1#define pr_fmt(fmt) "Hyper-V: " fmt 2 3#include <linux/hyperv.h> 4#include <linux/log2.h> 5#include <linux/slab.h> 6#include <linux/types.h> 7 8#include <asm/fpu/api.h> 9#include <asm/mshyperv.h> 10#include <asm/msr.h> 11#include <asm/tlbflush.h> 12#include <asm/tlb.h> 13 14#define CREATE_TRACE_POINTS 15#include <asm/trace/hyperv.h> 16 17/* Each gva in gva_list encodes up to 4096 pages to flush */ 18#define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) 19 20static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, 21 const struct flush_tlb_info *info); 22 23/* 24 * Fills in gva_list starting from offset. Returns the number of items added. 25 */ 26static inline int fill_gva_list(u64 gva_list[], int offset, 27 unsigned long start, unsigned long end) 28{ 29 int gva_n = offset; 30 unsigned long cur = start, diff; 31 32 do { 33 diff = end > cur ? end - cur : 0; 34 35 gva_list[gva_n] = cur & PAGE_MASK; 36 /* 37 * Lower 12 bits encode the number of additional 38 * pages to flush (in addition to the 'cur' page). 39 */ 40 if (diff >= HV_TLB_FLUSH_UNIT) { 41 gva_list[gva_n] |= ~PAGE_MASK; 42 cur += HV_TLB_FLUSH_UNIT; 43 } else if (diff) { 44 gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT; 45 cur = end; 46 } 47 48 gva_n++; 49 50 } while (cur < end); 51 52 return gva_n - offset; 53} 54 55static bool cpu_is_lazy(int cpu) 56{ 57 return per_cpu(cpu_tlbstate_shared.is_lazy, cpu); 58} 59 60static void hyperv_flush_tlb_multi(const struct cpumask *cpus, 61 const struct flush_tlb_info *info) 62{ 63 int cpu, vcpu, gva_n, max_gvas; 64 struct hv_tlb_flush *flush; 65 u64 status; 66 unsigned long flags; 67 bool do_lazy = !info->freed_tables; 68 69 trace_hyperv_mmu_flush_tlb_multi(cpus, info); 70 71 if (!hv_hypercall_pg) 72 goto do_native; 73 74 local_irq_save(flags); 75 76 flush = *this_cpu_ptr(hyperv_pcpu_input_arg); 77 78 if (unlikely(!flush)) { 79 local_irq_restore(flags); 80 goto do_native; 81 } 82 83 if (info->mm) { 84 /* 85 * AddressSpace argument must match the CR3 with PCID bits 86 * stripped out. 87 */ 88 flush->address_space = virt_to_phys(info->mm->pgd); 89 flush->address_space &= CR3_ADDR_MASK; 90 flush->flags = 0; 91 } else { 92 flush->address_space = 0; 93 flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; 94 } 95 96 flush->processor_mask = 0; 97 if (cpumask_equal(cpus, cpu_present_mask)) { 98 flush->flags |= HV_FLUSH_ALL_PROCESSORS; 99 } else { 100 /* 101 * From the supplied CPU set we need to figure out if we can get 102 * away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} 103 * hypercalls. This is possible when the highest VP number in 104 * the set is < 64. As VP numbers are usually in ascending order 105 * and match Linux CPU ids, here is an optimization: we check 106 * the VP number for the highest bit in the supplied set first 107 * so we can quickly find out if using *_EX hypercalls is a 108 * must. We will also check all VP numbers when walking the 109 * supplied CPU set to remain correct in all cases. 110 */ 111 cpu = cpumask_last(cpus); 112 113 if (cpu < nr_cpumask_bits && hv_cpu_number_to_vp_number(cpu) >= 64) 114 goto do_ex_hypercall; 115 116 for_each_cpu(cpu, cpus) { 117 if (do_lazy && cpu_is_lazy(cpu)) 118 continue; 119 vcpu = hv_cpu_number_to_vp_number(cpu); 120 if (vcpu == VP_INVAL) { 121 local_irq_restore(flags); 122 goto do_native; 123 } 124 125 if (vcpu >= 64) 126 goto do_ex_hypercall; 127 128 __set_bit(vcpu, (unsigned long *) 129 &flush->processor_mask); 130 } 131 132 /* nothing to flush if 'processor_mask' ends up being empty */ 133 if (!flush->processor_mask) { 134 local_irq_restore(flags); 135 return; 136 } 137 } 138 139 /* 140 * We can flush not more than max_gvas with one hypercall. Flush the 141 * whole address space if we were asked to do more. 142 */ 143 max_gvas = (PAGE_SIZE - sizeof(*flush)) / sizeof(flush->gva_list[0]); 144 145 if (info->end == TLB_FLUSH_ALL) { 146 flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; 147 status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE, 148 flush, NULL); 149 } else if (info->end && 150 ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { 151 status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE, 152 flush, NULL); 153 } else { 154 gva_n = fill_gva_list(flush->gva_list, 0, 155 info->start, info->end); 156 status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST, 157 gva_n, 0, flush, NULL); 158 } 159 goto check_status; 160 161do_ex_hypercall: 162 status = hyperv_flush_tlb_others_ex(cpus, info); 163 164check_status: 165 local_irq_restore(flags); 166 167 if (hv_result_success(status)) 168 return; 169do_native: 170 native_flush_tlb_multi(cpus, info); 171} 172 173static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, 174 const struct flush_tlb_info *info) 175{ 176 int nr_bank = 0, max_gvas, gva_n; 177 struct hv_tlb_flush_ex *flush; 178 u64 status; 179 180 if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) 181 return HV_STATUS_INVALID_PARAMETER; 182 183 flush = *this_cpu_ptr(hyperv_pcpu_input_arg); 184 185 if (info->mm) { 186 /* 187 * AddressSpace argument must match the CR3 with PCID bits 188 * stripped out. 189 */ 190 flush->address_space = virt_to_phys(info->mm->pgd); 191 flush->address_space &= CR3_ADDR_MASK; 192 flush->flags = 0; 193 } else { 194 flush->address_space = 0; 195 flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; 196 } 197 198 flush->hv_vp_set.valid_bank_mask = 0; 199 200 flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; 201 nr_bank = cpumask_to_vpset_skip(&flush->hv_vp_set, cpus, 202 info->freed_tables ? NULL : cpu_is_lazy); 203 if (nr_bank < 0) 204 return HV_STATUS_INVALID_PARAMETER; 205 206 /* 207 * We can flush not more than max_gvas with one hypercall. Flush the 208 * whole address space if we were asked to do more. 209 */ 210 max_gvas = 211 (PAGE_SIZE - sizeof(*flush) - nr_bank * 212 sizeof(flush->hv_vp_set.bank_contents[0])) / 213 sizeof(flush->gva_list[0]); 214 215 if (info->end == TLB_FLUSH_ALL) { 216 flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; 217 status = hv_do_rep_hypercall( 218 HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, 219 0, nr_bank, flush, NULL); 220 } else if (info->end && 221 ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { 222 status = hv_do_rep_hypercall( 223 HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, 224 0, nr_bank, flush, NULL); 225 } else { 226 gva_n = fill_gva_list(flush->gva_list, nr_bank, 227 info->start, info->end); 228 status = hv_do_rep_hypercall( 229 HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX, 230 gva_n, nr_bank, flush, NULL); 231 } 232 233 return status; 234} 235 236void hyperv_setup_mmu_ops(void) 237{ 238 if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)) 239 return; 240 241 pr_info("Using hypercall for remote TLB flush\n"); 242 pv_ops.mmu.flush_tlb_multi = hyperv_flush_tlb_multi; 243 pv_ops.mmu.tlb_remove_table = tlb_remove_table; 244} 245