From c17b98cf6028704e1f953d6a25ed6140425ccfd0 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 3 Dec 2014 13:30:38 +1100 Subject: KVM: PPC: Book3S HV: Remove code for PPC970 processors This removes the code that was added to enable HV KVM to work on PPC970 processors. The PPC970 is an old CPU that doesn't support virtualizing guest memory. Removing PPC970 support also lets us remove the code for allocating and managing contiguous real-mode areas, the code for the !kvm->arch.using_mmu_notifiers case, the code for pinning pages of guest memory when first accessed and keeping track of which pages have been pinned, and the code for handling H_ENTER hypercalls in virtual mode. Book3S HV KVM is now supported only on POWER7 and POWER8 processors. The KVM_CAP_PPC_RMA capability now always returns 0. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kvm/book3s_hv_builtin.c | 104 +---------------------------------- 1 file changed, 2 insertions(+), 102 deletions(-) (limited to 'arch/powerpc/kvm/book3s_hv_builtin.c') diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 4fdc27c80f4c..1786bf80bf00 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -33,95 +33,9 @@ * By default we reserve 5% of memory for hash pagetable allocation. */ static unsigned long kvm_cma_resv_ratio = 5; -/* - * We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area. - * Each RMA has to be physically contiguous and of a size that the - * hardware supports. PPC970 and POWER7 support 64MB, 128MB and 256MB, - * and other larger sizes. Since we are unlikely to be allocate that - * much physically contiguous memory after the system is up and running, - * we preallocate a set of RMAs in early boot using CMA. - * should be power of 2. - */ -unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT; /* 128MB */ -EXPORT_SYMBOL_GPL(kvm_rma_pages); static struct cma *kvm_cma; -/* Work out RMLS (real mode limit selector) field value for a given RMA size. - Assumes POWER7 or PPC970. */ -static inline int lpcr_rmls(unsigned long rma_size) -{ - switch (rma_size) { - case 32ul << 20: /* 32 MB */ - if (cpu_has_feature(CPU_FTR_ARCH_206)) - return 8; /* only supported on POWER7 */ - return -1; - case 64ul << 20: /* 64 MB */ - return 3; - case 128ul << 20: /* 128 MB */ - return 7; - case 256ul << 20: /* 256 MB */ - return 4; - case 1ul << 30: /* 1 GB */ - return 2; - case 16ul << 30: /* 16 GB */ - return 1; - case 256ul << 30: /* 256 GB */ - return 0; - default: - return -1; - } -} - -static int __init early_parse_rma_size(char *p) -{ - unsigned long kvm_rma_size; - - pr_debug("%s(%s)\n", __func__, p); - if (!p) - return -EINVAL; - kvm_rma_size = memparse(p, &p); - /* - * Check that the requested size is one supported in hardware - */ - if (lpcr_rmls(kvm_rma_size) < 0) { - pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size); - return -EINVAL; - } - kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT; - return 0; -} -early_param("kvm_rma_size", early_parse_rma_size); - -struct kvm_rma_info *kvm_alloc_rma() -{ - struct page *page; - struct kvm_rma_info *ri; - - ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL); - if (!ri) - return NULL; - page = cma_alloc(kvm_cma, kvm_rma_pages, order_base_2(kvm_rma_pages)); - if (!page) - goto err_out; - atomic_set(&ri->use_count, 1); - ri->base_pfn = page_to_pfn(page); - return ri; -err_out: - kfree(ri); - return NULL; -} -EXPORT_SYMBOL_GPL(kvm_alloc_rma); - -void kvm_release_rma(struct kvm_rma_info *ri) -{ - if (atomic_dec_and_test(&ri->use_count)) { - cma_release(kvm_cma, pfn_to_page(ri->base_pfn), kvm_rma_pages); - kfree(ri); - } -} -EXPORT_SYMBOL_GPL(kvm_release_rma); - static int __init early_parse_kvm_cma_resv(char *p) { pr_debug("%s(%s)\n", __func__, p); @@ -133,14 +47,9 @@ early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv); struct page *kvm_alloc_hpt(unsigned long nr_pages) { - unsigned long align_pages = HPT_ALIGN_PAGES; - VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); - /* Old CPUs require HPT aligned on a multiple of its size */ - if (!cpu_has_feature(CPU_FTR_ARCH_206)) - align_pages = nr_pages; - return cma_alloc(kvm_cma, nr_pages, order_base_2(align_pages)); + return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES)); } EXPORT_SYMBOL_GPL(kvm_alloc_hpt); @@ -181,16 +90,7 @@ void __init kvm_cma_reserve(void) if (selected_size) { pr_debug("%s: reserving %ld MiB for global area\n", __func__, (unsigned long)selected_size / SZ_1M); - /* - * Old CPUs require HPT aligned on a multiple of its size. So for them - * make the alignment as max size we could request. - */ - if (!cpu_has_feature(CPU_FTR_ARCH_206)) - align_size = __rounddown_pow_of_two(selected_size); - else - align_size = HPT_ALIGN_PAGES << PAGE_SHIFT; - - align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size); + align_size = HPT_ALIGN_PAGES << PAGE_SHIFT; cma_declare_contiguous(0, selected_size, 0, align_size, KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma); } -- cgit v1.2.3 From 90fd09f804213bcb9e092314c25b49d95153ad28 Mon Sep 17 00:00:00 2001 From: Sam Bobroff Date: Wed, 3 Dec 2014 13:30:40 +1100 Subject: KVM: PPC: Book3S HV: Improve H_CONFER implementation Currently the H_CONFER hcall is implemented in kernel virtual mode, meaning that whenever a guest thread does an H_CONFER, all the threads in that virtual core have to exit the guest. This is bad for performance because it interrupts the other threads even if they are doing useful work. The H_CONFER hcall is called by a guest VCPU when it is spinning on a spinlock and it detects that the spinlock is held by a guest VCPU that is currently not running on a physical CPU. The idea is to give this VCPU's time slice to the holder VCPU so that it can make progress towards releasing the lock. To avoid having the other threads exit the guest unnecessarily, we add a real-mode implementation of H_CONFER that checks whether the other threads are doing anything. If all the other threads are idle (i.e. in H_CEDE) or trying to confer (i.e. in H_CONFER), it returns H_TOO_HARD which causes a guest exit and allows the H_CONFER to be handled in virtual mode. Otherwise it spins for a short time (up to 10 microseconds) to give other threads the chance to observe that this thread is trying to confer. The spin loop also terminates when any thread exits the guest or when all other threads are idle or trying to confer. If the timeout is reached, the H_CONFER returns H_SUCCESS. In this case the guest VCPU will recheck the spinlock word and most likely call H_CONFER again. This also improves the implementation of the H_CONFER virtual mode handler. If the VCPU is part of a virtual core (vcore) which is runnable, there will be a 'runner' VCPU which has taken responsibility for running the vcore. In this case we yield to the runner VCPU rather than the target VCPU. We also introduce a check on the target VCPU's yield count: if it differs from the yield count passed to H_CONFER, the target VCPU has run since H_CONFER was called and may have already released the lock. This check is required by PAPR. Signed-off-by: Sam Bobroff Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kvm/book3s_hv_builtin.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'arch/powerpc/kvm/book3s_hv_builtin.c') diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 1786bf80bf00..3e43f815ac5d 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -96,6 +97,37 @@ void __init kvm_cma_reserve(void) } } +/* + * Real-mode H_CONFER implementation. + * We check if we are the only vcpu out of this virtual core + * still running in the guest and not ceded. If so, we pop up + * to the virtual-mode implementation; if not, just return to + * the guest. + */ +long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target, + unsigned int yield_count) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + int threads_running; + int threads_ceded; + int threads_conferring; + u64 stop = get_tb() + 10 * tb_ticks_per_usec; + int rv = H_SUCCESS; /* => don't yield */ + + set_bit(vcpu->arch.ptid, &vc->conferring_threads); + while ((get_tb() < stop) && (VCORE_EXIT_COUNT(vc) == 0)) { + threads_running = VCORE_ENTRY_COUNT(vc); + threads_ceded = hweight32(vc->napping_threads); + threads_conferring = hweight32(vc->conferring_threads); + if (threads_ceded + threads_conferring >= threads_running) { + rv = H_TOO_HARD; /* => do yield */ + break; + } + } + clear_bit(vcpu->arch.ptid, &vc->conferring_threads); + return rv; +} + /* * When running HV mode KVM we need to block certain operations while KVM VMs * exist in the system. We use a counter of VMs to track this. -- cgit v1.2.3