hw/i386/pc: improve physical address space bound check for 32-bit x86 systems

32-bit x86 systems do not have a reserved memory for hole64. On those 32-bit
systems without PSE36 or PAE CPU features, hotplugging memory devices are not
supported by QEMU as QEMU always places hotplugged memory above 4 GiB boundary
which is beyond the physical address space of the processor. Linux guests also
does not support memory hotplug on those systems. Please see Linux
kernel commit b59d02ed08690 ("mm/memory_hotplug: disable the functionality
for 32b") for more details.

Therefore, the maximum limit of the guest physical address in the absence of
additional memory devices effectively coincides with the end of
"above 4G memory space" region for 32-bit x86 without PAE/PSE36. When users
configure additional memory devices, after properly accounting for the
additional device memory region to find the maximum value of the guest
physical address, the address will be outside the range of the processor's
physical address space.

This change adds improvements to take above into consideration.

For example, previously this was allowed:

$ ./qemu-system-x86_64 -cpu pentium -m size=10G

With this change now it is no longer allowed:

$ ./qemu-system-x86_64 -cpu pentium -m size=10G
qemu-system-x86_64: Address space limit 0xffffffff < 0x2bfffffff phys-bits too low (32)

However, the following are allowed since on both cases physical address
space of the processor is 36 bits:

$ ./qemu-system-x86_64 -cpu pentium2 -m size=10G
$ ./qemu-system-x86_64 -cpu pentium,pse36=on -m size=10G

For 32-bit, without PAE/PSE36, hotplugging additional memory is no longer allowed.

$ ./qemu-system-i386 -m size=1G,maxmem=3G,slots=2
qemu-system-i386: Address space limit 0xffffffff < 0x1ffffffff phys-bits too low (32)
$ ./qemu-system-i386 -machine q35 -m size=1G,maxmem=3G,slots=2
qemu-system-i386: Address space limit 0xffffffff < 0x1ffffffff phys-bits too low (32)

A new compatibility flag is introduced to make sure pc_max_used_gpa() keeps
returning the old value for machines 8.1 and older.
Therefore, the above is still allowed for older machine types in order to support
compatibility. Hence, the following still works:

$ ./qemu-system-i386 -machine pc-i440fx-8.1 -m size=1G,maxmem=3G,slots=2
$ ./qemu-system-i386 -machine pc-q35-8.1 -m size=1G,maxmem=3G,slots=2

Further, following is also allowed as with PSE36, the processor has 36-bit
address space:

$ ./qemu-system-i386 -cpu 486,pse36=on -m size=1G,maxmem=3G,slots=2

After calling CPUID with EAX=0x80000001, all AMD64 compliant processors
have the longmode-capable-bit turned on in the extended feature flags (bit 29)
in EDX. The absence of CPUID longmode can be used to differentiate between
32-bit and 64-bit processors and is the recommended approach. QEMU takes this
approach elsewhere (for example, please see x86_cpu_realizefn()), With
this change, pc_max_used_gpa() also uses the same method to detect 32-bit
processors.

Unit tests are modified to not run 32-bit x86 tests that use memory hotplug.

Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Ani Sinha <anisinha@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Message-Id: <20230922160413.165702-1-anisinha@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 3db0743f319bc5bf5169827a9be2ff4a7b59bc92..a532d42cf4c5b91c3f057e4640d07b9259abecfb 100644 (file)
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -907,13 +907,39 @@ static uint64_t pc_get_cxl_range_end(PCMachineState *pcms)
 static hwaddr pc_max_used_gpa(PCMachineState *pcms, uint64_t pci_hole64_size)
 {
     X86CPU *cpu = X86_CPU(first_cpu);
+    PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
+    MachineState *ms = MACHINE(pcms);
 
-    /* 32-bit systems don't have hole64 thus return max CPU address */
-    if (cpu->phys_bits <= 32) {
+    if (cpu->env.features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) {
+        /* 64-bit systems */
+        return pc_pci_hole64_start() + pci_hole64_size - 1;
+    }
+
+    /* 32-bit systems */
+    if (pcmc->broken_32bit_mem_addr_check) {
+        /* old value for compatibility reasons */
         return ((hwaddr)1 << cpu->phys_bits) - 1;
     }
 
-    return pc_pci_hole64_start() + pci_hole64_size - 1;
+    /*
+     * 32-bit systems don't have hole64 but they might have a region for
+     * memory devices. Even if additional hotplugged memory devices might
+     * not be usable by most guest OSes, we need to still consider them for
+     * calculating the highest possible GPA so that we can properly report
+     * if someone configures them on a CPU that cannot possibly address them.
+     */
+    if (pcmc->has_reserved_memory &&
+        (ms->ram_size < ms->maxram_size)) {
+        hwaddr devmem_start;
+        ram_addr_t devmem_size;
+
+        pc_get_device_memory_range(pcms, &devmem_start, &devmem_size);
+        devmem_start += devmem_size;
+        return devmem_start - 1;
+    }
+
+    /* configuration without any memory hotplug */
+    return pc_above_4g_end(pcms) - 1;
 }
 
 /*

diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 8321f36f97f173e32641a5f87560202fc61134c8..71003759bbfb80a241f804bfc810a61aef20ff71 100644 (file)
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -517,9 +517,13 @@ DEFINE_I440FX_MACHINE(v8_2, "pc-i440fx-8.2", NULL,
 
 static void pc_i440fx_8_1_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+
     pc_i440fx_8_2_machine_options(m);
     m->alias = NULL;
     m->is_default = false;
+    pcmc->broken_32bit_mem_addr_check = true;
+
     compat_props_add(m->compat_props, hw_compat_8_1, hw_compat_8_1_len);
     compat_props_add(m->compat_props, pc_compat_8_1, pc_compat_8_1_len);
 }

diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 2dd1158b7085092e631e880920d636852e367cb5..a7386f2ca25192e17cec69e4a8a9a60db7fa2ea2 100644 (file)
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -394,8 +394,10 @@ DEFINE_Q35_MACHINE(v8_2, "pc-q35-8.2", NULL,
 
 static void pc_q35_8_1_machine_options(MachineClass *m)
 {
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_8_2_machine_options(m);
     m->alias = NULL;
+    pcmc->broken_32bit_mem_addr_check = true;
     compat_props_add(m->compat_props, hw_compat_8_1, hw_compat_8_1_len);
     compat_props_add(m->compat_props, pc_compat_8_1, pc_compat_8_1_len);
 }

diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 0fabece236cff20d2e3248bb89455a830e03deab..bec38cb92cf77d73a7fe4f8950d292ed9f70caf4 100644 (file)
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -129,6 +129,12 @@ struct PCMachineClass {
 
     /* resizable acpi blob compat */
     bool resizable_acpi_blob;
+
+    /*
+     * whether the machine type implements broken 32-bit address space bound
+     * check for memory.
+     */
+    bool broken_32bit_mem_addr_check;
 };
 
 #define TYPE_PC_MACHINE "generic-pc-machine"

diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c
index d1b80149f294e1b17c2854595236313dea94e0f0..f8e03dfd461581b9ffa7e1c7f1e7e6933503c8d5 100644 (file)
--- a/tests/qtest/bios-tables-test.c
+++ b/tests/qtest/bios-tables-test.c
@@ -2080,7 +2080,6 @@ int main(int argc, char *argv[])
                            test_acpi_piix4_no_acpi_pci_hotplug);
             qtest_add_func("acpi/piix4/ipmi", test_acpi_piix4_tcg_ipmi);
             qtest_add_func("acpi/piix4/cpuhp", test_acpi_piix4_tcg_cphp);
-            qtest_add_func("acpi/piix4/memhp", test_acpi_piix4_tcg_memhp);
             qtest_add_func("acpi/piix4/numamem", test_acpi_piix4_tcg_numamem);
             qtest_add_func("acpi/piix4/nosmm", test_acpi_piix4_tcg_nosmm);
             qtest_add_func("acpi/piix4/smm-compat",
@@ -2088,9 +2087,15 @@ int main(int argc, char *argv[])
             qtest_add_func("acpi/piix4/smm-compat-nosmm",
                            test_acpi_piix4_tcg_smm_compat_nosmm);
             qtest_add_func("acpi/piix4/nohpet", test_acpi_piix4_tcg_nohpet);
-            qtest_add_func("acpi/piix4/dimmpxm", test_acpi_piix4_tcg_dimm_pxm);
-            qtest_add_func("acpi/piix4/acpihmat",
-                           test_acpi_piix4_tcg_acpi_hmat);
+
+            /* i386 does not support memory hotplug */
+            if (strcmp(arch, "i386")) {
+                qtest_add_func("acpi/piix4/memhp", test_acpi_piix4_tcg_memhp);
+                qtest_add_func("acpi/piix4/dimmpxm",
+                               test_acpi_piix4_tcg_dimm_pxm);
+                qtest_add_func("acpi/piix4/acpihmat",
+                               test_acpi_piix4_tcg_acpi_hmat);
+            }
 #ifdef CONFIG_POSIX
             qtest_add_func("acpi/piix4/acpierst", test_acpi_piix4_acpi_erst);
 #endif
@@ -2108,11 +2113,9 @@ int main(int argc, char *argv[])
                            test_acpi_q35_tcg_no_acpi_hotplug);
             qtest_add_func("acpi/q35/multif-bridge",
                            test_acpi_q35_multif_bridge);
-            qtest_add_func("acpi/q35/mmio64", test_acpi_q35_tcg_mmio64);
             qtest_add_func("acpi/q35/ipmi", test_acpi_q35_tcg_ipmi);
             qtest_add_func("acpi/q35/smbus/ipmi", test_acpi_q35_tcg_smbus_ipmi);
             qtest_add_func("acpi/q35/cpuhp", test_acpi_q35_tcg_cphp);
-            qtest_add_func("acpi/q35/memhp", test_acpi_q35_tcg_memhp);
             qtest_add_func("acpi/q35/numamem", test_acpi_q35_tcg_numamem);
             qtest_add_func("acpi/q35/nosmm", test_acpi_q35_tcg_nosmm);
             qtest_add_func("acpi/q35/smm-compat",
@@ -2120,10 +2123,17 @@ int main(int argc, char *argv[])
             qtest_add_func("acpi/q35/smm-compat-nosmm",
                            test_acpi_q35_tcg_smm_compat_nosmm);
             qtest_add_func("acpi/q35/nohpet", test_acpi_q35_tcg_nohpet);
-            qtest_add_func("acpi/q35/dimmpxm", test_acpi_q35_tcg_dimm_pxm);
-            qtest_add_func("acpi/q35/acpihmat", test_acpi_q35_tcg_acpi_hmat);
             qtest_add_func("acpi/q35/acpihmat-noinitiator",
                            test_acpi_q35_tcg_acpi_hmat_noinitiator);
+
+            /* i386 does not support memory hotplug */
+            if (strcmp(arch, "i386")) {
+                qtest_add_func("acpi/q35/memhp", test_acpi_q35_tcg_memhp);
+                qtest_add_func("acpi/q35/dimmpxm", test_acpi_q35_tcg_dimm_pxm);
+                qtest_add_func("acpi/q35/acpihmat",
+                               test_acpi_q35_tcg_acpi_hmat);
+                qtest_add_func("acpi/q35/mmio64", test_acpi_q35_tcg_mmio64);
+            }
 #ifdef CONFIG_POSIX
             qtest_add_func("acpi/q35/acpierst", test_acpi_q35_acpi_erst);
 #endif

diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c
index c5eb13f349f716ad37733d2613682a338f058da4..4f4404a4b148626ddcffe43b4ccdd92100cf981c 100644 (file)
--- a/tests/qtest/numa-test.c
+++ b/tests/qtest/numa-test.c
@@ -568,7 +568,7 @@ int main(int argc, char **argv)
     qtest_add_data_func("/numa/mon/cpus/partial", args, test_mon_partial);
     qtest_add_data_func("/numa/qmp/cpus/query-cpus", args, test_query_cpus);
 
-    if (!strcmp(arch, "i386") || !strcmp(arch, "x86_64")) {
+    if (!strcmp(arch, "x86_64")) {
         qtest_add_data_func("/numa/pc/cpu/explicit", args, pc_numa_cpu);
         qtest_add_data_func("/numa/pc/dynamic/cpu", args, pc_dynamic_cpu_cfg);
         qtest_add_data_func("/numa/pc/hmat/build", args, pc_hmat_build_cfg);
@@ -576,6 +576,11 @@ int main(int argc, char **argv)
         qtest_add_data_func("/numa/pc/hmat/erange", args, pc_hmat_erange_cfg);
     }
 
+    if (!strcmp(arch, "i386")) {
+        qtest_add_data_func("/numa/pc/cpu/explicit", args, pc_numa_cpu);
+        qtest_add_data_func("/numa/pc/dynamic/cpu", args, pc_dynamic_cpu_cfg);
+    }
+
     if (!strcmp(arch, "ppc64")) {
         qtest_add_data_func("/numa/spapr/cpu/explicit", args, spapr_numa_cpu);
     }