[Qemu-ppc] [PATCH v5 4/7] target/ppc: Implement H_REGISTER_PROCESS_TABLE H_CALL

[Sam Bobroff]

From: Suraj Jitindar Singh <address@hidden>

The H_REGISTER_PROCESS_TABLE H_CALL is used by a guest to indicate to the
hypervisor where in memory its process table is and how translation should
be performed using this process table.

Provide the implementation of this H_CALL for a guest.

We first check for invalid flags, then parse the flags to determine the
operation, and then check the other parameters for valid values based on
the operation (register new table/deregister table/maintain registration).
The process table is then stored in the appropriate location and registered
with the hypervisor (if running under KVM), and the LPCR_[UPRT/GTSE] bits
are updated as required.

Signed-off-by: Suraj Jitindar Singh <address@hidden>
Signed-off-by: Sam Bobroff <address@hidden>
---
Changes in v5:
* Corrected "compacted" case statement.
* Re-arranged a bit and added non-KVM stub for kvmppc_configure_v3_mmu() to fix
  compile without KVM.
* Merged the parts of "Only setup HPT if necessary" that do not rely on the new
  option vector parsing (introduced later) into this patch, this covered the
  line that was from a stray hunk and reduced churn.

 hw/ppc/spapr.c         |  35 +++++++++------
 hw/ppc/spapr_hcall.c   | 113 +++++++++++++++++++++++++++++++++++++++++++++++--
 include/hw/ppc/spapr.h |   1 +
 target/ppc/kvm.c       |  31 ++++++++++++++
 target/ppc/kvm_ppc.h   |  10 +++++
 5 files changed, 175 insertions(+), 15 deletions(-)

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index d96e5f60fe..8f14914eea 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -40,6 +40,7 @@
 #include "kvm_ppc.h"
 #include "migration/migration.h"
 #include "mmu-hash64.h"
+#include "mmu-book3s-v3.h"
 #include "qom/cpu.h"
 
 #include "hw/boards.h"
@@ -1112,7 +1113,7 @@ static int get_htab_fd(sPAPRMachineState *spapr)
     return spapr->htab_fd;
 }
 
-static void close_htab_fd(sPAPRMachineState *spapr)
+void close_htab_fd(sPAPRMachineState *spapr)
 {
     if (spapr->htab_fd >= 0) {
         close(spapr->htab_fd);
@@ -1239,6 +1240,19 @@ static void spapr_reallocate_hpt(sPAPRMachineState 
*spapr, int shift,
     }
 }
 
+void spapr_setup_hpt_and_vrma(sPAPRMachineState *spapr)
+{
+    spapr_reallocate_hpt(spapr,
+                     spapr_hpt_shift_for_ramsize(MACHINE(spapr)->maxram_size),
+                     &error_fatal);
+    if (spapr->vrma_adjust) {
+        spapr->rma_size = kvmppc_rma_size(spapr_node0_size(),
+                                          spapr->htab_shift);
+    }
+    /* We're setting up a hash table, so that means we're not radix */
+    spapr->patb_entry = 0;
+}
+
 static void find_unknown_sysbus_device(SysBusDevice *sbdev, void *opaque)
 {
     bool matched = false;
@@ -1267,17 +1281,14 @@ static void ppc_spapr_reset(void)
     /* Check for unknown sysbus devices */
     foreach_dynamic_sysbus_device(find_unknown_sysbus_device, NULL);
 
-    spapr->patb_entry = 0;
-
-    /* Allocate and/or reset the hash page table */
-    spapr_reallocate_hpt(spapr,
-                         spapr_hpt_shift_for_ramsize(machine->maxram_size),
-                         &error_fatal);
-
-    /* Update the RMA size if necessary */
-    if (spapr->vrma_adjust) {
-        spapr->rma_size = kvmppc_rma_size(spapr_node0_size(),
-                                          spapr->htab_shift);
+    if (kvm_enabled() && kvmppc_has_cap_mmu_radix()) {
+        /* If using KVM with radix mode available, VCPUs can be started
+         * without a HPT because KVM will start them in radix mode.
+         * Set the GR bit in PATB so that we know there is no HPT. */
+        spapr->patb_entry = PATBE1_GR;
+    } else {
+        spapr->patb_entry = 0;
+        spapr_setup_hpt_and_vrma(spapr);
     }
 
     qemu_devices_reset();
diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index 87b94ef9e7..374eb0cc37 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -12,6 +12,8 @@
 #include "trace.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;
@@ -894,14 +896,119 @@ static target_ulong h_invalidate_pid(PowerPCCPU *cpu, 
sPAPRMachineState *spapr,
     return H_FUNCTION;
 }
 
+static void spapr_check_setup_free_hpt(sPAPRMachineState *spapr,
+                                       uint64_t patbe_old, uint64_t patbe_new)
+{
+    /*
+     * 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 ((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 */
+        g_free(spapr->htab);
+        spapr->htab = NULL;
+        spapr->htab_shift = 0;
+        close_htab_fd(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)
 {
-    qemu_log_mask(LOG_UNIMP, "Unimplemented SPAPR hcall 0x" TARGET_FMT_lx 
"%s\n",
-                  opcode, " (H_REGISTER_PROC_TBL)");
-    return H_FUNCTION;
+    CPUPPCState *env = &cpu->env;
+    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 (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 { /* 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 */
+    if ((flags & FLAG_RADIX) || (flags & FLAG_HASH_PROC_TBL)) {
+        /* Use Process TBL */
+        env->spr[SPR_LPCR] |= LPCR_UPRT;
+    } else {
+        env->spr[SPR_LPCR] &= ~LPCR_UPRT;
+    }
+    if (flags & FLAG_GTSE) { /* Partition Uses Guest Translation Shootdwn */
+        env->spr[SPR_LPCR] |= LPCR_GTSE;
+    } else {
+        env->spr[SPR_LPCR] &= ~LPCR_GTSE;
+    }
+
+    if (kvm_enabled()) {
+        return kvmppc_configure_v3_mmu(cpu, flags & FLAG_RADIX,
+                                       flags & FLAG_GTSE, cproc);
+    }
+    return H_SUCCESS;
 }
 
 #define H_SIGNAL_SYS_RESET_ALL         -1
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 342f7a61f4..e9a8eb47d9 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -608,6 +608,7 @@ void spapr_dt_events(sPAPRMachineState *sm, void *fdt);
 int spapr_h_cas_compose_response(sPAPRMachineState *sm,
                                  target_ulong addr, target_ulong size,
                                  sPAPROptionVector *ov5_updates);
+void close_htab_fd(sPAPRMachineState *spapr);
 sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn);
 void spapr_tce_table_enable(sPAPRTCETable *tcet,
                             uint32_t page_shift, uint64_t bus_offset,
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index b7c08ec2ec..5a5bea0794 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -361,6 +361,37 @@ struct ppc_radix_page_info *kvm_get_radix_page_info(void)
     return radix_page_info;
 }
 
+target_ulong kvmppc_configure_v3_mmu(PowerPCCPU *cpu,
+                                     bool radix, bool gtse,
+                                     uint64_t proc_tbl)
+{
+    CPUState *cs = CPU(cpu);
+    int ret;
+    uint64_t flags;
+    struct kvm_ppc_mmuv3_cfg cfg = {
+        .process_table = proc_tbl,
+    };
+
+    if (radix) {
+        flags |= KVM_PPC_MMUV3_RADIX;
+    }
+    if (gtse) {
+        flags |= KVM_PPC_MMUV3_GTSE;
+    }
+    cfg.flags = flags;
+    ret = kvm_vm_ioctl(cs->kvm_state, KVM_PPC_CONFIGURE_V3_MMU, &cfg);
+    switch (ret) {
+    case 0:
+        return H_SUCCESS;
+    case -EINVAL:
+        return H_PARAMETER;
+    case -ENODEV:
+        return H_NOT_AVAILABLE;
+    default:
+        return H_HARDWARE;
+    }
+}
+
 static bool kvm_valid_page_size(uint32_t flags, long rampgsize, uint32_t shift)
 {
     if (!(flags & KVM_PPC_PAGE_SIZES_REAL)) {
diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h
index 64189a48fa..4b2fd9a609 100644
--- a/target/ppc/kvm_ppc.h
+++ b/target/ppc/kvm_ppc.h
@@ -33,6 +33,9 @@ int kvmppc_clear_tsr_bits(PowerPCCPU *cpu, uint32_t tsr_bits);
 int kvmppc_or_tsr_bits(PowerPCCPU *cpu, uint32_t tsr_bits);
 int kvmppc_set_tcr(PowerPCCPU *cpu);
 int kvmppc_booke_watchdog_enable(PowerPCCPU *cpu);
+target_ulong kvmppc_configure_v3_mmu(PowerPCCPU *cpu,
+                                     bool radix, bool gtse,
+                                     uint64_t proc_tbl);
 #ifndef CONFIG_USER_ONLY
 off_t kvmppc_alloc_rma(void **rma);
 bool kvmppc_spapr_use_multitce(void);
@@ -159,6 +162,13 @@ static inline int kvmppc_booke_watchdog_enable(PowerPCCPU 
*cpu)
     return -1;
 }
 
+static inline target_ulong kvmppc_configure_v3_mmu(PowerPCCPU *cpu,
+                                     bool radix, bool gtse,
+                                     uint64_t proc_tbl)
+{
+    return 0;
+}
+
 #ifndef CONFIG_USER_ONLY
 static inline off_t kvmppc_alloc_rma(void **rma)
 {
-- 
2.11.0