Merge remote-tracking branch 'remotes/ehabkost/tags/machine-next-pull-request' into staging

Machine queue, 2019-04-25 * 4.1 machine-types (Cornelia Huck) * Support MAP_SYNC on pmem memory backends (Zhang Yi) * -cpu parsing fixes and cleanups (Eduardo Habkost) * machine initialization cleanups (Wei Yang, Markus Armbruster) # gpg: Signature made Thu 25 Apr 2019 18:54:57 BST # gpg: using RSA key 2807936F984DC5A6 # gpg: Good signature from "Eduardo Habkost <ehabkost@redhat.com>" [full] # Primary key fingerprint: 5A32 2FD5 ABC4 D3DB ACCF D1AA 2807 936F 984D C5A6 * remotes/ehabkost/tags/machine-next-pull-request: util/mmap-alloc: support MAP_SYNC in qemu_ram_mmap() linux-headers: add linux/mman.h. scripts/update-linux-headers: add linux/mman.h util/mmap-alloc: Add a 'is_pmem' parameter to qemu_ram_mmap cpu: Fix crash with empty -cpu option cpu: Rename parse_cpu_model() to parse_cpu_option() vl: Simplify machine_parse() vl: Clean up after previous commit vl.c: allocate TYPE_MACHINE list once during bootup vl.c: make find_default_machine() local hw: add compat machines for 4.1 Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2026-07-06 00:20:22 -07:00 · 2019-04-26 14:30:18 +01:00
parent f7526eece2 119906afa5
commit 06e6433955
31 changed files with 593 additions and 77 deletions
@@ -905,7 +905,7 @@ int main(int argc, char **argv)
    /* init tcg before creating CPUs and to get qemu_host_page_size */
    tcg_exec_init(0);

-    cpu_type = parse_cpu_model(cpu_model);
+    cpu_type = parse_cpu_option(cpu_model);
    cpu = cpu_create(cpu_type);
    env = cpu->env_ptr;
 #if defined(TARGET_SPARC) || defined(TARGET_PPC)
@@ -144,9 +144,25 @@ Guest Data Persistence
 ----------------------

 Though QEMU supports multiple types of vNVDIMM backends on Linux,
-currently the only one that can guarantee the guest write persistence
-is the device DAX on the real NVDIMM device (e.g., /dev/dax0.0), to
-which all guest access do not involve any host-side kernel cache.
+the only backend that can guarantee the guest write persistence is:
+
+A. DAX device (e.g., /dev/dax0.0, ) or
+B. DAX file(mounted with dax option)
+
+When using B (A file supporting direct mapping of persistent memory)
+as a backend, write persistence is guaranteed if the host kernel has
+support for the MAP_SYNC flag in the mmap system call (available
+since Linux 4.15 and on certain distro kernels) and additionally
+both 'pmem' and 'share' flags are set to 'on' on the backend.
+
+If these conditions are not satisfied i.e. if either 'pmem' or 'share'
+are not set, if the backend file does not support DAX or if MAP_SYNC
+is not supported by the host kernel, write persistence is not
+guaranteed after a system crash. For compatibility reasons, these
+conditions are ignored if not satisfied. Currently, no way is
+provided to test for them.
+For more details, please reference mmap(2) man page:
+http://man7.org/linux/man-pages/man2/mmap.2.html.

 When using other types of backends, it's suggested to set 'unarmed'
 option of '-device nvdimm' to 'on', which sets the unarmed flag of the
@@ -983,14 +983,18 @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp)
 #endif
 }

-const char *parse_cpu_model(const char *cpu_model)
+const char *parse_cpu_option(const char *cpu_option)
 {
    ObjectClass *oc;
    CPUClass *cc;
    gchar **model_pieces;
    const char *cpu_type;

-    model_pieces = g_strsplit(cpu_model, ",", 2);
+    model_pieces = g_strsplit(cpu_option, ",", 2);
+    if (!model_pieces[0]) {
+        error_report("-cpu option cannot be empty");
+        exit(1);
+    }

    oc = cpu_class_by_name(CPU_RESOLVING_TYPE, model_pieces[0]);
    if (oc == NULL) {
@@ -1915,7 +1919,7 @@ static void *file_ram_alloc(RAMBlock *block,
    }

    area = qemu_ram_mmap(fd, memory, block->mr->align,
-                         block->flags & RAM_SHARED);
+                         block->flags & RAM_SHARED, block->flags & RAM_PMEM);
    if (area == MAP_FAILED) {
        error_setg_errno(errp, errno,
                         "unable to map backing store for guest RAM");
@@ -1978,10 +1978,17 @@ static void machvirt_machine_init(void)
 }
 type_init(machvirt_machine_init);

-static void virt_machine_4_0_options(MachineClass *mc)
+static void virt_machine_4_1_options(MachineClass *mc)
 {
 }
-DEFINE_VIRT_MACHINE_AS_LATEST(4, 0)
+DEFINE_VIRT_MACHINE_AS_LATEST(4, 1)
+
+static void virt_machine_4_0_options(MachineClass *mc)
+{
+    virt_machine_4_1_options(mc);
+    compat_props_add(mc->compat_props, hw_compat_4_0, hw_compat_4_0_len);
+}
+DEFINE_VIRT_MACHINE(4, 0)

 static void virt_machine_3_1_options(MachineClass *mc)
 {
@@ -24,6 +24,9 @@
 #include "hw/pci/pci.h"
 #include "hw/mem/nvdimm.h"

+GlobalProperty hw_compat_4_0[] = {};
+const size_t hw_compat_4_0_len = G_N_ELEMENTS(hw_compat_4_0);
+
 GlobalProperty hw_compat_3_1[] = {
    { "pcie-root-port", "x-speed", "2_5" },
    { "pcie-root-port", "x-width", "1" },
@@ -115,6 +115,9 @@ struct hpet_fw_config hpet_cfg = {.count = UINT8_MAX};
 /* Physical Address of PVH entry point read from kernel ELF NOTE */
 static size_t pvh_start_addr;

+GlobalProperty pc_compat_4_0[] = {};
+const size_t pc_compat_4_0_len = G_N_ELEMENTS(pc_compat_4_0);
+
 GlobalProperty pc_compat_3_1[] = {
    { "intel-iommu", "dma-drain", "off" },
    { "Opteron_G3" "-" TYPE_X86_CPU, "rdtscp", "off" },
@@ -428,13 +428,25 @@ static void pc_i440fx_machine_options(MachineClass *m)
    machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE);
 }

-static void pc_i440fx_4_0_machine_options(MachineClass *m)
+static void pc_i440fx_4_1_machine_options(MachineClass *m)
 {
    pc_i440fx_machine_options(m);
    m->alias = "pc";
    m->is_default = 1;
 }

+DEFINE_I440FX_MACHINE(v4_1, "pc-i440fx-4.1", NULL,
+                      pc_i440fx_4_1_machine_options);
+
+static void pc_i440fx_4_0_machine_options(MachineClass *m)
+{
+    pc_i440fx_4_1_machine_options(m);
+    m->alias = NULL;
+    m->is_default = 0;
+    compat_props_add(m->compat_props, hw_compat_4_0, hw_compat_4_0_len);
+    compat_props_add(m->compat_props, pc_compat_4_0, pc_compat_4_0_len);
+}
+
 DEFINE_I440FX_MACHINE(v4_0, "pc-i440fx-4.0", NULL,
                      pc_i440fx_4_0_machine_options);

@@ -365,12 +365,23 @@ static void pc_q35_machine_options(MachineClass *m)
    m->max_cpus = 288;
 }

-static void pc_q35_4_0_machine_options(MachineClass *m)
+static void pc_q35_4_1_machine_options(MachineClass *m)
 {
    pc_q35_machine_options(m);
    m->alias = "q35";
 }

+DEFINE_Q35_MACHINE(v4_1, "pc-q35-4.1", NULL,
+                   pc_q35_4_1_machine_options);
+
+static void pc_q35_4_0_machine_options(MachineClass *m)
+{
+    pc_q35_4_1_machine_options(m);
+    m->alias = NULL;
+    compat_props_add(m->compat_props, hw_compat_4_0, hw_compat_4_0_len);
+    compat_props_add(m->compat_props, pc_compat_4_0, pc_compat_4_0_len);
+}
+
 DEFINE_Q35_MACHINE(v4_0, "pc-q35-4.0", NULL,
                   pc_q35_4_0_machine_options);

@@ -4345,14 +4345,25 @@ static const TypeInfo spapr_machine_info = {
    type_init(spapr_machine_register_##suffix)

 /*
- * pseries-4.0
+ * pseries-4.1
 */
-static void spapr_machine_4_0_class_options(MachineClass *mc)
+static void spapr_machine_4_1_class_options(MachineClass *mc)
 {
    /* Defaults for the latest behaviour inherited from the base class */
 }

-DEFINE_SPAPR_MACHINE(4_0, "4.0", true);
+DEFINE_SPAPR_MACHINE(4_1, "4.1", true);
+
+/*
+ * pseries-4.0
+ */
+static void spapr_machine_4_0_class_options(MachineClass *mc)
+{
+    spapr_machine_4_1_class_options(mc);
+    compat_props_add(mc->compat_props, hw_compat_4_0, hw_compat_4_0_len);
+}
+
+DEFINE_SPAPR_MACHINE(4_0, "4.0", false);

 /*
 * pseries-3.1
@@ -658,14 +658,26 @@ bool css_migration_enabled(void)
    }                                                                         \
    type_init(ccw_machine_register_##suffix)

+static void ccw_machine_4_1_instance_options(MachineState *machine)
+{
+}
+
+static void ccw_machine_4_1_class_options(MachineClass *mc)
+{
+}
+DEFINE_CCW_MACHINE(4_1, "4.1", true);
+
 static void ccw_machine_4_0_instance_options(MachineState *machine)
 {
+    ccw_machine_4_1_instance_options(machine);
 }

 static void ccw_machine_4_0_class_options(MachineClass *mc)
 {
+    ccw_machine_4_1_class_options(mc);
+    compat_props_add(mc->compat_props, hw_compat_4_0, hw_compat_4_0_len);
 }
-DEFINE_CCW_MACHINE(4_0, "4.0", true);
+DEFINE_CCW_MACHINE(4_0, "4.0", false);

 static void ccw_machine_3_1_instance_options(MachineState *machine)
 {
@@ -57,7 +57,6 @@ void memory_region_allocate_system_memory(MemoryRegion *mr, Object *owner,
 #define MACHINE_CLASS(klass) \
    OBJECT_CLASS_CHECK(MachineClass, (klass), TYPE_MACHINE)

-MachineClass *find_default_machine(void);
 extern MachineState *current_machine;

 void machine_run_board_init(MachineState *machine);
@@ -293,6 +292,9 @@ struct MachineState {
    } \
    type_init(machine_initfn##_register_types)

+extern GlobalProperty hw_compat_4_0[];
+extern const size_t hw_compat_4_0_len;
+
 extern GlobalProperty hw_compat_3_1[];
 extern const size_t hw_compat_3_1_len;

@@ -293,6 +293,9 @@ int e820_add_entry(uint64_t, uint64_t, uint32_t);
 int e820_get_num_entries(void);
 bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *);

+extern GlobalProperty pc_compat_4_0[];
+extern const size_t pc_compat_4_0_len;
+
 extern GlobalProperty pc_compat_3_1[];
 extern const size_t pc_compat_3_1_len;

@@ -7,7 +7,26 @@ size_t qemu_fd_getpagesize(int fd);

 size_t qemu_mempath_getpagesize(const char *mem_path);

-void *qemu_ram_mmap(int fd, size_t size, size_t align, bool shared);
+/**
+ * qemu_ram_mmap: mmap the specified file or device.
+ *
+ * Parameters:
+ *  @fd: the file or the device to mmap
+ *  @size: the number of bytes to be mmaped
+ *  @align: if not zero, specify the alignment of the starting mapping address;
+ *          otherwise, the alignment in use will be determined by QEMU.
+ *  @shared: map has RAM_SHARED flag.
+ *  @is_pmem: map has RAM_PMEM flag.
+ *
+ * Return:
+ *  On success, return a pointer to the mapped area.
+ *  On failure, return MAP_FAILED.
+ */
+void *qemu_ram_mmap(int fd,
+                    size_t size,
+                    size_t align,
+                    bool shared,
+                    bool is_pmem);

 void qemu_ram_munmap(int fd, void *ptr, size_t size);

@@ -681,15 +681,15 @@ ObjectClass *cpu_class_by_name(const char *typename, const char *cpu_model);
 CPUState *cpu_create(const char *typename);

 /**
- * parse_cpu_model:
- * @cpu_model: The model string including optional parameters.
+ * parse_cpu_option:
+ * @cpu_option: The -cpu option including optional parameters.
 *
 * processes optional parameters and registers them as global properties
 *
 * Returns: type of CPU to create or prints error and terminates process
 *          if an error occurred.
 */
-const char *parse_cpu_model(const char *cpu_model);
+const char *parse_cpu_option(const char *cpu_option);

 /**
 * cpu_has_work:
@@ -0,0 +1,4 @@
+#include <asm-generic/mman.h>
+
+#define arch_mmap_check(addr, len, flags) \
+	(((flags) & MAP_FIXED && (addr) < FIRST_USER_ADDRESS) ? -EINVAL : 0)
@@ -0,0 +1 @@
+#include <asm-generic/mman.h>
@@ -0,0 +1,36 @@
+#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_
+#define _ASM_GENERIC_HUGETLB_ENCODE_H_
+
+/*
+ * Several system calls take a flag to request "hugetlb" huge pages.
+ * Without further specification, these system calls will use the
+ * system's default huge page size.  If a system supports multiple
+ * huge page sizes, the desired huge page size can be specified in
+ * bits [26:31] of the flag arguments.  The value in these 6 bits
+ * will encode the log2 of the huge page size.
+ *
+ * The following definitions are associated with this huge page size
+ * encoding in flag arguments.  System call specific header files
+ * that use this encoding should include this file.  They can then
+ * provide definitions based on these with their own specific prefix.
+ * for example:
+ * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+ */
+
+#define HUGETLB_FLAG_ENCODE_SHIFT	26
+#define HUGETLB_FLAG_ENCODE_MASK	0x3f
+
+#define HUGETLB_FLAG_ENCODE_64KB	(16 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB	(19 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB		(20 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB		(21 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB		(23 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB	(24 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_32MB	(25 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB	(28 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512MB	(29 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB		(30 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB		(31 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB	(34 << HUGETLB_FLAG_ENCODE_SHIFT)
+
+#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_H
+#define __ASM_GENERIC_MMAN_COMMON_H
+
+/*
+ Author: Michael S. Tsirkin <mst@mellanox.co.il>, Mellanox Technologies Ltd.
+ Based on: asm-xxx/mman.h
+*/
+
+#define PROT_READ	0x1		/* page can be read */
+#define PROT_WRITE	0x2		/* page can be written */
+#define PROT_EXEC	0x4		/* page can be executed */
+#define PROT_SEM	0x8		/* page may be used for atomic ops */
+#define PROT_NONE	0x0		/* page can not be accessed */
+#define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
+#define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
+
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+#define MAP_TYPE	0x0f		/* Mask for type of mapping */
+#define MAP_FIXED	0x10		/* Interpret addr exactly */
+#define MAP_ANONYMOUS	0x20		/* don't use a file */
+#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
+# define MAP_UNINITIALIZED 0x4000000	/* For anonymous mmap, memory could be uninitialized */
+#else
+# define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
+#endif
+
+/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */
+#define MAP_FIXED_NOREPLACE	0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
+
+#define MS_ASYNC	1		/* sync memory asynchronously */
+#define MS_INVALIDATE	2		/* invalidate the caches */
+#define MS_SYNC		4		/* synchronous memory sync */
+
+#define MADV_NORMAL	0		/* no further special treatment */
+#define MADV_RANDOM	1		/* expect random page references */
+#define MADV_SEQUENTIAL	2		/* expect sequential page references */
+#define MADV_WILLNEED	3		/* will need these pages */
+#define MADV_DONTNEED	4		/* don't need these pages */
+
+/* common parameters: try to keep these consistent across architectures */
+#define MADV_FREE	8		/* free pages only if memory pressure */
+#define MADV_REMOVE	9		/* remove these pages & resources */
+#define MADV_DONTFORK	10		/* don't inherit across fork */
+#define MADV_DOFORK	11		/* do inherit across fork */
+#define MADV_HWPOISON	100		/* poison a page for testing */
+#define MADV_SOFT_OFFLINE 101		/* soft offline page for testing */
+
+#define MADV_MERGEABLE   12		/* KSM may merge identical pages */
+#define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */
+
+#define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
+#define MADV_NOHUGEPAGE	15		/* Not worth backing with hugepages */
+
+#define MADV_DONTDUMP   16		/* Explicity exclude from the core dump,
+					   overrides the coredump filter bits */
+#define MADV_DODUMP	17		/* Clear the MADV_DONTDUMP flag */
+
+#define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
+
+/* compatibility flags */
+#define MAP_FILE	0
+
+#define PKEY_DISABLE_ACCESS	0x1
+#define PKEY_DISABLE_WRITE	0x2
+#define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
+				 PKEY_DISABLE_WRITE)
+
+#endif /* __ASM_GENERIC_MMAN_COMMON_H */
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_H
+#define __ASM_GENERIC_MMAN_H
+
+#include <asm-generic/mman-common.h>
+
+#define MAP_GROWSDOWN	0x0100		/* stack-like segment */
+#define MAP_DENYWRITE	0x0800		/* ETXTBSY */
+#define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
+#define MAP_LOCKED	0x2000		/* pages are locked */
+#define MAP_NORESERVE	0x4000		/* don't check for reservations */
+#define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
+#define MAP_NONBLOCK	0x10000		/* do not block on IO */
+#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
+#define MAP_HUGETLB	0x40000		/* create a huge page mapping */
+#define MAP_SYNC	0x80000		/* perform synchronous page faults for the mapping */
+
+/* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
+
+#define MCL_CURRENT	1		/* lock all current mappings */
+#define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+#endif /* __ASM_GENERIC_MMAN_H */
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1995, 1999, 2002 by Ralf Baechle
+ */
+#ifndef _ASM_MMAN_H
+#define _ASM_MMAN_H
+
+/*
+ * Protections are chosen from these bits, OR'd together.  The
+ * implementation does not necessarily support PROT_EXEC or PROT_WRITE
+ * without PROT_READ.  The only guarantees are that no writing will be
+ * allowed without PROT_WRITE and no access will be allowed for PROT_NONE.
+ */
+#define PROT_NONE	0x00		/* page can not be accessed */
+#define PROT_READ	0x01		/* page can be read */
+#define PROT_WRITE	0x02		/* page can be written */
+#define PROT_EXEC	0x04		/* page can be executed */
+/*			0x08		   reserved for PROT_EXEC_NOFLUSH */
+#define PROT_SEM	0x10		/* page may be used for atomic ops */
+#define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
+#define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
+
+/*
+ * Flags for mmap
+ */
+#define MAP_SHARED	0x001		/* Share changes */
+#define MAP_PRIVATE	0x002		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x003	/* share + validate extension flags */
+#define MAP_TYPE	0x00f		/* Mask for type of mapping */
+#define MAP_FIXED	0x010		/* Interpret addr exactly */
+
+/* not used by linux, but here to make sure we don't clash with ABI defines */
+#define MAP_RENAME	0x020		/* Assign page to file */
+#define MAP_AUTOGROW	0x040		/* File may grow by writing */
+#define MAP_LOCAL	0x080		/* Copy on fork/sproc */
+#define MAP_AUTORSRV	0x100		/* Logical swap reserved on demand */
+
+/* These are linux-specific */
+#define MAP_NORESERVE	0x0400		/* don't check for reservations */
+#define MAP_ANONYMOUS	0x0800		/* don't use a file */
+#define MAP_GROWSDOWN	0x1000		/* stack-like segment */
+#define MAP_DENYWRITE	0x2000		/* ETXTBSY */
+#define MAP_EXECUTABLE	0x4000		/* mark it as an executable */
+#define MAP_LOCKED	0x8000		/* pages are locked */
+#define MAP_POPULATE	0x10000		/* populate (prefault) pagetables */
+#define MAP_NONBLOCK	0x20000		/* do not block on IO */
+#define MAP_STACK	0x40000		/* give out an address that is best suited for process/thread stacks */
+#define MAP_HUGETLB	0x80000		/* create a huge page mapping */
+#define MAP_FIXED_NOREPLACE 0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
+
+/*
+ * Flags for msync
+ */
+#define MS_ASYNC	0x0001		/* sync memory asynchronously */
+#define MS_INVALIDATE	0x0002		/* invalidate mappings & caches */
+#define MS_SYNC		0x0004		/* synchronous memory sync */
+
+/*
+ * Flags for mlockall
+ */
+#define MCL_CURRENT	1		/* lock all current mappings */
+#define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
+
+#define MADV_NORMAL	0		/* no further special treatment */
+#define MADV_RANDOM	1		/* expect random page references */
+#define MADV_SEQUENTIAL 2		/* expect sequential page references */
+#define MADV_WILLNEED	3		/* will need these pages */
+#define MADV_DONTNEED	4		/* don't need these pages */
+
+/* common parameters: try to keep these consistent across architectures */
+#define MADV_FREE	8		/* free pages only if memory pressure */
+#define MADV_REMOVE	9		/* remove these pages & resources */
+#define MADV_DONTFORK	10		/* don't inherit across fork */
+#define MADV_DOFORK	11		/* do inherit across fork */
+
+#define MADV_MERGEABLE	 12		/* KSM may merge identical pages */
+#define MADV_UNMERGEABLE 13		/* KSM may not merge identical pages */
+#define MADV_HWPOISON	 100		/* poison a page for testing */
+
+#define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
+#define MADV_NOHUGEPAGE 15		/* Not worth backing with hugepages */
+
+#define MADV_DONTDUMP	16		/* Explicity exclude from the core dump,
+					   overrides the coredump filter bits */
+#define MADV_DODUMP	17		/* Clear the MADV_NODUMP flag */
+
+#define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
+
+/* compatibility flags */
+#define MAP_FILE	0
+
+#define PKEY_DISABLE_ACCESS	0x1
+#define PKEY_DISABLE_WRITE	0x2
+#define PKEY_ACCESS_MASK	(PKEY_DISABLE_ACCESS |\
+				 PKEY_DISABLE_WRITE)
+
+#endif /* _ASM_MMAN_H */
--- a/Show More
+++ b/Show More