diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 27bb64469604..08c3e65bf0f2 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -24,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -511,12 +513,229 @@ static int __init set_ntlb(char *str) __setup("ntlb=", set_ntlb); -/* Comparison function for EntryHi VPN fields. */ -static int r4k_vpn_cmp(const void *a, const void *b) +/* The start bit position of VPN2 and Mask in EntryHi/PageMask registers. */ +#define VPN2_SHIFT 13 + +/* Read full EntryHi even with CONFIG_32BIT. */ +static inline unsigned long long read_c0_entryhi_native(void) { - long v = *(unsigned long *)a - *(unsigned long *)b; - int s = sizeof(long) > sizeof(int) ? sizeof(long) * 8 - 1: 0; - return s ? (v != 0) | v >> s : v; + return cpu_has_64bits ? read_c0_entryhi_64() : read_c0_entryhi(); +} + +/* Write full EntryHi even with CONFIG_32BIT. */ +static inline void write_c0_entryhi_native(unsigned long long v) +{ + if (cpu_has_64bits) + write_c0_entryhi_64(v); + else + write_c0_entryhi(v); +} + +/* TLB entry state for uniquification. */ +struct tlbent { + unsigned long long wired:1; + unsigned long long global:1; + unsigned long long asid:10; + unsigned long long vpn:51; + unsigned long long pagesz:5; + unsigned long long index:14; +}; + +/* + * Comparison function for TLB entry sorting. Place wired entries first, + * then global entries, then order by the increasing VPN/ASID and the + * decreasing page size. This lets us avoid clashes with wired entries + * easily and get entries for larger pages out of the way first. + * + * We could group bits so as to reduce the number of comparisons, but this + * is seldom executed and not performance-critical, so prefer legibility. + */ +static int r4k_entry_cmp(const void *a, const void *b) +{ + struct tlbent ea = *(struct tlbent *)a, eb = *(struct tlbent *)b; + + if (ea.wired > eb.wired) + return -1; + else if (ea.wired < eb.wired) + return 1; + else if (ea.global > eb.global) + return -1; + else if (ea.global < eb.global) + return 1; + else if (ea.vpn < eb.vpn) + return -1; + else if (ea.vpn > eb.vpn) + return 1; + else if (ea.asid < eb.asid) + return -1; + else if (ea.asid > eb.asid) + return 1; + else if (ea.pagesz > eb.pagesz) + return -1; + else if (ea.pagesz < eb.pagesz) + return 1; + else + return 0; +} + +/* + * Fetch all the TLB entries. Mask individual VPN values retrieved with + * the corresponding page mask and ignoring any 1KiB extension as we'll + * be using 4KiB pages for uniquification. + */ +static void __ref r4k_tlb_uniquify_read(struct tlbent *tlb_vpns, int tlbsize) +{ + int start = num_wired_entries(); + unsigned long long vpn_mask; + bool global; + int i; + + vpn_mask = GENMASK(current_cpu_data.vmbits - 1, VPN2_SHIFT); + vpn_mask |= cpu_has_64bits ? 3ULL << 62 : 1 << 31; + + for (i = 0; i < tlbsize; i++) { + unsigned long long entryhi, vpn, mask, asid; + unsigned int pagesz; + + write_c0_index(i); + mtc0_tlbr_hazard(); + tlb_read(); + tlb_read_hazard(); + + global = !!(read_c0_entrylo0() & ENTRYLO_G); + entryhi = read_c0_entryhi_native(); + mask = read_c0_pagemask(); + + asid = entryhi & cpu_asid_mask(¤t_cpu_data); + vpn = (entryhi & vpn_mask & ~mask) >> VPN2_SHIFT; + pagesz = ilog2((mask >> VPN2_SHIFT) + 1); + + tlb_vpns[i].global = global; + tlb_vpns[i].asid = global ? 0 : asid; + tlb_vpns[i].vpn = vpn; + tlb_vpns[i].pagesz = pagesz; + tlb_vpns[i].wired = i < start; + tlb_vpns[i].index = i; + } +} + +/* + * Write unique values to all but the wired TLB entries each, using + * the 4KiB page size. This size might not be supported with R6, but + * EHINV is mandatory for R6, so we won't ever be called in that case. + * + * A sorted table is supplied with any wired entries at the beginning, + * followed by any global entries, and then finally regular entries. + * We start at the VPN and ASID values of zero and only assign user + * addresses, therefore guaranteeing no clash with addresses produced + * by UNIQUE_ENTRYHI. We avoid any VPN values used by wired or global + * entries, by increasing the VPN value beyond the span of such entry. + * + * When a VPN/ASID clash is found with a regular entry we increment the + * ASID instead until no VPN/ASID clash has been found or the ASID space + * has been exhausted, in which case we increase the VPN value beyond + * the span of the largest clashing entry. + * + * We do not need to be concerned about FTLB or MMID configurations as + * those are required to implement the EHINV feature. + */ +static void __ref r4k_tlb_uniquify_write(struct tlbent *tlb_vpns, int tlbsize) +{ + unsigned long long asid, vpn, vpn_size, pagesz; + int widx, gidx, idx, sidx, lidx, i; + + vpn_size = 1ULL << (current_cpu_data.vmbits - VPN2_SHIFT); + pagesz = ilog2((PM_4K >> VPN2_SHIFT) + 1); + + write_c0_pagemask(PM_4K); + write_c0_entrylo0(0); + write_c0_entrylo1(0); + + asid = 0; + vpn = 0; + widx = 0; + gidx = 0; + for (sidx = 0; sidx < tlbsize && tlb_vpns[sidx].wired; sidx++) + ; + for (lidx = sidx; lidx < tlbsize && tlb_vpns[lidx].global; lidx++) + ; + idx = gidx = sidx + 1; + for (i = sidx; i < tlbsize; i++) { + unsigned long long entryhi, vpn_pagesz = 0; + + while (1) { + if (WARN_ON(vpn >= vpn_size)) { + dump_tlb_all(); + /* Pray local_flush_tlb_all() will cope. */ + return; + } + + /* VPN must be below the next wired entry. */ + if (widx < sidx && vpn >= tlb_vpns[widx].vpn) { + vpn = max(vpn, + (tlb_vpns[widx].vpn + + (1ULL << tlb_vpns[widx].pagesz))); + asid = 0; + widx++; + continue; + } + /* VPN must be below the next global entry. */ + if (gidx < lidx && vpn >= tlb_vpns[gidx].vpn) { + vpn = max(vpn, + (tlb_vpns[gidx].vpn + + (1ULL << tlb_vpns[gidx].pagesz))); + asid = 0; + gidx++; + continue; + } + /* Try to find a free ASID so as to conserve VPNs. */ + if (idx < tlbsize && vpn == tlb_vpns[idx].vpn && + asid == tlb_vpns[idx].asid) { + unsigned long long idx_pagesz; + + idx_pagesz = tlb_vpns[idx].pagesz; + vpn_pagesz = max(vpn_pagesz, idx_pagesz); + do + idx++; + while (idx < tlbsize && + vpn == tlb_vpns[idx].vpn && + asid == tlb_vpns[idx].asid); + asid++; + if (asid > cpu_asid_mask(¤t_cpu_data)) { + vpn += vpn_pagesz; + asid = 0; + vpn_pagesz = 0; + } + continue; + } + /* VPN mustn't be above the next regular entry. */ + if (idx < tlbsize && vpn > tlb_vpns[idx].vpn) { + vpn = max(vpn, + (tlb_vpns[idx].vpn + + (1ULL << tlb_vpns[idx].pagesz))); + asid = 0; + idx++; + continue; + } + break; + } + + entryhi = (vpn << VPN2_SHIFT) | asid; + write_c0_entryhi_native(entryhi); + write_c0_index(tlb_vpns[i].index); + mtc0_tlbw_hazard(); + tlb_write_indexed(); + + tlb_vpns[i].asid = asid; + tlb_vpns[i].vpn = vpn; + tlb_vpns[i].pagesz = pagesz; + + asid++; + if (asid > cpu_asid_mask(¤t_cpu_data)) { + vpn += 1ULL << pagesz; + asid = 0; + } + } } /* @@ -527,14 +746,8 @@ static void __ref r4k_tlb_uniquify(void) { int tlbsize = current_cpu_data.tlbsize; bool use_slab = slab_is_available(); - int start = num_wired_entries(); phys_addr_t tlb_vpn_size; - unsigned long *tlb_vpns; - unsigned long vpn_mask; - int cnt, ent, idx, i; - - vpn_mask = GENMASK(cpu_vmbits - 1, 13); - vpn_mask |= IS_ENABLED(CONFIG_64BIT) ? 3ULL << 62 : 1 << 31; + struct tlbent *tlb_vpns; tlb_vpn_size = tlbsize * sizeof(*tlb_vpns); tlb_vpns = (use_slab ? @@ -545,52 +758,13 @@ static void __ref r4k_tlb_uniquify(void) htw_stop(); - for (i = start, cnt = 0; i < tlbsize; i++, cnt++) { - unsigned long vpn; + r4k_tlb_uniquify_read(tlb_vpns, tlbsize); - write_c0_index(i); - mtc0_tlbr_hazard(); - tlb_read(); - tlb_read_hazard(); - vpn = read_c0_entryhi(); - vpn &= vpn_mask & PAGE_MASK; - tlb_vpns[cnt] = vpn; + sort(tlb_vpns, tlbsize, sizeof(*tlb_vpns), r4k_entry_cmp, NULL); - /* Prevent any large pages from overlapping regular ones. */ - write_c0_pagemask(read_c0_pagemask() & PM_DEFAULT_MASK); - mtc0_tlbw_hazard(); - tlb_write_indexed(); - tlbw_use_hazard(); - } - - sort(tlb_vpns, cnt, sizeof(tlb_vpns[0]), r4k_vpn_cmp, NULL); + r4k_tlb_uniquify_write(tlb_vpns, tlbsize); write_c0_pagemask(PM_DEFAULT_MASK); - write_c0_entrylo0(0); - write_c0_entrylo1(0); - - idx = 0; - ent = tlbsize; - for (i = start; i < tlbsize; i++) - while (1) { - unsigned long entryhi, vpn; - - entryhi = UNIQUE_ENTRYHI(ent); - vpn = entryhi & vpn_mask & PAGE_MASK; - - if (idx >= cnt || vpn < tlb_vpns[idx]) { - write_c0_entryhi(entryhi); - write_c0_index(i); - mtc0_tlbw_hazard(); - tlb_write_indexed(); - ent++; - break; - } else if (vpn == tlb_vpns[idx]) { - ent++; - } else { - idx++; - } - } tlbw_use_hazard(); htw_start();