#include "qemu/osdep.h"
#include "qapi/error.h"
+#include "sysemu/hw_accel.h"
#include "sysemu/sysemu.h"
#include "qemu/log.h"
+#include "qemu/error-report.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "helper_regs.h"
#include "mmu-hash64.h"
#include "cpu-models.h"
#include "trace.h"
-#include "sysemu/kvm.h"
#include "kvm_ppc.h"
#include "hw/ppc/spapr_ovec.h"
+#include "qemu/error-report.h"
+#include "mmu-book3s-v3.h"
struct SPRSyncState {
int spr;
target_ulong mask;
};
-static void do_spr_sync(CPUState *cs, void *arg)
+static void do_spr_sync(CPUState *cs, run_on_cpu_data arg)
{
- struct SPRSyncState *s = arg;
+ struct SPRSyncState *s = arg.host_ptr;
PowerPCCPU *cpu = POWERPC_CPU(cs);
CPUPPCState *env = &cpu->env;
.value = value,
.mask = mask
};
- run_on_cpu(cs, do_spr_sync, &s);
+ run_on_cpu(cs, do_spr_sync, RUN_ON_CPU_HOST_PTR(&s));
}
static bool has_spr(PowerPCCPU *cpu, int spr)
return cpu->env.spr_cb[spr].name != NULL;
}
-static inline bool valid_pte_index(CPUPPCState *env, target_ulong pte_index)
+static inline bool valid_ptex(PowerPCCPU *cpu, target_ulong ptex)
{
/*
- * hash value/pteg group index is normalized by htab_mask
+ * hash value/pteg group index is normalized by HPT mask
*/
- if (((pte_index & ~7ULL) / HPTES_PER_GROUP) & ~env->htab_mask) {
+ if (((ptex & ~7ULL) / HPTES_PER_GROUP) & ~ppc_hash64_hpt_mask(cpu)) {
return false;
}
return true;
static target_ulong h_enter(PowerPCCPU *cpu, sPAPRMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
- CPUPPCState *env = &cpu->env;
target_ulong flags = args[0];
- target_ulong pte_index = args[1];
+ target_ulong ptex = args[1];
target_ulong pteh = args[2];
target_ulong ptel = args[3];
unsigned apshift;
target_ulong raddr;
- target_ulong index;
- uint64_t token;
+ target_ulong slot;
+ const ppc_hash_pte64_t *hptes;
apshift = ppc_hash64_hpte_page_shift_noslb(cpu, pteh, ptel);
if (!apshift) {
pteh &= ~0x60ULL;
- if (!valid_pte_index(env, pte_index)) {
+ if (!valid_ptex(cpu, ptex)) {
return H_PARAMETER;
}
- index = 0;
+ slot = ptex & 7ULL;
+ ptex = ptex & ~7ULL;
+
if (likely((flags & H_EXACT) == 0)) {
- pte_index &= ~7ULL;
- token = ppc_hash64_start_access(cpu, pte_index);
- for (; index < 8; index++) {
- if (!(ppc_hash64_load_hpte0(cpu, token, index) & HPTE64_V_VALID)) {
+ hptes = ppc_hash64_map_hptes(cpu, ptex, HPTES_PER_GROUP);
+ for (slot = 0; slot < 8; slot++) {
+ if (!(ppc_hash64_hpte0(cpu, hptes, slot) & HPTE64_V_VALID)) {
break;
}
}
- ppc_hash64_stop_access(cpu, token);
- if (index == 8) {
+ ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP);
+ if (slot == 8) {
return H_PTEG_FULL;
}
} else {
- token = ppc_hash64_start_access(cpu, pte_index);
- if (ppc_hash64_load_hpte0(cpu, token, 0) & HPTE64_V_VALID) {
- ppc_hash64_stop_access(cpu, token);
+ hptes = ppc_hash64_map_hptes(cpu, ptex + slot, 1);
+ if (ppc_hash64_hpte0(cpu, hptes, 0) & HPTE64_V_VALID) {
+ ppc_hash64_unmap_hptes(cpu, hptes, ptex + slot, 1);
return H_PTEG_FULL;
}
- ppc_hash64_stop_access(cpu, token);
+ ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1);
}
- ppc_hash64_store_hpte(cpu, pte_index + index,
- pteh | HPTE64_V_HPTE_DIRTY, ptel);
+ ppc_hash64_store_hpte(cpu, ptex + slot, pteh | HPTE64_V_HPTE_DIRTY, ptel);
- args[0] = pte_index + index;
+ args[0] = ptex + slot;
return H_SUCCESS;
}
target_ulong flags,
target_ulong *vp, target_ulong *rp)
{
- CPUPPCState *env = &cpu->env;
- uint64_t token;
+ const ppc_hash_pte64_t *hptes;
target_ulong v, r;
- if (!valid_pte_index(env, ptex)) {
+ if (!valid_ptex(cpu, ptex)) {
return REMOVE_PARM;
}
- token = ppc_hash64_start_access(cpu, ptex);
- v = ppc_hash64_load_hpte0(cpu, token, 0);
- r = ppc_hash64_load_hpte1(cpu, token, 0);
- ppc_hash64_stop_access(cpu, token);
+ hptes = ppc_hash64_map_hptes(cpu, ptex, 1);
+ v = ppc_hash64_hpte0(cpu, hptes, 0);
+ r = ppc_hash64_hpte1(cpu, hptes, 0);
+ ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1);
if ((v & HPTE64_V_VALID) == 0 ||
((flags & H_AVPN) && (v & ~0x7fULL) != avpn) ||
{
CPUPPCState *env = &cpu->env;
target_ulong flags = args[0];
- target_ulong pte_index = args[1];
+ target_ulong ptex = args[1];
target_ulong avpn = args[2];
RemoveResult ret;
- ret = remove_hpte(cpu, pte_index, avpn, flags,
+ ret = remove_hpte(cpu, ptex, avpn, flags,
&args[0], &args[1]);
switch (ret) {
{
CPUPPCState *env = &cpu->env;
target_ulong flags = args[0];
- target_ulong pte_index = args[1];
+ target_ulong ptex = args[1];
target_ulong avpn = args[2];
- uint64_t token;
+ const ppc_hash_pte64_t *hptes;
target_ulong v, r;
- if (!valid_pte_index(env, pte_index)) {
+ if (!valid_ptex(cpu, ptex)) {
return H_PARAMETER;
}
- token = ppc_hash64_start_access(cpu, pte_index);
- v = ppc_hash64_load_hpte0(cpu, token, 0);
- r = ppc_hash64_load_hpte1(cpu, token, 0);
- ppc_hash64_stop_access(cpu, token);
+ hptes = ppc_hash64_map_hptes(cpu, ptex, 1);
+ v = ppc_hash64_hpte0(cpu, hptes, 0);
+ r = ppc_hash64_hpte1(cpu, hptes, 0);
+ ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1);
if ((v & HPTE64_V_VALID) == 0 ||
((flags & H_AVPN) && (v & ~0x7fULL) != avpn)) {
r |= (flags << 55) & HPTE64_R_PP0;
r |= (flags << 48) & HPTE64_R_KEY_HI;
r |= flags & (HPTE64_R_PP | HPTE64_R_N | HPTE64_R_KEY_LO);
- ppc_hash64_store_hpte(cpu, pte_index,
+ ppc_hash64_store_hpte(cpu, ptex,
(v & ~HPTE64_V_VALID) | HPTE64_V_HPTE_DIRTY, 0);
- ppc_hash64_tlb_flush_hpte(cpu, pte_index, v, r);
+ ppc_hash64_tlb_flush_hpte(cpu, ptex, v, r);
/* Flush the tlb */
check_tlb_flush(env, true);
/* Don't need a memory barrier, due to qemu's global lock */
- ppc_hash64_store_hpte(cpu, pte_index, v | HPTE64_V_HPTE_DIRTY, r);
+ ppc_hash64_store_hpte(cpu, ptex, v | HPTE64_V_HPTE_DIRTY, r);
return H_SUCCESS;
}
static target_ulong h_read(PowerPCCPU *cpu, sPAPRMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
- CPUPPCState *env = &cpu->env;
target_ulong flags = args[0];
- target_ulong pte_index = args[1];
+ target_ulong ptex = args[1];
uint8_t *hpte;
int i, ridx, n_entries = 1;
- if (!valid_pte_index(env, pte_index)) {
+ if (!valid_ptex(cpu, ptex)) {
return H_PARAMETER;
}
if (flags & H_READ_4) {
/* Clear the two low order bits */
- pte_index &= ~(3ULL);
+ ptex &= ~(3ULL);
n_entries = 4;
}
- hpte = env->external_htab + (pte_index * HASH_PTE_SIZE_64);
+ hpte = spapr->htab + (ptex * HASH_PTE_SIZE_64);
for (i = 0, ridx = 0; i < n_entries; i++) {
args[ridx++] = ldq_p(hpte);
return H_SUCCESS;
}
+struct sPAPRPendingHPT {
+ /* These fields are read-only after initialization */
+ int shift;
+ QemuThread thread;
+
+ /* These fields are protected by the BQL */
+ bool complete;
+
+ /* These fields are private to the preparation thread if
+ * !complete, otherwise protected by the BQL */
+ int ret;
+ void *hpt;
+};
+
+static void free_pending_hpt(sPAPRPendingHPT *pending)
+{
+ if (pending->hpt) {
+ qemu_vfree(pending->hpt);
+ }
+
+ g_free(pending);
+}
+
+static void *hpt_prepare_thread(void *opaque)
+{
+ sPAPRPendingHPT *pending = opaque;
+ size_t size = 1ULL << pending->shift;
+
+ pending->hpt = qemu_memalign(size, size);
+ if (pending->hpt) {
+ memset(pending->hpt, 0, size);
+ pending->ret = H_SUCCESS;
+ } else {
+ pending->ret = H_NO_MEM;
+ }
+
+ qemu_mutex_lock_iothread();
+
+ if (SPAPR_MACHINE(qdev_get_machine())->pending_hpt == pending) {
+ /* Ready to go */
+ pending->complete = true;
+ } else {
+ /* We've been cancelled, clean ourselves up */
+ free_pending_hpt(pending);
+ }
+
+ qemu_mutex_unlock_iothread();
+ return NULL;
+}
+
+/* Must be called with BQL held */
+static void cancel_hpt_prepare(sPAPRMachineState *spapr)
+{
+ sPAPRPendingHPT *pending = spapr->pending_hpt;
+
+ /* Let the thread know it's cancelled */
+ spapr->pending_hpt = NULL;
+
+ if (!pending) {
+ /* Nothing to do */
+ return;
+ }
+
+ if (!pending->complete) {
+ /* thread will clean itself up */
+ return;
+ }
+
+ free_pending_hpt(pending);
+}
+
+/* Convert a return code from the KVM ioctl()s implementing resize HPT
+ * into a PAPR hypercall return code */
+static target_ulong resize_hpt_convert_rc(int ret)
+{
+ if (ret >= 100000) {
+ return H_LONG_BUSY_ORDER_100_SEC;
+ } else if (ret >= 10000) {
+ return H_LONG_BUSY_ORDER_10_SEC;
+ } else if (ret >= 1000) {
+ return H_LONG_BUSY_ORDER_1_SEC;
+ } else if (ret >= 100) {
+ return H_LONG_BUSY_ORDER_100_MSEC;
+ } else if (ret >= 10) {
+ return H_LONG_BUSY_ORDER_10_MSEC;
+ } else if (ret > 0) {
+ return H_LONG_BUSY_ORDER_1_MSEC;
+ }
+
+ switch (ret) {
+ case 0:
+ return H_SUCCESS;
+ case -EPERM:
+ return H_AUTHORITY;
+ case -EINVAL:
+ return H_PARAMETER;
+ case -ENXIO:
+ return H_CLOSED;
+ case -ENOSPC:
+ return H_PTEG_FULL;
+ case -EBUSY:
+ return H_BUSY;
+ case -ENOMEM:
+ return H_NO_MEM;
+ default:
+ return H_HARDWARE;
+ }
+}
+
+static target_ulong h_resize_hpt_prepare(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ target_ulong opcode,
+ target_ulong *args)
+{
+ target_ulong flags = args[0];
+ int shift = args[1];
+ sPAPRPendingHPT *pending = spapr->pending_hpt;
+ uint64_t current_ram_size = MACHINE(spapr)->ram_size;
+ int rc;
+
+ if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED) {
+ return H_AUTHORITY;
+ }
+
+ if (!spapr->htab_shift) {
+ /* Radix guest, no HPT */
+ return H_NOT_AVAILABLE;
+ }
+
+ trace_spapr_h_resize_hpt_prepare(flags, shift);
+
+ if (flags != 0) {
+ return H_PARAMETER;
+ }
+
+ if (shift && ((shift < 18) || (shift > 46))) {
+ return H_PARAMETER;
+ }
+
+ current_ram_size = pc_existing_dimms_capacity(&error_fatal);
+
+ /* We only allow the guest to allocate an HPT one order above what
+ * we'd normally give them (to stop a small guest claiming a huge
+ * chunk of resources in the HPT */
+ if (shift > (spapr_hpt_shift_for_ramsize(current_ram_size) + 1)) {
+ return H_RESOURCE;
+ }
+
+ rc = kvmppc_resize_hpt_prepare(cpu, flags, shift);
+ if (rc != -ENOSYS) {
+ return resize_hpt_convert_rc(rc);
+ }
+
+ if (pending) {
+ /* something already in progress */
+ if (pending->shift == shift) {
+ /* and it's suitable */
+ if (pending->complete) {
+ return pending->ret;
+ } else {
+ return H_LONG_BUSY_ORDER_100_MSEC;
+ }
+ }
+
+ /* not suitable, cancel and replace */
+ cancel_hpt_prepare(spapr);
+ }
+
+ if (!shift) {
+ /* nothing to do */
+ return H_SUCCESS;
+ }
+
+ /* start new prepare */
+
+ pending = g_new0(sPAPRPendingHPT, 1);
+ pending->shift = shift;
+ pending->ret = H_HARDWARE;
+
+ qemu_thread_create(&pending->thread, "sPAPR HPT prepare",
+ hpt_prepare_thread, pending, QEMU_THREAD_DETACHED);
+
+ spapr->pending_hpt = pending;
+
+ /* In theory we could estimate the time more accurately based on
+ * the new size, but there's not much point */
+ return H_LONG_BUSY_ORDER_100_MSEC;
+}
+
+static uint64_t new_hpte_load0(void *htab, uint64_t pteg, int slot)
+{
+ uint8_t *addr = htab;
+
+ addr += pteg * HASH_PTEG_SIZE_64;
+ addr += slot * HASH_PTE_SIZE_64;
+ return ldq_p(addr);
+}
+
+static void new_hpte_store(void *htab, uint64_t pteg, int slot,
+ uint64_t pte0, uint64_t pte1)
+{
+ uint8_t *addr = htab;
+
+ addr += pteg * HASH_PTEG_SIZE_64;
+ addr += slot * HASH_PTE_SIZE_64;
+
+ stq_p(addr, pte0);
+ stq_p(addr + HASH_PTE_SIZE_64 / 2, pte1);
+}
+
+static int rehash_hpte(PowerPCCPU *cpu,
+ const ppc_hash_pte64_t *hptes,
+ void *old_hpt, uint64_t oldsize,
+ void *new_hpt, uint64_t newsize,
+ uint64_t pteg, int slot)
+{
+ uint64_t old_hash_mask = (oldsize >> 7) - 1;
+ uint64_t new_hash_mask = (newsize >> 7) - 1;
+ target_ulong pte0 = ppc_hash64_hpte0(cpu, hptes, slot);
+ target_ulong pte1;
+ uint64_t avpn;
+ unsigned base_pg_shift;
+ uint64_t hash, new_pteg, replace_pte0;
+
+ if (!(pte0 & HPTE64_V_VALID) || !(pte0 & HPTE64_V_BOLTED)) {
+ return H_SUCCESS;
+ }
+
+ pte1 = ppc_hash64_hpte1(cpu, hptes, slot);
+
+ base_pg_shift = ppc_hash64_hpte_page_shift_noslb(cpu, pte0, pte1);
+ assert(base_pg_shift); /* H_ENTER shouldn't allow a bad encoding */
+ avpn = HPTE64_V_AVPN_VAL(pte0) & ~(((1ULL << base_pg_shift) - 1) >> 23);
+
+ if (pte0 & HPTE64_V_SECONDARY) {
+ pteg = ~pteg;
+ }
+
+ if ((pte0 & HPTE64_V_SSIZE) == HPTE64_V_SSIZE_256M) {
+ uint64_t offset, vsid;
+
+ /* We only have 28 - 23 bits of offset in avpn */
+ offset = (avpn & 0x1f) << 23;
+ vsid = avpn >> 5;
+ /* We can find more bits from the pteg value */
+ if (base_pg_shift < 23) {
+ offset |= ((vsid ^ pteg) & old_hash_mask) << base_pg_shift;
+ }
+
+ hash = vsid ^ (offset >> base_pg_shift);
+ } else if ((pte0 & HPTE64_V_SSIZE) == HPTE64_V_SSIZE_1T) {
+ uint64_t offset, vsid;
+
+ /* We only have 40 - 23 bits of seg_off in avpn */
+ offset = (avpn & 0x1ffff) << 23;
+ vsid = avpn >> 17;
+ if (base_pg_shift < 23) {
+ offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask)
+ << base_pg_shift;
+ }
+
+ hash = vsid ^ (vsid << 25) ^ (offset >> base_pg_shift);
+ } else {
+ error_report("rehash_pte: Bad segment size in HPTE");
+ return H_HARDWARE;
+ }
+
+ new_pteg = hash & new_hash_mask;
+ if (pte0 & HPTE64_V_SECONDARY) {
+ assert(~pteg == (hash & old_hash_mask));
+ new_pteg = ~new_pteg;
+ } else {
+ assert(pteg == (hash & old_hash_mask));
+ }
+ assert((oldsize != newsize) || (pteg == new_pteg));
+ replace_pte0 = new_hpte_load0(new_hpt, new_pteg, slot);
+ /*
+ * Strictly speaking, we don't need all these tests, since we only
+ * ever rehash bolted HPTEs. We might in future handle non-bolted
+ * HPTEs, though so make the logic correct for those cases as
+ * well.
+ */
+ if (replace_pte0 & HPTE64_V_VALID) {
+ assert(newsize < oldsize);
+ if (replace_pte0 & HPTE64_V_BOLTED) {
+ if (pte0 & HPTE64_V_BOLTED) {
+ /* Bolted collision, nothing we can do */
+ return H_PTEG_FULL;
+ } else {
+ /* Discard this hpte */
+ return H_SUCCESS;
+ }
+ }
+ }
+
+ new_hpte_store(new_hpt, new_pteg, slot, pte0, pte1);
+ return H_SUCCESS;
+}
+
+static int rehash_hpt(PowerPCCPU *cpu,
+ void *old_hpt, uint64_t oldsize,
+ void *new_hpt, uint64_t newsize)
+{
+ uint64_t n_ptegs = oldsize >> 7;
+ uint64_t pteg;
+ int slot;
+ int rc;
+
+ for (pteg = 0; pteg < n_ptegs; pteg++) {
+ hwaddr ptex = pteg * HPTES_PER_GROUP;
+ const ppc_hash_pte64_t *hptes
+ = ppc_hash64_map_hptes(cpu, ptex, HPTES_PER_GROUP);
+
+ if (!hptes) {
+ return H_HARDWARE;
+ }
+
+ for (slot = 0; slot < HPTES_PER_GROUP; slot++) {
+ rc = rehash_hpte(cpu, hptes, old_hpt, oldsize, new_hpt, newsize,
+ pteg, slot);
+ if (rc != H_SUCCESS) {
+ ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP);
+ return rc;
+ }
+ }
+ ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP);
+ }
+
+ return H_SUCCESS;
+}
+
+static target_ulong h_resize_hpt_commit(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ target_ulong opcode,
+ target_ulong *args)
+{
+ target_ulong flags = args[0];
+ target_ulong shift = args[1];
+ sPAPRPendingHPT *pending = spapr->pending_hpt;
+ int rc;
+ size_t newsize;
+
+ if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED) {
+ return H_AUTHORITY;
+ }
+
+ trace_spapr_h_resize_hpt_commit(flags, shift);
+
+ rc = kvmppc_resize_hpt_commit(cpu, flags, shift);
+ if (rc != -ENOSYS) {
+ return resize_hpt_convert_rc(rc);
+ }
+
+ if (flags != 0) {
+ return H_PARAMETER;
+ }
+
+ if (!pending || (pending->shift != shift)) {
+ /* no matching prepare */
+ return H_CLOSED;
+ }
+
+ if (!pending->complete) {
+ /* prepare has not completed */
+ return H_BUSY;
+ }
+
+ /* Shouldn't have got past PREPARE without an HPT */
+ g_assert(spapr->htab_shift);
+
+ newsize = 1ULL << pending->shift;
+ rc = rehash_hpt(cpu, spapr->htab, HTAB_SIZE(spapr),
+ pending->hpt, newsize);
+ if (rc == H_SUCCESS) {
+ qemu_vfree(spapr->htab);
+ spapr->htab = pending->hpt;
+ spapr->htab_shift = pending->shift;
+
+ if (kvm_enabled()) {
+ /* For KVM PR, update the HPT pointer */
+ target_ulong sdr1 = (target_ulong)(uintptr_t)spapr->htab
+ | (spapr->htab_shift - 18);
+ kvmppc_update_sdr1(sdr1);
+ }
+
+ pending->hpt = NULL; /* so it's not free()d */
+ }
+
+ /* Clean up */
+ spapr->pending_hpt = NULL;
+ free_pending_hpt(pending);
+
+ return rc;
+}
+
static target_ulong h_set_sprg0(PowerPCCPU *cpu, sPAPRMachineState *spapr,
target_ulong opcode, target_ulong *args)
{
return ret;
}
-typedef struct {
- uint32_t cpu_version;
- Error *err;
-} SetCompatState;
-
-static void do_set_compat(CPUState *cs, void *arg)
+static target_ulong h_clean_slb(PowerPCCPU *cpu, sPAPRMachineState *spapr,
+ target_ulong opcode, target_ulong *args)
{
- PowerPCCPU *cpu = POWERPC_CPU(cs);
- SetCompatState *s = arg;
-
- cpu_synchronize_state(cs);
- ppc_set_compat(cpu, s->cpu_version, &s->err);
+ qemu_log_mask(LOG_UNIMP, "Unimplemented SPAPR hcall 0x"TARGET_FMT_lx"%s\n",
+ opcode, " (H_CLEAN_SLB)");
+ return H_FUNCTION;
}
-#define get_compat_level(cpuver) ( \
- ((cpuver) == CPU_POWERPC_LOGICAL_2_05) ? 2050 : \
- ((cpuver) == CPU_POWERPC_LOGICAL_2_06) ? 2060 : \
- ((cpuver) == CPU_POWERPC_LOGICAL_2_06_PLUS) ? 2061 : \
- ((cpuver) == CPU_POWERPC_LOGICAL_2_07) ? 2070 : 0)
+static target_ulong h_invalidate_pid(PowerPCCPU *cpu, sPAPRMachineState *spapr,
+ target_ulong opcode, target_ulong *args)
+{
+ qemu_log_mask(LOG_UNIMP, "Unimplemented SPAPR hcall 0x"TARGET_FMT_lx"%s\n",
+ opcode, " (H_INVALIDATE_PID)");
+ return H_FUNCTION;
+}
-static void cas_handle_compat_cpu(PowerPCCPUClass *pcc, uint32_t pvr,
- unsigned max_lvl, unsigned *compat_lvl,
- unsigned *cpu_version)
+static void spapr_check_setup_free_hpt(sPAPRMachineState *spapr,
+ uint64_t patbe_old, uint64_t patbe_new)
{
- unsigned lvl = get_compat_level(pvr);
- bool is205, is206, is207;
+ /*
+ * We have 4 Options:
+ * HASH->HASH || RADIX->RADIX || NOTHING->RADIX : Do Nothing
+ * HASH->RADIX : Free HPT
+ * RADIX->HASH : Allocate HPT
+ * NOTHING->HASH : Allocate HPT
+ * Note: NOTHING implies the case where we said the guest could choose
+ * later and so assumed radix and now it's called H_REG_PROC_TBL
+ */
- if (!lvl) {
- return;
+ if ((patbe_old & PATBE1_GR) == (patbe_new & PATBE1_GR)) {
+ /* We assume RADIX, so this catches all the "Do Nothing" cases */
+ } else if (!(patbe_old & PATBE1_GR)) {
+ /* HASH->RADIX : Free HPT */
+ spapr_free_hpt(spapr);
+ } else if (!(patbe_new & PATBE1_GR)) {
+ /* RADIX->HASH || NOTHING->HASH : Allocate HPT */
+ spapr_setup_hpt_and_vrma(spapr);
}
+ return;
+}
+
+#define FLAGS_MASK 0x01FULL
+#define FLAG_MODIFY 0x10
+#define FLAG_REGISTER 0x08
+#define FLAG_RADIX 0x04
+#define FLAG_HASH_PROC_TBL 0x02
+#define FLAG_GTSE 0x01
+
+static target_ulong h_register_process_table(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ target_ulong opcode,
+ target_ulong *args)
+{
+ CPUState *cs;
+ target_ulong flags = args[0];
+ target_ulong proc_tbl = args[1];
+ target_ulong page_size = args[2];
+ target_ulong table_size = args[3];
+ uint64_t cproc;
- /* If it is a logical PVR, try to determine the highest level */
- is205 = (pcc->pcr_supported & PCR_COMPAT_2_05) &&
- (lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_05));
- is206 = (pcc->pcr_supported & PCR_COMPAT_2_06) &&
- ((lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_06)) ||
- (lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_06_PLUS)));
- is207 = (pcc->pcr_supported & PCR_COMPAT_2_07) &&
- (lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_07));
-
- if (is205 || is206 || is207) {
- if (!max_lvl) {
- /* User did not set the level, choose the highest */
- if (*compat_lvl <= lvl) {
- *compat_lvl = lvl;
- *cpu_version = pvr;
+ if (flags & ~FLAGS_MASK) { /* Check no reserved bits are set */
+ return H_PARAMETER;
+ }
+ if (flags & FLAG_MODIFY) {
+ if (flags & FLAG_REGISTER) {
+ if (flags & FLAG_RADIX) { /* Register new RADIX process table */
+ if (proc_tbl & 0xfff || proc_tbl >> 60) {
+ return H_P2;
+ } else if (page_size) {
+ return H_P3;
+ } else if (table_size > 24) {
+ return H_P4;
+ }
+ cproc = PATBE1_GR | proc_tbl | table_size;
+ } else { /* Register new HPT process table */
+ if (flags & FLAG_HASH_PROC_TBL) { /* Hash with Segment Tables */
+ /* TODO - Not Supported */
+ /* Technically caused by flag bits => H_PARAMETER */
+ return H_PARAMETER;
+ } else { /* Hash with SLB */
+ if (proc_tbl >> 38) {
+ return H_P2;
+ } else if (page_size & ~0x7) {
+ return H_P3;
+ } else if (table_size > 24) {
+ return H_P4;
+ }
+ }
+ cproc = (proc_tbl << 25) | page_size << 5 | table_size;
}
- } else if (max_lvl >= lvl) {
- /* User chose the level, don't set higher than this */
- *compat_lvl = lvl;
- *cpu_version = pvr;
+
+ } else { /* Deregister current process table */
+ /* Set to benign value: (current GR) | 0. This allows
+ * deregistration in KVM to succeed even if the radix bit in flags
+ * doesn't match the radix bit in the old PATB. */
+ cproc = spapr->patb_entry & PATBE1_GR;
}
+ } else { /* Maintain current registration */
+ if (!(flags & FLAG_RADIX) != !(spapr->patb_entry & PATBE1_GR)) {
+ /* Technically caused by flag bits => H_PARAMETER */
+ return H_PARAMETER; /* Existing Process Table Mismatch */
+ }
+ cproc = spapr->patb_entry;
+ }
+
+ /* Check if we need to setup OR free the hpt */
+ spapr_check_setup_free_hpt(spapr, spapr->patb_entry, cproc);
+
+ spapr->patb_entry = cproc; /* Save new process table */
+
+ /* Update the UPRT and GTSE bits in the LPCR for all cpus */
+ CPU_FOREACH(cs) {
+ set_spr(cs, SPR_LPCR,
+ ((flags & (FLAG_RADIX | FLAG_HASH_PROC_TBL)) ? LPCR_UPRT : 0) |
+ ((flags & FLAG_GTSE) ? LPCR_GTSE : 0),
+ LPCR_UPRT | LPCR_GTSE);
+ }
+
+ if (kvm_enabled()) {
+ return kvmppc_configure_v3_mmu(cpu, flags & FLAG_RADIX,
+ flags & FLAG_GTSE, cproc);
}
+ return H_SUCCESS;
}
-static target_ulong h_client_architecture_support(PowerPCCPU *cpu_,
- sPAPRMachineState *spapr,
- target_ulong opcode,
- target_ulong *args)
+#define H_SIGNAL_SYS_RESET_ALL -1
+#define H_SIGNAL_SYS_RESET_ALLBUTSELF -2
+
+static target_ulong h_signal_sys_reset(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ target_ulong opcode, target_ulong *args)
{
- target_ulong list = ppc64_phys_to_real(args[0]);
- target_ulong ov_table;
- PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu_);
+ target_long target = args[0];
CPUState *cs;
- bool cpu_match = false, cpu_update = true;
- unsigned old_cpu_version = cpu_->cpu_version;
- unsigned compat_lvl = 0, cpu_version = 0;
- unsigned max_lvl = get_compat_level(cpu_->max_compat);
- int counter;
- sPAPROptionVector *ov5_guest, *ov5_cas_old, *ov5_updates;
-
- /* Parse PVR list */
- for (counter = 0; counter < 512; ++counter) {
- uint32_t pvr, pvr_mask;
- pvr_mask = ldl_be_phys(&address_space_memory, list);
- list += 4;
- pvr = ldl_be_phys(&address_space_memory, list);
- list += 4;
-
- trace_spapr_cas_pvr_try(pvr);
- if (!max_lvl &&
- ((cpu_->env.spr[SPR_PVR] & pvr_mask) == (pvr & pvr_mask))) {
- cpu_match = true;
- cpu_version = 0;
- } else if (pvr == cpu_->cpu_version) {
- cpu_match = true;
- cpu_version = cpu_->cpu_version;
- } else if (!cpu_match) {
- cas_handle_compat_cpu(pcc, pvr, max_lvl, &compat_lvl, &cpu_version);
+ if (target < 0) {
+ /* Broadcast */
+ if (target < H_SIGNAL_SYS_RESET_ALLBUTSELF) {
+ return H_PARAMETER;
}
- /* Terminator record */
- if (~pvr_mask & pvr) {
- break;
+
+ CPU_FOREACH(cs) {
+ PowerPCCPU *c = POWERPC_CPU(cs);
+
+ if (target == H_SIGNAL_SYS_RESET_ALLBUTSELF) {
+ if (c == cpu) {
+ continue;
+ }
+ }
+ run_on_cpu(cs, spapr_do_system_reset_on_cpu, RUN_ON_CPU_NULL);
+ }
+ return H_SUCCESS;
+
+ } else {
+ /* Unicast */
+ CPU_FOREACH(cs) {
+ if (cpu->cpu_dt_id == target) {
+ run_on_cpu(cs, spapr_do_system_reset_on_cpu, RUN_ON_CPU_NULL);
+ return H_SUCCESS;
+ }
}
+ return H_PARAMETER;
}
+}
- /* Parsing finished */
- trace_spapr_cas_pvr(cpu_->cpu_version, cpu_match,
- cpu_version, pcc->pcr_mask);
+static uint32_t cas_check_pvr(sPAPRMachineState *spapr, PowerPCCPU *cpu,
+ target_ulong *addr, Error **errp)
+{
+ bool explicit_match = false; /* Matched the CPU's real PVR */
+ uint32_t max_compat = spapr->max_compat_pvr;
+ uint32_t best_compat = 0;
+ int i;
- /* Update CPUs */
- if (old_cpu_version != cpu_version) {
- CPU_FOREACH(cs) {
- SetCompatState s = {
- .cpu_version = cpu_version,
- .err = NULL,
- };
+ /*
+ * We scan the supplied table of PVRs looking for two things
+ * 1. Is our real CPU PVR in the list?
+ * 2. What's the "best" listed logical PVR
+ */
+ for (i = 0; i < 512; ++i) {
+ uint32_t pvr, pvr_mask;
- run_on_cpu(cs, do_set_compat, &s);
+ pvr_mask = ldl_be_phys(&address_space_memory, *addr);
+ pvr = ldl_be_phys(&address_space_memory, *addr + 4);
+ *addr += 8;
- if (s.err) {
- error_report_err(s.err);
- return H_HARDWARE;
+ if (~pvr_mask & pvr) {
+ break; /* Terminator record */
+ }
+
+ if ((cpu->env.spr[SPR_PVR] & pvr_mask) == (pvr & pvr_mask)) {
+ explicit_match = true;
+ } else {
+ if (ppc_check_compat(cpu, pvr, best_compat, max_compat)) {
+ best_compat = pvr;
}
}
}
- if (!cpu_version) {
- cpu_update = false;
+ if ((best_compat == 0) && (!explicit_match || max_compat)) {
+ /* We couldn't find a suitable compatibility mode, and either
+ * the guest doesn't support "raw" mode for this CPU, or raw
+ * mode is disabled because a maximum compat mode is set */
+ error_setg(errp, "Couldn't negotiate a suitable PVR during CAS");
+ return 0;
+ }
+
+ /* Parsing finished */
+ trace_spapr_cas_pvr(cpu->compat_pvr, explicit_match, best_compat);
+
+ return best_compat;
+}
+
+static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
+ sPAPRMachineState *spapr,
+ target_ulong opcode,
+ target_ulong *args)
+{
+ /* Working address in data buffer */
+ target_ulong addr = ppc64_phys_to_real(args[0]);
+ target_ulong ov_table;
+ uint32_t cas_pvr;
+ sPAPROptionVector *ov1_guest, *ov5_guest, *ov5_cas_old, *ov5_updates;
+ bool guest_radix;
+ Error *local_err = NULL;
+
+ cas_pvr = cas_check_pvr(spapr, cpu, &addr, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ return H_HARDWARE;
+ }
+
+ /* Update CPUs */
+ if (cpu->compat_pvr != cas_pvr) {
+ ppc_set_compat_all(cas_pvr, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ return H_HARDWARE;
+ }
}
/* For the future use: here @ov_table points to the first option vector */
- ov_table = list;
+ ov_table = addr;
+ ov1_guest = spapr_ovec_parse_vector(ov_table, 1);
ov5_guest = spapr_ovec_parse_vector(ov_table, 5);
+ if (spapr_ovec_test(ov5_guest, OV5_MMU_BOTH)) {
+ error_report("guest requested hash and radix MMU, which is invalid.");
+ exit(EXIT_FAILURE);
+ }
+ /* The radix/hash bit in byte 24 requires special handling: */
+ guest_radix = spapr_ovec_test(ov5_guest, OV5_MMU_RADIX_300);
+ spapr_ovec_clear(ov5_guest, OV5_MMU_RADIX_300);
+
+ /*
+ * HPT resizing is a bit of a special case, because when enabled
+ * we assume an HPT guest will support it until it says it
+ * doesn't, instead of assuming it won't support it until it says
+ * it does. Strictly speaking that approach could break for
+ * guests which don't make a CAS call, but those are so old we
+ * don't care about them. Without that assumption we'd have to
+ * make at least a temporary allocation of an HPT sized for max
+ * memory, which could be impossibly difficult under KVM HV if
+ * maxram is large.
+ */
+ if (!guest_radix && !spapr_ovec_test(ov5_guest, OV5_HPT_RESIZE)) {
+ int maxshift = spapr_hpt_shift_for_ramsize(MACHINE(spapr)->maxram_size);
+
+ if (spapr->resize_hpt == SPAPR_RESIZE_HPT_REQUIRED) {
+ error_report(
+ "h_client_architecture_support: Guest doesn't support HPT resizing, but resize-hpt=required");
+ exit(1);
+ }
+
+ if (spapr->htab_shift < maxshift) {
+ CPUState *cs;
+
+ /* Guest doesn't know about HPT resizing, so we
+ * pre-emptively resize for the maximum permitted RAM. At
+ * the point this is called, nothing should have been
+ * entered into the existing HPT */
+ spapr_reallocate_hpt(spapr, maxshift, &error_fatal);
+ CPU_FOREACH(cs) {
+ if (kvm_enabled()) {
+ /* For KVM PR, update the HPT pointer */
+ target_ulong sdr1 = (target_ulong)(uintptr_t)spapr->htab
+ | (spapr->htab_shift - 18);
+ kvmppc_update_sdr1(sdr1);
+ }
+ }
+ }
+ }
/* NOTE: there are actually a number of ov5 bits where input from the
* guest is always zero, and the platform/QEMU enables them independently
ov5_updates = spapr_ovec_new();
spapr->cas_reboot = spapr_ovec_diff(ov5_updates,
ov5_cas_old, spapr->ov5_cas);
-
+ /* Now that processing is finished, set the radix/hash bit for the
+ * guest if it requested a valid mode; otherwise terminate the boot. */
+ if (guest_radix) {
+ if (kvm_enabled() && !kvmppc_has_cap_mmu_radix()) {
+ error_report("Guest requested unavailable MMU mode (radix).");
+ exit(EXIT_FAILURE);
+ }
+ spapr_ovec_set(spapr->ov5_cas, OV5_MMU_RADIX_300);
+ } else {
+ if (kvm_enabled() && kvmppc_has_cap_mmu_radix()
+ && !kvmppc_has_cap_mmu_hash_v3()) {
+ error_report("Guest requested unavailable MMU mode (hash).");
+ exit(EXIT_FAILURE);
+ }
+ }
+ spapr->cas_legacy_guest_workaround = !spapr_ovec_test(ov1_guest,
+ OV1_PPC_3_00);
if (!spapr->cas_reboot) {
spapr->cas_reboot =
- (spapr_h_cas_compose_response(spapr, args[1], args[2], cpu_update,
+ (spapr_h_cas_compose_response(spapr, args[1], args[2],
ov5_updates) != 0);
}
spapr_ovec_cleanup(ov5_updates);
if (spapr->cas_reboot) {
- qemu_system_reset_request();
+ qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET);
+ } else {
+ /* If ppc_spapr_reset() did not set up a HPT but one is necessary
+ * (because the guest isn't going to use radix) then set it up here. */
+ if ((spapr->patb_entry & PATBE1_GR) && !guest_radix) {
+ /* legacy hash or new hash: */
+ spapr_setup_hpt_and_vrma(spapr);
+ }
}
return H_SUCCESS;
/* hcall-bulk */
spapr_register_hypercall(H_BULK_REMOVE, h_bulk_remove);
+ /* hcall-hpt-resize */
+ spapr_register_hypercall(H_RESIZE_HPT_PREPARE, h_resize_hpt_prepare);
+ spapr_register_hypercall(H_RESIZE_HPT_COMMIT, h_resize_hpt_commit);
+
/* hcall-splpar */
spapr_register_hypercall(H_REGISTER_VPA, h_register_vpa);
spapr_register_hypercall(H_CEDE, h_cede);
+ spapr_register_hypercall(H_SIGNAL_SYS_RESET, h_signal_sys_reset);
/* processor register resource access h-calls */
spapr_register_hypercall(H_SET_SPRG0, h_set_sprg0);
spapr_register_hypercall(H_PAGE_INIT, h_page_init);
spapr_register_hypercall(H_SET_MODE, h_set_mode);
+ /* In Memory Table MMU h-calls */
+ spapr_register_hypercall(H_CLEAN_SLB, h_clean_slb);
+ spapr_register_hypercall(H_INVALIDATE_PID, h_invalidate_pid);
+ spapr_register_hypercall(H_REGISTER_PROC_TBL, h_register_process_table);
+
/* "debugger" hcalls (also used by SLOF). Note: We do -not- differenciate
* here between the "CI" and the "CACHE" variants, they will use whatever
* mapping attributes qemu is using. When using KVM, the kernel will
projects / qemu.git / blobdiff