Merge branch 'for-joerg/arm-smmu/updates' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/smmu

This commit is contained in:
Joerg Roedel 2014-07-10 15:28:28 +02:00
Родитель cd3de83f14 2907320df3
Коммит a188cf8d5e
2 изменённых файлов: 240 добавлений и 259 удалений

Просмотреть файл

@ -42,12 +42,6 @@ conditions.
** System MMU optional properties:
- smmu-parent : When multiple SMMUs are chained together, this
property can be used to provide a phandle to the
parent SMMU (that is the next SMMU on the path going
from the mmu-masters towards memory) node for this
SMMU.
- calxeda,smmu-secure-config-access : Enable proper handling of buggy
implementations that always use secure access to
SMMU configuration registers. In this case non-secure

Просмотреть файл

@ -39,6 +39,7 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
@ -316,8 +317,8 @@
#define FSR_AFF (1 << 2)
#define FSR_TF (1 << 1)
#define FSR_IGN (FSR_AFF | FSR_ASF | FSR_TLBMCF | \
FSR_TLBLKF)
#define FSR_IGN (FSR_AFF | FSR_ASF | \
FSR_TLBMCF | FSR_TLBLKF)
#define FSR_FAULT (FSR_MULTI | FSR_SS | FSR_UUT | \
FSR_EF | FSR_PF | FSR_TF | FSR_IGN)
@ -329,27 +330,20 @@ struct arm_smmu_smr {
u16 id;
};
struct arm_smmu_master {
struct device_node *of_node;
/*
* The following is specific to the master's position in the
* SMMU chain.
*/
struct rb_node node;
struct arm_smmu_master_cfg {
int num_streamids;
u16 streamids[MAX_MASTER_STREAMIDS];
/*
* We only need to allocate these on the root SMMU, as we
* configure unmatched streams to bypass translation.
*/
struct arm_smmu_smr *smrs;
};
struct arm_smmu_master {
struct device_node *of_node;
struct rb_node node;
struct arm_smmu_master_cfg cfg;
};
struct arm_smmu_device {
struct device *dev;
struct device_node *parent_of_node;
void __iomem *base;
unsigned long size;
@ -387,7 +381,6 @@ struct arm_smmu_device {
};
struct arm_smmu_cfg {
struct arm_smmu_device *smmu;
u8 cbndx;
u8 irptndx;
u32 cbar;
@ -399,15 +392,8 @@ struct arm_smmu_cfg {
#define ARM_SMMU_CB_VMID(cfg) ((cfg)->cbndx + 1)
struct arm_smmu_domain {
/*
* A domain can span across multiple, chained SMMUs and requires
* all devices within the domain to follow the same translation
* path.
*/
struct arm_smmu_device *leaf_smmu;
struct arm_smmu_cfg root_cfg;
phys_addr_t output_mask;
struct arm_smmu_device *smmu;
struct arm_smmu_cfg cfg;
spinlock_t lock;
};
@ -419,7 +405,7 @@ struct arm_smmu_option_prop {
const char *prop;
};
static struct arm_smmu_option_prop arm_smmu_options [] = {
static struct arm_smmu_option_prop arm_smmu_options[] = {
{ ARM_SMMU_OPT_SECURE_CFG_ACCESS, "calxeda,smmu-secure-config-access" },
{ 0, NULL},
};
@ -427,6 +413,7 @@ static struct arm_smmu_option_prop arm_smmu_options [] = {
static void parse_driver_options(struct arm_smmu_device *smmu)
{
int i = 0;
do {
if (of_property_read_bool(smmu->dev->of_node,
arm_smmu_options[i].prop)) {
@ -437,6 +424,19 @@ static void parse_driver_options(struct arm_smmu_device *smmu)
} while (arm_smmu_options[++i].opt);
}
static struct device *dev_get_master_dev(struct device *dev)
{
if (dev_is_pci(dev)) {
struct pci_bus *bus = to_pci_dev(dev)->bus;
while (!pci_is_root_bus(bus))
bus = bus->parent;
return bus->bridge->parent;
}
return dev;
}
static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
struct device_node *dev_node)
{
@ -444,6 +444,7 @@ static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
while (node) {
struct arm_smmu_master *master;
master = container_of(node, struct arm_smmu_master, node);
if (dev_node < master->of_node)
@ -457,6 +458,18 @@ static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
return NULL;
}
static struct arm_smmu_master_cfg *
find_smmu_master_cfg(struct arm_smmu_device *smmu, struct device *dev)
{
struct arm_smmu_master *master;
if (dev_is_pci(dev))
return dev->archdata.iommu;
master = find_smmu_master(smmu, dev->of_node);
return master ? &master->cfg : NULL;
}
static int insert_smmu_master(struct arm_smmu_device *smmu,
struct arm_smmu_master *master)
{
@ -465,8 +478,8 @@ static int insert_smmu_master(struct arm_smmu_device *smmu,
new = &smmu->masters.rb_node;
parent = NULL;
while (*new) {
struct arm_smmu_master *this;
this = container_of(*new, struct arm_smmu_master, node);
struct arm_smmu_master *this
= container_of(*new, struct arm_smmu_master, node);
parent = *new;
if (master->of_node < this->of_node)
@ -509,32 +522,29 @@ static int register_smmu_master(struct arm_smmu_device *smmu,
return -ENOMEM;
master->of_node = masterspec->np;
master->num_streamids = masterspec->args_count;
master->cfg.num_streamids = masterspec->args_count;
for (i = 0; i < master->num_streamids; ++i)
master->streamids[i] = masterspec->args[i];
for (i = 0; i < master->cfg.num_streamids; ++i)
master->cfg.streamids[i] = masterspec->args[i];
return insert_smmu_master(smmu, master);
}
static struct arm_smmu_device *find_parent_smmu(struct arm_smmu_device *smmu)
static struct arm_smmu_device *find_smmu_for_device(struct device *dev)
{
struct arm_smmu_device *parent;
if (!smmu->parent_of_node)
return NULL;
struct arm_smmu_device *smmu;
struct arm_smmu_master *master = NULL;
struct device_node *dev_node = dev_get_master_dev(dev)->of_node;
spin_lock(&arm_smmu_devices_lock);
list_for_each_entry(parent, &arm_smmu_devices, list)
if (parent->dev->of_node == smmu->parent_of_node)
goto out_unlock;
parent = NULL;
dev_warn(smmu->dev,
"Failed to find SMMU parent despite parent in DT\n");
out_unlock:
list_for_each_entry(smmu, &arm_smmu_devices, list) {
master = find_smmu_master(smmu, dev_node);
if (master)
break;
}
spin_unlock(&arm_smmu_devices_lock);
return parent;
return master ? smmu : NULL;
}
static int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end)
@ -574,9 +584,10 @@ static void arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
}
}
static void arm_smmu_tlb_inv_context(struct arm_smmu_cfg *cfg)
static void arm_smmu_tlb_inv_context(struct arm_smmu_domain *smmu_domain)
{
struct arm_smmu_device *smmu = cfg->smmu;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
struct arm_smmu_device *smmu = smmu_domain->smmu;
void __iomem *base = ARM_SMMU_GR0(smmu);
bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
@ -600,11 +611,11 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
unsigned long iova;
struct iommu_domain *domain = dev;
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
struct arm_smmu_device *smmu = root_cfg->smmu;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
struct arm_smmu_device *smmu = smmu_domain->smmu;
void __iomem *cb_base;
cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR);
if (!(fsr & FSR_FAULT))
@ -631,7 +642,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
} else {
dev_err_ratelimited(smmu->dev,
"Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n",
iova, fsynr, root_cfg->cbndx);
iova, fsynr, cfg->cbndx);
ret = IRQ_NONE;
resume = RESUME_TERMINATE;
}
@ -696,19 +707,19 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
{
u32 reg;
bool stage1;
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
struct arm_smmu_device *smmu = root_cfg->smmu;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
struct arm_smmu_device *smmu = smmu_domain->smmu;
void __iomem *cb_base, *gr0_base, *gr1_base;
gr0_base = ARM_SMMU_GR0(smmu);
gr1_base = ARM_SMMU_GR1(smmu);
stage1 = root_cfg->cbar != CBAR_TYPE_S2_TRANS;
cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
/* CBAR */
reg = root_cfg->cbar;
reg = cfg->cbar;
if (smmu->version == 1)
reg |= root_cfg->irptndx << CBAR_IRPTNDX_SHIFT;
reg |= cfg->irptndx << CBAR_IRPTNDX_SHIFT;
/*
* Use the weakest shareability/memory types, so they are
@ -718,9 +729,9 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) |
(CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
} else {
reg |= ARM_SMMU_CB_VMID(root_cfg) << CBAR_VMID_SHIFT;
reg |= ARM_SMMU_CB_VMID(cfg) << CBAR_VMID_SHIFT;
}
writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(root_cfg->cbndx));
writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(cfg->cbndx));
if (smmu->version > 1) {
/* CBA2R */
@ -730,7 +741,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
reg = CBA2R_RW64_32BIT;
#endif
writel_relaxed(reg,
gr1_base + ARM_SMMU_GR1_CBA2R(root_cfg->cbndx));
gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
/* TTBCR2 */
switch (smmu->input_size) {
@ -780,13 +791,13 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
}
/* TTBR0 */
arm_smmu_flush_pgtable(smmu, root_cfg->pgd,
arm_smmu_flush_pgtable(smmu, cfg->pgd,
PTRS_PER_PGD * sizeof(pgd_t));
reg = __pa(root_cfg->pgd);
reg = __pa(cfg->pgd);
writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
reg = (phys_addr_t)__pa(cfg->pgd) >> 32;
if (stage1)
reg |= ARM_SMMU_CB_ASID(root_cfg) << TTBRn_HI_ASID_SHIFT;
reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
/*
@ -800,6 +811,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
reg = TTBCR_TG0_64K;
if (!stage1) {
reg |= (64 - smmu->s1_output_size) << TTBCR_T0SZ_SHIFT;
switch (smmu->s2_output_size) {
case 32:
reg |= (TTBCR2_ADDR_32 << TTBCR_PASIZE_SHIFT);
@ -821,7 +834,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
break;
}
} else {
reg |= (64 - smmu->s1_output_size) << TTBCR_T0SZ_SHIFT;
reg |= (64 - smmu->input_size) << TTBCR_T0SZ_SHIFT;
}
} else {
reg = 0;
@ -853,44 +866,25 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
}
static int arm_smmu_init_domain_context(struct iommu_domain *domain,
struct device *dev)
struct arm_smmu_device *smmu)
{
int irq, ret, start;
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
struct arm_smmu_device *smmu, *parent;
/*
* Walk the SMMU chain to find the root device for this chain.
* We assume that no masters have translations which terminate
* early, and therefore check that the root SMMU does indeed have
* a StreamID for the master in question.
*/
parent = dev->archdata.iommu;
smmu_domain->output_mask = -1;
do {
smmu = parent;
smmu_domain->output_mask &= (1ULL << smmu->s2_output_size) - 1;
} while ((parent = find_parent_smmu(smmu)));
if (!find_smmu_master(smmu, dev->of_node)) {
dev_err(dev, "unable to find root SMMU for device\n");
return -ENODEV;
}
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
/*
* We will likely want to change this if/when KVM gets
* involved.
*/
root_cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
start = smmu->num_s2_context_banks;
} else if (smmu->features & ARM_SMMU_FEAT_TRANS_S1) {
cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
start = smmu->num_s2_context_banks;
} else if (smmu->features & ARM_SMMU_FEAT_TRANS_S2) {
root_cfg->cbar = CBAR_TYPE_S2_TRANS;
start = 0;
} else {
root_cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
start = smmu->num_s2_context_banks;
cfg->cbar = CBAR_TYPE_S2_TRANS;
start = 0;
}
ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
@ -898,38 +892,38 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
if (IS_ERR_VALUE(ret))
return ret;
root_cfg->cbndx = ret;
cfg->cbndx = ret;
if (smmu->version == 1) {
root_cfg->irptndx = atomic_inc_return(&smmu->irptndx);
root_cfg->irptndx %= smmu->num_context_irqs;
cfg->irptndx = atomic_inc_return(&smmu->irptndx);
cfg->irptndx %= smmu->num_context_irqs;
} else {
root_cfg->irptndx = root_cfg->cbndx;
cfg->irptndx = cfg->cbndx;
}
irq = smmu->irqs[smmu->num_global_irqs + root_cfg->irptndx];
irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
ret = request_irq(irq, arm_smmu_context_fault, IRQF_SHARED,
"arm-smmu-context-fault", domain);
if (IS_ERR_VALUE(ret)) {
dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
root_cfg->irptndx, irq);
root_cfg->irptndx = INVALID_IRPTNDX;
cfg->irptndx, irq);
cfg->irptndx = INVALID_IRPTNDX;
goto out_free_context;
}
root_cfg->smmu = smmu;
smmu_domain->smmu = smmu;
arm_smmu_init_context_bank(smmu_domain);
return ret;
return 0;
out_free_context:
__arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
return ret;
}
static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
{
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
struct arm_smmu_device *smmu = root_cfg->smmu;
struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
void __iomem *cb_base;
int irq;
@ -937,16 +931,16 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
return;
/* Disable the context bank and nuke the TLB before freeing it. */
cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
arm_smmu_tlb_inv_context(root_cfg);
arm_smmu_tlb_inv_context(smmu_domain);
if (root_cfg->irptndx != INVALID_IRPTNDX) {
irq = smmu->irqs[smmu->num_global_irqs + root_cfg->irptndx];
if (cfg->irptndx != INVALID_IRPTNDX) {
irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
free_irq(irq, domain);
}
__arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
}
static int arm_smmu_domain_init(struct iommu_domain *domain)
@ -963,10 +957,10 @@ static int arm_smmu_domain_init(struct iommu_domain *domain)
if (!smmu_domain)
return -ENOMEM;
pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
pgd = kcalloc(PTRS_PER_PGD, sizeof(pgd_t), GFP_KERNEL);
if (!pgd)
goto out_free_domain;
smmu_domain->root_cfg.pgd = pgd;
smmu_domain->cfg.pgd = pgd;
spin_lock_init(&smmu_domain->lock);
domain->priv = smmu_domain;
@ -980,6 +974,7 @@ out_free_domain:
static void arm_smmu_free_ptes(pmd_t *pmd)
{
pgtable_t table = pmd_pgtable(*pmd);
pgtable_page_dtor(table);
__free_page(table);
}
@ -1021,8 +1016,8 @@ static void arm_smmu_free_puds(pgd_t *pgd)
static void arm_smmu_free_pgtables(struct arm_smmu_domain *smmu_domain)
{
int i;
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
pgd_t *pgd, *pgd_base = root_cfg->pgd;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
pgd_t *pgd, *pgd_base = cfg->pgd;
/*
* Recursively free the page tables for this domain. We don't
@ -1054,7 +1049,7 @@ static void arm_smmu_domain_destroy(struct iommu_domain *domain)
}
static int arm_smmu_master_configure_smrs(struct arm_smmu_device *smmu,
struct arm_smmu_master *master)
struct arm_smmu_master_cfg *cfg)
{
int i;
struct arm_smmu_smr *smrs;
@ -1063,18 +1058,18 @@ static int arm_smmu_master_configure_smrs(struct arm_smmu_device *smmu,
if (!(smmu->features & ARM_SMMU_FEAT_STREAM_MATCH))
return 0;
if (master->smrs)
if (cfg->smrs)
return -EEXIST;
smrs = kmalloc(sizeof(*smrs) * master->num_streamids, GFP_KERNEL);
smrs = kmalloc_array(cfg->num_streamids, sizeof(*smrs), GFP_KERNEL);
if (!smrs) {
dev_err(smmu->dev, "failed to allocate %d SMRs for master %s\n",
master->num_streamids, master->of_node->name);
dev_err(smmu->dev, "failed to allocate %d SMRs\n",
cfg->num_streamids);
return -ENOMEM;
}
/* Allocate the SMRs on the root SMMU */
for (i = 0; i < master->num_streamids; ++i) {
/* Allocate the SMRs on the SMMU */
for (i = 0; i < cfg->num_streamids; ++i) {
int idx = __arm_smmu_alloc_bitmap(smmu->smr_map, 0,
smmu->num_mapping_groups);
if (IS_ERR_VALUE(idx)) {
@ -1085,18 +1080,18 @@ static int arm_smmu_master_configure_smrs(struct arm_smmu_device *smmu,
smrs[i] = (struct arm_smmu_smr) {
.idx = idx,
.mask = 0, /* We don't currently share SMRs */
.id = master->streamids[i],
.id = cfg->streamids[i],
};
}
/* It worked! Now, poke the actual hardware */
for (i = 0; i < master->num_streamids; ++i) {
for (i = 0; i < cfg->num_streamids; ++i) {
u32 reg = SMR_VALID | smrs[i].id << SMR_ID_SHIFT |
smrs[i].mask << SMR_MASK_SHIFT;
writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_SMR(smrs[i].idx));
}
master->smrs = smrs;
cfg->smrs = smrs;
return 0;
err_free_smrs:
@ -1107,68 +1102,55 @@ err_free_smrs:
}
static void arm_smmu_master_free_smrs(struct arm_smmu_device *smmu,
struct arm_smmu_master *master)
struct arm_smmu_master_cfg *cfg)
{
int i;
void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
struct arm_smmu_smr *smrs = master->smrs;
struct arm_smmu_smr *smrs = cfg->smrs;
/* Invalidate the SMRs before freeing back to the allocator */
for (i = 0; i < master->num_streamids; ++i) {
for (i = 0; i < cfg->num_streamids; ++i) {
u8 idx = smrs[i].idx;
writel_relaxed(~SMR_VALID, gr0_base + ARM_SMMU_GR0_SMR(idx));
__arm_smmu_free_bitmap(smmu->smr_map, idx);
}
master->smrs = NULL;
cfg->smrs = NULL;
kfree(smrs);
}
static void arm_smmu_bypass_stream_mapping(struct arm_smmu_device *smmu,
struct arm_smmu_master *master)
struct arm_smmu_master_cfg *cfg)
{
int i;
void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
for (i = 0; i < master->num_streamids; ++i) {
u16 sid = master->streamids[i];
for (i = 0; i < cfg->num_streamids; ++i) {
u16 sid = cfg->streamids[i];
writel_relaxed(S2CR_TYPE_BYPASS,
gr0_base + ARM_SMMU_GR0_S2CR(sid));
}
}
static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
struct arm_smmu_master *master)
struct arm_smmu_master_cfg *cfg)
{
int i, ret;
struct arm_smmu_device *parent, *smmu = smmu_domain->root_cfg.smmu;
struct arm_smmu_device *smmu = smmu_domain->smmu;
void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
ret = arm_smmu_master_configure_smrs(smmu, master);
ret = arm_smmu_master_configure_smrs(smmu, cfg);
if (ret)
return ret;
/* Bypass the leaves */
smmu = smmu_domain->leaf_smmu;
while ((parent = find_parent_smmu(smmu))) {
/*
* We won't have a StreamID match for anything but the root
* smmu, so we only need to worry about StreamID indexing,
* where we must install bypass entries in the S2CRs.
*/
if (smmu->features & ARM_SMMU_FEAT_STREAM_MATCH)
continue;
arm_smmu_bypass_stream_mapping(smmu, master);
smmu = parent;
}
/* Now we're at the root, time to point at our context bank */
for (i = 0; i < master->num_streamids; ++i) {
for (i = 0; i < cfg->num_streamids; ++i) {
u32 idx, s2cr;
idx = master->smrs ? master->smrs[i].idx : master->streamids[i];
idx = cfg->smrs ? cfg->smrs[i].idx : cfg->streamids[i];
s2cr = S2CR_TYPE_TRANS |
(smmu_domain->root_cfg.cbndx << S2CR_CBNDX_SHIFT);
(smmu_domain->cfg.cbndx << S2CR_CBNDX_SHIFT);
writel_relaxed(s2cr, gr0_base + ARM_SMMU_GR0_S2CR(idx));
}
@ -1176,58 +1158,57 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
}
static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain,
struct arm_smmu_master *master)
struct arm_smmu_master_cfg *cfg)
{
struct arm_smmu_device *smmu = smmu_domain->root_cfg.smmu;
struct arm_smmu_device *smmu = smmu_domain->smmu;
/*
* We *must* clear the S2CR first, because freeing the SMR means
* that it can be re-allocated immediately.
*/
arm_smmu_bypass_stream_mapping(smmu, master);
arm_smmu_master_free_smrs(smmu, master);
arm_smmu_bypass_stream_mapping(smmu, cfg);
arm_smmu_master_free_smrs(smmu, cfg);
}
static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
{
int ret = -EINVAL;
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_device *device_smmu = dev->archdata.iommu;
struct arm_smmu_master *master;
struct arm_smmu_device *smmu;
struct arm_smmu_master_cfg *cfg;
unsigned long flags;
if (!device_smmu) {
smmu = dev_get_master_dev(dev)->archdata.iommu;
if (!smmu) {
dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
return -ENXIO;
}
/*
* Sanity check the domain. We don't currently support domains
* that cross between different SMMU chains.
* Sanity check the domain. We don't support domains across
* different SMMUs.
*/
spin_lock_irqsave(&smmu_domain->lock, flags);
if (!smmu_domain->leaf_smmu) {
if (!smmu_domain->smmu) {
/* Now that we have a master, we can finalise the domain */
ret = arm_smmu_init_domain_context(domain, dev);
ret = arm_smmu_init_domain_context(domain, smmu);
if (IS_ERR_VALUE(ret))
goto err_unlock;
smmu_domain->leaf_smmu = device_smmu;
} else if (smmu_domain->leaf_smmu != device_smmu) {
} else if (smmu_domain->smmu != smmu) {
dev_err(dev,
"cannot attach to SMMU %s whilst already attached to domain on SMMU %s\n",
dev_name(smmu_domain->leaf_smmu->dev),
dev_name(device_smmu->dev));
dev_name(smmu_domain->smmu->dev),
dev_name(smmu->dev));
goto err_unlock;
}
spin_unlock_irqrestore(&smmu_domain->lock, flags);
/* Looks ok, so add the device to the domain */
master = find_smmu_master(smmu_domain->leaf_smmu, dev->of_node);
if (!master)
cfg = find_smmu_master_cfg(smmu_domain->smmu, dev);
if (!cfg)
return -ENODEV;
return arm_smmu_domain_add_master(smmu_domain, master);
return arm_smmu_domain_add_master(smmu_domain, cfg);
err_unlock:
spin_unlock_irqrestore(&smmu_domain->lock, flags);
@ -1237,11 +1218,11 @@ err_unlock:
static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
{
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_master *master;
struct arm_smmu_master_cfg *cfg;
master = find_smmu_master(smmu_domain->leaf_smmu, dev->of_node);
if (master)
arm_smmu_domain_remove_master(smmu_domain, master);
cfg = find_smmu_master_cfg(smmu_domain->smmu, dev);
if (cfg)
arm_smmu_domain_remove_master(smmu_domain, cfg);
}
static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
@ -1261,6 +1242,7 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
if (pmd_none(*pmd)) {
/* Allocate a new set of tables */
pgtable_t table = alloc_page(GFP_ATOMIC|__GFP_ZERO);
if (!table)
return -ENOMEM;
@ -1326,6 +1308,7 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
*/
do {
int i = 1;
pteval &= ~ARM_SMMU_PTE_CONT;
if (arm_smmu_pte_is_contiguous_range(addr, end)) {
@ -1340,7 +1323,8 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
idx &= ~(ARM_SMMU_PTE_CONT_ENTRIES - 1);
cont_start = pmd_page_vaddr(*pmd) + idx;
for (j = 0; j < ARM_SMMU_PTE_CONT_ENTRIES; ++j)
pte_val(*(cont_start + j)) &= ~ARM_SMMU_PTE_CONT;
pte_val(*(cont_start + j)) &=
~ARM_SMMU_PTE_CONT;
arm_smmu_flush_pgtable(smmu, cont_start,
sizeof(*pte) *
@ -1429,12 +1413,12 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
int ret, stage;
unsigned long end;
phys_addr_t input_mask, output_mask;
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
pgd_t *pgd = root_cfg->pgd;
struct arm_smmu_device *smmu = root_cfg->smmu;
struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
pgd_t *pgd = cfg->pgd;
unsigned long flags;
if (root_cfg->cbar == CBAR_TYPE_S2_TRANS) {
if (cfg->cbar == CBAR_TYPE_S2_TRANS) {
stage = 2;
output_mask = (1ULL << smmu->s2_output_size) - 1;
} else {
@ -1484,10 +1468,6 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
if (!smmu_domain)
return -ENODEV;
/* Check for silent address truncation up the SMMU chain. */
if ((phys_addr_t)iova & ~smmu_domain->output_mask)
return -ERANGE;
return arm_smmu_handle_mapping(smmu_domain, iova, paddr, size, prot);
}
@ -1498,7 +1478,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
struct arm_smmu_domain *smmu_domain = domain->priv;
ret = arm_smmu_handle_mapping(smmu_domain, iova, 0, size, 0);
arm_smmu_tlb_inv_context(&smmu_domain->root_cfg);
arm_smmu_tlb_inv_context(smmu_domain);
return ret ? 0 : size;
}
@ -1510,9 +1490,9 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
pmd_t pmd;
pte_t pte;
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
pgdp = root_cfg->pgd;
pgdp = cfg->pgd;
if (!pgdp)
return 0;
@ -1538,19 +1518,29 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
static int arm_smmu_domain_has_cap(struct iommu_domain *domain,
unsigned long cap)
{
unsigned long caps = 0;
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_device *smmu = smmu_domain->smmu;
u32 features = smmu ? smmu->features : 0;
if (smmu_domain->root_cfg.smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
caps |= IOMMU_CAP_CACHE_COHERENCY;
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
return features & ARM_SMMU_FEAT_COHERENT_WALK;
case IOMMU_CAP_INTR_REMAP:
return 1; /* MSIs are just memory writes */
default:
return 0;
}
}
return !!(cap & caps);
static int __arm_smmu_get_pci_sid(struct pci_dev *pdev, u16 alias, void *data)
{
*((u16 *)data) = alias;
return 0; /* Continue walking */
}
static int arm_smmu_add_device(struct device *dev)
{
struct arm_smmu_device *child, *parent, *smmu;
struct arm_smmu_master *master = NULL;
struct arm_smmu_device *smmu;
struct iommu_group *group;
int ret;
@ -1559,35 +1549,8 @@ static int arm_smmu_add_device(struct device *dev)
return -EINVAL;
}
spin_lock(&arm_smmu_devices_lock);
list_for_each_entry(parent, &arm_smmu_devices, list) {
smmu = parent;
/* Try to find a child of the current SMMU. */
list_for_each_entry(child, &arm_smmu_devices, list) {
if (child->parent_of_node == parent->dev->of_node) {
/* Does the child sit above our master? */
master = find_smmu_master(child, dev->of_node);
if (master) {
smmu = NULL;
break;
}
}
}
/* We found some children, so keep searching. */
if (!smmu) {
master = NULL;
continue;
}
master = find_smmu_master(smmu, dev->of_node);
if (master)
break;
}
spin_unlock(&arm_smmu_devices_lock);
if (!master)
smmu = find_smmu_for_device(dev);
if (!smmu)
return -ENODEV;
group = iommu_group_alloc();
@ -1596,15 +1559,40 @@ static int arm_smmu_add_device(struct device *dev)
return PTR_ERR(group);
}
ret = iommu_group_add_device(group, dev);
iommu_group_put(group);
dev->archdata.iommu = smmu;
if (dev_is_pci(dev)) {
struct arm_smmu_master_cfg *cfg;
struct pci_dev *pdev = to_pci_dev(dev);
cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
if (!cfg) {
ret = -ENOMEM;
goto out_put_group;
}
cfg->num_streamids = 1;
/*
* Assume Stream ID == Requester ID for now.
* We need a way to describe the ID mappings in FDT.
*/
pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid,
&cfg->streamids[0]);
dev->archdata.iommu = cfg;
} else {
dev->archdata.iommu = smmu;
}
ret = iommu_group_add_device(group, dev);
out_put_group:
iommu_group_put(group);
return ret;
}
static void arm_smmu_remove_device(struct device *dev)
{
if (dev_is_pci(dev))
kfree(dev->archdata.iommu);
dev->archdata.iommu = NULL;
iommu_group_remove_device(dev);
}
@ -1639,7 +1627,8 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
/* Mark all SMRn as invalid and all S2CRn as bypass */
for (i = 0; i < smmu->num_mapping_groups; ++i) {
writel_relaxed(~SMR_VALID, gr0_base + ARM_SMMU_GR0_SMR(i));
writel_relaxed(S2CR_TYPE_BYPASS, gr0_base + ARM_SMMU_GR0_S2CR(i));
writel_relaxed(S2CR_TYPE_BYPASS,
gr0_base + ARM_SMMU_GR0_S2CR(i));
}
/* Make sure all context banks are disabled and clear CB_FSR */
@ -1779,11 +1768,13 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
smmu->pagesize = (id & ID1_PAGESIZE) ? SZ_64K : SZ_4K;
/* Check for size mismatch of SMMU address space from mapped region */
size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
size = 1 <<
(((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
size *= (smmu->pagesize << 1);
if (smmu->size != size)
dev_warn(smmu->dev, "SMMU address space size (0x%lx) differs "
"from mapped region size (0x%lx)!\n", size, smmu->size);
dev_warn(smmu->dev,
"SMMU address space size (0x%lx) differs from mapped region size (0x%lx)!\n",
size, smmu->size);
smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) &
ID1_NUMS2CB_MASK;
@ -1804,14 +1795,14 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
* allocation (PTRS_PER_PGD).
*/
#ifdef CONFIG_64BIT
smmu->s1_output_size = min((unsigned long)VA_BITS, size);
smmu->s1_output_size = min_t(unsigned long, VA_BITS, size);
#else
smmu->s1_output_size = min(32UL, size);
#endif
/* The stage-2 output mask is also applied for bypass */
size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
smmu->s2_output_size = min((unsigned long)PHYS_MASK_SHIFT, size);
smmu->s2_output_size = min_t(unsigned long, PHYS_MASK_SHIFT, size);
if (smmu->version == 1) {
smmu->input_size = 32;
@ -1835,7 +1826,8 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
dev_notice(smmu->dev,
"\t%lu-bit VA, %lu-bit IPA, %lu-bit PA\n",
smmu->input_size, smmu->s1_output_size, smmu->s2_output_size);
smmu->input_size, smmu->s1_output_size,
smmu->s2_output_size);
return 0;
}
@ -1843,7 +1835,6 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
{
struct resource *res;
struct arm_smmu_device *smmu;
struct device_node *dev_node;
struct device *dev = &pdev->dev;
struct rb_node *node;
struct of_phandle_args masterspec;
@ -1890,6 +1881,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
for (i = 0; i < num_irqs; ++i) {
int irq = platform_get_irq(pdev, i);
if (irq < 0) {
dev_err(dev, "failed to get irq index %d\n", i);
return -ENODEV;
@ -1913,12 +1905,9 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
}
dev_notice(dev, "registered %d master devices\n", i);
if ((dev_node = of_parse_phandle(dev->of_node, "smmu-parent", 0)))
smmu->parent_of_node = dev_node;
err = arm_smmu_device_cfg_probe(smmu);
if (err)
goto out_put_parent;
goto out_put_masters;
parse_driver_options(smmu);
@ -1928,7 +1917,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
"found only %d context interrupt(s) but %d required\n",
smmu->num_context_irqs, smmu->num_context_banks);
err = -ENODEV;
goto out_put_parent;
goto out_put_masters;
}
for (i = 0; i < smmu->num_global_irqs; ++i) {
@ -1956,14 +1945,10 @@ out_free_irqs:
while (i--)
free_irq(smmu->irqs[i], smmu);
out_put_parent:
if (smmu->parent_of_node)
of_node_put(smmu->parent_of_node);
out_put_masters:
for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
struct arm_smmu_master *master;
master = container_of(node, struct arm_smmu_master, node);
struct arm_smmu_master *master
= container_of(node, struct arm_smmu_master, node);
of_node_put(master->of_node);
}
@ -1990,12 +1975,9 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
if (!smmu)
return -ENODEV;
if (smmu->parent_of_node)
of_node_put(smmu->parent_of_node);
for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
struct arm_smmu_master *master;
master = container_of(node, struct arm_smmu_master, node);
struct arm_smmu_master *master
= container_of(node, struct arm_smmu_master, node);
of_node_put(master->of_node);
}
@ -2006,7 +1988,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
free_irq(smmu->irqs[i], smmu);
/* Turn the thing off */
writel(sCR0_CLIENTPD,ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
return 0;
}
@ -2048,6 +2030,11 @@ static int __init arm_smmu_init(void)
bus_set_iommu(&amba_bustype, &arm_smmu_ops);
#endif
#ifdef CONFIG_PCI
if (!iommu_present(&pci_bus_type))
bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
#endif
return 0;
}