE_GRANULE(data) - 1);
return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova;
}
@@ -668,7 +671,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
(ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
(ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
- switch (1 << data->pg_shift) {
+ switch (ARM_LPAE_GRANULE(data)) {
case SZ_4K:
reg |= ARM_LPAE_TCR_TG0_4K;
break;
@@ -769,7 +772,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
sl = ARM_LPAE_START_LVL(data);
- switch (1 << data->pg_shift) {
+ switch (ARM_LPAE_GRANULE(data)) {
case SZ_4K:
reg |= ARM_LPAE_TCR_TG0_4K;
sl++; /* SL0 format is different for 4K granule size */
@@ -889,8 +892,8 @@ static void dummy_tlb_flush_all(void *cookie)
WARN_ON(cookie != cfg_cookie);
}
-static void dummy_tlb_add_flush(unsigned long iova, size_t size, bool leaf,
- void *cookie)
+static void dummy_tlb_add_flush(unsigned long iova, size_t size,
+ size_t granule, bool leaf, void *cookie)
{
WARN_ON(cookie != cfg_cookie);
WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h
index ac9e2341a633..36673c83de58 100644
--- a/drivers/iommu/io-pgtable.h
+++ b/drivers/iommu/io-pgtable.h
@@ -26,8 +26,8 @@ enum io_pgtable_fmt {
*/
struct iommu_gather_ops {
void (*tlb_flush_all)(void *cookie);
- void (*tlb_add_flush)(unsigned long iova, size_t size, bool leaf,
- void *cookie);
+ void (*tlb_add_flush)(unsigned long iova, size_t size, size_t granule,
+ bool leaf, void *cookie);
void (*tlb_sync)(void *cookie);
};
@@ -131,6 +131,8 @@ struct io_pgtable {
struct io_pgtable_ops ops;
};
+#define io_pgtable_ops_to_pgtable(x) container_of((x), struct io_pgtable, ops)
+
/**
* struct io_pgtable_init_fns - Alloc/free a set of page tables for a
* particular format.
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index abae363c7b9b..0e3b0092ec92 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1430,7 +1430,7 @@ size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap);
for_each_sg(sg, s, nents, i) {
- phys_addr_t phys = sg_phys(s);
+ phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset;
/*
* We are mapping on IOMMU page boundaries, so offset within
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 8cf605fa9946..2fdbac67a77f 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -277,8 +277,8 @@ static void ipmmu_tlb_flush_all(void *cookie)
ipmmu_tlb_invalidate(domain);
}
-static void ipmmu_tlb_add_flush(unsigned long iova, size_t size, bool leaf,
- void *cookie)
+static void ipmmu_tlb_add_flush(unsigned long iova, size_t size,
+ size_t granule, bool leaf, void *cookie)
{
/* The hardware doesn't support selective TLB flush. */
}
@@ -295,7 +295,7 @@ static struct iommu_gather_ops ipmmu_gather_ops = {
static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
{
- phys_addr_t ttbr;
+ u64 ttbr;
/*
* Allocate the page table operations.
diff --git a/drivers/iommu/msm_iommu_dev.c b/drivers/iommu/msm_iommu_dev.c
index b6d01f97e537..4b09e815accf 100644
--- a/drivers/iommu/msm_iommu_dev.c
+++ b/drivers/iommu/msm_iommu_dev.c
@@ -359,30 +359,19 @@ static struct platform_driver msm_iommu_ctx_driver = {
.remove = msm_iommu_ctx_remove,
};
+static struct platform_driver * const drivers[] = {
+ &msm_iommu_driver,
+ &msm_iommu_ctx_driver,
+};
+
static int __init msm_iommu_driver_init(void)
{
- int ret;
- ret = platform_driver_register(&msm_iommu_driver);
- if (ret != 0) {
- pr_err("Failed to register IOMMU driver\n");
- goto error;
- }
-
- ret = platform_driver_register(&msm_iommu_ctx_driver);
- if (ret != 0) {
- platform_driver_unregister(&msm_iommu_driver);
- pr_err("Failed to register IOMMU context driver\n");
- goto error;
- }
-
-error:
- return ret;
+ return platform_register_drivers(drivers, ARRAY_SIZE(drivers));
}
static void __exit msm_iommu_driver_exit(void)
{
- platform_driver_unregister(&msm_iommu_ctx_driver);
- platform_driver_unregister(&msm_iommu_driver);
+ platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
}
subsys_initcall(msm_iommu_driver_init);
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 471ee36b9c6e..a04d491cf431 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -49,7 +49,7 @@ static bool s390_iommu_capable(enum iommu_cap cap)
}
}
-struct iommu_domain *s390_domain_alloc(unsigned domain_type)
+static struct iommu_domain *s390_domain_alloc(unsigned domain_type)
{
struct s390_domain *s390_domain;
@@ -73,7 +73,7 @@ struct iommu_domain *s390_domain_alloc(unsigned domain_type)
return &s390_domain->domain;
}
-void s390_domain_free(struct iommu_domain *domain)
+static void s390_domain_free(struct iommu_domain *domain)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-01 02:25:26 +0000