diff options
65 files changed, 1118 insertions, 565 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 07e87a7c665d..cd209f7730af 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -123,6 +123,37 @@ memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the flag KVM_VM_MIPS_VZ. +On arm64, the physical address size for a VM (IPA Size limit) is limited +to 40bits by default. The limit can be configured if the host supports the +extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use +KVM_VM_TYPE_ARM_IPA_SIZE(IPA_Bits) to set the size in the machine type +identifier, where IPA_Bits is the maximum width of any physical +address used by the VM. The IPA_Bits is encoded in bits[7-0] of the +machine type identifier. + +e.g, to configure a guest to use 48bit physical address size : + + vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48)); + +The requested size (IPA_Bits) must be : + 0 - Implies default size, 40bits (for backward compatibility) + + or + + N - Implies N bits, where N is a positive integer such that, + 32 <= N <= Host_IPA_Limit + +Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and +is dependent on the CPU capability and the kernel configuration. The limit can +be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION +ioctl() at run-time. + +Please note that configuring the IPA size does not affect the capability +exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects +size of the address translated by the stage2 level (guest physical to +host physical address translations). + + 4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST diff --git a/MAINTAINERS b/MAINTAINERS index 1610fb26bdac..86e019c7b0fa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12260,6 +12260,7 @@ F: Documentation/networking/rds.txt RDT - RESOURCE ALLOCATION M: Fenghua Yu <fenghua.yu@intel.com> +M: Reinette Chatre <reinette.chatre@intel.com> L: linux-kernel@vger.kernel.org S: Supported F: arch/x86/kernel/cpu/intel_rdt* @@ -15924,6 +15925,7 @@ F: net/x25/ X86 ARCHITECTURE (32-BIT AND 64-BIT) M: Thomas Gleixner <tglx@linutronix.de> M: Ingo Molnar <mingo@redhat.com> +M: Borislav Petkov <bp@alien8.de> R: "H. Peter Anvin" <hpa@zytor.com> M: x86@kernel.org L: linux-kernel@vger.kernel.org @@ -15952,6 +15954,15 @@ M: Borislav Petkov <bp@alien8.de> S: Maintained F: arch/x86/kernel/cpu/microcode/* +X86 MM +M: Dave Hansen <dave.hansen@linux.intel.com> +M: Andy Lutomirski <luto@kernel.org> +M: Peter Zijlstra <peterz@infradead.org> +L: linux-kernel@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm +S: Maintained +F: arch/x86/mm/ + X86 PLATFORM DRIVERS M: Darren Hart <dvhart@infradead.org> M: Andy Shevchenko <andy@infradead.org> @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Merciless Moray # *DOCUMENTATION* diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 3ab8b3781bfe..c3f1f9b304b7 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -133,8 +133,7 @@ * space. */ #define KVM_PHYS_SHIFT (40) -#define KVM_PHYS_SIZE (_AC(1, ULL) << KVM_PHYS_SHIFT) -#define KVM_PHYS_MASK (KVM_PHYS_SIZE - _AC(1, ULL)) + #define PTRS_PER_S2_PGD (_AC(1, ULL) << (KVM_PHYS_SHIFT - 30)) /* Virtualization Translation Control Register (VTCR) bits */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 3ad482d2f1eb..5ca5d9af0c26 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -273,7 +273,7 @@ static inline void __cpu_init_stage2(void) kvm_call_hyp(__init_stage2_translation); } -static inline int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext) +static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) { return 0; } @@ -354,4 +354,15 @@ static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {} struct kvm *kvm_arch_alloc_vm(void); void kvm_arch_free_vm(struct kvm *kvm); +static inline int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type) +{ + /* + * On 32bit ARM, VMs get a static 40bit IPA stage2 setup, + * so any non-zero value used as type is illegal. + */ + if (type) + return -EINVAL; + return 0; +} + #endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 265ea9cf7df7..5ad1a54f98dc 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -35,16 +35,12 @@ addr; \ }) -/* - * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels. - */ -#define KVM_MMU_CACHE_MIN_PAGES 2 - #ifndef __ASSEMBLY__ #include <linux/highmem.h> #include <asm/cacheflush.h> #include <asm/cputype.h> +#include <asm/kvm_arm.h> #include <asm/kvm_hyp.h> #include <asm/pgalloc.h> #include <asm/stage2_pgtable.h> @@ -52,6 +48,13 @@ /* Ensure compatibility with arm64 */ #define VA_BITS 32 +#define kvm_phys_shift(kvm) KVM_PHYS_SHIFT +#define kvm_phys_size(kvm) (1ULL << kvm_phys_shift(kvm)) +#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - 1ULL) +#define kvm_vttbr_baddr_mask(kvm) VTTBR_BADDR_MASK + +#define stage2_pgd_size(kvm) (PTRS_PER_S2_PGD * sizeof(pgd_t)) + int create_hyp_mappings(void *from, void *to, pgprot_t prot); int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, @@ -355,6 +358,8 @@ static inline int hyp_map_aux_data(void) #define kvm_phys_to_vttbr(addr) (addr) +static inline void kvm_set_ipa_limit(void) {} + #endif /* !__ASSEMBLY__ */ #endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h index 460d616bb2d6..f6a7ea805232 100644 --- a/arch/arm/include/asm/stage2_pgtable.h +++ b/arch/arm/include/asm/stage2_pgtable.h @@ -19,43 +19,53 @@ #ifndef __ARM_S2_PGTABLE_H_ #define __ARM_S2_PGTABLE_H_ -#define stage2_pgd_none(pgd) pgd_none(pgd) -#define stage2_pgd_clear(pgd) pgd_clear(pgd) -#define stage2_pgd_present(pgd) pgd_present(pgd) -#define stage2_pgd_populate(pgd, pud) pgd_populate(NULL, pgd, pud) -#define stage2_pud_offset(pgd, address) pud_offset(pgd, address) -#define stage2_pud_free(pud) pud_free(NULL, pud) - -#define stage2_pud_none(pud) pud_none(pud) -#define stage2_pud_clear(pud) pud_clear(pud) -#define stage2_pud_present(pud) pud_present(pud) -#define stage2_pud_populate(pud, pmd) pud_populate(NULL, pud, pmd) -#define stage2_pmd_offset(pud, address) pmd_offset(pud, address) -#define stage2_pmd_free(pmd) pmd_free(NULL, pmd) - -#define stage2_pud_huge(pud) pud_huge(pud) +/* + * kvm_mmu_cache_min_pages() is the number of pages required + * to install a stage-2 translation. We pre-allocate the entry + * level table at VM creation. Since we have a 3 level page-table, + * we need only two pages to add a new mapping. + */ +#define kvm_mmu_cache_min_pages(kvm) 2 + +#define stage2_pgd_none(kvm, pgd) pgd_none(pgd) +#define stage2_pgd_clear(kvm, pgd) pgd_clear(pgd) +#define stage2_pgd_present(kvm, pgd) pgd_present(pgd) +#define stage2_pgd_populate(kvm, pgd, pud) pgd_populate(NULL, pgd, pud) +#define stage2_pud_offset(kvm, pgd, address) pud_offset(pgd, address) +#define stage2_pud_free(kvm, pud) pud_free(NULL, pud) + +#define stage2_pud_none(kvm, pud) pud_none(pud) +#define stage2_pud_clear(kvm, pud) pud_clear(pud) +#define stage2_pud_present(kvm, pud) pud_present(pud) +#define stage2_pud_populate(kvm, pud, pmd) pud_populate(NULL, pud, pmd) +#define stage2_pmd_offset(kvm, pud, address) pmd_offset(pud, address) +#define stage2_pmd_free(kvm, pmd) pmd_free(NULL, pmd) + +#define stage2_pud_huge(kvm, pud) pud_huge(pud) /* Open coded p*d_addr_end that can deal with 64bit addresses */ -static inline phys_addr_t stage2_pgd_addr_end(phys_addr_t addr, phys_addr_t end) +static inline phys_addr_t +stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) { phys_addr_t boundary = (addr + PGDIR_SIZE) & PGDIR_MASK; return (boundary - 1 < end - 1) ? boundary : end; } -#define stage2_pud_addr_end(addr, end) (end) +#define stage2_pud_addr_end(kvm, addr, end) (end) -static inline phys_addr_t stage2_pmd_addr_end(phys_addr_t addr, phys_addr_t end) +static inline phys_addr_t +stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) { phys_addr_t boundary = (addr + PMD_SIZE) & PMD_MASK; return (boundary - 1 < end - 1) ? boundary : end; } -#define stage2_pgd_index(addr) pgd_index(addr) +#define stage2_pgd_index(kvm, addr) pgd_index(addr) -#define stage2_pte_table_empty(ptep) kvm_page_empty(ptep) -#define stage2_pmd_table_empty(pmdp) kvm_page_empty(pmdp) -#define stage2_pud_table_empty(pudp) false +#define stage2_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) +#define stage2_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) +#define stage2_pud_table_empty(kvm, pudp) false #endif /* __ARM_S2_PGTABLE_H_ */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 1717ba1db35d..072cc1c970c2 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -530,6 +530,26 @@ void arm64_set_ssbd_mitigation(bool state); static inline void arm64_set_ssbd_mitigation(bool state) {} #endif +static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) +{ + switch (parange) { + case 0: return 32; + case 1: return 36; + case 2: return 40; + case 3: return 42; + case 4: return 44; + case 5: return 48; + case 6: return 52; + /* + * A future PE could use a value unknown to the kernel. + * However, by the "D10.1.4 Principles of the ID scheme + * for fields in ID registers", ARM DDI 0487C.a, any new + * value is guaranteed to be higher than what we know already. + * As a safe limit, we return the limit supported by the kernel. + */ + default: return CONFIG_ARM64_PA_BITS; + } +} #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index aa45df752a16..6e324d1f1231 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -107,6 +107,7 @@ #define VTCR_EL2_RES1 (1 << 31) #define VTCR_EL2_HD (1 << 22) #define VTCR_EL2_HA (1 << 21) +#define VTCR_EL2_PS_SHIFT TCR_EL2_PS_SHIFT #define VTCR_EL2_PS_MASK TCR_EL2_PS_MASK #define VTCR_EL2_TG0_MASK TCR_TG0_MASK #define VTCR_EL2_TG0_4K TCR_TG0_4K @@ -120,62 +121,149 @@ #define VTCR_EL2_IRGN0_WBWA TCR_IRGN0_WBWA #define VTCR_EL2_SL0_SHIFT 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) +#define VTCR_EL2_T0SZ(x) TCR_T0SZ(x) + /* * We configure the Stage-2 page tables to always restrict the IPA space to be * 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are * not known to exist and will break with this configuration. * - * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time - * (see hyp-init.S). + * The VTCR_EL2 is configured per VM and is initialised in kvm_arm_setup_stage2(). * * 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) -#ifdef CONFIG_ARM64_64K_PAGES /* - * Stage2 translation configuration: - * 64kB pages (TG0 = 1) - * 2 level page tables (SL = 1) + * VTCR_EL2:SL0 indicates the entry level for Stage2 translation. + * Interestingly, it depends on the page size. + * See D.10.2.121, VTCR_EL2, in ARM DDI 0487C.a + * + * ----------------------------------------- + * | Entry level | 4K | 16K/64K | + * ------------------------------------------ + * | Level: 0 | 2 | - | + * ------------------------------------------ + * | Level: 1 | 1 | 2 | + * ------------------------------------------ + * | Level: 2 | 0 | 1 | + * ------------------------------------------ + * | Level: 3 | - | 0 | + * ------------------------------------------ + * + * The table roughly translates to : + * + * SL0(PAGE_SIZE, Entry_level) = TGRAN_SL0_BASE - Entry_Level + * + * Where TGRAN_SL0_BASE is a magic number depending on the page size: + * TGRAN_SL0_BASE(4K) = 2 + * TGRAN_SL0_BASE(16K) = 3 + * TGRAN_SL0_BASE(64K) = 3 + * provided we take care of ruling out the unsupported cases and + * Entry_Level = 4 - Number_of_levels. + * */ -#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_64K | VTCR_EL2_SL0_LVL1) -#define VTTBR_X_TGRAN_MAGIC 38 +#ifdef CONFIG_ARM64_64K_PAGES + +#define VTCR_EL2_TGRAN VTCR_EL2_TG0_64K +#define VTCR_EL2_TGRAN_SL0_BASE 3UL + #elif defined(CONFIG_ARM64_16K_PAGES) -/* - * Stage2 translation configuration: - * 16kB pages (TG0 = 2) - * 2 level page tables (SL = 1) - */ -#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_16K | VTCR_EL2_SL0_LVL1) -#define VTTBR_X_TGRAN_MAGIC 42 + +#define VTCR_EL2_TGRAN VTCR_EL2_TG0_16K +#define VTCR_EL2_TGRAN_SL0_BASE 3UL + #else /* 4K */ -/* - * Stage2 translation configuration: - * 4kB pages (TG0 = 0) - * 3 level page tables (SL = 1) - */ -#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_4K | VTCR_EL2_SL0_LVL1) -#define VTTBR_X_TGRAN_MAGIC 37 + +#define VTCR_EL2_TGRAN VTCR_EL2_TG0_4K +#define VTCR_EL2_TGRAN_SL0_BASE 2UL + #endif -#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS) -#define VTTBR_X (VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA) +#define VTCR_EL2_LVLS_TO_SL0(levels) \ + ((VTCR_EL2_TGRAN_SL0_BASE - (4 - (levels))) << VTCR_EL2_SL0_SHIFT) +#define VTCR_EL2_SL0_TO_LVLS(sl0) \ + ((sl0) + 4 - VTCR_EL2_TGRAN_SL0_BASE) +#define VTCR_EL2_LVLS(vtcr) \ + VTCR_EL2_SL0_TO_LVLS(((vtcr) & VTCR_EL2_SL0_MASK) >> VTCR_EL2_SL0_SHIFT) + +#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN) +#define VTCR_EL2_IPA(vtcr) (64 - ((vtcr) & VTCR_EL2_T0SZ_MASK)) + +/* + * 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 translation table + * addresses for each level, based on PAGE_SIZE, entry level + * and the translation table size (T0SZ). The variable "x" in the + * algorithm determines the alignment of a table base address at a given + * level and thus determines the alignment of VTTBR:BADDR for stage2 + * page table entry level. + * Since the number of bits resolved at the entry level could vary + * depending on the T0SZ, the value of "x" is defined based on a + * Magic constant for a given PAGE_SIZE and Entry Level. The + * intermediate levels must be always aligned to the PAGE_SIZE (i.e, + * x = PAGE_SHIFT). + * + * The value of "x" for entry level is calculated as : + * x = Magic_N - T0SZ + * + * 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) @@ -223,6 +311,13 @@ /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ #define HPFAR_MASK (~UL(0xf)) +/* + * We have + * PAR [PA_Shift - 1 : 12] = PA [PA_Shift - 1 : 12] + * HPFAR [PA_Shift - 9 : 4] = FIPA [PA_Shift - 1 : 12] + */ +#define PAR_TO_HPFAR(par) \ + (((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8) #define kvm_arm_exception_type \ {0, "IRQ" }, \ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 102b5a5c47b6..aea01a09eb94 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -30,6 +30,7 @@ #define ARM_EXCEPTION_IRQ 0 #define ARM_EXCEPTION_EL1_SERROR 1 #define ARM_EXCEPTION_TRAP 2 +#define ARM_EXCEPTION_IL 3 /* The hyp-stub will return this for any kvm_call_hyp() call */ #define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR @@ -72,8 +73,6 @@ extern void __vgic_v3_init_lrs(void); extern u32 __kvm_get_mdcr_el2(void); -extern u32 __init_stage2_translation |