Re: [PATCH v5 11/18] kvm: arm64: Dynamic configuration of VTTBR mask

From: Auger Eric
Date: Thu Sep 20 2018 - 10:07:10 EST


Hi Suzuki,
On 9/17/18 12:41 PM, Suzuki K Poulose wrote:
> On arm64 VTTBR_EL2:BADDR holds the base address for the stage2
> translation table. The Arm ARM mandates that the bits BADDR[x-1:0]
> should be 0, where 'x' is defined for a given IPA Size and the
> number of levels for a translation granule size. It is defined
> using some magical constants. This patch is a reverse engineered
> implementation to calculate the 'x' at runtime for a given ipa and
> number of page table levels. See patch for more details.
>
> Cc: Marc Zyngier <marc.zyngier@xxxxxxx>
> Cc: Christoffer Dall <cdall@xxxxxxxxxx>
> Signed-off-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>

> ---
> Changes since V3:
> - Update reference to latest ARM ARM and improve commentary
> ---
> arch/arm64/include/asm/kvm_arm.h | 63 +++++++++++++++++++++++++++++---
> arch/arm64/include/asm/kvm_mmu.h | 25 ++++++++++++-
> 2 files changed, 81 insertions(+), 7 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
> index 14317b3a1820..3fb1d440be6e 100644
> --- a/arch/arm64/include/asm/kvm_arm.h
> +++ b/arch/arm64/include/asm/kvm_arm.h
> @@ -123,7 +123,6 @@
> #define VTCR_EL2_SL0_MASK (3 << VTCR_EL2_SL0_SHIFT)
> #define VTCR_EL2_SL0_LVL1 (1 << VTCR_EL2_SL0_SHIFT)
> #define VTCR_EL2_T0SZ_MASK 0x3f
> -#define VTCR_EL2_T0SZ_40B 24
> #define VTCR_EL2_VS_SHIFT 19
> #define VTCR_EL2_VS_8BIT (0 << VTCR_EL2_VS_SHIFT)
> #define VTCR_EL2_VS_16BIT (1 << VTCR_EL2_VS_SHIFT)
> @@ -140,11 +139,8 @@
> * Note that when using 4K pages, we concatenate two first level page tables
> * together. With 16K pages, we concatenate 16 first level page tables.
> *
> - * The magic numbers used for VTTBR_X in this patch can be found in Tables
> - * D4-23 and D4-25 in ARM DDI 0487A.b.
> */
>
> -#define VTCR_EL2_T0SZ_IPA VTCR_EL2_T0SZ_40B
> #define VTCR_EL2_COMMON_BITS (VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
> VTCR_EL2_IRGN0_WBWA | VTCR_EL2_RES1)
>
> @@ -175,9 +171,64 @@
> #endif
>
> #define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
> -#define VTTBR_X (VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
> +/*
> + * ARM VMSAv8-64 defines an algorithm for finding the translation table
> + * descriptors in section D4.2.8 in ARM DDI 0487C.a.
> + *
> + * The algorithm defines the expectations on the BaseAddress (for the page
> + * table) bits resolved at each level based on the page size, entry level
> + * and T0SZ. The variable "x" in the algorithm also affects the VTTBR:BADDR
> + * for stage2 page table.
> + *
> + * The value of "x" is calculated as :
> + * x = Magic_N - T0SZ

What is not crystal clear to me is the "if SL0b,c = n" case where x get
a value not based on Magic_N. Please could you explain why it is not
relevant?

Thanks

Eric
> + *
> + * where Magic_N is an integer depending on the page size and the entry
> + * level of the page table as below:
> + *
> + * --------------------------------------------
> + * | Entry level | 4K 16K 64K |
> + * --------------------------------------------
> + * | Level: 0 (4 levels) | 28 | - | - |
> + * --------------------------------------------
> + * | Level: 1 (3 levels) | 37 | 31 | 25 |
> + * --------------------------------------------
> + * | Level: 2 (2 levels) | 46 | 42 | 38 |
> + * --------------------------------------------
> + * | Level: 3 (1 level) | - | 53 | 51 |
> + * --------------------------------------------
> + *
> + * We have a magic formula for the Magic_N below:
> + *
> + * Magic_N(PAGE_SIZE, Level) = 64 - ((PAGE_SHIFT - 3) * Number_of_levels)
> + *
> + * where Number_of_levels = (4 - Level). We are only interested in the
> + * value for Entry_Level for the stage2 page table.
> + *
> + * So, given that T0SZ = (64 - IPA_SHIFT), we can compute 'x' as follows:
> + *
> + * x = (64 - ((PAGE_SHIFT - 3) * Number_of_levels)) - (64 - IPA_SHIFT)
> + * = IPA_SHIFT - ((PAGE_SHIFT - 3) * Number of levels)
> + *
> + * Here is one way to explain the Magic Formula:
> + *
> + * x = log2(Size_of_Entry_Level_Table)
> + *
> + * Since, we can resolve (PAGE_SHIFT - 3) bits at each level, and another
> + * PAGE_SHIFT bits in the PTE, we have :
> + *
> + * Bits_Entry_level = IPA_SHIFT - ((PAGE_SHIFT - 3) * (n - 1) + PAGE_SHIFT)
> + * = IPA_SHIFT - (PAGE_SHIFT - 3) * n - 3
> + * where n = number of levels, and since each pointer is 8bytes, we have:
> + *
> + * x = Bits_Entry_Level + 3
> + * = IPA_SHIFT - (PAGE_SHIFT - 3) * n
> + *
> + * The only constraint here is that, we have to find the number of page table
> + * levels for a given IPA size (which we do, see stage2_pt_levels())
> + */
> +#define ARM64_VTTBR_X(ipa, levels) ((ipa) - ((levels) * (PAGE_SHIFT - 3)))
>
> -#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
> #define VTTBR_VMID_SHIFT (UL(48))
> #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
>
> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
> index 7342d2c51773..ac3ca9690bad 100644
> --- a/arch/arm64/include/asm/kvm_mmu.h
> +++ b/arch/arm64/include/asm/kvm_mmu.h
> @@ -145,7 +145,6 @@ static inline unsigned long __kern_hyp_va(unsigned long v)
> #define kvm_phys_shift(kvm) KVM_PHYS_SHIFT
> #define kvm_phys_size(kvm) (_AC(1, ULL) << kvm_phys_shift(kvm))
> #define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - _AC(1, ULL))
> -#define kvm_vttbr_baddr_mask(kvm) VTTBR_BADDR_MASK
>
> static inline bool kvm_page_empty(void *ptr)
> {
> @@ -520,5 +519,29 @@ static inline int hyp_map_aux_data(void)
>
> #define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr)
>
> +/*
> + * Get the magic number 'x' for VTTBR:BADDR of this KVM instance.
> + * With v8.2 LVA extensions, 'x' should be a minimum of 6 with
> + * 52bit IPS.
> + */
> +static inline int arm64_vttbr_x(u32 ipa_shift, u32 levels)
> +{
> + int x = ARM64_VTTBR_X(ipa_shift, levels);
> +
> + return (IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && x < 6) ? 6 : x;
> +}
> +
> +static inline u64 vttbr_baddr_mask(u32 ipa_shift, u32 levels)
> +{
> + unsigned int x = arm64_vttbr_x(ipa_shift, levels);
> +
> + return GENMASK_ULL(PHYS_MASK_SHIFT - 1, x);
> +}
> +
> +static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm)
> +{
> + return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm));
> +}
> +
> #endif /* __ASSEMBLY__ */
> #endif /* __ARM64_KVM_MMU_H__ */
>