hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'core' into arm/tegra

This commit is contained in:
Joerg Roedel 2017-08-17 16:31:27 +02:00
parent ef954844c7 13cf017446
commit fa94cf84af
14 changed files with 429 additions and 499 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

229
drivers/iommu/amd_iommu.c
View File

@ -137,20 +137,7 @@ struct kmem_cache *amd_iommu_irq_cache;
static void update_domain(struct protection_domain *domain);
static int protection_domain_init(struct protection_domain *domain);
static void detach_device(struct device *dev);
#define FLUSH_QUEUE_SIZE 256
struct flush_queue_entry {
unsigned long iova_pfn;
unsigned long pages;
u64 counter; /* Flush counter when this entry was added to the queue */
};
struct flush_queue {
struct flush_queue_entry *entries;
unsigned head, tail;
spinlock_t lock;
};
static void iova_domain_flush_tlb(struct iova_domain *iovad);
/*
* Data container for a dma_ops specific protection domain
@ -161,36 +148,6 @@ struct dma_ops_domain {
/* IOVA RB-Tree */
struct iova_domain iovad;
struct flush_queue __percpu *flush_queue;
/*
* We need two counter here to be race-free wrt. IOTLB flushing and
* adding entries to the flush queue.
*
* The flush_start_cnt is incremented _before_ the IOTLB flush starts.
* New entries added to the flush ring-buffer get their 'counter' value
* from here. This way we can make sure that entries added to the queue
* (or other per-cpu queues of the same domain) while the TLB is about
* to be flushed are not considered to be flushed already.
*/
atomic64_t flush_start_cnt;
/*
* The flush_finish_cnt is incremented when an IOTLB flush is complete.
* This value is always smaller than flush_start_cnt. The queue_add
* function frees all IOVAs that have a counter value smaller than
* flush_finish_cnt. This makes sure that we only free IOVAs that are
* flushed out of the IOTLB of the domain.
*/
atomic64_t flush_finish_cnt;
/*
* Timer to make sure we don't keep IOVAs around unflushed
* for too long
*/
struct timer_list flush_timer;
atomic_t flush_timer_on;
};
static struct iova_domain reserved_iova_ranges;
@ -1788,178 +1745,19 @@ static void free_gcr3_table(struct protection_domain *domain)
free_page((unsigned long)domain->gcr3_tbl);
}
static void dma_ops_domain_free_flush_queue(struct dma_ops_domain *dom)
{
int cpu;
for_each_possible_cpu(cpu) {
struct flush_queue *queue;
queue = per_cpu_ptr(dom->flush_queue, cpu);
kfree(queue->entries);
}
free_percpu(dom->flush_queue);
dom->flush_queue = NULL;
}
static int dma_ops_domain_alloc_flush_queue(struct dma_ops_domain *dom)
{
int cpu;
atomic64_set(&dom->flush_start_cnt, 0);
atomic64_set(&dom->flush_finish_cnt, 0);
dom->flush_queue = alloc_percpu(struct flush_queue);
if (!dom->flush_queue)
return -ENOMEM;
/* First make sure everything is cleared */
for_each_possible_cpu(cpu) {
struct flush_queue *queue;
queue = per_cpu_ptr(dom->flush_queue, cpu);
queue->head = 0;
queue->tail = 0;
queue->entries = NULL;
}
/* Now start doing the allocation */
for_each_possible_cpu(cpu) {
struct flush_queue *queue;
queue = per_cpu_ptr(dom->flush_queue, cpu);
queue->entries = kzalloc(FLUSH_QUEUE_SIZE * sizeof(*queue->entries),
GFP_KERNEL);
if (!queue->entries) {
dma_ops_domain_free_flush_queue(dom);
return -ENOMEM;
}
spin_lock_init(&queue->lock);
}
return 0;
}
static void dma_ops_domain_flush_tlb(struct dma_ops_domain *dom)
{
atomic64_inc(&dom->flush_start_cnt);
domain_flush_tlb(&dom->domain);
domain_flush_complete(&dom->domain);
atomic64_inc(&dom->flush_finish_cnt);
}
static inline bool queue_ring_full(struct flush_queue *queue)
static void iova_domain_flush_tlb(struct iova_domain *iovad)
{
assert_spin_locked(&queue->lock);
struct dma_ops_domain *dom;
return (((queue->tail + 1) % FLUSH_QUEUE_SIZE) == queue->head);
}
#define queue_ring_for_each(i, q) \
for (i = (q)->head; i != (q)->tail; i = (i + 1) % FLUSH_QUEUE_SIZE)
static inline unsigned queue_ring_add(struct flush_queue *queue)
{
unsigned idx = queue->tail;
assert_spin_locked(&queue->lock);
queue->tail = (idx + 1) % FLUSH_QUEUE_SIZE;
return idx;
}
static inline void queue_ring_remove_head(struct flush_queue *queue)
{
assert_spin_locked(&queue->lock);
queue->head = (queue->head + 1) % FLUSH_QUEUE_SIZE;
}
static void queue_ring_free_flushed(struct dma_ops_domain *dom,
struct flush_queue *queue)
{
u64 counter = atomic64_read(&dom->flush_finish_cnt);
int idx;
queue_ring_for_each(idx, queue) {
/*
* This assumes that counter values in the ring-buffer are
* monotonously rising.
*/
if (queue->entries[idx].counter >= counter)
break;
free_iova_fast(&dom->iovad,
queue->entries[idx].iova_pfn,
queue->entries[idx].pages);
queue_ring_remove_head(queue);
}
}
static void queue_add(struct dma_ops_domain *dom,
unsigned long address, unsigned long pages)
{
struct flush_queue *queue;
unsigned long flags;
int idx;
pages = __roundup_pow_of_two(pages);
address >>= PAGE_SHIFT;
queue = get_cpu_ptr(dom->flush_queue);
spin_lock_irqsave(&queue->lock, flags);
/*
* First remove the enries from the ring-buffer that are already
* flushed to make the below queue_ring_full() check less likely
*/
queue_ring_free_flushed(dom, queue);
/*
* When ring-queue is full, flush the entries from the IOTLB so
* that we can free all entries with queue_ring_free_flushed()
* below.
*/
if (queue_ring_full(queue)) {
dma_ops_domain_flush_tlb(dom);
queue_ring_free_flushed(dom, queue);
}
idx = queue_ring_add(queue);
queue->entries[idx].iova_pfn = address;
queue->entries[idx].pages = pages;
queue->entries[idx].counter = atomic64_read(&dom->flush_start_cnt);
spin_unlock_irqrestore(&queue->lock, flags);
if (atomic_cmpxchg(&dom->flush_timer_on, 0, 1) == 0)
mod_timer(&dom->flush_timer, jiffies + msecs_to_jiffies(10));
put_cpu_ptr(dom->flush_queue);
}
static void queue_flush_timeout(unsigned long data)
{
struct dma_ops_domain *dom = (struct dma_ops_domain *)data;
int cpu;
atomic_set(&dom->flush_timer_on, 0);
dom = container_of(iovad, struct dma_ops_domain, iovad);
dma_ops_domain_flush_tlb(dom);
for_each_possible_cpu(cpu) {
struct flush_queue *queue;
unsigned long flags;
queue = per_cpu_ptr(dom->flush_queue, cpu);
spin_lock_irqsave(&queue->lock, flags);
queue_ring_free_flushed(dom, queue);
spin_unlock_irqrestore(&queue->lock, flags);
}
}
/*
@ -1973,11 +1771,6 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
del_domain_from_list(&dom->domain);
if (timer_pending(&dom->flush_timer))
del_timer(&dom->flush_timer);
dma_ops_domain_free_flush_queue(dom);
put_iova_domain(&dom->iovad);
free_pagetable(&dom->domain);
@ -2013,16 +1806,11 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
init_iova_domain(&dma_dom->iovad, PAGE_SIZE,
IOVA_START_PFN, DMA_32BIT_PFN);
/* Initialize reserved ranges */
copy_reserved_iova(&reserved_iova_ranges, &dma_dom->iovad);
if (dma_ops_domain_alloc_flush_queue(dma_dom))
if (init_iova_flush_queue(&dma_dom->iovad, iova_domain_flush_tlb, NULL))
goto free_dma_dom;
setup_timer(&dma_dom->flush_timer, queue_flush_timeout,
(unsigned long)dma_dom);
atomic_set(&dma_dom->flush_timer_on, 0);
/* Initialize reserved ranges */
copy_reserved_iova(&reserved_iova_ranges, &dma_dom->iovad);
add_domain_to_list(&dma_dom->domain);
@ -2619,7 +2407,8 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
domain_flush_tlb(&dma_dom->domain);
domain_flush_complete(&dma_dom->domain);
} else {
queue_add(dma_dom, dma_addr, pages);
pages = __roundup_pow_of_two(pages);
queue_iova(&dma_dom->iovad, dma_addr >> PAGE_SHIFT, pages, 0);
}
}

2
drivers/iommu/dmar.c
View File

@ -1343,7 +1343,7 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
if (mask) {
BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
addr |= (1 << (VTD_PAGE_SHIFT + mask - 1)) - 1;
addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
} else
desc.high = QI_DEV_IOTLB_ADDR(addr);

20
drivers/iommu/fsl_pamu.c
View File

@ -530,8 +530,8 @@ u32 get_stash_id(u32 stash_dest_hint, u32 vcpu)
if (node) {
prop = of_get_property(node, "cache-stash-id", NULL);
if (!prop) {
pr_debug("missing cache-stash-id at %s\n",
node->full_name);
pr_debug("missing cache-stash-id at %pOF\n",
node);
of_node_put(node);
return ~(u32)0;
}
@ -557,8 +557,8 @@ found_cpu_node:
if (stash_dest_hint == cache_level) {
prop = of_get_property(node, "cache-stash-id", NULL);
if (!prop) {
pr_debug("missing cache-stash-id at %s\n",
node->full_name);
pr_debug("missing cache-stash-id at %pOF\n",
node);
of_node_put(node);
return ~(u32)0;
}
@ -568,8 +568,7 @@ found_cpu_node:
prop = of_get_property(node, "next-level-cache", NULL);
if (!prop) {
pr_debug("can't find next-level-cache at %s\n",
node->full_name);
pr_debug("can't find next-level-cache at %pOF\n", node);
of_node_put(node);
return ~(u32)0; /* can't traverse any further */
}
@ -1063,8 +1062,7 @@ static int fsl_pamu_probe(struct platform_device *pdev)
guts_node = of_find_matching_node(NULL, guts_device_ids);
if (!guts_node) {
dev_err(dev, "could not find GUTS node %s\n",
dev->of_node->full_name);
dev_err(dev, "could not find GUTS node %pOF\n", dev->of_node);
ret = -ENODEV;
goto error;
}
@ -1246,8 +1244,7 @@ static __init int fsl_pamu_init(void)
pdev = platform_device_alloc("fsl-of-pamu", 0);
if (!pdev) {
pr_err("could not allocate device %s\n",
np->full_name);
pr_err("could not allocate device %pOF\n", np);
ret = -ENOMEM;
goto error_device_alloc;
}
@ -1259,8 +1256,7 @@ static __init int fsl_pamu_init(void)
ret = platform_device_add(pdev);
if (ret) {
pr_err("could not add device %s (err=%i)\n",
np->full_name, ret);
pr_err("could not add device %pOF (err=%i)\n", np, ret);
goto error_device_add;
}

10
drivers/iommu/fsl_pamu_domain.c
View File

@ -619,8 +619,8 @@ static int handle_attach_device(struct fsl_dma_domain *dma_domain,
for (i = 0; i < num; i++) {
/* Ensure that LIODN value is valid */
if (liodn[i] >= PAACE_NUMBER_ENTRIES) {
pr_debug("Invalid liodn %d, attach device failed for %s\n",
liodn[i], dev->of_node->full_name);
pr_debug("Invalid liodn %d, attach device failed for %pOF\n",
liodn[i], dev->of_node);
ret = -EINVAL;
break;
}
@ -684,8 +684,7 @@ static int fsl_pamu_attach_device(struct iommu_domain *domain,
liodn_cnt = len / sizeof(u32);
ret = handle_attach_device(dma_domain, dev, liodn, liodn_cnt);
} else {
pr_debug("missing fsl,liodn property at %s\n",
dev->of_node->full_name);
pr_debug("missing fsl,liodn property at %pOF\n", dev->of_node);
ret = -EINVAL;
}
@ -720,8 +719,7 @@ static void fsl_pamu_detach_device(struct iommu_domain *domain,
if (prop)
detach_device(dev, dma_domain);
else
pr_debug("missing fsl,liodn property at %s\n",
dev->of_node->full_name);
pr_debug("missing fsl,liodn property at %pOF\n", dev->of_node);
}
static int configure_domain_geometry(struct iommu_domain *domain, void *data)

197
drivers/iommu/intel-iommu.c
View File

@ -458,31 +458,6 @@ static LIST_HEAD(dmar_rmrr_units);
#define for_each_rmrr_units(rmrr) \
list_for_each_entry(rmrr, &dmar_rmrr_units, list)
static void flush_unmaps_timeout(unsigned long data);
struct deferred_flush_entry {
unsigned long iova_pfn;
unsigned long nrpages;
struct dmar_domain *domain;
struct page *freelist;
};
#define HIGH_WATER_MARK 250
struct deferred_flush_table {
int next;
struct deferred_flush_entry entries[HIGH_WATER_MARK];
};
struct deferred_flush_data {
spinlock_t lock;
int timer_on;
struct timer_list timer;
long size;
struct deferred_flush_table *tables;
};
static DEFINE_PER_CPU(struct deferred_flush_data, deferred_flush);
/* bitmap for indexing intel_iommus */
static int g_num_of_iommus;
@ -1309,6 +1284,13 @@ static void dma_free_pagelist(struct page *freelist)
}
}
static void iova_entry_free(unsigned long data)
{
struct page *freelist = (struct page *)data;
dma_free_pagelist(freelist);
}
/* iommu handling */
static int iommu_alloc_root_entry(struct intel_iommu *iommu)
{
@ -1622,6 +1604,25 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
addr, mask);
}
static void iommu_flush_iova(struct iova_domain *iovad)
{
struct dmar_domain *domain;
int idx;
domain = container_of(iovad, struct dmar_domain, iovad);
for_each_domain_iommu(idx, domain) {
struct intel_iommu *iommu = g_iommus[idx];
u16 did = domain->iommu_did[iommu->seq_id];
iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
if (!cap_caching_mode(iommu->cap))
iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
0, MAX_AGAW_PFN_WIDTH);
}
}
static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
{
u32 pmen;
@ -1932,9 +1933,16 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu,
{
int adjust_width, agaw;
unsigned long sagaw;
int err;
init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
DMA_32BIT_PFN);
err = init_iova_flush_queue(&domain->iovad,
iommu_flush_iova, iova_entry_free);
if (err)
return err;
domain_reserve_special_ranges(domain);
/* calculate AGAW */
@ -1986,14 +1994,6 @@ static void domain_exit(struct dmar_domain *domain)
if (!domain)
return;
/* Flush any lazy unmaps that may reference this domain */
if (!intel_iommu_strict) {
int cpu;
for_each_possible_cpu(cpu)
flush_unmaps_timeout(cpu);
}
/* Remove associated devices and clear attached or cached domains */
rcu_read_lock();
domain_remove_dev_info(domain);
@ -3206,7 +3206,7 @@ static int __init init_dmars(void)
bool copied_tables = false;
struct device *dev;
struct intel_iommu *iommu;
int i, ret, cpu;
int i, ret;
/*
* for each drhd
@ -3239,22 +3239,6 @@ static int __init init_dmars(void)
goto error;
}
for_each_possible_cpu(cpu) {
struct deferred_flush_data *dfd = per_cpu_ptr(&deferred_flush,
cpu);
dfd->tables = kzalloc(g_num_of_iommus *
sizeof(struct deferred_flush_table),
GFP_KERNEL);
if (!dfd->tables) {
ret = -ENOMEM;
goto free_g_iommus;
}
spin_lock_init(&dfd->lock);
setup_timer(&dfd->timer, flush_unmaps_timeout, cpu);
}
for_each_active_iommu(iommu, drhd) {
g_iommus[iommu->seq_id] = iommu;
@ -3437,10 +3421,9 @@ free_iommu:
disable_dmar_iommu(iommu);
free_dmar_iommu(iommu);
}
free_g_iommus:
for_each_possible_cpu(cpu)
kfree(per_cpu_ptr(&deferred_flush, cpu)->tables);
kfree(g_iommus);
error:
return ret;
}
@ -3645,110 +3628,6 @@ static dma_addr_t intel_map_page(struct device *dev, struct page *page,
dir, *dev->dma_mask);
}
static void flush_unmaps(struct deferred_flush_data *flush_data)
{
int i, j;
flush_data->timer_on = 0;
/* just flush them all */
for (i = 0; i < g_num_of_iommus; i++) {
struct intel_iommu *iommu = g_iommus[i];
struct deferred_flush_table *flush_table =
&flush_data->tables[i];
if (!iommu)
continue;
if (!flush_table->next)
continue;
/* In caching mode, global flushes turn emulation expensive */
if (!cap_caching_mode(iommu->cap))
iommu->flush.flush_iotlb(iommu, 0, 0, 0,
DMA_TLB_GLOBAL_FLUSH);
for (j = 0; j < flush_table->next; j++) {
unsigned long mask;
struct deferred_flush_entry *entry =
&flush_table->entries[j];
unsigned long iova_pfn = entry->iova_pfn;
unsigned long nrpages = entry->nrpages;
struct dmar_domain *domain = entry->domain;
struct page *freelist = entry->freelist;
/* On real hardware multiple invalidations are expensive */
if (cap_caching_mode(iommu->cap))
iommu_flush_iotlb_psi(iommu, domain,
mm_to_dma_pfn(iova_pfn),
nrpages, !freelist, 0);
else {
mask = ilog2(nrpages);
iommu_flush_dev_iotlb(domain,
(uint64_t)iova_pfn << PAGE_SHIFT, mask);
}
free_iova_fast(&domain->iovad, iova_pfn, nrpages);
if (freelist)
dma_free_pagelist(freelist);
}
flush_table->next = 0;
}
flush_data->size = 0;
}
static void flush_unmaps_timeout(unsigned long cpuid)
{
struct deferred_flush_data *flush_data = per_cpu_ptr(&deferred_flush, cpuid);
unsigned long flags;
spin_lock_irqsave(&flush_data->lock, flags);
flush_unmaps(flush_data);
spin_unlock_irqrestore(&flush_data->lock, flags);
}
static void add_unmap(struct dmar_domain *dom, unsigned long iova_pfn,
unsigned long nrpages, struct page *freelist)
{
unsigned long flags;
int entry_id, iommu_id;
struct intel_iommu *iommu;
struct deferred_flush_entry *entry;
struct deferred_flush_data *flush_data;
flush_data = raw_cpu_ptr(&deferred_flush);
/* Flush all CPUs' entries to avoid deferring too much. If
* this becomes a bottleneck, can just flush us, and rely on
* flush timer for the rest.
*/
if (flush_data->size == HIGH_WATER_MARK) {
int cpu;
for_each_online_cpu(cpu)
flush_unmaps_timeout(cpu);
}
spin_lock_irqsave(&flush_data->lock, flags);
iommu = domain_get_iommu(dom);
iommu_id = iommu->seq_id;
entry_id = flush_data->tables[iommu_id].next;
++(flush_data->tables[iommu_id].next);
entry = &flush_data->tables[iommu_id].entries[entry_id];
entry->domain = dom;
entry->iova_pfn = iova_pfn;
entry->nrpages = nrpages;
entry->freelist = freelist;
if (!flush_data->timer_on) {
mod_timer(&flush_data->timer, jiffies + msecs_to_jiffies(10));
flush_data->timer_on = 1;
}
flush_data->size++;
spin_unlock_irqrestore(&flush_data->lock, flags);
}
static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
{
struct dmar_domain *domain;
@ -3784,7 +3663,8 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(nrpages));
dma_free_pagelist(freelist);
} else {
add_unmap(domain, iova_pfn, nrpages, freelist);
queue_iova(&domain->iovad, iova_pfn, nrpages,
(unsigned long)freelist);
/*
* queue up the release of the unmap to save the 1/6th of the
* cpu used up by the iotlb flush operation...
@ -4721,7 +4601,6 @@ static void free_all_cpu_cached_iovas(unsigned int cpu)
static int intel_iommu_cpu_dead(unsigned int cpu)
{
free_all_cpu_cached_iovas(cpu);
flush_unmaps_timeout(cpu);
return 0;
}

19
drivers/iommu/iommu.c
View File

@ -1005,11 +1005,10 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
if (group)
return group;
group = ERR_PTR(-EINVAL);
if (ops && ops->device_group)
group = ops->device_group(dev);
if (!ops)
return ERR_PTR(-EINVAL);
group = ops->device_group(dev);
if (WARN_ON_ONCE(group == NULL))
return ERR_PTR(-EINVAL);
@ -1298,12 +1297,8 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
int ret;
group = iommu_group_get(dev);
/* FIXME: Remove this when groups a mandatory for iommu drivers */
if (group == NULL)
return __iommu_attach_device(domain, dev);
/*
* We have a group - lock it to make sure the device-count doesn't
* Lock the group to make sure the device-count doesn't
* change while we are attaching
*/
mutex_lock(&group->mutex);
@ -1336,9 +1331,6 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
struct iommu_group *group;
group = iommu_group_get(dev);
/* FIXME: Remove this when groups a mandatory for iommu drivers */
if (group == NULL)
return __iommu_detach_device(domain, dev);
mutex_lock(&group->mutex);
if (iommu_group_device_count(group) != 1) {
@ -1360,9 +1352,6 @@ struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
struct iommu_group *group;
group = iommu_group_get(dev);
/* FIXME: Remove this when groups a mandatory for iommu drivers */
if (group == NULL)
return NULL;
domain = group->domain;

183
drivers/iommu/iova.c
View File

@ -32,6 +32,8 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
unsigned long limit_pfn);
static void init_iova_rcaches(struct iova_domain *iovad);
static void free_iova_rcaches(struct iova_domain *iovad);
static void fq_destroy_all_entries(struct iova_domain *iovad);
static void fq_flush_timeout(unsigned long data);
void
init_iova_domain(struct iova_domain *iovad, unsigned long granule,
@ -50,10 +52,61 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
iovad->granule = granule;
iovad->start_pfn = start_pfn;
iovad->dma_32bit_pfn = pfn_32bit + 1;
iovad->flush_cb = NULL;
iovad->fq = NULL;
init_iova_rcaches(iovad);
}
EXPORT_SYMBOL_GPL(init_iova_domain);
static void free_iova_flush_queue(struct iova_domain *iovad)
{
if (!iovad->fq)
return;
if (timer_pending(&iovad->fq_timer))
del_timer(&iovad->fq_timer);
fq_destroy_all_entries(iovad);
free_percpu(iovad->fq);
iovad->fq = NULL;
iovad->flush_cb = NULL;
iovad->entry_dtor = NULL;
}
int init_iova_flush_queue(struct iova_domain *iovad,
iova_flush_cb flush_cb, iova_entry_dtor entry_dtor)
{
int cpu;
atomic64_set(&iovad->fq_flush_start_cnt, 0);
atomic64_set(&iovad->fq_flush_finish_cnt, 0);
iovad->fq = alloc_percpu(struct iova_fq);
if (!iovad->fq)
return -ENOMEM;
iovad->flush_cb = flush_cb;
iovad->entry_dtor = entry_dtor;
for_each_possible_cpu(cpu) {
struct iova_fq *fq;
fq = per_cpu_ptr(iovad->fq, cpu);
fq->head = 0;
fq->tail = 0;
spin_lock_init(&fq->lock);
}
setup_timer(&iovad->fq_timer, fq_flush_timeout, (unsigned long)iovad);
atomic_set(&iovad->fq_timer_on, 0);
return 0;
}
EXPORT_SYMBOL_GPL(init_iova_flush_queue);
static struct rb_node *
__get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
{
@ -423,6 +476,135 @@ free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
}
EXPORT_SYMBOL_GPL(free_iova_fast);
#define fq_ring_for_each(i, fq) \
for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE)
static inline bool fq_full(struct iova_fq *fq)
{
assert_spin_locked(&fq->lock);
return (((fq->tail + 1) % IOVA_FQ_SIZE) == fq->head);
}
static inline unsigned fq_ring_add(struct iova_fq *fq)
{
unsigned idx = fq->tail;
assert_spin_locked(&fq->lock);
fq->tail = (idx + 1) % IOVA_FQ_SIZE;
return idx;
}
static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq)
{
u64 counter = atomic64_read(&iovad->fq_flush_finish_cnt);
unsigned idx;
assert_spin_locked(&fq->lock);
fq_ring_for_each(idx, fq) {
if (fq->entries[idx].counter >= counter)
break;
if (iovad->entry_dtor)
iovad->entry_dtor(fq->entries[idx].data);
free_iova_fast(iovad,
fq->entries[idx].iova_pfn,
fq->entries[idx].pages);
fq->head = (fq->head + 1) % IOVA_FQ_SIZE;
}
}
static void iova_domain_flush(struct iova_domain *iovad)
{
atomic64_inc(&iovad->fq_flush_start_cnt);
iovad->flush_cb(iovad);
atomic64_inc(&iovad->fq_flush_finish_cnt);
}
static void fq_destroy_all_entries(struct iova_domain *iovad)
{
int cpu;
/*
* This code runs when the iova_domain is being detroyed, so don't
* bother to free iovas, just call the entry_dtor on all remaining
* entries.
*/
if (!iovad->entry_dtor)
return;
for_each_possible_cpu(cpu) {
struct iova_fq *fq = per_cpu_ptr(iovad->fq, cpu);
int idx;
fq_ring_for_each(idx, fq)
iovad->entry_dtor(fq->entries[idx].data);
}
}
static void fq_flush_timeout(unsigned long data)
{
struct iova_domain *iovad = (struct iova_domain *)data;
int cpu;
atomic_set(&iovad->fq_timer_on, 0);
iova_domain_flush(iovad);
for_each_possible_cpu(cpu) {
unsigned long flags;
struct iova_fq *fq;
fq = per_cpu_ptr(iovad->fq, cpu);
spin_lock_irqsave(&fq->lock, flags);
fq_ring_free(iovad, fq);
spin_unlock_irqrestore(&fq->lock, flags);
}
}
void queue_iova(struct iova_domain *iovad,
unsigned long pfn, unsigned long pages,
unsigned long data)
{
struct iova_fq *fq = get_cpu_ptr(iovad->fq);
unsigned long flags;
unsigned idx;
spin_lock_irqsave(&fq->lock, flags);
/*
* First remove all entries from the flush queue that have already been
* flushed out on another CPU. This makes the fq_full() check below less
* likely to be true.
*/
fq_ring_free(iovad, fq);
if (fq_full(fq)) {
iova_domain_flush(iovad);
fq_ring_free(iovad, fq);
}
idx = fq_ring_add(fq);
fq->entries[idx].iova_pfn = pfn;
fq->entries[idx].pages = pages;
fq->entries[idx].data = data;
fq->entries[idx].counter = atomic64_read(&iovad->fq_flush_start_cnt);
spin_unlock_irqrestore(&fq->lock, flags);
if (atomic_cmpxchg(&iovad->fq_timer_on, 0, 1) == 0)
mod_timer(&iovad->fq_timer,
jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
put_cpu_ptr(iovad->fq);
}
EXPORT_SYMBOL_GPL(queue_iova);
/**
* put_iova_domain - destroys the iova doamin
* @iovad: - iova domain in question.
@ -433,6 +615,7 @@ void put_iova_domain(struct iova_domain *iovad)
struct rb_node *node;
unsigned long flags;
free_iova_flush_queue(iovad);
free_iova_rcaches(iovad);
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
node = rb_first(&iovad->rbroot);

15
drivers/iommu/msm_iommu.c
View File

@ -393,6 +393,7 @@ static struct msm_iommu_dev *find_iommu_for_dev(struct device *dev)
static int msm_iommu_add_device(struct device *dev)
{
struct msm_iommu_dev *iommu;
struct iommu_group *group;
unsigned long flags;
int ret = 0;
@ -406,7 +407,16 @@ static int msm_iommu_add_device(struct device *dev)
spin_unlock_irqrestore(&msm_iommu_lock, flags);
return ret;
if (ret)
return ret;
group = iommu_group_get_for_dev(dev);
if (IS_ERR(group))
return PTR_ERR(group);
iommu_group_put(group);
return 0;
}
static void msm_iommu_remove_device(struct device *dev)
@ -421,6 +431,8 @@ static void msm_iommu_remove_device(struct device *dev)
iommu_device_unlink(&iommu->iommu, dev);
spin_unlock_irqrestore(&msm_iommu_lock, flags);
iommu_group_remove_device(dev);
}
static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
@ -700,6 +712,7 @@ static struct iommu_ops msm_iommu_ops = {
.iova_to_phys = msm_iommu_iova_to_phys,
.add_device = msm_iommu_add_device,
.remove_device = msm_iommu_remove_device,
.device_group = generic_device_group,
.pgsize_bitmap = MSM_IOMMU_PGSIZES,
.of_xlate = qcom_iommu_of_xlate,
};

144
drivers/iommu/of_iommu.c
View File

@ -25,6 +25,8 @@
#include <linux/of_pci.h>
#include <linux/slab.h>
#define NO_IOMMU 1
static const struct of_device_id __iommu_of_table_sentinel
__used __section(__iommu_of_table_end);
@ -109,8 +111,8 @@ static bool of_iommu_driver_present(struct device_node *np)
return of_match_node(&__iommu_of_table, np);
}
static const struct iommu_ops
*of_iommu_xlate(struct device *dev, struct of_phandle_args *iommu_spec)
static int of_iommu_xlate(struct device *dev,
struct of_phandle_args *iommu_spec)
{
const struct iommu_ops *ops;
struct fwnode_handle *fwnode = &iommu_spec->np->fwnode;
@ -120,95 +122,53 @@ static const struct iommu_ops
if ((ops && !ops->of_xlate) ||
!of_device_is_available(iommu_spec->np) ||
(!ops && !of_iommu_driver_present(iommu_spec->np)))
return NULL;
return NO_IOMMU;
err = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
if (err)
return ERR_PTR(err);
return err;
/*
* The otherwise-empty fwspec handily serves to indicate the specific
* IOMMU device we're waiting for, which will be useful if we ever get
* a proper probe-ordering dependency mechanism in future.
*/
if (!ops)
return ERR_PTR(-EPROBE_DEFER);
return -EPROBE_DEFER;
err = ops->of_xlate(dev, iommu_spec);
if (err)
return ERR_PTR(err);
return ops;
return ops->of_xlate(dev, iommu_spec);
}
static int __get_pci_rid(struct pci_dev *pdev, u16 alias, void *data)
{
struct of_phandle_args *iommu_spec = data;
struct of_pci_iommu_alias_info {
struct device *dev;
struct device_node *np;
};
iommu_spec->args[0] = alias;
return iommu_spec->np == pdev->bus->dev.of_node;
}
static const struct iommu_ops
*of_pci_iommu_init(struct pci_dev *pdev, struct device_node *bridge_np)
static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
{
const struct iommu_ops *ops;
struct of_phandle_args iommu_spec;
struct of_pci_iommu_alias_info *info = data;
struct of_phandle_args iommu_spec = { .args_count = 1 };
int err;
/*
* Start by tracing the RID alias down the PCI topology as
* far as the host bridge whose OF node we have...
* (we're not even attempting to handle multi-alias devices yet)
*/
iommu_spec.args_count = 1;
iommu_spec.np = bridge_np;
pci_for_each_dma_alias(pdev, __get_pci_rid, &iommu_spec);
/*
* ...then find out what that becomes once it escapes the PCI
* bus into the system beyond, and which IOMMU it ends up at.
*/
iommu_spec.np = NULL;
err = of_pci_map_rid(bridge_np, iommu_spec.args[0], "iommu-map",
err = of_pci_map_rid(info->np, alias, "iommu-map",
"iommu-map-mask", &iommu_spec.np,
iommu_spec.args);
if (err)
return err == -ENODEV ? NULL : ERR_PTR(err);
ops = of_iommu_xlate(&pdev->dev, &iommu_spec);
return err == -ENODEV ? NO_IOMMU : err;
err = of_iommu_xlate(info->dev, &iommu_spec);
of_node_put(iommu_spec.np);
return ops;
}
if (err)
return err;
static const struct iommu_ops
*of_platform_iommu_init(struct device *dev, struct device_node *np)
{
struct of_phandle_args iommu_spec;
const struct iommu_ops *ops = NULL;
int idx = 0;
/*
* We don't currently walk up the tree looking for a parent IOMMU.
* See the `Notes:' section of
* Documentation/devicetree/bindings/iommu/iommu.txt
*/
while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells",
idx, &iommu_spec)) {
ops = of_iommu_xlate(dev, &iommu_spec);
of_node_put(iommu_spec.np);
idx++;
if (IS_ERR_OR_NULL(ops))
break;
}
return ops;
return info->np == pdev->bus->dev.of_node;
}
const struct iommu_ops *of_iommu_configure(struct device *dev,
struct device_node *master_np)
{
const struct iommu_ops *ops;
const struct iommu_ops *ops = NULL;
struct iommu_fwspec *fwspec = dev->iommu_fwspec;
int err = NO_IOMMU;
if (!master_np)
return NULL;
@ -221,25 +181,54 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
iommu_fwspec_free(dev);
}
if (dev_is_pci(dev))
ops = of_pci_iommu_init(to_pci_dev(dev), master_np);
else
ops = of_platform_iommu_init(dev, master_np);
/*
* We don't currently walk up the tree looking for a parent IOMMU.
* See the `Notes:' section of
* Documentation/devicetree/bindings/iommu/iommu.txt
*/
if (dev_is_pci(dev)) {
struct of_pci_iommu_alias_info info = {
.dev = dev,
.np = master_np,
};
err = pci_for_each_dma_alias(to_pci_dev(dev),
of_pci_iommu_init, &info);
} else {
struct of_phandle_args iommu_spec;
int idx = 0;
while (!of_parse_phandle_with_args(master_np, "iommus",
"#iommu-cells",
idx, &iommu_spec)) {
err = of_iommu_xlate(dev, &iommu_spec);
of_node_put(iommu_spec.np);
idx++;
if (err)
break;
}
}
/*
* Two success conditions can be represented by non-negative err here:
* >0 : there is no IOMMU, or one was unavailable for non-fatal reasons
* 0 : we found an IOMMU, and dev->fwspec is initialised appropriately
* <0 : any actual error
*/
if (!err)
ops = dev->iommu_fwspec->ops;
/*
* If we have reason to believe the IOMMU driver missed the initial
* add_device callback for dev, replay it to get things in order.
*/
if (!IS_ERR_OR_NULL(ops) && ops->add_device &&
dev->bus && !dev->iommu_group) {
int err = ops->add_device(dev);
if (err)
ops = ERR_PTR(err);
}
if (ops && ops->add_device && dev->bus && !dev->iommu_group)
err = ops->add_device(dev);
/* Ignore all other errors apart from EPROBE_DEFER */
if (IS_ERR(ops) && (PTR_ERR(ops) != -EPROBE_DEFER)) {
dev_dbg(dev, "Adding to IOMMU failed: %ld\n", PTR_ERR(ops));
if (err == -EPROBE_DEFER) {
ops = ERR_PTR(err);
} else if (err < 0) {
dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
ops = NULL;
}
@ -255,8 +244,7 @@ static int __init of_iommu_init(void)
const of_iommu_init_fn init_fn = match->data;
if (init_fn && init_fn(np))
pr_err("Failed to initialise IOMMU %s\n",
of_node_full_name(np));
pr_err("Failed to initialise IOMMU %pOF\n", np);
}
return 0;

10
drivers/iommu/rockchip-iommu.c
View File

@ -1008,20 +1008,20 @@ static int rk_iommu_group_set_iommudata(struct iommu_group *group,
ret = of_parse_phandle_with_args(np, "iommus", "#iommu-cells", 0,
&args);
if (ret) {
dev_err(dev, "of_parse_phandle_with_args(%s) => %d\n",
np->full_name, ret);
dev_err(dev, "of_parse_phandle_with_args(%pOF) => %d\n",
np, ret);
return ret;
}
if (args.args_count != 0) {
dev_err(dev, "incorrect number of iommu params found for %s (found %d, expected 0)\n",
args.np->full_name, args.args_count);
dev_err(dev, "incorrect number of iommu params found for %pOF (found %d, expected 0)\n",
args.np, args.args_count);
return -EINVAL;
}
pd = of_find_device_by_node(args.np);
of_node_put(args.np);
if (!pd) {
dev_err(dev, "iommu %s not found\n", args.np->full_name);
dev_err(dev, "iommu %pOF not found\n", args.np);
return -EPROBE_DEFER;
}

19
drivers/iommu/tegra-gart.c
View File

@ -334,12 +334,31 @@ static bool gart_iommu_capable(enum iommu_cap cap)
return false;
}
static int gart_iommu_add_device(struct device *dev)
{
struct iommu_group *group = iommu_group_get_for_dev(dev);
if (IS_ERR(group))
return PTR_ERR(group);
iommu_group_put(group);
return 0;
}
static void gart_iommu_remove_device(struct device *dev)
{
iommu_group_remove_device(dev);
}
static const struct iommu_ops gart_iommu_ops = {
.capable = gart_iommu_capable,
.domain_alloc = gart_iommu_domain_alloc,
.domain_free = gart_iommu_domain_free,
.attach_dev = gart_iommu_attach_dev,
.detach_dev = gart_iommu_detach_dev,
.add_device = gart_iommu_add_device,
.remove_device = gart_iommu_remove_device,
.device_group = generic_device_group,
.map = gart_iommu_map,
.map_sg = default_iommu_map_sg,
.unmap = gart_iommu_unmap,

9
drivers/iommu/tegra-smmu.c
View File

@ -704,6 +704,7 @@ static struct tegra_smmu *tegra_smmu_find(struct device_node *np)
static int tegra_smmu_add_device(struct device *dev)
{
struct device_node *np = dev->of_node;
struct iommu_group *group;
struct of_phandle_args args;
unsigned int index = 0;
@ -725,12 +726,19 @@ static int tegra_smmu_add_device(struct device *dev)
index++;
}
group = iommu_group_get_for_dev(dev);
if (IS_ERR(group))
return PTR_ERR(group);
iommu_group_put(group);
return 0;
}
static void tegra_smmu_remove_device(struct device *dev)
{
dev->archdata.iommu = NULL;
iommu_group_remove_device(dev);
}
static const struct iommu_ops tegra_smmu_ops = {
@ -741,6 +749,7 @@ static const struct iommu_ops tegra_smmu_ops = {
.detach_dev = tegra_smmu_detach_dev,
.add_device = tegra_smmu_add_device,
.remove_device = tegra_smmu_remove_device,
.device_group = generic_device_group,
.map = tegra_smmu_map,
.unmap = tegra_smmu_unmap,
.map_sg = default_iommu_map_sg,

4
include/linux/iommu.h
View File

@ -425,13 +425,13 @@ static inline struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
}
static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
phys_addr_t paddr, int gfp_order, int prot)
phys_addr_t paddr, size_t size, int prot)
{
return -ENODEV;
}
static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
int gfp_order)
size_t size)
{
return -ENODEV;
}

67
include/linux/iova.h
View File

@ -14,6 +14,7 @@
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/rbtree.h>
#include <linux/atomic.h>
#include <linux/dma-mapping.h>
/* iova structure */
@ -36,6 +37,35 @@ struct iova_rcache {
struct iova_cpu_rcache __percpu *cpu_rcaches;
};
struct iova_domain;
/* Call-Back from IOVA code into IOMMU drivers */
typedef void (* iova_flush_cb)(struct iova_domain *domain);
/* Destructor for per-entry data */
typedef void (* iova_entry_dtor)(unsigned long data);
/* Number of entries per Flush Queue */
#define IOVA_FQ_SIZE 256
/* Timeout (in ms) after which entries are flushed from the Flush-Queue */
#define IOVA_FQ_TIMEOUT 10
/* Flush Queue entry for defered flushing */
struct iova_fq_entry {
unsigned long iova_pfn;
unsigned long pages;
unsigned long data;
u64 counter; /* Flush counter when this entrie was added */
};
/* Per-CPU Flush Queue structure */
struct iova_fq {
struct iova_fq_entry entries[IOVA_FQ_SIZE];
unsigned head, tail;
spinlock_t lock;
};
/* holds all the iova translations for a domain */
struct iova_domain {
spinlock_t iova_rbtree_lock; /* Lock to protect update of rbtree */
@ -45,6 +75,25 @@ struct iova_domain {
unsigned long start_pfn; /* Lower limit for this domain */
unsigned long dma_32bit_pfn;
struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */
iova_flush_cb flush_cb; /* Call-Back function to flush IOMMU
TLBs */
iova_entry_dtor entry_dtor; /* IOMMU driver specific destructor for
iova entry */
struct iova_fq __percpu *fq; /* Flush Queue */
atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that
have been started */
atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that
have been finished */
struct timer_list fq_timer; /* Timer to regularily empty the
flush-queues */
atomic_t fq_timer_on; /* 1 when timer is active, 0
when not */
};
static inline unsigned long iova_size(struct iova *iova)
@ -95,6 +144,9 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
bool size_aligned);
void free_iova_fast(struct iova_domain *iovad, unsigned long pfn,
unsigned long size);
void queue_iova(struct iova_domain *iovad,
unsigned long pfn, unsigned long pages,
unsigned long data);
unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
unsigned long limit_pfn);
struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
@ -102,6 +154,8 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
void init_iova_domain(struct iova_domain *iovad, unsigned long granule,
unsigned long start_pfn, unsigned long pfn_32bit);
int init_iova_flush_queue(struct iova_domain *iovad,
iova_flush_cb flush_cb, iova_entry_dtor entry_dtor);
struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
void put_iova_domain(struct iova_domain *iovad);
struct iova *split_and_remove_iova(struct iova_domain *iovad,
@ -148,6 +202,12 @@ static inline void free_iova_fast(struct iova_domain *iovad,
{
}
static inline void queue_iova(struct iova_domain *iovad,
unsigned long pfn, unsigned long pages,
unsigned long data)
{
}
static inline unsigned long alloc_iova_fast(struct iova_domain *iovad,
unsigned long size,
unsigned long limit_pfn)
@ -174,6 +234,13 @@ static inline void init_iova_domain(struct iova_domain *iovad,
{
}
static inline int init_iova_flush_queue(struct iova_domain *iovad,
iova_flush_cb flush_cb,
iova_entry_dtor entry_dtor)
{
return -ENODEV;
}
static inline struct iova *find_iova(struct iova_domain *iovad,
unsigned long pfn)
{