Re: [PATCH v2 05/14] iommu/io-pgtable-arm-v7s: Extend MediaTek 4GB Mode

[Robin Murphy]

On 24/09/2018 09:58, Yong Wu wrote:
> MediaTek extend the arm v7s descriptor to support the dram over 4GB.
> 
> In the mt2712 and mt8173, it's called "4GB mode", the physical address
> is from 0x4000_0000 to 0x1_3fff_ffff, but from EMI point of view, it
> is remapped to high address from 0x1_0000_0000 to 0x1_ffff_ffff, the
> bit32 is always enabled. thus, in the M4U, we always enable the bit9
> for all PTEs which means to enable bit32 of physical address.
> 
> but in mt8183, M4U support the dram from 0x4000_0000 to 0x3_ffff_ffff
> which isn't remaped. We extend the PTEs: the bit9 represent bit32 of
> PA and the bit4 represent bit33 of PA. Meanwhile the iova still is
> 32bits.
> 
> In order to unify code, in the "4GB mode", we add the bit32 for the
> physical address manually in our driver.
> 
> Correspondingly, Adding bit32 and bit33 for the PA in the iova_to_phys
> has to been moved into v7s.
> 
> Signed-off-by: Yong Wu <yong.wu@xxxxxxxxxxxx>
> ---
>   drivers/iommu/io-pgtable-arm-v7s.c | 34 +++++++++++++++++++++++++++-------
>   drivers/iommu/io-pgtable.h         |  7 +++----
>   drivers/iommu/mtk_iommu.c          | 16 ++++++++++------
>   drivers/iommu/mtk_iommu.h          |  1 +
>   4 files changed, 41 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
> index fa3b9ec..3679a5f 100644
> --- a/drivers/iommu/io-pgtable-arm-v7s.c
> +++ b/drivers/iommu/io-pgtable-arm-v7s.c
> @@ -124,7 +124,9 @@
>   #define ARM_V7S_TEX_MASK		0x7
>   #define ARM_V7S_ATTR_TEX(val)		(((val) & ARM_V7S_TEX_MASK) << ARM_V7S_TEX_SHIFT)
>   
> -#define ARM_V7S_ATTR_MTK_4GB		BIT(9) /* MTK extend it for 4GB mode */
> +/* MediaTek extend the two bits below for over 4GB mode */
> +#define ARM_V7S_ATTR_MTK_PA_BIT32	BIT(9)
> +#define ARM_V7S_ATTR_MTK_PA_BIT33	BIT(4)
>   
>   /* *well, except for TEX on level 2 large pages, of course :( */
>   #define ARM_V7S_CONT_PAGE_TEX_SHIFT	6
> @@ -183,13 +185,24 @@ static dma_addr_t __arm_v7s_dma_addr(void *pages)
>   static arm_v7s_iopte paddr_to_iopte(phys_addr_t paddr, int lvl,
>   				    struct arm_v7s_io_pgtable *data)
>   {
> -	return paddr & ARM_V7S_LVL_MASK(lvl);
> +	arm_v7s_iopte pte = paddr & ARM_V7S_LVL_MASK(lvl);
> +	struct io_pgtable_cfg *cfg = &data->iop.cfg;
> +
> +	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB) {
> +		if (paddr & BIT_ULL(32))
> +			pte |= ARM_V7S_ATTR_MTK_PA_BIT32;
> +		if (paddr & BIT_ULL(33))
> +			pte |= ARM_V7S_ATTR_MTK_PA_BIT33;
> +	}
> +	return pte;
>   }
>   
>   static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
>   				  struct arm_v7s_io_pgtable *data)
>   {
> +	struct io_pgtable_cfg *cfg = &data->iop.cfg;
>   	arm_v7s_iopte mask;
> +	phys_addr_t paddr;
>   
>   	if (ARM_V7S_PTE_IS_TABLE(pte, lvl))
>   		mask = ARM_V7S_TABLE_MASK;
> @@ -198,7 +211,15 @@ static phys_addr_t iopte_to_paddr(arm_v7s_iopte pte, int lvl,
>   	else
>   		mask = ARM_V7S_LVL_MASK(lvl);
>   
> -	return pte & mask;
> +	paddr = pte & mask;
> +	if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&

I don't think we need this IS_ENABLED() check - we don't have one in the 
equivalent paddr_to_iopte() case above, and what it's protecting is 
clearly a no-op anyway when paddr has a 32-bit type (a GCC 7 build for 
non-LPAE arch/arm doesn't complain with the check removed).

Other than that, though, the rest looks good now;

Reviewed-by: Robin Murphy <robin.murphy@xxxxxxx>

> +	    cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB) {
> +		if (pte & ARM_V7S_ATTR_MTK_PA_BIT32)
> +			paddr |= BIT_ULL(32);
> +		if (pte & ARM_V7S_ATTR_MTK_PA_BIT33)
> +			paddr |= BIT_ULL(33);
> +	}
> +	return paddr;
>   }
>   
>   static arm_v7s_iopte *iopte_deref(arm_v7s_iopte pte, int lvl,
> @@ -315,9 +336,6 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
>   	if (lvl == 1 && (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS))
>   		pte |= ARM_V7S_ATTR_NS_SECTION;
>   
> -	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB)
> -		pte |= ARM_V7S_ATTR_MTK_4GB;
> -
>   	return pte;
>   }
>   
> @@ -504,7 +522,9 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
>   	if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
>   		return 0;
>   
> -	if (WARN_ON(upper_32_bits(iova) || upper_32_bits(paddr)))
> +	if (WARN_ON(upper_32_bits(iova)) ||
> +	    WARN_ON(upper_32_bits(paddr) &&
> +		    !(iop->cfg.quirks & IO_PGTABLE_QUIRK_ARM_MTK_4GB)))
>   		return -ERANGE;
>   
>   	ret = __arm_v7s_map(data, iova, paddr, size, prot, 1, data->pgd);
> diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h
> index 2df7909..ee7beb5 100644
> --- a/drivers/iommu/io-pgtable.h
> +++ b/drivers/iommu/io-pgtable.h
> @@ -62,10 +62,9 @@ struct io_pgtable_cfg {
>   	 *	(unmapped) entries but the hardware might do so anyway, perform
>   	 *	TLB maintenance when mapping as well as when unmapping.
>   	 *
> -	 * IO_PGTABLE_QUIRK_ARM_MTK_4GB: (ARM v7s format) Set bit 9 in all
> -	 *	PTEs, for Mediatek IOMMUs which treat it as a 33rd address bit
> -	 *	when the SoC is in "4GB mode" and they can only access the high
> -	 *	remap of DRAM (0x1_00000000 to 0x1_ffffffff).
> +	 * IO_PGTABLE_QUIRK_ARM_MTK_4GB: (ARM v7s format) MediaTek IOMMUs extend
> +	 *	to support up to 34 bits PA where the bit32 and bit33 are
> +	 *	encoded in the bit9 and bit4 of the PTE respectively.
>   	 *
>   	 * IO_PGTABLE_QUIRK_NO_DMA: Guarantees that the tables will only ever
>   	 *	be accessed by a fully cache-coherent IOMMU or CPU (e.g. for a
> diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
> index c0e2da5..84a12ed 100644
> --- a/drivers/iommu/mtk_iommu.c
> +++ b/drivers/iommu/mtk_iommu.c
> @@ -367,12 +367,18 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
>   			 phys_addr_t paddr, size_t size, int prot)
>   {
>   	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
> +	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
>   	unsigned long flags;
>   	int ret;
>   
> +	/* The "4GB mode" M4U physically can not use the lower remap of Dram. */
> +	if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&
> +	    data->plat_data->has_4gb_mode &&
> +	    data->enable_4GB)
> +		paddr |= BIT_ULL(32);
> +
>   	spin_lock_irqsave(&dom->pgtlock, flags);
> -	ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32),
> -			    size, prot);
> +	ret = dom->iop->map(dom->iop, iova, paddr, size, prot);
>   	spin_unlock_irqrestore(&dom->pgtlock, flags);
>   
>   	return ret;
> @@ -401,7 +407,6 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
>   					  dma_addr_t iova)
>   {
>   	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
> -	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
>   	unsigned long flags;
>   	phys_addr_t pa;
>   
> @@ -409,9 +414,6 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
>   	pa = dom->iop->iova_to_phys(dom->iop, iova);
>   	spin_unlock_irqrestore(&dom->pgtlock, flags);
>   
> -	if (data->enable_4GB)
> -		pa |= BIT_ULL(32);
> -
>   	return pa;
>   }
>   
> @@ -735,10 +737,12 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
>   
>   static const struct mtk_iommu_plat_data mt2712_data = {
>   	.m4u_plat = M4U_MT2712,
> +	.has_4gb_mode = true,
>   };
>   
>   static const struct mtk_iommu_plat_data mt8173_data = {
>   	.m4u_plat = M4U_MT8173,
> +	.has_4gb_mode = true,
>   };
>   
>   static const struct of_device_id mtk_iommu_of_ids[] = {
> diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
> index 333a0ef..a243047 100644
> --- a/drivers/iommu/mtk_iommu.h
> +++ b/drivers/iommu/mtk_iommu.h
> @@ -43,6 +43,7 @@ enum mtk_iommu_plat {
>   
>   struct mtk_iommu_plat_data {
>   	enum mtk_iommu_plat m4u_plat;
> +	bool has_4gb_mode;
>   };
>   
>   struct mtk_iommu_domain;
>