diff options
Diffstat (limited to 'target-arm/helper.c')
| -rw-r--r-- | target-arm/helper.c | 122 |
1 files changed, 117 insertions, 5 deletions
diff --git a/target-arm/helper.c b/target-arm/helper.c index 62f7fd3280..2ffc588575 100644 --- a/target-arm/helper.c +++ b/target-arm/helper.c @@ -10,6 +10,8 @@ #include <zlib.h> /* For crc32 */ #ifndef CONFIG_USER_ONLY +#include "exec/softmmu_exec.h" + static inline int get_phys_addr(CPUARMState *env, target_ulong address, int access_type, int is_user, hwaddr *phys_ptr, int *prot, @@ -1745,6 +1747,29 @@ static void tlbi_aa64_asid_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush(CPU(cpu), asid == 0); } +static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* We don't implement EL2, so the only control on DC ZVA is the + * bit in the SCTLR which can prohibit access for EL0. + */ + if (arm_current_pl(env) == 0 && !(env->cp15.c1_sys & SCTLR_DZE)) { + return CP_ACCESS_TRAP; + } + return CP_ACCESS_OK; +} + +static uint64_t aa64_dczid_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + ARMCPU *cpu = arm_env_get_cpu(env); + int dzp_bit = 1 << 4; + + /* DZP indicates whether DC ZVA access is allowed */ + if (aa64_zva_access(env, NULL) != CP_ACCESS_OK) { + dzp_bit = 0; + } + return cpu->dcz_blocksize | dzp_bit; +} + static const ARMCPRegInfo v8_cp_reginfo[] = { /* Minimal set of EL0-visible registers. This will need to be expanded * significantly for system emulation of AArch64 CPUs. @@ -1764,13 +1789,18 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { { .name = "FPSR", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .opc2 = 1, .crn = 4, .crm = 4, .access = PL0_RW, .readfn = aa64_fpsr_read, .writefn = aa64_fpsr_write }, - /* Prohibit use of DC ZVA. OPTME: implement DC ZVA and allow its use. - * For system mode the DZP bit here will need to be computed, not constant. - */ { .name = "DCZID_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .opc2 = 7, .crn = 0, .crm = 0, - .access = PL0_R, .type = ARM_CP_CONST, - .resetvalue = 0x10 }, + .access = PL0_R, .type = ARM_CP_NO_MIGRATE, + .readfn = aa64_dczid_read }, + { .name = "DC_ZVA", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 3, .crn = 7, .crm = 4, .opc2 = 1, + .access = PL0_W, .type = ARM_CP_DC_ZVA, +#ifndef CONFIG_USER_ONLY + /* Avoid overhead of an access check that always passes in user-mode */ + .accessfn = aa64_zva_access, +#endif + }, { .name = "CURRENTEL", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .opc2 = 2, .crn = 4, .crm = 2, .access = PL1_R, .type = ARM_CP_CURRENTEL }, @@ -3930,6 +3960,88 @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t reg, uint32_t val) #endif +void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) +{ + /* Implement DC ZVA, which zeroes a fixed-length block of memory. + * Note that we do not implement the (architecturally mandated) + * alignment fault for attempts to use this on Device memory + * (which matches the usual QEMU behaviour of not implementing either + * alignment faults or any memory attribute handling). + */ + + ARMCPU *cpu = arm_env_get_cpu(env); + uint64_t blocklen = 4 << cpu->dcz_blocksize; + uint64_t vaddr = vaddr_in & ~(blocklen - 1); + +#ifndef CONFIG_USER_ONLY + { + /* Slightly awkwardly, QEMU's TARGET_PAGE_SIZE may be less than + * the block size so we might have to do more than one TLB lookup. + * We know that in fact for any v8 CPU the page size is at least 4K + * and the block size must be 2K or less, but TARGET_PAGE_SIZE is only + * 1K as an artefact of legacy v5 subpage support being present in the + * same QEMU executable. + */ + int maxidx = DIV_ROUND_UP(blocklen, TARGET_PAGE_SIZE); + void *hostaddr[maxidx]; + int try, i; + + for (try = 0; try < 2; try++) { + + for (i = 0; i < maxidx; i++) { + hostaddr[i] = tlb_vaddr_to_host(env, + vaddr + TARGET_PAGE_SIZE * i, + 1, cpu_mmu_index(env)); + if (!hostaddr[i]) { + break; + } + } + if (i == maxidx) { + /* If it's all in the TLB it's fair game for just writing to; + * we know we don't need to update dirty status, etc. + */ + for (i = 0; i < maxidx - 1; i++) { + memset(hostaddr[i], 0, TARGET_PAGE_SIZE); + } + memset(hostaddr[i], 0, blocklen - (i * TARGET_PAGE_SIZE)); + return; + } + /* OK, try a store and see if we can populate the tlb. This + * might cause an exception if the memory isn't writable, + * in which case we will longjmp out of here. We must for + * this purpose use the actual register value passed to us + * so that we get the fault address right. + */ + helper_ret_stb_mmu(env, vaddr_in, 0, cpu_mmu_index(env), GETRA()); + /* Now we can populate the other TLB entries, if any */ + for (i = 0; i < maxidx; i++) { + uint64_t va = vaddr + TARGET_PAGE_SIZE * i; + if (va != (vaddr_in & TARGET_PAGE_MASK)) { + helper_ret_stb_mmu(env, va, 0, cpu_mmu_index(env), GETRA()); + } + } + } + + /* Slow path (probably attempt to do this to an I/O device or + * similar, or clearing of a block of code we have translations + * cached for). Just do a series of byte writes as the architecture + * demands. It's not worth trying to use a cpu_physical_memory_map(), + * memset(), unmap() sequence here because: + * + we'd need to account for the blocksize being larger than a page + * + the direct-RAM access case is almost always going to be dealt + * with in the fastpath code above, so there's no speed benefit + * + we would have to deal with the map returning NULL because the + * bounce buffer was in use + */ + for (i = 0; i < blocklen; i++) { + helper_ret_stb_mmu(env, vaddr + i, 0, cpu_mmu_index(env), GETRA()); + } + } +#else + memset(g2h(vaddr), 0, blocklen); +#endif +} + /* Note that signed overflow is undefined in C. The following routines are careful to use unsigned types where modulo arithmetic is required. Failure to do so _will_ break on newer gcc. */ |