diff options
32 files changed, 921 insertions, 1729 deletions
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index d7912b66c874..7e29c73e3dd4 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -51,13 +51,11 @@ struct iommu_table_ops { int (*xchg_no_kill)(struct iommu_table *tbl, long index, unsigned long *hpa, - enum dma_data_direction *direction, - bool realmode); + enum dma_data_direction *direction); void (*tce_kill)(struct iommu_table *tbl, unsigned long index, - unsigned long pages, - bool realmode); + unsigned long pages); __be64 *(*useraddrptr)(struct iommu_table *tbl, long index, bool alloc); #endif diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index b6d31bff5209..c8882d9b86c2 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -14,9 +14,6 @@ #define XICS_MFRR 0xc #define XICS_IPI 2 /* interrupt source # for IPIs */ -/* LPIDs we support with this build -- runtime limit may be lower */ -#define KVMPPC_NR_LPIDS (LPID_RSVD + 1) - /* Maximum number of threads per physical core */ #define MAX_SMT_THREADS 8 diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index faf301d0dec0..2909a88acd16 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -36,7 +36,12 @@ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #include <asm/kvm_book3s_asm.h> /* for MAX_SMT_THREADS */ #define KVM_MAX_VCPU_IDS (MAX_SMT_THREADS * KVM_MAX_VCORES) -#define KVM_MAX_NESTED_GUESTS KVMPPC_NR_LPIDS + +/* + * Limit the nested partition table to 4096 entries (because that's what + * hardware supports). Both guest and host use this value. + */ +#define KVM_MAX_NESTED_GUESTS_SHIFT 12 #else #define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS @@ -327,8 +332,7 @@ struct kvm_arch { struct list_head uvmem_pfns; struct mutex mmu_setup_lock; /* nests inside vcpu mutexes */ u64 l1_ptcr; - int max_nested_lpid; - struct kvm_nested_guest *nested_guests[KVM_MAX_NESTED_GUESTS]; + struct idr kvm_nested_guest_idr; /* This array can grow quite large, keep it at the end */ struct kvmppc_vcore *vcores[KVM_MAX_VCORES]; #endif diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 838d4cb460b7..9f625af3b65b 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -177,8 +177,6 @@ extern void kvmppc_setup_partition_table(struct kvm *kvm); extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce_64 *args); -extern struct kvmppc_spapr_tce_table *kvmppc_find_table( - struct kvm *kvm, unsigned long liobn); #define kvmppc_ioba_validate(stt, ioba, npages) \ (iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \ (stt)->size, (ioba), (npages)) ? \ @@ -685,7 +683,7 @@ extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu); extern void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu); -extern void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu); +extern bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu); static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) { @@ -723,7 +721,7 @@ static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 ir int level, bool line_status) { return -ENODEV; } static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { } static inline void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu) { } -static inline void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { } +static inline bool kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { return true; } static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) { return 0; } @@ -789,13 +787,6 @@ long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long dest, unsigned long src); long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr, unsigned long slb_v, unsigned int status, bool data); -unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu); -unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu); -unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server); -int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, - unsigned long mfrr); -int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr); -int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr); void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu); /* @@ -877,7 +868,6 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu, struct kvm_dirty_tlb *cfg); long kvmppc_alloc_lpid(void); -void kvmppc_claim_lpid(long lpid); void kvmppc_free_lpid(long lpid); void kvmppc_init_lpid(unsigned long nr_lpids); diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b8527a74bd4d..3f25bd3e14eb 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -34,15 +34,10 @@ extern void mm_iommu_init(struct mm_struct *mm); extern void mm_iommu_cleanup(struct mm_struct *mm); extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm, unsigned long ua, unsigned long size); -extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm( - struct mm_struct *mm, unsigned long ua, unsigned long size); extern struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries); extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); -extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned int pageshift, unsigned long *hpa); -extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua); extern bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa, unsigned int pageshift, unsigned long *size); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 2835f6363228..1e8b2e04e626 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -417,7 +417,6 @@ #define FSCR_DSCR __MASK(FSCR_DSCR_LG) #define FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56) /* interrupt cause */ #define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */ -#define HFSCR_PREFIX __MASK(FSCR_PREFIX_LG) #define HFSCR_MSGP __MASK(FSCR_MSGP_LG) #define HFSCR_TAR __MASK(FSCR_TAR_LG) #define HFSCR_EBB __MASK(FSCR_EBB_LG) @@ -474,8 +473,6 @@ #ifndef SPRN_LPID #define SPRN_LPID 0x13F /* Logical Partition Identifier */ #endif -#define LPID_RSVD_POWER7 0x3ff /* Reserved LPID for partn switching */ -#define LPID_RSVD 0xfff /* Reserved LPID for partn switching */ #define SPRN_HMER 0x150 /* Hypervisor maintenance exception reg */ #define HMER_DEBUG_TRIG (1ul << (63 - 17)) /* Debug trigger */ #define SPRN_HMEER 0x151 /* Hyp maintenance exception enable reg */ diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index d440a2436feb..7e56ddb3e0b9 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1064,7 +1064,7 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm, long ret; unsigned long size = 0; - ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, false); + ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction); if (!ret && ((*direction == DMA_FROM_DEVICE) || (*direction == DMA_BIDIRECTIONAL)) && !mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift, @@ -1079,7 +1079,7 @@ void iommu_tce_kill(struct iommu_table *tbl, unsigned long entry, unsigned long pages) { if (tbl->it_ops->tce_kill) - tbl->it_ops->tce_kill(tbl, entry, pages, false); + tbl->it_ops->tce_kill(tbl, entry, pages); } EXPORT_SYMBOL_GPL(iommu_tce_kill); diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 9bdfc8b50899..f17379b0f161 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -37,9 +37,6 @@ kvm-e500mc-objs := \ e500_emulate.o kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs) -kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \ - book3s_64_vio_hv.o - kvm-pr-y := \ fpu.o \ emulate.o \ @@ -76,7 +73,7 @@ kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \ book3s_hv_tm.o kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \ - book3s_hv_rm_xics.o book3s_hv_rm_xive.o + book3s_hv_rm_xics.o kvm-book3s_64-builtin-tm-objs-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \ book3s_hv_tm_builtin.o diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 1137c4df726c..514fd45c1994 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -256,26 +256,34 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, int kvmppc_mmu_hv_init(void) { - unsigned long host_lpid, rsvd_lpid; + unsigned long nr_lpids; if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE)) return -EINVAL; - host_lpid = 0; - if (cpu_has_feature(CPU_FTR_HVMODE)) - host_lpid = mfspr(SPRN_LPID); + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (WARN_ON(mfspr(SPRN_LPID) != 0)) + return -EINVAL; + nr_lpids = 1UL << mmu_lpid_bits; + } else { + nr_lpids = 1UL << KVM_MAX_NESTED_GUESTS_SHIFT; + } - /* POWER8 and above have 12-bit LPIDs (10-bit in POWER7) */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) - rsvd_lpid = LPID_RSVD; - else - rsvd_lpid = LPID_RSVD_POWER7; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + /* POWER7 has 10-bit LPIDs, POWER8 has 12-bit LPIDs */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + WARN_ON(nr_lpids != 1UL << 12); + else + WARN_ON(nr_lpids != 1UL << 10); - kvmppc_init_lpid(rsvd_lpid + 1); + /* + * Reserve the last implemented LPID use in partition + * switching for POWER7 and POWER8. + */ + nr_lpids -= 1; + } - kvmppc_claim_lpid(host_lpid); - /* rsvd_lpid is reserved for use in partition switching */ - kvmppc_claim_lpid(rsvd_lpid); + kvmppc_init_lpid(nr_lpids); return 0; } @@ -879,7 +887,7 @@ static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, struct revmap_entry *rev = kvm->arch.hpt.rev; unsigned long head, i, j; __be64 *hptep; - int ret = 0; + bool ret = false; unsigned long *rmapp; rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; @@ -887,7 +895,7 @@ static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_rmap(rmapp); if (*rmapp & KVMPPC_RMAP_REFERENCED) { *rmapp &= ~KVMPPC_RMAP_REFERENCED; - ret = 1; + ret = true; } if (!(*rmapp & KVMPPC_RMAP_PRESENT)) { unlock_rmap(rmapp); @@ -919,7 +927,7 @@ static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, rev[i].guest_rpte |= HPTE_R_R; note_hpte_modification(kvm, &rev[i]); } - ret = 1; + ret = true; } __unlock_hpte(hptep, be64_to_cpu(hptep[0])); } while ((i = j) != head); diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 85cfa6328222..d6589c4fe889 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -32,6 +32,18 @@ #include <asm/tce.h> #include <asm/mmu_context.h> +static struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm, + unsigned long liobn) +{ + struct kvmppc_spapr_tce_table *stt; + + list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list) + if (stt->liobn == liobn) + return stt; + + return NULL; +} + static unsigned long kvmppc_tce_pages(unsigned long iommu_pages) { return ALIGN(iommu_pages * sizeof(u64), PAGE_SIZE) / PAGE_SIZE; @@ -753,3 +765,34 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce); + +long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, + unsigned long ioba) +{ + struct kvmppc_spapr_tce_table *stt; + long ret; + unsigned long idx; + struct page *page; + u64 *tbl; + + stt = kvmppc_find_table(vcpu->kvm, liobn); + if (!stt) + return H_TOO_HARD; + + ret = kvmppc_ioba_validate(stt, ioba, 1); + if (ret != H_SUCCESS) + return ret; + + idx = (ioba >> stt->page_shift) - stt->offset; + page = stt->pages[idx / TCES_PER_PAGE]; + if (!page) { + vcpu->arch.regs.gpr[4] = 0; + return H_SUCCESS; + } + tbl = (u64 *)page_address(page); + + vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE]; + + return H_SUCCESS; +} +EXPORT_SYMBOL_GPL(kvmppc_h_get_tce); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c deleted file mode 100644 index fdcc7b287dd8..000000000000 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ /dev/null @@ -1,672 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * - * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> - * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com> - * Copyright 2016 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com> - */ - -#include <linux/types.h> -#include <linux/string.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <linux/highmem.h> -#include <linux/gfp.h> -#include <linux/slab.h> -#include <linux/hugetlb.h> -#include <linux/list.h> -#include <linux/stringify.h> - -#include <asm/kvm_ppc.h> -#include <asm/kvm_book3s.h> -#include <asm/book3s/64/mmu-hash.h> -#include <asm/mmu_context.h> -#include <asm/hvcall.h> -#include <asm/synch.h> -#include <asm/ppc-opcode.h> -#include <asm/udbg.h> -#include <asm/iommu.h> -#include <asm/tce.h> -#include <asm/pte-walk.h> - -#ifdef CONFIG_BUG - -#define WARN_ON_ONCE_RM(condition) ({ \ - static bool __section(".data.unlikely") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n", \ - __stringify(condition), \ - __func__, __LINE__); \ - dump_stack(); \ - } \ - unlikely(__ret_warn_once); \ -}) - -#else - -#define WARN_ON_ONCE_RM(condition) ({ \ - int __ret_warn_on = !!(condition); \ - unlikely(__ret_warn_on); \ -}) - -#endif - -/* - * Finds a TCE table descriptor by LIOBN. - * - * WARNING: This will be called in real or virtual mode on HV KVM and virtual - * mode on PR KVM - */ -struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm, - unsigned long liobn) -{ - struct kvmppc_spapr_tce_table *stt; - - list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list) - if (stt->liobn == liobn) - return stt; - - return NULL; -} -EXPORT_SYMBOL_GPL(kvmppc_find_table); - -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE -static long kvmppc_rm_tce_to_ua(struct kvm *kvm, - unsigned long tce, unsigned long *ua) -{ - unsigned long gfn = tce >> PAGE_SHIFT; - struct kvm_memory_slot *memslot; - - memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn); - if (!memslot) - return -EINVAL; - - *ua = __gfn_to_hva_memslot(memslot, gfn) | - (tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE)); - - return 0; -} - -/* - * Validates TCE address. - * At the moment flags and page mask are validated. - * As the host kernel does not access those addresses (just puts them - * to the table and user space is supposed to process them), we can skip - * checking other things (such as TCE is a guest RAM address or the page - * was actually allocated). - */ -static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt, - unsigned long tce) -{ - unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE); - enum dma_data_direction dir = iommu_tce_direction(tce); - struct kvmppc_spapr_tce_iommu_table *stit; - unsigned long ua = 0; - - /* Allow userspace to poison TCE table */ - if (dir == DMA_NONE) - return H_SUCCESS; - - if (iommu_tce_check_gpa(stt->page_shift, gpa)) - return H_PARAMETER; - - if (kvmppc_rm_tce_to_ua(stt->kvm, tce, &ua)) - return H_TOO_HARD; - - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { - unsigned long hpa = 0; - struct mm_iommu_table_group_mem_t *mem; - long shift = stit->tbl->it_page_shift; - - mem = mm_iommu_lookup_rm(stt->kvm->mm, ua, 1ULL << shift); - if (!mem) - return H_TOO_HARD; - - if (mm_iommu_ua_to_hpa_rm(mem, ua, shift, &hpa)) - return H_TOO_HARD; - } - - return H_SUCCESS; -} - -/* Note on the use of page_address() in real mode, - * - * It is safe to use page_address() in real mode on ppc64 because - * page_address() is always defined as lowmem_page_address() - * which returns __va(PFN_PHYS(page_to_pfn(page))) which is arithmetic - * operation and does not access page struct. - * - * Theoretically page_address() could be defined different - * but either WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL - * would have to be enabled. - * WANT_PAGE_VIRTUAL is never enabled on ppc32/ppc64, - * HASHED_PAGE_VIRTUAL could be enabled for ppc32 only and only - * if CONFIG_HIGHMEM is defined. As CONFIG_SPARSEMEM_VMEMMAP - * is not expected to be enabled on ppc32, page_address() - * is safe for ppc32 as well. - * - * WARNING: This will be called in real-mode on HV KVM and virtual - * mode on PR KVM - */ -static u64 *kvmppc_page_address(struct page *page) -{ -#if defined(HASHED_PAGE_VIRTUAL) || defined(WANT_PAGE_VIRTUAL) -#error TODO: fix to avoid page_address() here -#endif - return (u64 *) page_address(page); -} - -/* - * Handles TCE requests for emulated devices. - * Puts guest TCE values to the table and expects user space to convert them. - * Cannot fail so kvmppc_rm_tce_validate must be called before it. - */ -static void kvmppc_rm_tce_put(struct kvmppc_spapr_tce_table *stt, - unsigned long idx, unsigned long tce) -{ - struct page *page; - u64 *tbl; - - idx -= stt->offset; - page = stt->pages[idx / TCES_PER_PAGE]; - /* - * kvmppc_rm_ioba_validate() allows pages not be allocated if TCE is - * being cleared, otherwise it returns H_TOO_HARD and we skip this. - */ - if (!page) { - WARN_ON_ONCE_RM(tce != 0); - return; - } - tbl = kvmppc_page_address(page); - - tbl[idx % TCES_PER_PAGE] = tce; -} - -/* - * TCEs pages are allocated in kvmppc_rm_tce_put() which won't be able to do so - * in real mode. - * Check if kvmppc_rm_tce_put() can succeed in real mode, i.e. a TCEs page is - * allocated or not required (when clearing a tce entry). - */ -static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt, - unsigned long ioba, unsigned long npages, bool clearing) -{ - unsigned long i, idx, sttpage, sttpages; - unsigned long ret = kvmppc_ioba_validate(stt, ioba, npages); - - if (ret) - return ret; - /* - * clearing==true says kvmppc_rm_tce_put won't be allocating pages - * for empty tces. - */ - if (clearing) - return H_SUCCESS; - - idx = (ioba >> stt->page_shift) - stt->offset; - sttpage = idx / TCES_PER_PAGE; - sttpages = ALIGN(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) / - TCES_PER_PAGE; - for (i = sttpage; i < sttpage + sttpages; ++i) - if (!stt->pages[i]) - return H_TOO_HARD; - - return H_SUCCESS; -} - -static long iommu_tce_xchg_no_kill_rm(struct mm_struct *mm, - struct iommu_table *tbl, - unsigned long entry, unsigned long *hpa, - enum dma_data_direction *direction) -{ - long ret; - - ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, true); - - if (!ret && ((*direction == DMA_FROM_DEVICE) || - (*direction == DMA_BIDIRECTIONAL))) { - __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry); - /* - * kvmppc_rm_tce_iommu_do_map() updates the UA cache after - * calling this so we still get here a valid UA. - */ - if (pua && *pua) - mm_iommu_ua_mark_dirty_rm(mm, be64_to_cpu(*pua)); - } - - return ret; -} - -static void iommu_tce_kill_rm(struct iommu_table *tbl, - unsigned long entry, unsigned long pages) -{ - if (tbl->it_ops->tce_kill) - tbl->it_ops->tce_kill(tbl, entry, pages, true); -} - -static void kvmppc_rm_clear_tce(struct kvm *kvm, struct kvmppc_spapr_tce_table *stt, - struct iommu_table *tbl, unsigned long entry) -{ - unsigned long i; - unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); - unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); - - for (i = 0; i < subpages; ++i) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; - - iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, io_entry + i, &hpa, &dir); - } -} - -static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, - struct iommu_table *tbl, unsigned long entry) -{ - struct mm_iommu_table_group_mem_t *mem = NULL; - const unsigned long pgsize = 1ULL << tbl->it_page_shift; - __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry); - - if (!pua) - /* it_userspace allocation might be delayed */ - return H_TOO_HARD; - - mem = mm_iommu_lookup_rm(kvm->mm, be64_to_cpu(*pua), pgsize); - if (!mem) - return H_TOO_HARD; - - mm_iommu_mapped_dec(mem); - - *pua = cpu_to_be64(0); - - return H_SUCCESS; -} - -static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, - struct iommu_table *tbl, unsigned long entry) -{ - enum dma_data_direction dir = DMA_NONE; - unsigned long hpa = 0; - long ret; - - if (iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir)) - /* - * real mode xchg can fail if struct page crosses - * a page boundary - */ - return H_TOO_HARD; - - if (dir == DMA_NONE) - return H_SUCCESS; - - ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); - if (ret) - iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); - - return ret; -} - -static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm, - struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl, - unsigned long entry) -{ - unsigned long i, ret = H_SUCCESS; - unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); - unsigned long io_entry = entry * subpages; - - for (i = 0; i < subpages; ++i) { - ret = kvmppc_rm_tce_iommu_do_unmap(kvm, tbl, io_entry + i); - if (ret != H_SUCCESS) - break; - } - - iommu_tce_kill_rm(tbl, io_entry, subpages); - - return ret; -} - -static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, - unsigned long entry, unsigned long ua, - enum dma_data_direction dir) -{ - long ret; - unsigned long hpa = 0; - __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry); - struct mm_iommu_table_group_mem_t *mem; - - if (!pua) - /* it_userspace allocation might be delayed */ - return H_TOO_HARD; - - mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift); - if (!mem) - return H_TOO_HARD; - - if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift, - &hpa))) - return H_TOO_HARD; - - if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) - return H_TOO_HARD; - - ret = iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); - if (ret) { - mm_iommu_mapped_dec(mem); - /* - * real mode xchg can fail if struct page crosses - * a page boundary - */ - return H_TOO_HARD; - } - - if (dir != DMA_NONE) - kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); - - *pua = cpu_to_be64(ua); - - return 0; -} - -static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, - struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl, - unsigned long entry, unsigned long ua, - enum dma_data_direction dir) -{ - unsigned long i, pgoff, ret = H_SUCCESS; - unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); - unsigned long io_entry = entry * subpages; - - for (i = 0, pgoff = 0; i < subpages; - ++i, pgoff += IOMMU_PAGE_SIZE(tbl)) { - - ret = kvmppc_rm_tce_iommu_do_map(kvm, tbl, - io_entry + i, ua + pgoff, dir); - if (ret != H_SUCCESS) - break; - } - - iommu_tce_kill_rm(tbl, io_entry, subpages); - - return ret; -} - -long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, - unsigned long ioba, unsigned long tce) -{ - struct kvmppc_spapr_tce_table *stt; - long ret; - struct kvmppc_spapr_tce_iommu_table *stit; - unsigned long entry, ua = 0; - enum dma_data_direction dir; - - /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ - /* liobn, ioba, tce); */ - - stt = kvmppc_find_table(vcpu->kvm, liobn); - if (!stt) - return H_TOO_HARD; - - ret = kvmppc_rm_ioba_validate(stt, ioba, 1, tce == 0); - if (ret != H_SUCCESS) - return ret; - - ret = kvmppc_rm_tce_validate(stt, tce); - if (ret != H_SUCCESS) - return ret; - - dir = iommu_tce_direction(tce); - if ((dir != DMA_NONE) && kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) - return H_PARAMETER; - - entry = ioba >> stt->page_shift; - - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { - if (dir == DMA_NONE) - ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, stt, - stit->tbl, entry); - else - ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt, - stit->tbl, entry, ua, dir); - - if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry); - return ret; - } - } - - kvmppc_rm_tce_put(stt, entry, tce); - - return H_SUCCESS; -} - -static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu, unsigned long mmu_seq, - unsigned long ua, unsigned long *phpa) -{ - pte_t *ptep, pte; - unsigned shift = 0; - - /* - * Called in real mode with MSR_EE = 0. We are safe here. - * It is ok to do the lookup with arch.pgdir here, because - * we are doing this on secondary cpus and current task there - * is not the hypervisor. Also this is safe against THP in the - * host, because an IPI to primary thread will wait for the secondary - * to exit which will again result in the below page table walk - * to finish. - */ - /* an rmap lock won't make it safe. because that just ensure hash - * page table entries are removed with rmap lock held. After that - * mmu notifier returns and we go ahead and removing ptes from Qemu page table. - */ - ptep = find_kvm_host_pte(vcpu->kvm, mmu_seq, ua, &shift); - if (!ptep) - return -ENXIO; - - pte = READ_ONCE(*ptep); - if (!pte_present(pte)) - return -ENXIO; - - if (!shift) - shift = PAGE_SHIFT; - - /* Avoi |