[Qemu-devel] [PATCH rebased for-1.8] i386: pc: align gpa<->hpa on 1GB boundary (v6)

[Paolo Bonzini]

v2: condition enablement of new mapping to new machine types (Paolo)
v3: fix changelog
v4: rebase
v5: ensure alignment of piecetwo on 2MB GPA (Igor)
    do not register zero-sized piece-one    (Igor)
v6: fix memory leak                         (Igor)
    fix integer overflow                    (Igor)

----

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 <address@hidden>
[Reorganize code, keep same logic. - Paolo]
Signed-off-by: Paolo Bonzini <address@hidden>
---
 hw/i386/pc.c         |   67 +++++++++++++++++++++++++++++++++++++++++++------
 hw/i386/pc_piix.c    |    3 ++
 hw/i386/pc_q35.c     |    3 ++
 include/hw/i386/pc.h |    1 +
 4 files changed, 65 insertions(+), 9 deletions(-)

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 6c82ada..485b44d 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1148,8 +1148,10 @@ 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_pieceone, *ram_above_4g_piecetwo;
     FWCfgState *fw_cfg;
+    uint64_t holesize, pieceonesize, piecetwosize;
+    uint64_t memsize, align_offset;
 
     linux_boot = (kernel_filename != NULL);
 
@@ -1157,26 +1159,73 @@ FWCfgState *pc_memory_init(MemoryRegion *system_memory,
      * aliases to address portions of it, mostly for backwards compatibility
      * with older qemus that used qemu_ram_alloc().
      */
+    memsize = below_4g_mem_size + above_4g_mem_size;
+    holesize = 0x100000000ULL - below_4g_mem_size;
+
+    /* If 1GB hugepages are used to back guest RAM, we want the
+     * physical address 4GB to map to 4GB in the RAM, so that
+     * memory beyond 4GB is aligned on a 1GB boundary, at the
+     * host physical address space.  Thus, the ram block range
+     * [holestart, 4GB] is mapped to the last holesize bytes of RAM:
+     *
+     *                      0      h     4G     memsize-holesize
+     *
+     * contiguous-ram-block [xxxxxx][yyy][zzzzz]
+     *                                '-----------.
+     * guest-addr-space     [xxxxxx]     [zzzzz][yyy]
+     *
+     * This is only done in new-enough machine types, and of course
+     * it  is only possible if the [zzzzz] block exists at all.
+     */
+    if (guest_info->gb_align && above_4g_mem_size > holesize) {
+        /* Round the allocation up to 2 MB to make [zzzzz]'s size
+         * aligned, removing the extra from the [yyy] piece.
+         */
+        align_offset = ROUND_UP(memsize, 1UL << 21) - memsize;
+        piecetwosize = holesize - align_offset;
+    } else {
+        /* There's no [zzzzz] piece, all memory above 4G starts
+         * at below_4g_mem_size in the RAM block.  Also no need
+         * to align anything.
+         */
+        align_offset = 0;
+        piecetwosize = above_4g_mem_size;
+    }
+
     ram = g_malloc(sizeof(*ram));
-    memory_region_init_ram(ram, NULL, "pc.ram",
-                           below_4g_mem_size + above_4g_mem_size);
+    memory_region_init_ram(ram, NULL, "pc.ram", memsize + align_offset);
     vmstate_register_ram_global(ram);
     *ram_memory = ram;
+
     ram_below_4g = g_malloc(sizeof(*ram_below_4g));
     memory_region_init_alias(ram_below_4g, NULL, "ram-below-4g", ram,
                              0, below_4g_mem_size);
     memory_region_add_subregion(system_memory, 0, ram_below_4g);
+
+    pieceonesize = above_4g_mem_size - piecetwosize;
+    if (pieceonesize) {
+        ram_above_4g_pieceone = g_malloc(sizeof(*ram_above_4g_pieceone));
+        memory_region_init_alias(ram_above_4g_pieceone, NULL,
+                                 "ram-above-4g-pieceone", ram,
+                                 0x100000000ULL, pieceonesize);
+        memory_region_add_subregion(system_memory, 0x100000000ULL,
+                                    ram_above_4g_pieceone);
+    }
+    if (piecetwosize) {
+        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,
+                                 below_4g_mem_size, piecetwosize);
+        memory_region_add_subregion(system_memory,
+                                    0x100000000ULL + pieceonesize,
+                                    ram_above_4g_piecetwo);
+    }
+
     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,
-                                    ram_above_4g);
         e820_add_entry(0x100000000ULL, above_4g_mem_size, E820_RAM);
     }
 
-
     /* Initialize PC system firmware */
     pc_system_firmware_init(rom_memory, guest_info->isapc_ram_fw);
 
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 36f2495..ca9bd2e 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -62,6 +62,7 @@ static bool has_pvpanic;
 static bool has_pci_info;
 static bool has_acpi_build = true;
 static bool smbios_type1_defaults = true;
+static bool gb_align = true;
 
 /* PC hardware initialisation */
 static void pc_init1(QEMUMachineInitArgs *args,
@@ -130,6 +131,7 @@ 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;
 
     if (smbios_type1_defaults) {
         /* These values are guest ABI, do not change */
@@ -249,6 +251,7 @@ static void pc_init_pci(QEMUMachineInitArgs *args)
 static void pc_compat_1_7(QEMUMachineInitArgs *args)
 {
     smbios_type1_defaults = false;
+    gb_align = false;
 }
 
 static void pc_compat_1_6(QEMUMachineInitArgs *args)
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 50ca458..89c7720 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -52,6 +52,7 @@ static bool has_pvpanic;
 static bool has_pci_info;
 static bool has_acpi_build = true;
 static bool smbios_type1_defaults = true;
+static bool gb_align = true;
 
 /* PC hardware initialisation */
 static void pc_q35_init(QEMUMachineInitArgs *args)
@@ -115,6 +116,7 @@ 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;
 
     if (smbios_type1_defaults) {
         /* These values are guest ABI, do not change */
@@ -233,6 +235,7 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
 static void pc_compat_1_7(QEMUMachineInitArgs *args)
 {
     smbios_type1_defaults = false;
+    gb_align = false;
 }
 
 static void pc_compat_1_6(QEMUMachineInitArgs *args)
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 9af09d3..8047e82 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 */
-- 
1.7.1