diff options
author | Will Deacon <will.deacon@arm.com> | 2014-11-14 17:18:23 +0000 |
---|---|---|
committer | Will Deacon <will.deacon@arm.com> | 2015-01-19 14:46:44 +0000 |
commit | e1d3c0fd701df831169b116cd5c5d6203ac07f70 (patch) | |
tree | eb2537042682bf45a36148d06bb0bfb10ce3da74 /drivers/iommu | |
parent | fdb1d7be7c4d452e9735aeb2b60ae8a2fcf0a514 (diff) | |
download | op-kernel-dev-e1d3c0fd701df831169b116cd5c5d6203ac07f70.zip op-kernel-dev-e1d3c0fd701df831169b116cd5c5d6203ac07f70.tar.gz |
iommu: add ARM LPAE page table allocator
A number of IOMMUs found in ARM SoCs can walk architecture-compatible
page tables.
This patch adds a generic allocator for Stage-1 and Stage-2 v7/v8
long-descriptor page tables. 4k, 16k and 64k pages are supported, with
up to 4-levels of walk to cover a 48-bit address space.
Tested-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Diffstat (limited to 'drivers/iommu')
-rw-r--r-- | drivers/iommu/Kconfig | 9 | ||||
-rw-r--r-- | drivers/iommu/Makefile | 1 | ||||
-rw-r--r-- | drivers/iommu/io-pgtable-arm.c | 781 | ||||
-rw-r--r-- | drivers/iommu/io-pgtable.c | 11 | ||||
-rw-r--r-- | drivers/iommu/io-pgtable.h | 14 |
5 files changed, 816 insertions, 0 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 3faaa41..306454f 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -19,6 +19,15 @@ menu "Generic IOMMU Pagetable Support" config IOMMU_IO_PGTABLE bool +config IOMMU_IO_PGTABLE_LPAE + bool "ARMv7/v8 Long Descriptor Format" + select IOMMU_IO_PGTABLE + help + Enable support for the ARM long descriptor pagetable format. + This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page + sizes at both stage-1 and stage-2, as well as address spaces + up to 48-bits in size. + endmenu config OF_IOMMU diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 701c951..d6889b4 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_IOMMU_API) += iommu.o obj-$(CONFIG_IOMMU_API) += iommu-traces.o obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o +obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c new file mode 100644 index 0000000..dbe6178 --- /dev/null +++ b/drivers/iommu/io-pgtable-arm.c @@ -0,0 +1,781 @@ +/* + * CPU-agnostic ARM page table allocator. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + * + * Copyright (C) 2014 ARM Limited + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +#define pr_fmt(fmt) "arm-lpae io-pgtable: " fmt + +#include <linux/iommu.h> +#include <linux/kernel.h> +#include <linux/sizes.h> +#include <linux/slab.h> +#include <linux/types.h> + +#include "io-pgtable.h" + +#define ARM_LPAE_MAX_ADDR_BITS 48 +#define ARM_LPAE_S2_MAX_CONCAT_PAGES 16 +#define ARM_LPAE_MAX_LEVELS 4 + +/* Struct accessors */ +#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)) + +/* + * For consistency with the architecture, we always consider + * ARM_LPAE_MAX_LEVELS levels, with the walk starting at level n >=0 + */ +#define ARM_LPAE_START_LVL(d) (ARM_LPAE_MAX_LEVELS - (d)->levels) + +/* + * Calculate the right shift amount to get to the portion describing level l + * in a virtual address mapped by the pagetable in d. + */ +#define ARM_LPAE_LVL_SHIFT(l,d) \ + ((((d)->levels - ((l) - ARM_LPAE_START_LVL(d) + 1)) \ + * (d)->bits_per_level) + (d)->pg_shift) + +#define ARM_LPAE_PAGES_PER_PGD(d) ((d)->pgd_size >> (d)->pg_shift) + +/* + * Calculate the index at level l used to map virtual address a using the + * pagetable in d. + */ +#define ARM_LPAE_PGD_IDX(l,d) \ + ((l) == ARM_LPAE_START_LVL(d) ? ilog2(ARM_LPAE_PAGES_PER_PGD(d)) : 0) + +#define ARM_LPAE_LVL_IDX(a,l,d) \ + (((a) >> ARM_LPAE_LVL_SHIFT(l,d)) & \ + ((1 << ((d)->bits_per_level + ARM_LPAE_PGD_IDX(l,d))) - 1)) + +/* Calculate the block/page mapping size at level l for pagetable in d. */ +#define ARM_LPAE_BLOCK_SIZE(l,d) \ + (1 << (ilog2(sizeof(arm_lpae_iopte)) + \ + ((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level))) + +/* Page table bits */ +#define ARM_LPAE_PTE_TYPE_SHIFT 0 +#define ARM_LPAE_PTE_TYPE_MASK 0x3 + +#define ARM_LPAE_PTE_TYPE_BLOCK 1 +#define ARM_LPAE_PTE_TYPE_TABLE 3 +#define ARM_LPAE_PTE_TYPE_PAGE 3 + +#define ARM_LPAE_PTE_XN (((arm_lpae_iopte)3) << 53) +#define ARM_LPAE_PTE_AF (((arm_lpae_iopte)1) << 10) +#define ARM_LPAE_PTE_SH_NS (((arm_lpae_iopte)0) << 8) +#define ARM_LPAE_PTE_SH_OS (((arm_lpae_iopte)2) << 8) +#define ARM_LPAE_PTE_SH_IS (((arm_lpae_iopte)3) << 8) +#define ARM_LPAE_PTE_VALID (((arm_lpae_iopte)1) << 0) + +#define ARM_LPAE_PTE_ATTR_LO_MASK (((arm_lpae_iopte)0x3ff) << 2) +/* Ignore the contiguous bit for block splitting */ +#define ARM_LPAE_PTE_ATTR_HI_MASK (((arm_lpae_iopte)6) << 52) +#define ARM_LPAE_PTE_ATTR_MASK (ARM_LPAE_PTE_ATTR_LO_MASK | \ + ARM_LPAE_PTE_ATTR_HI_MASK) + +/* Stage-1 PTE */ +#define ARM_LPAE_PTE_AP_UNPRIV (((arm_lpae_iopte)1) << 6) +#define ARM_LPAE_PTE_AP_RDONLY (((arm_lpae_iopte)2) << 6) +#define ARM_LPAE_PTE_ATTRINDX_SHIFT 2 +#define ARM_LPAE_PTE_nG (((arm_lpae_iopte)1) << 11) + +/* Stage-2 PTE */ +#define ARM_LPAE_PTE_HAP_FAULT (((arm_lpae_iopte)0) << 6) +#define ARM_LPAE_PTE_HAP_READ (((arm_lpae_iopte)1) << 6) +#define ARM_LPAE_PTE_HAP_WRITE (((arm_lpae_iopte)2) << 6) +#define ARM_LPAE_PTE_MEMATTR_OIWB (((arm_lpae_iopte)0xf) << 2) +#define ARM_LPAE_PTE_MEMATTR_NC (((arm_lpae_iopte)0x5) << 2) +#define ARM_LPAE_PTE_MEMATTR_DEV (((arm_lpae_iopte)0x1) << 2) + +/* Register bits */ +#define ARM_32_LPAE_TCR_EAE (1 << 31) +#define ARM_64_LPAE_S2_TCR_RES1 (1 << 31) + +#define ARM_LPAE_TCR_TG0_4K (0 << 14) +#define ARM_LPAE_TCR_TG0_64K (1 << 14) +#define ARM_LPAE_TCR_TG0_16K (2 << 14) + +#define ARM_LPAE_TCR_SH0_SHIFT 12 +#define ARM_LPAE_TCR_SH0_MASK 0x3 +#define ARM_LPAE_TCR_SH_NS 0 +#define ARM_LPAE_TCR_SH_OS 2 +#define ARM_LPAE_TCR_SH_IS 3 + +#define ARM_LPAE_TCR_ORGN0_SHIFT 10 +#define ARM_LPAE_TCR_IRGN0_SHIFT 8 +#define ARM_LPAE_TCR_RGN_MASK 0x3 +#define ARM_LPAE_TCR_RGN_NC 0 +#define ARM_LPAE_TCR_RGN_WBWA 1 +#define ARM_LPAE_TCR_RGN_WT 2 +#define ARM_LPAE_TCR_RGN_WB 3 + +#define ARM_LPAE_TCR_SL0_SHIFT 6 +#define ARM_LPAE_TCR_SL0_MASK 0x3 + +#define ARM_LPAE_TCR_T0SZ_SHIFT 0 +#define ARM_LPAE_TCR_SZ_MASK 0xf + +#define ARM_LPAE_TCR_PS_SHIFT 16 +#define ARM_LPAE_TCR_PS_MASK 0x7 + +#define ARM_LPAE_TCR_IPS_SHIFT 32 +#define ARM_LPAE_TCR_IPS_MASK 0x7 + +#define ARM_LPAE_TCR_PS_32_BIT 0x0ULL +#define ARM_LPAE_TCR_PS_36_BIT 0x1ULL +#define ARM_LPAE_TCR_PS_40_BIT 0x2ULL +#define ARM_LPAE_TCR_PS_42_BIT 0x3ULL +#define ARM_LPAE_TCR_PS_44_BIT 0x4ULL +#define ARM_LPAE_TCR_PS_48_BIT 0x5ULL + +#define ARM_LPAE_MAIR_ATTR_SHIFT(n) ((n) << 3) +#define ARM_LPAE_MAIR_ATTR_MASK 0xff +#define ARM_LPAE_MAIR_ATTR_DEVICE 0x04 +#define ARM_LPAE_MAIR_ATTR_NC 0x44 +#define ARM_LPAE_MAIR_ATTR_WBRWA 0xff +#define ARM_LPAE_MAIR_ATTR_IDX_NC 0 +#define ARM_LPAE_MAIR_ATTR_IDX_CACHE 1 +#define ARM_LPAE_MAIR_ATTR_IDX_DEV 2 + +/* IOPTE accessors */ +#define iopte_deref(pte,d) \ + (__va((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1) \ + & ~((1ULL << (d)->pg_shift) - 1))) + +#define iopte_type(pte,l) \ + (((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK) + +#define iopte_prot(pte) ((pte) & ARM_LPAE_PTE_ATTR_MASK) + +#define iopte_leaf(pte,l) \ + (l == (ARM_LPAE_MAX_LEVELS - 1) ? \ + (iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_PAGE) : \ + (iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_BLOCK)) + +#define iopte_to_pfn(pte,d) \ + (((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) >> (d)->pg_shift) + +#define pfn_to_iopte(pfn,d) \ + (((pfn) << (d)->pg_shift) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) + +struct arm_lpae_io_pgtable { + struct io_pgtable iop; + + int levels; + size_t pgd_size; + unsigned long pg_shift; + unsigned long bits_per_level; + + void *pgd; +}; + +typedef u64 arm_lpae_iopte; + +static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, + unsigned long iova, phys_addr_t paddr, + arm_lpae_iopte prot, int lvl, + arm_lpae_iopte *ptep) +{ + arm_lpae_iopte pte = prot; + + /* We require an unmap first */ + if (WARN_ON(iopte_leaf(*ptep, lvl))) + return -EEXIST; + + if (lvl == ARM_LPAE_MAX_LEVELS - 1) + pte |= ARM_LPAE_PTE_TYPE_PAGE; + else + pte |= ARM_LPAE_PTE_TYPE_BLOCK; + + pte |= ARM_LPAE_PTE_AF | ARM_LPAE_PTE_SH_IS; + pte |= pfn_to_iopte(paddr >> data->pg_shift, data); + + *ptep = pte; + data->iop.cfg.tlb->flush_pgtable(ptep, sizeof(*ptep), data->iop.cookie); + return 0; +} + +static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, + phys_addr_t paddr, size_t size, arm_lpae_iopte prot, + int lvl, arm_lpae_iopte *ptep) +{ + arm_lpae_iopte *cptep, pte; + void *cookie = data->iop.cookie; + size_t block_size = ARM_LPAE_BLOCK_SIZE(lvl, data); + + /* Find our entry at the current level */ + ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); + + /* If we can install a leaf entry at this level, then do so */ + if (size == block_size && (size & data->iop.cfg.pgsize_bitmap)) + return arm_lpae_init_pte(data, iova, paddr, prot, lvl, ptep); + + /* We can't allocate tables at the final level */ + if (WARN_ON(lvl >= ARM_LPAE_MAX_LEVELS - 1)) + return -EINVAL; + + /* Grab a pointer to the next level */ + pte = *ptep; + if (!pte) { + cptep = alloc_pages_exact(1UL << data->pg_shift, + GFP_ATOMIC | __GFP_ZERO); + if (!cptep) + return -ENOMEM; + + data->iop.cfg.tlb->flush_pgtable(cptep, 1UL << data->pg_shift, + cookie); + pte = __pa(cptep) | ARM_LPAE_PTE_TYPE_TABLE; + *ptep = pte; + data->iop.cfg.tlb->flush_pgtable(ptep, sizeof(*ptep), cookie); + } else { + cptep = iopte_deref(pte, data); + } + + /* Rinse, repeat */ + return __arm_lpae_map(data, iova, paddr, size, prot, lvl + 1, cptep); +} + +static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, + int prot) +{ + arm_lpae_iopte pte; + + if (data->iop.fmt == ARM_64_LPAE_S1 || + data->iop.fmt == ARM_32_LPAE_S1) { + pte = ARM_LPAE_PTE_AP_UNPRIV | ARM_LPAE_PTE_nG; + + if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ)) + pte |= ARM_LPAE_PTE_AP_RDONLY; + + if (prot & IOMMU_CACHE) + pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE + << ARM_LPAE_PTE_ATTRINDX_SHIFT); + } else { + pte = ARM_LPAE_PTE_HAP_FAULT; + if (prot & IOMMU_READ) + pte |= ARM_LPAE_PTE_HAP_READ; + if (prot & IOMMU_WRITE) + pte |= ARM_LPAE_PTE_HAP_WRITE; + if (prot & IOMMU_CACHE) + pte |= ARM_LPAE_PTE_MEMATTR_OIWB; + else + pte |= ARM_LPAE_PTE_MEMATTR_NC; + } + + if (prot & IOMMU_NOEXEC) + pte |= ARM_LPAE_PTE_XN; + + return pte; +} + +static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t size, int iommu_prot) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + arm_lpae_iopte *ptep = data->pgd; + int lvl = ARM_LPAE_START_LVL(data); + arm_lpae_iopte prot; + + /* If no access, then nothing to do */ + if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE))) + return 0; + + prot = arm_lpae_prot_to_pte(data, iommu_prot); + return __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep); +} + +static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl, + arm_lpae_iopte *ptep) +{ + 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; + + start = ptep; + end = (void *)ptep + table_size; + + while (ptep != end) { + arm_lpae_iopte pte = *ptep++; + + if (!pte || iopte_leaf(pte, lvl)) + continue; + + __arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data)); + } + + free_pages_exact(start, table_size); +} + +static void arm_lpae_free_pgtable(struct io_pgtable *iop) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_to_data(iop); + + __arm_lpae_free_pgtable(data, ARM_LPAE_START_LVL(data), data->pgd); + kfree(data); +} + +static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, + arm_lpae_iopte prot, int lvl, + arm_lpae_iopte *ptep, size_t blk_size) +{ + unsigned long blk_start, blk_end; + phys_addr_t blk_paddr; + arm_lpae_iopte table = 0; + void *cookie = data->iop.cookie; + const struct iommu_gather_ops *tlb = data->iop.cfg.tlb; + + blk_start = iova & ~(blk_size - 1); + blk_end = blk_start + blk_size; + blk_paddr = iopte_to_pfn(*ptep, data) << data->pg_shift; + + for (; blk_start < blk_end; blk_start += size, blk_paddr += size) { + arm_lpae_iopte *tablep; + + /* Unmap! */ + if (blk_start == iova) + continue; + + /* __arm_lpae_map expects a pointer to the start of the table */ + tablep = &table - ARM_LPAE_LVL_IDX(blk_start, lvl, data); + if (__arm_lpae_map(data, blk_start, blk_paddr, size, prot, lvl, + tablep) < 0) { + if (table) { + /* Free the table we allocated */ + tablep = iopte_deref(table, data); + __arm_lpae_free_pgtable(data, lvl + 1, tablep); + } + return 0; /* Bytes unmapped */ + } + } + + *ptep = table; + tlb->flush_pgtable(ptep, sizeof(*ptep), cookie); + iova &= ~(blk_size - 1); + tlb->tlb_add_flush(iova, blk_size, true, cookie); + return size; +} + +static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_lpae_iopte *ptep) +{ + arm_lpae_iopte pte; + const struct iommu_gather_ops *tlb = data->iop.cfg.tlb; + void *cookie = data->iop.cookie; + size_t blk_size = ARM_LPAE_BLOCK_SIZE(lvl, data); + + 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))) + return 0; + + /* If the size matches this level, we're in the right place */ + if (size == blk_size) { + *ptep = 0; + tlb->flush_pgtable(ptep, sizeof(*ptep), cookie); + + if (!iopte_leaf(pte, lvl)) { + /* Also flush any partial walks */ + tlb->tlb_add_flush(iova, size, false, cookie); + tlb->tlb_sync(data->iop.cookie); + ptep = iopte_deref(pte, data); + __arm_lpae_free_pgtable(data, lvl + 1, ptep); + } else { + tlb->tlb_add_flush(iova, size, true, cookie); + } + + return size; + } else if (iopte_leaf(pte, lvl)) { + /* + * Insert a table at the next level to map the old region, + * minus the part we want to unmap + */ + return arm_lpae_split_blk_unmap(data, iova, size, + iopte_prot(pte), lvl, ptep, + blk_size); + } + + /* Keep on walkin' */ + ptep = iopte_deref(pte, data); + return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep); +} + +static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, + size_t size) +{ + size_t unmapped; + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + struct io_pgtable *iop = &data->iop; + arm_lpae_iopte *ptep = data->pgd; + int lvl = ARM_LPAE_START_LVL(data); + + unmapped = __arm_lpae_unmap(data, iova, size, lvl, ptep); + if (unmapped) + iop->cfg.tlb->tlb_sync(iop->cookie); + + return unmapped; +} + +static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, + unsigned long iova) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + arm_lpae_iopte pte, *ptep = data->pgd; + int lvl = ARM_LPAE_START_LVL(data); + + do { + /* Valid IOPTE pointer? */ + if (!ptep) + return 0; + + /* Grab the IOPTE we're interested in */ + pte = *(ptep + ARM_LPAE_LVL_IDX(iova, lvl, data)); + + /* Valid entry? */ + if (!pte) + return 0; + + /* Leaf entry? */ + if (iopte_leaf(pte,lvl)) + goto found_translation; + + /* Take it to the next level */ + ptep = iopte_deref(pte, data); + } while (++lvl < ARM_LPAE_MAX_LEVELS); + + /* Ran out of page tables to walk */ + return 0; + +found_translation: + iova &= ((1 << data->pg_shift) - 1); + return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova; +} + +static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) +{ + unsigned long granule; + + /* + * We need to restrict the supported page sizes to match the + * translation regime for a particular granule. Aim to match + * the CPU page size if possible, otherwise prefer smaller sizes. + * While we're at it, restrict the block sizes to match the + * chosen granule. + */ + if (cfg->pgsize_bitmap & PAGE_SIZE) + granule = PAGE_SIZE; + else if (cfg->pgsize_bitmap & ~PAGE_MASK) + granule = 1UL << __fls(cfg->pgsize_bitmap & ~PAGE_MASK); + else if (cfg->pgsize_bitmap & PAGE_MASK) + granule = 1UL << __ffs(cfg->pgsize_bitmap & PAGE_MASK); + else + granule = 0; + + switch (granule) { + case SZ_4K: + cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G); + break; + case SZ_16K: + cfg->pgsize_bitmap &= (SZ_16K | SZ_32M); + break; + case SZ_64K: + cfg->pgsize_bitmap &= (SZ_64K | SZ_512M); + break; + default: + cfg->pgsize_bitmap = 0; + } +} + +static struct arm_lpae_io_pgtable * +arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg) +{ + unsigned long va_bits, pgd_bits; + struct arm_lpae_io_pgtable *data; + + arm_lpae_restrict_pgsizes(cfg); + + if (!(cfg->pgsize_bitmap & (SZ_4K | SZ_16K | SZ_64K))) + return NULL; + + if (cfg->ias > ARM_LPAE_MAX_ADDR_BITS) + return NULL; + + if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS) + return NULL; + + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return NULL; + + data->pg_shift = __ffs(cfg->pgsize_bitmap); + data->bits_per_level = data->pg_shift - ilog2(sizeof(arm_lpae_iopte)); + + va_bits = cfg->ias - data->pg_shift; + data->levels = DIV_ROUND_UP(va_bits, data->bits_per_level); + + /* Calculate the actual size of our pgd (without concatenation) */ + pgd_bits = va_bits - (data->bits_per_level * (data->levels - 1)); + data->pgd_size = 1UL << (pgd_bits + ilog2(sizeof(arm_lpae_iopte))); + + data->iop.ops = (struct io_pgtable_ops) { + .map = arm_lpae_map, + .unmap = arm_lpae_unmap, + .iova_to_phys = arm_lpae_iova_to_phys, + }; + + return data; +} + +static struct io_pgtable * +arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) +{ + u64 reg; + struct arm_lpae_io_pgtable *data = arm_lpae_alloc_pgtable(cfg); + + if (!data) + return NULL; + + /* TCR */ + reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) | + (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) { + case SZ_4K: + reg |= ARM_LPAE_TCR_TG0_4K; + break; + case SZ_16K: + reg |= ARM_LPAE_TCR_TG0_16K; + break; + case SZ_64K: + reg |= ARM_LPAE_TCR_TG0_64K; + break; + } + + switch (cfg->oas) { + case 32: + reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_IPS_SHIFT); + break; + case 36: + reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_IPS_SHIFT); + break; + case 40: + reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_IPS_SHIFT); + break; + case 42: + reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_IPS_SHIFT); + break; + case 44: + reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_IPS_SHIFT); + break; + case 48: + reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT); + break; + default: + goto out_free_data; + } + + reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT; + cfg->arm_lpae_s1_cfg.tcr = reg; + + /* MAIRs */ + reg = (ARM_LPAE_MAIR_ATTR_NC + << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) | + (ARM_LPAE_MAIR_ATTR_WBRWA + << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) | + (ARM_LPAE_MAIR_ATTR_DEVICE + << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV)); + + cfg->arm_lpae_s1_cfg.mair[0] = reg; + cfg->arm_lpae_s1_cfg.mair[1] = 0; + + /* Looking good; allocate a pgd */ + data->pgd = alloc_pages_exact(data->pgd_size, GFP_KERNEL | __GFP_ZERO); + if (!data->pgd) + goto out_free_data; + + cfg->tlb->flush_pgtable(data->pgd, data->pgd_size, cookie); + + /* TTBRs */ + cfg->arm_lpae_s1_cfg.ttbr[0] = virt_to_phys(data->pgd); + cfg->arm_lpae_s1_cfg.ttbr[1] = 0; + return &data->iop; + +out_free_data: + kfree(data); + return NULL; +} + +static struct io_pgtable * +arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) +{ + u64 reg, sl; + struct arm_lpae_io_pgtable *data = arm_lpae_alloc_pgtable(cfg); + + if (!data) + return NULL; + + /* + * Concatenate PGDs at level 1 if possible in order to reduce + * the depth of the stage-2 walk. + */ + if (data->levels == ARM_LPAE_MAX_LEVELS) { + unsigned long pgd_pages; + + pgd_pages = data->pgd_size >> ilog2(sizeof(arm_lpae_iopte)); + if (pgd_pages <= ARM_LPAE_S2_MAX_CONCAT_PAGES) { + data->pgd_size = pgd_pages << data->pg_shift; + data->levels--; + } + } + + /* VTCR */ + reg = ARM_64_LPAE_S2_TCR_RES1 | + (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) | + (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) | + (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT); + + sl = ARM_LPAE_START_LVL(data); + + switch (1 << data->pg_shift) { + case SZ_4K: + reg |= ARM_LPAE_TCR_TG0_4K; + sl++; /* SL0 format is different for 4K granule size */ + break; + case SZ_16K: + reg |= ARM_LPAE_TCR_TG0_16K; + break; + case SZ_64K: + reg |= ARM_LPAE_TCR_TG0_64K; + break; + } + + switch (cfg->oas) { + case 32: + reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_PS_SHIFT); + break; + case 36: + reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_PS_SHIFT); + break; + case 40: + reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_PS_SHIFT); + break; + case 42: + reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_PS_SHIFT); + break; + case 44: + reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_PS_SHIFT); + break; + case 48: + reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT); + break; + default: + goto out_free_data; + } + + reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT; + reg |= (~sl & ARM_LPAE_TCR_SL0_MASK) << ARM_LPAE_TCR_SL0_SHIFT; + cfg->arm_lpae_s2_cfg.vtcr = reg; + + /* Allocate pgd pages */ + data->pgd = alloc_pages_exact(data->pgd_size, GFP_KERNEL | __GFP_ZERO); + if (!data->pgd) + goto out_free_data; + + cfg->tlb->flush_pgtable(data->pgd, data->pgd_size, cookie); + + /* VTTBR */ + cfg->arm_lpae_s2_cfg.vttbr = virt_to_phys(data->pgd); + return &data->iop; + +out_free_data: + kfree(data); + return NULL; +} + +static struct io_pgtable * +arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) +{ + struct io_pgtable *iop; + + if (cfg->ias > 32 || cfg->oas > 40) + return NULL; + + cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G); + iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie); + if (iop) { + cfg->arm_lpae_s1_cfg.tcr |= ARM_32_LPAE_TCR_EAE; + cfg->arm_lpae_s1_cfg.tcr &= 0xffffffff; + } + + return iop; +} + +static struct io_pgtable * +arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) +{ + struct io_pgtable *iop; + + if (cfg->ias > 40 || cfg->oas > 40) + return NULL; + + cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G); + iop = arm_64_lpae_alloc_pgtable_s2(cfg, cookie); + if (iop) + cfg->arm_lpae_s2_cfg.vtcr &= 0xffffffff; + + return iop; +} + +struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = { + .alloc = arm_64_lpae_alloc_pgtable_s1, + .free = arm_lpae_free_pgtable, +}; + +struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns = { + .alloc = arm_64_lpae_alloc_pgtable_s2, + .free = arm_lpae_free_pgtable, +}; + +struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns = { + .alloc = arm_32_lpae_alloc_pgtable_s1, + .free = arm_lpae_free_pgtable, +}; + +struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = { + .alloc = arm_32_lpae_alloc_pgtable_s2, + .free = arm_lpae_free_pgtable, +}; diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c index f664a1c..6436fe2 100644 --- a/drivers/iommu/io-pgtable.c +++ b/drivers/iommu/io-pgtable.c @@ -24,9 +24,20 @@ #include "io-pgtable.h" +extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns; +extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns; +extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns; +extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns; + static const struct io_pgtable_init_fns * io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = { +#ifdef CONFIG_IOMMU_IO_PGTABLE_LPAE + [ARM_32_LPAE_S1] = &io_pgtable_arm_32_lpae_s1_init_fns, + [ARM_32_LPAE_S2] = &io_pgtable_arm_32_lpae_s2_init_fns, + [ARM_64_LPAE_S1] = &io_pgtable_arm_64_lpae_s1_init_fns, + [ARM_64_LPAE_S2] = &io_pgtable_arm_64_lpae_s2_init_fns, +#endif }; struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt, diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h index fdd792c..05c4e59 100644 --- a/drivers/iommu/io-pgtable.h +++ b/drivers/iommu/io-pgtable.h @@ -5,6 +5,10 @@ * Public API for use by IOMMU drivers */ enum io_pgtable_fmt { + ARM_32_LPAE_S1, + ARM_32_LPAE_S2, + ARM_64_LPAE_S1, + ARM_64_LPAE_S2, IO_PGTABLE_NUM_FMTS, }; @@ -47,6 +51,16 @@ struct io_pgtable_cfg { /* Low-level data specific to the table format */ union { + struct { + u64 ttbr[2]; + u64 tcr; + u64 mair[2]; + } arm_lpae_s1_cfg; + + struct { + u64 vttbr; + u64 vtcr; + } arm_lpae_s2_cfg; }; }; |