Merge tag 'dump-pull-request' of https://gitlab.com/marcandre.lureau/qemu into staging

dump queue

Hi

The "dump" queue, with:
- [PATCH v3/v4 0/9] dump: Cleanup and consolidation
- [PATCH v4 0/4] dump: add 32-bit guest Windows support

# -----BEGIN PGP SIGNATURE-----
#
# iQJQBAABCAA6FiEEh6m9kz+HxgbSdvYt2ujhCXWWnOUFAmNY9gMcHG1hcmNhbmRy
# ZS5sdXJlYXVAcmVkaGF0LmNvbQAKCRDa6OEJdZac5ZUtD/kByfamsq/8hnS6N/ok
# xs9kXO+HZA1A1Kng19RjYWbTka1LpEAf6y6tPtV27l5rWJZxCgqFp3Q2VKQyzAxl
# Bcf4gvEhUDJI87jHrZ8WBJ0JvPL8pKNjPn4JUPOQO+6kX8A/3XTwAyvH/T3uxlTo
# I+4HLwY0EkJ6NU6Cokud5Uo36Zj7JghKrBxTDrd3NC0qSy8xOoIsB5Pbp2PVKuX2
# F5Zfll3F+NUDsj9zmMR6agP4PBUJUB680TtvMpMZXb2BXumKDLngthCLRtGrgsDh
# ChjYr6xkRS9qlXn0PWIYsUyDucDuRFfqTz/Pa9OcGhQuQfIfQiGOM2IFQUE3UcuN
# OphJEFi44za3E7xEZziAGIFmro+k8zX2fjgN3+mApxpBjUAF/uzoW1VzIIdx65Gh
# H/IguECFu7AwMxPucRUI7PkwexgIcqpufeTRqep2nCFsAwS6bS+obzrAzIMd9kj1
# ApLhj36lkub0Tn77B8bkf1TYJnpBcYbGZpmPCILtOxpBZGlXm++KD1DKAYt6rbnR
# 8rQugZNRzEB92aSRTkLJ6QKsqudnbR9ssGbOdEJP+v1fgVtFzYbgygx5QMezGkRw
# vRLWrNbDLog+uYpI2Kb30ItU7+bsDrads9n/gqiGvTP887T3alCtRdIq+Fb28oor
# tSBhBMqMOtccMy3k+EoXBXX5gw==
# =BUEY
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 26 Oct 2022 04:55:31 EDT
# gpg:                using RSA key 87A9BD933F87C606D276F62DDAE8E10975969CE5
# gpg:                issuer "marcandre.lureau@redhat.com"
# gpg: Good signature from "Marc-André Lureau <marcandre.lureau@redhat.com>" [full]
# gpg:                 aka "Marc-André Lureau <marcandre.lureau@gmail.com>" [full]
# Primary key fingerprint: 87A9 BD93 3F87 C606 D276  F62D DAE8 E109 7596 9CE5

* tag 'dump-pull-request' of https://gitlab.com/marcandre.lureau/qemu:
  dump/win_dump: limit number of processed PRCBs
  s390x: pv: Add dump support
  s390x: Add KVM PV dump interface
  include/elf.h: add s390x note types
  s390x: Introduce PV query interface
  s390x: Add protected dump cap
  dump: Add architecture section and section string table support
  dump: Reintroduce memory_offset and section_offset
  dump: Reorder struct DumpState
  dump: Write ELF section headers right after ELF header
  dump: Use a buffer for ELF section data and headers

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

5 files changed, 257 insertions, 27 deletions

diff --git a/target/s390x/arch_dump.c b/target/s390x/arch_dump.c
index f60a14920d..a2329141e8 100644
--- a/target/s390x/arch_dump.c
+++ b/target/s390x/arch_dump.c
@@ -12,11 +12,13 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/units.h"
 #include "cpu.h"
 #include "s390x-internal.h"
 #include "elf.h"
 #include "sysemu/dump.h"
-
+#include "hw/s390x/pv.h"
+#include "kvm/kvm_s390x.h"
 
 struct S390xUserRegsStruct {
     uint64_t psw[2];
@@ -76,9 +78,16 @@ typedef struct noteStruct {
         uint64_t todcmp;
         uint32_t todpreg;
         uint64_t ctrs[16];
+        uint8_t dynamic[1];  /*
+                              * Would be a flexible array member, if
+                              * that was legal inside a union. Real
+                              * size comes from PV info interface.
+                              */
     } contents;
 } QEMU_PACKED Note;
 
+static bool pv_dump_initialized;
+
 static void s390x_write_elf64_prstatus(Note *note, S390CPU *cpu, int id)
 {
     int i;
@@ -177,28 +186,39 @@ static void s390x_write_elf64_prefix(Note *note, S390CPU *cpu, int id)
     note->contents.prefix = cpu_to_be32((uint32_t)(cpu->env.psa));
 }
 
+static void s390x_write_elf64_pv(Note *note, S390CPU *cpu, int id)
+{
+    note->hdr.n_type = cpu_to_be32(NT_S390_PV_CPU_DATA);
+    if (!pv_dump_initialized) {
+        return;
+    }
+    kvm_s390_dump_cpu(cpu, &note->contents.dynamic);
+}
 
 typedef struct NoteFuncDescStruct {
     int contents_size;
+    uint64_t (*note_size_func)(void); /* NULL for non-dynamic sized contents */
     void (*note_contents_func)(Note *note, S390CPU *cpu, int id);
+    bool pvonly;
 } NoteFuncDesc;
 
 static const NoteFuncDesc note_core[] = {
-    {sizeof_field(Note, contents.prstatus), s390x_write_elf64_prstatus},
-    {sizeof_field(Note, contents.fpregset), s390x_write_elf64_fpregset},
-    { 0, NULL}
+    {sizeof_field(Note, contents.prstatus), NULL, s390x_write_elf64_prstatus, false},
+    {sizeof_field(Note, contents.fpregset), NULL, s390x_write_elf64_fpregset, false},
+    { 0, NULL, NULL, false}
 };
 
 static const NoteFuncDesc note_linux[] = {
-    {sizeof_field(Note, contents.prefix),   s390x_write_elf64_prefix},
-    {sizeof_field(Note, contents.ctrs),     s390x_write_elf64_ctrs},
-    {sizeof_field(Note, contents.timer),    s390x_write_elf64_timer},
-    {sizeof_field(Note, contents.todcmp),   s390x_write_elf64_todcmp},
-    {sizeof_field(Note, contents.todpreg),  s390x_write_elf64_todpreg},
-    {sizeof_field(Note, contents.vregslo),  s390x_write_elf64_vregslo},
-    {sizeof_field(Note, contents.vregshi),  s390x_write_elf64_vregshi},
-    {sizeof_field(Note, contents.gscb),     s390x_write_elf64_gscb},
-    { 0, NULL}
+    {sizeof_field(Note, contents.prefix),   NULL, s390x_write_elf64_prefix,  false},
+    {sizeof_field(Note, contents.ctrs),     NULL, s390x_write_elf64_ctrs,    false},
+    {sizeof_field(Note, contents.timer),    NULL, s390x_write_elf64_timer,   false},
+    {sizeof_field(Note, contents.todcmp),   NULL, s390x_write_elf64_todcmp,  false},
+    {sizeof_field(Note, contents.todpreg),  NULL, s390x_write_elf64_todpreg, false},
+    {sizeof_field(Note, contents.vregslo),  NULL, s390x_write_elf64_vregslo, false},
+    {sizeof_field(Note, contents.vregshi),  NULL, s390x_write_elf64_vregshi, false},
+    {sizeof_field(Note, contents.gscb),     NULL, s390x_write_elf64_gscb,    false},
+    {0, kvm_s390_pv_dmp_get_size_cpu,       s390x_write_elf64_pv, true},
+    { 0, NULL, NULL, false}
 };
 
 static int s390x_write_elf64_notes(const char *note_name,
@@ -207,22 +227,41 @@ static int s390x_write_elf64_notes(const char *note_name,
                                        DumpState *s,
                                        const NoteFuncDesc *funcs)
 {
-    Note note;
+    Note note, *notep;
     const NoteFuncDesc *nf;
-    int note_size;
+    int note_size, content_size;
     int ret = -1;
 
     assert(strlen(note_name) < sizeof(note.name));
 
     for (nf = funcs; nf->note_contents_func; nf++) {
-        memset(&note, 0, sizeof(note));
-        note.hdr.n_namesz = cpu_to_be32(strlen(note_name) + 1);
-        note.hdr.n_descsz = cpu_to_be32(nf->contents_size);
-        g_strlcpy(note.name, note_name, sizeof(note.name));
-        (*nf->note_contents_func)(&note, cpu, id);
+        notep = &note;
+        if (nf->pvonly && !s390_is_pv()) {
+            continue;
+        }
+
+        content_size = nf->note_size_func ? nf->note_size_func() : nf->contents_size;
+        note_size = sizeof(note) - sizeof(notep->contents) + content_size;
+
+        /* Notes with dynamic sizes need to allocate a note */
+        if (nf->note_size_func) {
+            notep = g_malloc(note_size);
+        }
+
+        memset(notep, 0, sizeof(note));
 
-        note_size = sizeof(note) - sizeof(note.contents) + nf->contents_size;
-        ret = f(&note, note_size, s);
+        /* Setup note header data */
+        notep->hdr.n_descsz = cpu_to_be32(content_size);
+        notep->hdr.n_namesz = cpu_to_be32(strlen(note_name) + 1);
+        g_strlcpy(notep->name, note_name, sizeof(notep->name));
+
+        /* Get contents and write them out */
+        (*nf->note_contents_func)(notep, cpu, id);
+        ret = f(notep, note_size, s);
+
+        if (nf->note_size_func) {
+            g_free(notep);
+        }
 
         if (ret < 0) {
             return -1;
@@ -247,13 +286,179 @@ int s390_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs,
     return s390x_write_elf64_notes("LINUX", f, cpu, cpuid, s, note_linux);
 }
 
+/* PV dump section size functions */
+static uint64_t get_mem_state_size_from_len(uint64_t len)
+{
+    return (len / (MiB)) * kvm_s390_pv_dmp_get_size_mem_state();
+}
+
+static uint64_t get_size_mem_state(DumpState *s)
+{
+    return get_mem_state_size_from_len(s->total_size);
+}
+
+static uint64_t get_size_completion_data(DumpState *s)
+{
+    return kvm_s390_pv_dmp_get_size_completion_data();
+}
+
+/* PV dump section data functions*/
+static int get_data_completion(DumpState *s, uint8_t *buff)
+{
+    int rc;
+
+    if (!pv_dump_initialized) {
+        return 0;
+    }
+    rc = kvm_s390_dump_completion_data(buff);
+    if (!rc) {
+            pv_dump_initialized = false;
+    }
+    return rc;
+}
+
+static int get_mem_state(DumpState *s, uint8_t *buff)
+{
+    int64_t memblock_size, memblock_start;
+    GuestPhysBlock *block;
+    uint64_t off;
+    int rc;
+
+    QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+        memblock_start = dump_filtered_memblock_start(block, s->filter_area_begin,
+                                                      s->filter_area_length);
+        if (memblock_start == -1) {
+            continue;
+        }
+
+        memblock_size = dump_filtered_memblock_size(block, s->filter_area_begin,
+                                                    s->filter_area_length);
+
+        off = get_mem_state_size_from_len(block->target_start);
+
+        rc = kvm_s390_dump_mem_state(block->target_start,
+                                     get_mem_state_size_from_len(memblock_size),
+                                     buff + off);
+        if (rc) {
+            return rc;
+        }
+    }
+
+    return 0;
+}
+
+static struct sections {
+    uint64_t (*sections_size_func)(DumpState *s);
+    int (*sections_contents_func)(DumpState *s, uint8_t *buff);
+    char sctn_str[12];
+} sections[] = {
+    { get_size_mem_state, get_mem_state, "pv_mem_meta"},
+    { get_size_completion_data, get_data_completion, "pv_compl"},
+    {NULL , NULL, ""}
+};
+
+static uint64_t arch_sections_write_hdr(DumpState *s, uint8_t *buff)
+{
+    Elf64_Shdr *shdr = (void *)buff;
+    struct sections *sctn = sections;
+    uint64_t off = s->section_offset;
+
+    if (!pv_dump_initialized) {
+        return 0;
+    }
+
+    for (; sctn->sections_size_func; off += shdr->sh_size, sctn++, shdr++) {
+        memset(shdr, 0, sizeof(*shdr));
+        shdr->sh_type = SHT_PROGBITS;
+        shdr->sh_offset = off;
+        shdr->sh_size = sctn->sections_size_func(s);
+        shdr->sh_name = s->string_table_buf->len;
+        g_array_append_vals(s->string_table_buf, sctn->sctn_str, sizeof(sctn->sctn_str));
+    }
+
+    return (uintptr_t)shdr - (uintptr_t)buff;
+}
+
+
+/* Add arch specific number of sections and their respective sizes */
+static void arch_sections_add(DumpState *s)
+{
+    struct sections *sctn = sections;
+
+    /*
+     * We only do a PV dump if we are running a PV guest, KVM supports
+     * the dump API and we got valid dump length information.
+     */
+    if (!s390_is_pv() || !kvm_s390_get_protected_dump() ||
+        !kvm_s390_pv_info_basic_valid()) {
+        return;
+    }
+
+    /*
+     * Start the UV dump process by doing the initialize dump call via
+     * KVM as the proxy.
+     */
+    if (!kvm_s390_dump_init()) {
+        pv_dump_initialized = true;
+    } else {
+        /*
+         * Dump init failed, maybe the guest owner disabled dumping.
+         * We'll continue the non-PV dump process since this is no
+         * reason to crash qemu.
+         */
+        return;
+    }
+
+    for (; sctn->sections_size_func; sctn++) {
+        s->shdr_num += 1;
+        s->elf_section_data_size += sctn->sections_size_func(s);
+    }
+}
+
+/*
+ * After the PV dump has been initialized, the CPU data has been
+ * fetched and memory has been dumped, we need to grab the tweak data
+ * and the completion data.
+ */
+static int arch_sections_write(DumpState *s, uint8_t *buff)
+{
+    struct sections *sctn = sections;
+    int rc;
+
+    if (!pv_dump_initialized) {
+        return -EINVAL;
+    }
+
+    for (; sctn->sections_size_func; sctn++) {
+        rc = sctn->sections_contents_func(s, buff);
+        buff += sctn->sections_size_func(s);
+        if (rc) {
+            return rc;
+        }
+    }
+    return 0;
+}
+
 int cpu_get_dump_info(ArchDumpInfo *info,
                       const struct GuestPhysBlockList *guest_phys_blocks)
 {
     info->d_machine = EM_S390;
     info->d_endian = ELFDATA2MSB;
     info->d_class = ELFCLASS64;
-
+    /*
+     * This is evaluated for each dump so we can freely switch
+     * between PV and non-PV.
+     */
+    if (s390_is_pv() && kvm_s390_get_protected_dump() &&
+        kvm_s390_pv_info_basic_valid()) {
+        info->arch_sections_add_fn = *arch_sections_add;
+        info->arch_sections_write_hdr_fn = *arch_sections_write_hdr;
+        info->arch_sections_write_fn = *arch_sections_write;
+    } else {
+        info->arch_sections_add_fn = NULL;
+        info->arch_sections_write_hdr_fn = NULL;
+        info->arch_sections_write_fn = NULL;
+    }
     return 0;
 }
 
@@ -261,7 +466,7 @@ ssize_t cpu_get_note_size(int class, int machine, int nr_cpus)
 {
     int name_size = 8; /* "LINUX" or "CORE" + pad */
     size_t elf_note_size = 0;
-    int note_head_size;
+    int note_head_size, content_size;
     const NoteFuncDesc *nf;
 
     assert(class == ELFCLASS64);
@@ -270,12 +475,15 @@ ssize_t cpu_get_note_size(int class, int machine, int nr_cpus)
     note_head_size = sizeof(Elf64_Nhdr);
 
     for (nf = note_core; nf->note_contents_func; nf++) {
-        elf_note_size = elf_note_size + note_head_size + name_size +
-                        nf->contents_size;
+        elf_note_size = elf_note_size + note_head_size + name_size + nf->contents_size;
     }
     for (nf = note_linux; nf->note_contents_func; nf++) {
+        if (nf->pvonly && !s390_is_pv()) {
+            continue;
+        }
+        content_size = nf->contents_size ? nf->contents_size : nf->note_size_func();
         elf_note_size = elf_note_size + note_head_size + name_size +
-                        nf->contents_size;
+                        content_size;
     }
 
     return (elf_note_size) * nr_cpus;
diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c
index da8c47f57b..3ac7ec9acf 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -158,6 +158,7 @@ static int cap_hpage_1m;
 static int cap_vcpu_resets;
 static int cap_protected;
 static int cap_zpci_op;
+static int cap_protected_dump;
 
 static bool mem_op_storage_key_support;
 
@@ -364,6 +365,7 @@ 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);
     cap_zpci_op = kvm_check_extension(s, KVM_CAP_S390_ZPCI_OP);
+    cap_protected_dump = kvm_check_extension(s, KVM_CAP_S390_PROTECTED_DUMP);
 
     kvm_vm_enable_cap(s, KVM_CAP_S390_USER_SIGP, 0);
     kvm_vm_enable_cap(s, KVM_CAP_S390_VECTOR_REGISTERS, 0);
@@ -2045,6 +2047,11 @@ int kvm_s390_assign_subch_ioeventfd(EventNotifier *notifier, uint32_t sch,
     return kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
 }
 
+int kvm_s390_get_protected_dump(void)
+{
+    return cap_protected_dump;
+}
+
 int kvm_s390_get_ri(void)
 {
     return cap_ri;
diff --git a/target/s390x/kvm/kvm_s390x.h b/target/s390x/kvm/kvm_s390x.h
index aaae8570de..f9785564d0 100644
--- a/target/s390x/kvm/kvm_s390x.h
+++ b/target/s390x/kvm/kvm_s390x.h
@@ -26,6 +26,7 @@ int kvm_s390_set_cpu_state(S390CPU *cpu, uint8_t cpu_state);
 void kvm_s390_vcpu_interrupt_pre_save(S390CPU *cpu);
 int kvm_s390_vcpu_interrupt_post_load(S390CPU *cpu);
 int kvm_s390_get_hpage_1m(void);
+int kvm_s390_get_protected_dump(void);
 int kvm_s390_get_ri(void);
 int kvm_s390_get_zpci_op(void);
 int kvm_s390_get_clock(uint8_t *tod_high, uint64_t *tod_clock);
diff --git a/target/s390x/kvm/meson.build b/target/s390x/kvm/meson.build
index d1356356b1..aef52b6686 100644
--- a/target/s390x/kvm/meson.build
+++ b/target/s390x/kvm/meson.build
@@ -1,6 +1,8 @@
 
 s390x_ss.add(when: 'CONFIG_KVM', if_true: files(
   'kvm.c'
+), if_false: files(
+  'stubs.c'
 ))
 
 # Newer kernels on s390 check for an S390_PGSTE program header and
diff --git a/target/s390x/kvm/stubs.c b/target/s390x/kvm/stubs.c
new file mode 100644
index 0000000000..5fd63b9a7e
--- /dev/null
+++ b/target/s390x/kvm/stubs.c
@@ -0,0 +1,12 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+
+#include "kvm_s390x.h"
+
+int kvm_s390_get_protected_dump(void)
+{
+    return false;
+}