Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

virtio,pc: features, cleanups, fixes

Part of ACPI ERST support
fixes, cleanups

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Sun 06 Feb 2022 09:36:24 GMT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream: (24 commits)
  util/oslib-posix: Fix missing unlock in the error path of os_mem_prealloc()
  ACPI ERST: step 6 of bios-tables-test.c
  ACPI ERST: bios-tables-test testcase
  ACPI ERST: qtest for ERST
  ACPI ERST: create ACPI ERST table for pc/x86 machines
  ACPI ERST: build the ACPI ERST table
  ACPI ERST: support for ACPI ERST feature
  ACPI ERST: header file for ERST
  ACPI ERST: PCI device_id for ERST
  ACPI ERST: bios-tables-test.c steps 1 and 2
  libvhost-user: Map shared RAM with MAP_NORESERVE to support virtio-mem with hugetlb
  libvhost-user: handle removal of identical regions
  libvhost-user: prevent over-running max RAM slots
  libvhost-user: fix VHOST_USER_REM_MEM_REG not closing the fd
  libvhost-user: Simplify VHOST_USER_REM_MEM_REG
  libvhost-user: Add vu_add_mem_reg input validation
  libvhost-user: Add vu_rem_mem_reg input validation
  tests: acpi: test short OEM_ID/OEM_TABLE_ID values in test_oem_fields()
  tests: acpi: update expected blobs
  acpi: fix OEM ID/OEM Table ID padding
  ...

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

configure

@@ -2768,7 +2768,7 @@ cat > $TMPC << EOF
 #include <cpuid.h>
 int main(void) {
     unsigned a, b, c, d;
-    int max = __get_cpuid_max(0, 0);
+    unsigned max = __get_cpuid_max(0, 0);
 
     if (max >= 1) {
         __cpuid(1, a, b, c, d);

hw/acpi/Kconfig

@@ -10,6 +10,7 @@ config ACPI_X86
     select ACPI_HMAT
     select ACPI_PIIX4
     select ACPI_PCIHP
+    select ACPI_ERST
 
 config ACPI_X86_ICH
     bool
@@ -60,3 +61,8 @@ config ACPI_HW_REDUCED
     select ACPI
     select ACPI_MEMORY_HOTPLUG
     select ACPI_NVDIMM
+
+config ACPI_ERST
+    bool
+    default y
+    depends on ACPI && PCI

hw/acpi/aml-build.c

@@ -1724,9 +1724,9 @@ void acpi_table_begin(AcpiTable *desc, GArray *array)
     build_append_int_noprefix(array, 0, 4); /* Length */
     build_append_int_noprefix(array, desc->rev, 1); /* Revision */
     build_append_int_noprefix(array, 0, 1); /* Checksum */
-    build_append_padded_str(array, desc->oem_id, 6, ' '); /* OEMID */
+    build_append_padded_str(array, desc->oem_id, 6, '\0'); /* OEMID */
     /* OEM Table ID */
-    build_append_padded_str(array, desc->oem_table_id, 8, ' ');
+    build_append_padded_str(array, desc->oem_table_id, 8, '\0');
     build_append_int_noprefix(array, 1, 4); /* OEM Revision */
     g_array_append_vals(array, ACPI_BUILD_APPNAME8, 4); /* Creator ID */
     build_append_int_noprefix(array, 1, 4); /* Creator Revision */

hw/acpi/meson.build

@@ -22,6 +22,7 @@ acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_true: files('pcihp.c'))
 acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_false: files('acpi-pci-hotplug-stub.c'))
 acpi_ss.add(when: 'CONFIG_ACPI_VIOT', if_true: files('viot.c'))
 acpi_ss.add(when: 'CONFIG_ACPI_X86_ICH', if_true: files('ich9.c', 'tco.c'))
+acpi_ss.add(when: 'CONFIG_ACPI_ERST', if_true: files('erst.c'))
 acpi_ss.add(when: 'CONFIG_IPMI', if_true: files('ipmi.c'), if_false: files('ipmi-stub.c'))
 acpi_ss.add(when: 'CONFIG_PC', if_false: files('acpi-x86-stub.c'))
 acpi_ss.add(when: 'CONFIG_TPM', if_true: files('tpm.c'))

hw/acpi/trace-events

@@ -55,3 +55,18 @@ piix4_gpe_writeb(uint64_t addr, unsigned width, uint64_t val) "addr: 0x%" PRIx64
 # tco.c
 tco_timer_reload(int ticks, int msec) "ticks=%d (%d ms)"
 tco_timer_expired(int timeouts_no, bool strap, bool no_reboot) "timeouts_no=%d no_reboot=%d/%d"
+
+# erst.c
+acpi_erst_reg_write(uint64_t addr, uint64_t val, unsigned size) "addr: 0x%04" PRIx64 " <== 0x%016" PRIx64 " (size: %u)"
+acpi_erst_reg_read(uint64_t addr, uint64_t val, unsigned size) " addr: 0x%04" PRIx64 " ==> 0x%016" PRIx64 " (size: %u)"
+acpi_erst_mem_write(uint64_t addr, uint64_t val, unsigned size) "addr: 0x%06" PRIx64 " <== 0x%016" PRIx64 " (size: %u)"
+acpi_erst_mem_read(uint64_t addr, uint64_t val, unsigned size) " addr: 0x%06" PRIx64 " ==> 0x%016" PRIx64 " (size: %u)"
+acpi_erst_pci_bar_0(uint64_t addr) "BAR0: 0x%016" PRIx64
+acpi_erst_pci_bar_1(uint64_t addr) "BAR1: 0x%016" PRIx64
+acpi_erst_realizefn_in(void)
+acpi_erst_realizefn_out(unsigned size) "total nvram size %u bytes"
+acpi_erst_reset_in(unsigned record_count) "record_count %u"
+acpi_erst_reset_out(unsigned record_count) "record_count %u"
+acpi_erst_post_load(void *header, unsigned slot_size) "header: 0x%p slot_size %u"
+acpi_erst_class_init_in(void)
+acpi_erst_class_init_out(void)

hw/i386/acpi-build.c

@@ -43,6 +43,7 @@
 #include "sysemu/tpm.h"
 #include "hw/acpi/tpm.h"
 #include "hw/acpi/vmgenid.h"
+#include "hw/acpi/erst.h"
 #include "sysemu/tpm_backend.h"
 #include "hw/rtc/mc146818rtc_regs.h"
 #include "migration/vmstate.h"
@@ -74,6 +75,8 @@
 #include "hw/acpi/hmat.h"
 #include "hw/acpi/viot.h"
 
+#include CONFIG_DEVICES
+
 /* These are used to size the ACPI tables for -M pc-i440fx-1.7 and
  * -M pc-i440fx-2.0.  Even if the actual amount of AML generated grows
  * a little bit, there should be plenty of free space since the DSDT
@@ -2575,6 +2578,18 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)
                     ACPI_DEVICE_IF(x86ms->acpi_dev), x86ms->oem_id,
                     x86ms->oem_table_id);
 
+#ifdef CONFIG_ACPI_ERST
+    {
+        Object *erst_dev;
+        erst_dev = find_erst_dev();
+        if (erst_dev) {
+            acpi_add_table(table_offsets, tables_blob);
+            build_erst(tables_blob, tables->linker, erst_dev,
+                       x86ms->oem_id, x86ms->oem_table_id);
+        }
+    }
+#endif
+
     vmgenid_dev = find_vmgenid_dev();
     if (vmgenid_dev) {
         acpi_add_table(table_offsets, tables_blob);

hw/i386/acpi-microvm.c

@@ -30,6 +30,7 @@
 #include "hw/acpi/bios-linker-loader.h"
 #include "hw/acpi/generic_event_device.h"
 #include "hw/acpi/utils.h"
+#include "hw/acpi/erst.h"
 #include "hw/i386/fw_cfg.h"
 #include "hw/i386/microvm.h"
 #include "hw/pci/pci.h"
@@ -40,6 +41,8 @@
 #include "acpi-common.h"
 #include "acpi-microvm.h"
 
+#include CONFIG_DEVICES
+
 static void acpi_dsdt_add_virtio(Aml *scope,
                                  MicrovmMachineState *mms)
 {
@@ -207,6 +210,18 @@ static void acpi_build_microvm(AcpiBuildTables *tables,
                     ACPI_DEVICE_IF(x86ms->acpi_dev), x86ms->oem_id,
                     x86ms->oem_table_id);
 
+#ifdef CONFIG_ACPI_ERST
+    {
+        Object *erst_dev;
+        erst_dev = find_erst_dev();
+        if (erst_dev) {
+            acpi_add_table(table_offsets, tables_blob);
+            build_erst(tables_blob, tables->linker, erst_dev,
+                       x86ms->oem_id, x86ms->oem_table_id);
+        }
+    }
+#endif
+
     xsdt = tables_blob->len;
     build_xsdt(tables_blob, tables->linker, table_offsets, x86ms->oem_id,
                x86ms->oem_table_id);

hw/i386/pc_piix.c

@@ -357,10 +357,12 @@ static void pc_compat_1_4_fn(MachineState *machine)
     pc_compat_1_5_fn(machine);
 }
 
+#ifdef CONFIG_ISAPC
 static void pc_init_isa(MachineState *machine)
 {
     pc_init1(machine, TYPE_I440FX_PCI_HOST_BRIDGE, TYPE_I440FX_PCI_DEVICE);
 }
+#endif
 
 #ifdef CONFIG_XEN
 static void pc_xen_hvm_init_pci(MachineState *machine)
@@ -916,6 +918,7 @@ void igd_passthrough_isa_bridge_create(PCIBus *bus, uint16_t gpu_dev_id)
     pci_config_set_revision(bridge_dev->config, pch_rev_id);
 }
 
+#ifdef CONFIG_ISAPC
 static void isapc_machine_options(MachineClass *m)
 {
     PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
@@ -935,7 +938,7 @@ static void isapc_machine_options(MachineClass *m)
 
 DEFINE_PC_MACHINE(isapc, "isapc", pc_init_isa,
                   isapc_machine_options);
-
+#endif
 
 #ifdef CONFIG_XEN
 static void xenfv_4_2_machine_options(MachineClass *m)

include/hw/acpi/erst.h

@@ -0,0 +1,24 @@
+/*
+ * ACPI Error Record Serialization Table, ERST, Implementation
+ *
+ * ACPI ERST introduced in ACPI 4.0, June 16, 2009.
+ * ACPI Platform Error Interfaces : Error Serialization
+ *
+ * Copyright (c) 2021 Oracle and/or its affiliates.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+#ifndef HW_ACPI_ERST_H
+#define HW_ACPI_ERST_H
+
+void build_erst(GArray *table_data, BIOSLinker *linker, Object *erst_dev,
+                const char *oem_id, const char *oem_table_id);
+
+#define TYPE_ACPI_ERST "acpi-erst"
+
+/* returns NULL unless there is exactly one device */
+static inline Object *find_erst_dev(void)
+{
+    return object_resolve_path_type("", TYPE_ACPI_ERST, NULL);
+}
+#endif

include/hw/pci/pci.h

@@ -108,6 +108,7 @@ extern bool pci_available;
 #define PCI_DEVICE_ID_REDHAT_MDPY        0x000f
 #define PCI_DEVICE_ID_REDHAT_NVME        0x0010
 #define PCI_DEVICE_ID_REDHAT_PVPANIC     0x0011
+#define PCI_DEVICE_ID_REDHAT_ACPI_ERST   0x0012
 #define PCI_DEVICE_ID_REDHAT_QXL         0x0100
 
 #define FMT_PCIBUS                      PRIx64

subprojects/libvhost-user/libvhost-user.c

@@ -690,6 +690,29 @@ vu_add_mem_reg(VuDev *dev, VhostUserMsg *vmsg) {
     VuDevRegion *dev_region = &dev->regions[dev->nregions];
     void *mmap_addr;
 
+    if (vmsg->fd_num != 1) {
+        vmsg_close_fds(vmsg);
+        vu_panic(dev, "VHOST_USER_ADD_MEM_REG received %d fds - only 1 fd "
+                      "should be sent for this message type", vmsg->fd_num);
+        return false;
+    }
+
+    if (vmsg->size < VHOST_USER_MEM_REG_SIZE) {
+        close(vmsg->fds[0]);
+        vu_panic(dev, "VHOST_USER_ADD_MEM_REG requires a message size of at "
+                      "least %d bytes and only %d bytes were received",
+                      VHOST_USER_MEM_REG_SIZE, vmsg->size);
+        return false;
+    }
+
+    if (dev->nregions == VHOST_USER_MAX_RAM_SLOTS) {
+        close(vmsg->fds[0]);
+        vu_panic(dev, "failing attempt to hot add memory via "
+                      "VHOST_USER_ADD_MEM_REG message because the backend has "
+                      "no free ram slots available");
+        return false;
+    }
+
     /*
      * If we are in postcopy mode and we receive a u64 payload with a 0 value
      * we know all the postcopy client bases have been received, and we
@@ -728,12 +751,12 @@ vu_add_mem_reg(VuDev *dev, VhostUserMsg *vmsg) {
          * accessing it before we userfault.
          */
         mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset,
-                         PROT_NONE, MAP_SHARED,
+                         PROT_NONE, MAP_SHARED | MAP_NORESERVE,
                          vmsg->fds[0], 0);
     } else {
         mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset,
-                         PROT_READ | PROT_WRITE, MAP_SHARED, vmsg->fds[0],
-                         0);
+                         PROT_READ | PROT_WRITE, MAP_SHARED | MAP_NORESERVE,
+                         vmsg->fds[0], 0);
     }
 
     if (mmap_addr == MAP_FAILED) {
@@ -796,10 +819,24 @@ static inline bool reg_equal(VuDevRegion *vudev_reg,
 
 static bool
 vu_rem_mem_reg(VuDev *dev, VhostUserMsg *vmsg) {
-    int i, j;
-    bool found = false;
-    VuDevRegion shadow_regions[VHOST_USER_MAX_RAM_SLOTS] = {};
     VhostUserMemoryRegion m = vmsg->payload.memreg.region, *msg_region = &m;
+    int i;
+    bool found = false;
+
+    if (vmsg->fd_num != 1) {
+        vmsg_close_fds(vmsg);
+        vu_panic(dev, "VHOST_USER_REM_MEM_REG received %d fds - only 1 fd "
+                      "should be sent for this message type", vmsg->fd_num);
+        return false;
+    }
+
+    if (vmsg->size < VHOST_USER_MEM_REG_SIZE) {
+        close(vmsg->fds[0]);
+        vu_panic(dev, "VHOST_USER_REM_MEM_REG requires a message size of at "
+                      "least %d bytes and only %d bytes were received",
+                      VHOST_USER_MEM_REG_SIZE, vmsg->size);
+        return false;
+    }
 
     DPRINT("Removing region:\n");
     DPRINT("    guest_phys_addr: 0x%016"PRIx64"\n",
@@ -811,35 +848,40 @@ vu_rem_mem_reg(VuDev *dev, VhostUserMsg *vmsg) {
     DPRINT("    mmap_offset      0x%016"PRIx64"\n",
            msg_region->mmap_offset);
 
-    for (i = 0, j = 0; i < dev->nregions; i++) {
-        if (!reg_equal(&dev->regions[i], msg_region)) {
-            shadow_regions[j].gpa = dev->regions[i].gpa;
-            shadow_regions[j].size = dev->regions[i].size;
-            shadow_regions[j].qva = dev->regions[i].qva;
-            shadow_regions[j].mmap_addr = dev->regions[i].mmap_addr;
-            shadow_regions[j].mmap_offset = dev->regions[i].mmap_offset;
-            j++;
-        } else {
-            found = true;
+    for (i = 0; i < dev->nregions; i++) {
+        if (reg_equal(&dev->regions[i], msg_region)) {
             VuDevRegion *r = &dev->regions[i];
             void *m = (void *) (uintptr_t) r->mmap_addr;
 
             if (m) {
                 munmap(m, r->size + r->mmap_offset);
             }
+
+            /*
+             * Shift all affected entries by 1 to close the hole at index i and
+             * zero out the last entry.
+             */
+            memmove(dev->regions + i, dev->regions + i + 1,
+                    sizeof(VuDevRegion) * (dev->nregions - i - 1));
+            memset(dev->regions + dev->nregions - 1, 0, sizeof(VuDevRegion));
+            DPRINT("Successfully removed a region\n");
+            dev->nregions--;
+            i--;
+
+            found = true;
+
+            /* Continue the search for eventual duplicates. */
         }
     }
 
     if (found) {
-        memcpy(dev->regions, shadow_regions,
-               sizeof(VuDevRegion) * VHOST_USER_MAX_RAM_SLOTS);
-        DPRINT("Successfully removed a region\n");
-        dev->nregions--;
         vmsg_set_reply_u64(vmsg, 0);
     } else {
         vu_panic(dev, "Specified region not found\n");
     }
 
+    close(vmsg->fds[0]);
+
     return true;
 }
 
@@ -878,7 +920,7 @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg)
          * accessing it before we userfault
          */
         mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset,
-                         PROT_NONE, MAP_SHARED,
+                         PROT_NONE, MAP_SHARED | MAP_NORESERVE,
                          vmsg->fds[i], 0);
 
         if (mmap_addr == MAP_FAILED) {
@@ -965,7 +1007,7 @@ vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg)
          * mapped address has to be page aligned, and we use huge
          * pages.  */
         mmap_addr = mmap(0, dev_region->size + dev_region->mmap_offset,
-                         PROT_READ | PROT_WRITE, MAP_SHARED,
+                         PROT_READ | PROT_WRITE, MAP_SHARED | MAP_NORESERVE,
                          vmsg->fds[i], 0);
 
         if (mmap_addr == MAP_FAILED) {

subprojects/libvhost-user/libvhost-user.h

@@ -129,6 +129,8 @@ typedef struct VhostUserMemoryRegion {
     uint64_t mmap_offset;
 } VhostUserMemoryRegion;
 
+#define VHOST_USER_MEM_REG_SIZE (sizeof(VhostUserMemoryRegion))
+
 typedef struct VhostUserMemory {
     uint32_t nregions;
     uint32_t padding;

tcg/i386/tcg-target.c.inc

@@ -3747,7 +3747,7 @@ static void tcg_target_init(TCGContext *s)
 {
 #ifdef CONFIG_CPUID_H
     unsigned a, b, c, d, b7 = 0;
-    int max = __get_cpuid_max(0, 0);
+    unsigned max = __get_cpuid_max(0, 0);
 
     if (max >= 7) {
         /* BMI1 is available on AMD Piledriver and Intel Haswell CPUs.  */