[Qemu-devel] i386: pc: align gpa<->hpa on 1GB boundary (v4)

[Marcelo Tosatti <mtosatti@redhat.com>]

v2: condition enablement of new mapping to new machine types (Paolo)
v3: fix changelog
v4: rebase

-----


Align guest physical address and host physical address
beyond guest 4GB on a 1GB boundary.

Otherwise 1GB TLBs cannot be cached for the range.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>


diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 12c436e..d29196d 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1156,7 +1156,7 @@ FWCfgState *pc_memory_init(MemoryRegion *system_memory,
 {
     int linux_boot, i;
     MemoryRegion *ram, *option_rom_mr;
-    MemoryRegion *ram_below_4g, *ram_above_4g;
+    MemoryRegion *ram_below_4g, *ram_above_4g, *ram_above_4g_piecetwo;
     FWCfgState *fw_cfg;
 
     linux_boot = (kernel_filename != NULL);
@@ -1177,10 +1177,45 @@ FWCfgState *pc_memory_init(MemoryRegion *system_memory,
     e820_add_entry(0, below_4g_mem_size, E820_RAM);
     if (above_4g_mem_size > 0) {
         ram_above_4g = g_malloc(sizeof(*ram_above_4g));
-        memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
-                                 below_4g_mem_size, above_4g_mem_size);
-        memory_region_add_subregion(system_memory, 0x100000000ULL,
+        /*
+         *
+         * If 1GB hugepages are used to back guest RAM, map guest address
+         * space in the range [ramsize,ramsize+holesize] to the ram block
+         * range [holestart, 4GB]
+         *
+         *                      0      h     4G     [ramsize,ramsize+holesize]
+         *
+         * guest-addr-space     [      ]     [      ][xxx]
+         *                                /----------/
+         * contiguous-ram-block [      ][xxx][     ]
+         *
+         * So that memory beyond 4GB is aligned on a 1GB boundary,
+         * at the host physical address space.
+         *
+         */
+        if (guest_info->gb_align) {
+            unsigned long holesize = 0x100000000ULL - below_4g_mem_size;
+
+            memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
+                                    0x100000000ULL,
+                                    above_4g_mem_size - holesize);
+            memory_region_add_subregion(system_memory, 0x100000000ULL,
                                     ram_above_4g);
+
+            ram_above_4g_piecetwo = g_malloc(sizeof(*ram_above_4g_piecetwo));
+            memory_region_init_alias(ram_above_4g_piecetwo, NULL,
+                                     "ram-above-4g-piecetwo", ram,
+                                     0x100000000ULL - holesize, holesize);
+            memory_region_add_subregion(system_memory,
+                                        0x100000000ULL +
+                                        above_4g_mem_size - holesize,
+                                        ram_above_4g_piecetwo);
+        } else {
+            memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,
+                                    below_4g_mem_size, above_4g_mem_size);
+            memory_region_add_subregion(system_memory, 0x100000000ULL,
+                                    ram_above_4g);
+        }
         e820_add_entry(0x100000000ULL, above_4g_mem_size, E820_RAM);
     }
 
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 4fdb7b6..686736e 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -60,6 +60,7 @@ static const int ide_irq[MAX_IDE_BUS] = { 14, 15 };
 static bool has_pvpanic;
 static bool has_pci_info = true;
 static bool has_acpi_build = true;
+static bool gb_align = true;
 
 /* PC hardware initialisation */
 static void pc_init1(QEMUMachineInitArgs *args,
@@ -128,6 +129,7 @@ static void pc_init1(QEMUMachineInitArgs *args,
 
     guest_info->has_pci_info = has_pci_info;
     guest_info->isapc_ram_fw = !pci_enabled;
+    guest_info->gb_align = gb_align;
 
     /* allocate ram and load rom/bios */
     if (!xen_enabled()) {
@@ -240,8 +242,14 @@ static void pc_init_pci(QEMUMachineInitArgs *args)
     pc_init1(args, 1, 1);
 }
 
+static void pc_compat_1_7(QEMUMachineInitArgs *args)
+{
+    gb_align = false;
+}
+
 static void pc_compat_1_6(QEMUMachineInitArgs *args)
 {
+    pc_compat_1_7(args);
     has_pci_info = false;
     rom_file_in_ram = false;
     has_acpi_build = false;
@@ -274,6 +282,12 @@ static void pc_compat_1_2(QEMUMachineInitArgs *args)
     disable_kvm_pv_eoi();
 }
 
+static void pc_init_pci_1_7(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_7(args);
+    pc_init_pci(args);
+}
+
 static void pc_init_pci_1_6(QEMUMachineInitArgs *args)
 {
     pc_compat_1_6(args);
@@ -346,13 +360,21 @@ static void pc_xen_hvm_init(QEMUMachineInitArgs *args)
     .desc = "Standard PC (i440FX + PIIX, 1996)", \
     .hot_add_cpu = pc_hot_add_cpu
 
+#define PC_I440FX_1_8_MACHINE_OPTIONS PC_I440FX_MACHINE_OPTIONS
+static QEMUMachine pc_i440fx_machine_v1_8 = {
+    PC_I440FX_1_8_MACHINE_OPTIONS,
+    .name = "pc-i440fx-1.8",
+    .alias = "pc",
+    .init = pc_init_pci,
+    .is_default = 1,
+};
+
 #define PC_I440FX_1_7_MACHINE_OPTIONS PC_I440FX_MACHINE_OPTIONS
 static QEMUMachine pc_i440fx_machine_v1_7 = {
     PC_I440FX_1_7_MACHINE_OPTIONS,
     .name = "pc-i440fx-1.7",
     .alias = "pc",
-    .init = pc_init_pci,
-    .is_default = 1,
+    .init = pc_init_pci_1_7,
 };
 
 #define PC_I440FX_1_6_MACHINE_OPTIONS PC_I440FX_MACHINE_OPTIONS
@@ -754,6 +776,7 @@ static QEMUMachine xenfv_machine = {
 
 static void pc_machine_init(void)
 {
+    qemu_register_machine(&pc_i440fx_machine_v1_8);
     qemu_register_machine(&pc_i440fx_machine_v1_7);
     qemu_register_machine(&pc_i440fx_machine_v1_6);
     qemu_register_machine(&pc_i440fx_machine_v1_5);
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 4c191d3..c2eb568 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -50,6 +50,7 @@
 static bool has_pvpanic;
 static bool has_pci_info = true;
 static bool has_acpi_build = true;
+static bool gb_align = true;
 
 /* PC hardware initialisation */
 static void pc_q35_init(QEMUMachineInitArgs *args)
@@ -113,6 +114,7 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
     guest_info->has_pci_info = has_pci_info;
     guest_info->isapc_ram_fw = false;
     guest_info->has_acpi_build = has_acpi_build;
+    guest_info->gb_align = gb_align;
 
     /* allocate ram and load rom/bios */
     if (!xen_enabled()) {
@@ -222,8 +224,14 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
     }
 }
 
+static void pc_compat_1_7(QEMUMachineInitArgs *args)
+{
+   gb_align = false;
+}
+
 static void pc_compat_1_6(QEMUMachineInitArgs *args)
 {
+    pc_compat_1_7(args);
     has_pci_info = false;
     rom_file_in_ram = false;
     has_acpi_build = false;
@@ -243,6 +251,12 @@ static void pc_compat_1_4(QEMUMachineInitArgs *args)
     x86_cpu_compat_set_features("Westmere", FEAT_1_ECX, 0, CPUID_EXT_PCLMULQDQ);
 }
 
+static void pc_q35_init_1_7(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_7(args);
+    pc_q35_init(args);
+}
+
 static void pc_q35_init_1_6(QEMUMachineInitArgs *args)
 {
     pc_compat_1_6(args);
@@ -266,13 +280,22 @@ static void pc_q35_init_1_4(QEMUMachineInitArgs *args)
     .desc = "Standard PC (Q35 + ICH9, 2009)", \
     .hot_add_cpu = pc_hot_add_cpu
 
+#define PC_Q35_1_8_MACHINE_OPTIONS PC_Q35_MACHINE_OPTIONS
+
+static QEMUMachine pc_q35_machine_v1_8 = {
+    PC_Q35_1_8_MACHINE_OPTIONS,
+    .name = "pc-q35-1.8",
+    .alias = "q35",
+    .init = pc_q35_init,
+};
+
 #define PC_Q35_1_7_MACHINE_OPTIONS PC_Q35_MACHINE_OPTIONS
 
 static QEMUMachine pc_q35_machine_v1_7 = {
     PC_Q35_1_7_MACHINE_OPTIONS,
     .name = "pc-q35-1.7",
     .alias = "q35",
-    .init = pc_q35_init,
+    .init = pc_q35_init_1_7,
 };
 
 #define PC_Q35_1_6_MACHINE_OPTIONS PC_Q35_MACHINE_OPTIONS
@@ -313,6 +336,7 @@ static QEMUMachine pc_q35_machine_v1_4 = {
 
 static void pc_q35_machine_init(void)
 {
+    qemu_register_machine(&pc_q35_machine_v1_8);
     qemu_register_machine(&pc_q35_machine_v1_7);
     qemu_register_machine(&pc_q35_machine_v1_6);
     qemu_register_machine(&pc_q35_machine_v1_5);
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 03cc0ba..35a6885 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -41,6 +41,7 @@ struct PcGuestInfo {
     uint64_t *node_cpu;
     FWCfgState *fw_cfg;
     bool has_acpi_build;
+    bool gb_align;
 };
 
 /* parallel.c */