From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

These features are essential to support dirty log tracking for SMMU with io-pgtable mapping.

The dirty state information is encoded using the access permission bits AP[2] (stage 1) or S2AP[1] (stage 2) in conjunction with the DBM (Dirty Bit Modifier) bit, where DBM means writable and AP[2]/ S2AP[1] means dirty.

When has ARM_HD, we set DBM bit for S1 mapping. As SMMU nested mode is not upstreamed for now, we just aim to support dirty log tracking for stage1 with io-pgtable mapping (means not support SVA).

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/io-pgtable-arm.c | 8 +++++++- include/linux/io-pgtable.h | 11 +++++++++++ 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 72dcdd468cf3..5c4033ada65a 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -75,6 +75,7 @@

#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 +85,7 @@

#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_iopte)13) << 51) #define ARM_LPAE_PTE_ATTR_MASK (ARM_LPAE_PTE_ATTR_LO_MASK | \ ARM_LPAE_PTE_ATTR_HI_MASK) /* Software bit for solving coherency races */ @@ -400,6 +401,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, int prot) { + struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_lpae_iopte pte;

if (data->iop.fmt == ARM_64_LPAE_S1 || @@ -407,6 +409,10 @@ 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.fmt == ARM_64_LPAE_S1 && + cfg->quirks & IO_PGTABLE_QUIRK_ARM_HD) + pte |= ARM_LPAE_PTE_DBM; + if (!(prot & IOMMU_PRIV)) pte |= ARM_LPAE_PTE_AP_UNPRIV; } else { diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 1b7a44b35616..84b39e820d0e 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -85,6 +85,14 @@ struct io_pgtable_cfg { * * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability * attributes set in the TCR for a non-coherent page-table walker. + * + * IO_PGTABLE_QUIRK_ARM_HD: Support hardware management of dirty status. + * + * IO_PGTABLE_QUIRK_ARM_BBML1: ARM SMMU supports BBM Level 1 behavior + * when changing block size. + * + * IO_PGTABLE_QUIRK_ARM_BBML2: ARM SMMU supports BBM Level 2 behavior + * when changing block size. */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) @@ -92,6 +100,9 @@ struct io_pgtable_cfg { #define IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT BIT(4) #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) + #define IO_PGTABLE_QUIRK_ARM_HD BIT(7) + #define IO_PGTABLE_QUIRK_ARM_BBML1 BIT(8) + #define IO_PGTABLE_QUIRK_ARM_BBML2 BIT(9) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias;

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

Block(largepage) mapping is not a proper granule for dirty log tracking. Take an extreme example, if DMA writes one byte, under 1G mapping, the dirty amount reported is 1G, but under 4K mapping, the dirty amount is just 4K.

This splits block descriptor to an span of page descriptors. BBML1 or BBML2 feature is required.

Spliting block is designed to be only used by dirty log tracking, which does not concurrently work with other pgtable ops that access underlying page table, so race condition does not exist.

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/io-pgtable-arm.c | 122 +++++++++++++++++++++++++++++++++ include/linux/io-pgtable.h | 2 + 2 files changed, 124 insertions(+)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 825ac51a5559..89a73ef4b41e 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -82,6 +82,8 @@ #define ARM_LPAE_PTE_SH_IS (((arm_lpae_iopte)3) << 8) #define ARM_LPAE_PTE_NS (((arm_lpae_iopte)1) << 5) #define ARM_LPAE_PTE_VALID (((arm_lpae_iopte)1) << 0) +/* Block descriptor bits */ +#define ARM_LPAE_PTE_NT (((arm_lpae_iopte)1) << 16)

#define ARM_LPAE_PTE_ATTR_LO_MASK (((arm_lpae_iopte)0x3ff) << 2) /* Ignore the contiguous bit for block splitting */ @@ -717,6 +719,125 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, return iopte_to_paddr(pte, data) | iova; }

+static size_t __arm_lpae_split_block(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_lpae_iopte *ptep); + +static size_t arm_lpae_do_split_blk(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, + arm_lpae_iopte blk_pte, int lvl, + arm_lpae_iopte *ptep) +{ + 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 i; + + if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) + return 0; + + tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg); + if (!tablep) + return 0; + + blk_paddr = iopte_to_paddr(blk_pte, data); + pte = iopte_prot(blk_pte); + for (i = 0; i < tablesz / sizeof(pte); i++, blk_paddr += split_sz) + __arm_lpae_init_pte(data, blk_paddr, pte, lvl, &tablep[i]); + + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_BBML1) { + /* Race does not exist */ + blk_pte |= ARM_LPAE_PTE_NT; + __arm_lpae_set_pte(ptep, blk_pte, cfg); + io_pgtable_tlb_flush_walk(&data->iop, iova, size, size); + } + /* Race does not exist */ + pte = arm_lpae_install_table(tablep, ptep, blk_pte, cfg); + + /* Have splited it into page? */ + if (lvl == (ARM_LPAE_MAX_LEVELS - 1)) + return size; + + /* Go back to lvl - 1 */ + ptep -= ARM_LPAE_LVL_IDX(iova, lvl - 1, data); + return __arm_lpae_split_block(data, iova, size, lvl - 1, ptep); +} + +static size_t __arm_lpae_split_block(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_lpae_iopte *ptep) +{ + arm_lpae_iopte pte; + struct io_pgtable *iop = &data->iop; + size_t base, next_size, total_size; + + if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) + return 0; + + ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); + pte = READ_ONCE(*ptep); + if (WARN_ON(!pte)) + return 0; + + if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) { + if (iopte_leaf(pte, lvl, iop->fmt)) { + if (lvl == (ARM_LPAE_MAX_LEVELS - 1) || + (pte & ARM_LPAE_PTE_AP_RDONLY)) + return size; + + /* We find a writable block, split it. */ + return arm_lpae_do_split_blk(data, iova, size, pte, + lvl + 1, ptep); + } else { + /* If it is the last table level, then nothing to do */ + if (lvl == (ARM_LPAE_MAX_LEVELS - 2)) + return size; + + total_size = 0; + next_size = ARM_LPAE_BLOCK_SIZE(lvl + 1, data); + ptep = iopte_deref(pte, data); + for (base = 0; base < size; base += next_size) + total_size += __arm_lpae_split_block(data, + iova + base, next_size, lvl + 1, + ptep); + return total_size; + } + } else if (iopte_leaf(pte, lvl, iop->fmt)) { + WARN(1, "Can't split behind a block.\n"); + return 0; + } + + /* Keep on walkin */ + ptep = iopte_deref(pte, data); + return __arm_lpae_split_block(data, iova, size, lvl + 1, ptep); +} + +static size_t arm_lpae_split_block(struct io_pgtable_ops *ops, + unsigned long iova, size_t size) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + struct io_pgtable_cfg *cfg = &data->iop.cfg; + arm_lpae_iopte *ptep = data->pgd; + int lvl = data->start_level; + long iaext = (s64)iova >> cfg->ias; + + if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size)) + return 0; + + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) + iaext = ~iaext; + if (WARN_ON(iaext)) + return 0; + + /* If it is smallest granule, then nothing to do */ + if (size == ARM_LPAE_BLOCK_SIZE(ARM_LPAE_MAX_LEVELS - 1, data)) + return size; + + return __arm_lpae_split_block(data, iova, size, lvl, ptep); +} + static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) { unsigned long granule, page_sizes; @@ -795,6 +916,7 @@ 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, + .split_block = arm_lpae_split_block, };

return data; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 84b39e820d0e..388f0a281de4 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -177,6 +177,8 @@ struct io_pgtable_ops { struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); + size_t (*split_block)(struct io_pgtable_ops *ops, unsigned long iova, + size_t size); };

/**

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

If block(largepage) mappings are split during start dirty log, then when stop dirty log, we need to recover them for better DMA performance.

This recovers block mappings and unmap the span of page mappings. BBML1 or BBML2 feature is required.

Merging page is designed to be only used by dirty log tracking, which does not concurrently work with other pgtable ops that access underlying page table, so race condition does not exist.

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/io-pgtable-arm.c | 78 ++++++++++++++++++++++++++++++++++ include/linux/io-pgtable.h | 2 + 2 files changed, 80 insertions(+)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index d220642b2645..8b4ce1a6b511 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -838,6 +838,83 @@ static size_t arm_lpae_split_block(struct io_pgtable_ops *ops, return __arm_lpae_split_block(data, iova, size, lvl, ptep); }

+static size_t __arm_lpae_merge_page(struct arm_lpae_io_pgtable *data, + unsigned long iova, phys_addr_t paddr, + size_t size, int lvl, arm_lpae_iopte *ptep, + arm_lpae_iopte prot) +{ + arm_lpae_iopte pte, *tablep; + struct io_pgtable *iop = &data->iop; + struct io_pgtable_cfg *cfg = &data->iop.cfg; + + if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) + return 0; + + ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); + pte = READ_ONCE(*ptep); + if (WARN_ON(!pte)) + return 0; + + if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) { + if (iopte_leaf(pte, lvl, iop->fmt)) + return size; + + /* Race does not exist */ + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_BBML1) { + prot |= ARM_LPAE_PTE_NT; + __arm_lpae_init_pte(data, paddr, prot, lvl, ptep); + io_pgtable_tlb_flush_walk(iop, iova, size, + ARM_LPAE_GRANULE(data)); + + prot &= ~(ARM_LPAE_PTE_NT); + __arm_lpae_init_pte(data, paddr, prot, lvl, ptep); + } else { + __arm_lpae_init_pte(data, paddr, prot, lvl, ptep); + } + + tablep = iopte_deref(pte, data); + __arm_lpae_free_pgtable(data, lvl + 1, tablep); + return size; + } else if (iopte_leaf(pte, lvl, iop->fmt)) { + /* The size is too small, already merged */ + return size; + } + + /* Keep on walkin */ + ptep = iopte_deref(pte, data); + return __arm_lpae_merge_page(data, iova, paddr, size, lvl + 1, ptep, prot); +} + +static size_t arm_lpae_merge_page(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); + struct io_pgtable_cfg *cfg = &data->iop.cfg; + arm_lpae_iopte *ptep = data->pgd; + int lvl = data->start_level; + arm_lpae_iopte prot; + long iaext = (s64)iova >> cfg->ias; + + if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size)) + return 0; + + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) + iaext = ~iaext; + if (WARN_ON(iaext || paddr >> cfg->oas)) + return 0; + + /* If no access, then nothing to do */ + if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE))) + return size; + + /* If it is smallest granule, then nothing to do */ + if (size == ARM_LPAE_BLOCK_SIZE(ARM_LPAE_MAX_LEVELS - 1, data)) + return size; + + prot = arm_lpae_prot_to_pte(data, iommu_prot); + return __arm_lpae_merge_page(data, iova, paddr, size, lvl, ptep, prot); +} + static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) { unsigned long granule, page_sizes; @@ -917,6 +994,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg) .unmap_pages = arm_lpae_unmap_pages, .iova_to_phys = arm_lpae_iova_to_phys, .split_block = arm_lpae_split_block, + .merge_page = arm_lpae_merge_page, };

return data; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 388f0a281de4..9f8c80cda0ed 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -179,6 +179,8 @@ struct io_pgtable_ops { unsigned long iova); size_t (*split_block)(struct io_pgtable_ops *ops, unsigned long iova, size_t size); + size_t (*merge_page)(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t phys, size_t size, int prot); };

/**

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

During dirty log tracking, user will try to retrieve dirty log from iommu if it supports hardware dirty log. Scan leaf TTD and treat it is dirty if it's writable. As we just set DBM bit for stage1 mapping, so check whether AP[2] is not set.

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/io-pgtable-arm.c | 89 ++++++++++++++++++++++++++++++++++ include/linux/io-pgtable.h | 4 ++ 2 files changed, 93 insertions(+)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 2967d9f836a6..95a99c01794c 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -915,6 +915,94 @@ static size_t arm_lpae_merge_page(struct io_pgtable_ops *ops, unsigned long iova return __arm_lpae_merge_page(data, iova, paddr, size, lvl, ptep, prot); }

+static int __arm_lpae_sync_dirty_log(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, + int lvl, arm_lpae_iopte *ptep, + unsigned long *bitmap, + unsigned long base_iova, + unsigned long bitmap_pgshift) +{ + arm_lpae_iopte pte; + struct io_pgtable *iop = &data->iop; + size_t base, next_size; + unsigned long offset; + int nbits, ret; + + if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) + return -EINVAL; + + ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); + pte = READ_ONCE(*ptep); + if (WARN_ON(!pte)) + return -EINVAL; + + if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) { + if (iopte_leaf(pte, lvl, iop->fmt)) { + if (pte & ARM_LPAE_PTE_AP_RDONLY) + return 0; + + /* It is writable, set the bitmap */ + nbits = size >> bitmap_pgshift; + offset = (iova - base_iova) >> bitmap_pgshift; + bitmap_set(bitmap, offset, nbits); + return 0; + } + /* Current level is table, traverse next level */ + next_size = ARM_LPAE_BLOCK_SIZE(lvl + 1, data); + ptep = iopte_deref(pte, data); + for (base = 0; base < size; base += next_size) { + ret = __arm_lpae_sync_dirty_log(data, iova + base, + next_size, lvl + 1, ptep, bitmap, + base_iova, bitmap_pgshift); + if (ret) + return ret; + } + return 0; + } else if (iopte_leaf(pte, lvl, iop->fmt)) { + if (pte & ARM_LPAE_PTE_AP_RDONLY) + return 0; + + /* Though the size is too small, also set bitmap */ + nbits = size >> bitmap_pgshift; + offset = (iova - base_iova) >> bitmap_pgshift; + bitmap_set(bitmap, offset, nbits); + return 0; + } + + /* Keep on walkin */ + ptep = iopte_deref(pte, data); + return __arm_lpae_sync_dirty_log(data, iova, size, lvl + 1, ptep, + bitmap, base_iova, bitmap_pgshift); +} + +static int arm_lpae_sync_dirty_log(struct io_pgtable_ops *ops, + unsigned long iova, size_t size, + unsigned long *bitmap, + unsigned long base_iova, + unsigned long bitmap_pgshift) +{ + struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); + struct io_pgtable_cfg *cfg = &data->iop.cfg; + arm_lpae_iopte *ptep = data->pgd; + int lvl = data->start_level; + long iaext = (s64)iova >> cfg->ias; + + if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size)) + return -EINVAL; + + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) + iaext = ~iaext; + if (WARN_ON(iaext)) + return -EINVAL; + + if (data->iop.fmt != ARM_64_LPAE_S1 && + data->iop.fmt != ARM_32_LPAE_S1) + return -EINVAL; + + return __arm_lpae_sync_dirty_log(data, iova, size, lvl, ptep, + bitmap, base_iova, bitmap_pgshift); +} + static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) { unsigned long granule, page_sizes; @@ -995,6 +1083,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg) .iova_to_phys = arm_lpae_iova_to_phys, .split_block = arm_lpae_split_block, .merge_page = arm_lpae_merge_page, + .sync_dirty_log = arm_lpae_sync_dirty_log, };

return data; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 9f8c80cda0ed..72eee0080e17 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -181,6 +181,10 @@ struct io_pgtable_ops { size_t size); size_t (*merge_page)(struct io_pgtable_ops *ops, unsigned long iova, phys_addr_t phys, size_t size, int prot); + int (*sync_dirty_log)(struct io_pgtable_ops *ops, + unsigned long iova, size_t size, + unsigned long *bitmap, unsigned long base_iova, + unsigned long bitmap_pgshift); };

/**

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

This detects BBML feature and if SMMU supports it, transfer BBMLx quirk to io-pgtable.

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 19 +++++++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 6 ++++++ 2 files changed, 25 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index d0422bb13724..4bad986cdd76 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2229,6 +2229,11 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain, .iommu_dev = smmu->dev, };

+ if (smmu->features & ARM_SMMU_FEAT_BBML1) + pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_BBML1; + else if (smmu->features & ARM_SMMU_FEAT_BBML2) + pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_BBML2; + pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain); if (!pgtbl_ops) return -ENOMEM; @@ -3681,6 +3686,20 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)

/* IDR3 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + switch (FIELD_GET(IDR3_BBML, reg)) { + case IDR3_BBML0: + break; + case IDR3_BBML1: + smmu->features |= ARM_SMMU_FEAT_BBML1; + break; + case IDR3_BBML2: + smmu->features |= ARM_SMMU_FEAT_BBML2; + break; + default: + dev_err(smmu->dev, "unknown/unsupported BBM behavior level\n"); + return -ENXIO; + } + if (FIELD_GET(IDR3_RIL, reg)) smmu->features |= ARM_SMMU_FEAT_RANGE_INV;

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 269b6fa705d4..44771da77816 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -51,6 +51,10 @@ #define IDR1_SIDSIZE GENMASK(5, 0)

#define ARM_SMMU_IDR3 0xc +#define IDR3_BBML GENMASK(12, 11) +#define IDR3_BBML0 0 +#define IDR3_BBML1 1 +#define IDR3_BBML2 2 #define IDR3_RIL (1 << 10)

#define ARM_SMMU_IDR5 0x14 @@ -646,6 +650,8 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_E2H (1 << 18) #define ARM_SMMU_FEAT_NESTING (1 << 19) +#define ARM_SMMU_FEAT_BBML1 (1 << 20) +#define ARM_SMMU_FEAT_BBML2 (1 << 21) u32 features;

#define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0)

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

This realizes switch_dirty_log. In order to get finer dirty granule, it invokes arm_smmu_split_block when start dirty log, and invokes arm_smmu_merge_page() to recover block mapping when stop dirty log.

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 142 ++++++++++++++++++++ drivers/iommu/iommu.c | 5 +- include/linux/iommu.h | 2 + 3 files changed, 147 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 4bad986cdd76..2c2726a53b9f 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2780,6 +2780,147 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain) return ret; }

+static int arm_smmu_split_block(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops; + size_t handled_size; + + if (!(smmu->features & (ARM_SMMU_FEAT_BBML1 | ARM_SMMU_FEAT_BBML2))) { + dev_err(smmu->dev, "don't support BBML1/2, can't split block\n"); + return -ENODEV; + } + if (!ops || !ops->split_block) { + pr_err("io-pgtable don't realize split block\n"); + return -ENODEV; + } + + handled_size = ops->split_block(ops, iova, size); + if (handled_size != size) { + pr_err("split block failed\n"); + return -EFAULT; + } + + return 0; +} + +static int __arm_smmu_merge_page(struct iommu_domain *domain, + unsigned long iova, phys_addr_t paddr, + size_t size, int prot) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops; + size_t handled_size; + + if (!ops || !ops->merge_page) { + pr_err("io-pgtable don't realize merge page\n"); + return -ENODEV; + } + + while (size) { + size_t pgsize = iommu_pgsize(domain, iova | paddr, size); + + handled_size = ops->merge_page(ops, iova, paddr, pgsize, prot); + if (handled_size != pgsize) { + pr_err("merge page failed\n"); + return -EFAULT; + } + + pr_debug("merge handled: iova 0x%lx pa %pa size 0x%zx\n", + iova, &paddr, pgsize); + + iova += pgsize; + paddr += pgsize; + size -= pgsize; + } + + return 0; +} + +static int arm_smmu_merge_page(struct iommu_domain *domain, unsigned long iova, + size_t size, int prot) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops; + phys_addr_t phys; + dma_addr_t p, i; + size_t cont_size; + int ret = 0; + + if (!(smmu->features & (ARM_SMMU_FEAT_BBML1 | ARM_SMMU_FEAT_BBML2))) { + dev_err(smmu->dev, "don't support BBML1/2, can't merge page\n"); + return -ENODEV; + } + + if (!ops || !ops->iova_to_phys) + return -ENODEV; + + while (size) { + phys = ops->iova_to_phys(ops, iova); + cont_size = PAGE_SIZE; + p = phys + cont_size; + i = iova + cont_size; + + while (cont_size < size && p == ops->iova_to_phys(ops, i)) { + p += PAGE_SIZE; + i += PAGE_SIZE; + cont_size += PAGE_SIZE; + } + + if (cont_size != PAGE_SIZE) { + ret = __arm_smmu_merge_page(domain, iova, phys, + cont_size, prot); + if (ret) + break; + } + + iova += cont_size; + size -= cont_size; + } + + return ret; +} + +static int arm_smmu_switch_dirty_log(struct iommu_domain *domain, bool enable, + unsigned long iova, size_t size, int prot) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct arm_smmu_device *smmu = smmu_domain->smmu; + + if (!(smmu->features & ARM_SMMU_FEAT_HD)) + return -ENODEV; + if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1) + return -EINVAL; + + if (enable) { + /* + * For SMMU, the hardware dirty management is always enabled if + * hardware supports HTTU HD. The action to start dirty log is + * spliting block mapping. + * + * We don't return error even if the split operation fail, as we + * can still track dirty at block granule, which is still a much + * better choice compared to full dirty policy. + */ + arm_smmu_split_block(domain, iova, size); + } else { + /* + * For SMMU, the hardware dirty management is always enabled if + * hardware supports HTTU HD. The action to stop dirty log is + * merging page mapping. + * + * We don't return error even if the merge operation fail, as it + * just effects performace of DMA transaction. + */ + arm_smmu_merge_page(domain, iova, size, prot); + } + + return 0; +} + static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args) { return iommu_fwspec_add_ids(dev, args->args, 1); @@ -2890,6 +3031,7 @@ static struct iommu_ops arm_smmu_ops = { .probe_device = arm_smmu_probe_device, .release_device = arm_smmu_release_device, .device_group = arm_smmu_device_group, + .switch_dirty_log = arm_smmu_switch_dirty_log, .of_xlate = arm_smmu_of_xlate, .get_resv_regions = arm_smmu_get_resv_regions, .remove_dev_pasid = arm_smmu_remove_dev_pasid, diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3a67e636287a..7b2dc57f738d 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2364,8 +2364,8 @@ phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) } EXPORT_SYMBOL_GPL(iommu_iova_to_phys);

-static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, size_t *count) +size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, size_t *count) { unsigned int pgsize_idx, pgsize_idx_next; unsigned long pgsizes; @@ -2417,6 +2417,7 @@ static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova, *count = size >> pgsize_idx; return pgsize; } +EXPORT_SYMBOL_GPL(iommu_pgsize);

static int __iommu_map_pages(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0225cf7445de..c484ceda2c70 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -475,6 +475,8 @@ extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); +extern size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, size_t *count); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

This realizes sync_dirty_log iommu ops based on sync_dirty_log io-pgtable ops.

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 30 +++++++++++++++++++++ 1 file changed, 30 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 8785b37c78c7..819b12dca934 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2921,6 +2921,35 @@ static int arm_smmu_switch_dirty_log(struct iommu_domain *domain, bool enable, return 0; }

+static int arm_smmu_sync_dirty_log(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, + unsigned long base_iova, + unsigned long bitmap_pgshift) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops; + struct arm_smmu_device *smmu = smmu_domain->smmu; + + if (!(smmu->features & ARM_SMMU_FEAT_HD)) + return -ENODEV; + if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1) + return -EINVAL; + + if (!ops || !ops->sync_dirty_log) { + pr_err("io-pgtable don't realize sync dirty log\n"); + return -ENODEV; + } + + /* + * Flush iotlb to ensure all inflight transactions are completed. + * See doc IHI0070Da 3.13.4 "HTTU behavior summary". + */ + arm_smmu_flush_iotlb_all(domain); + return ops->sync_dirty_log(ops, iova, size, bitmap, base_iova, + bitmap_pgshift); +} + static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args) { return iommu_fwspec_add_ids(dev, args->args, 1); @@ -3032,6 +3061,7 @@ static struct iommu_ops arm_smmu_ops = { .release_device = arm_smmu_release_device, .device_group = arm_smmu_device_group, .switch_dirty_log = arm_smmu_switch_dirty_log, + .sync_dirty_log = arm_smmu_sync_dirty_log, .of_xlate = arm_smmu_of_xlate, .get_resv_regions = arm_smmu_get_resv_regions, .remove_dev_pasid = arm_smmu_remove_dev_pasid,

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

We have implemented these interfaces required to support iommu dirty log tracking. The last step is reporting this feature to upper user, then the user can perform higher policy base on it. For arm smmuv3, it is equal to ARM_SMMU_FEAT_HD.

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 16a7d0ffb268..4dc6fab6ff5a 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2884,6 +2884,13 @@ static int arm_smmu_merge_page(struct iommu_domain *domain, unsigned long iova, return ret; }

+static bool arm_smmu_support_dirty_log(struct iommu_domain *domain) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + + return !!(smmu_domain->smmu->features & ARM_SMMU_FEAT_HD); +} + static int arm_smmu_switch_dirty_log(struct iommu_domain *domain, bool enable, unsigned long iova, size_t size, int prot) { @@ -3084,6 +3091,7 @@ static struct iommu_ops arm_smmu_ops = { .probe_device = arm_smmu_probe_device, .release_device = arm_smmu_release_device, .device_group = arm_smmu_device_group, + .support_dirty_log = arm_smmu_support_dirty_log, .switch_dirty_log = arm_smmu_switch_dirty_log, .sync_dirty_log = arm_smmu_sync_dirty_log, .clear_dirty_log = arm_smmu_clear_dirty_log,

Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/vfio/vfio_iommu_type1.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 9edc28f4a2d1..74e1211d9aaf 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1356,7 +1356,7 @@ static void vfio_dma_dirty_log_switch(struct vfio_iommu *iommu, if (!d->iommu_hwdbm) continue; WARN_ON(iommu_switch_dirty_log(d->domain, enable, dma->iova, - dma->size, d->prot | dma->prot)); + dma->size, IOMMU_CACHE | dma->prot)); } }

@@ -2253,7 +2253,7 @@ static void vfio_domain_dirty_log_switch(struct vfio_iommu *iommu, if (!dma->iommu_mapped) continue; WARN_ON(iommu_switch_dirty_log(d->domain, enable, dma->iova, - dma->size, d->prot | dma->prot)); + dma->size, IOMMU_CACHE | dma->prot)); } }

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6FHYK CVE: NA

--------------------------------

For security purposes, kvzalloc is used to allocate memory. Because the memory may be allocated by vmalloc. So we replace kfree with kvfree here.

Reported-by: Zhaolong Wang wangzhaolong1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Jialin Zhang zhangjialin11@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/vfio/vfio_iommu_type1.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index fc62430a73dd..88081c22e1c3 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1214,7 +1214,7 @@ static int vfio_iova_dirty_log_clear(u64 __user *bitmap, int ret = 0;

bitmap_size = DIRTY_BITMAP_BYTES(size >> pgshift); - bitmap_buffer = kvmalloc(bitmap_size, GFP_KERNEL); + bitmap_buffer = kvzalloc(bitmap_size, GFP_KERNEL); if (!bitmap_buffer) { ret = -ENOMEM; goto out; @@ -1264,7 +1264,7 @@ static int vfio_iova_dirty_log_clear(u64 __user *bitmap, }

out: - kfree(bitmap_buffer); + kvfree(bitmap_buffer); return ret; }

From: Kunkun Jiang jiangkunkun@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

As nested mode is not upstreamed now, we just aim to support dirty log tracking for stage1 with io-pgtable mapping (means not support SVA mapping). If HTTU is supported, we enable HA/HD bits in the SMMU CD and transfer ARM_HD quirk to io-pgtable.

Co-developed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 83600e9b2e69..f024093e5e4f 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2131,6 +2131,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain, FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, tcr->orgn) | FIELD_PREP(CTXDESC_CD_0_TCR_SH0, tcr->sh) | FIELD_PREP(CTXDESC_CD_0_TCR_IPS, tcr->ips) | + CTXDESC_CD_0_TCR_HA | CTXDESC_CD_0_TCR_HD | CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64; cfg->cd.mair = pgtbl_cfg->arm_lpae_s1_cfg.mair;

@@ -2240,6 +2241,8 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain, pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_BBML1; else if (smmu->features & ARM_SMMU_FEAT_BBML2) pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_BBML2; + if (smmu->features & ARM_SMMU_FEAT_HD) + pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_HD;

pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain); if (!pgtbl_ops)

From: Keqian Zhu zhukeqian1@huawei.com

virt inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZUKK CVE: NA

------------------------------

Some types of IOMMU are capable of tracking DMA dirty log, such as ARM SMMU with HTTU or Intel IOMMU with SLADE. This introduces the dirty log tracking framework in the IOMMU base layer.

Four new essential interfaces are added, and we maintaince the status of dirty log tracking in iommu_domain. 1. iommu_support_dirty_log: Check whether domain supports dirty log tracking 2. iommu_switch_dirty_log: Perform actions to start|stop dirty log tracking 3. iommu_sync_dirty_log: Sync dirty log from IOMMU into a dirty bitmap 4. iommu_clear_dirty_log: Clear dirty log of IOMMU by a mask bitmap

Note: Don't concurrently call these interfaces with other ops that access underlying page table.

Signed-off-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Keqian Zhu zhukeqian1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/iommu.c | 202 +++++++++++++++++++++++++++++++++++ include/linux/iommu.h | 68 +++++++++++- include/trace/events/iommu.h | 63 +++++++++++ 3 files changed, 332 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 7b2dc57f738d..4cd140bb3175 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1998,6 +1998,8 @@ static struct iommu_domain *__iommu_domain_alloc(const struct bus_type *bus, iommu_domain_free(domain); domain = NULL; } + mutex_init(&domain->switch_log_lock); + return domain; }

@@ -2746,6 +2748,206 @@ int iommu_set_pgtable_quirks(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_set_pgtable_quirks);

+bool iommu_support_dirty_log(struct iommu_domain *domain) +{ + const struct iommu_ops *ops = domain->ops; + + return ops->support_dirty_log && ops->support_dirty_log(domain); +} +EXPORT_SYMBOL_GPL(iommu_support_dirty_log); + +int iommu_switch_dirty_log(struct iommu_domain *domain, bool enable, + unsigned long iova, size_t size, int prot) +{ + const struct iommu_ops *ops = domain->ops; + unsigned long orig_iova = iova; + unsigned int min_pagesz; + size_t orig_size = size; + bool flush = false; + int ret = 0; + + if (unlikely(!ops->switch_dirty_log)) + return -ENODEV; + + min_pagesz = 1 << __ffs(domain->pgsize_bitmap); + if (!IS_ALIGNED(iova | size, min_pagesz)) { + pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n", + iova, size, min_pagesz); + return -EINVAL; + } + + mutex_lock(&domain->switch_log_lock); + if (enable && domain->dirty_log_tracking) { + ret = -EBUSY; + goto out; + } else if (!enable && !domain->dirty_log_tracking) { + ret = -EINVAL; + goto out; + } + + pr_debug("switch_dirty_log %s for: iova 0x%lx size 0x%zx\n", + enable ? "enable" : "disable", iova, size); + + while (size) { + size_t pgsize = iommu_pgsize(domain, iova, size); + + flush = true; + ret = ops->switch_dirty_log(domain, enable, iova, pgsize, prot); + if (ret) + break; + + pr_debug("switch_dirty_log handled: iova 0x%lx size 0x%zx\n", + iova, pgsize); + + iova += pgsize; + size -= pgsize; + } + + if (flush) + iommu_flush_iotlb_all(domain); + + if (!ret) { + domain->dirty_log_tracking = enable; + trace_switch_dirty_log(orig_iova, orig_size, enable); + } +out: + mutex_unlock(&domain->switch_log_lock); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_switch_dirty_log); + +int iommu_sync_dirty_log(struct iommu_domain *domain, unsigned long iova, + size_t size, unsigned long *bitmap, + unsigned long base_iova, unsigned long bitmap_pgshift) +{ + const struct iommu_ops *ops = domain->ops; + unsigned long orig_iova = iova; + unsigned int min_pagesz; + size_t orig_size = size; + int ret = 0; + + if (unlikely(!ops->sync_dirty_log)) + return -ENODEV; + + min_pagesz = 1 << __ffs(domain->pgsize_bitmap); + if (!IS_ALIGNED(iova | size, min_pagesz)) { + pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n", + iova, size, min_pagesz); + return -EINVAL; + } + + mutex_lock(&domain->switch_log_lock); + if (!domain->dirty_log_tracking) { + ret = -EINVAL; + goto out; + } + + pr_debug("sync_dirty_log for: iova 0x%lx size 0x%zx\n", iova, size); + + while (size) { + size_t pgsize = iommu_pgsize(domain, iova, size); + + ret = ops->sync_dirty_log(domain, iova, pgsize, + bitmap, base_iova, bitmap_pgshift); + if (ret) + break; + + pr_debug("sync_dirty_log handled: iova 0x%lx size 0x%zx\n", + iova, pgsize); + + iova += pgsize; + size -= pgsize; + } + + if (!ret) + trace_sync_dirty_log(orig_iova, orig_size); +out: + mutex_unlock(&domain->switch_log_lock); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_sync_dirty_log); + +static int __iommu_clear_dirty_log(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, + unsigned long base_iova, + unsigned long bitmap_pgshift) +{ + const struct iommu_ops *ops = domain->ops; + unsigned long orig_iova = iova; + size_t orig_size = size; + int ret = 0; + + if (unlikely(!ops->clear_dirty_log)) + return -ENODEV; + + pr_debug("clear_dirty_log for: iova 0x%lx size 0x%zx\n", iova, size); + + while (size) { + size_t pgsize = iommu_pgsize(domain, iova, size); + + ret = ops->clear_dirty_log(domain, iova, pgsize, bitmap, + base_iova, bitmap_pgshift); + if (ret) + break; + + pr_debug("clear_dirty_log handled: iova 0x%lx size 0x%zx\n", + iova, pgsize); + + iova += pgsize; + size -= pgsize; + } + + if (!ret) + trace_clear_dirty_log(orig_iova, orig_size); + + return ret; +} + +int iommu_clear_dirty_log(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, unsigned long base_iova, + unsigned long bitmap_pgshift) +{ + unsigned long riova, rsize; + unsigned int min_pagesz; + bool flush = false; + int rs, re, start, end; + int ret = 0; + + min_pagesz = 1 << __ffs(domain->pgsize_bitmap); + if (!IS_ALIGNED(iova | size, min_pagesz)) { + pr_err("unaligned: iova 0x%lx min_pagesz 0x%x\n", + iova, min_pagesz); + return -EINVAL; + } + + mutex_lock(&domain->switch_log_lock); + if (!domain->dirty_log_tracking) { + ret = -EINVAL; + goto out; + } + + start = (iova - base_iova) >> bitmap_pgshift; + end = start + (size >> bitmap_pgshift); + bitmap_for_each_set_region(bitmap, rs, re, start, end) { + flush = true; + riova = base_iova + (rs << bitmap_pgshift); + rsize = (re - rs) << bitmap_pgshift; + ret = __iommu_clear_dirty_log(domain, riova, rsize, bitmap, + base_iova, bitmap_pgshift); + if (ret) + break; + } + + if (flush) + iommu_flush_iotlb_all(domain); +out: + mutex_unlock(&domain->switch_log_lock); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_clear_dirty_log); + /** * iommu_get_resv_regions - get reserved regions * @dev: device for which to get reserved regions diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 56a366e4e60e..5413160ebbfb 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -111,6 +111,8 @@ struct iommu_domain { int users; }; }; + bool dirty_log_tracking; + struct mutex switch_log_lock; };

static inline bool iommu_is_dma_domain(struct iommu_domain *domain) @@ -243,6 +245,10 @@ struct iommu_iotlb_gather { * is to support old IOMMU drivers, new drivers should use * default domains, and the common IOMMU DMA ops. * @device_group: find iommu group for a particular device + * @support_dirty_log: Check whether domain supports dirty log tracking + * @switch_dirty_log: Perform actions to start|stop dirty log tracking + * @sync_dirty_log: Sync dirty log from IOMMU into a dirty bitmap + * @clear_dirty_log: Clear dirty log of IOMMU by a mask bitmap * @get_resv_regions: Request list of reserved regions for a device * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu @@ -274,6 +280,22 @@ struct iommu_ops { void (*set_platform_dma_ops)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev);

+ /* + * Track dirty log. Note: Don't concurrently call these interfaces with + * other ops that access underlying page table. + */ + bool (*support_dirty_log)(struct iommu_domain *domain); + int (*switch_dirty_log)(struct iommu_domain *domain, bool enable, + unsigned long iova, size_t size, int prot); + int (*sync_dirty_log)(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, unsigned long base_iova, + unsigned long bitmap_pgshift); + int (*clear_dirty_log)(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, unsigned long base_iova, + unsigned long bitmap_pgshift); + /* Request/Free a list of reserved regions for a device */ void (*get_resv_regions)(struct device *dev, struct list_head *list);

@@ -538,6 +560,18 @@ int iommu_enable_nesting(struct iommu_domain *domain); int iommu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirks);

+extern bool iommu_support_dirty_log(struct iommu_domain *domain); +extern int iommu_switch_dirty_log(struct iommu_domain *domain, bool enable, + unsigned long iova, size_t size, int prot); +extern int iommu_sync_dirty_log(struct iommu_domain *domain, unsigned long iova, + size_t size, unsigned long *bitmap, + unsigned long base_iova, + unsigned long bitmap_pgshift); +extern int iommu_clear_dirty_log(struct iommu_domain *domain, unsigned long iova, + size_t dma_size, unsigned long *bitmap, + unsigned long base_iova, + unsigned long bitmap_pgshift); + void iommu_set_dma_strict(void);

extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, @@ -945,7 +979,39 @@ static inline int iommu_set_pgtable_quirks(struct iommu_domain *domain, return 0; }

-static inline int iommu_device_register(struct iommu_device *iommu) +static inline bool iommu_support_dirty_log(struct iommu_domain *domain) +{ + return false; +} + +static inline int iommu_switch_dirty_log(struct iommu_domain *domain, + bool enable, unsigned long iova, + size_t size, int prot) +{ + return -EINVAL; +} + +static inline int iommu_sync_dirty_log(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, + unsigned long base_iova, + unsigned long pgshift) +{ + return -EINVAL; +} + +static inline int iommu_clear_dirty_log(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, + unsigned long base_iova, + unsigned long pgshift) +{ + return -EINVAL; +} + +static inline int iommu_device_register(struct iommu_device *iommu, + const struct iommu_ops *ops, + struct device *hwdev) { return -ENODEV; } diff --git a/include/trace/events/iommu.h b/include/trace/events/iommu.h index 70743db1fb75..231e50f111ca 100644 --- a/include/trace/events/iommu.h +++ b/include/trace/events/iommu.h @@ -124,6 +124,69 @@ TRACE_EVENT(unmap, ) );

+TRACE_EVENT(switch_dirty_log, + + TP_PROTO(unsigned long iova, size_t size, bool enable), + + TP_ARGS(iova, size, enable), + + TP_STRUCT__entry( + __field(u64, iova) + __field(size_t, size) + __field(bool, enable) + ), + + TP_fast_assign( + __entry->iova = iova; + __entry->size = size; + __entry->enable = enable; + ), + + TP_printk("IOMMU: iova=0x%016llx size=%zu enable=%u", + __entry->iova, __entry->size, __entry->enable + ) +); + +TRACE_EVENT(sync_dirty_log, + + TP_PROTO(unsigned long iova, size_t size), + + TP_ARGS(iova, size), + + TP_STRUCT__entry( + __field(u64, iova) + __field(size_t, size) + ), + + TP_fast_assign( + __entry->iova = iova; + __entry->size = size; + ), + + TP_printk("IOMMU: iova=0x%016llx size=%zu", __entry->iova, + __entry->size) +); + +TRACE_EVENT(clear_dirty_log, + + TP_PROTO(unsigned long iova, size_t size), + + TP_ARGS(iova, size), + + TP_STRUCT__entry( + __field(u64, iova) + __field(size_t, size) + ), + + TP_fast_assign( + __entry->iova = iova; + __entry->size = size; + ), + + TP_printk("IOMMU: iova=0x%016llx size=%zu", __entry->iova, + __entry->size) +); + DECLARE_EVENT_CLASS(iommu_error,

TP_PROTO(struct device *dev, unsigned long iova, int flags),

conflit with 89d5b9601f70b72f524fdb7bc6cf1b1e8e20e867 pass phy as virt as origin

Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/io-pgtable-arm.c | 2 +- drivers/iommu/iommu.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 404c87422338..4e5b1f4dd1a8 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -760,7 +760,7 @@ static size_t arm_lpae_do_split_blk(struct arm_lpae_io_pgtable *data, io_pgtable_tlb_flush_walk(&data->iop, iova, size, size); } /* Race does not exist */ - pte = arm_lpae_install_table(tablep, ptep, blk_pte, cfg); + pte = arm_lpae_install_table(tablep, ptep, blk_pte, data);

/* Have splited it into page? */ if (lvl == (ARM_LPAE_MAX_LEVELS - 1)) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 40912af6c304..0ebea4808212 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2789,7 +2789,7 @@ int iommu_switch_dirty_log(struct iommu_domain *domain, bool enable, enable ? "enable" : "disable", iova, size);

while (size) { - size_t pgsize = iommu_pgsize(domain, iova, size); + size_t pgsize = iommu_pgsize(domain, iova, iova, size, NULL);

flush = true; ret = ops->switch_dirty_log(domain, enable, iova, pgsize, prot); @@ -2845,7 +2845,7 @@ int iommu_sync_dirty_log(struct iommu_domain *domain, unsigned long iova, pr_debug("sync_dirty_log for: iova 0x%lx size 0x%zx\n", iova, size);

while (size) { - size_t pgsize = iommu_pgsize(domain, iova, size); + size_t pgsize = iommu_pgsize(domain, iova, iova, size, NULL);

ret = ops->sync_dirty_log(domain, iova, pgsize, bitmap, base_iova, bitmap_pgshift); @@ -2884,7 +2884,7 @@ static int __iommu_clear_dirty_log(struct iommu_domain *domain, pr_debug("clear_dirty_log for: iova 0x%lx size 0x%zx\n", iova, size);

while (size) { - size_t pgsize = iommu_pgsize(domain, iova, size); + size_t pgsize = iommu_pgsize(domain, iova, iova, size, NULL);

ret = ops->clear_dirty_log(domain, iova, pgsize, bitmap, base_iova, bitmap_pgshift);

Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 8 ++--- drivers/iommu/iommu.c | 13 ++++--- drivers/vfio/vfio_iommu_type1.c | 5 ++- include/linux/iommu.h | 39 +++++++++++---------- 4 files changed, 32 insertions(+), 33 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index f024093e5e4f..326bd2ed5541 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3101,10 +3101,6 @@ static struct iommu_ops arm_smmu_ops = { .probe_device = arm_smmu_probe_device, .release_device = arm_smmu_release_device, .device_group = arm_smmu_device_group, - .support_dirty_log = arm_smmu_support_dirty_log, - .switch_dirty_log = arm_smmu_switch_dirty_log, - .sync_dirty_log = arm_smmu_sync_dirty_log, - .clear_dirty_log = arm_smmu_clear_dirty_log, .of_xlate = arm_smmu_of_xlate, .get_resv_regions = arm_smmu_get_resv_regions, .remove_dev_pasid = arm_smmu_remove_dev_pasid, @@ -3125,6 +3121,10 @@ static struct iommu_ops arm_smmu_ops = { #endif .iova_to_phys = arm_smmu_iova_to_phys, .enable_nesting = arm_smmu_enable_nesting, + .support_dirty_log = arm_smmu_support_dirty_log, + .switch_dirty_log = arm_smmu_switch_dirty_log, + .sync_dirty_log = arm_smmu_sync_dirty_log, + .clear_dirty_log = arm_smmu_clear_dirty_log, .free = arm_smmu_domain_free, } }; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 0ebea4808212..dbae8a71c0f0 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2750,7 +2750,7 @@ EXPORT_SYMBOL_GPL(iommu_set_pgtable_quirks);

bool iommu_support_dirty_log(struct iommu_domain *domain) { - const struct iommu_ops *ops = domain->ops; + const struct iommu_domain_ops *ops = domain->ops;

return ops->support_dirty_log && ops->support_dirty_log(domain); } @@ -2759,7 +2759,7 @@ EXPORT_SYMBOL_GPL(iommu_support_dirty_log); int iommu_switch_dirty_log(struct iommu_domain *domain, bool enable, unsigned long iova, size_t size, int prot) { - const struct iommu_ops *ops = domain->ops; + const struct iommu_domain_ops *ops = domain->ops; unsigned long orig_iova = iova; unsigned int min_pagesz; size_t orig_size = size; @@ -2820,7 +2820,7 @@ int iommu_sync_dirty_log(struct iommu_domain *domain, unsigned long iova, size_t size, unsigned long *bitmap, unsigned long base_iova, unsigned long bitmap_pgshift) { - const struct iommu_ops *ops = domain->ops; + const struct iommu_domain_ops *ops = domain->ops; unsigned long orig_iova = iova; unsigned int min_pagesz; size_t orig_size = size; @@ -2873,7 +2873,7 @@ static int __iommu_clear_dirty_log(struct iommu_domain *domain, unsigned long base_iova, unsigned long bitmap_pgshift) { - const struct iommu_ops *ops = domain->ops; + const struct iommu_domain_ops *ops = domain->ops; unsigned long orig_iova = iova; size_t orig_size = size; int ret = 0; @@ -2927,9 +2927,8 @@ int iommu_clear_dirty_log(struct iommu_domain *domain, goto out; }

- start = (iova - base_iova) >> bitmap_pgshift; - end = start + (size >> bitmap_pgshift); - bitmap_for_each_set_region(bitmap, rs, re, start, end) { + rs = (iova - base_iova) >> bitmap_pgshift; + for_each_set_bitrange_from(rs, re, bitmap, (size >> bitmap_pgshift)) { flush = true; riova = base_iova + ((unsigned long)rs << bitmap_pgshift); rsize = (unsigned long)(re - rs) << bitmap_pgshift; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index b7c9f4f3b796..cb7957a6dcb4 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1238,9 +1238,8 @@ static int vfio_iova_dirty_log_clear(u64 __user *bitmap, /* Similar logic as the tail of vfio_iova_dirty_bitmap */

clear_valid = false; - start = (start_iova - iova) >> pgshift; - end = (end_iova - iova) >> pgshift; - bitmap_for_each_set_region(bitmap_buffer, rs, re, start, end) { + rs = (start_iova - iova) >> pgshift; + for_each_set_bitrange(rs, re, bitmap_buffer, (end_iova - iova) >> pgshift) { clear_valid = true; riova = iova + ((unsigned long)rs << pgshift); dma_offset = (riova - dma->iova) >> pgshift; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5413160ebbfb..45734fd9cfd4 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -245,10 +245,6 @@ struct iommu_iotlb_gather { * is to support old IOMMU drivers, new drivers should use * default domains, and the common IOMMU DMA ops. * @device_group: find iommu group for a particular device - * @support_dirty_log: Check whether domain supports dirty log tracking - * @switch_dirty_log: Perform actions to start|stop dirty log tracking - * @sync_dirty_log: Sync dirty log from IOMMU into a dirty bitmap - * @clear_dirty_log: Clear dirty log of IOMMU by a mask bitmap * @get_resv_regions: Request list of reserved regions for a device * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu @@ -280,21 +276,6 @@ struct iommu_ops { void (*set_platform_dma_ops)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev);

- /* - * Track dirty log. Note: Don't concurrently call these interfaces with - * other ops that access underlying page table. - */ - bool (*support_dirty_log)(struct iommu_domain *domain); - int (*switch_dirty_log)(struct iommu_domain *domain, bool enable, - unsigned long iova, size_t size, int prot); - int (*sync_dirty_log)(struct iommu_domain *domain, - unsigned long iova, size_t size, - unsigned long *bitmap, unsigned long base_iova, - unsigned long bitmap_pgshift); - int (*clear_dirty_log)(struct iommu_domain *domain, - unsigned long iova, size_t size, - unsigned long *bitmap, unsigned long base_iova, - unsigned long bitmap_pgshift);

/* Request/Free a list of reserved regions for a device */ void (*get_resv_regions)(struct device *dev, struct list_head *list); @@ -349,6 +330,10 @@ struct iommu_ops { * specific mechanisms. * @enable_nesting: Enable nesting * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) + * @support_dirty_log: Check whether domain supports dirty log tracking + * @switch_dirty_log: Perform actions to start|stop dirty log tracking + * @sync_dirty_log: Sync dirty log from IOMMU into a dirty bitmap + * @clear_dirty_log: Clear dirty log of IOMMU by a mask bitmap * @free: Release the domain after use. */ struct iommu_domain_ops { @@ -381,6 +366,22 @@ struct iommu_domain_ops { int (*set_pgtable_quirks)(struct iommu_domain *domain, unsigned long quirks);

+ /* + * Track dirty log. Note: Don't concurrently call these interfaces with + * other ops that access underlying page table. + */ + bool (*support_dirty_log)(struct iommu_domain *domain); + int (*switch_dirty_log)(struct iommu_domain *domain, bool enable, + unsigned long iova, size_t size, int prot); + int (*sync_dirty_log)(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, unsigned long base_iova, + unsigned long bitmap_pgshift); + int (*clear_dirty_log)(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long *bitmap, unsigned long base_iova, + unsigned long bitmap_pgshift); + void (*free)(struct iommu_domain *domain); };

From: Keqian Zhu zhukeqian1@huawei.com

virt inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4WK5B CVE: NA

------------------------------

The iommu_domain may contain more than one DMA range which can be dirty log tracked separately, so it's hard to track the dirty log status of iommu_domain. The upper layer (e.g. vfio) should make sure it's doing right thing.

Fixes: bbf3b39e5576 (iommu: Introduce dirty log tracking framework) Signed-off-by: Keqian Zhu zhukeqian1@huawei.com Tested-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Kunkun Jiang jiangkunkun@huawei.com Reviewed-by: Zenghui Yu yuzenghui@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Signed-off-by: jiaqingtong jiaqingtong@huawei.com --- drivers/iommu/iommu.c | 25 ++++--------------------- 1 file changed, 4 insertions(+), 21 deletions(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index dbae8a71c0f0..32f0f6c461b3 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2777,13 +2777,6 @@ int iommu_switch_dirty_log(struct iommu_domain *domain, bool enable, }

mutex_lock(&domain->switch_log_lock); - if (enable && domain->dirty_log_tracking) { - ret = -EBUSY; - goto out; - } else if (!enable && !domain->dirty_log_tracking) { - ret = -EINVAL; - goto out; - }

pr_debug("switch_dirty_log %s for: iova 0x%lx size 0x%zx\n", enable ? "enable" : "disable", iova, size); @@ -2806,11 +2799,9 @@ int iommu_switch_dirty_log(struct iommu_domain *domain, bool enable, if (flush) iommu_flush_iotlb_all(domain);

- if (!ret) { - domain->dirty_log_tracking = enable; + if (!ret) trace_switch_dirty_log(orig_iova, orig_size, enable); - } -out: + mutex_unlock(&domain->switch_log_lock); return ret; } @@ -2837,10 +2828,6 @@ int iommu_sync_dirty_log(struct iommu_domain *domain, unsigned long iova, }

mutex_lock(&domain->switch_log_lock); - if (!domain->dirty_log_tracking) { - ret = -EINVAL; - goto out; - }

pr_debug("sync_dirty_log for: iova 0x%lx size 0x%zx\n", iova, size);

@@ -2861,7 +2848,7 @@ int iommu_sync_dirty_log(struct iommu_domain *domain, unsigned long iova,

if (!ret) trace_sync_dirty_log(orig_iova, orig_size); -out: + mutex_unlock(&domain->switch_log_lock); return ret; } @@ -2922,10 +2909,6 @@ int iommu_clear_dirty_log(struct iommu_domain *domain, }

mutex_lock(&domain->switch_log_lock); - if (!domain->dirty_log_tracking) { - ret = -EINVAL; - goto out; - }

rs = (iova - base_iova) >> bitmap_pgshift; for_each_set_bitrange_from(rs, re, bitmap, (size >> bitmap_pgshift)) { @@ -2940,7 +2923,7 @@ int iommu_clear_dirty_log(struct iommu_domain *domain,

if (flush) iommu_flush_iotlb_all(domain); -out: + mutex_unlock(&domain->switch_log_lock); return ret; }