From 8f20a3ab27342171462781cef4637c18d3dbc5f8 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Thu, 17 Apr 2014 13:25:33 +0200 Subject: KVM: PPC: E500: Add dcbtls emulation The dcbtls instruction is able to lock data inside the L1 cache. We don't want to give the guest actual access to hardware cache locks, as that could influence other VMs on the same system. But we can tell the guest that its locking attempt failed. By implementing the instruction we at least don't give the guest a program exception which it definitely does not expect. Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/reg_booke.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 163c3b05a76e..464f1089b532 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -583,6 +583,7 @@ /* Bit definitions for L1CSR0. */ #define L1CSR0_CPE 0x00010000 /* Data Cache Parity Enable */ +#define L1CSR0_CUL 0x00000400 /* Data Cache Unable to Lock */ #define L1CSR0_CLFC 0x00000100 /* Cache Lock Bits Flash Clear */ #define L1CSR0_DCFI 0x00000002 /* Data Cache Flash Invalidate */ #define L1CSR0_CFI 0x00000002 /* Cache Flash Invalidate */ -- cgit From e5ee5422f8867d8b8108f8e1f0f47dc59b043f5b Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 5 May 2014 08:39:44 +0530 Subject: KVM: PPC: BOOK3S: PR: Enable Little Endian PR guest This patch make sure we inherit the LE bit correctly in different case so that we can run Little Endian distro in PR mode Signed-off-by: Aneesh Kumar K.V Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1eaea2dea174..d342f8efc843 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -562,6 +562,7 @@ struct kvm_vcpu_arch { #ifdef CONFIG_PPC_BOOK3S ulong fault_dar; u32 fault_dsisr; + unsigned long intr_msr; #endif #ifdef CONFIG_BOOKE @@ -654,7 +655,6 @@ struct kvm_vcpu_arch { spinlock_t tbacct_lock; u64 busy_stolen; u64 busy_preempt; - unsigned long intr_msr; #endif }; -- cgit From 5deb8e7ad8ac7e3fcdfa042acff617f461b361c2 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Thu, 24 Apr 2014 13:46:24 +0200 Subject: KVM: PPC: Make shared struct aka magic page guest endian The shared (magic) page is a data structure that contains often used supervisor privileged SPRs accessible via memory to the user to reduce the number of exits we have to take to read/write them. When we actually share this structure with the guest we have to maintain it in guest endianness, because some of the patch tricks only work with native endian load/store operations. Since we only share the structure with either host or guest in little endian on book3s_64 pr mode, we don't have to worry about booke or book3s hv. For booke, the shared struct stays big endian. For book3s_64 hv we maintain the struct in host native endian, since it never gets shared with the guest. For book3s_64 pr we introduce a variable that tells us which endianness the shared struct is in and route every access to it through helper inline functions that evaluate this variable. Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/kvm_book3s.h | 3 +- arch/powerpc/include/asm/kvm_booke.h | 5 --- arch/powerpc/include/asm/kvm_host.h | 3 ++ arch/powerpc/include/asm/kvm_ppc.h | 80 ++++++++++++++++++++++++++++++++++- 4 files changed, 84 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index bb1e38a23ac7..f52f65694527 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -268,9 +268,10 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) return vcpu->arch.pc; } +static inline u64 kvmppc_get_msr(struct kvm_vcpu *vcpu); static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu) { - return (vcpu->arch.shared->msr & MSR_LE) != (MSR_KERNEL & MSR_LE); + return (kvmppc_get_msr(vcpu) & MSR_LE) != (MSR_KERNEL & MSR_LE); } static inline u32 kvmppc_get_last_inst_internal(struct kvm_vcpu *vcpu, ulong pc) diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index 80d46b5a7efb..c7aed6105ff9 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -108,9 +108,4 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) { return vcpu->arch.fault_dear; } - -static inline ulong kvmppc_get_msr(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.shared->msr; -} #endif /* __ASM_KVM_BOOKE_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index d342f8efc843..15f19d3cc584 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -623,6 +623,9 @@ struct kvm_vcpu_arch { wait_queue_head_t cpu_run; struct kvm_vcpu_arch_shared *shared; +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE) + bool shared_big_endian; +#endif unsigned long magic_page_pa; /* phys addr to map the magic page to */ unsigned long magic_page_ea; /* effect. addr to map the magic page to */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 4096f16502a9..4a7cc453be0b 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -448,6 +448,84 @@ static inline void kvmppc_mmu_flush_icache(pfn_t pfn) } } +/* + * Shared struct helpers. The shared struct can be little or big endian, + * depending on the guest endianness. So expose helpers to all of them. + */ +static inline bool kvmppc_shared_big_endian(struct kvm_vcpu *vcpu) +{ +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE) + /* Only Book3S_64 PR supports bi-endian for now */ + return vcpu->arch.shared_big_endian; +#elif defined(CONFIG_PPC_BOOK3S_64) && defined(__LITTLE_ENDIAN__) + /* Book3s_64 HV on little endian is always little endian */ + return false; +#else + return true; +#endif +} + +#define SHARED_WRAPPER_GET(reg, size) \ +static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \ +{ \ + if (kvmppc_shared_big_endian(vcpu)) \ + return be##size##_to_cpu(vcpu->arch.shared->reg); \ + else \ + return le##size##_to_cpu(vcpu->arch.shared->reg); \ +} \ + +#define SHARED_WRAPPER_SET(reg, size) \ +static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val) \ +{ \ + if (kvmppc_shared_big_endian(vcpu)) \ + vcpu->arch.shared->reg = cpu_to_be##size(val); \ + else \ + vcpu->arch.shared->reg = cpu_to_le##size(val); \ +} \ + +#define SHARED_WRAPPER(reg, size) \ + SHARED_WRAPPER_GET(reg, size) \ + SHARED_WRAPPER_SET(reg, size) \ + +SHARED_WRAPPER(critical, 64) +SHARED_WRAPPER(sprg0, 64) +SHARED_WRAPPER(sprg1, 64) +SHARED_WRAPPER(sprg2, 64) +SHARED_WRAPPER(sprg3, 64) +SHARED_WRAPPER(srr0, 64) +SHARED_WRAPPER(srr1, 64) +SHARED_WRAPPER(dar, 64) +SHARED_WRAPPER_GET(msr, 64) +static inline void kvmppc_set_msr_fast(struct kvm_vcpu *vcpu, u64 val) +{ + if (kvmppc_shared_big_endian(vcpu)) + vcpu->arch.shared->msr = cpu_to_be64(val); + else + vcpu->arch.shared->msr = cpu_to_le64(val); +} +SHARED_WRAPPER(dsisr, 32) +SHARED_WRAPPER(int_pending, 32) +SHARED_WRAPPER(sprg4, 64) +SHARED_WRAPPER(sprg5, 64) +SHARED_WRAPPER(sprg6, 64) +SHARED_WRAPPER(sprg7, 64) + +static inline u32 kvmppc_get_sr(struct kvm_vcpu *vcpu, int nr) +{ + if (kvmppc_shared_big_endian(vcpu)) + return be32_to_cpu(vcpu->arch.shared->sr[nr]); + else + return le32_to_cpu(vcpu->arch.shared->sr[nr]); +} + +static inline void kvmppc_set_sr(struct kvm_vcpu *vcpu, int nr, u32 val) +{ + if (kvmppc_shared_big_endian(vcpu)) + vcpu->arch.shared->sr[nr] = cpu_to_be32(val); + else + vcpu->arch.shared->sr[nr] = cpu_to_le32(val); +} + /* * Please call after prepare_to_enter. This function puts the lazy ee and irq * disabled tracking state back to normal mode, without actually enabling @@ -485,7 +563,7 @@ static inline ulong kvmppc_get_ea_indexed(struct kvm_vcpu *vcpu, int ra, int rb) msr_64bit = MSR_SF; #endif - if (!(vcpu->arch.shared->msr & msr_64bit)) + if (!(kvmppc_get_msr(vcpu) & msr_64bit)) ea = (uint32_t)ea; return ea; -- cgit From 616dff86028298dbc91174fb3d12b8ed8cd74955 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 29 Apr 2014 16:48:44 +0200 Subject: KVM: PPC: Book3S PR: Handle Facility interrupt and FSCR POWER8 introduced a new interrupt type called "Facility unavailable interrupt" which contains its status message in a new register called FSCR. Handle these exits and try to emulate instructions for unhandled facilities. Follow-on patches enable KVM to expose specific facilities into the guest. Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/kvm_asm.h | 18 ++++++++++-------- arch/powerpc/include/asm/kvm_book3s_asm.h | 2 ++ arch/powerpc/include/asm/kvm_host.h | 1 + 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 19eb74a95b59..9601741080e5 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -102,6 +102,7 @@ #define BOOK3S_INTERRUPT_PERFMON 0xf00 #define BOOK3S_INTERRUPT_ALTIVEC 0xf20 #define BOOK3S_INTERRUPT_VSX 0xf40 +#define BOOK3S_INTERRUPT_FAC_UNAVAIL 0xf60 #define BOOK3S_INTERRUPT_H_FAC_UNAVAIL 0xf80 #define BOOK3S_IRQPRIO_SYSTEM_RESET 0 @@ -114,14 +115,15 @@ #define BOOK3S_IRQPRIO_FP_UNAVAIL 7 #define BOOK3S_IRQPRIO_ALTIVEC 8 #define BOOK3S_IRQPRIO_VSX 9 -#define BOOK3S_IRQPRIO_SYSCALL 10 -#define BOOK3S_IRQPRIO_MACHINE_CHECK 11 -#define BOOK3S_IRQPRIO_DEBUG 12 -#define BOOK3S_IRQPRIO_EXTERNAL 13 -#define BOOK3S_IRQPRIO_DECREMENTER 14 -#define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR 15 -#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL 16 -#define BOOK3S_IRQPRIO_MAX 17 +#define BOOK3S_IRQPRIO_FAC_UNAVAIL 10 +#define BOOK3S_IRQPRIO_SYSCALL 11 +#define BOOK3S_IRQPRIO_MACHINE_CHECK 12 +#define BOOK3S_IRQPRIO_DEBUG 13 +#define BOOK3S_IRQPRIO_EXTERNAL 14 +#define BOOK3S_IRQPRIO_DECREMENTER 15 +#define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR 16 +#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL 17 +#define BOOK3S_IRQPRIO_MAX 18 #define BOOK3S_HFLAG_DCBZ32 0x1 #define BOOK3S_HFLAG_SLB 0x2 diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 821725c1bf46..5bdfb5dd3400 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -104,6 +104,7 @@ struct kvmppc_host_state { #ifdef CONFIG_PPC_BOOK3S_64 u64 cfar; u64 ppr; + u64 host_fscr; #endif }; @@ -133,6 +134,7 @@ struct kvmppc_book3s_shadow_vcpu { u64 esid; u64 vsid; } slb[64]; /* guest SLB */ + u64 shadow_fscr; #endif }; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 15f19d3cc584..232ec5f0b886 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -475,6 +475,7 @@ struct kvm_vcpu_arch { ulong ppr; ulong pspb; ulong fscr; + ulong shadow_fscr; ulong ebbhr; ulong ebbrr; ulong bescr; -- cgit From e14e7a1e537d6e18f9c511f25c25c5efb7799fb5 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 22 Apr 2014 12:26:58 +0200 Subject: KVM: PPC: Book3S PR: Expose TAR facility to guest POWER8 implements a new register called TAR. This register has to be enabled in FSCR and then from KVM's point of view is mere storage. This patch enables the guest to use TAR. Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 232ec5f0b886..29fbb554af5c 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -449,7 +449,9 @@ struct kvm_vcpu_arch { ulong pc; ulong ctr; ulong lr; +#ifdef CONFIG_PPC_BOOK3S ulong tar; +#endif ulong xer; u32 cr; -- cgit From 1f365bb0de12da4a9ef8e56ffba2218d9a026011 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 6 May 2014 23:31:36 +0530 Subject: KVM: PPC: BOOK3S: HV: Add mixed page-size support for guest On recent IBM Power CPUs, while the hashed page table is looked up using the page size from the segmentation hardware (i.e. the SLB), it is possible to have the HPT entry indicate a larger page size. Thus for example it is possible to put a 16MB page in a 64kB segment, but since the hash lookup is done using a 64kB page size, it may be necessary to put multiple entries in the HPT for a single 16MB page. This capability is called mixed page-size segment (MPSS). With MPSS, there are two relevant page sizes: the base page size, which is the size used in searching the HPT, and the actual page size, which is the size indicated in the HPT entry. [ Note that the actual page size is always >= base page size ]. We use "ibm,segment-page-sizes" device tree node to advertise the MPSS support to PAPR guest. The penc encoding indicates whether we support a specific combination of base page size and actual page size in the same segment. We also use the penc value in the LP encoding of HPTE entry. This patch exposes MPSS support to KVM guest by advertising the feature via "ibm,segment-page-sizes". It also adds the necessary changes to decode the base page size and the actual page size correctly from the HPTE entry. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/kvm_book3s_64.h | 146 ++++++++++++++++++++++++++----- 1 file changed, 123 insertions(+), 23 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 51388befeddb..fddb72b48ce9 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -77,34 +77,122 @@ static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits) return old == 0; } +static inline int __hpte_actual_psize(unsigned int lp, int psize) +{ + int i, shift; + unsigned int mask; + + /* start from 1 ignoring MMU_PAGE_4K */ + for (i = 1; i < MMU_PAGE_COUNT; i++) { + + /* invalid penc */ + if (mmu_psize_defs[psize].penc[i] == -1) + continue; + /* + * encoding bits per actual page size + * PTE LP actual page size + * rrrr rrrz >=8KB + * rrrr rrzz >=16KB + * rrrr rzzz >=32KB + * rrrr zzzz >=64KB + * ....... + */ + shift = mmu_psize_defs[i].shift - LP_SHIFT; + if (shift > LP_BITS) + shift = LP_BITS; + mask = (1 << shift) - 1; + if ((lp & mask) == mmu_psize_defs[psize].penc[i]) + return i; + } + return -1; +} + static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, unsigned long pte_index) { - unsigned long rb, va_low; + int b_psize, a_psize; + unsigned int penc; + unsigned long rb = 0, va_low, sllp; + unsigned int lp = (r >> LP_SHIFT) & ((1 << LP_BITS) - 1); + + if (!(v & HPTE_V_LARGE)) { + /* both base and actual psize is 4k */ + b_psize = MMU_PAGE_4K; + a_psize = MMU_PAGE_4K; + } else { + for (b_psize = 0; b_psize < MMU_PAGE_COUNT; b_psize++) { + + /* valid entries have a shift value */ + if (!mmu_psize_defs[b_psize].shift) + continue; + a_psize = __hpte_actual_psize(lp, b_psize); + if (a_psize != -1) + break; + } + } + /* + * Ignore the top 14 bits of va + * v have top two bits covering segment size, hence move + * by 16 bits, Also clear the lower HPTE_V_AVPN_SHIFT (7) bits. + * AVA field in v also have the lower 23 bits ignored. + * For base page size 4K we need 14 .. 65 bits (so need to + * collect extra 11 bits) + * For others we need 14..14+i + */ + /* This covers 14..54 bits of va*/ rb = (v & ~0x7fUL) << 16; /* AVA field */ + /* + * AVA in v had cleared lower 23 bits. We need to derive + * that from pteg index + */ va_low = pte_index >> 3; if (v & HPTE_V_SECONDARY) va_low = ~va_low; - /* xor vsid from AVA */ + /* + * get the vpn bits from va_low using reverse of hashing. + * In v we have va with 23 bits dropped and then left shifted + * HPTE_V_AVPN_SHIFT (7) bits. Now to find vsid we need + * right shift it with (SID_SHIFT - (23 - 7)) + */ if (!(v & HPTE_V_1TB_SEG)) - va_low ^= v >> 12; + va_low ^= v >> (SID_SHIFT - 16); else - va_low ^= v >> 24; + va_low ^= v >> (SID_SHIFT_1T - 16); va_low &= 0x7ff; - if (v & HPTE_V_LARGE) { - rb |= 1; /* L field */ - if (cpu_has_feature(CPU_FTR_ARCH_206) && - (r & 0xff000)) { - /* non-16MB large page, must be 64k */ - /* (masks depend on page size) */ - rb |= 0x1000; /* page encoding in LP field */ - rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */ - rb |= ((va_low << 4) & 0xf0); /* AVAL field (P7 doesn't seem to care) */ - } - } else { - /* 4kB page */ - rb |= (va_low & 0x7ff) << 12; /* remaining 11b of VA */ + + switch (b_psize) { + case MMU_PAGE_4K: + sllp = ((mmu_psize_defs[a_psize].sllp & SLB_VSID_L) >> 6) | + ((mmu_psize_defs[a_psize].sllp & SLB_VSID_LP) >> 4); + rb |= sllp << 5; /* AP field */ + rb |= (va_low & 0x7ff) << 12; /* remaining 11 bits of AVA */ + break; + default: + { + int aval_shift; + /* + * remaining 7bits of AVA/LP fields + * Also contain the rr bits of LP + */ + rb |= (va_low & 0x7f) << 16; + /* + * Now clear not needed LP bits based on actual psize + */ + rb &= ~((1ul << mmu_psize_defs[a_psize].shift) - 1); + /* + * AVAL field 58..77 - base_page_shift bits of va + * we have space for 58..64 bits, Missing bits should + * be zero filled. +1 is to take care of L bit shift + */ + aval_shift = 64 - (77 - mmu_psize_defs[b_psize].shift) + 1; + rb |= ((va_low << aval_shift) & 0xfe); + + rb |= 1; /* L field */ + penc = mmu_psize_defs[b_psize].penc[a_psize]; + rb |= penc << 12; /* LP field */ + break; + } } rb |= (v >> 54) & 0x300; /* B field */ return rb; @@ -112,14 +200,26 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, static inline unsigned long hpte_page_size(unsigned long h, unsigned long l) { + int size, a_psize; + /* Look at the 8 bit LP value */ + unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1); + /* only handle 4k, 64k and 16M pages for now */ if (!(h & HPTE_V_LARGE)) - return 1ul << 12; /* 4k page */ - if ((l & 0xf000) == 0x1000 && cpu_has_feature(CPU_FTR_ARCH_206)) - return 1ul << 16; /* 64k page */ - if ((l & 0xff000) == 0) - return 1ul << 24; /* 16M page */ - return 0; /* error */ + return 1ul << 12; + else { + for (size = 0; size < MMU_PAGE_COUNT; size++) { + /* valid entries have a shift value */ + if (!mmu_psize_defs[size].shift) + continue; + + a_psize = __hpte_actual_psize(lp, size); + if (a_psize != -1) + return 1ul << mmu_psize_defs[a_psize].shift; + } + + } + return 0; } static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize) -- cgit From f3383cf80e417e86fcc84a2eb4c96bc52842d8d9 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 12 May 2014 01:08:32 +0200 Subject: KVM: PPC: Disable NX for old magic page using guests Old guests try to use the magic page, but map their trampoline code inside of an NX region. Since we can't fix those old kernels, try to detect whether the guest is sane or not. If not, just disable NX functionality in KVM so that old guests at least work at all. For newer guests, add a bit that we can set to keep NX functionality available. Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/include/uapi/asm/kvm_para.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 29fbb554af5c..bb66d8b8efdf 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -631,6 +631,7 @@ struct kvm_vcpu_arch { #endif unsigned long magic_page_pa; /* phys addr to map the magic page to */ unsigned long magic_page_ea; /* effect. addr to map the magic page to */ + bool disable_kernel_nx; int irq_type; /* one of KVM_IRQ_* */ int irq_cpu_id; diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h index e3af3286a068..91e42f09b323 100644 --- a/arch/powerpc/include/uapi/asm/kvm_para.h +++ b/arch/powerpc/include/uapi/asm/kvm_para.h @@ -82,10 +82,16 @@ struct kvm_vcpu_arch_shared { #define KVM_FEATURE_MAGIC_PAGE 1 +/* Magic page flags from host to guest */ + #define KVM_MAGIC_FEAT_SR (1 << 0) /* MASn, ESR, PIR, and high SPRGs */ #define KVM_MAGIC_FEAT_MAS0_TO_SPRG7 (1 << 1) +/* Magic page flags from guest to host */ + +#define MAGIC_PAGE_FLAG_NOT_MAPPED_NX (1 << 0) + #endif /* _UAPI__POWERPC_KVM_PARA_H__ */ -- cgit From ddca156ae6bafc0c6af61805bfe4b37440448a4c Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 12 May 2014 17:04:06 +0530 Subject: KVM: PPC: BOOK3S: Remove open coded make_dsisr in alignment handler Use make_dsisr instead of open coding it. This also have the added benefit of handling alignment interrupt on additional instructions. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/disassemble.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/disassemble.h b/arch/powerpc/include/asm/disassemble.h index 856f8deb557a..6330a61b875a 100644 --- a/arch/powerpc/include/asm/disassemble.h +++ b/arch/powerpc/include/asm/disassemble.h @@ -81,4 +81,38 @@ static inline unsigned int get_oc(u32 inst) { return (inst >> 11) & 0x7fff; } + +#define IS_XFORM(inst) (get_op(inst) == 31) +#define IS_DSFORM(inst) (get_op(inst) >= 56) + +/* + * Create a DSISR value from the instruction + */ +static inline unsigned make_dsisr(unsigned instr) +{ + unsigned dsisr; + + + /* bits 6:15 --> 22:31 */ + dsisr = (instr & 0x03ff0000) >> 16; + + if (IS_XFORM(instr)) { + /* bits 29:30 --> 15:16 */ + dsisr |= (instr & 0x00000006) << 14; + /* bit 25 --> 17 */ + dsisr |= (instr & 0x00000040) << 8; + /* bits 21:24 --> 18:21 */ + dsisr |= (instr & 0x00000780) << 3; + } else { + /* bit 5 --> 17 */ + dsisr |= (instr & 0x04000000) >> 12; + /* bits 1: 4 --> 18:21 */ + dsisr |= (instr & 0x78000000) >> 17; + /* bits 30:31 --> 12:13 */ + if (IS_DSFORM(instr)) + dsisr |= (instr & 0x00000003) << 18; + } + + return dsisr; +} #endif /* __ASM_PPC_DISASSEMBLE_H__ */ -- cgit From e1d8a96daf641aea11c25268eab678a76215541a Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 26 May 2014 19:48:35 +1000 Subject: KVM: PPC: Book3S: Move KVM_REG_PPC_WORT to an unused register number Commit b005255e12a3 ("KVM: PPC: Book3S HV: Context-switch new POWER8 SPRs") added a definition of KVM_REG_PPC_WORT with the same register number as the existing KVM_REG_PPC_VRSAVE (though in fact the definitions are not identical because of the different register sizes.) For clarity, this moves KVM_REG_PPC_WORT to the next unused number, and also adds it to api.txt. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/include/uapi/asm/kvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index a6665be4f3ab..2bc4a9409a93 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -545,7 +545,6 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_TCSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1) #define KVM_REG_PPC_PID (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2) #define KVM_REG_PPC_ACOP (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3) -#define KVM_REG_PPC_WORT (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb4) #define KVM_REG_PPC_VRSAVE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4) #define KVM_REG_PPC_LPCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5) @@ -555,6 +554,7 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_ARCH_COMPAT (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7) #define KVM_REG_PPC_DABRX (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb8) +#define KVM_REG_PPC_WORT (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb9) /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs -- cgit From 9bc01a9bc77edac2ea6db62c5111a7f4335d4021 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 26 May 2014 19:48:40 +1000 Subject: KVM: PPC: Book3S HV: Work around POWER8 performance monitor bugs This adds workarounds for two hardware bugs in the POWER8 performance monitor unit (PMU), both related to interrupt generation. The effect of these bugs is that PMU interrupts can get lost, leading to tools such as perf reporting fewer counts and samples than they should. The first bug relates to the PMAO (perf. mon. alert occurred) bit in MMCR0; setting it should cause an interrupt, but doesn't. The other bug relates to the PMAE (perf. mon. alert enable) bit in MMCR0. Setting PMAE when a counter is negative and counter negative conditions are enabled to cause alerts should cause an alert, but doesn't. The workaround for the first bug is to create conditions where a counter will overflow, whenever we are about to restore a MMCR0 value that has PMAO set (and PMAO_SYNC clear). The workaround for the second bug is to freeze all counters using MMCR2 before reading MMCR0. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/reg.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index e5d2e0bc7e03..4852bcf270f3 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -670,18 +670,20 @@ #define MMCR0_PROBLEM_DISABLE MMCR0_FCP #define MMCR0_FCM1 0x10000000UL /* freeze counters while MSR mark = 1 */ #define MMCR0_FCM0 0x08000000UL /* freeze counters while MSR mark = 0 */ -#define MMCR0_PMXE 0x04000000UL /* performance monitor exception enable */ -#define MMCR0_FCECE 0x02000000UL /* freeze ctrs on enabled cond or event */ +#define MMCR0_PMXE ASM_CONST(0x04000000) /* perf mon exception enable */ +#define MMCR0_FCECE ASM_CONST(0x02000000) /* freeze ctrs on enabled cond or event */ #define MMCR0_TBEE 0x00400000UL /* time base exception enable */ #define MMCR0_BHRBA 0x00200000UL /* BHRB Access allowed in userspace */ #define MMCR0_EBE 0x00100000UL /* Event based branch enable */ #define MMCR0_PMCC 0x000c0000UL /* PMC control */ #define MMCR0_PMCC_U6 0x00080000UL /* PMC1-6 are R/W by user (PR) */ #define MMCR0_PMC1CE 0x00008000UL /* PMC1 count enable*/ -#define MMCR0_PMCjCE 0x00004000UL /* PMCj count enable*/ +#define MMCR0_PMCjCE ASM_CONST(0x00004000) /* PMCj count enable*/ #define MMCR0_TRIGGER 0x00002000UL /* TRIGGER enable */ -#define MMCR0_PMAO_SYNC 0x00000800UL /* PMU interrupt is synchronous */ -#define MMCR0_PMAO 0x00000080UL /* performance monitor alert has occurred, set to 0 after handling exception */ +#define MMCR0_PMAO_SYNC ASM_CONST(0x00000800) /* PMU intr is synchronous */ +#define MMCR0_C56RUN ASM_CONST(0x00000100) /* PMC5/6 count when RUN=0 */ +/* performance monitor alert has occurred, set to 0 after handling exception */ +#define MMCR0_PMAO ASM_CONST(0x00000080) #define MMCR0_SHRFC 0x00000040UL /* SHRre freeze conditions between threads */ #define MMCR0_FC56 0x00000010UL /* freeze counters 5 and 6 */ #define MMCR0_FCTI 0x00000008UL /* freeze counters in tags inactive mode */ -- cgit