Merge remote-tracking branch 'remotes/cohuck-gitlab/tags/s390x-20210316' into staging

s390x updates:
- get rid of legacy_s390_alloc() and phys_mem_set_alloc()
- tcg: implement the MVPG condition-code-option bit
- fix g_autofree variable handing in the pci vfio code
- use official z15 names in the cpu model definitions

# gpg: Signature made Tue 16 Mar 2021 10:04:21 GMT
# gpg:                using RSA key C3D0D66DC3624FF6A8C018CEDECF6B93C6F02FAF
# gpg:                issuer "cohuck@redhat.com"
# gpg: Good signature from "Cornelia Huck <conny@cornelia-huck.de>" [unknown]
# gpg:                 aka "Cornelia Huck <huckc@linux.vnet.ibm.com>" [full]
# gpg:                 aka "Cornelia Huck <cornelia.huck@de.ibm.com>" [full]
# gpg:                 aka "Cornelia Huck <cohuck@kernel.org>" [unknown]
# gpg:                 aka "Cornelia Huck <cohuck@redhat.com>" [unknown]
# Primary key fingerprint: C3D0 D66D C362 4FF6 A8C0  18CE DECF 6B93 C6F0 2FAF

* remotes/cohuck-gitlab/tags/s390x-20210316:
  s390x/pci: Add missing initialization for g_autofree variables
  target/s390x: Store r1/r2 for page-translation exceptions during MVPG
  target/s390x: Implement the MVPG condition-code-option bit
  s390x/cpu_model: use official name for 8562
  exec: Get rid of phys_mem_set_alloc()
  s390x/kvm: Get rid of legacy_s390_alloc()

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

11 files changed, 159 insertions, 116 deletions

diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c
index ead4f22..2a153fa 100644
--- a/hw/s390x/s390-pci-vfio.c
+++ b/hw/s390x/s390-pci-vfio.c
@@ -29,14 +29,11 @@
  */
 bool s390_pci_update_dma_avail(int fd, unsigned int *avail)
 {
-    g_autofree struct vfio_iommu_type1_info *info;
-    uint32_t argsz;
+    uint32_t argsz = sizeof(struct vfio_iommu_type1_info);
+    g_autofree struct vfio_iommu_type1_info *info = g_malloc0(argsz);
 
     assert(avail);
 
-    argsz = sizeof(struct vfio_iommu_type1_info);
-    info = g_malloc0(argsz);
-
     /*
      * If the specified argsz is not large enough to contain all capabilities
      * it will be updated upon return from the ioctl.  Retry until we have
@@ -230,7 +227,7 @@ static void s390_pci_read_pfip(S390PCIBusDevice *pbdev,
  */
 void s390_pci_get_clp_info(S390PCIBusDevice *pbdev)
 {
-    g_autofree struct vfio_device_info *info;
+    g_autofree struct vfio_device_info *info = NULL;
     VFIOPCIDevice *vfio_pci;
     uint32_t argsz;
     int fd;
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index 687c598..a1ab1ee 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -249,10 +249,6 @@ int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap);
 int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr);
 int kvm_on_sigbus(int code, void *addr);
 
-/* interface with exec.c */
-
-void phys_mem_set_alloc(void *(*alloc)(size_t, uint64_t *align, bool shared));
-
 /* internal API */
 
 int kvm_ioctl(KVMState *s, int type, ...);
diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index 7e8b0fa..9e5ef48 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -1144,19 +1144,6 @@ static int subpage_register(subpage_t *mmio, uint32_t start, uint32_t end,
                             uint16_t section);
 static subpage_t *subpage_init(FlatView *fv, hwaddr base);
 
-static void *(*phys_mem_alloc)(size_t size, uint64_t *align, bool shared) =
-                               qemu_anon_ram_alloc;
-
-/*
- * Set a custom physical guest memory alloator.
- * Accelerators with unusual needs may need this.  Hopefully, we can
- * get rid of it eventually.
- */
-void phys_mem_set_alloc(void *(*alloc)(size_t, uint64_t *align, bool shared))
-{
-    phys_mem_alloc = alloc;
-}
-
 static uint16_t phys_section_add(PhysPageMap *map,
                                  MemoryRegionSection *section)
 {
@@ -1962,8 +1949,9 @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared)
                 return;
             }
         } else {
-            new_block->host = phys_mem_alloc(new_block->max_length,
-                                             &new_block->mr->align, shared);
+            new_block->host = qemu_anon_ram_alloc(new_block->max_length,
+                                                  &new_block->mr->align,
+                                                  shared);
             if (!new_block->host) {
                 error_setg_errno(errp, errno,
                                  "cannot set up guest memory '%s'",
@@ -2047,17 +2035,6 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
         return NULL;
     }
 
-    if (phys_mem_alloc != qemu_anon_ram_alloc) {
-        /*
-         * file_ram_alloc() needs to allocate just like
-         * phys_mem_alloc, but we haven't bothered to provide
-         * a hook there.
-         */
-        error_setg(errp,
-                   "-mem-path not supported with this accelerator");
-        return NULL;
-    }
-
     size = HOST_PAGE_ALIGN(size);
     file_size = get_file_size(fd);
     if (file_size > 0 && file_size < size) {
@@ -2247,13 +2224,6 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
                     area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
                                 flags, block->fd, offset);
                 } else {
-                    /*
-                     * Remap needs to match alloc.  Accelerators that
-                     * set phys_mem_alloc never remap.  If they did,
-                     * we'd need a remap hook here.
-                     */
-                    assert(phys_mem_alloc == qemu_anon_ram_alloc);
-
                     flags |= MAP_PRIVATE | MAP_ANONYMOUS;
                     area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
                                 flags, -1, 0);
diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h
index 60d434d..468b443 100644
--- a/target/s390x/cpu.h
+++ b/target/s390x/cpu.h
@@ -114,6 +114,11 @@ struct CPUS390XState {
 
     uint64_t diag318_info;
 
+#if !defined(CONFIG_USER_ONLY)
+    uint64_t tlb_fill_tec;   /* translation exception code during tlb_fill */
+    int tlb_fill_exc;        /* exception number seen during tlb_fill */
+#endif
+
     /* Fields up to this point are cleared by a CPU reset */
     struct {} end_reset_fields;
 
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index dd474c5..050dcf2 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -86,8 +86,8 @@ static S390CPUDef s390_cpu_defs[] = {
     CPUDEF_INIT(0x3906, 14, 1, 47, 0x08000000U, "z14", "IBM z14 GA1"),
     CPUDEF_INIT(0x3906, 14, 2, 47, 0x08000000U, "z14.2", "IBM z14 GA2"),
     CPUDEF_INIT(0x3907, 14, 1, 47, 0x08000000U, "z14ZR1", "IBM z14 Model ZR1 GA1"),
-    CPUDEF_INIT(0x8561, 15, 1, 47, 0x08000000U, "gen15a", "IBM z15 GA1"),
-    CPUDEF_INIT(0x8562, 15, 1, 47, 0x08000000U, "gen15b", "IBM 8562 GA1"),
+    CPUDEF_INIT(0x8561, 15, 1, 47, 0x08000000U, "gen15a", "IBM z15 T01 GA1"),
+    CPUDEF_INIT(0x8562, 15, 1, 47, 0x08000000U, "gen15b", "IBM z15 T02 GA1"),
 };
 
 #define QEMU_MAX_CPU_TYPE 0x2964
diff --git a/target/s390x/excp_helper.c b/target/s390x/excp_helper.c
index ce16af3..c48cd6b 100644
--- a/target/s390x/excp_helper.c
+++ b/target/s390x/excp_helper.c
@@ -164,6 +164,9 @@ bool s390_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
         tec = 0; /* unused */
     }
 
+    env->tlb_fill_exc = excp;
+    env->tlb_fill_tec = tec;
+
     if (!excp) {
         qemu_log_mask(CPU_LOG_MMU,
                       "%s: set tlb %" PRIx64 " -> %" PRIx64 " (%x)\n",
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 55bd155..d4e4f33 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -18,7 +18,7 @@ DEF_HELPER_3(srstu, void, env, i32, i32)
 DEF_HELPER_4(clst, i64, env, i64, i64, i64)
 DEF_HELPER_FLAGS_4(mvn, TCG_CALL_NO_WG, void, env, i32, i64, i64)
 DEF_HELPER_FLAGS_4(mvo, TCG_CALL_NO_WG, void, env, i32, i64, i64)
-DEF_HELPER_FLAGS_4(mvpg, TCG_CALL_NO_WG, i32, env, i64, i64, i64)
+DEF_HELPER_FLAGS_4(mvpg, TCG_CALL_NO_WG, i32, env, i64, i32, i32)
 DEF_HELPER_FLAGS_4(mvz, TCG_CALL_NO_WG, void, env, i32, i64, i64)
 DEF_HELPER_3(mvst, i32, env, i32, i32)
 DEF_HELPER_4(ex, void, env, i32, i64, i64)
diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index e5b6efa..0bb1886 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -641,7 +641,7 @@
 /* MOVE NUMERICS */
     C(0xd100, MVN,     SS_a,  Z,   la1, a2, 0, 0, mvn, 0)
 /* MOVE PAGE */
-    C(0xb254, MVPG,    RRE,   Z,   r1_o, r2_o, 0, 0, mvpg, 0)
+    C(0xb254, MVPG,    RRE,   Z,   0, 0, 0, 0, mvpg, 0)
 /* MOVE STRING */
     C(0xb255, MVST,    RRE,   Z,   0, 0, 0, 0, mvst, 0)
 /* MOVE WITH OPTIONAL SPECIFICATION */
diff --git a/target/s390x/kvm.c b/target/s390x/kvm.c
index 73f816a..4fb3bbf 100644
--- a/target/s390x/kvm.c
+++ b/target/s390x/kvm.c
@@ -161,8 +161,6 @@ static int cap_protected;
 
 static int active_cmma;
 
-static void *legacy_s390_alloc(size_t size, uint64_t *align, bool shared);
-
 static int kvm_s390_query_mem_limit(uint64_t *memory_limit)
 {
     struct kvm_device_attr attr = {
@@ -349,6 +347,11 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
                      "please use kernel 3.15 or newer");
         return -1;
     }
+    if (!kvm_check_extension(s, KVM_CAP_S390_COW)) {
+        error_report("KVM is missing capability KVM_CAP_S390_COW - "
+                     "unsupported environment");
+        return -1;
+    }
 
     cap_sync_regs = kvm_check_extension(s, KVM_CAP_SYNC_REGS);
     cap_async_pf = kvm_check_extension(s, KVM_CAP_ASYNC_PF);
@@ -357,11 +360,6 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
     cap_vcpu_resets = kvm_check_extension(s, KVM_CAP_S390_VCPU_RESETS);
     cap_protected = kvm_check_extension(s, KVM_CAP_S390_PROTECTED);
 
-    if (!kvm_check_extension(s, KVM_CAP_S390_GMAP)
-        || !kvm_check_extension(s, KVM_CAP_S390_COW)) {
-        phys_mem_set_alloc(legacy_s390_alloc);
-    }
-
     kvm_vm_enable_cap(s, KVM_CAP_S390_USER_SIGP, 0);
     kvm_vm_enable_cap(s, KVM_CAP_S390_VECTOR_REGISTERS, 0);
     kvm_vm_enable_cap(s, KVM_CAP_S390_USER_STSI, 0);
@@ -889,37 +887,6 @@ int kvm_s390_mem_op_pv(S390CPU *cpu, uint64_t offset, void *hostbuf,
     return ret;
 }
 
-/*
- * Legacy layout for s390:
- * Older S390 KVM requires the topmost vma of the RAM to be
- * smaller than an system defined value, which is at least 256GB.
- * Larger systems have larger values. We put the guest between
- * the end of data segment (system break) and this value. We
- * use 32GB as a base to have enough room for the system break
- * to grow. We also have to use MAP parameters that avoid
- * read-only mapping of guest pages.
- */
-static void *legacy_s390_alloc(size_t size, uint64_t *align, bool shared)
-{
-    static void *mem;
-
-    if (mem) {
-        /* we only support one allocation, which is enough for initial ram */
-        return NULL;
-    }
-
-    mem = mmap((void *) 0x800000000ULL, size,
-               PROT_EXEC|PROT_READ|PROT_WRITE,
-               MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
-    if (mem == MAP_FAILED) {
-        mem = NULL;
-    }
-    if (mem && align) {
-        *align = QEMU_VMALLOC_ALIGN;
-    }
-    return mem;
-}
-
 static uint8_t const *sw_bp_inst;
 static uint8_t sw_bp_ilen;
 
diff --git a/target/s390x/mem_helper.c b/target/s390x/mem_helper.c
index 25cfede..12e84a4 100644
--- a/target/s390x/mem_helper.c
+++ b/target/s390x/mem_helper.c
@@ -130,28 +130,103 @@ typedef struct S390Access {
     int mmu_idx;
 } S390Access;
 
-static S390Access access_prepare(CPUS390XState *env, vaddr vaddr, int size,
-                                 MMUAccessType access_type, int mmu_idx,
-                                 uintptr_t ra)
+/*
+ * With nonfault=1, return the PGM_ exception that would have been injected
+ * into the guest; return 0 if no exception was detected.
+ *
+ * For !CONFIG_USER_ONLY, the TEC is stored stored to env->tlb_fill_tec.
+ * For CONFIG_USER_ONLY, the faulting address is stored to env->__excp_addr.
+ */
+static int s390_probe_access(CPUArchState *env, target_ulong addr, int size,
+                             MMUAccessType access_type, int mmu_idx,
+                             bool nonfault, void **phost, uintptr_t ra)
 {
-    S390Access access = {
-        .vaddr1 = vaddr,
-        .size1 = MIN(size, -(vaddr | TARGET_PAGE_MASK)),
-        .mmu_idx = mmu_idx,
-    };
+    int flags;
+
+#if defined(CONFIG_USER_ONLY)
+    flags = page_get_flags(addr);
+    if (!(flags & (access_type == MMU_DATA_LOAD ?  PAGE_READ : PAGE_WRITE))) {
+        env->__excp_addr = addr;
+        flags = (flags & PAGE_VALID) ? PGM_PROTECTION : PGM_ADDRESSING;
+        if (nonfault) {
+            return flags;
+        }
+        tcg_s390_program_interrupt(env, flags, ra);
+    }
+    *phost = g2h(env_cpu(env), addr);
+#else
+    /*
+     * For !CONFIG_USER_ONLY, we cannot rely on TLB_INVALID_MASK or haddr==NULL
+     * to detect if there was an exception during tlb_fill().
+     */
+    env->tlb_fill_exc = 0;
+    flags = probe_access_flags(env, addr, access_type, mmu_idx, nonfault, phost,
+                               ra);
+    if (env->tlb_fill_exc) {
+        return env->tlb_fill_exc;
+    }
+
+    if (unlikely(flags & TLB_WATCHPOINT)) {
+        /* S390 does not presently use transaction attributes. */
+        cpu_check_watchpoint(env_cpu(env), addr, size,
+                             MEMTXATTRS_UNSPECIFIED,
+                             (access_type == MMU_DATA_STORE
+                              ? BP_MEM_WRITE : BP_MEM_READ), ra);
+    }
+#endif
+    return 0;
+}
 
-    g_assert(size > 0 && size <= 4096);
-    access.haddr1 = probe_access(env, access.vaddr1, access.size1, access_type,
-                                 mmu_idx, ra);
+static int access_prepare_nf(S390Access *access, CPUS390XState *env,
+                             bool nonfault, vaddr vaddr1, int size,
+                             MMUAccessType access_type,
+                             int mmu_idx, uintptr_t ra)
+{
+    void *haddr1, *haddr2 = NULL;
+    int size1, size2, exc;
+    vaddr vaddr2 = 0;
 
-    if (unlikely(access.size1 != size)) {
-        /* The access crosses page boundaries. */
-        access.vaddr2 = wrap_address(env, vaddr + access.size1);
-        access.size2 = size - access.size1;
-        access.haddr2 = probe_access(env, access.vaddr2, access.size2,
-                                     access_type, mmu_idx, ra);
+    assert(size > 0 && size <= 4096);
+
+    size1 = MIN(size, -(vaddr1 | TARGET_PAGE_MASK)),
+    size2 = size - size1;
+
+    exc = s390_probe_access(env, vaddr1, size1, access_type, mmu_idx, nonfault,
+                            &haddr1, ra);
+    if (exc) {
+        return exc;
     }
-    return access;
+    if (unlikely(size2)) {
+        /* The access crosses page boundaries. */
+        vaddr2 = wrap_address(env, vaddr1 + size1);
+        exc = s390_probe_access(env, vaddr2, size2, access_type, mmu_idx,
+                                nonfault, &haddr2, ra);
+        if (exc) {
+            return exc;
+        }
+    }
+
+    *access = (S390Access) {
+        .vaddr1 = vaddr1,
+        .vaddr2 = vaddr2,
+        .haddr1 = haddr1,
+        .haddr2 = haddr2,
+        .size1 = size1,
+        .size2 = size2,
+        .mmu_idx = mmu_idx
+    };
+    return 0;
+}
+
+static S390Access access_prepare(CPUS390XState *env, vaddr vaddr, int size,
+                                 MMUAccessType access_type, int mmu_idx,
+                                 uintptr_t ra)
+{
+    S390Access ret;
+    int exc = access_prepare_nf(&ret, env, false, vaddr, size,
+                                access_type, mmu_idx, ra);
+    assert(!exc);
+    return ret;
 }
 
 /* Helper to handle memset on a single page. */
@@ -840,33 +915,58 @@ uint64_t HELPER(clst)(CPUS390XState *env, uint64_t c, uint64_t s1, uint64_t s2)
 }
 
 /* move page */
-uint32_t HELPER(mvpg)(CPUS390XState *env, uint64_t r0, uint64_t r1, uint64_t r2)
+uint32_t HELPER(mvpg)(CPUS390XState *env, uint64_t r0, uint32_t r1, uint32_t r2)
 {
+    const uint64_t src = get_address(env, r2) & TARGET_PAGE_MASK;
+    const uint64_t dst = get_address(env, r1) & TARGET_PAGE_MASK;
     const int mmu_idx = cpu_mmu_index(env, false);
     const bool f = extract64(r0, 11, 1);
     const bool s = extract64(r0, 10, 1);
+    const bool cco = extract64(r0, 8, 1);
     uintptr_t ra = GETPC();
     S390Access srca, desta;
+    int exc;
 
     if ((f && s) || extract64(r0, 12, 4)) {
         tcg_s390_program_interrupt(env, PGM_SPECIFICATION, GETPC());
     }
 
-    r1 = wrap_address(env, r1 & TARGET_PAGE_MASK);
-    r2 = wrap_address(env, r2 & TARGET_PAGE_MASK);
-
     /*
-     * TODO:
-     * - Access key handling
-     * - CC-option with surpression of page-translation exceptions
-     * - Store r1/r2 register identifiers at real location 162
+     * We always manually handle exceptions such that we can properly store
+     * r1/r2 to the lowcore on page-translation exceptions.
+     *
+     * TODO: Access key handling
      */
-    srca = access_prepare(env, r2, TARGET_PAGE_SIZE, MMU_DATA_LOAD, mmu_idx,
-                          ra);
-    desta = access_prepare(env, r1, TARGET_PAGE_SIZE, MMU_DATA_STORE, mmu_idx,
-                           ra);
+    exc = access_prepare_nf(&srca, env, true, src, TARGET_PAGE_SIZE,
+                            MMU_DATA_LOAD, mmu_idx, ra);
+    if (exc) {
+        if (cco) {
+            return 2;
+        }
+        goto inject_exc;
+    }
+    exc = access_prepare_nf(&desta, env, true, dst, TARGET_PAGE_SIZE,
+                            MMU_DATA_STORE, mmu_idx, ra);
+    if (exc) {
+        if (cco && exc != PGM_PROTECTION) {
+            return 1;
+        }
+        goto inject_exc;
+    }
     access_memmove(env, &desta, &srca, ra);
     return 0; /* data moved */
+inject_exc:
+#if !defined(CONFIG_USER_ONLY)
+    if (exc != PGM_ADDRESSING) {
+        stq_phys(env_cpu(env)->as, env->psa + offsetof(LowCore, trans_exc_code),
+                 env->tlb_fill_tec);
+    }
+    if (exc == PGM_PAGE_TRANS) {
+        stb_phys(env_cpu(env)->as, env->psa + offsetof(LowCore, op_access_id),
+                 r1 << 4 | r2);
+    }
+#endif
+    tcg_s390_program_interrupt(env, exc, ra);
 }
 
 /* string copy */
diff --git a/target/s390x/translate.c b/target/s390x/translate.c
index 61dd034..4f953dd 100644
--- a/target/s390x/translate.c
+++ b/target/s390x/translate.c
@@ -3513,7 +3513,12 @@ static DisasJumpType op_mvo(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_mvpg(DisasContext *s, DisasOps *o)
 {
-    gen_helper_mvpg(cc_op, cpu_env, regs[0], o->in1, o->in2);
+    TCGv_i32 t1 = tcg_const_i32(get_field(s, r1));
+    TCGv_i32 t2 = tcg_const_i32(get_field(s, r2));
+
+    gen_helper_mvpg(cc_op, cpu_env, regs[0], t1, t2);
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
     set_cc_static(s);
     return DISAS_NEXT;
 }