From 2d58b733c87689d3d5144e4ac94ea861cc729145 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 14 Jan 2014 19:13:10 +0000 Subject: arm64: KVM: force cache clean on page fault when caches are off In order for the guest with caches off to observe data written contained in a given page, we need to make sure that page is committed to memory, and not just hanging in the cache (as guest accesses are completely bypassing the cache until it decides to enable it). For this purpose, hook into the coherent_icache_guest_page function and flush the region if the guest SCTLR_EL1 register doesn't show the MMU and caches as being enabled. The function also get renamed to coherent_cache_guest_page. Signed-off-by: Marc Zyngier Reviewed-by: Catalin Marinas Reviewed-by: Christoffer Dall --- arch/arm64/include/asm/kvm_mmu.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 7f1f9408ff66..6eaf69b5e42c 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -106,7 +106,6 @@ static inline bool kvm_is_write_fault(unsigned long esr) return true; } -static inline void kvm_clean_dcache_area(void *addr, size_t size) {} static inline void kvm_clean_pgd(pgd_t *pgd) {} static inline void kvm_clean_pmd_entry(pmd_t *pmd) {} static inline void kvm_clean_pte(pte_t *pte) {} @@ -124,9 +123,19 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) struct kvm; -static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva, - unsigned long size) +#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l)) + +static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) { + return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; +} + +static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, + unsigned long size) +{ + if (!vcpu_has_cache_enabled(vcpu)) + kvm_flush_dcache_to_poc((void *)hva, size); + if (!icache_is_aliasing()) { /* PIPT */ flush_icache_range(hva, hva + size); } else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */ @@ -135,7 +144,6 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva, } } -#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l)) #define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x)) #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 2072d29c46b73e39b3c6c56c6027af77086f45fd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 21 Jan 2014 10:55:17 +0000 Subject: arm64: KVM: allows discrimination of AArch32 sysreg access The current handling of AArch32 trapping is slightly less than perfect, as it is not possible (from a handler point of view) to distinguish it from an AArch64 access, nor to tell a 32bit from a 64bit access either. Fix this by introducing two additional flags: - is_aarch32: true if the access was made in AArch32 mode - is_32bit: true if is_aarch32 == true and a MCR/MRC instruction was used to perform the access (as opposed to MCRR/MRRC). This allows a handler to cover all the possible conditions in which a system register gets trapped. Signed-off-by: Marc Zyngier Acked-by: Christoffer Dall --- arch/arm64/kvm/sys_regs.c | 6 ++++++ arch/arm64/kvm/sys_regs.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'arch/arm64') diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 02e9d09e1d80..bf03e0fadf1f 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -437,6 +437,8 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run) u32 hsr = kvm_vcpu_get_hsr(vcpu); int Rt2 = (hsr >> 10) & 0xf; + params.is_aarch32 = true; + params.is_32bit = false; params.CRm = (hsr >> 1) & 0xf; params.Rt = (hsr >> 5) & 0xf; params.is_write = ((hsr & 1) == 0); @@ -480,6 +482,8 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run) struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); + params.is_aarch32 = true; + params.is_32bit = true; params.CRm = (hsr >> 1) & 0xf; params.Rt = (hsr >> 5) & 0xf; params.is_write = ((hsr & 1) == 0); @@ -549,6 +553,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) struct sys_reg_params params; unsigned long esr = kvm_vcpu_get_hsr(vcpu); + params.is_aarch32 = false; + params.is_32bit = false; params.Op0 = (esr >> 20) & 3; params.Op1 = (esr >> 14) & 0x7; params.CRn = (esr >> 10) & 0xf; diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index d50d3722998e..d411e251412c 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -30,6 +30,8 @@ struct sys_reg_params { u8 Op2; u8 Rt; bool is_write; + bool is_aarch32; + bool is_32bit; /* Only valid if is_aarch32 is true */ }; struct sys_reg_desc { -- cgit v1.2.3 From 4d44923b17bff283c002ed961373848284aaff1b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 14 Jan 2014 18:00:55 +0000 Subject: arm64: KVM: trap VM system registers until MMU and caches are ON In order to be able to detect the point where the guest enables its MMU and caches, trap all the VM related system registers. Once we see the guest enabling both the MMU and the caches, we can go back to a saner mode of operation, which is to leave these registers in complete control of the guest. Signed-off-by: Marc Zyngier Reviewed-by: Catalin Marinas Reviewed-by: Christoffer Dall --- arch/arm64/include/asm/kvm_arm.h | 3 +- arch/arm64/include/asm/kvm_asm.h | 3 +- arch/arm64/kvm/sys_regs.c | 90 ++++++++++++++++++++++++++++++++++------ 3 files changed, 82 insertions(+), 14 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 0eb398655378..00fbaa75dc7b 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -62,6 +62,7 @@ * RW: 64bit by default, can be overriden for 32bit VMs * TAC: Trap ACTLR * TSC: Trap SMC + * TVM: Trap VM ops (until M+C set in SCTLR_EL1) * TSW: Trap cache operations by set/way * TWE: Trap WFE * TWI: Trap WFI @@ -74,7 +75,7 @@ * SWIO: Turn set/way invalidates into set/way clean+invalidate */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ - HCR_BSU_IS | HCR_FB | HCR_TAC | \ + HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_IMO | HCR_FMO | \ HCR_SWIO | HCR_TIDCP | HCR_RW) #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index b25763bc0ec4..9fcd54b1e16d 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -79,7 +79,8 @@ #define c13_TID_URW (TPIDR_EL0 * 2) /* Thread ID, User R/W */ #define c13_TID_URO (TPIDRRO_EL0 * 2)/* Thread ID, User R/O */ #define c13_TID_PRIV (TPIDR_EL1 * 2) /* Thread ID, Privileged */ -#define c10_AMAIR (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */ +#define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */ +#define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */ #define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */ #define NR_CP15_REGS (NR_SYS_REGS * 2) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index bf03e0fadf1f..2097e5ecba42 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -120,6 +120,46 @@ done: return true; } +/* + * Generic accessor for VM registers. Only called as long as HCR_TVM + * is set. + */ +static bool access_vm_reg(struct kvm_vcpu *vcpu, + const struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + unsigned long val; + + BUG_ON(!p->is_write); + + val = *vcpu_reg(vcpu, p->Rt); + if (!p->is_aarch32) { + vcpu_sys_reg(vcpu, r->reg) = val; + } else { + vcpu_cp15(vcpu, r->reg) = val & 0xffffffffUL; + if (!p->is_32bit) + vcpu_cp15(vcpu, r->reg + 1) = val >> 32; + } + return true; +} + +/* + * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set. If the + * guest enables the MMU, we stop trapping the VM sys_regs and leave + * it in complete control of the caches. + */ +static bool access_sctlr(struct kvm_vcpu *vcpu, + const struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + access_vm_reg(vcpu, p, r); + + if (vcpu_has_cache_enabled(vcpu)) /* MMU+Caches enabled? */ + vcpu->arch.hcr_el2 &= ~HCR_TVM; + + return true; +} + /* * We could trap ID_DFR0 and tell the guest we don't support performance * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was @@ -185,32 +225,32 @@ static const struct sys_reg_desc sys_reg_descs[] = { NULL, reset_mpidr, MPIDR_EL1 }, /* SCTLR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000), - NULL, reset_val, SCTLR_EL1, 0x00C50078 }, + access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 }, /* CPACR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010), NULL, reset_val, CPACR_EL1, 0 }, /* TTBR0_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000), - NULL, reset_unknown, TTBR0_EL1 }, + access_vm_reg, reset_unknown, TTBR0_EL1 }, /* TTBR1_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001), - NULL, reset_unknown, TTBR1_EL1 }, + access_vm_reg, reset_unknown, TTBR1_EL1 }, /* TCR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010), - NULL, reset_val, TCR_EL1, 0 }, + access_vm_reg, reset_val, TCR_EL1, 0 }, /* AFSR0_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000), - NULL, reset_unknown, AFSR0_EL1 }, + access_vm_reg, reset_unknown, AFSR0_EL1 }, /* AFSR1_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001), - NULL, reset_unknown, AFSR1_EL1 }, + access_vm_reg, reset_unknown, AFSR1_EL1 }, /* ESR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000), - NULL, reset_unknown, ESR_EL1 }, + access_vm_reg, reset_unknown, ESR_EL1 }, /* FAR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000), - NULL, reset_unknown, FAR_EL1 }, + access_vm_reg, reset_unknown, FAR_EL1 }, /* PAR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000), NULL, reset_unknown, PAR_EL1 }, @@ -224,17 +264,17 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* MAIR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000), - NULL, reset_unknown, MAIR_EL1 }, + access_vm_reg, reset_unknown, MAIR_EL1 }, /* AMAIR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000), - NULL, reset_amair_el1, AMAIR_EL1 }, + access_vm_reg, reset_amair_el1, AMAIR_EL1 }, /* VBAR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000), NULL, reset_val, VBAR_EL1, 0 }, /* CONTEXTIDR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001), - NULL, reset_val, CONTEXTIDR_EL1, 0 }, + access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 }, /* TPIDR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100), NULL, reset_unknown, TPIDR_EL1 }, @@ -305,14 +345,32 @@ static const struct sys_reg_desc sys_reg_descs[] = { NULL, reset_val, FPEXC32_EL2, 0x70 }, }; -/* Trapped cp15 registers */ +/* + * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding, + * depending on the way they are accessed (as a 32bit or a 64bit + * register). + */ static const struct sys_reg_desc cp15_regs[] = { + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, + { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR }, + { Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR }, + { Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR }, + { Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR }, + { Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR }, + { Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR }, + { Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR }, + { Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR }, + /* * DC{C,I,CI}SW operations: */ { Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw }, { Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw }, { Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw }, + { Op1( 0), CRn( 9), CRm(12), Op2( 0), pm_fake }, { Op1( 0), CRn( 9), CRm(12), Op2( 1), pm_fake }, { Op1( 0), CRn( 9), CRm(12), Op2( 2), pm_fake }, @@ -326,6 +384,14 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 9), CRm(14), Op2( 0), pm_fake }, { Op1( 0), CRn( 9), CRm(14), Op2( 1), pm_fake }, { Op1( 0), CRn( 9), CRm(14), Op2( 2), pm_fake }, + + { Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR }, + { Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR }, + { Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 }, + { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 }, + { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID }, + + { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 }, }; /* Target specific emulation tables */ -- cgit v1.2.3 From a3c8bd31af260a17d626514f636849ee1cd1f63e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 18 Feb 2014 14:29:03 +0000 Subject: ARM: KVM: introduce kvm_p*d_addr_end The use of p*d_addr_end with stage-2 translation is slightly dodgy, as the IPA is 40bits, while all the p*d_addr_end helpers are taking an unsigned long (arm64 is fine with that as unligned long is 64bit). The fix is to introduce 64bit clean versions of the same helpers, and use them in the stage-2 page table code. Signed-off-by: Marc Zyngier Acked-by: Catalin Marinas Reviewed-by: Christoffer Dall --- arch/arm/include/asm/kvm_mmu.h | 13 +++++++++++++ arch/arm/kvm/mmu.c | 10 +++++----- arch/arm64/include/asm/kvm_mmu.h | 4 ++++ 3 files changed, 22 insertions(+), 5 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 6d0f3d3023b7..891afe78311a 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -114,6 +114,19 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) pmd_val(*pmd) |= L_PMD_S2_RDWR; } +/* Open coded p*d_addr_end that can deal with 64bit addresses */ +#define kvm_pgd_addr_end(addr, end) \ +({ u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + +#define kvm_pud_addr_end(addr,end) (end) + +#define kvm_pmd_addr_end(addr, end) \ +({ u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + struct kvm; static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index fc71a8df0e13..c1c08b240f35 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -145,7 +145,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, pgd = pgdp + pgd_index(addr); pud = pud_offset(pgd, addr); if (pud_none(*pud)) { - addr = pud_addr_end(addr, end); + addr = kvm_pud_addr_end(addr, end); continue; } @@ -155,13 +155,13 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, * move on. */ clear_pud_entry(kvm, pud, addr); - addr = pud_addr_end(addr, end); + addr = kvm_pud_addr_end(addr, end); continue; } pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { - addr = pmd_addr_end(addr, end); + addr = kvm_pmd_addr_end(addr, end); continue; } @@ -176,10 +176,10 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, */ if (kvm_pmd_huge(*pmd) || page_empty(pte)) { clear_pmd_entry(kvm, pmd, addr); - next = pmd_addr_end(addr, end); + next = kvm_pmd_addr_end(addr, end); if (page_empty(pmd) && !page_empty(pud)) { clear_pud_entry(kvm, pud, addr); - next = pud_addr_end(addr, end); + next = kvm_pud_addr_end(addr, end); } } diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 6eaf69b5e42c..00c0cc8b8045 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -121,6 +121,10 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) pmd_val(*pmd) |= PMD_S2_RDWR; } +#define kvm_pgd_addr_end(addr, end) pgd_addr_end(addr, end) +#define kvm_pud_addr_end(addr, end) pud_addr_end(addr, end) +#define kvm_pmd_addr_end(addr, end) pmd_addr_end(addr, end) + struct kvm; #define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l)) -- cgit v1.2.3 From 9d218a1fcf4c6b759d442ef702842fae92e1ea61 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 15 Jan 2014 12:50:23 +0000 Subject: arm64: KVM: flush VM pages before letting the guest enable caches When the guest runs with caches disabled (like in an early boot sequence, for example), all the writes are diectly going to RAM, bypassing the caches altogether. Once the MMU and caches are enabled, whatever sits in the cache becomes suddenly visible, which isn't what the guest expects. A way to avoid this potential disaster is to invalidate the cache when the MMU is being turned on. For this, we hook into the SCTLR_EL1 trapping code, and scan the stage-2 page tables, invalidating the pages/sections that have already been mapped in. Signed-off-by: Marc Zyngier Reviewed-by: Catalin Marinas Reviewed-by: Christoffer Dall --- arch/arm/include/asm/kvm_mmu.h | 2 + arch/arm/kvm/mmu.c | 93 ++++++++++++++++++++++++++++++++++++++++ arch/arm64/include/asm/kvm_mmu.h | 2 + arch/arm64/kvm/sys_regs.c | 5 ++- 4 files changed, 101 insertions(+), 1 deletion(-) (limited to 'arch/arm64') diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 891afe78311a..eb85b81eea6f 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -155,6 +155,8 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, #define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l)) #define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x)) +void stage2_flush_vm(struct kvm *kvm); + #endif /* !__ASSEMBLY__ */ #endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index c1c08b240f35..d7e998c6a08f 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -187,6 +187,99 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, } } +static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, + phys_addr_t addr, phys_addr_t end) +{ + pte_t *pte; + + pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte)) { + hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); + kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE); + } + } while (pte++, addr += PAGE_SIZE, addr != end); +} + +static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, + phys_addr_t addr, phys_addr_t end) +{ + pmd_t *pmd; + phys_addr_t next; + + pmd = pmd_offset(pud, addr); + do { + next = kvm_pmd_addr_end(addr, end); + if (!pmd_none(*pmd)) { + if (kvm_pmd_huge(*pmd)) { + hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); + kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE); + } else { + stage2_flush_ptes(kvm, pmd, addr, next); + } + } + } while (pmd++, addr = next, addr != end); +} + +static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd, + phys_addr_t addr, phys_addr_t end) +{ + pud_t *pud; + phys_addr_t next; + + pud = pud_offset(pgd, addr); + do { + next = kvm_pud_addr_end(addr, end); + if (!pud_none(*pud)) { + if (pud_huge(*pud)) { + hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT); + kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE); + } else { + stage2_flush_pmds(kvm, pud, addr, next); + } + } + } while (pud++, addr = next, addr != end); +} + +static void stage2_flush_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t end = addr + PAGE_SIZE * memslot->npages; + phys_addr_t next; + pgd_t *pgd; + + pgd = kvm->arch.pgd + pgd_index(addr); + do { + next = kvm_pgd_addr_end(addr, end); + stage2_flush_puds(kvm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +/** + * stage2_flush_vm - Invalidate cache for pages mapped in stage 2 + * @kvm: The struct kvm pointer + * + * Go through the stage 2 page tables and invalidate any cache lines + * backing memory already mapped to the VM. + */ +void stage2_flush_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_flush_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); +} + /** * free_boot_hyp_pgd - free HYP boot page tables * diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 00c0cc8b8045..7d29847a893b 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -150,5 +150,7 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva, #define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x)) +void stage2_flush_vm(struct kvm *kvm); + #endif /* __ASSEMBLY__ */ #endif /* __ARM64_KVM_MMU_H__ */ diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 2097e5ecba42..03244582bc55 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -154,8 +155,10 @@ static bool access_sctlr(struct kvm_vcpu *vcpu, { access_vm_reg(vcpu, p, r); - if (vcpu_has_cache_enabled(vcpu)) /* MMU+Caches enabled? */ + if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */ vcpu->arch.hcr_el2 &= ~HCR_TVM; + stage2_flush_vm(vcpu->kvm); + } return true; } -- cgit v1.2.3