diff options
Diffstat (limited to 'drivers/iommu/io-pgtable-arm.c')
| -rw-r--r-- | drivers/iommu/io-pgtable-arm.c | 514 |
1 files changed, 335 insertions, 179 deletions
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index f7828a7aad41..96425e92f313 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -13,6 +13,7 @@ #include <linux/bitops.h> #include <linux/io-pgtable.h> #include <linux/kernel.h> +#include <linux/device/faux.h> #include <linux/sizes.h> #include <linux/slab.h> #include <linux/types.h> @@ -21,6 +22,7 @@ #include <asm/barrier.h> #include "io-pgtable-arm.h" +#include "iommu-pages.h" #define ARM_LPAE_MAX_ADDR_BITS 52 #define ARM_LPAE_S2_MAX_CONCAT_PAGES 16 @@ -75,6 +77,7 @@ #define ARM_LPAE_PTE_NSTABLE (((arm_lpae_iopte)1) << 63) #define ARM_LPAE_PTE_XN (((arm_lpae_iopte)3) << 53) +#define ARM_LPAE_PTE_DBM (((arm_lpae_iopte)1) << 51) #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) @@ -84,7 +87,7 @@ #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_HI_MASK (ARM_LPAE_PTE_XN | ARM_LPAE_PTE_DBM) #define ARM_LPAE_PTE_ATTR_MASK (ARM_LPAE_PTE_ATTR_LO_MASK | \ ARM_LPAE_PTE_ATTR_HI_MASK) /* Software bit for solving coherency races */ @@ -92,7 +95,11 @@ /* 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_AP_RDONLY_BIT 7 +#define ARM_LPAE_PTE_AP_RDONLY (((arm_lpae_iopte)1) << \ + ARM_LPAE_PTE_AP_RDONLY_BIT) +#define ARM_LPAE_PTE_AP_WR_CLEAN_MASK (ARM_LPAE_PTE_AP_RDONLY | \ + ARM_LPAE_PTE_DBM) #define ARM_LPAE_PTE_ATTRINDX_SHIFT 2 #define ARM_LPAE_PTE_nG (((arm_lpae_iopte)1) << 11) @@ -100,6 +107,18 @@ #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) +/* + * For !FWB these code to: + * 1111 = Normal outer write back cachable / Inner Write Back Cachable + * Permit S1 to override + * 0101 = Normal Non-cachable / Inner Non-cachable + * 0001 = Device / Device-nGnRE + * For S2FWB these code: + * 0110 Force Normal Write Back + * 0101 Normal* is forced Normal-NC, Device unchanged + * 0001 Force Device-nGnRE + */ +#define ARM_LPAE_PTE_MEMATTR_FWB_WB (((arm_lpae_iopte)0x6) << 2) #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) @@ -138,6 +157,12 @@ #define iopte_prot(pte) ((pte) & ARM_LPAE_PTE_ATTR_MASK) +#define iopte_writeable_dirty(pte) \ + (((pte) & ARM_LPAE_PTE_AP_WR_CLEAN_MASK) == ARM_LPAE_PTE_DBM) + +#define iopte_set_writeable_clean(ptep) \ + set_bit(ARM_LPAE_PTE_AP_RDONLY_BIT, (unsigned long *)(ptep)) + struct arm_lpae_io_pgtable { struct io_pgtable iop; @@ -159,6 +184,13 @@ static inline bool iopte_leaf(arm_lpae_iopte pte, int lvl, return iopte_type(pte) == ARM_LPAE_PTE_TYPE_BLOCK; } +static inline bool iopte_table(arm_lpae_iopte pte, int lvl) +{ + if (lvl == (ARM_LPAE_MAX_LEVELS - 1)) + return false; + return iopte_type(pte) == ARM_LPAE_PTE_TYPE_TABLE; +} + static arm_lpae_iopte paddr_to_iopte(phys_addr_t paddr, struct arm_lpae_io_pgtable *data) { @@ -180,7 +212,45 @@ static phys_addr_t iopte_to_paddr(arm_lpae_iopte pte, return (paddr | (paddr << (48 - 12))) & (ARM_LPAE_PTE_ADDR_MASK << 4); } -static bool selftest_running = false; +/* + * Convert an index returned by ARM_LPAE_PGD_IDX(), which can point into + * a concatenated PGD, into the maximum number of entries that can be + * mapped in the same table page. + */ +static inline int arm_lpae_max_entries(int i, struct arm_lpae_io_pgtable *data) +{ + int ptes_per_table = ARM_LPAE_PTES_PER_TABLE(data); + + return ptes_per_table - (i & (ptes_per_table - 1)); +} + +/* + * Check if concatenated PGDs are mandatory according to Arm DDI0487 (K.a) + * 1) R_DXBSH: For 16KB, and 48-bit input size, use level 1 instead of 0. + * 2) R_SRKBC: After de-ciphering the table for PA size and valid initial lookup + * a) 40 bits PA size with 4K: use level 1 instead of level 0 (2 tables for ias = oas) + * b) 40 bits PA size with 16K: use level 2 instead of level 1 (16 tables for ias = oas) + * c) 42 bits PA size with 4K: use level 1 instead of level 0 (8 tables for ias = oas) + * d) 48 bits PA size with 16K: use level 1 instead of level 0 (2 tables for ias = oas) + */ +static inline bool arm_lpae_concat_mandatory(struct io_pgtable_cfg *cfg, + struct arm_lpae_io_pgtable *data) +{ + unsigned int ias = cfg->ias; + unsigned int oas = cfg->oas; + + /* Covers 1 and 2.d */ + if ((ARM_LPAE_GRANULE(data) == SZ_16K) && (data->start_level == 0)) + return (oas == 48) || (ias == 48); + + /* Covers 2.a and 2.c */ + if ((ARM_LPAE_GRANULE(data) == SZ_4K) && (data->start_level == 0)) + return (oas == 40) || (oas == 42); + + /* Case 2.b */ + return (ARM_LPAE_GRANULE(data) == SZ_16K) && + (data->start_level == 1) && (oas == 40); +} static dma_addr_t __arm_lpae_dma_addr(void *pages) { @@ -192,20 +262,20 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp, void *cookie) { struct device *dev = cfg->iommu_dev; - int order = get_order(size); + size_t alloc_size; dma_addr_t dma; void *pages; - VM_BUG_ON((gfp & __GFP_HIGHMEM)); - - if (cfg->alloc) { - pages = cfg->alloc(cookie, size, gfp); - } else { - struct page *p; - - p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order); - pages = p ? page_address(p) : NULL; - } + /* + * For very small starting-level translation tables the HW requires a + * minimum alignment of at least 64 to cover all cases. + */ + alloc_size = max(size, 64); + if (cfg->alloc) + pages = cfg->alloc(cookie, alloc_size, gfp); + else + pages = iommu_alloc_pages_node_sz(dev_to_node(dev), gfp, + alloc_size); if (!pages) return NULL; @@ -233,7 +303,7 @@ out_free: if (cfg->free) cfg->free(cookie, pages, size); else - free_pages((unsigned long)pages, order); + iommu_free_pages(pages); return NULL; } @@ -249,7 +319,7 @@ static void __arm_lpae_free_pages(void *pages, size_t size, if (cfg->free) cfg->free(cookie, pages, size); else - free_pages((unsigned long)pages, get_order(size)); + iommu_free_pages(pages); } static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries, @@ -259,13 +329,13 @@ static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries, sizeof(*ptep) * num_entries, DMA_TO_DEVICE); } -static void __arm_lpae_clear_pte(arm_lpae_iopte *ptep, struct io_pgtable_cfg *cfg) +static void __arm_lpae_clear_pte(arm_lpae_iopte *ptep, struct io_pgtable_cfg *cfg, int num_entries) { + for (int i = 0; i < num_entries; i++) + ptep[i] = 0; - *ptep = 0; - - if (!cfg->coherent_walk) - __arm_lpae_sync_pte(ptep, 1, cfg); + if (!cfg->coherent_walk && num_entries) + __arm_lpae_sync_pte(ptep, num_entries, cfg); } static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, @@ -304,7 +374,7 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, for (i = 0; i < num_entries; i++) if (iopte_leaf(ptep[i], lvl, data->iop.fmt)) { /* We require an unmap first */ - WARN_ON(!selftest_running); + WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN)); return -EEXIST; } else if (iopte_type(ptep[i]) == ARM_LPAE_PTE_TYPE_TABLE) { /* @@ -375,7 +445,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, /* If we can install a leaf entry at this level, then do so */ if (size == block_size) { - max_entries = ARM_LPAE_PTES_PER_TABLE(data) - map_idx_start; + max_entries = arm_lpae_max_entries(map_idx_start, data); num_entries = min_t(int, pgcount, max_entries); ret = arm_lpae_init_pte(data, iova, paddr, prot, lvl, num_entries, ptep); if (!ret) @@ -406,7 +476,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, cptep = iopte_deref(pte, data); } else if (pte) { /* We require an unmap first */ - WARN_ON(!selftest_running); + WARN_ON(!(cfg->quirks & IO_PGTABLE_QUIRK_NO_WARN)); return -EEXIST; } @@ -425,6 +495,8 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, pte = ARM_LPAE_PTE_nG; if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ)) pte |= ARM_LPAE_PTE_AP_RDONLY; + else if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_HD) + pte |= ARM_LPAE_PTE_DBM; if (!(prot & IOMMU_PRIV)) pte |= ARM_LPAE_PTE_AP_UNPRIV; } else { @@ -441,12 +513,16 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, */ if (data->iop.fmt == ARM_64_LPAE_S2 || data->iop.fmt == ARM_32_LPAE_S2) { - if (prot & IOMMU_MMIO) + if (prot & IOMMU_MMIO) { pte |= ARM_LPAE_PTE_MEMATTR_DEV; - else if (prot & IOMMU_CACHE) - pte |= ARM_LPAE_PTE_MEMATTR_OIWB; - else + } else if (prot & IOMMU_CACHE) { + if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_S2FWB) + pte |= ARM_LPAE_PTE_MEMATTR_FWB_WB; + else + pte |= ARM_LPAE_PTE_MEMATTR_OIWB; + } else { pte |= ARM_LPAE_PTE_MEMATTR_NC; + } } else { if (prot & IOMMU_MMIO) pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV @@ -498,9 +574,8 @@ static int arm_lpae_map_pages(struct io_pgtable_ops *ops, unsigned long iova, if (WARN_ON(iaext || paddr >> cfg->oas)) return -ERANGE; - /* If no access, then nothing to do */ if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE))) - return 0; + return -EINVAL; prot = arm_lpae_prot_to_pte(data, iommu_prot); ret = __arm_lpae_map(data, iova, paddr, pgsize, pgcount, prot, lvl, @@ -553,66 +628,6 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop) kfree(data); } -static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, - struct iommu_iotlb_gather *gather, - unsigned long iova, size_t size, - arm_lpae_iopte blk_pte, int lvl, - arm_lpae_iopte *ptep, size_t pgcount) -{ - struct io_pgtable_cfg *cfg = &data->iop.cfg; - arm_lpae_iopte pte, *tablep; - phys_addr_t blk_paddr; - size_t tablesz = ARM_LPAE_GRANULE(data); - size_t split_sz = ARM_LPAE_BLOCK_SIZE(lvl, data); - int ptes_per_table = ARM_LPAE_PTES_PER_TABLE(data); - int i, unmap_idx_start = -1, num_entries = 0, max_entries; - - if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) - return 0; - - tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg, data->iop.cookie); - if (!tablep) - return 0; /* Bytes unmapped */ - - if (size == split_sz) { - unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data); - max_entries = ptes_per_table - unmap_idx_start; - num_entries = min_t(int, pgcount, max_entries); - } - - blk_paddr = iopte_to_paddr(blk_pte, data); - pte = iopte_prot(blk_pte); - - for (i = 0; i < ptes_per_table; i++, blk_paddr += split_sz) { - /* Unmap! */ - if (i >= unmap_idx_start && i < (unmap_idx_start + num_entries)) - continue; - - __arm_lpae_init_pte(data, blk_paddr, pte, lvl, 1, &tablep[i]); - } - - pte = arm_lpae_install_table(tablep, ptep, blk_pte, data); - if (pte != blk_pte) { - __arm_lpae_free_pages(tablep, tablesz, cfg, data->iop.cookie); - /* - * We may race against someone unmapping another part of this - * block, but anything else is invalid. We can't misinterpret - * a page entry here since we're never at the last level. - */ - if (iopte_type(pte) != ARM_LPAE_PTE_TYPE_TABLE) - return 0; - - tablep = iopte_deref(pte, data); - } else if (unmap_idx_start >= 0) { - for (i = 0; i < num_entries; i++) - io_pgtable_tlb_add_page(&data->iop, gather, iova + i * size, size); - - return num_entries * size; - } - - return __arm_lpae_unmap(data, gather, iova, size, pgcount, lvl, tablep); -} - static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, struct iommu_iotlb_gather *gather, unsigned long iova, size_t size, size_t pgcount, @@ -629,42 +644,45 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data); ptep += unmap_idx_start; pte = READ_ONCE(*ptep); - if (WARN_ON(!pte)) - return 0; + if (!pte) { + WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN)); + return -ENOENT; + } /* If the size matches this level, we're in the right place */ if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) { - max_entries = ARM_LPAE_PTES_PER_TABLE(data) - unmap_idx_start; + max_entries = arm_lpae_max_entries(unmap_idx_start, data); num_entries = min_t(int, pgcount, max_entries); - while (i < num_entries) { - pte = READ_ONCE(*ptep); - if (WARN_ON(!pte)) + /* Find and handle non-leaf entries */ + for (i = 0; i < num_entries; i++) { + pte = READ_ONCE(ptep[i]); + if (!pte) { + WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN)); break; - - __arm_lpae_clear_pte(ptep, &iop->cfg); + } if (!iopte_leaf(pte, lvl, iop->fmt)) { + __arm_lpae_clear_pte(&ptep[i], &iop->cfg, 1); + /* Also flush any partial walks */ io_pgtable_tlb_flush_walk(iop, iova + i * size, size, ARM_LPAE_GRANULE(data)); __arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data)); - } else if (!iommu_iotlb_gather_queued(gather)) { - io_pgtable_tlb_add_page(iop, gather, iova + i * size, size); } - - ptep++; - i++; } + /* Clear the remaining entries */ + __arm_lpae_clear_pte(ptep, &iop->cfg, i); + + if (gather && !iommu_iotlb_gather_queued(gather)) + for (int j = 0; j < i; j++) + io_pgtable_tlb_add_page(iop, gather, iova + j * size, size); + return i * size; } else if (iopte_leaf(pte, lvl, iop->fmt)) { - /* - * 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, gather, iova, size, pte, - lvl + 1, ptep, pgcount); + WARN_ONCE(true, "Unmap of a partial large IOPTE is not allowed"); + return 0; } /* Keep on walkin' */ @@ -693,40 +711,172 @@ static size_t arm_lpae_unmap_pages(struct io_pgtable_ops *ops, unsigned long iov data->start_level, ptep); } +struct io_pgtable_walk_data { + struct io_pgtable *iop; + void *data; + int (*visit)(struct io_pgtable_walk_data *walk_data, int lvl, + arm_lpae_iopte *ptep, size_t size); + unsigned long flags; + u64 addr; + const u64 end; +}; + +static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data, + struct io_pgtable_walk_data *walk_data, + arm_lpae_iopte *ptep, + int lvl); + +struct iova_to_phys_data { + arm_lpae_iopte pte; + int lvl; +}; + +static int visit_iova_to_phys(struct io_pgtable_walk_data *walk_data, int lvl, + arm_lpae_iopte *ptep, size_t size) +{ + struct iova_to_phys_data *data = walk_data->data; + data->pte = *ptep; + data->lvl = lvl; + return 0; +} + 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 = data->start_level; + struct iova_to_phys_data d; + struct io_pgtable_walk_data walk_data = { + .data = &d, + .visit = visit_iova_to_phys, + .addr = iova, + .end = iova + 1, + }; + int ret; + + ret = __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level); + if (ret) + return 0; + + iova &= (ARM_LPAE_BLOCK_SIZE(d.lvl, data) - 1); + return iopte_to_paddr(d.pte, data) | iova; +} + +static int visit_pgtable_walk(struct io_pgtable_walk_data *walk_data, int lvl, + arm_lpae_iopte *ptep, size_t size) +{ + struct arm_lpae_io_pgtable_walk_data *data = walk_data->data; + data->ptes[lvl] = *ptep; + return 0; +} + +static int arm_lpae_pgtable_walk(struct io_pgtable_ops *ops, unsigned long iova, + void *wd) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + struct io_pgtable_walk_data walk_data = { + .data = wd, + .visit = visit_pgtable_walk, + .addr = iova, + .end = iova + 1, + }; + + return __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level); +} + +static int io_pgtable_visit(struct arm_lpae_io_pgtable *data, + struct io_pgtable_walk_data *walk_data, + arm_lpae_iopte *ptep, int lvl) +{ + struct io_pgtable *iop = &data->iop; + arm_lpae_iopte pte = READ_ONCE(*ptep); + + size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data); + int ret = walk_data->visit(walk_data, lvl, ptep, size); + if (ret) + return ret; + + if (iopte_leaf(pte, lvl, iop->fmt)) { + walk_data->addr += size; + return 0; + } + + if (!iopte_table(pte, lvl)) { + return -EINVAL; + } + + ptep = iopte_deref(pte, data); + return __arm_lpae_iopte_walk(data, walk_data, ptep, lvl + 1); +} + +static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data, + struct io_pgtable_walk_data *walk_data, + arm_lpae_iopte *ptep, + int lvl) +{ + u32 idx; + int max_entries, ret; + + if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) + return -EINVAL; + + if (lvl == data->start_level) + max_entries = ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte); + else + max_entries = ARM_LPAE_PTES_PER_TABLE(data); - do { - /* Valid IOPTE pointer? */ - if (!ptep) - return 0; + for (idx = ARM_LPAE_LVL_IDX(walk_data->addr, lvl, data); + (idx < max_entries) && (walk_data->addr < walk_data->end); ++idx) { + ret = io_pgtable_visit(data, walk_data, ptep + idx, lvl); + if (ret) + return ret; + } - /* Grab the IOPTE we're interested in */ - ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); - pte = READ_ONCE(*ptep); + return 0; +} - /* Valid entry? */ - if (!pte) - return 0; +static int visit_dirty(struct io_pgtable_walk_data *walk_data, int lvl, + arm_lpae_iopte *ptep, size_t size) +{ + struct iommu_dirty_bitmap *dirty = walk_data->data; - /* Leaf entry? */ - if (iopte_leaf(pte, lvl, data->iop.fmt)) - goto found_translation; + if (!iopte_leaf(*ptep, lvl, walk_data->iop->fmt)) + return 0; - /* Take it to the next level */ - ptep = iopte_deref(pte, data); - } while (++lvl < ARM_LPAE_MAX_LEVELS); + if (iopte_writeable_dirty(*ptep)) { + iommu_dirty_bitmap_record(dirty, walk_data->addr, size); + if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR)) + iopte_set_writeable_clean(ptep); + } - /* Ran out of page tables to walk */ return 0; +} -found_translation: - iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1); - return iopte_to_paddr(pte, data) | iova; +static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops, + unsigned long iova, size_t size, + unsigned long flags, + struct iommu_dirty_bitmap *dirty) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + struct io_pgtable_cfg *cfg = &data->iop.cfg; + struct io_pgtable_walk_data walk_data = { + .iop = &data->iop, + .data = dirty, + .visit = visit_dirty, + .flags = flags, + .addr = iova, + .end = iova + size, + }; + arm_lpae_iopte *ptep = data->pgd; + int lvl = data->start_level; + + if (WARN_ON(!size)) + return -EINVAL; + if (WARN_ON((iova + size - 1) & ~(BIT(cfg->ias) - 1))) + return -EINVAL; + if (data->iop.fmt != ARM_64_LPAE_S1) + return -EINVAL; + + return __arm_lpae_iopte_walk(data, &walk_data, ptep, lvl); } static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) @@ -807,6 +957,8 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg) .map_pages = arm_lpae_map_pages, .unmap_pages = arm_lpae_unmap_pages, .iova_to_phys = arm_lpae_iova_to_phys, + .read_and_clear_dirty = arm_lpae_read_and_clear_dirty, + .pgtable_walk = arm_lpae_pgtable_walk, }; return data; @@ -822,7 +974,9 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_ARM_TTBR1 | - IO_PGTABLE_QUIRK_ARM_OUTER_WBWA)) + IO_PGTABLE_QUIRK_ARM_OUTER_WBWA | + IO_PGTABLE_QUIRK_ARM_HD | + IO_PGTABLE_QUIRK_NO_WARN)) return NULL; data = arm_lpae_alloc_pgtable(cfg); @@ -923,26 +1077,20 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) struct arm_lpae_io_pgtable *data; typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr; - /* The NS quirk doesn't apply at stage 2 */ - if (cfg->quirks) + if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_S2FWB | + IO_PGTABLE_QUIRK_NO_WARN)) return NULL; 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->start_level == 0) { - unsigned long pgd_pages; - - pgd_pages = ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte); - if (pgd_pages <= ARM_LPAE_S2_MAX_CONCAT_PAGES) { - data->pgd_bits += data->bits_per_level; - data->start_level++; - } + if (arm_lpae_concat_mandatory(cfg, data)) { + if (WARN_ON((ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte)) > + ARM_LPAE_S2_MAX_CONCAT_PAGES)) + return NULL; + data->pgd_bits += data->bits_per_level; + data->start_level++; } /* VTCR */ @@ -1171,7 +1319,6 @@ static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops) #define __FAIL(ops, i) ({ \ WARN(1, "selftest: test failed for fmt idx %d\n", (i)); \ arm_lpae_dump_ops(ops); \ - selftest_running = false; \ -EFAULT; \ }) @@ -1187,8 +1334,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) size_t size, mapped; struct io_pgtable_ops *ops; - selftest_running = true; - for (i = 0; i < ARRAY_SIZE(fmts); ++i) { cfg_cookie = cfg; ops = alloc_io_pgtable_ops(fmts[i], cfg, cfg); @@ -1235,19 +1380,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) iova += SZ_1G; } - /* Partial unmap */ - size = 1UL << __ffs(cfg->pgsize_bitmap); - if (ops->unmap_pages(ops, SZ_1G + size, size, 1, NULL) != size) - return __FAIL(ops, i); - - /* Remap of partial unmap */ - if (ops->map_pages(ops, SZ_1G + size, size, size, 1, - IOMMU_READ, GFP_KERNEL, &mapped)) - return __FAIL(ops, i); - - if (ops->iova_to_phys(ops, SZ_1G + size + 42) != (size + 42)) - return __FAIL(ops, i); - /* Full unmap */ iova = 0; for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) { @@ -1270,10 +1402,26 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) iova += SZ_1G; } + /* + * Map/unmap the last largest supported page of the IAS, this can + * trigger corner cases in the concatednated page tables. + */ + mapped = 0; + size = 1UL << __fls(cfg->pgsize_bitmap); + iova = (1UL << cfg->ias) - size; + if (ops->map_pages(ops, iova, iova, size, 1, + IOMMU_READ | IOMMU_WRITE | + IOMMU_NOEXEC | IOMMU_CACHE, + GFP_KERNEL, &mapped)) + return __FAIL(ops, i); + if (mapped != size) + return __FAIL(ops, i); + if (ops->unmap_pages(ops, iova, size, 1, NULL) != size) + return __FAIL(ops, i); + free_io_pgtable_ops(ops); } - selftest_running = false; return 0; } @@ -1285,36 +1433,44 @@ static int __init arm_lpae_do_selftests(void) SZ_64K | SZ_512M, }; - static const unsigned int ias[] __initconst = { + static const unsigned int address_size[] __initconst = { 32, 36, 40, 42, 44, 48, }; - int i, j, pass = 0, fail = 0; - struct device dev; + int i, j, k, pass = 0, fail = 0; + struct faux_device *dev; struct io_pgtable_cfg cfg = { .tlb = &dummy_tlb_ops, - .oas = 48, .coherent_walk = true, - .iommu_dev = &dev, + .quirks = IO_PGTABLE_QUIRK_NO_WARN, }; - /* __arm_lpae_alloc_pages() merely needs dev_to_node() to work */ - set_dev_node(&dev, NUMA_NO_NODE); + dev = faux_device_create("io-pgtable-test", NULL, 0); + if (!dev) + return -ENOMEM; + + cfg.iommu_dev = &dev->dev; for (i = 0; i < ARRAY_SIZE(pgsize); ++i) { - for (j = 0; j < ARRAY_SIZE(ias); ++j) { - cfg.pgsize_bitmap = pgsize[i]; - cfg.ias = ias[j]; - pr_info("selftest: pgsize_bitmap 0x%08lx, IAS %u\n", - pgsize[i], ias[j]); - if (arm_lpae_run_tests(&cfg)) - fail++; - else - pass++; + for (j = 0; j < ARRAY_SIZE(address_size); ++j) { + /* Don't use ias > oas as it is not valid for stage-2. */ + for (k = 0; k <= j; ++k) { + cfg.pgsize_bitmap = pgsize[i]; + cfg.ias = address_size[k]; + cfg.oas = address_size[j]; + pr_info("selftest: pgsize_bitmap 0x%08lx, IAS %u OAS %u\n", + pgsize[i], cfg.ias, cfg.oas); + if (arm_lpae_run_tests(&cfg)) + fail++; + else + pass++; + } } } pr_info("selftest: completed with %d PASS %d FAIL\n", pass, fail); + faux_device_destroy(dev); + return fail ? -EFAULT : 0; } subsys_initcall(arm_lpae_do_selftests); |