| Message ID | 20220611102656.10954-2-yf.wang@mediatek.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | iommu/mediatek: TTBR up to 35bit support | expand |
Hi, For some reason, this series has landed in my spam folder so apologies for the delay :/ On Sat, Jun 11, 2022 at 06:26:53PM +0800, yf.wang@mediatek.com wrote: > From: Yunfei Wang <yf.wang@mediatek.com> > > Single memory zone feature will remove ZONE_DMA32 and ZONE_DMA and > cause pgtable PA size larger than 32bit. > > Since Mediatek IOMMU hardware support at most 35bit PA in pgtable, > so add a quirk to allow the PA of pgtables support up to bit35. > > Signed-off-by: Ning Li <ning.li@mediatek.com> > Signed-off-by: Yunfei Wang <yf.wang@mediatek.com> > --- > drivers/iommu/io-pgtable-arm-v7s.c | 48 ++++++++++++++++++++++-------- > include/linux/io-pgtable.h | 17 +++++++---- > 2 files changed, 46 insertions(+), 19 deletions(-) > > diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c > index be066c1503d3..d4702d8d825a 100644 > --- a/drivers/iommu/io-pgtable-arm-v7s.c > +++ b/drivers/iommu/io-pgtable-arm-v7s.c > @@ -182,14 +182,8 @@ static bool arm_v7s_is_mtk_enabled(struct io_pgtable_cfg *cfg) > (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT); > } > > -static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl, > - struct io_pgtable_cfg *cfg) > +static arm_v7s_iopte to_iopte_mtk(phys_addr_t paddr, arm_v7s_iopte pte) > { > - arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl); > - > - if (!arm_v7s_is_mtk_enabled(cfg)) > - return pte; > - > if (paddr & BIT_ULL(32)) > pte |= ARM_V7S_ATTR_MTK_PA_BIT32; > if (paddr & BIT_ULL(33)) > @@ -199,6 +193,17 @@ static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl, > return pte; > } > > +static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl, > + struct io_pgtable_cfg *cfg) > +{ > + arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl); > + > + if (!arm_v7s_is_mtk_enabled(cfg)) > + return pte; > + > + return to_iopte_mtk(paddr, pte); nit, but can we rename and rework this so it reads a bit better, please? Something like: if (arm_v7s_is_mtk_enabled(cfg)) return to_mtk_iopte(paddr, pte); return pte; > static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl, > struct io_pgtable_cfg *cfg) > { > @@ -234,6 +239,7 @@ static arm_v7s_iopte *iopte_deref(arm_v7s_iopte pte, int lvl, > static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, > struct arm_v7s_io_pgtable *data) > { > + gfp_t gfp_l1 = __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA; > struct io_pgtable_cfg *cfg = &data->iop.cfg; > struct device *dev = cfg->iommu_dev; > phys_addr_t phys; > @@ -241,9 +247,11 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, > size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg); > void *table = NULL; > > + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) > + gfp_l1 = GFP_KERNEL | __GFP_ZERO; I think it's a bit grotty to override the flags inline like this (same for the slab flag later on). Something like this is a bit cleaner: /* * Comment explaining why GFP_KERNEL is desirable here. * I'm assuming it's because the walker can address all of memory. */ gfp_l1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ? GFP_KERNEL : ARM_V7S_TABLE_GFP_DMA; ... __get_free_pages(gfp_l1 | __GFP_ZERO, ...); and similar for the slab flag. > if (lvl == 1) > - table = (void *)__get_free_pages( > - __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size)); > + table = (void *)__get_free_pages(gfp_l1, get_order(size)); > else if (lvl == 2) > table = kmem_cache_zalloc(data->l2_tables, gfp); > > @@ -251,7 +259,8 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, > return NULL; > > phys = virt_to_phys(table); > - if (phys != (arm_v7s_iopte)phys) { > + if (phys != (arm_v7s_iopte)phys && > + !(cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT)) { > /* Doesn't fit in PTE */ Shouldn't we be checking that the address is within 35 bits here? Perhaps we should generate a mask from the oas instead of just using the cast. > dev_err(dev, "Page table does not fit in PTE: %pa", &phys); > goto out_free; > @@ -457,9 +466,14 @@ static arm_v7s_iopte arm_v7s_install_table(arm_v7s_iopte *table, > arm_v7s_iopte curr, > struct io_pgtable_cfg *cfg) > { > + phys_addr_t phys = virt_to_phys(table); > arm_v7s_iopte old, new; > > - new = virt_to_phys(table) | ARM_V7S_PTE_TYPE_TABLE; > + new = phys | ARM_V7S_PTE_TYPE_TABLE; > + > + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) > + new = to_iopte_mtk(phys, new); > + > if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS) > new |= ARM_V7S_ATTR_NS_TABLE; > > @@ -778,6 +792,7 @@ static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops, > static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, > void *cookie) > { > + slab_flags_t slab_flag = ARM_V7S_TABLE_SLAB_FLAGS; > struct arm_v7s_io_pgtable *data; > > if (cfg->ias > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS)) > @@ -788,7 +803,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, > > if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | > IO_PGTABLE_QUIRK_NO_PERMS | > - IO_PGTABLE_QUIRK_ARM_MTK_EXT)) > + IO_PGTABLE_QUIRK_ARM_MTK_EXT | > + IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT)) > return NULL; > > /* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */ > @@ -796,15 +812,21 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, > !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS)) > return NULL; > > + if ((cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) && > + !arm_v7s_is_mtk_enabled(cfg)) > + return NULL; > + > data = kmalloc(sizeof(*data), GFP_KERNEL); > if (!data) > return NULL; > > spin_lock_init(&data->split_lock); > + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) > + slab_flag = 0; > data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2", > ARM_V7S_TABLE_SIZE(2, cfg), > ARM_V7S_TABLE_SIZE(2, cfg), > - ARM_V7S_TABLE_SLAB_FLAGS, NULL); > + slab_flag, NULL); > if (!data->l2_tables) > goto out_free_data; > > diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h > index 86af6f0a00a2..c9189716f6bd 100644 > --- a/include/linux/io-pgtable.h > +++ b/include/linux/io-pgtable.h > @@ -74,17 +74,22 @@ struct io_pgtable_cfg { > * to support up to 35 bits PA where the bit32, bit33 and bit34 are > * encoded in the bit9, bit4 and bit5 of the PTE respectively. > * > + * IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT: (ARM v7s format) MediaTek IOMMUs > + * extend the translation table base support up to 35 bits PA, the > + * encoding format is same with IO_PGTABLE_QUIRK_ARM_MTK_EXT. > + * One thing I don't get is how the existing driver handles this. It seems as though if the HAS_4GB_MODE flag is not set, then we set oas to 35 but without any pgtable changes. How does this work? If it turns out that the existing devices can't handle 35-bit PAs, then could we use an oas of 35 to indicate that this new format is in use instead of introducing another quirk? Will
On Tue, 2022-06-14 at 13:56 +0100, Will Deacon wrote: > > @@ -74,17 +74,22 @@ struct io_pgtable_cfg { > > * to support up to 35 bits PA where the bit32, bit33 and > > bit34 are > > * encoded in the bit9, bit4 and bit5 of the PTE respectively. > > * > > + * IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT: (ARM v7s format) MediaTek > > IOMMUs > > + * extend the translation table base support up to 35 bits PA, > > the > > + * encoding format is same with IO_PGTABLE_QUIRK_ARM_MTK_EXT. > > + * > > One thing I don't get is how the existing driver handles this. It > seems > as though if the HAS_4GB_MODE flag is not set, then we set oas to 35 > but > without any pgtable changes. How does this work? Regarding the pgtable, we already use the quirk IO_PGTABLE_QUIRK_ARM_MTK_EXT to support 35bits oas. HAS_4GB_MODE is the flag for the previous SoC that only supports 33bits oas, it also is covered by IO_PGTABLE_QUIRK_ARM_MTK_EXT. and in 4GB mode we add PA32 manually in mtk_iommu_map. > > If it turns out that the existing devices can't handle 35-bit PAs, > then > could we use an oas of 35 to indicate that this new format is in use > instead of introducing another quirk? The existed devices can handle 35bits oas. The problem is that if the pgtable PA could support up to 35bits. The previous SoC like mt8173 can't support while the lastest SoC can. This is the purpose of this new quick. therefore we need GFP_DMA/DMA32 for pgtable allocating in mt8173 and GFP_DMA/DMA32 is not needed in the new quirk. > > Will
On Tue, 2022-06-14 at 13:56 +0100, Will Deacon wrote: > Hi, > > For some reason, this series has landed in my spam folder so > apologies > for the delay :/ > > > > +static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl, > > + struct io_pgtable_cfg *cfg) > > +{ > > + arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl); > > + > > + if (!arm_v7s_is_mtk_enabled(cfg)) > > + return pte; > > + > > + return to_iopte_mtk(paddr, pte); > > nit, but can we rename and rework this so it reads a bit better, > please? > Something like: > > > if (arm_v7s_is_mtk_enabled(cfg)) > return to_mtk_iopte(paddr, pte); > > return pte; > > Hi Will, Thanks for your suggestion, PATCH v9 version will modify it. > > static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl, > > struct io_pgtable_cfg *cfg) > > { > > @@ -234,6 +239,7 @@ static arm_v7s_iopte *iopte_deref(arm_v7s_iopte > > pte, int lvl, > > static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, > > struct arm_v7s_io_pgtable *data) > > { > > + gfp_t gfp_l1 = __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA; > > struct io_pgtable_cfg *cfg = &data->iop.cfg; > > struct device *dev = cfg->iommu_dev; > > phys_addr_t phys; > > @@ -241,9 +247,11 @@ static void *__arm_v7s_alloc_table(int lvl, > > gfp_t gfp, > > size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg); > > void *table = NULL; > > > > + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) > > + gfp_l1 = GFP_KERNEL | __GFP_ZERO; > > I think it's a bit grotty to override the flags inline like this > (same for > the slab flag later on). Something like this is a bit cleaner: > > > /* > * Comment explaining why GFP_KERNEL is desirable here. > * I'm assuming it's because the walker can address all of > memory. > */ > gfp_l1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ? > GFP_KERNEL : ARM_V7S_TABLE_GFP_DMA; > > ... > > __get_free_pages(gfp_l1 | __GFP_ZERO, ...); > > > and similar for the slab flag. > Hi Will, Thanks for your suggestion, PATCH v9 version will modify it. > > if (lvl == 1) > > - table = (void *)__get_free_pages( > > - __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, > > get_order(size)); > > + table = (void *)__get_free_pages(gfp_l1, > > get_order(size)); > > else if (lvl == 2) > > table = kmem_cache_zalloc(data->l2_tables, gfp); > > > > @@ -251,7 +259,8 @@ static void *__arm_v7s_alloc_table(int lvl, > > gfp_t gfp, > > return NULL; > > > > phys = virt_to_phys(table); > > - if (phys != (arm_v7s_iopte)phys) { > > + if (phys != (arm_v7s_iopte)phys && > > + !(cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT)) { > > /* Doesn't fit in PTE */ > > Shouldn't we be checking that the address is within 35 bits here? > Perhaps we > should generate a mask from the oas instead of just using the cast. > Hi Will, Thanks for your suggestion, PATCH v9 version will add checking that the address is within 35 bits: phys = virt_to_phys(table); if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT ? phys >= (1ULL << cfg->oas) : phys != (arm_v7s_iopte)phys) { /* Doesn't fit in PTE */ Thanks, Yunfei.
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index be066c1503d3..d4702d8d825a 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -182,14 +182,8 @@ static bool arm_v7s_is_mtk_enabled(struct io_pgtable_cfg *cfg) (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_EXT); } -static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl, - struct io_pgtable_cfg *cfg) +static arm_v7s_iopte to_iopte_mtk(phys_addr_t paddr, arm_v7s_iopte pte) { - arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl); - - if (!arm_v7s_is_mtk_enabled(cfg)) - return pte; - if (paddr & BIT_ULL(32)) pte |= ARM_V7S_ATTR_MTK_PA_BIT32; if (paddr & BIT_ULL(33)) @@ -199,6 +193,17 @@ static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl, return pte; } +static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl, + struct io_pgtable_cfg *cfg) +{ + arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl); + + if (!arm_v7s_is_mtk_enabled(cfg)) + return pte; + + return to_iopte_mtk(paddr, pte); +} + static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl, struct io_pgtable_cfg *cfg) { @@ -234,6 +239,7 @@ static arm_v7s_iopte *iopte_deref(arm_v7s_iopte pte, int lvl, static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, struct arm_v7s_io_pgtable *data) { + gfp_t gfp_l1 = __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA; struct io_pgtable_cfg *cfg = &data->iop.cfg; struct device *dev = cfg->iommu_dev; phys_addr_t phys; @@ -241,9 +247,11 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, size_t size = ARM_V7S_TABLE_SIZE(lvl, cfg); void *table = NULL; + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) + gfp_l1 = GFP_KERNEL | __GFP_ZERO; + if (lvl == 1) - table = (void *)__get_free_pages( - __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size)); + table = (void *)__get_free_pages(gfp_l1, get_order(size)); else if (lvl == 2) table = kmem_cache_zalloc(data->l2_tables, gfp); @@ -251,7 +259,8 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, return NULL; phys = virt_to_phys(table); - if (phys != (arm_v7s_iopte)phys) { + if (phys != (arm_v7s_iopte)phys && + !(cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT)) { /* Doesn't fit in PTE */ dev_err(dev, "Page table does not fit in PTE: %pa", &phys); goto out_free; @@ -457,9 +466,14 @@ static arm_v7s_iopte arm_v7s_install_table(arm_v7s_iopte *table, arm_v7s_iopte curr, struct io_pgtable_cfg *cfg) { + phys_addr_t phys = virt_to_phys(table); arm_v7s_iopte old, new; - new = virt_to_phys(table) | ARM_V7S_PTE_TYPE_TABLE; + new = phys | ARM_V7S_PTE_TYPE_TABLE; + + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) + new = to_iopte_mtk(phys, new); + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS) new |= ARM_V7S_ATTR_NS_TABLE; @@ -778,6 +792,7 @@ static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops, static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) { + slab_flags_t slab_flag = ARM_V7S_TABLE_SLAB_FLAGS; struct arm_v7s_io_pgtable *data; if (cfg->ias > (arm_v7s_is_mtk_enabled(cfg) ? 34 : ARM_V7S_ADDR_BITS)) @@ -788,7 +803,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_PERMS | - IO_PGTABLE_QUIRK_ARM_MTK_EXT)) + IO_PGTABLE_QUIRK_ARM_MTK_EXT | + IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT)) return NULL; /* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */ @@ -796,15 +812,21 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, !(cfg->quirks & IO_PGTABLE_QUIRK_NO_PERMS)) return NULL; + if ((cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) && + !arm_v7s_is_mtk_enabled(cfg)) + return NULL; + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return NULL; spin_lock_init(&data->split_lock); + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT) + slab_flag = 0; data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2", ARM_V7S_TABLE_SIZE(2, cfg), ARM_V7S_TABLE_SIZE(2, cfg), - ARM_V7S_TABLE_SLAB_FLAGS, NULL); + slab_flag, NULL); if (!data->l2_tables) goto out_free_data; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 86af6f0a00a2..c9189716f6bd 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -74,17 +74,22 @@ struct io_pgtable_cfg { * to support up to 35 bits PA where the bit32, bit33 and bit34 are * encoded in the bit9, bit4 and bit5 of the PTE respectively. * + * IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT: (ARM v7s format) MediaTek IOMMUs + * extend the translation table base support up to 35 bits PA, the + * encoding format is same with IO_PGTABLE_QUIRK_ARM_MTK_EXT. + * * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table * for use in the upper half of a split address space. * * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability * attributes set in the TCR for a non-coherent page-table walker. */ - #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) - #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) - #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3) - #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) - #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) + #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) + #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) + #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3) + #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) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias; @@ -122,7 +127,7 @@ struct io_pgtable_cfg { } arm_lpae_s2_cfg; struct { - u32 ttbr; + u64 ttbr; u32 tcr; u32 nmrr; u32 prrr;