* [Qemu-devel] [PULL 01/38] intel_iommu: Add support for translation for devices behind bridges
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 02/38] exec: factor out duplicate mmap code Michael S. Tsirkin
` (37 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Richard Henderson, Knut Omang, Eduardo Habkost,
Paolo Bonzini
From: Knut Omang <knut.omang@oracle.com>
- Use a hash table indexed on bus pointers to store information about buses
instead of using the bus numbers.
Bus pointers are stored in a new VTDBus struct together with the vector
of device address space pointers indexed by devfn.
- The bus number is still used for lookup for selective SID based invalidate,
in which case the bus number is lazily resolved from the bus hash table and
cached in a separate index.
Signed-off-by: Knut Omang <knut.omang@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/hw/i386/intel_iommu.h | 16 +++++++-
hw/i386/intel_iommu.c | 89 +++++++++++++++++++++++++++++++++++--------
hw/pci-host/q35.c | 25 ++----------
3 files changed, 90 insertions(+), 40 deletions(-)
diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
index e321ee4..5dbadb7 100644
--- a/include/hw/i386/intel_iommu.h
+++ b/include/hw/i386/intel_iommu.h
@@ -49,6 +49,7 @@ typedef struct VTDContextCacheEntry VTDContextCacheEntry;
typedef struct IntelIOMMUState IntelIOMMUState;
typedef struct VTDAddressSpace VTDAddressSpace;
typedef struct VTDIOTLBEntry VTDIOTLBEntry;
+typedef struct VTDBus VTDBus;
/* Context-Entry */
struct VTDContextEntry {
@@ -65,7 +66,7 @@ struct VTDContextCacheEntry {
};
struct VTDAddressSpace {
- uint8_t bus_num;
+ PCIBus *bus;
uint8_t devfn;
AddressSpace as;
MemoryRegion iommu;
@@ -73,6 +74,11 @@ struct VTDAddressSpace {
VTDContextCacheEntry context_cache_entry;
};
+struct VTDBus {
+ PCIBus* bus; /* A reference to the bus to provide translation for */
+ VTDAddressSpace *dev_as[0]; /* A table of VTDAddressSpace objects indexed by devfn */
+};
+
struct VTDIOTLBEntry {
uint64_t gfn;
uint16_t domain_id;
@@ -114,7 +120,13 @@ struct IntelIOMMUState {
GHashTable *iotlb; /* IOTLB */
MemoryRegionIOMMUOps iommu_ops;
- VTDAddressSpace **address_spaces[VTD_PCI_BUS_MAX];
+ GHashTable *vtd_as_by_busptr; /* VTDBus objects indexed by PCIBus* reference */
+ VTDBus *vtd_as_by_bus_num[VTD_PCI_BUS_MAX]; /* VTDBus objects indexed by bus number */
};
+/* Find the VTD Address space associated with the given bus pointer,
+ * create a new one if none exists
+ */
+VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, int devfn);
+
#endif
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 08055a8..3fe27fa 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -22,6 +22,7 @@
#include "hw/sysbus.h"
#include "exec/address-spaces.h"
#include "intel_iommu_internal.h"
+#include "hw/pci/pci.h"
/*#define DEBUG_INTEL_IOMMU*/
#ifdef DEBUG_INTEL_IOMMU
@@ -166,19 +167,17 @@ static gboolean vtd_hash_remove_by_page(gpointer key, gpointer value,
*/
static void vtd_reset_context_cache(IntelIOMMUState *s)
{
- VTDAddressSpace **pvtd_as;
VTDAddressSpace *vtd_as;
- uint32_t bus_it;
+ VTDBus *vtd_bus;
+ GHashTableIter bus_it;
uint32_t devfn_it;
+ g_hash_table_iter_init(&bus_it, s->vtd_as_by_busptr);
+
VTD_DPRINTF(CACHE, "global context_cache_gen=1");
- for (bus_it = 0; bus_it < VTD_PCI_BUS_MAX; ++bus_it) {
- pvtd_as = s->address_spaces[bus_it];
- if (!pvtd_as) {
- continue;
- }
+ while (g_hash_table_iter_next (&bus_it, NULL, (void**)&vtd_bus)) {
for (devfn_it = 0; devfn_it < VTD_PCI_DEVFN_MAX; ++devfn_it) {
- vtd_as = pvtd_as[devfn_it];
+ vtd_as = vtd_bus->dev_as[devfn_it];
if (!vtd_as) {
continue;
}
@@ -754,12 +753,13 @@ static inline bool vtd_is_interrupt_addr(hwaddr addr)
* @is_write: The access is a write operation
* @entry: IOMMUTLBEntry that contain the addr to be translated and result
*/
-static void vtd_do_iommu_translate(VTDAddressSpace *vtd_as, uint8_t bus_num,
+static void vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
uint8_t devfn, hwaddr addr, bool is_write,
IOMMUTLBEntry *entry)
{
IntelIOMMUState *s = vtd_as->iommu_state;
VTDContextEntry ce;
+ uint8_t bus_num = pci_bus_num(bus);
VTDContextCacheEntry *cc_entry = &vtd_as->context_cache_entry;
uint64_t slpte;
uint32_t level;
@@ -874,6 +874,29 @@ static void vtd_context_global_invalidate(IntelIOMMUState *s)
}
}
+
+/* Find the VTD address space currently associated with a given bus number,
+ */
+static VTDBus *vtd_find_as_from_bus_num(IntelIOMMUState *s, uint8_t bus_num)
+{
+ VTDBus *vtd_bus = s->vtd_as_by_bus_num[bus_num];
+ if (!vtd_bus) {
+ /* Iterate over the registered buses to find the one
+ * which currently hold this bus number, and update the bus_num lookup table:
+ */
+ GHashTableIter iter;
+
+ g_hash_table_iter_init(&iter, s->vtd_as_by_busptr);
+ while (g_hash_table_iter_next (&iter, NULL, (void**)&vtd_bus)) {
+ if (pci_bus_num(vtd_bus->bus) == bus_num) {
+ s->vtd_as_by_bus_num[bus_num] = vtd_bus;
+ return vtd_bus;
+ }
+ }
+ }
+ return vtd_bus;
+}
+
/* Do a context-cache device-selective invalidation.
* @func_mask: FM field after shifting
*/
@@ -882,7 +905,7 @@ static void vtd_context_device_invalidate(IntelIOMMUState *s,
uint16_t func_mask)
{
uint16_t mask;
- VTDAddressSpace **pvtd_as;
+ VTDBus *vtd_bus;
VTDAddressSpace *vtd_as;
uint16_t devfn;
uint16_t devfn_it;
@@ -903,11 +926,11 @@ static void vtd_context_device_invalidate(IntelIOMMUState *s,
}
VTD_DPRINTF(INV, "device-selective invalidation source 0x%"PRIx16
" mask %"PRIu16, source_id, mask);
- pvtd_as = s->address_spaces[VTD_SID_TO_BUS(source_id)];
- if (pvtd_as) {
+ vtd_bus = vtd_find_as_from_bus_num(s, VTD_SID_TO_BUS(source_id));
+ if (vtd_bus) {
devfn = VTD_SID_TO_DEVFN(source_id);
for (devfn_it = 0; devfn_it < VTD_PCI_DEVFN_MAX; ++devfn_it) {
- vtd_as = pvtd_as[devfn_it];
+ vtd_as = vtd_bus->dev_as[devfn_it];
if (vtd_as && ((devfn_it & mask) == (devfn & mask))) {
VTD_DPRINTF(INV, "invalidate context-cahce of devfn 0x%"PRIx16,
devfn_it);
@@ -1805,11 +1828,11 @@ static IOMMUTLBEntry vtd_iommu_translate(MemoryRegion *iommu, hwaddr addr,
return ret;
}
- vtd_do_iommu_translate(vtd_as, vtd_as->bus_num, vtd_as->devfn, addr,
+ vtd_do_iommu_translate(vtd_as, vtd_as->bus, vtd_as->devfn, addr,
is_write, &ret);
VTD_DPRINTF(MMU,
"bus %"PRIu8 " slot %"PRIu8 " func %"PRIu8 " devfn %"PRIu8
- " gpa 0x%"PRIx64 " hpa 0x%"PRIx64, vtd_as->bus_num,
+ " gpa 0x%"PRIx64 " hpa 0x%"PRIx64, pci_bus_num(vtd_as->bus),
VTD_PCI_SLOT(vtd_as->devfn), VTD_PCI_FUNC(vtd_as->devfn),
vtd_as->devfn, addr, ret.translated_addr);
return ret;
@@ -1839,6 +1862,38 @@ static Property vtd_properties[] = {
DEFINE_PROP_END_OF_LIST(),
};
+
+VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, int devfn)
+{
+ uintptr_t key = (uintptr_t)bus;
+ VTDBus *vtd_bus = g_hash_table_lookup(s->vtd_as_by_busptr, &key);
+ VTDAddressSpace *vtd_dev_as;
+
+ if (!vtd_bus) {
+ /* No corresponding free() */
+ vtd_bus = g_malloc0(sizeof(VTDBus) + sizeof(VTDAddressSpace *) * VTD_PCI_DEVFN_MAX);
+ vtd_bus->bus = bus;
+ key = (uintptr_t)bus;
+ g_hash_table_insert(s->vtd_as_by_busptr, &key, vtd_bus);
+ }
+
+ vtd_dev_as = vtd_bus->dev_as[devfn];
+
+ if (!vtd_dev_as) {
+ vtd_bus->dev_as[devfn] = vtd_dev_as = g_malloc0(sizeof(VTDAddressSpace));
+
+ vtd_dev_as->bus = bus;
+ vtd_dev_as->devfn = (uint8_t)devfn;
+ vtd_dev_as->iommu_state = s;
+ vtd_dev_as->context_cache_entry.context_cache_gen = 0;
+ memory_region_init_iommu(&vtd_dev_as->iommu, OBJECT(s),
+ &s->iommu_ops, "intel_iommu", UINT64_MAX);
+ address_space_init(&vtd_dev_as->as,
+ &vtd_dev_as->iommu, "intel_iommu");
+ }
+ return vtd_dev_as;
+}
+
/* Do the initialization. It will also be called when reset, so pay
* attention when adding new initialization stuff.
*/
@@ -1931,13 +1986,15 @@ static void vtd_realize(DeviceState *dev, Error **errp)
IntelIOMMUState *s = INTEL_IOMMU_DEVICE(dev);
VTD_DPRINTF(GENERAL, "");
- memset(s->address_spaces, 0, sizeof(s->address_spaces));
+ memset(s->vtd_as_by_bus_num, 0, sizeof(s->vtd_as_by_bus_num));
memory_region_init_io(&s->csrmem, OBJECT(s), &vtd_mem_ops, s,
"intel_iommu", DMAR_REG_SIZE);
sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->csrmem);
/* No corresponding destroy */
s->iotlb = g_hash_table_new_full(vtd_uint64_hash, vtd_uint64_equal,
g_free, g_free);
+ s->vtd_as_by_busptr = g_hash_table_new_full(vtd_uint64_hash, vtd_uint64_equal,
+ g_free, g_free);
vtd_init(s);
}
diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c
index bd74094..c81507d 100644
--- a/hw/pci-host/q35.c
+++ b/hw/pci-host/q35.c
@@ -426,31 +426,12 @@ static void mch_reset(DeviceState *qdev)
static AddressSpace *q35_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
{
IntelIOMMUState *s = opaque;
- VTDAddressSpace **pvtd_as;
- int bus_num = pci_bus_num(bus);
+ VTDAddressSpace *vtd_as;
- assert(0 <= bus_num && bus_num <= VTD_PCI_BUS_MAX);
assert(0 <= devfn && devfn <= VTD_PCI_DEVFN_MAX);
- pvtd_as = s->address_spaces[bus_num];
- if (!pvtd_as) {
- /* No corresponding free() */
- pvtd_as = g_malloc0(sizeof(VTDAddressSpace *) * VTD_PCI_DEVFN_MAX);
- s->address_spaces[bus_num] = pvtd_as;
- }
- if (!pvtd_as[devfn]) {
- pvtd_as[devfn] = g_malloc0(sizeof(VTDAddressSpace));
-
- pvtd_as[devfn]->bus_num = (uint8_t)bus_num;
- pvtd_as[devfn]->devfn = (uint8_t)devfn;
- pvtd_as[devfn]->iommu_state = s;
- pvtd_as[devfn]->context_cache_entry.context_cache_gen = 0;
- memory_region_init_iommu(&pvtd_as[devfn]->iommu, OBJECT(s),
- &s->iommu_ops, "intel_iommu", UINT64_MAX);
- address_space_init(&pvtd_as[devfn]->as,
- &pvtd_as[devfn]->iommu, "intel_iommu");
- }
- return &pvtd_as[devfn]->as;
+ vtd_as = vtd_find_add_as(s, bus, devfn);
+ return &vtd_as->as;
}
static void mch_init_dmar(MCHPCIState *mch)
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 02/38] exec: factor out duplicate mmap code
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 01/38] intel_iommu: Add support for translation for devices behind bridges Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 03/38] net: don't set native endianness Michael S. Tsirkin
` (36 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Thibaut Collet, Paolo Bonzini
Anonymous and file-backed RAM allocation are now almost exactly the same.
Reduce code duplication by moving RAM mmap code out of oslib-posix.c and
exec.c.
Reported-by: Marc-André Lureau <mlureau@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/qemu/mmap-alloc.h | 10 +++++++
exec.c | 47 +++++++------------------------
util/mmap-alloc.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++
util/oslib-posix.c | 28 +++----------------
util/Makefile.objs | 1 +
5 files changed, 96 insertions(+), 61 deletions(-)
create mode 100644 include/qemu/mmap-alloc.h
create mode 100644 util/mmap-alloc.c
diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h
new file mode 100644
index 0000000..56388e6
--- /dev/null
+++ b/include/qemu/mmap-alloc.h
@@ -0,0 +1,10 @@
+#ifndef QEMU_MMAP_ALLOC
+#define QEMU_MMAP_ALLOC
+
+#include "qemu-common.h"
+
+void *qemu_ram_mmap(int fd, size_t size, size_t align, bool shared);
+
+void qemu_ram_munmap(void *ptr, size_t size);
+
+#endif
diff --git a/exec.c b/exec.c
index 7d90a52..4505dc7 100644
--- a/exec.c
+++ b/exec.c
@@ -55,6 +55,9 @@
#include "exec/ram_addr.h"
#include "qemu/range.h"
+#ifndef _WIN32
+#include "qemu/mmap-alloc.h"
+#endif
//#define DEBUG_SUBPAGE
@@ -84,9 +87,9 @@ static MemoryRegion io_mem_unassigned;
*/
#define RAM_RESIZEABLE (1 << 2)
-/* An extra page is mapped on top of this RAM.
+/* RAM is backed by an mmapped file.
*/
-#define RAM_EXTRA (1 << 3)
+#define RAM_FILE (1 << 3)
#endif
struct CPUTailQ cpus = QTAILQ_HEAD_INITIALIZER(cpus);
@@ -1188,13 +1191,10 @@ static void *file_ram_alloc(RAMBlock *block,
char *filename;
char *sanitized_name;
char *c;
- void *ptr;
- void *area = NULL;
+ void *area;
int fd;
uint64_t hpagesize;
- uint64_t total;
Error *local_err = NULL;
- size_t offset;
hpagesize = gethugepagesize(path, &local_err);
if (local_err) {
@@ -1238,7 +1238,6 @@ static void *file_ram_alloc(RAMBlock *block,
g_free(filename);
memory = ROUND_UP(memory, hpagesize);
- total = memory + hpagesize;
/*
* ftruncate is not supported by hugetlbfs in older
@@ -1250,40 +1249,14 @@ static void *file_ram_alloc(RAMBlock *block,
perror("ftruncate");
}
- ptr = mmap(0, total, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS,
- -1, 0);
- if (ptr == MAP_FAILED) {
- error_setg_errno(errp, errno,
- "unable to allocate memory range for hugepages");
- close(fd);
- goto error;
- }
-
- offset = QEMU_ALIGN_UP((uintptr_t)ptr, hpagesize) - (uintptr_t)ptr;
-
- area = mmap(ptr + offset, memory, PROT_READ | PROT_WRITE,
- (block->flags & RAM_SHARED ? MAP_SHARED : MAP_PRIVATE) |
- MAP_FIXED,
- fd, 0);
+ area = qemu_ram_mmap(fd, memory, hpagesize, block->flags & RAM_SHARED);
if (area == MAP_FAILED) {
error_setg_errno(errp, errno,
"unable to map backing store for hugepages");
- munmap(ptr, total);
close(fd);
goto error;
}
- if (offset > 0) {
- munmap(ptr, offset);
- }
- ptr += offset;
- total -= offset;
-
- if (total > memory + getpagesize()) {
- munmap(ptr + memory + getpagesize(),
- total - memory - getpagesize());
- }
-
if (mem_prealloc) {
os_mem_prealloc(fd, area, memory);
}
@@ -1601,7 +1574,7 @@ ram_addr_t qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
new_block->used_length = size;
new_block->max_length = size;
new_block->flags = share ? RAM_SHARED : 0;
- new_block->flags |= RAM_EXTRA;
+ new_block->flags |= RAM_FILE;
new_block->host = file_ram_alloc(new_block, size,
mem_path, errp);
if (!new_block->host) {
@@ -1703,8 +1676,8 @@ static void reclaim_ramblock(RAMBlock *block)
xen_invalidate_map_cache_entry(block->host);
#ifndef _WIN32
} else if (block->fd >= 0) {
- if (block->flags & RAM_EXTRA) {
- munmap(block->host, block->max_length + getpagesize());
+ if (block->flags & RAM_FILE) {
+ qemu_ram_munmap(block->host, block->max_length);
} else {
munmap(block->host, block->max_length);
}
diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
new file mode 100644
index 0000000..1394269
--- /dev/null
+++ b/util/mmap-alloc.c
@@ -0,0 +1,71 @@
+/*
+ * Support for RAM backed by mmaped host memory.
+ *
+ * Copyright (c) 2015 Red Hat, Inc.
+ *
+ * Authors:
+ * Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later. See the COPYING file in the top-level directory.
+ */
+#include <qemu/mmap-alloc.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <assert.h>
+
+void *qemu_ram_mmap(int fd, size_t size, size_t align, bool shared)
+{
+ /*
+ * Note: this always allocates at least one extra page of virtual address
+ * space, even if size is already aligned.
+ */
+ size_t total = size + align;
+ void *ptr = mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ size_t offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;
+ void *ptr1;
+
+ if (ptr == MAP_FAILED) {
+ return NULL;
+ }
+
+ /* Make sure align is a power of 2 */
+ assert(!(align & (align - 1)));
+ /* Always align to host page size */
+ assert(align >= getpagesize());
+
+ ptr1 = mmap(ptr + offset, size, PROT_READ | PROT_WRITE,
+ MAP_FIXED |
+ (fd == -1 ? MAP_ANONYMOUS : 0) |
+ (shared ? MAP_SHARED : MAP_PRIVATE),
+ fd, 0);
+ if (ptr1 == MAP_FAILED) {
+ munmap(ptr, total);
+ return NULL;
+ }
+
+ ptr += offset;
+ total -= offset;
+
+ if (offset > 0) {
+ munmap(ptr - offset, offset);
+ }
+
+ /*
+ * Leave a single PROT_NONE page allocated after the RAM block, to serve as
+ * a guard page guarding against potential buffer overflows.
+ */
+ if (total > size + getpagesize()) {
+ munmap(ptr + size + getpagesize(), total - size - getpagesize());
+ }
+
+ return ptr;
+}
+
+void qemu_ram_munmap(void *ptr, size_t size)
+{
+ if (ptr) {
+ /* Unmap both the RAM block and the guard page */
+ munmap(ptr, size + getpagesize());
+ }
+}
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index a0fcdc2..892d2d8 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -72,6 +72,8 @@ extern int daemon(int, int);
#include <sys/sysctl.h>
#endif
+#include <qemu/mmap-alloc.h>
+
int qemu_get_thread_id(void)
{
#if defined(__linux__)
@@ -128,10 +130,7 @@ void *qemu_memalign(size_t alignment, size_t size)
void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment)
{
size_t align = QEMU_VMALLOC_ALIGN;
- size_t total = size + align;
- void *ptr = mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
- size_t offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;
- void *ptr1;
+ void *ptr = qemu_ram_mmap(-1, size, align, false);
if (ptr == MAP_FAILED) {
return NULL;
@@ -141,23 +140,6 @@ void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment)
*alignment = align;
}
- ptr1 = mmap(ptr + offset, size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
- if (ptr1 == MAP_FAILED) {
- munmap(ptr, total);
- return NULL;
- }
-
- ptr += offset;
- total -= offset;
-
- if (offset > 0) {
- munmap(ptr - offset, offset);
- }
- if (total > size + getpagesize()) {
- munmap(ptr + size + getpagesize(), total - size - getpagesize());
- }
-
trace_qemu_anon_ram_alloc(size, ptr);
return ptr;
}
@@ -171,9 +153,7 @@ void qemu_vfree(void *ptr)
void qemu_anon_ram_free(void *ptr, size_t size)
{
trace_qemu_anon_ram_free(ptr, size);
- if (ptr) {
- munmap(ptr, size + getpagesize());
- }
+ qemu_ram_munmap(ptr, size);
}
void qemu_set_block(int fd)
diff --git a/util/Makefile.objs b/util/Makefile.objs
index 114d657..f011b81 100644
--- a/util/Makefile.objs
+++ b/util/Makefile.objs
@@ -1,6 +1,7 @@
util-obj-y = osdep.o cutils.o unicode.o qemu-timer-common.o
util-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o event_notifier-win32.o
util-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o event_notifier-posix.o qemu-openpty.o
+util-obj-$(CONFIG_POSIX) += mmap-alloc.o
util-obj-y += envlist.o path.o module.o
util-obj-$(call lnot,$(CONFIG_INT128)) += host-utils.o
util-obj-y += bitmap.o bitops.o hbitmap.o
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 03/38] net: don't set native endianness
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 01/38] intel_iommu: Add support for translation for devices behind bridges Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 02/38] exec: factor out duplicate mmap code Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 04/38] tests: re-enable vhost-user-test Michael S. Tsirkin
` (35 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel
Cc: Marcel Apfelbaum, Peter Maydell, Jason Wang, qemu-stable, Greg Kurz
commit 5be7d9f1b1452613b95c6ba70b8d7ad3d0797991
vhost-net: tell tap backend about the vnet endianness
makes vhost net always try to set LE - even if that matches the
native endian-ness.
This makes it fail on older kernels on x86 without TUNSETVNETLE support.
To fix, make qemu_set_vnet_le/qemu_set_vnet_be skip the
ioctl if it matches the host endian-ness.
Reported-by: Marcel Apfelbaum <marcel@redhat.com>
Cc: Greg Kurz <gkurz@linux.vnet.ibm.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
---
net/net.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/net/net.c b/net/net.c
index 39af893..3c68f3f 100644
--- a/net/net.c
+++ b/net/net.c
@@ -524,20 +524,28 @@ void qemu_set_vnet_hdr_len(NetClientState *nc, int len)
int qemu_set_vnet_le(NetClientState *nc, bool is_le)
{
+#ifdef HOST_WORDS_BIGENDIAN
if (!nc || !nc->info->set_vnet_le) {
return -ENOSYS;
}
return nc->info->set_vnet_le(nc, is_le);
+#else
+ return 0;
+#endif
}
int qemu_set_vnet_be(NetClientState *nc, bool is_be)
{
+#ifdef HOST_WORDS_BIGENDIAN
+ return 0;
+#else
if (!nc || !nc->info->set_vnet_be) {
return -ENOSYS;
}
return nc->info->set_vnet_be(nc, is_be);
+#endif
}
int qemu_can_send_packet(NetClientState *sender)
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 04/38] tests: re-enable vhost-user-test
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (2 preceding siblings ...)
2015-10-21 10:26 ` [Qemu-devel] [PULL 03/38] net: don't set native endianness Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-22 11:36 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 05/38] vhost: add vhost_has_free_slot() interface Michael S. Tsirkin
` (34 subsequent siblings)
38 siblings, 1 reply; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Michael Tokarev, Markus Armbruster, Gerd Hoffmann,
Stefan Hajnoczi, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Paolo Bonzini
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Commit 7fe34ca9c2e actually disabled vhost-user-test altogether,
since CONFIG_VHOST_NET is a per-target config variable.
tests/vhost-user-test is already x86/64 softmmu specific test, in order
to enable it correctly, kvm & vhost-net are also conditions. To check
that, set CONFIG_VHOST_NET_TEST when kvm is also enabled.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
configure | 1 +
tests/Makefile | 4 +---
2 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/configure b/configure
index f08327e..9eec860 100755
--- a/configure
+++ b/configure
@@ -5562,6 +5562,7 @@ case "$target_name" in
echo "CONFIG_KVM=y" >> $config_target_mak
if test "$vhost_net" = "yes" ; then
echo "CONFIG_VHOST_NET=y" >> $config_target_mak
+ echo "CONFIG_VHOST_NET_TEST=y" >> $config_host_mak
fi
fi
esac
diff --git a/tests/Makefile b/tests/Makefile
index cb221de..d69e097 100644
--- a/tests/Makefile
+++ b/tests/Makefile
@@ -191,9 +191,7 @@ gcov-files-i386-y += hw/usb/hcd-xhci.c
check-qtest-i386-y += tests/pc-cpu-test$(EXESUF)
check-qtest-i386-y += tests/q35-test$(EXESUF)
gcov-files-i386-y += hw/pci-host/q35.c
-ifeq ($(CONFIG_VHOST_NET),y)
-check-qtest-i386-$(CONFIG_LINUX) += tests/vhost-user-test$(EXESUF)
-endif
+check-qtest-i386-$(CONFIG_VHOST_NET_TEST) += tests/vhost-user-test$(EXESUF)
check-qtest-i386-y += tests/test-netfilter$(EXESUF)
check-qtest-x86_64-y = $(check-qtest-i386-y)
gcov-files-i386-y += i386-softmmu/hw/timer/mc146818rtc.c
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* Re: [Qemu-devel] [PULL 04/38] tests: re-enable vhost-user-test
2015-10-21 10:26 ` [Qemu-devel] [PULL 04/38] tests: re-enable vhost-user-test Michael S. Tsirkin
@ 2015-10-22 11:36 ` Michael S. Tsirkin
0 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-22 11:36 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Michael Tokarev, Markus Armbruster, Gerd Hoffmann,
Stefan Hajnoczi, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Paolo Bonzini
On Wed, Oct 21, 2015 at 01:26:36PM +0300, Michael S. Tsirkin wrote:
> From: Marc-André Lureau <marcandre.lureau@redhat.com>
>
> Commit 7fe34ca9c2e actually disabled vhost-user-test altogether,
> since CONFIG_VHOST_NET is a per-target config variable.
>
> tests/vhost-user-test is already x86/64 softmmu specific test, in order
> to enable it correctly, kvm & vhost-net are also conditions. To check
> that, set CONFIG_VHOST_NET_TEST when kvm is also enabled.
>
> Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
> Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
I dropped this one since it still breaks on some setups.
Marc-André, pls work to re-enable this upstream
when you are back.
> ---
> configure | 1 +
> tests/Makefile | 4 +---
> 2 files changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/configure b/configure
> index f08327e..9eec860 100755
> --- a/configure
> +++ b/configure
> @@ -5562,6 +5562,7 @@ case "$target_name" in
> echo "CONFIG_KVM=y" >> $config_target_mak
> if test "$vhost_net" = "yes" ; then
> echo "CONFIG_VHOST_NET=y" >> $config_target_mak
> + echo "CONFIG_VHOST_NET_TEST=y" >> $config_host_mak
> fi
> fi
> esac
> diff --git a/tests/Makefile b/tests/Makefile
> index cb221de..d69e097 100644
> --- a/tests/Makefile
> +++ b/tests/Makefile
> @@ -191,9 +191,7 @@ gcov-files-i386-y += hw/usb/hcd-xhci.c
> check-qtest-i386-y += tests/pc-cpu-test$(EXESUF)
> check-qtest-i386-y += tests/q35-test$(EXESUF)
> gcov-files-i386-y += hw/pci-host/q35.c
> -ifeq ($(CONFIG_VHOST_NET),y)
> -check-qtest-i386-$(CONFIG_LINUX) += tests/vhost-user-test$(EXESUF)
> -endif
> +check-qtest-i386-$(CONFIG_VHOST_NET_TEST) += tests/vhost-user-test$(EXESUF)
> check-qtest-i386-y += tests/test-netfilter$(EXESUF)
> check-qtest-x86_64-y = $(check-qtest-i386-y)
> gcov-files-i386-y += i386-softmmu/hw/timer/mc146818rtc.c
> --
> MST
>
^ permalink raw reply [flat|nested] 45+ messages in thread
* [Qemu-devel] [PULL 05/38] vhost: add vhost_has_free_slot() interface
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (3 preceding siblings ...)
2015-10-21 10:26 ` [Qemu-devel] [PULL 04/38] tests: re-enable vhost-user-test Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 06/38] pc-dimm: add vhost slots limit check before commiting to hotplug Michael S. Tsirkin
` (33 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel; +Cc: Peter Maydell, Igor Mammedov
From: Igor Mammedov <imammedo@redhat.com>
it will allow for other parts of QEMU check if it's safe
to map memory region during hotplug/runtime.
That way hotplug path will have a chance to cancel
hotplug operation instead of crashing in vhost_commit().
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/hw/virtio/vhost-backend.h | 2 ++
include/hw/virtio/vhost.h | 2 ++
hw/virtio/vhost-backend.c | 19 +++++++++++++++++++
hw/virtio/vhost-user.c | 6 ++++++
hw/virtio/vhost.c | 21 +++++++++++++++++++++
stubs/vhost.c | 6 ++++++
stubs/Makefile.objs | 1 +
7 files changed, 57 insertions(+)
create mode 100644 stubs/vhost.c
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index 3a0f6e2..7d4a8ad 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -26,6 +26,7 @@ typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque);
typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev);
typedef int (*vhost_backend_get_vq_index)(struct vhost_dev *dev, int idx);
typedef int (*vhost_backend_set_vring_enable)(struct vhost_dev *dev, int enable);
+typedef int (*vhost_backend_memslots_limit)(struct vhost_dev *dev);
typedef struct VhostOps {
VhostBackendType backend_type;
@@ -34,6 +35,7 @@ typedef struct VhostOps {
vhost_backend_cleanup vhost_backend_cleanup;
vhost_backend_get_vq_index vhost_backend_get_vq_index;
vhost_backend_set_vring_enable vhost_backend_set_vring_enable;
+ vhost_backend_memslots_limit vhost_backend_memslots_limit;
} VhostOps;
extern const VhostOps user_ops;
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index c3758f3..080831e 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -59,6 +59,7 @@ struct vhost_dev {
const VhostOps *vhost_ops;
void *opaque;
struct vhost_log *log;
+ QLIST_ENTRY(vhost_dev) entry;
};
int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
@@ -83,4 +84,5 @@ uint64_t vhost_get_features(struct vhost_dev *hdev, const int *feature_bits,
uint64_t features);
void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits,
uint64_t features);
+bool vhost_has_free_slot(void);
#endif
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 72d1392..910d8e0 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -11,6 +11,7 @@
#include "hw/virtio/vhost.h"
#include "hw/virtio/vhost-backend.h"
#include "qemu/error-report.h"
+#include "linux/vhost.h"
#include <sys/ioctl.h>
@@ -49,12 +50,30 @@ static int vhost_kernel_get_vq_index(struct vhost_dev *dev, int idx)
return idx - dev->vq_index;
}
+static int vhost_kernel_memslots_limit(struct vhost_dev *dev)
+{
+ int limit = 64;
+ char *s;
+
+ if (g_file_get_contents("/sys/module/vhost/parameters/max_mem_regions",
+ &s, NULL, NULL)) {
+ uint64_t val = g_ascii_strtoull(s, NULL, 10);
+ if (!((val == G_MAXUINT64 || !val) && errno)) {
+ return val;
+ }
+ error_report("ignoring invalid max_mem_regions value in vhost module:"
+ " %s", s);
+ }
+ return limit;
+}
+
static const VhostOps kernel_ops = {
.backend_type = VHOST_BACKEND_TYPE_KERNEL,
.vhost_call = vhost_kernel_call,
.vhost_backend_init = vhost_kernel_init,
.vhost_backend_cleanup = vhost_kernel_cleanup,
.vhost_backend_get_vq_index = vhost_kernel_get_vq_index,
+ .vhost_backend_memslots_limit = vhost_kernel_memslots_limit,
};
int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index b11c0d2..9585637 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -440,6 +440,11 @@ static int vhost_user_get_vq_index(struct vhost_dev *dev, int idx)
return idx;
}
+static int vhost_user_memslots_limit(struct vhost_dev *dev)
+{
+ return VHOST_MEMORY_MAX_NREGIONS;
+}
+
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
.vhost_call = vhost_user_call,
@@ -447,4 +452,5 @@ const VhostOps user_ops = {
.vhost_backend_cleanup = vhost_user_cleanup,
.vhost_backend_get_vq_index = vhost_user_get_vq_index,
.vhost_backend_set_vring_enable = vhost_user_set_vring_enable,
+ .vhost_backend_memslots_limit = vhost_user_memslots_limit,
};
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index c0ed5b2..a3b4f9e 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -26,6 +26,22 @@
static struct vhost_log *vhost_log;
+static unsigned int used_memslots;
+static QLIST_HEAD(, vhost_dev) vhost_devices =
+ QLIST_HEAD_INITIALIZER(vhost_devices);
+
+bool vhost_has_free_slot(void)
+{
+ unsigned int slots_limit = ~0U;
+ struct vhost_dev *hdev;
+
+ QLIST_FOREACH(hdev, &vhost_devices, entry) {
+ unsigned int r = hdev->vhost_ops->vhost_backend_memslots_limit(hdev);
+ slots_limit = MIN(slots_limit, r);
+ }
+ return slots_limit > used_memslots;
+}
+
static void vhost_dev_sync_region(struct vhost_dev *dev,
MemoryRegionSection *section,
uint64_t mfirst, uint64_t mlast,
@@ -457,6 +473,7 @@ static void vhost_set_memory(MemoryListener *listener,
dev->mem_changed_start_addr = MIN(dev->mem_changed_start_addr, start_addr);
dev->mem_changed_end_addr = MAX(dev->mem_changed_end_addr, start_addr + size - 1);
dev->memory_changed = true;
+ used_memslots = dev->mem->nregions;
}
static bool vhost_section(MemoryRegionSection *section)
@@ -916,6 +933,8 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
return -errno;
}
+ QLIST_INSERT_HEAD(&vhost_devices, hdev, entry);
+
r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_OWNER, NULL);
if (r < 0) {
goto fail;
@@ -972,6 +991,7 @@ fail_vq:
fail:
r = -errno;
hdev->vhost_ops->vhost_backend_cleanup(hdev);
+ QLIST_REMOVE(hdev, entry);
return r;
}
@@ -989,6 +1009,7 @@ void vhost_dev_cleanup(struct vhost_dev *hdev)
g_free(hdev->mem);
g_free(hdev->mem_sections);
hdev->vhost_ops->vhost_backend_cleanup(hdev);
+ QLIST_REMOVE(hdev, entry);
}
/* Stop processing guest IO notifications in qemu.
diff --git a/stubs/vhost.c b/stubs/vhost.c
new file mode 100644
index 0000000..d346b85
--- /dev/null
+++ b/stubs/vhost.c
@@ -0,0 +1,6 @@
+#include "hw/virtio/vhost.h"
+
+bool vhost_has_free_slot(void)
+{
+ return true;
+}
diff --git a/stubs/Makefile.objs b/stubs/Makefile.objs
index 85e4e81..ce6ce11 100644
--- a/stubs/Makefile.objs
+++ b/stubs/Makefile.objs
@@ -39,3 +39,4 @@ stub-obj-y += cpus.o
stub-obj-y += kvm.o
stub-obj-y += qmp_pc_dimm_device_list.o
stub-obj-y += target-monitor-defs.o
+stub-obj-y += vhost.o
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 06/38] pc-dimm: add vhost slots limit check before commiting to hotplug
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (4 preceding siblings ...)
2015-10-21 10:26 ` [Qemu-devel] [PULL 05/38] vhost: add vhost_has_free_slot() interface Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 07/38] vhost: fail backend intialization early Michael S. Tsirkin
` (32 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel; +Cc: Peter Maydell, Igor Mammedov
From: Igor Mammedov <imammedo@redhat.com>
it allows safely cancel memory hotplug if vhost backend
doesn't support necessary amount of memory slots and prevents
QEMU crashing in vhost due to hitting vhost limit on amount
of supported memory ranges.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
hw/mem/pc-dimm.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/hw/mem/pc-dimm.c b/hw/mem/pc-dimm.c
index 506fe0d..2bae994 100644
--- a/hw/mem/pc-dimm.c
+++ b/hw/mem/pc-dimm.c
@@ -25,6 +25,7 @@
#include "sysemu/numa.h"
#include "sysemu/kvm.h"
#include "trace.h"
+#include "hw/virtio/vhost.h"
typedef struct pc_dimms_capacity {
uint64_t size;
@@ -96,6 +97,12 @@ void pc_dimm_memory_plug(DeviceState *dev, MemoryHotplugState *hpms,
goto out;
}
+ if (!vhost_has_free_slot()) {
+ error_setg(&local_err, "a used vhost backend has no free"
+ " memory slots left");
+ goto out;
+ }
+
memory_region_add_subregion(&hpms->mr, addr - hpms->base, mr);
vmstate_register_ram(mr, dev);
numa_set_mem_node_id(addr, memory_region_size(mr), dimm->node);
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 07/38] vhost: fail backend intialization early
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (5 preceding siblings ...)
2015-10-21 10:26 ` [Qemu-devel] [PULL 06/38] pc-dimm: add vhost slots limit check before commiting to hotplug Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 08/38] virtio: add some migration doc Michael S. Tsirkin
` (31 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel; +Cc: Peter Maydell, Igor Mammedov
From: Igor Mammedov <imammedo@redhat.com>
Don't initialize vhost backend if memslots number exceeds the supported
limit. This prevents failures down the road when backend
is actually started.
[MST: rewrite commit log]
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
hw/virtio/vhost.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index a3b4f9e..f14a5c5 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -933,6 +933,12 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
return -errno;
}
+ if (used_memslots > hdev->vhost_ops->vhost_backend_memslots_limit(hdev)) {
+ fprintf(stderr, "vhost backend memory slots limit is less"
+ " than current number of present memory slots\n");
+ close((uintptr_t)opaque);
+ return -1;
+ }
QLIST_INSERT_HEAD(&vhost_devices, hdev, entry);
r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_OWNER, NULL);
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 08/38] virtio: add some migration doc
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (6 preceding siblings ...)
2015-10-21 10:26 ` [Qemu-devel] [PULL 07/38] vhost: fail backend intialization early Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 09/38] configure: probe for memfd Michael S. Tsirkin
` (30 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel; +Cc: Cornelia Huck, Peter Maydell, Jason Wang, Greg Kurz
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Try to cover the basics of virtio migration.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
---
docs/virtio-migration.txt | 106 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 106 insertions(+)
create mode 100644 docs/virtio-migration.txt
diff --git a/docs/virtio-migration.txt b/docs/virtio-migration.txt
new file mode 100644
index 0000000..cf66458
--- /dev/null
+++ b/docs/virtio-migration.txt
@@ -0,0 +1,106 @@
+Virtio devices and migration
+============================
+
+Copyright 2015 IBM Corp.
+
+This work is licensed under the terms of the GNU GPL, version 2 or later. See
+the COPYING file in the top-level directory.
+
+Saving and restoring the state of virtio devices is a bit of a twisty maze,
+for several reasons:
+- state is distributed between several parts:
+ - virtio core, for common fields like features, number of queues, ...
+ - virtio transport (pci, ccw, ...), for the different proxy devices and
+ transport specific state (msix vectors, indicators, ...)
+ - virtio device (net, blk, ...), for the different device types and their
+ state (mac address, request queue, ...)
+- most fields are saved via the stream interface; subsequently, subsections
+ have been added to make cross-version migration possible
+
+This file attempts to document the current procedure and point out some
+caveats.
+
+
+Save state procedure
+====================
+
+virtio core virtio transport virtio device
+----------- ---------------- -------------
+
+ save() function registered
+ via register_savevm()
+virtio_save() <----------
+ ------> save_config()
+ - save proxy device
+ - save transport-specific
+ device fields
+- save common device
+ fields
+- save common virtqueue
+ fields
+ ------> save_queue()
+ - save transport-specific
+ virtqueue fields
+ ------> save_device()
+ - save device-specific
+ fields
+- save subsections
+ - device endianness,
+ if changed from
+ default endianness
+ - 64 bit features, if
+ any high feature bit
+ is set
+ - virtio-1 virtqueue
+ fields, if VERSION_1
+ is set
+
+
+Load state procedure
+====================
+
+virtio core virtio transport virtio device
+----------- ---------------- -------------
+
+ load() function registered
+ via register_savevm()
+virtio_load() <----------
+ ------> load_config()
+ - load proxy device
+ - load transport-specific
+ device fields
+- load common device
+ fields
+- load common virtqueue
+ fields
+ ------> load_queue()
+ - load transport-specific
+ virtqueue fields
+- notify guest
+ ------> load_device()
+ - load device-specific
+ fields
+- load subsections
+ - device endianness
+ - 64 bit features
+ - virtio-1 virtqueue
+ fields
+- sanitize endianness
+- sanitize features
+- virtqueue index sanity
+ check
+ - feature-dependent setup
+
+
+Implications of this setup
+==========================
+
+Devices need to be careful in their state processing during load: The
+load_device() procedure is invoked by the core before subsections have
+been loaded. Any code that depends on information transmitted in subsections
+therefore has to be invoked in the device's load() function _after_
+virtio_load() returned (like e.g. code depending on features).
+
+Any extension of the state being migrated should be done in subsections
+added to the core for compatibility reasons. If transport or device specific
+state is added, core needs to invoke a callback from the new subsection.
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 09/38] configure: probe for memfd
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (7 preceding siblings ...)
2015-10-21 10:26 ` [Qemu-devel] [PULL 08/38] virtio: add some migration doc Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:26 ` [Qemu-devel] [PULL 10/38] linux-headers: add unistd.h Michael S. Tsirkin
` (29 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, Michael Tokarev, Gerd Hoffmann,
Stefan Hajnoczi, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Paolo Bonzini
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Check if memfd_create() is part of system libc.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
configure | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/configure b/configure
index 9eec860..8d9b83c 100755
--- a/configure
+++ b/configure
@@ -3495,6 +3495,22 @@ if compile_prog "" "" ; then
eventfd=yes
fi
+# check if memfd is supported
+memfd=no
+cat > $TMPC << EOF
+#include <sys/memfd.h>
+
+int main(void)
+{
+ return memfd_create("foo", MFD_ALLOW_SEALING);
+}
+EOF
+if compile_prog "" "" ; then
+ memfd=yes
+fi
+
+
+
# check for fallocate
fallocate=no
cat > $TMPC << EOF
@@ -4889,6 +4905,9 @@ fi
if test "$eventfd" = "yes" ; then
echo "CONFIG_EVENTFD=y" >> $config_host_mak
fi
+if test "$memfd" = "yes" ; then
+ echo "CONFIG_MEMFD=y" >> $config_host_mak
+fi
if test "$fallocate" = "yes" ; then
echo "CONFIG_FALLOCATE=y" >> $config_host_mak
fi
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 10/38] linux-headers: add unistd.h
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (8 preceding siblings ...)
2015-10-21 10:26 ` [Qemu-devel] [PULL 09/38] configure: probe for memfd Michael S. Tsirkin
@ 2015-10-21 10:26 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 11/38] build-sys: split util-obj- on multi-lines Michael S. Tsirkin
` (28 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:26 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
New syscalls are not yet widely distributed. Add them to qemu
linux-headers include directory. Update based on v4.3-rc3 kernel headers.
Exclude mips for now, which is more problematic due to extra header
inclusion and probably unnecessary here.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
| 448 +++++++++++++++
| 37 +-
| 16 +
| 1063 ++++++++++++++++++++++++++++++++++++
| 392 +++++++++++++
| 404 ++++++++++++++
| 15 +
| 377 +++++++++++++
| 330 +++++++++++
| 319 +++++++++++
| 7 +-
11 files changed, 3404 insertions(+), 4 deletions(-)
create mode 100644 linux-headers/asm-arm/unistd.h
create mode 100644 linux-headers/asm-arm64/unistd.h
create mode 100644 linux-headers/asm-mips/unistd.h
create mode 100644 linux-headers/asm-powerpc/unistd.h
create mode 100644 linux-headers/asm-s390/unistd.h
create mode 100644 linux-headers/asm-x86/unistd.h
create mode 100644 linux-headers/asm-x86/unistd_32.h
create mode 100644 linux-headers/asm-x86/unistd_64.h
create mode 100644 linux-headers/asm-x86/unistd_x32.h
--git a/linux-headers/asm-arm/unistd.h b/linux-headers/asm-arm/unistd.h
new file mode 100644
index 0000000..0a1376c
--- /dev/null
+++ b/linux-headers/asm-arm/unistd.h
@@ -0,0 +1,448 @@
+/*
+ * arch/arm/include/asm/unistd.h
+ *
+ * Copyright (C) 2001-2005 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Please forward _all_ changes to this file to rmk@arm.linux.org.uk,
+ * no matter what the change is. Thanks!
+ */
+#ifndef __ASM_ARM_UNISTD_H
+#define __ASM_ARM_UNISTD_H
+
+#define __NR_OABI_SYSCALL_BASE 0x900000
+
+#if defined(__thumb__) || defined(__ARM_EABI__)
+#define __NR_SYSCALL_BASE 0
+#else
+#define __NR_SYSCALL_BASE __NR_OABI_SYSCALL_BASE
+#endif
+
+/*
+ * This file contains the system call numbers.
+ */
+
+#define __NR_restart_syscall (__NR_SYSCALL_BASE+ 0)
+#define __NR_exit (__NR_SYSCALL_BASE+ 1)
+#define __NR_fork (__NR_SYSCALL_BASE+ 2)
+#define __NR_read (__NR_SYSCALL_BASE+ 3)
+#define __NR_write (__NR_SYSCALL_BASE+ 4)
+#define __NR_open (__NR_SYSCALL_BASE+ 5)
+#define __NR_close (__NR_SYSCALL_BASE+ 6)
+ /* 7 was sys_waitpid */
+#define __NR_creat (__NR_SYSCALL_BASE+ 8)
+#define __NR_link (__NR_SYSCALL_BASE+ 9)
+#define __NR_unlink (__NR_SYSCALL_BASE+ 10)
+#define __NR_execve (__NR_SYSCALL_BASE+ 11)
+#define __NR_chdir (__NR_SYSCALL_BASE+ 12)
+#define __NR_time (__NR_SYSCALL_BASE+ 13)
+#define __NR_mknod (__NR_SYSCALL_BASE+ 14)
+#define __NR_chmod (__NR_SYSCALL_BASE+ 15)
+#define __NR_lchown (__NR_SYSCALL_BASE+ 16)
+ /* 17 was sys_break */
+ /* 18 was sys_stat */
+#define __NR_lseek (__NR_SYSCALL_BASE+ 19)
+#define __NR_getpid (__NR_SYSCALL_BASE+ 20)
+#define __NR_mount (__NR_SYSCALL_BASE+ 21)
+#define __NR_umount (__NR_SYSCALL_BASE+ 22)
+#define __NR_setuid (__NR_SYSCALL_BASE+ 23)
+#define __NR_getuid (__NR_SYSCALL_BASE+ 24)
+#define __NR_stime (__NR_SYSCALL_BASE+ 25)
+#define __NR_ptrace (__NR_SYSCALL_BASE+ 26)
+#define __NR_alarm (__NR_SYSCALL_BASE+ 27)
+ /* 28 was sys_fstat */
+#define __NR_pause (__NR_SYSCALL_BASE+ 29)
+#define __NR_utime (__NR_SYSCALL_BASE+ 30)
+ /* 31 was sys_stty */
+ /* 32 was sys_gtty */
+#define __NR_access (__NR_SYSCALL_BASE+ 33)
+#define __NR_nice (__NR_SYSCALL_BASE+ 34)
+ /* 35 was sys_ftime */
+#define __NR_sync (__NR_SYSCALL_BASE+ 36)
+#define __NR_kill (__NR_SYSCALL_BASE+ 37)
+#define __NR_rename (__NR_SYSCALL_BASE+ 38)
+#define __NR_mkdir (__NR_SYSCALL_BASE+ 39)
+#define __NR_rmdir (__NR_SYSCALL_BASE+ 40)
+#define __NR_dup (__NR_SYSCALL_BASE+ 41)
+#define __NR_pipe (__NR_SYSCALL_BASE+ 42)
+#define __NR_times (__NR_SYSCALL_BASE+ 43)
+ /* 44 was sys_prof */
+#define __NR_brk (__NR_SYSCALL_BASE+ 45)
+#define __NR_setgid (__NR_SYSCALL_BASE+ 46)
+#define __NR_getgid (__NR_SYSCALL_BASE+ 47)
+ /* 48 was sys_signal */
+#define __NR_geteuid (__NR_SYSCALL_BASE+ 49)
+#define __NR_getegid (__NR_SYSCALL_BASE+ 50)
+#define __NR_acct (__NR_SYSCALL_BASE+ 51)
+#define __NR_umount2 (__NR_SYSCALL_BASE+ 52)
+ /* 53 was sys_lock */
+#define __NR_ioctl (__NR_SYSCALL_BASE+ 54)
+#define __NR_fcntl (__NR_SYSCALL_BASE+ 55)
+ /* 56 was sys_mpx */
+#define __NR_setpgid (__NR_SYSCALL_BASE+ 57)
+ /* 58 was sys_ulimit */
+ /* 59 was sys_olduname */
+#define __NR_umask (__NR_SYSCALL_BASE+ 60)
+#define __NR_chroot (__NR_SYSCALL_BASE+ 61)
+#define __NR_ustat (__NR_SYSCALL_BASE+ 62)
+#define __NR_dup2 (__NR_SYSCALL_BASE+ 63)
+#define __NR_getppid (__NR_SYSCALL_BASE+ 64)
+#define __NR_getpgrp (__NR_SYSCALL_BASE+ 65)
+#define __NR_setsid (__NR_SYSCALL_BASE+ 66)
+#define __NR_sigaction (__NR_SYSCALL_BASE+ 67)
+ /* 68 was sys_sgetmask */
+ /* 69 was sys_ssetmask */
+#define __NR_setreuid (__NR_SYSCALL_BASE+ 70)
+#define __NR_setregid (__NR_SYSCALL_BASE+ 71)
+#define __NR_sigsuspend (__NR_SYSCALL_BASE+ 72)
+#define __NR_sigpending (__NR_SYSCALL_BASE+ 73)
+#define __NR_sethostname (__NR_SYSCALL_BASE+ 74)
+#define __NR_setrlimit (__NR_SYSCALL_BASE+ 75)
+#define __NR_getrlimit (__NR_SYSCALL_BASE+ 76) /* Back compat 2GB limited rlimit */
+#define __NR_getrusage (__NR_SYSCALL_BASE+ 77)
+#define __NR_gettimeofday (__NR_SYSCALL_BASE+ 78)
+#define __NR_settimeofday (__NR_SYSCALL_BASE+ 79)
+#define __NR_getgroups (__NR_SYSCALL_BASE+ 80)
+#define __NR_setgroups (__NR_SYSCALL_BASE+ 81)
+#define __NR_select (__NR_SYSCALL_BASE+ 82)
+#define __NR_symlink (__NR_SYSCALL_BASE+ 83)
+ /* 84 was sys_lstat */
+#define __NR_readlink (__NR_SYSCALL_BASE+ 85)
+#define __NR_uselib (__NR_SYSCALL_BASE+ 86)
+#define __NR_swapon (__NR_SYSCALL_BASE+ 87)
+#define __NR_reboot (__NR_SYSCALL_BASE+ 88)
+#define __NR_readdir (__NR_SYSCALL_BASE+ 89)
+#define __NR_mmap (__NR_SYSCALL_BASE+ 90)
+#define __NR_munmap (__NR_SYSCALL_BASE+ 91)
+#define __NR_truncate (__NR_SYSCALL_BASE+ 92)
+#define __NR_ftruncate (__NR_SYSCALL_BASE+ 93)
+#define __NR_fchmod (__NR_SYSCALL_BASE+ 94)
+#define __NR_fchown (__NR_SYSCALL_BASE+ 95)
+#define __NR_getpriority (__NR_SYSCALL_BASE+ 96)
+#define __NR_setpriority (__NR_SYSCALL_BASE+ 97)
+ /* 98 was sys_profil */
+#define __NR_statfs (__NR_SYSCALL_BASE+ 99)
+#define __NR_fstatfs (__NR_SYSCALL_BASE+100)
+ /* 101 was sys_ioperm */
+#define __NR_socketcall (__NR_SYSCALL_BASE+102)
+#define __NR_syslog (__NR_SYSCALL_BASE+103)
+#define __NR_setitimer (__NR_SYSCALL_BASE+104)
+#define __NR_getitimer (__NR_SYSCALL_BASE+105)
+#define __NR_stat (__NR_SYSCALL_BASE+106)
+#define __NR_lstat (__NR_SYSCALL_BASE+107)
+#define __NR_fstat (__NR_SYSCALL_BASE+108)
+ /* 109 was sys_uname */
+ /* 110 was sys_iopl */
+#define __NR_vhangup (__NR_SYSCALL_BASE+111)
+ /* 112 was sys_idle */
+#define __NR_syscall (__NR_SYSCALL_BASE+113) /* syscall to call a syscall! */
+#define __NR_wait4 (__NR_SYSCALL_BASE+114)
+#define __NR_swapoff (__NR_SYSCALL_BASE+115)
+#define __NR_sysinfo (__NR_SYSCALL_BASE+116)
+#define __NR_ipc (__NR_SYSCALL_BASE+117)
+#define __NR_fsync (__NR_SYSCALL_BASE+118)
+#define __NR_sigreturn (__NR_SYSCALL_BASE+119)
+#define __NR_clone (__NR_SYSCALL_BASE+120)
+#define __NR_setdomainname (__NR_SYSCALL_BASE+121)
+#define __NR_uname (__NR_SYSCALL_BASE+122)
+ /* 123 was sys_modify_ldt */
+#define __NR_adjtimex (__NR_SYSCALL_BASE+124)
+#define __NR_mprotect (__NR_SYSCALL_BASE+125)
+#define __NR_sigprocmask (__NR_SYSCALL_BASE+126)
+ /* 127 was sys_create_module */
+#define __NR_init_module (__NR_SYSCALL_BASE+128)
+#define __NR_delete_module (__NR_SYSCALL_BASE+129)
+ /* 130 was sys_get_kernel_syms */
+#define __NR_quotactl (__NR_SYSCALL_BASE+131)
+#define __NR_getpgid (__NR_SYSCALL_BASE+132)
+#define __NR_fchdir (__NR_SYSCALL_BASE+133)
+#define __NR_bdflush (__NR_SYSCALL_BASE+134)
+#define __NR_sysfs (__NR_SYSCALL_BASE+135)
+#define __NR_personality (__NR_SYSCALL_BASE+136)
+ /* 137 was sys_afs_syscall */
+#define __NR_setfsuid (__NR_SYSCALL_BASE+138)
+#define __NR_setfsgid (__NR_SYSCALL_BASE+139)
+#define __NR__llseek (__NR_SYSCALL_BASE+140)
+#define __NR_getdents (__NR_SYSCALL_BASE+141)
+#define __NR__newselect (__NR_SYSCALL_BASE+142)
+#define __NR_flock (__NR_SYSCALL_BASE+143)
+#define __NR_msync (__NR_SYSCALL_BASE+144)
+#define __NR_readv (__NR_SYSCALL_BASE+145)
+#define __NR_writev (__NR_SYSCALL_BASE+146)
+#define __NR_getsid (__NR_SYSCALL_BASE+147)
+#define __NR_fdatasync (__NR_SYSCALL_BASE+148)
+#define __NR__sysctl (__NR_SYSCALL_BASE+149)
+#define __NR_mlock (__NR_SYSCALL_BASE+150)
+#define __NR_munlock (__NR_SYSCALL_BASE+151)
+#define __NR_mlockall (__NR_SYSCALL_BASE+152)
+#define __NR_munlockall (__NR_SYSCALL_BASE+153)
+#define __NR_sched_setparam (__NR_SYSCALL_BASE+154)
+#define __NR_sched_getparam (__NR_SYSCALL_BASE+155)
+#define __NR_sched_setscheduler (__NR_SYSCALL_BASE+156)
+#define __NR_sched_getscheduler (__NR_SYSCALL_BASE+157)
+#define __NR_sched_yield (__NR_SYSCALL_BASE+158)
+#define __NR_sched_get_priority_max (__NR_SYSCALL_BASE+159)
+#define __NR_sched_get_priority_min (__NR_SYSCALL_BASE+160)
+#define __NR_sched_rr_get_interval (__NR_SYSCALL_BASE+161)
+#define __NR_nanosleep (__NR_SYSCALL_BASE+162)
+#define __NR_mremap (__NR_SYSCALL_BASE+163)
+#define __NR_setresuid (__NR_SYSCALL_BASE+164)
+#define __NR_getresuid (__NR_SYSCALL_BASE+165)
+ /* 166 was sys_vm86 */
+ /* 167 was sys_query_module */
+#define __NR_poll (__NR_SYSCALL_BASE+168)
+#define __NR_nfsservctl (__NR_SYSCALL_BASE+169)
+#define __NR_setresgid (__NR_SYSCALL_BASE+170)
+#define __NR_getresgid (__NR_SYSCALL_BASE+171)
+#define __NR_prctl (__NR_SYSCALL_BASE+172)
+#define __NR_rt_sigreturn (__NR_SYSCALL_BASE+173)
+#define __NR_rt_sigaction (__NR_SYSCALL_BASE+174)
+#define __NR_rt_sigprocmask (__NR_SYSCALL_BASE+175)
+#define __NR_rt_sigpending (__NR_SYSCALL_BASE+176)
+#define __NR_rt_sigtimedwait (__NR_SYSCALL_BASE+177)
+#define __NR_rt_sigqueueinfo (__NR_SYSCALL_BASE+178)
+#define __NR_rt_sigsuspend (__NR_SYSCALL_BASE+179)
+#define __NR_pread64 (__NR_SYSCALL_BASE+180)
+#define __NR_pwrite64 (__NR_SYSCALL_BASE+181)
+#define __NR_chown (__NR_SYSCALL_BASE+182)
+#define __NR_getcwd (__NR_SYSCALL_BASE+183)
+#define __NR_capget (__NR_SYSCALL_BASE+184)
+#define __NR_capset (__NR_SYSCALL_BASE+185)
+#define __NR_sigaltstack (__NR_SYSCALL_BASE+186)
+#define __NR_sendfile (__NR_SYSCALL_BASE+187)
+ /* 188 reserved */
+ /* 189 reserved */
+#define __NR_vfork (__NR_SYSCALL_BASE+190)
+#define __NR_ugetrlimit (__NR_SYSCALL_BASE+191) /* SuS compliant getrlimit */
+#define __NR_mmap2 (__NR_SYSCALL_BASE+192)
+#define __NR_truncate64 (__NR_SYSCALL_BASE+193)
+#define __NR_ftruncate64 (__NR_SYSCALL_BASE+194)
+#define __NR_stat64 (__NR_SYSCALL_BASE+195)
+#define __NR_lstat64 (__NR_SYSCALL_BASE+196)
+#define __NR_fstat64 (__NR_SYSCALL_BASE+197)
+#define __NR_lchown32 (__NR_SYSCALL_BASE+198)
+#define __NR_getuid32 (__NR_SYSCALL_BASE+199)
+#define __NR_getgid32 (__NR_SYSCALL_BASE+200)
+#define __NR_geteuid32 (__NR_SYSCALL_BASE+201)
+#define __NR_getegid32 (__NR_SYSCALL_BASE+202)
+#define __NR_setreuid32 (__NR_SYSCALL_BASE+203)
+#define __NR_setregid32 (__NR_SYSCALL_BASE+204)
+#define __NR_getgroups32 (__NR_SYSCALL_BASE+205)
+#define __NR_setgroups32 (__NR_SYSCALL_BASE+206)
+#define __NR_fchown32 (__NR_SYSCALL_BASE+207)
+#define __NR_setresuid32 (__NR_SYSCALL_BASE+208)
+#define __NR_getresuid32 (__NR_SYSCALL_BASE+209)
+#define __NR_setresgid32 (__NR_SYSCALL_BASE+210)
+#define __NR_getresgid32 (__NR_SYSCALL_BASE+211)
+#define __NR_chown32 (__NR_SYSCALL_BASE+212)
+#define __NR_setuid32 (__NR_SYSCALL_BASE+213)
+#define __NR_setgid32 (__NR_SYSCALL_BASE+214)
+#define __NR_setfsuid32 (__NR_SYSCALL_BASE+215)
+#define __NR_setfsgid32 (__NR_SYSCALL_BASE+216)
+#define __NR_getdents64 (__NR_SYSCALL_BASE+217)
+#define __NR_pivot_root (__NR_SYSCALL_BASE+218)
+#define __NR_mincore (__NR_SYSCALL_BASE+219)
+#define __NR_madvise (__NR_SYSCALL_BASE+220)
+#define __NR_fcntl64 (__NR_SYSCALL_BASE+221)
+ /* 222 for tux */
+ /* 223 is unused */
+#define __NR_gettid (__NR_SYSCALL_BASE+224)
+#define __NR_readahead (__NR_SYSCALL_BASE+225)
+#define __NR_setxattr (__NR_SYSCALL_BASE+226)
+#define __NR_lsetxattr (__NR_SYSCALL_BASE+227)
+#define __NR_fsetxattr (__NR_SYSCALL_BASE+228)
+#define __NR_getxattr (__NR_SYSCALL_BASE+229)
+#define __NR_lgetxattr (__NR_SYSCALL_BASE+230)
+#define __NR_fgetxattr (__NR_SYSCALL_BASE+231)
+#define __NR_listxattr (__NR_SYSCALL_BASE+232)
+#define __NR_llistxattr (__NR_SYSCALL_BASE+233)
+#define __NR_flistxattr (__NR_SYSCALL_BASE+234)
+#define __NR_removexattr (__NR_SYSCALL_BASE+235)
+#define __NR_lremovexattr (__NR_SYSCALL_BASE+236)
+#define __NR_fremovexattr (__NR_SYSCALL_BASE+237)
+#define __NR_tkill (__NR_SYSCALL_BASE+238)
+#define __NR_sendfile64 (__NR_SYSCALL_BASE+239)
+#define __NR_futex (__NR_SYSCALL_BASE+240)
+#define __NR_sched_setaffinity (__NR_SYSCALL_BASE+241)
+#define __NR_sched_getaffinity (__NR_SYSCALL_BASE+242)
+#define __NR_io_setup (__NR_SYSCALL_BASE+243)
+#define __NR_io_destroy (__NR_SYSCALL_BASE+244)
+#define __NR_io_getevents (__NR_SYSCALL_BASE+245)
+#define __NR_io_submit (__NR_SYSCALL_BASE+246)
+#define __NR_io_cancel (__NR_SYSCALL_BASE+247)
+#define __NR_exit_group (__NR_SYSCALL_BASE+248)
+#define __NR_lookup_dcookie (__NR_SYSCALL_BASE+249)
+#define __NR_epoll_create (__NR_SYSCALL_BASE+250)
+#define __NR_epoll_ctl (__NR_SYSCALL_BASE+251)
+#define __NR_epoll_wait (__NR_SYSCALL_BASE+252)
+#define __NR_remap_file_pages (__NR_SYSCALL_BASE+253)
+ /* 254 for set_thread_area */
+ /* 255 for get_thread_area */
+#define __NR_set_tid_address (__NR_SYSCALL_BASE+256)
+#define __NR_timer_create (__NR_SYSCALL_BASE+257)
+#define __NR_timer_settime (__NR_SYSCALL_BASE+258)
+#define __NR_timer_gettime (__NR_SYSCALL_BASE+259)
+#define __NR_timer_getoverrun (__NR_SYSCALL_BASE+260)
+#define __NR_timer_delete (__NR_SYSCALL_BASE+261)
+#define __NR_clock_settime (__NR_SYSCALL_BASE+262)
+#define __NR_clock_gettime (__NR_SYSCALL_BASE+263)
+#define __NR_clock_getres (__NR_SYSCALL_BASE+264)
+#define __NR_clock_nanosleep (__NR_SYSCALL_BASE+265)
+#define __NR_statfs64 (__NR_SYSCALL_BASE+266)
+#define __NR_fstatfs64 (__NR_SYSCALL_BASE+267)
+#define __NR_tgkill (__NR_SYSCALL_BASE+268)
+#define __NR_utimes (__NR_SYSCALL_BASE+269)
+#define __NR_arm_fadvise64_64 (__NR_SYSCALL_BASE+270)
+#define __NR_pciconfig_iobase (__NR_SYSCALL_BASE+271)
+#define __NR_pciconfig_read (__NR_SYSCALL_BASE+272)
+#define __NR_pciconfig_write (__NR_SYSCALL_BASE+273)
+#define __NR_mq_open (__NR_SYSCALL_BASE+274)
+#define __NR_mq_unlink (__NR_SYSCALL_BASE+275)
+#define __NR_mq_timedsend (__NR_SYSCALL_BASE+276)
+#define __NR_mq_timedreceive (__NR_SYSCALL_BASE+277)
+#define __NR_mq_notify (__NR_SYSCALL_BASE+278)
+#define __NR_mq_getsetattr (__NR_SYSCALL_BASE+279)
+#define __NR_waitid (__NR_SYSCALL_BASE+280)
+#define __NR_socket (__NR_SYSCALL_BASE+281)
+#define __NR_bind (__NR_SYSCALL_BASE+282)
+#define __NR_connect (__NR_SYSCALL_BASE+283)
+#define __NR_listen (__NR_SYSCALL_BASE+284)
+#define __NR_accept (__NR_SYSCALL_BASE+285)
+#define __NR_getsockname (__NR_SYSCALL_BASE+286)
+#define __NR_getpeername (__NR_SYSCALL_BASE+287)
+#define __NR_socketpair (__NR_SYSCALL_BASE+288)
+#define __NR_send (__NR_SYSCALL_BASE+289)
+#define __NR_sendto (__NR_SYSCALL_BASE+290)
+#define __NR_recv (__NR_SYSCALL_BASE+291)
+#define __NR_recvfrom (__NR_SYSCALL_BASE+292)
+#define __NR_shutdown (__NR_SYSCALL_BASE+293)
+#define __NR_setsockopt (__NR_SYSCALL_BASE+294)
+#define __NR_getsockopt (__NR_SYSCALL_BASE+295)
+#define __NR_sendmsg (__NR_SYSCALL_BASE+296)
+#define __NR_recvmsg (__NR_SYSCALL_BASE+297)
+#define __NR_semop (__NR_SYSCALL_BASE+298)
+#define __NR_semget (__NR_SYSCALL_BASE+299)
+#define __NR_semctl (__NR_SYSCALL_BASE+300)
+#define __NR_msgsnd (__NR_SYSCALL_BASE+301)
+#define __NR_msgrcv (__NR_SYSCALL_BASE+302)
+#define __NR_msgget (__NR_SYSCALL_BASE+303)
+#define __NR_msgctl (__NR_SYSCALL_BASE+304)
+#define __NR_shmat (__NR_SYSCALL_BASE+305)
+#define __NR_shmdt (__NR_SYSCALL_BASE+306)
+#define __NR_shmget (__NR_SYSCALL_BASE+307)
+#define __NR_shmctl (__NR_SYSCALL_BASE+308)
+#define __NR_add_key (__NR_SYSCALL_BASE+309)
+#define __NR_request_key (__NR_SYSCALL_BASE+310)
+#define __NR_keyctl (__NR_SYSCALL_BASE+311)
+#define __NR_semtimedop (__NR_SYSCALL_BASE+312)
+#define __NR_vserver (__NR_SYSCALL_BASE+313)
+#define __NR_ioprio_set (__NR_SYSCALL_BASE+314)
+#define __NR_ioprio_get (__NR_SYSCALL_BASE+315)
+#define __NR_inotify_init (__NR_SYSCALL_BASE+316)
+#define __NR_inotify_add_watch (__NR_SYSCALL_BASE+317)
+#define __NR_inotify_rm_watch (__NR_SYSCALL_BASE+318)
+#define __NR_mbind (__NR_SYSCALL_BASE+319)
+#define __NR_get_mempolicy (__NR_SYSCALL_BASE+320)
+#define __NR_set_mempolicy (__NR_SYSCALL_BASE+321)
+#define __NR_openat (__NR_SYSCALL_BASE+322)
+#define __NR_mkdirat (__NR_SYSCALL_BASE+323)
+#define __NR_mknodat (__NR_SYSCALL_BASE+324)
+#define __NR_fchownat (__NR_SYSCALL_BASE+325)
+#define __NR_futimesat (__NR_SYSCALL_BASE+326)
+#define __NR_fstatat64 (__NR_SYSCALL_BASE+327)
+#define __NR_unlinkat (__NR_SYSCALL_BASE+328)
+#define __NR_renameat (__NR_SYSCALL_BASE+329)
+#define __NR_linkat (__NR_SYSCALL_BASE+330)
+#define __NR_symlinkat (__NR_SYSCALL_BASE+331)
+#define __NR_readlinkat (__NR_SYSCALL_BASE+332)
+#define __NR_fchmodat (__NR_SYSCALL_BASE+333)
+#define __NR_faccessat (__NR_SYSCALL_BASE+334)
+#define __NR_pselect6 (__NR_SYSCALL_BASE+335)
+#define __NR_ppoll (__NR_SYSCALL_BASE+336)
+#define __NR_unshare (__NR_SYSCALL_BASE+337)
+#define __NR_set_robust_list (__NR_SYSCALL_BASE+338)
+#define __NR_get_robust_list (__NR_SYSCALL_BASE+339)
+#define __NR_splice (__NR_SYSCALL_BASE+340)
+#define __NR_arm_sync_file_range (__NR_SYSCALL_BASE+341)
+#define __NR_sync_file_range2 __NR_arm_sync_file_range
+#define __NR_tee (__NR_SYSCALL_BASE+342)
+#define __NR_vmsplice (__NR_SYSCALL_BASE+343)
+#define __NR_move_pages (__NR_SYSCALL_BASE+344)
+#define __NR_getcpu (__NR_SYSCALL_BASE+345)
+#define __NR_epoll_pwait (__NR_SYSCALL_BASE+346)
+#define __NR_kexec_load (__NR_SYSCALL_BASE+347)
+#define __NR_utimensat (__NR_SYSCALL_BASE+348)
+#define __NR_signalfd (__NR_SYSCALL_BASE+349)
+#define __NR_timerfd_create (__NR_SYSCALL_BASE+350)
+#define __NR_eventfd (__NR_SYSCALL_BASE+351)
+#define __NR_fallocate (__NR_SYSCALL_BASE+352)
+#define __NR_timerfd_settime (__NR_SYSCALL_BASE+353)
+#define __NR_timerfd_gettime (__NR_SYSCALL_BASE+354)
+#define __NR_signalfd4 (__NR_SYSCALL_BASE+355)
+#define __NR_eventfd2 (__NR_SYSCALL_BASE+356)
+#define __NR_epoll_create1 (__NR_SYSCALL_BASE+357)
+#define __NR_dup3 (__NR_SYSCALL_BASE+358)
+#define __NR_pipe2 (__NR_SYSCALL_BASE+359)
+#define __NR_inotify_init1 (__NR_SYSCALL_BASE+360)
+#define __NR_preadv (__NR_SYSCALL_BASE+361)
+#define __NR_pwritev (__NR_SYSCALL_BASE+362)
+#define __NR_rt_tgsigqueueinfo (__NR_SYSCALL_BASE+363)
+#define __NR_perf_event_open (__NR_SYSCALL_BASE+364)
+#define __NR_recvmmsg (__NR_SYSCALL_BASE+365)
+#define __NR_accept4 (__NR_SYSCALL_BASE+366)
+#define __NR_fanotify_init (__NR_SYSCALL_BASE+367)
+#define __NR_fanotify_mark (__NR_SYSCALL_BASE+368)
+#define __NR_prlimit64 (__NR_SYSCALL_BASE+369)
+#define __NR_name_to_handle_at (__NR_SYSCALL_BASE+370)
+#define __NR_open_by_handle_at (__NR_SYSCALL_BASE+371)
+#define __NR_clock_adjtime (__NR_SYSCALL_BASE+372)
+#define __NR_syncfs (__NR_SYSCALL_BASE+373)
+#define __NR_sendmmsg (__NR_SYSCALL_BASE+374)
+#define __NR_setns (__NR_SYSCALL_BASE+375)
+#define __NR_process_vm_readv (__NR_SYSCALL_BASE+376)
+#define __NR_process_vm_writev (__NR_SYSCALL_BASE+377)
+#define __NR_kcmp (__NR_SYSCALL_BASE+378)
+#define __NR_finit_module (__NR_SYSCALL_BASE+379)
+#define __NR_sched_setattr (__NR_SYSCALL_BASE+380)
+#define __NR_sched_getattr (__NR_SYSCALL_BASE+381)
+#define __NR_renameat2 (__NR_SYSCALL_BASE+382)
+#define __NR_seccomp (__NR_SYSCALL_BASE+383)
+#define __NR_getrandom (__NR_SYSCALL_BASE+384)
+#define __NR_memfd_create (__NR_SYSCALL_BASE+385)
+#define __NR_bpf (__NR_SYSCALL_BASE+386)
+#define __NR_execveat (__NR_SYSCALL_BASE+387)
+#define __NR_userfaultfd (__NR_SYSCALL_BASE+388)
+#define __NR_membarrier (__NR_SYSCALL_BASE+389)
+
+/*
+ * The following SWIs are ARM private.
+ */
+#define __ARM_NR_BASE (__NR_SYSCALL_BASE+0x0f0000)
+#define __ARM_NR_breakpoint (__ARM_NR_BASE+1)
+#define __ARM_NR_cacheflush (__ARM_NR_BASE+2)
+#define __ARM_NR_usr26 (__ARM_NR_BASE+3)
+#define __ARM_NR_usr32 (__ARM_NR_BASE+4)
+#define __ARM_NR_set_tls (__ARM_NR_BASE+5)
+
+/*
+ * The following syscalls are obsolete and no longer available for EABI.
+ */
+#if defined(__ARM_EABI__)
+#undef __NR_time
+#undef __NR_umount
+#undef __NR_stime
+#undef __NR_alarm
+#undef __NR_utime
+#undef __NR_getrlimit
+#undef __NR_select
+#undef __NR_readdir
+#undef __NR_mmap
+#undef __NR_socketcall
+#undef __NR_syscall
+#undef __NR_ipc
+#endif
+
+#endif /* __ASM_ARM_UNISTD_H */
--git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h
index c8abf25..d3714c0 100644
--- a/linux-headers/asm-arm64/kvm.h
+++ b/linux-headers/asm-arm64/kvm.h
@@ -53,14 +53,20 @@ struct kvm_regs {
struct user_fpsimd_state fp_regs;
};
-/* Supported Processor Types */
+/*
+ * Supported CPU Targets - Adding a new target type is not recommended,
+ * unless there are some special registers not supported by the
+ * genericv8 syreg table.
+ */
#define KVM_ARM_TARGET_AEM_V8 0
#define KVM_ARM_TARGET_FOUNDATION_V8 1
#define KVM_ARM_TARGET_CORTEX_A57 2
#define KVM_ARM_TARGET_XGENE_POTENZA 3
#define KVM_ARM_TARGET_CORTEX_A53 4
+/* Generic ARM v8 target */
+#define KVM_ARM_TARGET_GENERIC_V8 5
-#define KVM_ARM_NUM_TARGETS 5
+#define KVM_ARM_NUM_TARGETS 6
/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
#define KVM_ARM_DEVICE_TYPE_SHIFT 0
@@ -100,12 +106,39 @@ struct kvm_sregs {
struct kvm_fpu {
};
+/*
+ * See v8 ARM ARM D7.3: Debug Registers
+ *
+ * The architectural limit is 16 debug registers of each type although
+ * in practice there are usually less (see ID_AA64DFR0_EL1).
+ *
+ * Although the control registers are architecturally defined as 32
+ * bits wide we use a 64 bit structure here to keep parity with
+ * KVM_GET/SET_ONE_REG behaviour which treats all system registers as
+ * 64 bit values. It also allows for the possibility of the
+ * architecture expanding the control registers without having to
+ * change the userspace ABI.
+ */
+#define KVM_ARM_MAX_DBG_REGS 16
struct kvm_guest_debug_arch {
+ __u64 dbg_bcr[KVM_ARM_MAX_DBG_REGS];
+ __u64 dbg_bvr[KVM_ARM_MAX_DBG_REGS];
+ __u64 dbg_wcr[KVM_ARM_MAX_DBG_REGS];
+ __u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS];
};
struct kvm_debug_exit_arch {
+ __u32 hsr;
+ __u64 far; /* used for watchpoints */
};
+/*
+ * Architecture specific defines for kvm_guest_debug->control
+ */
+
+#define KVM_GUESTDBG_USE_SW_BP (1 << 16)
+#define KVM_GUESTDBG_USE_HW (1 << 17)
+
struct kvm_sync_regs {
};
--git a/linux-headers/asm-arm64/unistd.h b/linux-headers/asm-arm64/unistd.h
new file mode 100644
index 0000000..1caadc2
--- /dev/null
+++ b/linux-headers/asm-arm64/unistd.h
@@ -0,0 +1,16 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <asm-generic/unistd.h>
--git a/linux-headers/asm-mips/unistd.h b/linux-headers/asm-mips/unistd.h
new file mode 100644
index 0000000..2a20209
--- /dev/null
+++ b/linux-headers/asm-mips/unistd.h
@@ -0,0 +1,1063 @@
+/*
+ * 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, 96, 97, 98, 99, 2000 by Ralf Baechle
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ *
+ * Changed system calls macros _syscall5 - _syscall7 to push args 5 to 7 onto
+ * the stack. Robin Farine for ACN S.A, Copyright (C) 1996 by ACN S.A
+ */
+#ifndef _ASM_UNISTD_H
+#define _ASM_UNISTD_H
+
+#include <asm/sgidefs.h>
+
+#if _MIPS_SIM == _MIPS_SIM_ABI32
+
+/*
+ * Linux o32 style syscalls are in the range from 4000 to 4999.
+ */
+#define __NR_Linux 4000
+#define __NR_syscall (__NR_Linux + 0)
+#define __NR_exit (__NR_Linux + 1)
+#define __NR_fork (__NR_Linux + 2)
+#define __NR_read (__NR_Linux + 3)
+#define __NR_write (__NR_Linux + 4)
+#define __NR_open (__NR_Linux + 5)
+#define __NR_close (__NR_Linux + 6)
+#define __NR_waitpid (__NR_Linux + 7)
+#define __NR_creat (__NR_Linux + 8)
+#define __NR_link (__NR_Linux + 9)
+#define __NR_unlink (__NR_Linux + 10)
+#define __NR_execve (__NR_Linux + 11)
+#define __NR_chdir (__NR_Linux + 12)
+#define __NR_time (__NR_Linux + 13)
+#define __NR_mknod (__NR_Linux + 14)
+#define __NR_chmod (__NR_Linux + 15)
+#define __NR_lchown (__NR_Linux + 16)
+#define __NR_break (__NR_Linux + 17)
+#define __NR_unused18 (__NR_Linux + 18)
+#define __NR_lseek (__NR_Linux + 19)
+#define __NR_getpid (__NR_Linux + 20)
+#define __NR_mount (__NR_Linux + 21)
+#define __NR_umount (__NR_Linux + 22)
+#define __NR_setuid (__NR_Linux + 23)
+#define __NR_getuid (__NR_Linux + 24)
+#define __NR_stime (__NR_Linux + 25)
+#define __NR_ptrace (__NR_Linux + 26)
+#define __NR_alarm (__NR_Linux + 27)
+#define __NR_unused28 (__NR_Linux + 28)
+#define __NR_pause (__NR_Linux + 29)
+#define __NR_utime (__NR_Linux + 30)
+#define __NR_stty (__NR_Linux + 31)
+#define __NR_gtty (__NR_Linux + 32)
+#define __NR_access (__NR_Linux + 33)
+#define __NR_nice (__NR_Linux + 34)
+#define __NR_ftime (__NR_Linux + 35)
+#define __NR_sync (__NR_Linux + 36)
+#define __NR_kill (__NR_Linux + 37)
+#define __NR_rename (__NR_Linux + 38)
+#define __NR_mkdir (__NR_Linux + 39)
+#define __NR_rmdir (__NR_Linux + 40)
+#define __NR_dup (__NR_Linux + 41)
+#define __NR_pipe (__NR_Linux + 42)
+#define __NR_times (__NR_Linux + 43)
+#define __NR_prof (__NR_Linux + 44)
+#define __NR_brk (__NR_Linux + 45)
+#define __NR_setgid (__NR_Linux + 46)
+#define __NR_getgid (__NR_Linux + 47)
+#define __NR_signal (__NR_Linux + 48)
+#define __NR_geteuid (__NR_Linux + 49)
+#define __NR_getegid (__NR_Linux + 50)
+#define __NR_acct (__NR_Linux + 51)
+#define __NR_umount2 (__NR_Linux + 52)
+#define __NR_lock (__NR_Linux + 53)
+#define __NR_ioctl (__NR_Linux + 54)
+#define __NR_fcntl (__NR_Linux + 55)
+#define __NR_mpx (__NR_Linux + 56)
+#define __NR_setpgid (__NR_Linux + 57)
+#define __NR_ulimit (__NR_Linux + 58)
+#define __NR_unused59 (__NR_Linux + 59)
+#define __NR_umask (__NR_Linux + 60)
+#define __NR_chroot (__NR_Linux + 61)
+#define __NR_ustat (__NR_Linux + 62)
+#define __NR_dup2 (__NR_Linux + 63)
+#define __NR_getppid (__NR_Linux + 64)
+#define __NR_getpgrp (__NR_Linux + 65)
+#define __NR_setsid (__NR_Linux + 66)
+#define __NR_sigaction (__NR_Linux + 67)
+#define __NR_sgetmask (__NR_Linux + 68)
+#define __NR_ssetmask (__NR_Linux + 69)
+#define __NR_setreuid (__NR_Linux + 70)
+#define __NR_setregid (__NR_Linux + 71)
+#define __NR_sigsuspend (__NR_Linux + 72)
+#define __NR_sigpending (__NR_Linux + 73)
+#define __NR_sethostname (__NR_Linux + 74)
+#define __NR_setrlimit (__NR_Linux + 75)
+#define __NR_getrlimit (__NR_Linux + 76)
+#define __NR_getrusage (__NR_Linux + 77)
+#define __NR_gettimeofday (__NR_Linux + 78)
+#define __NR_settimeofday (__NR_Linux + 79)
+#define __NR_getgroups (__NR_Linux + 80)
+#define __NR_setgroups (__NR_Linux + 81)
+#define __NR_reserved82 (__NR_Linux + 82)
+#define __NR_symlink (__NR_Linux + 83)
+#define __NR_unused84 (__NR_Linux + 84)
+#define __NR_readlink (__NR_Linux + 85)
+#define __NR_uselib (__NR_Linux + 86)
+#define __NR_swapon (__NR_Linux + 87)
+#define __NR_reboot (__NR_Linux + 88)
+#define __NR_readdir (__NR_Linux + 89)
+#define __NR_mmap (__NR_Linux + 90)
+#define __NR_munmap (__NR_Linux + 91)
+#define __NR_truncate (__NR_Linux + 92)
+#define __NR_ftruncate (__NR_Linux + 93)
+#define __NR_fchmod (__NR_Linux + 94)
+#define __NR_fchown (__NR_Linux + 95)
+#define __NR_getpriority (__NR_Linux + 96)
+#define __NR_setpriority (__NR_Linux + 97)
+#define __NR_profil (__NR_Linux + 98)
+#define __NR_statfs (__NR_Linux + 99)
+#define __NR_fstatfs (__NR_Linux + 100)
+#define __NR_ioperm (__NR_Linux + 101)
+#define __NR_socketcall (__NR_Linux + 102)
+#define __NR_syslog (__NR_Linux + 103)
+#define __NR_setitimer (__NR_Linux + 104)
+#define __NR_getitimer (__NR_Linux + 105)
+#define __NR_stat (__NR_Linux + 106)
+#define __NR_lstat (__NR_Linux + 107)
+#define __NR_fstat (__NR_Linux + 108)
+#define __NR_unused109 (__NR_Linux + 109)
+#define __NR_iopl (__NR_Linux + 110)
+#define __NR_vhangup (__NR_Linux + 111)
+#define __NR_idle (__NR_Linux + 112)
+#define __NR_vm86 (__NR_Linux + 113)
+#define __NR_wait4 (__NR_Linux + 114)
+#define __NR_swapoff (__NR_Linux + 115)
+#define __NR_sysinfo (__NR_Linux + 116)
+#define __NR_ipc (__NR_Linux + 117)
+#define __NR_fsync (__NR_Linux + 118)
+#define __NR_sigreturn (__NR_Linux + 119)
+#define __NR_clone (__NR_Linux + 120)
+#define __NR_setdomainname (__NR_Linux + 121)
+#define __NR_uname (__NR_Linux + 122)
+#define __NR_modify_ldt (__NR_Linux + 123)
+#define __NR_adjtimex (__NR_Linux + 124)
+#define __NR_mprotect (__NR_Linux + 125)
+#define __NR_sigprocmask (__NR_Linux + 126)
+#define __NR_create_module (__NR_Linux + 127)
+#define __NR_init_module (__NR_Linux + 128)
+#define __NR_delete_module (__NR_Linux + 129)
+#define __NR_get_kernel_syms (__NR_Linux + 130)
+#define __NR_quotactl (__NR_Linux + 131)
+#define __NR_getpgid (__NR_Linux + 132)
+#define __NR_fchdir (__NR_Linux + 133)
+#define __NR_bdflush (__NR_Linux + 134)
+#define __NR_sysfs (__NR_Linux + 135)
+#define __NR_personality (__NR_Linux + 136)
+#define __NR_afs_syscall (__NR_Linux + 137) /* Syscall for Andrew File System */
+#define __NR_setfsuid (__NR_Linux + 138)
+#define __NR_setfsgid (__NR_Linux + 139)
+#define __NR__llseek (__NR_Linux + 140)
+#define __NR_getdents (__NR_Linux + 141)
+#define __NR__newselect (__NR_Linux + 142)
+#define __NR_flock (__NR_Linux + 143)
+#define __NR_msync (__NR_Linux + 144)
+#define __NR_readv (__NR_Linux + 145)
+#define __NR_writev (__NR_Linux + 146)
+#define __NR_cacheflush (__NR_Linux + 147)
+#define __NR_cachectl (__NR_Linux + 148)
+#define __NR_sysmips (__NR_Linux + 149)
+#define __NR_unused150 (__NR_Linux + 150)
+#define __NR_getsid (__NR_Linux + 151)
+#define __NR_fdatasync (__NR_Linux + 152)
+#define __NR__sysctl (__NR_Linux + 153)
+#define __NR_mlock (__NR_Linux + 154)
+#define __NR_munlock (__NR_Linux + 155)
+#define __NR_mlockall (__NR_Linux + 156)
+#define __NR_munlockall (__NR_Linux + 157)
+#define __NR_sched_setparam (__NR_Linux + 158)
+#define __NR_sched_getparam (__NR_Linux + 159)
+#define __NR_sched_setscheduler (__NR_Linux + 160)
+#define __NR_sched_getscheduler (__NR_Linux + 161)
+#define __NR_sched_yield (__NR_Linux + 162)
+#define __NR_sched_get_priority_max (__NR_Linux + 163)
+#define __NR_sched_get_priority_min (__NR_Linux + 164)
+#define __NR_sched_rr_get_interval (__NR_Linux + 165)
+#define __NR_nanosleep (__NR_Linux + 166)
+#define __NR_mremap (__NR_Linux + 167)
+#define __NR_accept (__NR_Linux + 168)
+#define __NR_bind (__NR_Linux + 169)
+#define __NR_connect (__NR_Linux + 170)
+#define __NR_getpeername (__NR_Linux + 171)
+#define __NR_getsockname (__NR_Linux + 172)
+#define __NR_getsockopt (__NR_Linux + 173)
+#define __NR_listen (__NR_Linux + 174)
+#define __NR_recv (__NR_Linux + 175)
+#define __NR_recvfrom (__NR_Linux + 176)
+#define __NR_recvmsg (__NR_Linux + 177)
+#define __NR_send (__NR_Linux + 178)
+#define __NR_sendmsg (__NR_Linux + 179)
+#define __NR_sendto (__NR_Linux + 180)
+#define __NR_setsockopt (__NR_Linux + 181)
+#define __NR_shutdown (__NR_Linux + 182)
+#define __NR_socket (__NR_Linux + 183)
+#define __NR_socketpair (__NR_Linux + 184)
+#define __NR_setresuid (__NR_Linux + 185)
+#define __NR_getresuid (__NR_Linux + 186)
+#define __NR_query_module (__NR_Linux + 187)
+#define __NR_poll (__NR_Linux + 188)
+#define __NR_nfsservctl (__NR_Linux + 189)
+#define __NR_setresgid (__NR_Linux + 190)
+#define __NR_getresgid (__NR_Linux + 191)
+#define __NR_prctl (__NR_Linux + 192)
+#define __NR_rt_sigreturn (__NR_Linux + 193)
+#define __NR_rt_sigaction (__NR_Linux + 194)
+#define __NR_rt_sigprocmask (__NR_Linux + 195)
+#define __NR_rt_sigpending (__NR_Linux + 196)
+#define __NR_rt_sigtimedwait (__NR_Linux + 197)
+#define __NR_rt_sigqueueinfo (__NR_Linux + 198)
+#define __NR_rt_sigsuspend (__NR_Linux + 199)
+#define __NR_pread64 (__NR_Linux + 200)
+#define __NR_pwrite64 (__NR_Linux + 201)
+#define __NR_chown (__NR_Linux + 202)
+#define __NR_getcwd (__NR_Linux + 203)
+#define __NR_capget (__NR_Linux + 204)
+#define __NR_capset (__NR_Linux + 205)
+#define __NR_sigaltstack (__NR_Linux + 206)
+#define __NR_sendfile (__NR_Linux + 207)
+#define __NR_getpmsg (__NR_Linux + 208)
+#define __NR_putpmsg (__NR_Linux + 209)
+#define __NR_mmap2 (__NR_Linux + 210)
+#define __NR_truncate64 (__NR_Linux + 211)
+#define __NR_ftruncate64 (__NR_Linux + 212)
+#define __NR_stat64 (__NR_Linux + 213)
+#define __NR_lstat64 (__NR_Linux + 214)
+#define __NR_fstat64 (__NR_Linux + 215)
+#define __NR_pivot_root (__NR_Linux + 216)
+#define __NR_mincore (__NR_Linux + 217)
+#define __NR_madvise (__NR_Linux + 218)
+#define __NR_getdents64 (__NR_Linux + 219)
+#define __NR_fcntl64 (__NR_Linux + 220)
+#define __NR_reserved221 (__NR_Linux + 221)
+#define __NR_gettid (__NR_Linux + 222)
+#define __NR_readahead (__NR_Linux + 223)
+#define __NR_setxattr (__NR_Linux + 224)
+#define __NR_lsetxattr (__NR_Linux + 225)
+#define __NR_fsetxattr (__NR_Linux + 226)
+#define __NR_getxattr (__NR_Linux + 227)
+#define __NR_lgetxattr (__NR_Linux + 228)
+#define __NR_fgetxattr (__NR_Linux + 229)
+#define __NR_listxattr (__NR_Linux + 230)
+#define __NR_llistxattr (__NR_Linux + 231)
+#define __NR_flistxattr (__NR_Linux + 232)
+#define __NR_removexattr (__NR_Linux + 233)
+#define __NR_lremovexattr (__NR_Linux + 234)
+#define __NR_fremovexattr (__NR_Linux + 235)
+#define __NR_tkill (__NR_Linux + 236)
+#define __NR_sendfile64 (__NR_Linux + 237)
+#define __NR_futex (__NR_Linux + 238)
+#define __NR_sched_setaffinity (__NR_Linux + 239)
+#define __NR_sched_getaffinity (__NR_Linux + 240)
+#define __NR_io_setup (__NR_Linux + 241)
+#define __NR_io_destroy (__NR_Linux + 242)
+#define __NR_io_getevents (__NR_Linux + 243)
+#define __NR_io_submit (__NR_Linux + 244)
+#define __NR_io_cancel (__NR_Linux + 245)
+#define __NR_exit_group (__NR_Linux + 246)
+#define __NR_lookup_dcookie (__NR_Linux + 247)
+#define __NR_epoll_create (__NR_Linux + 248)
+#define __NR_epoll_ctl (__NR_Linux + 249)
+#define __NR_epoll_wait (__NR_Linux + 250)
+#define __NR_remap_file_pages (__NR_Linux + 251)
+#define __NR_set_tid_address (__NR_Linux + 252)
+#define __NR_restart_syscall (__NR_Linux + 253)
+#define __NR_fadvise64 (__NR_Linux + 254)
+#define __NR_statfs64 (__NR_Linux + 255)
+#define __NR_fstatfs64 (__NR_Linux + 256)
+#define __NR_timer_create (__NR_Linux + 257)
+#define __NR_timer_settime (__NR_Linux + 258)
+#define __NR_timer_gettime (__NR_Linux + 259)
+#define __NR_timer_getoverrun (__NR_Linux + 260)
+#define __NR_timer_delete (__NR_Linux + 261)
+#define __NR_clock_settime (__NR_Linux + 262)
+#define __NR_clock_gettime (__NR_Linux + 263)
+#define __NR_clock_getres (__NR_Linux + 264)
+#define __NR_clock_nanosleep (__NR_Linux + 265)
+#define __NR_tgkill (__NR_Linux + 266)
+#define __NR_utimes (__NR_Linux + 267)
+#define __NR_mbind (__NR_Linux + 268)
+#define __NR_get_mempolicy (__NR_Linux + 269)
+#define __NR_set_mempolicy (__NR_Linux + 270)
+#define __NR_mq_open (__NR_Linux + 271)
+#define __NR_mq_unlink (__NR_Linux + 272)
+#define __NR_mq_timedsend (__NR_Linux + 273)
+#define __NR_mq_timedreceive (__NR_Linux + 274)
+#define __NR_mq_notify (__NR_Linux + 275)
+#define __NR_mq_getsetattr (__NR_Linux + 276)
+#define __NR_vserver (__NR_Linux + 277)
+#define __NR_waitid (__NR_Linux + 278)
+/* #define __NR_sys_setaltroot (__NR_Linux + 279) */
+#define __NR_add_key (__NR_Linux + 280)
+#define __NR_request_key (__NR_Linux + 281)
+#define __NR_keyctl (__NR_Linux + 282)
+#define __NR_set_thread_area (__NR_Linux + 283)
+#define __NR_inotify_init (__NR_Linux + 284)
+#define __NR_inotify_add_watch (__NR_Linux + 285)
+#define __NR_inotify_rm_watch (__NR_Linux + 286)
+#define __NR_migrate_pages (__NR_Linux + 287)
+#define __NR_openat (__NR_Linux + 288)
+#define __NR_mkdirat (__NR_Linux + 289)
+#define __NR_mknodat (__NR_Linux + 290)
+#define __NR_fchownat (__NR_Linux + 291)
+#define __NR_futimesat (__NR_Linux + 292)
+#define __NR_fstatat64 (__NR_Linux + 293)
+#define __NR_unlinkat (__NR_Linux + 294)
+#define __NR_renameat (__NR_Linux + 295)
+#define __NR_linkat (__NR_Linux + 296)
+#define __NR_symlinkat (__NR_Linux + 297)
+#define __NR_readlinkat (__NR_Linux + 298)
+#define __NR_fchmodat (__NR_Linux + 299)
+#define __NR_faccessat (__NR_Linux + 300)
+#define __NR_pselect6 (__NR_Linux + 301)
+#define __NR_ppoll (__NR_Linux + 302)
+#define __NR_unshare (__NR_Linux + 303)
+#define __NR_splice (__NR_Linux + 304)
+#define __NR_sync_file_range (__NR_Linux + 305)
+#define __NR_tee (__NR_Linux + 306)
+#define __NR_vmsplice (__NR_Linux + 307)
+#define __NR_move_pages (__NR_Linux + 308)
+#define __NR_set_robust_list (__NR_Linux + 309)
+#define __NR_get_robust_list (__NR_Linux + 310)
+#define __NR_kexec_load (__NR_Linux + 311)
+#define __NR_getcpu (__NR_Linux + 312)
+#define __NR_epoll_pwait (__NR_Linux + 313)
+#define __NR_ioprio_set (__NR_Linux + 314)
+#define __NR_ioprio_get (__NR_Linux + 315)
+#define __NR_utimensat (__NR_Linux + 316)
+#define __NR_signalfd (__NR_Linux + 317)
+#define __NR_timerfd (__NR_Linux + 318)
+#define __NR_eventfd (__NR_Linux + 319)
+#define __NR_fallocate (__NR_Linux + 320)
+#define __NR_timerfd_create (__NR_Linux + 321)
+#define __NR_timerfd_gettime (__NR_Linux + 322)
+#define __NR_timerfd_settime (__NR_Linux + 323)
+#define __NR_signalfd4 (__NR_Linux + 324)
+#define __NR_eventfd2 (__NR_Linux + 325)
+#define __NR_epoll_create1 (__NR_Linux + 326)
+#define __NR_dup3 (__NR_Linux + 327)
+#define __NR_pipe2 (__NR_Linux + 328)
+#define __NR_inotify_init1 (__NR_Linux + 329)
+#define __NR_preadv (__NR_Linux + 330)
+#define __NR_pwritev (__NR_Linux + 331)
+#define __NR_rt_tgsigqueueinfo (__NR_Linux + 332)
+#define __NR_perf_event_open (__NR_Linux + 333)
+#define __NR_accept4 (__NR_Linux + 334)
+#define __NR_recvmmsg (__NR_Linux + 335)
+#define __NR_fanotify_init (__NR_Linux + 336)
+#define __NR_fanotify_mark (__NR_Linux + 337)
+#define __NR_prlimit64 (__NR_Linux + 338)
+#define __NR_name_to_handle_at (__NR_Linux + 339)
+#define __NR_open_by_handle_at (__NR_Linux + 340)
+#define __NR_clock_adjtime (__NR_Linux + 341)
+#define __NR_syncfs (__NR_Linux + 342)
+#define __NR_sendmmsg (__NR_Linux + 343)
+#define __NR_setns (__NR_Linux + 344)
+#define __NR_process_vm_readv (__NR_Linux + 345)
+#define __NR_process_vm_writev (__NR_Linux + 346)
+#define __NR_kcmp (__NR_Linux + 347)
+#define __NR_finit_module (__NR_Linux + 348)
+#define __NR_sched_setattr (__NR_Linux + 349)
+#define __NR_sched_getattr (__NR_Linux + 350)
+#define __NR_renameat2 (__NR_Linux + 351)
+#define __NR_seccomp (__NR_Linux + 352)
+#define __NR_getrandom (__NR_Linux + 353)
+#define __NR_memfd_create (__NR_Linux + 354)
+#define __NR_bpf (__NR_Linux + 355)
+#define __NR_execveat (__NR_Linux + 356)
+
+/*
+ * Offset of the last Linux o32 flavoured syscall
+ */
+#define __NR_Linux_syscalls 356
+
+#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
+
+#define __NR_O32_Linux 4000
+#define __NR_O32_Linux_syscalls 356
+
+#if _MIPS_SIM == _MIPS_SIM_ABI64
+
+/*
+ * Linux 64-bit syscalls are in the range from 5000 to 5999.
+ */
+#define __NR_Linux 5000
+#define __NR_read (__NR_Linux + 0)
+#define __NR_write (__NR_Linux + 1)
+#define __NR_open (__NR_Linux + 2)
+#define __NR_close (__NR_Linux + 3)
+#define __NR_stat (__NR_Linux + 4)
+#define __NR_fstat (__NR_Linux + 5)
+#define __NR_lstat (__NR_Linux + 6)
+#define __NR_poll (__NR_Linux + 7)
+#define __NR_lseek (__NR_Linux + 8)
+#define __NR_mmap (__NR_Linux + 9)
+#define __NR_mprotect (__NR_Linux + 10)
+#define __NR_munmap (__NR_Linux + 11)
+#define __NR_brk (__NR_Linux + 12)
+#define __NR_rt_sigaction (__NR_Linux + 13)
+#define __NR_rt_sigprocmask (__NR_Linux + 14)
+#define __NR_ioctl (__NR_Linux + 15)
+#define __NR_pread64 (__NR_Linux + 16)
+#define __NR_pwrite64 (__NR_Linux + 17)
+#define __NR_readv (__NR_Linux + 18)
+#define __NR_writev (__NR_Linux + 19)
+#define __NR_access (__NR_Linux + 20)
+#define __NR_pipe (__NR_Linux + 21)
+#define __NR__newselect (__NR_Linux + 22)
+#define __NR_sched_yield (__NR_Linux + 23)
+#define __NR_mremap (__NR_Linux + 24)
+#define __NR_msync (__NR_Linux + 25)
+#define __NR_mincore (__NR_Linux + 26)
+#define __NR_madvise (__NR_Linux + 27)
+#define __NR_shmget (__NR_Linux + 28)
+#define __NR_shmat (__NR_Linux + 29)
+#define __NR_shmctl (__NR_Linux + 30)
+#define __NR_dup (__NR_Linux + 31)
+#define __NR_dup2 (__NR_Linux + 32)
+#define __NR_pause (__NR_Linux + 33)
+#define __NR_nanosleep (__NR_Linux + 34)
+#define __NR_getitimer (__NR_Linux + 35)
+#define __NR_setitimer (__NR_Linux + 36)
+#define __NR_alarm (__NR_Linux + 37)
+#define __NR_getpid (__NR_Linux + 38)
+#define __NR_sendfile (__NR_Linux + 39)
+#define __NR_socket (__NR_Linux + 40)
+#define __NR_connect (__NR_Linux + 41)
+#define __NR_accept (__NR_Linux + 42)
+#define __NR_sendto (__NR_Linux + 43)
+#define __NR_recvfrom (__NR_Linux + 44)
+#define __NR_sendmsg (__NR_Linux + 45)
+#define __NR_recvmsg (__NR_Linux + 46)
+#define __NR_shutdown (__NR_Linux + 47)
+#define __NR_bind (__NR_Linux + 48)
+#define __NR_listen (__NR_Linux + 49)
+#define __NR_getsockname (__NR_Linux + 50)
+#define __NR_getpeername (__NR_Linux + 51)
+#define __NR_socketpair (__NR_Linux + 52)
+#define __NR_setsockopt (__NR_Linux + 53)
+#define __NR_getsockopt (__NR_Linux + 54)
+#define __NR_clone (__NR_Linux + 55)
+#define __NR_fork (__NR_Linux + 56)
+#define __NR_execve (__NR_Linux + 57)
+#define __NR_exit (__NR_Linux + 58)
+#define __NR_wait4 (__NR_Linux + 59)
+#define __NR_kill (__NR_Linux + 60)
+#define __NR_uname (__NR_Linux + 61)
+#define __NR_semget (__NR_Linux + 62)
+#define __NR_semop (__NR_Linux + 63)
+#define __NR_semctl (__NR_Linux + 64)
+#define __NR_shmdt (__NR_Linux + 65)
+#define __NR_msgget (__NR_Linux + 66)
+#define __NR_msgsnd (__NR_Linux + 67)
+#define __NR_msgrcv (__NR_Linux + 68)
+#define __NR_msgctl (__NR_Linux + 69)
+#define __NR_fcntl (__NR_Linux + 70)
+#define __NR_flock (__NR_Linux + 71)
+#define __NR_fsync (__NR_Linux + 72)
+#define __NR_fdatasync (__NR_Linux + 73)
+#define __NR_truncate (__NR_Linux + 74)
+#define __NR_ftruncate (__NR_Linux + 75)
+#define __NR_getdents (__NR_Linux + 76)
+#define __NR_getcwd (__NR_Linux + 77)
+#define __NR_chdir (__NR_Linux + 78)
+#define __NR_fchdir (__NR_Linux + 79)
+#define __NR_rename (__NR_Linux + 80)
+#define __NR_mkdir (__NR_Linux + 81)
+#define __NR_rmdir (__NR_Linux + 82)
+#define __NR_creat (__NR_Linux + 83)
+#define __NR_link (__NR_Linux + 84)
+#define __NR_unlink (__NR_Linux + 85)
+#define __NR_symlink (__NR_Linux + 86)
+#define __NR_readlink (__NR_Linux + 87)
+#define __NR_chmod (__NR_Linux + 88)
+#define __NR_fchmod (__NR_Linux + 89)
+#define __NR_chown (__NR_Linux + 90)
+#define __NR_fchown (__NR_Linux + 91)
+#define __NR_lchown (__NR_Linux + 92)
+#define __NR_umask (__NR_Linux + 93)
+#define __NR_gettimeofday (__NR_Linux + 94)
+#define __NR_getrlimit (__NR_Linux + 95)
+#define __NR_getrusage (__NR_Linux + 96)
+#define __NR_sysinfo (__NR_Linux + 97)
+#define __NR_times (__NR_Linux + 98)
+#define __NR_ptrace (__NR_Linux + 99)
+#define __NR_getuid (__NR_Linux + 100)
+#define __NR_syslog (__NR_Linux + 101)
+#define __NR_getgid (__NR_Linux + 102)
+#define __NR_setuid (__NR_Linux + 103)
+#define __NR_setgid (__NR_Linux + 104)
+#define __NR_geteuid (__NR_Linux + 105)
+#define __NR_getegid (__NR_Linux + 106)
+#define __NR_setpgid (__NR_Linux + 107)
+#define __NR_getppid (__NR_Linux + 108)
+#define __NR_getpgrp (__NR_Linux + 109)
+#define __NR_setsid (__NR_Linux + 110)
+#define __NR_setreuid (__NR_Linux + 111)
+#define __NR_setregid (__NR_Linux + 112)
+#define __NR_getgroups (__NR_Linux + 113)
+#define __NR_setgroups (__NR_Linux + 114)
+#define __NR_setresuid (__NR_Linux + 115)
+#define __NR_getresuid (__NR_Linux + 116)
+#define __NR_setresgid (__NR_Linux + 117)
+#define __NR_getresgid (__NR_Linux + 118)
+#define __NR_getpgid (__NR_Linux + 119)
+#define __NR_setfsuid (__NR_Linux + 120)
+#define __NR_setfsgid (__NR_Linux + 121)
+#define __NR_getsid (__NR_Linux + 122)
+#define __NR_capget (__NR_Linux + 123)
+#define __NR_capset (__NR_Linux + 124)
+#define __NR_rt_sigpending (__NR_Linux + 125)
+#define __NR_rt_sigtimedwait (__NR_Linux + 126)
+#define __NR_rt_sigqueueinfo (__NR_Linux + 127)
+#define __NR_rt_sigsuspend (__NR_Linux + 128)
+#define __NR_sigaltstack (__NR_Linux + 129)
+#define __NR_utime (__NR_Linux + 130)
+#define __NR_mknod (__NR_Linux + 131)
+#define __NR_personality (__NR_Linux + 132)
+#define __NR_ustat (__NR_Linux + 133)
+#define __NR_statfs (__NR_Linux + 134)
+#define __NR_fstatfs (__NR_Linux + 135)
+#define __NR_sysfs (__NR_Linux + 136)
+#define __NR_getpriority (__NR_Linux + 137)
+#define __NR_setpriority (__NR_Linux + 138)
+#define __NR_sched_setparam (__NR_Linux + 139)
+#define __NR_sched_getparam (__NR_Linux + 140)
+#define __NR_sched_setscheduler (__NR_Linux + 141)
+#define __NR_sched_getscheduler (__NR_Linux + 142)
+#define __NR_sched_get_priority_max (__NR_Linux + 143)
+#define __NR_sched_get_priority_min (__NR_Linux + 144)
+#define __NR_sched_rr_get_interval (__NR_Linux + 145)
+#define __NR_mlock (__NR_Linux + 146)
+#define __NR_munlock (__NR_Linux + 147)
+#define __NR_mlockall (__NR_Linux + 148)
+#define __NR_munlockall (__NR_Linux + 149)
+#define __NR_vhangup (__NR_Linux + 150)
+#define __NR_pivot_root (__NR_Linux + 151)
+#define __NR__sysctl (__NR_Linux + 152)
+#define __NR_prctl (__NR_Linux + 153)
+#define __NR_adjtimex (__NR_Linux + 154)
+#define __NR_setrlimit (__NR_Linux + 155)
+#define __NR_chroot (__NR_Linux + 156)
+#define __NR_sync (__NR_Linux + 157)
+#define __NR_acct (__NR_Linux + 158)
+#define __NR_settimeofday (__NR_Linux + 159)
+#define __NR_mount (__NR_Linux + 160)
+#define __NR_umount2 (__NR_Linux + 161)
+#define __NR_swapon (__NR_Linux + 162)
+#define __NR_swapoff (__NR_Linux + 163)
+#define __NR_reboot (__NR_Linux + 164)
+#define __NR_sethostname (__NR_Linux + 165)
+#define __NR_setdomainname (__NR_Linux + 166)
+#define __NR_create_module (__NR_Linux + 167)
+#define __NR_init_module (__NR_Linux + 168)
+#define __NR_delete_module (__NR_Linux + 169)
+#define __NR_get_kernel_syms (__NR_Linux + 170)
+#define __NR_query_module (__NR_Linux + 171)
+#define __NR_quotactl (__NR_Linux + 172)
+#define __NR_nfsservctl (__NR_Linux + 173)
+#define __NR_getpmsg (__NR_Linux + 174)
+#define __NR_putpmsg (__NR_Linux + 175)
+#define __NR_afs_syscall (__NR_Linux + 176)
+#define __NR_reserved177 (__NR_Linux + 177)
+#define __NR_gettid (__NR_Linux + 178)
+#define __NR_readahead (__NR_Linux + 179)
+#define __NR_setxattr (__NR_Linux + 180)
+#define __NR_lsetxattr (__NR_Linux + 181)
+#define __NR_fsetxattr (__NR_Linux + 182)
+#define __NR_getxattr (__NR_Linux + 183)
+#define __NR_lgetxattr (__NR_Linux + 184)
+#define __NR_fgetxattr (__NR_Linux + 185)
+#define __NR_listxattr (__NR_Linux + 186)
+#define __NR_llistxattr (__NR_Linux + 187)
+#define __NR_flistxattr (__NR_Linux + 188)
+#define __NR_removexattr (__NR_Linux + 189)
+#define __NR_lremovexattr (__NR_Linux + 190)
+#define __NR_fremovexattr (__NR_Linux + 191)
+#define __NR_tkill (__NR_Linux + 192)
+#define __NR_reserved193 (__NR_Linux + 193)
+#define __NR_futex (__NR_Linux + 194)
+#define __NR_sched_setaffinity (__NR_Linux + 195)
+#define __NR_sched_getaffinity (__NR_Linux + 196)
+#define __NR_cacheflush (__NR_Linux + 197)
+#define __NR_cachectl (__NR_Linux + 198)
+#define __NR_sysmips (__NR_Linux + 199)
+#define __NR_io_setup (__NR_Linux + 200)
+#define __NR_io_destroy (__NR_Linux + 201)
+#define __NR_io_getevents (__NR_Linux + 202)
+#define __NR_io_submit (__NR_Linux + 203)
+#define __NR_io_cancel (__NR_Linux + 204)
+#define __NR_exit_group (__NR_Linux + 205)
+#define __NR_lookup_dcookie (__NR_Linux + 206)
+#define __NR_epoll_create (__NR_Linux + 207)
+#define __NR_epoll_ctl (__NR_Linux + 208)
+#define __NR_epoll_wait (__NR_Linux + 209)
+#define __NR_remap_file_pages (__NR_Linux + 210)
+#define __NR_rt_sigreturn (__NR_Linux + 211)
+#define __NR_set_tid_address (__NR_Linux + 212)
+#define __NR_restart_syscall (__NR_Linux + 213)
+#define __NR_semtimedop (__NR_Linux + 214)
+#define __NR_fadvise64 (__NR_Linux + 215)
+#define __NR_timer_create (__NR_Linux + 216)
+#define __NR_timer_settime (__NR_Linux + 217)
+#define __NR_timer_gettime (__NR_Linux + 218)
+#define __NR_timer_getoverrun (__NR_Linux + 219)
+#define __NR_timer_delete (__NR_Linux + 220)
+#define __NR_clock_settime (__NR_Linux + 221)
+#define __NR_clock_gettime (__NR_Linux + 222)
+#define __NR_clock_getres (__NR_Linux + 223)
+#define __NR_clock_nanosleep (__NR_Linux + 224)
+#define __NR_tgkill (__NR_Linux + 225)
+#define __NR_utimes (__NR_Linux + 226)
+#define __NR_mbind (__NR_Linux + 227)
+#define __NR_get_mempolicy (__NR_Linux + 228)
+#define __NR_set_mempolicy (__NR_Linux + 229)
+#define __NR_mq_open (__NR_Linux + 230)
+#define __NR_mq_unlink (__NR_Linux + 231)
+#define __NR_mq_timedsend (__NR_Linux + 232)
+#define __NR_mq_timedreceive (__NR_Linux + 233)
+#define __NR_mq_notify (__NR_Linux + 234)
+#define __NR_mq_getsetattr (__NR_Linux + 235)
+#define __NR_vserver (__NR_Linux + 236)
+#define __NR_waitid (__NR_Linux + 237)
+/* #define __NR_sys_setaltroot (__NR_Linux + 238) */
+#define __NR_add_key (__NR_Linux + 239)
+#define __NR_request_key (__NR_Linux + 240)
+#define __NR_keyctl (__NR_Linux + 241)
+#define __NR_set_thread_area (__NR_Linux + 242)
+#define __NR_inotify_init (__NR_Linux + 243)
+#define __NR_inotify_add_watch (__NR_Linux + 244)
+#define __NR_inotify_rm_watch (__NR_Linux + 245)
+#define __NR_migrate_pages (__NR_Linux + 246)
+#define __NR_openat (__NR_Linux + 247)
+#define __NR_mkdirat (__NR_Linux + 248)
+#define __NR_mknodat (__NR_Linux + 249)
+#define __NR_fchownat (__NR_Linux + 250)
+#define __NR_futimesat (__NR_Linux + 251)
+#define __NR_newfstatat (__NR_Linux + 252)
+#define __NR_unlinkat (__NR_Linux + 253)
+#define __NR_renameat (__NR_Linux + 254)
+#define __NR_linkat (__NR_Linux + 255)
+#define __NR_symlinkat (__NR_Linux + 256)
+#define __NR_readlinkat (__NR_Linux + 257)
+#define __NR_fchmodat (__NR_Linux + 258)
+#define __NR_faccessat (__NR_Linux + 259)
+#define __NR_pselect6 (__NR_Linux + 260)
+#define __NR_ppoll (__NR_Linux + 261)
+#define __NR_unshare (__NR_Linux + 262)
+#define __NR_splice (__NR_Linux + 263)
+#define __NR_sync_file_range (__NR_Linux + 264)
+#define __NR_tee (__NR_Linux + 265)
+#define __NR_vmsplice (__NR_Linux + 266)
+#define __NR_move_pages (__NR_Linux + 267)
+#define __NR_set_robust_list (__NR_Linux + 268)
+#define __NR_get_robust_list (__NR_Linux + 269)
+#define __NR_kexec_load (__NR_Linux + 270)
+#define __NR_getcpu (__NR_Linux + 271)
+#define __NR_epoll_pwait (__NR_Linux + 272)
+#define __NR_ioprio_set (__NR_Linux + 273)
+#define __NR_ioprio_get (__NR_Linux + 274)
+#define __NR_utimensat (__NR_Linux + 275)
+#define __NR_signalfd (__NR_Linux + 276)
+#define __NR_timerfd (__NR_Linux + 277)
+#define __NR_eventfd (__NR_Linux + 278)
+#define __NR_fallocate (__NR_Linux + 279)
+#define __NR_timerfd_create (__NR_Linux + 280)
+#define __NR_timerfd_gettime (__NR_Linux + 281)
+#define __NR_timerfd_settime (__NR_Linux + 282)
+#define __NR_signalfd4 (__NR_Linux + 283)
+#define __NR_eventfd2 (__NR_Linux + 284)
+#define __NR_epoll_create1 (__NR_Linux + 285)
+#define __NR_dup3 (__NR_Linux + 286)
+#define __NR_pipe2 (__NR_Linux + 287)
+#define __NR_inotify_init1 (__NR_Linux + 288)
+#define __NR_preadv (__NR_Linux + 289)
+#define __NR_pwritev (__NR_Linux + 290)
+#define __NR_rt_tgsigqueueinfo (__NR_Linux + 291)
+#define __NR_perf_event_open (__NR_Linux + 292)
+#define __NR_accept4 (__NR_Linux + 293)
+#define __NR_recvmmsg (__NR_Linux + 294)
+#define __NR_fanotify_init (__NR_Linux + 295)
+#define __NR_fanotify_mark (__NR_Linux + 296)
+#define __NR_prlimit64 (__NR_Linux + 297)
+#define __NR_name_to_handle_at (__NR_Linux + 298)
+#define __NR_open_by_handle_at (__NR_Linux + 299)
+#define __NR_clock_adjtime (__NR_Linux + 300)
+#define __NR_syncfs (__NR_Linux + 301)
+#define __NR_sendmmsg (__NR_Linux + 302)
+#define __NR_setns (__NR_Linux + 303)
+#define __NR_process_vm_readv (__NR_Linux + 304)
+#define __NR_process_vm_writev (__NR_Linux + 305)
+#define __NR_kcmp (__NR_Linux + 306)
+#define __NR_finit_module (__NR_Linux + 307)
+#define __NR_getdents64 (__NR_Linux + 308)
+#define __NR_sched_setattr (__NR_Linux + 309)
+#define __NR_sched_getattr (__NR_Linux + 310)
+#define __NR_renameat2 (__NR_Linux + 311)
+#define __NR_seccomp (__NR_Linux + 312)
+#define __NR_getrandom (__NR_Linux + 313)
+#define __NR_memfd_create (__NR_Linux + 314)
+#define __NR_bpf (__NR_Linux + 315)
+#define __NR_execveat (__NR_Linux + 316)
+
+/*
+ * Offset of the last Linux 64-bit flavoured syscall
+ */
+#define __NR_Linux_syscalls 316
+
+#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
+
+#define __NR_64_Linux 5000
+#define __NR_64_Linux_syscalls 316
+
+#if _MIPS_SIM == _MIPS_SIM_NABI32
+
+/*
+ * Linux N32 syscalls are in the range from 6000 to 6999.
+ */
+#define __NR_Linux 6000
+#define __NR_read (__NR_Linux + 0)
+#define __NR_write (__NR_Linux + 1)
+#define __NR_open (__NR_Linux + 2)
+#define __NR_close (__NR_Linux + 3)
+#define __NR_stat (__NR_Linux + 4)
+#define __NR_fstat (__NR_Linux + 5)
+#define __NR_lstat (__NR_Linux + 6)
+#define __NR_poll (__NR_Linux + 7)
+#define __NR_lseek (__NR_Linux + 8)
+#define __NR_mmap (__NR_Linux + 9)
+#define __NR_mprotect (__NR_Linux + 10)
+#define __NR_munmap (__NR_Linux + 11)
+#define __NR_brk (__NR_Linux + 12)
+#define __NR_rt_sigaction (__NR_Linux + 13)
+#define __NR_rt_sigprocmask (__NR_Linux + 14)
+#define __NR_ioctl (__NR_Linux + 15)
+#define __NR_pread64 (__NR_Linux + 16)
+#define __NR_pwrite64 (__NR_Linux + 17)
+#define __NR_readv (__NR_Linux + 18)
+#define __NR_writev (__NR_Linux + 19)
+#define __NR_access (__NR_Linux + 20)
+#define __NR_pipe (__NR_Linux + 21)
+#define __NR__newselect (__NR_Linux + 22)
+#define __NR_sched_yield (__NR_Linux + 23)
+#define __NR_mremap (__NR_Linux + 24)
+#define __NR_msync (__NR_Linux + 25)
+#define __NR_mincore (__NR_Linux + 26)
+#define __NR_madvise (__NR_Linux + 27)
+#define __NR_shmget (__NR_Linux + 28)
+#define __NR_shmat (__NR_Linux + 29)
+#define __NR_shmctl (__NR_Linux + 30)
+#define __NR_dup (__NR_Linux + 31)
+#define __NR_dup2 (__NR_Linux + 32)
+#define __NR_pause (__NR_Linux + 33)
+#define __NR_nanosleep (__NR_Linux + 34)
+#define __NR_getitimer (__NR_Linux + 35)
+#define __NR_setitimer (__NR_Linux + 36)
+#define __NR_alarm (__NR_Linux + 37)
+#define __NR_getpid (__NR_Linux + 38)
+#define __NR_sendfile (__NR_Linux + 39)
+#define __NR_socket (__NR_Linux + 40)
+#define __NR_connect (__NR_Linux + 41)
+#define __NR_accept (__NR_Linux + 42)
+#define __NR_sendto (__NR_Linux + 43)
+#define __NR_recvfrom (__NR_Linux + 44)
+#define __NR_sendmsg (__NR_Linux + 45)
+#define __NR_recvmsg (__NR_Linux + 46)
+#define __NR_shutdown (__NR_Linux + 47)
+#define __NR_bind (__NR_Linux + 48)
+#define __NR_listen (__NR_Linux + 49)
+#define __NR_getsockname (__NR_Linux + 50)
+#define __NR_getpeername (__NR_Linux + 51)
+#define __NR_socketpair (__NR_Linux + 52)
+#define __NR_setsockopt (__NR_Linux + 53)
+#define __NR_getsockopt (__NR_Linux + 54)
+#define __NR_clone (__NR_Linux + 55)
+#define __NR_fork (__NR_Linux + 56)
+#define __NR_execve (__NR_Linux + 57)
+#define __NR_exit (__NR_Linux + 58)
+#define __NR_wait4 (__NR_Linux + 59)
+#define __NR_kill (__NR_Linux + 60)
+#define __NR_uname (__NR_Linux + 61)
+#define __NR_semget (__NR_Linux + 62)
+#define __NR_semop (__NR_Linux + 63)
+#define __NR_semctl (__NR_Linux + 64)
+#define __NR_shmdt (__NR_Linux + 65)
+#define __NR_msgget (__NR_Linux + 66)
+#define __NR_msgsnd (__NR_Linux + 67)
+#define __NR_msgrcv (__NR_Linux + 68)
+#define __NR_msgctl (__NR_Linux + 69)
+#define __NR_fcntl (__NR_Linux + 70)
+#define __NR_flock (__NR_Linux + 71)
+#define __NR_fsync (__NR_Linux + 72)
+#define __NR_fdatasync (__NR_Linux + 73)
+#define __NR_truncate (__NR_Linux + 74)
+#define __NR_ftruncate (__NR_Linux + 75)
+#define __NR_getdents (__NR_Linux + 76)
+#define __NR_getcwd (__NR_Linux + 77)
+#define __NR_chdir (__NR_Linux + 78)
+#define __NR_fchdir (__NR_Linux + 79)
+#define __NR_rename (__NR_Linux + 80)
+#define __NR_mkdir (__NR_Linux + 81)
+#define __NR_rmdir (__NR_Linux + 82)
+#define __NR_creat (__NR_Linux + 83)
+#define __NR_link (__NR_Linux + 84)
+#define __NR_unlink (__NR_Linux + 85)
+#define __NR_symlink (__NR_Linux + 86)
+#define __NR_readlink (__NR_Linux + 87)
+#define __NR_chmod (__NR_Linux + 88)
+#define __NR_fchmod (__NR_Linux + 89)
+#define __NR_chown (__NR_Linux + 90)
+#define __NR_fchown (__NR_Linux + 91)
+#define __NR_lchown (__NR_Linux + 92)
+#define __NR_umask (__NR_Linux + 93)
+#define __NR_gettimeofday (__NR_Linux + 94)
+#define __NR_getrlimit (__NR_Linux + 95)
+#define __NR_getrusage (__NR_Linux + 96)
+#define __NR_sysinfo (__NR_Linux + 97)
+#define __NR_times (__NR_Linux + 98)
+#define __NR_ptrace (__NR_Linux + 99)
+#define __NR_getuid (__NR_Linux + 100)
+#define __NR_syslog (__NR_Linux + 101)
+#define __NR_getgid (__NR_Linux + 102)
+#define __NR_setuid (__NR_Linux + 103)
+#define __NR_setgid (__NR_Linux + 104)
+#define __NR_geteuid (__NR_Linux + 105)
+#define __NR_getegid (__NR_Linux + 106)
+#define __NR_setpgid (__NR_Linux + 107)
+#define __NR_getppid (__NR_Linux + 108)
+#define __NR_getpgrp (__NR_Linux + 109)
+#define __NR_setsid (__NR_Linux + 110)
+#define __NR_setreuid (__NR_Linux + 111)
+#define __NR_setregid (__NR_Linux + 112)
+#define __NR_getgroups (__NR_Linux + 113)
+#define __NR_setgroups (__NR_Linux + 114)
+#define __NR_setresuid (__NR_Linux + 115)
+#define __NR_getresuid (__NR_Linux + 116)
+#define __NR_setresgid (__NR_Linux + 117)
+#define __NR_getresgid (__NR_Linux + 118)
+#define __NR_getpgid (__NR_Linux + 119)
+#define __NR_setfsuid (__NR_Linux + 120)
+#define __NR_setfsgid (__NR_Linux + 121)
+#define __NR_getsid (__NR_Linux + 122)
+#define __NR_capget (__NR_Linux + 123)
+#define __NR_capset (__NR_Linux + 124)
+#define __NR_rt_sigpending (__NR_Linux + 125)
+#define __NR_rt_sigtimedwait (__NR_Linux + 126)
+#define __NR_rt_sigqueueinfo (__NR_Linux + 127)
+#define __NR_rt_sigsuspend (__NR_Linux + 128)
+#define __NR_sigaltstack (__NR_Linux + 129)
+#define __NR_utime (__NR_Linux + 130)
+#define __NR_mknod (__NR_Linux + 131)
+#define __NR_personality (__NR_Linux + 132)
+#define __NR_ustat (__NR_Linux + 133)
+#define __NR_statfs (__NR_Linux + 134)
+#define __NR_fstatfs (__NR_Linux + 135)
+#define __NR_sysfs (__NR_Linux + 136)
+#define __NR_getpriority (__NR_Linux + 137)
+#define __NR_setpriority (__NR_Linux + 138)
+#define __NR_sched_setparam (__NR_Linux + 139)
+#define __NR_sched_getparam (__NR_Linux + 140)
+#define __NR_sched_setscheduler (__NR_Linux + 141)
+#define __NR_sched_getscheduler (__NR_Linux + 142)
+#define __NR_sched_get_priority_max (__NR_Linux + 143)
+#define __NR_sched_get_priority_min (__NR_Linux + 144)
+#define __NR_sched_rr_get_interval (__NR_Linux + 145)
+#define __NR_mlock (__NR_Linux + 146)
+#define __NR_munlock (__NR_Linux + 147)
+#define __NR_mlockall (__NR_Linux + 148)
+#define __NR_munlockall (__NR_Linux + 149)
+#define __NR_vhangup (__NR_Linux + 150)
+#define __NR_pivot_root (__NR_Linux + 151)
+#define __NR__sysctl (__NR_Linux + 152)
+#define __NR_prctl (__NR_Linux + 153)
+#define __NR_adjtimex (__NR_Linux + 154)
+#define __NR_setrlimit (__NR_Linux + 155)
+#define __NR_chroot (__NR_Linux + 156)
+#define __NR_sync (__NR_Linux + 157)
+#define __NR_acct (__NR_Linux + 158)
+#define __NR_settimeofday (__NR_Linux + 159)
+#define __NR_mount (__NR_Linux + 160)
+#define __NR_umount2 (__NR_Linux + 161)
+#define __NR_swapon (__NR_Linux + 162)
+#define __NR_swapoff (__NR_Linux + 163)
+#define __NR_reboot (__NR_Linux + 164)
+#define __NR_sethostname (__NR_Linux + 165)
+#define __NR_setdomainname (__NR_Linux + 166)
+#define __NR_create_module (__NR_Linux + 167)
+#define __NR_init_module (__NR_Linux + 168)
+#define __NR_delete_module (__NR_Linux + 169)
+#define __NR_get_kernel_syms (__NR_Linux + 170)
+#define __NR_query_module (__NR_Linux + 171)
+#define __NR_quotactl (__NR_Linux + 172)
+#define __NR_nfsservctl (__NR_Linux + 173)
+#define __NR_getpmsg (__NR_Linux + 174)
+#define __NR_putpmsg (__NR_Linux + 175)
+#define __NR_afs_syscall (__NR_Linux + 176)
+#define __NR_reserved177 (__NR_Linux + 177)
+#define __NR_gettid (__NR_Linux + 178)
+#define __NR_readahead (__NR_Linux + 179)
+#define __NR_setxattr (__NR_Linux + 180)
+#define __NR_lsetxattr (__NR_Linux + 181)
+#define __NR_fsetxattr (__NR_Linux + 182)
+#define __NR_getxattr (__NR_Linux + 183)
+#define __NR_lgetxattr (__NR_Linux + 184)
+#define __NR_fgetxattr (__NR_Linux + 185)
+#define __NR_listxattr (__NR_Linux + 186)
+#define __NR_llistxattr (__NR_Linux + 187)
+#define __NR_flistxattr (__NR_Linux + 188)
+#define __NR_removexattr (__NR_Linux + 189)
+#define __NR_lremovexattr (__NR_Linux + 190)
+#define __NR_fremovexattr (__NR_Linux + 191)
+#define __NR_tkill (__NR_Linux + 192)
+#define __NR_reserved193 (__NR_Linux + 193)
+#define __NR_futex (__NR_Linux + 194)
+#define __NR_sched_setaffinity (__NR_Linux + 195)
+#define __NR_sched_getaffinity (__NR_Linux + 196)
+#define __NR_cacheflush (__NR_Linux + 197)
+#define __NR_cachectl (__NR_Linux + 198)
+#define __NR_sysmips (__NR_Linux + 199)
+#define __NR_io_setup (__NR_Linux + 200)
+#define __NR_io_destroy (__NR_Linux + 201)
+#define __NR_io_getevents (__NR_Linux + 202)
+#define __NR_io_submit (__NR_Linux + 203)
+#define __NR_io_cancel (__NR_Linux + 204)
+#define __NR_exit_group (__NR_Linux + 205)
+#define __NR_lookup_dcookie (__NR_Linux + 206)
+#define __NR_epoll_create (__NR_Linux + 207)
+#define __NR_epoll_ctl (__NR_Linux + 208)
+#define __NR_epoll_wait (__NR_Linux + 209)
+#define __NR_remap_file_pages (__NR_Linux + 210)
+#define __NR_rt_sigreturn (__NR_Linux + 211)
+#define __NR_fcntl64 (__NR_Linux + 212)
+#define __NR_set_tid_address (__NR_Linux + 213)
+#define __NR_restart_syscall (__NR_Linux + 214)
+#define __NR_semtimedop (__NR_Linux + 215)
+#define __NR_fadvise64 (__NR_Linux + 216)
+#define __NR_statfs64 (__NR_Linux + 217)
+#define __NR_fstatfs64 (__NR_Linux + 218)
+#define __NR_sendfile64 (__NR_Linux + 219)
+#define __NR_timer_create (__NR_Linux + 220)
+#define __NR_timer_settime (__NR_Linux + 221)
+#define __NR_timer_gettime (__NR_Linux + 222)
+#define __NR_timer_getoverrun (__NR_Linux + 223)
+#define __NR_timer_delete (__NR_Linux + 224)
+#define __NR_clock_settime (__NR_Linux + 225)
+#define __NR_clock_gettime (__NR_Linux + 226)
+#define __NR_clock_getres (__NR_Linux + 227)
+#define __NR_clock_nanosleep (__NR_Linux + 228)
+#define __NR_tgkill (__NR_Linux + 229)
+#define __NR_utimes (__NR_Linux + 230)
+#define __NR_mbind (__NR_Linux + 231)
+#define __NR_get_mempolicy (__NR_Linux + 232)
+#define __NR_set_mempolicy (__NR_Linux + 233)
+#define __NR_mq_open (__NR_Linux + 234)
+#define __NR_mq_unlink (__NR_Linux + 235)
+#define __NR_mq_timedsend (__NR_Linux + 236)
+#define __NR_mq_timedreceive (__NR_Linux + 237)
+#define __NR_mq_notify (__NR_Linux + 238)
+#define __NR_mq_getsetattr (__NR_Linux + 239)
+#define __NR_vserver (__NR_Linux + 240)
+#define __NR_waitid (__NR_Linux + 241)
+/* #define __NR_sys_setaltroot (__NR_Linux + 242) */
+#define __NR_add_key (__NR_Linux + 243)
+#define __NR_request_key (__NR_Linux + 244)
+#define __NR_keyctl (__NR_Linux + 245)
+#define __NR_set_thread_area (__NR_Linux + 246)
+#define __NR_inotify_init (__NR_Linux + 247)
+#define __NR_inotify_add_watch (__NR_Linux + 248)
+#define __NR_inotify_rm_watch (__NR_Linux + 249)
+#define __NR_migrate_pages (__NR_Linux + 250)
+#define __NR_openat (__NR_Linux + 251)
+#define __NR_mkdirat (__NR_Linux + 252)
+#define __NR_mknodat (__NR_Linux + 253)
+#define __NR_fchownat (__NR_Linux + 254)
+#define __NR_futimesat (__NR_Linux + 255)
+#define __NR_newfstatat (__NR_Linux + 256)
+#define __NR_unlinkat (__NR_Linux + 257)
+#define __NR_renameat (__NR_Linux + 258)
+#define __NR_linkat (__NR_Linux + 259)
+#define __NR_symlinkat (__NR_Linux + 260)
+#define __NR_readlinkat (__NR_Linux + 261)
+#define __NR_fchmodat (__NR_Linux + 262)
+#define __NR_faccessat (__NR_Linux + 263)
+#define __NR_pselect6 (__NR_Linux + 264)
+#define __NR_ppoll (__NR_Linux + 265)
+#define __NR_unshare (__NR_Linux + 266)
+#define __NR_splice (__NR_Linux + 267)
+#define __NR_sync_file_range (__NR_Linux + 268)
+#define __NR_tee (__NR_Linux + 269)
+#define __NR_vmsplice (__NR_Linux + 270)
+#define __NR_move_pages (__NR_Linux + 271)
+#define __NR_set_robust_list (__NR_Linux + 272)
+#define __NR_get_robust_list (__NR_Linux + 273)
+#define __NR_kexec_load (__NR_Linux + 274)
+#define __NR_getcpu (__NR_Linux + 275)
+#define __NR_epoll_pwait (__NR_Linux + 276)
+#define __NR_ioprio_set (__NR_Linux + 277)
+#define __NR_ioprio_get (__NR_Linux + 278)
+#define __NR_utimensat (__NR_Linux + 279)
+#define __NR_signalfd (__NR_Linux + 280)
+#define __NR_timerfd (__NR_Linux + 281)
+#define __NR_eventfd (__NR_Linux + 282)
+#define __NR_fallocate (__NR_Linux + 283)
+#define __NR_timerfd_create (__NR_Linux + 284)
+#define __NR_timerfd_gettime (__NR_Linux + 285)
+#define __NR_timerfd_settime (__NR_Linux + 286)
+#define __NR_signalfd4 (__NR_Linux + 287)
+#define __NR_eventfd2 (__NR_Linux + 288)
+#define __NR_epoll_create1 (__NR_Linux + 289)
+#define __NR_dup3 (__NR_Linux + 290)
+#define __NR_pipe2 (__NR_Linux + 291)
+#define __NR_inotify_init1 (__NR_Linux + 292)
+#define __NR_preadv (__NR_Linux + 293)
+#define __NR_pwritev (__NR_Linux + 294)
+#define __NR_rt_tgsigqueueinfo (__NR_Linux + 295)
+#define __NR_perf_event_open (__NR_Linux + 296)
+#define __NR_accept4 (__NR_Linux + 297)
+#define __NR_recvmmsg (__NR_Linux + 298)
+#define __NR_getdents64 (__NR_Linux + 299)
+#define __NR_fanotify_init (__NR_Linux + 300)
+#define __NR_fanotify_mark (__NR_Linux + 301)
+#define __NR_prlimit64 (__NR_Linux + 302)
+#define __NR_name_to_handle_at (__NR_Linux + 303)
+#define __NR_open_by_handle_at (__NR_Linux + 304)
+#define __NR_clock_adjtime (__NR_Linux + 305)
+#define __NR_syncfs (__NR_Linux + 306)
+#define __NR_sendmmsg (__NR_Linux + 307)
+#define __NR_setns (__NR_Linux + 308)
+#define __NR_process_vm_readv (__NR_Linux + 309)
+#define __NR_process_vm_writev (__NR_Linux + 310)
+#define __NR_kcmp (__NR_Linux + 311)
+#define __NR_finit_module (__NR_Linux + 312)
+#define __NR_sched_setattr (__NR_Linux + 313)
+#define __NR_sched_getattr (__NR_Linux + 314)
+#define __NR_renameat2 (__NR_Linux + 315)
+#define __NR_seccomp (__NR_Linux + 316)
+#define __NR_getrandom (__NR_Linux + 317)
+#define __NR_memfd_create (__NR_Linux + 318)
+#define __NR_bpf (__NR_Linux + 319)
+#define __NR_execveat (__NR_Linux + 320)
+
+/*
+ * Offset of the last N32 flavoured syscall
+ */
+#define __NR_Linux_syscalls 320
+
+#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
+
+#define __NR_N32_Linux 6000
+#define __NR_N32_Linux_syscalls 320
+
+#endif /* _ASM_UNISTD_H */
--git a/linux-headers/asm-powerpc/unistd.h b/linux-headers/asm-powerpc/unistd.h
new file mode 100644
index 0000000..28deee0
--- /dev/null
+++ b/linux-headers/asm-powerpc/unistd.h
@@ -0,0 +1,392 @@
+/*
+ * This file contains the system call numbers.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _ASM_POWERPC_UNISTD_H_
+#define _ASM_POWERPC_UNISTD_H_
+
+
+#define __NR_restart_syscall 0
+#define __NR_exit 1
+#define __NR_fork 2
+#define __NR_read 3
+#define __NR_write 4
+#define __NR_open 5
+#define __NR_close 6
+#define __NR_waitpid 7
+#define __NR_creat 8
+#define __NR_link 9
+#define __NR_unlink 10
+#define __NR_execve 11
+#define __NR_chdir 12
+#define __NR_time 13
+#define __NR_mknod 14
+#define __NR_chmod 15
+#define __NR_lchown 16
+#define __NR_break 17
+#define __NR_oldstat 18
+#define __NR_lseek 19
+#define __NR_getpid 20
+#define __NR_mount 21
+#define __NR_umount 22
+#define __NR_setuid 23
+#define __NR_getuid 24
+#define __NR_stime 25
+#define __NR_ptrace 26
+#define __NR_alarm 27
+#define __NR_oldfstat 28
+#define __NR_pause 29
+#define __NR_utime 30
+#define __NR_stty 31
+#define __NR_gtty 32
+#define __NR_access 33
+#define __NR_nice 34
+#define __NR_ftime 35
+#define __NR_sync 36
+#define __NR_kill 37
+#define __NR_rename 38
+#define __NR_mkdir 39
+#define __NR_rmdir 40
+#define __NR_dup 41
+#define __NR_pipe 42
+#define __NR_times 43
+#define __NR_prof 44
+#define __NR_brk 45
+#define __NR_setgid 46
+#define __NR_getgid 47
+#define __NR_signal 48
+#define __NR_geteuid 49
+#define __NR_getegid 50
+#define __NR_acct 51
+#define __NR_umount2 52
+#define __NR_lock 53
+#define __NR_ioctl 54
+#define __NR_fcntl 55
+#define __NR_mpx 56
+#define __NR_setpgid 57
+#define __NR_ulimit 58
+#define __NR_oldolduname 59
+#define __NR_umask 60
+#define __NR_chroot 61
+#define __NR_ustat 62
+#define __NR_dup2 63
+#define __NR_getppid 64
+#define __NR_getpgrp 65
+#define __NR_setsid 66
+#define __NR_sigaction 67
+#define __NR_sgetmask 68
+#define __NR_ssetmask 69
+#define __NR_setreuid 70
+#define __NR_setregid 71
+#define __NR_sigsuspend 72
+#define __NR_sigpending 73
+#define __NR_sethostname 74
+#define __NR_setrlimit 75
+#define __NR_getrlimit 76
+#define __NR_getrusage 77
+#define __NR_gettimeofday 78
+#define __NR_settimeofday 79
+#define __NR_getgroups 80
+#define __NR_setgroups 81
+#define __NR_select 82
+#define __NR_symlink 83
+#define __NR_oldlstat 84
+#define __NR_readlink 85
+#define __NR_uselib 86
+#define __NR_swapon 87
+#define __NR_reboot 88
+#define __NR_readdir 89
+#define __NR_mmap 90
+#define __NR_munmap 91
+#define __NR_truncate 92
+#define __NR_ftruncate 93
+#define __NR_fchmod 94
+#define __NR_fchown 95
+#define __NR_getpriority 96
+#define __NR_setpriority 97
+#define __NR_profil 98
+#define __NR_statfs 99
+#define __NR_fstatfs 100
+#define __NR_ioperm 101
+#define __NR_socketcall 102
+#define __NR_syslog 103
+#define __NR_setitimer 104
+#define __NR_getitimer 105
+#define __NR_stat 106
+#define __NR_lstat 107
+#define __NR_fstat 108
+#define __NR_olduname 109
+#define __NR_iopl 110
+#define __NR_vhangup 111
+#define __NR_idle 112
+#define __NR_vm86 113
+#define __NR_wait4 114
+#define __NR_swapoff 115
+#define __NR_sysinfo 116
+#define __NR_ipc 117
+#define __NR_fsync 118
+#define __NR_sigreturn 119
+#define __NR_clone 120
+#define __NR_setdomainname 121
+#define __NR_uname 122
+#define __NR_modify_ldt 123
+#define __NR_adjtimex 124
+#define __NR_mprotect 125
+#define __NR_sigprocmask 126
+#define __NR_create_module 127
+#define __NR_init_module 128
+#define __NR_delete_module 129
+#define __NR_get_kernel_syms 130
+#define __NR_quotactl 131
+#define __NR_getpgid 132
+#define __NR_fchdir 133
+#define __NR_bdflush 134
+#define __NR_sysfs 135
+#define __NR_personality 136
+#define __NR_afs_syscall 137 /* Syscall for Andrew File System */
+#define __NR_setfsuid 138
+#define __NR_setfsgid 139
+#define __NR__llseek 140
+#define __NR_getdents 141
+#define __NR__newselect 142
+#define __NR_flock 143
+#define __NR_msync 144
+#define __NR_readv 145
+#define __NR_writev 146
+#define __NR_getsid 147
+#define __NR_fdatasync 148
+#define __NR__sysctl 149
+#define __NR_mlock 150
+#define __NR_munlock 151
+#define __NR_mlockall 152
+#define __NR_munlockall 153
+#define __NR_sched_setparam 154
+#define __NR_sched_getparam 155
+#define __NR_sched_setscheduler 156
+#define __NR_sched_getscheduler 157
+#define __NR_sched_yield 158
+#define __NR_sched_get_priority_max 159
+#define __NR_sched_get_priority_min 160
+#define __NR_sched_rr_get_interval 161
+#define __NR_nanosleep 162
+#define __NR_mremap 163
+#define __NR_setresuid 164
+#define __NR_getresuid 165
+#define __NR_query_module 166
+#define __NR_poll 167
+#define __NR_nfsservctl 168
+#define __NR_setresgid 169
+#define __NR_getresgid 170
+#define __NR_prctl 171
+#define __NR_rt_sigreturn 172
+#define __NR_rt_sigaction 173
+#define __NR_rt_sigprocmask 174
+#define __NR_rt_sigpending 175
+#define __NR_rt_sigtimedwait 176
+#define __NR_rt_sigqueueinfo 177
+#define __NR_rt_sigsuspend 178
+#define __NR_pread64 179
+#define __NR_pwrite64 180
+#define __NR_chown 181
+#define __NR_getcwd 182
+#define __NR_capget 183
+#define __NR_capset 184
+#define __NR_sigaltstack 185
+#define __NR_sendfile 186
+#define __NR_getpmsg 187 /* some people actually want streams */
+#define __NR_putpmsg 188 /* some people actually want streams */
+#define __NR_vfork 189
+#define __NR_ugetrlimit 190 /* SuS compliant getrlimit */
+#define __NR_readahead 191
+#ifndef __powerpc64__ /* these are 32-bit only */
+#define __NR_mmap2 192
+#define __NR_truncate64 193
+#define __NR_ftruncate64 194
+#define __NR_stat64 195
+#define __NR_lstat64 196
+#define __NR_fstat64 197
+#endif
+#define __NR_pciconfig_read 198
+#define __NR_pciconfig_write 199
+#define __NR_pciconfig_iobase 200
+#define __NR_multiplexer 201
+#define __NR_getdents64 202
+#define __NR_pivot_root 203
+#ifndef __powerpc64__
+#define __NR_fcntl64 204
+#endif
+#define __NR_madvise 205
+#define __NR_mincore 206
+#define __NR_gettid 207
+#define __NR_tkill 208
+#define __NR_setxattr 209
+#define __NR_lsetxattr 210
+#define __NR_fsetxattr 211
+#define __NR_getxattr 212
+#define __NR_lgetxattr 213
+#define __NR_fgetxattr 214
+#define __NR_listxattr 215
+#define __NR_llistxattr 216
+#define __NR_flistxattr 217
+#define __NR_removexattr 218
+#define __NR_lremovexattr 219
+#define __NR_fremovexattr 220
+#define __NR_futex 221
+#define __NR_sched_setaffinity 222
+#define __NR_sched_getaffinity 223
+/* 224 currently unused */
+#define __NR_tuxcall 225
+#ifndef __powerpc64__
+#define __NR_sendfile64 226
+#endif
+#define __NR_io_setup 227
+#define __NR_io_destroy 228
+#define __NR_io_getevents 229
+#define __NR_io_submit 230
+#define __NR_io_cancel 231
+#define __NR_set_tid_address 232
+#define __NR_fadvise64 233
+#define __NR_exit_group 234
+#define __NR_lookup_dcookie 235
+#define __NR_epoll_create 236
+#define __NR_epoll_ctl 237
+#define __NR_epoll_wait 238
+#define __NR_remap_file_pages 239
+#define __NR_timer_create 240
+#define __NR_timer_settime 241
+#define __NR_timer_gettime 242
+#define __NR_timer_getoverrun 243
+#define __NR_timer_delete 244
+#define __NR_clock_settime 245
+#define __NR_clock_gettime 246
+#define __NR_clock_getres 247
+#define __NR_clock_nanosleep 248
+#define __NR_swapcontext 249
+#define __NR_tgkill 250
+#define __NR_utimes 251
+#define __NR_statfs64 252
+#define __NR_fstatfs64 253
+#ifndef __powerpc64__
+#define __NR_fadvise64_64 254
+#endif
+#define __NR_rtas 255
+#define __NR_sys_debug_setcontext 256
+/* Number 257 is reserved for vserver */
+#define __NR_migrate_pages 258
+#define __NR_mbind 259
+#define __NR_get_mempolicy 260
+#define __NR_set_mempolicy 261
+#define __NR_mq_open 262
+#define __NR_mq_unlink 263
+#define __NR_mq_timedsend 264
+#define __NR_mq_timedreceive 265
+#define __NR_mq_notify 266
+#define __NR_mq_getsetattr 267
+#define __NR_kexec_load 268
+#define __NR_add_key 269
+#define __NR_request_key 270
+#define __NR_keyctl 271
+#define __NR_waitid 272
+#define __NR_ioprio_set 273
+#define __NR_ioprio_get 274
+#define __NR_inotify_init 275
+#define __NR_inotify_add_watch 276
+#define __NR_inotify_rm_watch 277
+#define __NR_spu_run 278
+#define __NR_spu_create 279
+#define __NR_pselect6 280
+#define __NR_ppoll 281
+#define __NR_unshare 282
+#define __NR_splice 283
+#define __NR_tee 284
+#define __NR_vmsplice 285
+#define __NR_openat 286
+#define __NR_mkdirat 287
+#define __NR_mknodat 288
+#define __NR_fchownat 289
+#define __NR_futimesat 290
+#ifdef __powerpc64__
+#define __NR_newfstatat 291
+#else
+#define __NR_fstatat64 291
+#endif
+#define __NR_unlinkat 292
+#define __NR_renameat 293
+#define __NR_linkat 294
+#define __NR_symlinkat 295
+#define __NR_readlinkat 296
+#define __NR_fchmodat 297
+#define __NR_faccessat 298
+#define __NR_get_robust_list 299
+#define __NR_set_robust_list 300
+#define __NR_move_pages 301
+#define __NR_getcpu 302
+#define __NR_epoll_pwait 303
+#define __NR_utimensat 304
+#define __NR_signalfd 305
+#define __NR_timerfd_create 306
+#define __NR_eventfd 307
+#define __NR_sync_file_range2 308
+#define __NR_fallocate 309
+#define __NR_subpage_prot 310
+#define __NR_timerfd_settime 311
+#define __NR_timerfd_gettime 312
+#define __NR_signalfd4 313
+#define __NR_eventfd2 314
+#define __NR_epoll_create1 315
+#define __NR_dup3 316
+#define __NR_pipe2 317
+#define __NR_inotify_init1 318
+#define __NR_perf_event_open 319
+#define __NR_preadv 320
+#define __NR_pwritev 321
+#define __NR_rt_tgsigqueueinfo 322
+#define __NR_fanotify_init 323
+#define __NR_fanotify_mark 324
+#define __NR_prlimit64 325
+#define __NR_socket 326
+#define __NR_bind 327
+#define __NR_connect 328
+#define __NR_listen 329
+#define __NR_accept 330
+#define __NR_getsockname 331
+#define __NR_getpeername 332
+#define __NR_socketpair 333
+#define __NR_send 334
+#define __NR_sendto 335
+#define __NR_recv 336
+#define __NR_recvfrom 337
+#define __NR_shutdown 338
+#define __NR_setsockopt 339
+#define __NR_getsockopt 340
+#define __NR_sendmsg 341
+#define __NR_recvmsg 342
+#define __NR_recvmmsg 343
+#define __NR_accept4 344
+#define __NR_name_to_handle_at 345
+#define __NR_open_by_handle_at 346
+#define __NR_clock_adjtime 347
+#define __NR_syncfs 348
+#define __NR_sendmmsg 349
+#define __NR_setns 350
+#define __NR_process_vm_readv 351
+#define __NR_process_vm_writev 352
+#define __NR_finit_module 353
+#define __NR_kcmp 354
+#define __NR_sched_setattr 355
+#define __NR_sched_getattr 356
+#define __NR_renameat2 357
+#define __NR_seccomp 358
+#define __NR_getrandom 359
+#define __NR_memfd_create 360
+#define __NR_bpf 361
+#define __NR_execveat 362
+#define __NR_switch_endian 363
+#define __NR_userfaultfd 364
+#define __NR_membarrier 365
+
+#endif /* _ASM_POWERPC_UNISTD_H_ */
--git a/linux-headers/asm-s390/unistd.h b/linux-headers/asm-s390/unistd.h
new file mode 100644
index 0000000..04b43b1
--- /dev/null
+++ b/linux-headers/asm-s390/unistd.h
@@ -0,0 +1,404 @@
+/*
+ * S390 version
+ *
+ * Derived from "include/asm-i386/unistd.h"
+ */
+
+#ifndef _ASM_S390_UNISTD_H_
+#define _ASM_S390_UNISTD_H_
+
+/*
+ * This file contains the system call numbers.
+ */
+
+#define __NR_exit 1
+#define __NR_fork 2
+#define __NR_read 3
+#define __NR_write 4
+#define __NR_open 5
+#define __NR_close 6
+#define __NR_restart_syscall 7
+#define __NR_creat 8
+#define __NR_link 9
+#define __NR_unlink 10
+#define __NR_execve 11
+#define __NR_chdir 12
+#define __NR_mknod 14
+#define __NR_chmod 15
+#define __NR_lseek 19
+#define __NR_getpid 20
+#define __NR_mount 21
+#define __NR_umount 22
+#define __NR_ptrace 26
+#define __NR_alarm 27
+#define __NR_pause 29
+#define __NR_utime 30
+#define __NR_access 33
+#define __NR_nice 34
+#define __NR_sync 36
+#define __NR_kill 37
+#define __NR_rename 38
+#define __NR_mkdir 39
+#define __NR_rmdir 40
+#define __NR_dup 41
+#define __NR_pipe 42
+#define __NR_times 43
+#define __NR_brk 45
+#define __NR_signal 48
+#define __NR_acct 51
+#define __NR_umount2 52
+#define __NR_ioctl 54
+#define __NR_fcntl 55
+#define __NR_setpgid 57
+#define __NR_umask 60
+#define __NR_chroot 61
+#define __NR_ustat 62
+#define __NR_dup2 63
+#define __NR_getppid 64
+#define __NR_getpgrp 65
+#define __NR_setsid 66
+#define __NR_sigaction 67
+#define __NR_sigsuspend 72
+#define __NR_sigpending 73
+#define __NR_sethostname 74
+#define __NR_setrlimit 75
+#define __NR_getrusage 77
+#define __NR_gettimeofday 78
+#define __NR_settimeofday 79
+#define __NR_symlink 83
+#define __NR_readlink 85
+#define __NR_uselib 86
+#define __NR_swapon 87
+#define __NR_reboot 88
+#define __NR_readdir 89
+#define __NR_mmap 90
+#define __NR_munmap 91
+#define __NR_truncate 92
+#define __NR_ftruncate 93
+#define __NR_fchmod 94
+#define __NR_getpriority 96
+#define __NR_setpriority 97
+#define __NR_statfs 99
+#define __NR_fstatfs 100
+#define __NR_socketcall 102
+#define __NR_syslog 103
+#define __NR_setitimer 104
+#define __NR_getitimer 105
+#define __NR_stat 106
+#define __NR_lstat 107
+#define __NR_fstat 108
+#define __NR_lookup_dcookie 110
+#define __NR_vhangup 111
+#define __NR_idle 112
+#define __NR_wait4 114
+#define __NR_swapoff 115
+#define __NR_sysinfo 116
+#define __NR_ipc 117
+#define __NR_fsync 118
+#define __NR_sigreturn 119
+#define __NR_clone 120
+#define __NR_setdomainname 121
+#define __NR_uname 122
+#define __NR_adjtimex 124
+#define __NR_mprotect 125
+#define __NR_sigprocmask 126
+#define __NR_create_module 127
+#define __NR_init_module 128
+#define __NR_delete_module 129
+#define __NR_get_kernel_syms 130
+#define __NR_quotactl 131
+#define __NR_getpgid 132
+#define __NR_fchdir 133
+#define __NR_bdflush 134
+#define __NR_sysfs 135
+#define __NR_personality 136
+#define __NR_afs_syscall 137 /* Syscall for Andrew File System */
+#define __NR_getdents 141
+#define __NR_flock 143
+#define __NR_msync 144
+#define __NR_readv 145
+#define __NR_writev 146
+#define __NR_getsid 147
+#define __NR_fdatasync 148
+#define __NR__sysctl 149
+#define __NR_mlock 150
+#define __NR_munlock 151
+#define __NR_mlockall 152
+#define __NR_munlockall 153
+#define __NR_sched_setparam 154
+#define __NR_sched_getparam 155
+#define __NR_sched_setscheduler 156
+#define __NR_sched_getscheduler 157
+#define __NR_sched_yield 158
+#define __NR_sched_get_priority_max 159
+#define __NR_sched_get_priority_min 160
+#define __NR_sched_rr_get_interval 161
+#define __NR_nanosleep 162
+#define __NR_mremap 163
+#define __NR_query_module 167
+#define __NR_poll 168
+#define __NR_nfsservctl 169
+#define __NR_prctl 172
+#define __NR_rt_sigreturn 173
+#define __NR_rt_sigaction 174
+#define __NR_rt_sigprocmask 175
+#define __NR_rt_sigpending 176
+#define __NR_rt_sigtimedwait 177
+#define __NR_rt_sigqueueinfo 178
+#define __NR_rt_sigsuspend 179
+#define __NR_pread64 180
+#define __NR_pwrite64 181
+#define __NR_getcwd 183
+#define __NR_capget 184
+#define __NR_capset 185
+#define __NR_sigaltstack 186
+#define __NR_sendfile 187
+#define __NR_getpmsg 188
+#define __NR_putpmsg 189
+#define __NR_vfork 190
+#define __NR_pivot_root 217
+#define __NR_mincore 218
+#define __NR_madvise 219
+#define __NR_getdents64 220
+#define __NR_readahead 222
+#define __NR_setxattr 224
+#define __NR_lsetxattr 225
+#define __NR_fsetxattr 226
+#define __NR_getxattr 227
+#define __NR_lgetxattr 228
+#define __NR_fgetxattr 229
+#define __NR_listxattr 230
+#define __NR_llistxattr 231
+#define __NR_flistxattr 232
+#define __NR_removexattr 233
+#define __NR_lremovexattr 234
+#define __NR_fremovexattr 235
+#define __NR_gettid 236
+#define __NR_tkill 237
+#define __NR_futex 238
+#define __NR_sched_setaffinity 239
+#define __NR_sched_getaffinity 240
+#define __NR_tgkill 241
+/* Number 242 is reserved for tux */
+#define __NR_io_setup 243
+#define __NR_io_destroy 244
+#define __NR_io_getevents 245
+#define __NR_io_submit 246
+#define __NR_io_cancel 247
+#define __NR_exit_group 248
+#define __NR_epoll_create 249
+#define __NR_epoll_ctl 250
+#define __NR_epoll_wait 251
+#define __NR_set_tid_address 252
+#define __NR_fadvise64 253
+#define __NR_timer_create 254
+#define __NR_timer_settime (__NR_timer_create+1)
+#define __NR_timer_gettime (__NR_timer_create+2)
+#define __NR_timer_getoverrun (__NR_timer_create+3)
+#define __NR_timer_delete (__NR_timer_create+4)
+#define __NR_clock_settime (__NR_timer_create+5)
+#define __NR_clock_gettime (__NR_timer_create+6)
+#define __NR_clock_getres (__NR_timer_create+7)
+#define __NR_clock_nanosleep (__NR_timer_create+8)
+/* Number 263 is reserved for vserver */
+#define __NR_statfs64 265
+#define __NR_fstatfs64 266
+#define __NR_remap_file_pages 267
+#define __NR_mbind 268
+#define __NR_get_mempolicy 269
+#define __NR_set_mempolicy 270
+#define __NR_mq_open 271
+#define __NR_mq_unlink 272
+#define __NR_mq_timedsend 273
+#define __NR_mq_timedreceive 274
+#define __NR_mq_notify 275
+#define __NR_mq_getsetattr 276
+#define __NR_kexec_load 277
+#define __NR_add_key 278
+#define __NR_request_key 279
+#define __NR_keyctl 280
+#define __NR_waitid 281
+#define __NR_ioprio_set 282
+#define __NR_ioprio_get 283
+#define __NR_inotify_init 284
+#define __NR_inotify_add_watch 285
+#define __NR_inotify_rm_watch 286
+#define __NR_migrate_pages 287
+#define __NR_openat 288
+#define __NR_mkdirat 289
+#define __NR_mknodat 290
+#define __NR_fchownat 291
+#define __NR_futimesat 292
+#define __NR_unlinkat 294
+#define __NR_renameat 295
+#define __NR_linkat 296
+#define __NR_symlinkat 297
+#define __NR_readlinkat 298
+#define __NR_fchmodat 299
+#define __NR_faccessat 300
+#define __NR_pselect6 301
+#define __NR_ppoll 302
+#define __NR_unshare 303
+#define __NR_set_robust_list 304
+#define __NR_get_robust_list 305
+#define __NR_splice 306
+#define __NR_sync_file_range 307
+#define __NR_tee 308
+#define __NR_vmsplice 309
+#define __NR_move_pages 310
+#define __NR_getcpu 311
+#define __NR_epoll_pwait 312
+#define __NR_utimes 313
+#define __NR_fallocate 314
+#define __NR_utimensat 315
+#define __NR_signalfd 316
+#define __NR_timerfd 317
+#define __NR_eventfd 318
+#define __NR_timerfd_create 319
+#define __NR_timerfd_settime 320
+#define __NR_timerfd_gettime 321
+#define __NR_signalfd4 322
+#define __NR_eventfd2 323
+#define __NR_inotify_init1 324
+#define __NR_pipe2 325
+#define __NR_dup3 326
+#define __NR_epoll_create1 327
+#define __NR_preadv 328
+#define __NR_pwritev 329
+#define __NR_rt_tgsigqueueinfo 330
+#define __NR_perf_event_open 331
+#define __NR_fanotify_init 332
+#define __NR_fanotify_mark 333
+#define __NR_prlimit64 334
+#define __NR_name_to_handle_at 335
+#define __NR_open_by_handle_at 336
+#define __NR_clock_adjtime 337
+#define __NR_syncfs 338
+#define __NR_setns 339
+#define __NR_process_vm_readv 340
+#define __NR_process_vm_writev 341
+#define __NR_s390_runtime_instr 342
+#define __NR_kcmp 343
+#define __NR_finit_module 344
+#define __NR_sched_setattr 345
+#define __NR_sched_getattr 346
+#define __NR_renameat2 347
+#define __NR_seccomp 348
+#define __NR_getrandom 349
+#define __NR_memfd_create 350
+#define __NR_bpf 351
+#define __NR_s390_pci_mmio_write 352
+#define __NR_s390_pci_mmio_read 353
+#define __NR_execveat 354
+#define __NR_userfaultfd 355
+#define __NR_membarrier 356
+#define __NR_recvmmsg 357
+#define __NR_sendmmsg 358
+#define __NR_socket 359
+#define __NR_socketpair 360
+#define __NR_bind 361
+#define __NR_connect 362
+#define __NR_listen 363
+#define __NR_accept4 364
+#define __NR_getsockopt 365
+#define __NR_setsockopt 366
+#define __NR_getsockname 367
+#define __NR_getpeername 368
+#define __NR_sendto 369
+#define __NR_sendmsg 370
+#define __NR_recvfrom 371
+#define __NR_recvmsg 372
+#define __NR_shutdown 373
+#define NR_syscalls 374
+
+/*
+ * There are some system calls that are not present on 64 bit, some
+ * have a different name although they do the same (e.g. __NR_chown32
+ * is __NR_chown on 64 bit).
+ */
+#ifndef __s390x__
+
+#define __NR_time 13
+#define __NR_lchown 16
+#define __NR_setuid 23
+#define __NR_getuid 24
+#define __NR_stime 25
+#define __NR_setgid 46
+#define __NR_getgid 47
+#define __NR_geteuid 49
+#define __NR_getegid 50
+#define __NR_setreuid 70
+#define __NR_setregid 71
+#define __NR_getrlimit 76
+#define __NR_getgroups 80
+#define __NR_setgroups 81
+#define __NR_fchown 95
+#define __NR_ioperm 101
+#define __NR_setfsuid 138
+#define __NR_setfsgid 139
+#define __NR__llseek 140
+#define __NR__newselect 142
+#define __NR_setresuid 164
+#define __NR_getresuid 165
+#define __NR_setresgid 170
+#define __NR_getresgid 171
+#define __NR_chown 182
+#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */
+#define __NR_mmap2 192
+#define __NR_truncate64 193
+#define __NR_ftruncate64 194
+#define __NR_stat64 195
+#define __NR_lstat64 196
+#define __NR_fstat64 197
+#define __NR_lchown32 198
+#define __NR_getuid32 199
+#define __NR_getgid32 200
+#define __NR_geteuid32 201
+#define __NR_getegid32 202
+#define __NR_setreuid32 203
+#define __NR_setregid32 204
+#define __NR_getgroups32 205
+#define __NR_setgroups32 206
+#define __NR_fchown32 207
+#define __NR_setresuid32 208
+#define __NR_getresuid32 209
+#define __NR_setresgid32 210
+#define __NR_getresgid32 211
+#define __NR_chown32 212
+#define __NR_setuid32 213
+#define __NR_setgid32 214
+#define __NR_setfsuid32 215
+#define __NR_setfsgid32 216
+#define __NR_fcntl64 221
+#define __NR_sendfile64 223
+#define __NR_fadvise64_64 264
+#define __NR_fstatat64 293
+
+#else
+
+#define __NR_select 142
+#define __NR_getrlimit 191 /* SuS compliant getrlimit */
+#define __NR_lchown 198
+#define __NR_getuid 199
+#define __NR_getgid 200
+#define __NR_geteuid 201
+#define __NR_getegid 202
+#define __NR_setreuid 203
+#define __NR_setregid 204
+#define __NR_getgroups 205
+#define __NR_setgroups 206
+#define __NR_fchown 207
+#define __NR_setresuid 208
+#define __NR_getresuid 209
+#define __NR_setresgid 210
+#define __NR_getresgid 211
+#define __NR_chown 212
+#define __NR_setuid 213
+#define __NR_setgid 214
+#define __NR_setfsuid 215
+#define __NR_setfsgid 216
+#define __NR_newfstatat 293
+
+#endif
+
+#endif /* _ASM_S390_UNISTD_H_ */
--git a/linux-headers/asm-x86/unistd.h b/linux-headers/asm-x86/unistd.h
new file mode 100644
index 0000000..1f99b12
--- /dev/null
+++ b/linux-headers/asm-x86/unistd.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_X86_UNISTD_H
+#define _ASM_X86_UNISTD_H
+
+/* x32 syscall flag bit */
+#define __X32_SYSCALL_BIT 0x40000000
+
+# ifdef __i386__
+# include <asm/unistd_32.h>
+# elif defined(__ILP32__)
+# include <asm/unistd_x32.h>
+# else
+# include <asm/unistd_64.h>
+# endif
+
+#endif /* _ASM_X86_UNISTD_H */
--git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h
new file mode 100644
index 0000000..7570c80
--- /dev/null
+++ b/linux-headers/asm-x86/unistd_32.h
@@ -0,0 +1,377 @@
+#ifndef _ASM_X86_UNISTD_32_H
+#define _ASM_X86_UNISTD_32_H 1
+
+#define __NR_restart_syscall 0
+#define __NR_exit 1
+#define __NR_fork 2
+#define __NR_read 3
+#define __NR_write 4
+#define __NR_open 5
+#define __NR_close 6
+#define __NR_waitpid 7
+#define __NR_creat 8
+#define __NR_link 9
+#define __NR_unlink 10
+#define __NR_execve 11
+#define __NR_chdir 12
+#define __NR_time 13
+#define __NR_mknod 14
+#define __NR_chmod 15
+#define __NR_lchown 16
+#define __NR_break 17
+#define __NR_oldstat 18
+#define __NR_lseek 19
+#define __NR_getpid 20
+#define __NR_mount 21
+#define __NR_umount 22
+#define __NR_setuid 23
+#define __NR_getuid 24
+#define __NR_stime 25
+#define __NR_ptrace 26
+#define __NR_alarm 27
+#define __NR_oldfstat 28
+#define __NR_pause 29
+#define __NR_utime 30
+#define __NR_stty 31
+#define __NR_gtty 32
+#define __NR_access 33
+#define __NR_nice 34
+#define __NR_ftime 35
+#define __NR_sync 36
+#define __NR_kill 37
+#define __NR_rename 38
+#define __NR_mkdir 39
+#define __NR_rmdir 40
+#define __NR_dup 41
+#define __NR_pipe 42
+#define __NR_times 43
+#define __NR_prof 44
+#define __NR_brk 45
+#define __NR_setgid 46
+#define __NR_getgid 47
+#define __NR_signal 48
+#define __NR_geteuid 49
+#define __NR_getegid 50
+#define __NR_acct 51
+#define __NR_umount2 52
+#define __NR_lock 53
+#define __NR_ioctl 54
+#define __NR_fcntl 55
+#define __NR_mpx 56
+#define __NR_setpgid 57
+#define __NR_ulimit 58
+#define __NR_oldolduname 59
+#define __NR_umask 60
+#define __NR_chroot 61
+#define __NR_ustat 62
+#define __NR_dup2 63
+#define __NR_getppid 64
+#define __NR_getpgrp 65
+#define __NR_setsid 66
+#define __NR_sigaction 67
+#define __NR_sgetmask 68
+#define __NR_ssetmask 69
+#define __NR_setreuid 70
+#define __NR_setregid 71
+#define __NR_sigsuspend 72
+#define __NR_sigpending 73
+#define __NR_sethostname 74
+#define __NR_setrlimit 75
+#define __NR_getrlimit 76
+#define __NR_getrusage 77
+#define __NR_gettimeofday 78
+#define __NR_settimeofday 79
+#define __NR_getgroups 80
+#define __NR_setgroups 81
+#define __NR_select 82
+#define __NR_symlink 83
+#define __NR_oldlstat 84
+#define __NR_readlink 85
+#define __NR_uselib 86
+#define __NR_swapon 87
+#define __NR_reboot 88
+#define __NR_readdir 89
+#define __NR_mmap 90
+#define __NR_munmap 91
+#define __NR_truncate 92
+#define __NR_ftruncate 93
+#define __NR_fchmod 94
+#define __NR_fchown 95
+#define __NR_getpriority 96
+#define __NR_setpriority 97
+#define __NR_profil 98
+#define __NR_statfs 99
+#define __NR_fstatfs 100
+#define __NR_ioperm 101
+#define __NR_socketcall 102
+#define __NR_syslog 103
+#define __NR_setitimer 104
+#define __NR_getitimer 105
+#define __NR_stat 106
+#define __NR_lstat 107
+#define __NR_fstat 108
+#define __NR_olduname 109
+#define __NR_iopl 110
+#define __NR_vhangup 111
+#define __NR_idle 112
+#define __NR_vm86old 113
+#define __NR_wait4 114
+#define __NR_swapoff 115
+#define __NR_sysinfo 116
+#define __NR_ipc 117
+#define __NR_fsync 118
+#define __NR_sigreturn 119
+#define __NR_clone 120
+#define __NR_setdomainname 121
+#define __NR_uname 122
+#define __NR_modify_ldt 123
+#define __NR_adjtimex 124
+#define __NR_mprotect 125
+#define __NR_sigprocmask 126
+#define __NR_create_module 127
+#define __NR_init_module 128
+#define __NR_delete_module 129
+#define __NR_get_kernel_syms 130
+#define __NR_quotactl 131
+#define __NR_getpgid 132
+#define __NR_fchdir 133
+#define __NR_bdflush 134
+#define __NR_sysfs 135
+#define __NR_personality 136
+#define __NR_afs_syscall 137
+#define __NR_setfsuid 138
+#define __NR_setfsgid 139
+#define __NR__llseek 140
+#define __NR_getdents 141
+#define __NR__newselect 142
+#define __NR_flock 143
+#define __NR_msync 144
+#define __NR_readv 145
+#define __NR_writev 146
+#define __NR_getsid 147
+#define __NR_fdatasync 148
+#define __NR__sysctl 149
+#define __NR_mlock 150
+#define __NR_munlock 151
+#define __NR_mlockall 152
+#define __NR_munlockall 153
+#define __NR_sched_setparam 154
+#define __NR_sched_getparam 155
+#define __NR_sched_setscheduler 156
+#define __NR_sched_getscheduler 157
+#define __NR_sched_yield 158
+#define __NR_sched_get_priority_max 159
+#define __NR_sched_get_priority_min 160
+#define __NR_sched_rr_get_interval 161
+#define __NR_nanosleep 162
+#define __NR_mremap 163
+#define __NR_setresuid 164
+#define __NR_getresuid 165
+#define __NR_vm86 166
+#define __NR_query_module 167
+#define __NR_poll 168
+#define __NR_nfsservctl 169
+#define __NR_setresgid 170
+#define __NR_getresgid 171
+#define __NR_prctl 172
+#define __NR_rt_sigreturn 173
+#define __NR_rt_sigaction 174
+#define __NR_rt_sigprocmask 175
+#define __NR_rt_sigpending 176
+#define __NR_rt_sigtimedwait 177
+#define __NR_rt_sigqueueinfo 178
+#define __NR_rt_sigsuspend 179
+#define __NR_pread64 180
+#define __NR_pwrite64 181
+#define __NR_chown 182
+#define __NR_getcwd 183
+#define __NR_capget 184
+#define __NR_capset 185
+#define __NR_sigaltstack 186
+#define __NR_sendfile 187
+#define __NR_getpmsg 188
+#define __NR_putpmsg 189
+#define __NR_vfork 190
+#define __NR_ugetrlimit 191
+#define __NR_mmap2 192
+#define __NR_truncate64 193
+#define __NR_ftruncate64 194
+#define __NR_stat64 195
+#define __NR_lstat64 196
+#define __NR_fstat64 197
+#define __NR_lchown32 198
+#define __NR_getuid32 199
+#define __NR_getgid32 200
+#define __NR_geteuid32 201
+#define __NR_getegid32 202
+#define __NR_setreuid32 203
+#define __NR_setregid32 204
+#define __NR_getgroups32 205
+#define __NR_setgroups32 206
+#define __NR_fchown32 207
+#define __NR_setresuid32 208
+#define __NR_getresuid32 209
+#define __NR_setresgid32 210
+#define __NR_getresgid32 211
+#define __NR_chown32 212
+#define __NR_setuid32 213
+#define __NR_setgid32 214
+#define __NR_setfsuid32 215
+#define __NR_setfsgid32 216
+#define __NR_pivot_root 217
+#define __NR_mincore 218
+#define __NR_madvise 219
+#define __NR_getdents64 220
+#define __NR_fcntl64 221
+#define __NR_gettid 224
+#define __NR_readahead 225
+#define __NR_setxattr 226
+#define __NR_lsetxattr 227
+#define __NR_fsetxattr 228
+#define __NR_getxattr 229
+#define __NR_lgetxattr 230
+#define __NR_fgetxattr 231
+#define __NR_listxattr 232
+#define __NR_llistxattr 233
+#define __NR_flistxattr 234
+#define __NR_removexattr 235
+#define __NR_lremovexattr 236
+#define __NR_fremovexattr 237
+#define __NR_tkill 238
+#define __NR_sendfile64 239
+#define __NR_futex 240
+#define __NR_sched_setaffinity 241
+#define __NR_sched_getaffinity 242
+#define __NR_set_thread_area 243
+#define __NR_get_thread_area 244
+#define __NR_io_setup 245
+#define __NR_io_destroy 246
+#define __NR_io_getevents 247
+#define __NR_io_submit 248
+#define __NR_io_cancel 249
+#define __NR_fadvise64 250
+#define __NR_exit_group 252
+#define __NR_lookup_dcookie 253
+#define __NR_epoll_create 254
+#define __NR_epoll_ctl 255
+#define __NR_epoll_wait 256
+#define __NR_remap_file_pages 257
+#define __NR_set_tid_address 258
+#define __NR_timer_create 259
+#define __NR_timer_settime 260
+#define __NR_timer_gettime 261
+#define __NR_timer_getoverrun 262
+#define __NR_timer_delete 263
+#define __NR_clock_settime 264
+#define __NR_clock_gettime 265
+#define __NR_clock_getres 266
+#define __NR_clock_nanosleep 267
+#define __NR_statfs64 268
+#define __NR_fstatfs64 269
+#define __NR_tgkill 270
+#define __NR_utimes 271
+#define __NR_fadvise64_64 272
+#define __NR_vserver 273
+#define __NR_mbind 274
+#define __NR_get_mempolicy 275
+#define __NR_set_mempolicy 276
+#define __NR_mq_open 277
+#define __NR_mq_unlink 278
+#define __NR_mq_timedsend 279
+#define __NR_mq_timedreceive 280
+#define __NR_mq_notify 281
+#define __NR_mq_getsetattr 282
+#define __NR_kexec_load 283
+#define __NR_waitid 284
+#define __NR_add_key 286
+#define __NR_request_key 287
+#define __NR_keyctl 288
+#define __NR_ioprio_set 289
+#define __NR_ioprio_get 290
+#define __NR_inotify_init 291
+#define __NR_inotify_add_watch 292
+#define __NR_inotify_rm_watch 293
+#define __NR_migrate_pages 294
+#define __NR_openat 295
+#define __NR_mkdirat 296
+#define __NR_mknodat 297
+#define __NR_fchownat 298
+#define __NR_futimesat 299
+#define __NR_fstatat64 300
+#define __NR_unlinkat 301
+#define __NR_renameat 302
+#define __NR_linkat 303
+#define __NR_symlinkat 304
+#define __NR_readlinkat 305
+#define __NR_fchmodat 306
+#define __NR_faccessat 307
+#define __NR_pselect6 308
+#define __NR_ppoll 309
+#define __NR_unshare 310
+#define __NR_set_robust_list 311
+#define __NR_get_robust_list 312
+#define __NR_splice 313
+#define __NR_sync_file_range 314
+#define __NR_tee 315
+#define __NR_vmsplice 316
+#define __NR_move_pages 317
+#define __NR_getcpu 318
+#define __NR_epoll_pwait 319
+#define __NR_utimensat 320
+#define __NR_signalfd 321
+#define __NR_timerfd_create 322
+#define __NR_eventfd 323
+#define __NR_fallocate 324
+#define __NR_timerfd_settime 325
+#define __NR_timerfd_gettime 326
+#define __NR_signalfd4 327
+#define __NR_eventfd2 328
+#define __NR_epoll_create1 329
+#define __NR_dup3 330
+#define __NR_pipe2 331
+#define __NR_inotify_init1 332
+#define __NR_preadv 333
+#define __NR_pwritev 334
+#define __NR_rt_tgsigqueueinfo 335
+#define __NR_perf_event_open 336
+#define __NR_recvmmsg 337
+#define __NR_fanotify_init 338
+#define __NR_fanotify_mark 339
+#define __NR_prlimit64 340
+#define __NR_name_to_handle_at 341
+#define __NR_open_by_handle_at 342
+#define __NR_clock_adjtime 343
+#define __NR_syncfs 344
+#define __NR_sendmmsg 345
+#define __NR_setns 346
+#define __NR_process_vm_readv 347
+#define __NR_process_vm_writev 348
+#define __NR_kcmp 349
+#define __NR_finit_module 350
+#define __NR_sched_setattr 351
+#define __NR_sched_getattr 352
+#define __NR_renameat2 353
+#define __NR_seccomp 354
+#define __NR_getrandom 355
+#define __NR_memfd_create 356
+#define __NR_bpf 357
+#define __NR_execveat 358
+#define __NR_socket 359
+#define __NR_socketpair 360
+#define __NR_bind 361
+#define __NR_connect 362
+#define __NR_listen 363
+#define __NR_accept4 364
+#define __NR_getsockopt 365
+#define __NR_setsockopt 366
+#define __NR_getsockname 367
+#define __NR_getpeername 368
+#define __NR_sendto 369
+#define __NR_sendmsg 370
+#define __NR_recvfrom 371
+#define __NR_recvmsg 372
+#define __NR_shutdown 373
+#define __NR_userfaultfd 374
+#define __NR_membarrier 375
+
+#endif /* _ASM_X86_UNISTD_32_H */
--git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h
new file mode 100644
index 0000000..fdc7afb
--- /dev/null
+++ b/linux-headers/asm-x86/unistd_64.h
@@ -0,0 +1,330 @@
+#ifndef _ASM_X86_UNISTD_64_H
+#define _ASM_X86_UNISTD_64_H 1
+
+#define __NR_read 0
+#define __NR_write 1
+#define __NR_open 2
+#define __NR_close 3
+#define __NR_stat 4
+#define __NR_fstat 5
+#define __NR_lstat 6
+#define __NR_poll 7
+#define __NR_lseek 8
+#define __NR_mmap 9
+#define __NR_mprotect 10
+#define __NR_munmap 11
+#define __NR_brk 12
+#define __NR_rt_sigaction 13
+#define __NR_rt_sigprocmask 14
+#define __NR_rt_sigreturn 15
+#define __NR_ioctl 16
+#define __NR_pread64 17
+#define __NR_pwrite64 18
+#define __NR_readv 19
+#define __NR_writev 20
+#define __NR_access 21
+#define __NR_pipe 22
+#define __NR_select 23
+#define __NR_sched_yield 24
+#define __NR_mremap 25
+#define __NR_msync 26
+#define __NR_mincore 27
+#define __NR_madvise 28
+#define __NR_shmget 29
+#define __NR_shmat 30
+#define __NR_shmctl 31
+#define __NR_dup 32
+#define __NR_dup2 33
+#define __NR_pause 34
+#define __NR_nanosleep 35
+#define __NR_getitimer 36
+#define __NR_alarm 37
+#define __NR_setitimer 38
+#define __NR_getpid 39
+#define __NR_sendfile 40
+#define __NR_socket 41
+#define __NR_connect 42
+#define __NR_accept 43
+#define __NR_sendto 44
+#define __NR_recvfrom 45
+#define __NR_sendmsg 46
+#define __NR_recvmsg 47
+#define __NR_shutdown 48
+#define __NR_bind 49
+#define __NR_listen 50
+#define __NR_getsockname 51
+#define __NR_getpeername 52
+#define __NR_socketpair 53
+#define __NR_setsockopt 54
+#define __NR_getsockopt 55
+#define __NR_clone 56
+#define __NR_fork 57
+#define __NR_vfork 58
+#define __NR_execve 59
+#define __NR_exit 60
+#define __NR_wait4 61
+#define __NR_kill 62
+#define __NR_uname 63
+#define __NR_semget 64
+#define __NR_semop 65
+#define __NR_semctl 66
+#define __NR_shmdt 67
+#define __NR_msgget 68
+#define __NR_msgsnd 69
+#define __NR_msgrcv 70
+#define __NR_msgctl 71
+#define __NR_fcntl 72
+#define __NR_flock 73
+#define __NR_fsync 74
+#define __NR_fdatasync 75
+#define __NR_truncate 76
+#define __NR_ftruncate 77
+#define __NR_getdents 78
+#define __NR_getcwd 79
+#define __NR_chdir 80
+#define __NR_fchdir 81
+#define __NR_rename 82
+#define __NR_mkdir 83
+#define __NR_rmdir 84
+#define __NR_creat 85
+#define __NR_link 86
+#define __NR_unlink 87
+#define __NR_symlink 88
+#define __NR_readlink 89
+#define __NR_chmod 90
+#define __NR_fchmod 91
+#define __NR_chown 92
+#define __NR_fchown 93
+#define __NR_lchown 94
+#define __NR_umask 95
+#define __NR_gettimeofday 96
+#define __NR_getrlimit 97
+#define __NR_getrusage 98
+#define __NR_sysinfo 99
+#define __NR_times 100
+#define __NR_ptrace 101
+#define __NR_getuid 102
+#define __NR_syslog 103
+#define __NR_getgid 104
+#define __NR_setuid 105
+#define __NR_setgid 106
+#define __NR_geteuid 107
+#define __NR_getegid 108
+#define __NR_setpgid 109
+#define __NR_getppid 110
+#define __NR_getpgrp 111
+#define __NR_setsid 112
+#define __NR_setreuid 113
+#define __NR_setregid 114
+#define __NR_getgroups 115
+#define __NR_setgroups 116
+#define __NR_setresuid 117
+#define __NR_getresuid 118
+#define __NR_setresgid 119
+#define __NR_getresgid 120
+#define __NR_getpgid 121
+#define __NR_setfsuid 122
+#define __NR_setfsgid 123
+#define __NR_getsid 124
+#define __NR_capget 125
+#define __NR_capset 126
+#define __NR_rt_sigpending 127
+#define __NR_rt_sigtimedwait 128
+#define __NR_rt_sigqueueinfo 129
+#define __NR_rt_sigsuspend 130
+#define __NR_sigaltstack 131
+#define __NR_utime 132
+#define __NR_mknod 133
+#define __NR_uselib 134
+#define __NR_personality 135
+#define __NR_ustat 136
+#define __NR_statfs 137
+#define __NR_fstatfs 138
+#define __NR_sysfs 139
+#define __NR_getpriority 140
+#define __NR_setpriority 141
+#define __NR_sched_setparam 142
+#define __NR_sched_getparam 143
+#define __NR_sched_setscheduler 144
+#define __NR_sched_getscheduler 145
+#define __NR_sched_get_priority_max 146
+#define __NR_sched_get_priority_min 147
+#define __NR_sched_rr_get_interval 148
+#define __NR_mlock 149
+#define __NR_munlock 150
+#define __NR_mlockall 151
+#define __NR_munlockall 152
+#define __NR_vhangup 153
+#define __NR_modify_ldt 154
+#define __NR_pivot_root 155
+#define __NR__sysctl 156
+#define __NR_prctl 157
+#define __NR_arch_prctl 158
+#define __NR_adjtimex 159
+#define __NR_setrlimit 160
+#define __NR_chroot 161
+#define __NR_sync 162
+#define __NR_acct 163
+#define __NR_settimeofday 164
+#define __NR_mount 165
+#define __NR_umount2 166
+#define __NR_swapon 167
+#define __NR_swapoff 168
+#define __NR_reboot 169
+#define __NR_sethostname 170
+#define __NR_setdomainname 171
+#define __NR_iopl 172
+#define __NR_ioperm 173
+#define __NR_create_module 174
+#define __NR_init_module 175
+#define __NR_delete_module 176
+#define __NR_get_kernel_syms 177
+#define __NR_query_module 178
+#define __NR_quotactl 179
+#define __NR_nfsservctl 180
+#define __NR_getpmsg 181
+#define __NR_putpmsg 182
+#define __NR_afs_syscall 183
+#define __NR_tuxcall 184
+#define __NR_security 185
+#define __NR_gettid 186
+#define __NR_readahead 187
+#define __NR_setxattr 188
+#define __NR_lsetxattr 189
+#define __NR_fsetxattr 190
+#define __NR_getxattr 191
+#define __NR_lgetxattr 192
+#define __NR_fgetxattr 193
+#define __NR_listxattr 194
+#define __NR_llistxattr 195
+#define __NR_flistxattr 196
+#define __NR_removexattr 197
+#define __NR_lremovexattr 198
+#define __NR_fremovexattr 199
+#define __NR_tkill 200
+#define __NR_time 201
+#define __NR_futex 202
+#define __NR_sched_setaffinity 203
+#define __NR_sched_getaffinity 204
+#define __NR_set_thread_area 205
+#define __NR_io_setup 206
+#define __NR_io_destroy 207
+#define __NR_io_getevents 208
+#define __NR_io_submit 209
+#define __NR_io_cancel 210
+#define __NR_get_thread_area 211
+#define __NR_lookup_dcookie 212
+#define __NR_epoll_create 213
+#define __NR_epoll_ctl_old 214
+#define __NR_epoll_wait_old 215
+#define __NR_remap_file_pages 216
+#define __NR_getdents64 217
+#define __NR_set_tid_address 218
+#define __NR_restart_syscall 219
+#define __NR_semtimedop 220
+#define __NR_fadvise64 221
+#define __NR_timer_create 222
+#define __NR_timer_settime 223
+#define __NR_timer_gettime 224
+#define __NR_timer_getoverrun 225
+#define __NR_timer_delete 226
+#define __NR_clock_settime 227
+#define __NR_clock_gettime 228
+#define __NR_clock_getres 229
+#define __NR_clock_nanosleep 230
+#define __NR_exit_group 231
+#define __NR_epoll_wait 232
+#define __NR_epoll_ctl 233
+#define __NR_tgkill 234
+#define __NR_utimes 235
+#define __NR_vserver 236
+#define __NR_mbind 237
+#define __NR_set_mempolicy 238
+#define __NR_get_mempolicy 239
+#define __NR_mq_open 240
+#define __NR_mq_unlink 241
+#define __NR_mq_timedsend 242
+#define __NR_mq_timedreceive 243
+#define __NR_mq_notify 244
+#define __NR_mq_getsetattr 245
+#define __NR_kexec_load 246
+#define __NR_waitid 247
+#define __NR_add_key 248
+#define __NR_request_key 249
+#define __NR_keyctl 250
+#define __NR_ioprio_set 251
+#define __NR_ioprio_get 252
+#define __NR_inotify_init 253
+#define __NR_inotify_add_watch 254
+#define __NR_inotify_rm_watch 255
+#define __NR_migrate_pages 256
+#define __NR_openat 257
+#define __NR_mkdirat 258
+#define __NR_mknodat 259
+#define __NR_fchownat 260
+#define __NR_futimesat 261
+#define __NR_newfstatat 262
+#define __NR_unlinkat 263
+#define __NR_renameat 264
+#define __NR_linkat 265
+#define __NR_symlinkat 266
+#define __NR_readlinkat 267
+#define __NR_fchmodat 268
+#define __NR_faccessat 269
+#define __NR_pselect6 270
+#define __NR_ppoll 271
+#define __NR_unshare 272
+#define __NR_set_robust_list 273
+#define __NR_get_robust_list 274
+#define __NR_splice 275
+#define __NR_tee 276
+#define __NR_sync_file_range 277
+#define __NR_vmsplice 278
+#define __NR_move_pages 279
+#define __NR_utimensat 280
+#define __NR_epoll_pwait 281
+#define __NR_signalfd 282
+#define __NR_timerfd_create 283
+#define __NR_eventfd 284
+#define __NR_fallocate 285
+#define __NR_timerfd_settime 286
+#define __NR_timerfd_gettime 287
+#define __NR_accept4 288
+#define __NR_signalfd4 289
+#define __NR_eventfd2 290
+#define __NR_epoll_create1 291
+#define __NR_dup3 292
+#define __NR_pipe2 293
+#define __NR_inotify_init1 294
+#define __NR_preadv 295
+#define __NR_pwritev 296
+#define __NR_rt_tgsigqueueinfo 297
+#define __NR_perf_event_open 298
+#define __NR_recvmmsg 299
+#define __NR_fanotify_init 300
+#define __NR_fanotify_mark 301
+#define __NR_prlimit64 302
+#define __NR_name_to_handle_at 303
+#define __NR_open_by_handle_at 304
+#define __NR_clock_adjtime 305
+#define __NR_syncfs 306
+#define __NR_sendmmsg 307
+#define __NR_setns 308
+#define __NR_getcpu 309
+#define __NR_process_vm_readv 310
+#define __NR_process_vm_writev 311
+#define __NR_kcmp 312
+#define __NR_finit_module 313
+#define __NR_sched_setattr 314
+#define __NR_sched_getattr 315
+#define __NR_renameat2 316
+#define __NR_seccomp 317
+#define __NR_getrandom 318
+#define __NR_memfd_create 319
+#define __NR_kexec_file_load 320
+#define __NR_bpf 321
+#define __NR_execveat 322
+#define __NR_userfaultfd 323
+#define __NR_membarrier 324
+
+#endif /* _ASM_X86_UNISTD_64_H */
--git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h
new file mode 100644
index 0000000..ac6d198
--- /dev/null
+++ b/linux-headers/asm-x86/unistd_x32.h
@@ -0,0 +1,319 @@
+#ifndef _ASM_X86_UNISTD_X32_H
+#define _ASM_X86_UNISTD_X32_H 1
+
+#define __NR_read (__X32_SYSCALL_BIT + 0)
+#define __NR_write (__X32_SYSCALL_BIT + 1)
+#define __NR_open (__X32_SYSCALL_BIT + 2)
+#define __NR_close (__X32_SYSCALL_BIT + 3)
+#define __NR_stat (__X32_SYSCALL_BIT + 4)
+#define __NR_fstat (__X32_SYSCALL_BIT + 5)
+#define __NR_lstat (__X32_SYSCALL_BIT + 6)
+#define __NR_poll (__X32_SYSCALL_BIT + 7)
+#define __NR_lseek (__X32_SYSCALL_BIT + 8)
+#define __NR_mmap (__X32_SYSCALL_BIT + 9)
+#define __NR_mprotect (__X32_SYSCALL_BIT + 10)
+#define __NR_munmap (__X32_SYSCALL_BIT + 11)
+#define __NR_brk (__X32_SYSCALL_BIT + 12)
+#define __NR_rt_sigprocmask (__X32_SYSCALL_BIT + 14)
+#define __NR_pread64 (__X32_SYSCALL_BIT + 17)
+#define __NR_pwrite64 (__X32_SYSCALL_BIT + 18)
+#define __NR_access (__X32_SYSCALL_BIT + 21)
+#define __NR_pipe (__X32_SYSCALL_BIT + 22)
+#define __NR_select (__X32_SYSCALL_BIT + 23)
+#define __NR_sched_yield (__X32_SYSCALL_BIT + 24)
+#define __NR_mremap (__X32_SYSCALL_BIT + 25)
+#define __NR_msync (__X32_SYSCALL_BIT + 26)
+#define __NR_mincore (__X32_SYSCALL_BIT + 27)
+#define __NR_madvise (__X32_SYSCALL_BIT + 28)
+#define __NR_shmget (__X32_SYSCALL_BIT + 29)
+#define __NR_shmat (__X32_SYSCALL_BIT + 30)
+#define __NR_shmctl (__X32_SYSCALL_BIT + 31)
+#define __NR_dup (__X32_SYSCALL_BIT + 32)
+#define __NR_dup2 (__X32_SYSCALL_BIT + 33)
+#define __NR_pause (__X32_SYSCALL_BIT + 34)
+#define __NR_nanosleep (__X32_SYSCALL_BIT + 35)
+#define __NR_getitimer (__X32_SYSCALL_BIT + 36)
+#define __NR_alarm (__X32_SYSCALL_BIT + 37)
+#define __NR_setitimer (__X32_SYSCALL_BIT + 38)
+#define __NR_getpid (__X32_SYSCALL_BIT + 39)
+#define __NR_sendfile (__X32_SYSCALL_BIT + 40)
+#define __NR_socket (__X32_SYSCALL_BIT + 41)
+#define __NR_connect (__X32_SYSCALL_BIT + 42)
+#define __NR_accept (__X32_SYSCALL_BIT + 43)
+#define __NR_sendto (__X32_SYSCALL_BIT + 44)
+#define __NR_shutdown (__X32_SYSCALL_BIT + 48)
+#define __NR_bind (__X32_SYSCALL_BIT + 49)
+#define __NR_listen (__X32_SYSCALL_BIT + 50)
+#define __NR_getsockname (__X32_SYSCALL_BIT + 51)
+#define __NR_getpeername (__X32_SYSCALL_BIT + 52)
+#define __NR_socketpair (__X32_SYSCALL_BIT + 53)
+#define __NR_clone (__X32_SYSCALL_BIT + 56)
+#define __NR_fork (__X32_SYSCALL_BIT + 57)
+#define __NR_vfork (__X32_SYSCALL_BIT + 58)
+#define __NR_exit (__X32_SYSCALL_BIT + 60)
+#define __NR_wait4 (__X32_SYSCALL_BIT + 61)
+#define __NR_kill (__X32_SYSCALL_BIT + 62)
+#define __NR_uname (__X32_SYSCALL_BIT + 63)
+#define __NR_semget (__X32_SYSCALL_BIT + 64)
+#define __NR_semop (__X32_SYSCALL_BIT + 65)
+#define __NR_semctl (__X32_SYSCALL_BIT + 66)
+#define __NR_shmdt (__X32_SYSCALL_BIT + 67)
+#define __NR_msgget (__X32_SYSCALL_BIT + 68)
+#define __NR_msgsnd (__X32_SYSCALL_BIT + 69)
+#define __NR_msgrcv (__X32_SYSCALL_BIT + 70)
+#define __NR_msgctl (__X32_SYSCALL_BIT + 71)
+#define __NR_fcntl (__X32_SYSCALL_BIT + 72)
+#define __NR_flock (__X32_SYSCALL_BIT + 73)
+#define __NR_fsync (__X32_SYSCALL_BIT + 74)
+#define __NR_fdatasync (__X32_SYSCALL_BIT + 75)
+#define __NR_truncate (__X32_SYSCALL_BIT + 76)
+#define __NR_ftruncate (__X32_SYSCALL_BIT + 77)
+#define __NR_getdents (__X32_SYSCALL_BIT + 78)
+#define __NR_getcwd (__X32_SYSCALL_BIT + 79)
+#define __NR_chdir (__X32_SYSCALL_BIT + 80)
+#define __NR_fchdir (__X32_SYSCALL_BIT + 81)
+#define __NR_rename (__X32_SYSCALL_BIT + 82)
+#define __NR_mkdir (__X32_SYSCALL_BIT + 83)
+#define __NR_rmdir (__X32_SYSCALL_BIT + 84)
+#define __NR_creat (__X32_SYSCALL_BIT + 85)
+#define __NR_link (__X32_SYSCALL_BIT + 86)
+#define __NR_unlink (__X32_SYSCALL_BIT + 87)
+#define __NR_symlink (__X32_SYSCALL_BIT + 88)
+#define __NR_readlink (__X32_SYSCALL_BIT + 89)
+#define __NR_chmod (__X32_SYSCALL_BIT + 90)
+#define __NR_fchmod (__X32_SYSCALL_BIT + 91)
+#define __NR_chown (__X32_SYSCALL_BIT + 92)
+#define __NR_fchown (__X32_SYSCALL_BIT + 93)
+#define __NR_lchown (__X32_SYSCALL_BIT + 94)
+#define __NR_umask (__X32_SYSCALL_BIT + 95)
+#define __NR_gettimeofday (__X32_SYSCALL_BIT + 96)
+#define __NR_getrlimit (__X32_SYSCALL_BIT + 97)
+#define __NR_getrusage (__X32_SYSCALL_BIT + 98)
+#define __NR_sysinfo (__X32_SYSCALL_BIT + 99)
+#define __NR_times (__X32_SYSCALL_BIT + 100)
+#define __NR_getuid (__X32_SYSCALL_BIT + 102)
+#define __NR_syslog (__X32_SYSCALL_BIT + 103)
+#define __NR_getgid (__X32_SYSCALL_BIT + 104)
+#define __NR_setuid (__X32_SYSCALL_BIT + 105)
+#define __NR_setgid (__X32_SYSCALL_BIT + 106)
+#define __NR_geteuid (__X32_SYSCALL_BIT + 107)
+#define __NR_getegid (__X32_SYSCALL_BIT + 108)
+#define __NR_setpgid (__X32_SYSCALL_BIT + 109)
+#define __NR_getppid (__X32_SYSCALL_BIT + 110)
+#define __NR_getpgrp (__X32_SYSCALL_BIT + 111)
+#define __NR_setsid (__X32_SYSCALL_BIT + 112)
+#define __NR_setreuid (__X32_SYSCALL_BIT + 113)
+#define __NR_setregid (__X32_SYSCALL_BIT + 114)
+#define __NR_getgroups (__X32_SYSCALL_BIT + 115)
+#define __NR_setgroups (__X32_SYSCALL_BIT + 116)
+#define __NR_setresuid (__X32_SYSCALL_BIT + 117)
+#define __NR_getresuid (__X32_SYSCALL_BIT + 118)
+#define __NR_setresgid (__X32_SYSCALL_BIT + 119)
+#define __NR_getresgid (__X32_SYSCALL_BIT + 120)
+#define __NR_getpgid (__X32_SYSCALL_BIT + 121)
+#define __NR_setfsuid (__X32_SYSCALL_BIT + 122)
+#define __NR_setfsgid (__X32_SYSCALL_BIT + 123)
+#define __NR_getsid (__X32_SYSCALL_BIT + 124)
+#define __NR_capget (__X32_SYSCALL_BIT + 125)
+#define __NR_capset (__X32_SYSCALL_BIT + 126)
+#define __NR_rt_sigsuspend (__X32_SYSCALL_BIT + 130)
+#define __NR_utime (__X32_SYSCALL_BIT + 132)
+#define __NR_mknod (__X32_SYSCALL_BIT + 133)
+#define __NR_personality (__X32_SYSCALL_BIT + 135)
+#define __NR_ustat (__X32_SYSCALL_BIT + 136)
+#define __NR_statfs (__X32_SYSCALL_BIT + 137)
+#define __NR_fstatfs (__X32_SYSCALL_BIT + 138)
+#define __NR_sysfs (__X32_SYSCALL_BIT + 139)
+#define __NR_getpriority (__X32_SYSCALL_BIT + 140)
+#define __NR_setpriority (__X32_SYSCALL_BIT + 141)
+#define __NR_sched_setparam (__X32_SYSCALL_BIT + 142)
+#define __NR_sched_getparam (__X32_SYSCALL_BIT + 143)
+#define __NR_sched_setscheduler (__X32_SYSCALL_BIT + 144)
+#define __NR_sched_getscheduler (__X32_SYSCALL_BIT + 145)
+#define __NR_sched_get_priority_max (__X32_SYSCALL_BIT + 146)
+#define __NR_sched_get_priority_min (__X32_SYSCALL_BIT + 147)
+#define __NR_sched_rr_get_interval (__X32_SYSCALL_BIT + 148)
+#define __NR_mlock (__X32_SYSCALL_BIT + 149)
+#define __NR_munlock (__X32_SYSCALL_BIT + 150)
+#define __NR_mlockall (__X32_SYSCALL_BIT + 151)
+#define __NR_munlockall (__X32_SYSCALL_BIT + 152)
+#define __NR_vhangup (__X32_SYSCALL_BIT + 153)
+#define __NR_modify_ldt (__X32_SYSCALL_BIT + 154)
+#define __NR_pivot_root (__X32_SYSCALL_BIT + 155)
+#define __NR_prctl (__X32_SYSCALL_BIT + 157)
+#define __NR_arch_prctl (__X32_SYSCALL_BIT + 158)
+#define __NR_adjtimex (__X32_SYSCALL_BIT + 159)
+#define __NR_setrlimit (__X32_SYSCALL_BIT + 160)
+#define __NR_chroot (__X32_SYSCALL_BIT + 161)
+#define __NR_sync (__X32_SYSCALL_BIT + 162)
+#define __NR_acct (__X32_SYSCALL_BIT + 163)
+#define __NR_settimeofday (__X32_SYSCALL_BIT + 164)
+#define __NR_mount (__X32_SYSCALL_BIT + 165)
+#define __NR_umount2 (__X32_SYSCALL_BIT + 166)
+#define __NR_swapon (__X32_SYSCALL_BIT + 167)
+#define __NR_swapoff (__X32_SYSCALL_BIT + 168)
+#define __NR_reboot (__X32_SYSCALL_BIT + 169)
+#define __NR_sethostname (__X32_SYSCALL_BIT + 170)
+#define __NR_setdomainname (__X32_SYSCALL_BIT + 171)
+#define __NR_iopl (__X32_SYSCALL_BIT + 172)
+#define __NR_ioperm (__X32_SYSCALL_BIT + 173)
+#define __NR_init_module (__X32_SYSCALL_BIT + 175)
+#define __NR_delete_module (__X32_SYSCALL_BIT + 176)
+#define __NR_quotactl (__X32_SYSCALL_BIT + 179)
+#define __NR_getpmsg (__X32_SYSCALL_BIT + 181)
+#define __NR_putpmsg (__X32_SYSCALL_BIT + 182)
+#define __NR_afs_syscall (__X32_SYSCALL_BIT + 183)
+#define __NR_tuxcall (__X32_SYSCALL_BIT + 184)
+#define __NR_security (__X32_SYSCALL_BIT + 185)
+#define __NR_gettid (__X32_SYSCALL_BIT + 186)
+#define __NR_readahead (__X32_SYSCALL_BIT + 187)
+#define __NR_setxattr (__X32_SYSCALL_BIT + 188)
+#define __NR_lsetxattr (__X32_SYSCALL_BIT + 189)
+#define __NR_fsetxattr (__X32_SYSCALL_BIT + 190)
+#define __NR_getxattr (__X32_SYSCALL_BIT + 191)
+#define __NR_lgetxattr (__X32_SYSCALL_BIT + 192)
+#define __NR_fgetxattr (__X32_SYSCALL_BIT + 193)
+#define __NR_listxattr (__X32_SYSCALL_BIT + 194)
+#define __NR_llistxattr (__X32_SYSCALL_BIT + 195)
+#define __NR_flistxattr (__X32_SYSCALL_BIT + 196)
+#define __NR_removexattr (__X32_SYSCALL_BIT + 197)
+#define __NR_lremovexattr (__X32_SYSCALL_BIT + 198)
+#define __NR_fremovexattr (__X32_SYSCALL_BIT + 199)
+#define __NR_tkill (__X32_SYSCALL_BIT + 200)
+#define __NR_time (__X32_SYSCALL_BIT + 201)
+#define __NR_futex (__X32_SYSCALL_BIT + 202)
+#define __NR_sched_setaffinity (__X32_SYSCALL_BIT + 203)
+#define __NR_sched_getaffinity (__X32_SYSCALL_BIT + 204)
+#define __NR_io_destroy (__X32_SYSCALL_BIT + 207)
+#define __NR_io_getevents (__X32_SYSCALL_BIT + 208)
+#define __NR_io_cancel (__X32_SYSCALL_BIT + 210)
+#define __NR_lookup_dcookie (__X32_SYSCALL_BIT + 212)
+#define __NR_epoll_create (__X32_SYSCALL_BIT + 213)
+#define __NR_remap_file_pages (__X32_SYSCALL_BIT + 216)
+#define __NR_getdents64 (__X32_SYSCALL_BIT + 217)
+#define __NR_set_tid_address (__X32_SYSCALL_BIT + 218)
+#define __NR_restart_syscall (__X32_SYSCALL_BIT + 219)
+#define __NR_semtimedop (__X32_SYSCALL_BIT + 220)
+#define __NR_fadvise64 (__X32_SYSCALL_BIT + 221)
+#define __NR_timer_settime (__X32_SYSCALL_BIT + 223)
+#define __NR_timer_gettime (__X32_SYSCALL_BIT + 224)
+#define __NR_timer_getoverrun (__X32_SYSCALL_BIT + 225)
+#define __NR_timer_delete (__X32_SYSCALL_BIT + 226)
+#define __NR_clock_settime (__X32_SYSCALL_BIT + 227)
+#define __NR_clock_gettime (__X32_SYSCALL_BIT + 228)
+#define __NR_clock_getres (__X32_SYSCALL_BIT + 229)
+#define __NR_clock_nanosleep (__X32_SYSCALL_BIT + 230)
+#define __NR_exit_group (__X32_SYSCALL_BIT + 231)
+#define __NR_epoll_wait (__X32_SYSCALL_BIT + 232)
+#define __NR_epoll_ctl (__X32_SYSCALL_BIT + 233)
+#define __NR_tgkill (__X32_SYSCALL_BIT + 234)
+#define __NR_utimes (__X32_SYSCALL_BIT + 235)
+#define __NR_mbind (__X32_SYSCALL_BIT + 237)
+#define __NR_set_mempolicy (__X32_SYSCALL_BIT + 238)
+#define __NR_get_mempolicy (__X32_SYSCALL_BIT + 239)
+#define __NR_mq_open (__X32_SYSCALL_BIT + 240)
+#define __NR_mq_unlink (__X32_SYSCALL_BIT + 241)
+#define __NR_mq_timedsend (__X32_SYSCALL_BIT + 242)
+#define __NR_mq_timedreceive (__X32_SYSCALL_BIT + 243)
+#define __NR_mq_getsetattr (__X32_SYSCALL_BIT + 245)
+#define __NR_add_key (__X32_SYSCALL_BIT + 248)
+#define __NR_request_key (__X32_SYSCALL_BIT + 249)
+#define __NR_keyctl (__X32_SYSCALL_BIT + 250)
+#define __NR_ioprio_set (__X32_SYSCALL_BIT + 251)
+#define __NR_ioprio_get (__X32_SYSCALL_BIT + 252)
+#define __NR_inotify_init (__X32_SYSCALL_BIT + 253)
+#define __NR_inotify_add_watch (__X32_SYSCALL_BIT + 254)
+#define __NR_inotify_rm_watch (__X32_SYSCALL_BIT + 255)
+#define __NR_migrate_pages (__X32_SYSCALL_BIT + 256)
+#define __NR_openat (__X32_SYSCALL_BIT + 257)
+#define __NR_mkdirat (__X32_SYSCALL_BIT + 258)
+#define __NR_mknodat (__X32_SYSCALL_BIT + 259)
+#define __NR_fchownat (__X32_SYSCALL_BIT + 260)
+#define __NR_futimesat (__X32_SYSCALL_BIT + 261)
+#define __NR_newfstatat (__X32_SYSCALL_BIT + 262)
+#define __NR_unlinkat (__X32_SYSCALL_BIT + 263)
+#define __NR_renameat (__X32_SYSCALL_BIT + 264)
+#define __NR_linkat (__X32_SYSCALL_BIT + 265)
+#define __NR_symlinkat (__X32_SYSCALL_BIT + 266)
+#define __NR_readlinkat (__X32_SYSCALL_BIT + 267)
+#define __NR_fchmodat (__X32_SYSCALL_BIT + 268)
+#define __NR_faccessat (__X32_SYSCALL_BIT + 269)
+#define __NR_pselect6 (__X32_SYSCALL_BIT + 270)
+#define __NR_ppoll (__X32_SYSCALL_BIT + 271)
+#define __NR_unshare (__X32_SYSCALL_BIT + 272)
+#define __NR_splice (__X32_SYSCALL_BIT + 275)
+#define __NR_tee (__X32_SYSCALL_BIT + 276)
+#define __NR_sync_file_range (__X32_SYSCALL_BIT + 277)
+#define __NR_utimensat (__X32_SYSCALL_BIT + 280)
+#define __NR_epoll_pwait (__X32_SYSCALL_BIT + 281)
+#define __NR_signalfd (__X32_SYSCALL_BIT + 282)
+#define __NR_timerfd_create (__X32_SYSCALL_BIT + 283)
+#define __NR_eventfd (__X32_SYSCALL_BIT + 284)
+#define __NR_fallocate (__X32_SYSCALL_BIT + 285)
+#define __NR_timerfd_settime (__X32_SYSCALL_BIT + 286)
+#define __NR_timerfd_gettime (__X32_SYSCALL_BIT + 287)
+#define __NR_accept4 (__X32_SYSCALL_BIT + 288)
+#define __NR_signalfd4 (__X32_SYSCALL_BIT + 289)
+#define __NR_eventfd2 (__X32_SYSCALL_BIT + 290)
+#define __NR_epoll_create1 (__X32_SYSCALL_BIT + 291)
+#define __NR_dup3 (__X32_SYSCALL_BIT + 292)
+#define __NR_pipe2 (__X32_SYSCALL_BIT + 293)
+#define __NR_inotify_init1 (__X32_SYSCALL_BIT + 294)
+#define __NR_perf_event_open (__X32_SYSCALL_BIT + 298)
+#define __NR_fanotify_init (__X32_SYSCALL_BIT + 300)
+#define __NR_fanotify_mark (__X32_SYSCALL_BIT + 301)
+#define __NR_prlimit64 (__X32_SYSCALL_BIT + 302)
+#define __NR_name_to_handle_at (__X32_SYSCALL_BIT + 303)
+#define __NR_open_by_handle_at (__X32_SYSCALL_BIT + 304)
+#define __NR_clock_adjtime (__X32_SYSCALL_BIT + 305)
+#define __NR_syncfs (__X32_SYSCALL_BIT + 306)
+#define __NR_setns (__X32_SYSCALL_BIT + 308)
+#define __NR_getcpu (__X32_SYSCALL_BIT + 309)
+#define __NR_kcmp (__X32_SYSCALL_BIT + 312)
+#define __NR_finit_module (__X32_SYSCALL_BIT + 313)
+#define __NR_sched_setattr (__X32_SYSCALL_BIT + 314)
+#define __NR_sched_getattr (__X32_SYSCALL_BIT + 315)
+#define __NR_renameat2 (__X32_SYSCALL_BIT + 316)
+#define __NR_seccomp (__X32_SYSCALL_BIT + 317)
+#define __NR_getrandom (__X32_SYSCALL_BIT + 318)
+#define __NR_memfd_create (__X32_SYSCALL_BIT + 319)
+#define __NR_kexec_file_load (__X32_SYSCALL_BIT + 320)
+#define __NR_bpf (__X32_SYSCALL_BIT + 321)
+#define __NR_userfaultfd (__X32_SYSCALL_BIT + 323)
+#define __NR_membarrier (__X32_SYSCALL_BIT + 324)
+#define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512)
+#define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513)
+#define __NR_ioctl (__X32_SYSCALL_BIT + 514)
+#define __NR_readv (__X32_SYSCALL_BIT + 515)
+#define __NR_writev (__X32_SYSCALL_BIT + 516)
+#define __NR_recvfrom (__X32_SYSCALL_BIT + 517)
+#define __NR_sendmsg (__X32_SYSCALL_BIT + 518)
+#define __NR_recvmsg (__X32_SYSCALL_BIT + 519)
+#define __NR_execve (__X32_SYSCALL_BIT + 520)
+#define __NR_ptrace (__X32_SYSCALL_BIT + 521)
+#define __NR_rt_sigpending (__X32_SYSCALL_BIT + 522)
+#define __NR_rt_sigtimedwait (__X32_SYSCALL_BIT + 523)
+#define __NR_rt_sigqueueinfo (__X32_SYSCALL_BIT + 524)
+#define __NR_sigaltstack (__X32_SYSCALL_BIT + 525)
+#define __NR_timer_create (__X32_SYSCALL_BIT + 526)
+#define __NR_mq_notify (__X32_SYSCALL_BIT + 527)
+#define __NR_kexec_load (__X32_SYSCALL_BIT + 528)
+#define __NR_waitid (__X32_SYSCALL_BIT + 529)
+#define __NR_set_robust_list (__X32_SYSCALL_BIT + 530)
+#define __NR_get_robust_list (__X32_SYSCALL_BIT + 531)
+#define __NR_vmsplice (__X32_SYSCALL_BIT + 532)
+#define __NR_move_pages (__X32_SYSCALL_BIT + 533)
+#define __NR_preadv (__X32_SYSCALL_BIT + 534)
+#define __NR_pwritev (__X32_SYSCALL_BIT + 535)
+#define __NR_rt_tgsigqueueinfo (__X32_SYSCALL_BIT + 536)
+#define __NR_recvmmsg (__X32_SYSCALL_BIT + 537)
+#define __NR_sendmmsg (__X32_SYSCALL_BIT + 538)
+#define __NR_process_vm_readv (__X32_SYSCALL_BIT + 539)
+#define __NR_process_vm_writev (__X32_SYSCALL_BIT + 540)
+#define __NR_setsockopt (__X32_SYSCALL_BIT + 541)
+#define __NR_getsockopt (__X32_SYSCALL_BIT + 542)
+#define __NR_io_setup (__X32_SYSCALL_BIT + 543)
+#define __NR_io_submit (__X32_SYSCALL_BIT + 544)
+#define __NR_execveat (__X32_SYSCALL_BIT + 545)
+
+#endif /* _ASM_X86_UNISTD_X32_H */
--git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh
index 457ef37..096d090 100755
--- a/scripts/update-linux-headers.sh
+++ b/scripts/update-linux-headers.sh
@@ -69,7 +69,7 @@ for arch in $ARCHLIST; do
fi
# Blacklist architectures which have KVM headers but are actually dead
- if [ "$arch" = "ia64" ]; then
+ if [ "$arch" = "ia64" -o "$arch" = "mips" ]; then
continue
fi
@@ -77,7 +77,7 @@ for arch in $ARCHLIST; do
rm -rf "$output/linux-headers/asm-$arch"
mkdir -p "$output/linux-headers/asm-$arch"
- for header in kvm.h kvm_para.h; do
+ for header in kvm.h kvm_para.h unistd.h; do
cp "$tmpdir/include/asm/$header" "$output/linux-headers/asm-$arch"
done
if [ $arch = powerpc ]; then
@@ -92,6 +92,9 @@ for arch in $ARCHLIST; do
fi
if [ $arch = x86 ]; then
cp_portable "$tmpdir/include/asm/hyperv.h" "$output/include/standard-headers/asm-x86/"
+ cp "$tmpdir/include/asm/unistd_32.h" "$output/linux-headers/asm-x86/"
+ cp "$tmpdir/include/asm/unistd_x32.h" "$output/linux-headers/asm-x86/"
+ cp "$tmpdir/include/asm/unistd_64.h" "$output/linux-headers/asm-x86/"
fi
done
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 11/38] build-sys: split util-obj- on multi-lines
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (9 preceding siblings ...)
2015-10-21 10:26 ` [Qemu-devel] [PULL 10/38] linux-headers: add unistd.h Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 12/38] util: add linux-only memfd fallback Michael S. Tsirkin
` (27 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Fam Zheng, Thibaut Collet,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Paolo Bonzini
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Make it easier to add new unrelated units with shorter lines.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
util/Makefile.objs | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/util/Makefile.objs b/util/Makefile.objs
index f011b81..f217901 100644
--- a/util/Makefile.objs
+++ b/util/Makefile.objs
@@ -1,14 +1,19 @@
util-obj-y = osdep.o cutils.o unicode.o qemu-timer-common.o
-util-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o event_notifier-win32.o
-util-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o event_notifier-posix.o qemu-openpty.o
+util-obj-$(CONFIG_POSIX) += compatfd.o
+util-obj-$(CONFIG_POSIX) += event_notifier-posix.o
util-obj-$(CONFIG_POSIX) += mmap-alloc.o
+util-obj-$(CONFIG_POSIX) += oslib-posix.o
+util-obj-$(CONFIG_POSIX) += qemu-openpty.o
+util-obj-$(CONFIG_POSIX) += qemu-thread-posix.o
+util-obj-$(CONFIG_WIN32) += event_notifier-win32.o
+util-obj-$(CONFIG_WIN32) += oslib-win32.o
+util-obj-$(CONFIG_WIN32) += qemu-thread-win32.o
util-obj-y += envlist.o path.o module.o
util-obj-$(call lnot,$(CONFIG_INT128)) += host-utils.o
util-obj-y += bitmap.o bitops.o hbitmap.o
util-obj-y += fifo8.o
util-obj-y += acl.o
util-obj-y += error.o qemu-error.o
-util-obj-$(CONFIG_POSIX) += compatfd.o
util-obj-y += id.o
util-obj-y += iov.o qemu-config.o qemu-sockets.o uri.o notify.o
util-obj-y += qemu-option.o qemu-progress.o
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 12/38] util: add linux-only memfd fallback
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (10 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 11/38] build-sys: split util-obj- on multi-lines Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 13/38] util: add memfd helpers Michael S. Tsirkin
` (26 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Fam Zheng, Thibaut Collet,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Paolo Bonzini
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Implement memfd_create() fallback if not available in system libc.
memfd_create() is still not included in glibc today, atlhough it's been
available since Linux 3.17 in Oct 2014.
memfd has numerous advantages over traditional shm/mmap for ipc memory
sharing with fd handler, which we are going to make use of for
vhost-user logging memory in following patches.
The next patches are going to introduce helpers to use best practices of
memfd usage and provide some compatibility fallback. memfd.c is thus
temporarily useless and eventually empty if memfd_create() is provided
by the system.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/qemu/memfd.h | 20 +++++++++++++++++++
util/memfd.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++
util/Makefile.objs | 1 +
3 files changed, 75 insertions(+)
create mode 100644 include/qemu/memfd.h
create mode 100644 util/memfd.c
diff --git a/include/qemu/memfd.h b/include/qemu/memfd.h
new file mode 100644
index 0000000..8b1fe6a
--- /dev/null
+++ b/include/qemu/memfd.h
@@ -0,0 +1,20 @@
+#ifndef QEMU_MEMFD_H
+#define QEMU_MEMFD_H
+
+#include "config-host.h"
+
+#ifndef F_LINUX_SPECIFIC_BASE
+#define F_LINUX_SPECIFIC_BASE 1024
+#endif
+
+#ifndef F_ADD_SEALS
+#define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10)
+
+#define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */
+#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
+#define F_SEAL_GROW 0x0004 /* prevent file from growing */
+#define F_SEAL_WRITE 0x0008 /* prevent writes */
+#endif
+
+#endif /* QEMU_MEMFD_H */
diff --git a/util/memfd.c b/util/memfd.c
new file mode 100644
index 0000000..c509692
--- /dev/null
+++ b/util/memfd.c
@@ -0,0 +1,54 @@
+/*
+ * memfd.c
+ *
+ * Copyright (c) 2015 Red Hat, Inc.
+ *
+ * QEMU library functions on POSIX which are shared between QEMU and
+ * the QEMU tools.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+
+#include "qemu/memfd.h"
+
+#ifdef CONFIG_MEMFD
+#include <sys/memfd.h>
+#elif defined CONFIG_LINUX
+#include <sys/syscall.h>
+#include <asm/unistd.h>
+
+inline static int memfd_create(const char *name, unsigned int flags)
+{
+#ifdef __NR_memfd_create
+ return syscall(__NR_memfd_create, name, flags);
+#else
+ return -1;
+#endif
+}
+#endif
+
+#ifndef MFD_CLOEXEC
+#define MFD_CLOEXEC 0x0001U
+#endif
+
+#ifndef MFD_ALLOW_SEALING
+#define MFD_ALLOW_SEALING 0x0002U
+#endif
diff --git a/util/Makefile.objs b/util/Makefile.objs
index f217901..bab1722 100644
--- a/util/Makefile.objs
+++ b/util/Makefile.objs
@@ -6,6 +6,7 @@ util-obj-$(CONFIG_POSIX) += oslib-posix.o
util-obj-$(CONFIG_POSIX) += qemu-openpty.o
util-obj-$(CONFIG_POSIX) += qemu-thread-posix.o
util-obj-$(CONFIG_WIN32) += event_notifier-win32.o
+util-obj-$(CONFIG_POSIX) += memfd.o
util-obj-$(CONFIG_WIN32) += oslib-win32.o
util-obj-$(CONFIG_WIN32) += qemu-thread-win32.o
util-obj-y += envlist.o path.o module.o
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 13/38] util: add memfd helpers
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (11 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 12/38] util: add linux-only memfd fallback Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 14/38] util: add fallback for qemu_memfd_alloc() Michael S. Tsirkin
` (25 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Add qemu_memfd_alloc/free() helpers.
The function helps to allocate and seal shared memory.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/qemu/memfd.h | 4 +++
util/memfd.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 75 insertions(+), 1 deletion(-)
diff --git a/include/qemu/memfd.h b/include/qemu/memfd.h
index 8b1fe6a..950fb88 100644
--- a/include/qemu/memfd.h
+++ b/include/qemu/memfd.h
@@ -17,4 +17,8 @@
#define F_SEAL_WRITE 0x0008 /* prevent writes */
#endif
+void *qemu_memfd_alloc(const char *name, size_t size, unsigned int seals,
+ int *fd);
+void qemu_memfd_free(void *ptr, size_t size, int fd);
+
#endif /* QEMU_MEMFD_H */
diff --git a/util/memfd.c b/util/memfd.c
index c509692..c119483 100644
--- a/util/memfd.c
+++ b/util/memfd.c
@@ -27,6 +27,11 @@
#include "qemu/osdep.h"
+#include <glib.h>
+#include <glib/gprintf.h>
+
+#include <sys/mman.h>
+
#include "qemu/memfd.h"
#ifdef CONFIG_MEMFD
@@ -35,7 +40,7 @@
#include <sys/syscall.h>
#include <asm/unistd.h>
-inline static int memfd_create(const char *name, unsigned int flags)
+static int memfd_create(const char *name, unsigned int flags)
{
#ifdef __NR_memfd_create
return syscall(__NR_memfd_create, name, flags);
@@ -52,3 +57,68 @@ inline static int memfd_create(const char *name, unsigned int flags)
#ifndef MFD_ALLOW_SEALING
#define MFD_ALLOW_SEALING 0x0002U
#endif
+
+/*
+ * This is a best-effort helper for shared memory allocation, with
+ * optional sealing. The helper will do his best to allocate using
+ * memfd with sealing, but may fallback on other methods without
+ * sealing.
+ */
+void *qemu_memfd_alloc(const char *name, size_t size, unsigned int seals,
+ int *fd)
+{
+ void *ptr;
+ int mfd = -1;
+
+ *fd = -1;
+
+#ifdef CONFIG_LINUX
+ if (seals) {
+ mfd = memfd_create(name, MFD_ALLOW_SEALING | MFD_CLOEXEC);
+ }
+
+ if (mfd == -1) {
+ /* some systems have memfd without sealing */
+ mfd = memfd_create(name, MFD_CLOEXEC);
+ seals = 0;
+ }
+#endif
+
+ if (mfd != -1) {
+ if (ftruncate(mfd, size) == -1) {
+ perror("ftruncate");
+ close(mfd);
+ return NULL;
+ }
+
+ if (seals && fcntl(mfd, F_ADD_SEALS, seals) == -1) {
+ perror("fcntl");
+ close(mfd);
+ return NULL;
+ }
+ } else {
+ perror("memfd");
+ return NULL;
+ }
+
+ ptr = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, mfd, 0);
+ if (ptr == MAP_FAILED) {
+ perror("mmap");
+ close(mfd);
+ return NULL;
+ }
+
+ *fd = mfd;
+ return ptr;
+}
+
+void qemu_memfd_free(void *ptr, size_t size, int fd)
+{
+ if (ptr) {
+ munmap(ptr, size);
+ }
+
+ if (fd != -1) {
+ close(fd);
+ }
+}
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 14/38] util: add fallback for qemu_memfd_alloc()
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (12 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 13/38] util: add memfd helpers Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 15/38] vhost: document log resizing Michael S. Tsirkin
` (24 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Add an open/unlink/mmap fallback for system that do not support
memfd (only available since 3.17, ~1y ago).
This patch may require additional SELinux policies to work for enforced
systems, but should fail gracefully in this case.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
util/memfd.c | 20 ++++++++++++++++++--
1 file changed, 18 insertions(+), 2 deletions(-)
diff --git a/util/memfd.c b/util/memfd.c
index c119483..4b23765 100644
--- a/util/memfd.c
+++ b/util/memfd.c
@@ -97,8 +97,24 @@ void *qemu_memfd_alloc(const char *name, size_t size, unsigned int seals,
return NULL;
}
} else {
- perror("memfd");
- return NULL;
+ const char *tmpdir = g_get_tmp_dir();
+ gchar *fname;
+
+ fname = g_strdup_printf("%s/memfd-XXXXXX", tmpdir);
+ mfd = mkstemp(fname);
+ unlink(fname);
+ g_free(fname);
+
+ if (mfd == -1) {
+ perror("mkstemp");
+ return NULL;
+ }
+
+ if (ftruncate(mfd, size) == -1) {
+ perror("ftruncate");
+ close(mfd);
+ return NULL;
+ }
}
ptr = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, mfd, 0);
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 15/38] vhost: document log resizing
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (13 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 14/38] util: add fallback for qemu_memfd_alloc() Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 16/38] vhost: add vhost_set_log_base op Michael S. Tsirkin
` (23 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
hw/virtio/vhost.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index f14a5c5..f5ecaf0 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -350,6 +350,8 @@ static inline void vhost_dev_log_resize(struct vhost_dev* dev, uint64_t size)
uint64_t log_base = (uintptr_t)log->log;
int r;
+ /* inform backend of log switching, this must be done before
+ releasing the current log, to ensure no logging is lost */
r = dev->vhost_ops->vhost_call(dev, VHOST_SET_LOG_BASE, &log_base);
assert(r >= 0);
vhost_log_put(dev, true);
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 16/38] vhost: add vhost_set_log_base op
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (14 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 15/38] vhost: document log resizing Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 17/38] vhost-user: add vhost_user_requires_shm_log() Michael S. Tsirkin
` (22 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Split VHOST_SET_LOG_BASE call in a seperate function callback, so that
type safety works and more arguments can be added in the next patches.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/hw/virtio/vhost-backend.h | 3 +++
hw/virtio/vhost-backend.c | 6 ++++++
hw/virtio/vhost-user.c | 16 +++++++++++++++-
hw/virtio/vhost.c | 6 +++---
4 files changed, 27 insertions(+), 4 deletions(-)
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index 7d4a8ad..c903573 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -28,6 +28,8 @@ typedef int (*vhost_backend_get_vq_index)(struct vhost_dev *dev, int idx);
typedef int (*vhost_backend_set_vring_enable)(struct vhost_dev *dev, int enable);
typedef int (*vhost_backend_memslots_limit)(struct vhost_dev *dev);
+typedef int (*vhost_set_log_base_op)(struct vhost_dev *dev, uint64_t base);
+
typedef struct VhostOps {
VhostBackendType backend_type;
vhost_call vhost_call;
@@ -36,6 +38,7 @@ typedef struct VhostOps {
vhost_backend_get_vq_index vhost_backend_get_vq_index;
vhost_backend_set_vring_enable vhost_backend_set_vring_enable;
vhost_backend_memslots_limit vhost_backend_memslots_limit;
+ vhost_set_log_base_op vhost_set_log_base;
} VhostOps;
extern const VhostOps user_ops;
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 910d8e0..5846c37 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -67,6 +67,11 @@ static int vhost_kernel_memslots_limit(struct vhost_dev *dev)
return limit;
}
+static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base)
+{
+ return vhost_kernel_call(dev, VHOST_SET_LOG_BASE, &base);
+}
+
static const VhostOps kernel_ops = {
.backend_type = VHOST_BACKEND_TYPE_KERNEL,
.vhost_call = vhost_kernel_call,
@@ -74,6 +79,7 @@ static const VhostOps kernel_ops = {
.vhost_backend_cleanup = vhost_kernel_cleanup,
.vhost_backend_get_vq_index = vhost_kernel_get_vq_index,
.vhost_backend_memslots_limit = vhost_kernel_memslots_limit,
+ .vhost_set_log_base = vhost_set_log_base,
};
int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 9585637..5d51289 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -242,7 +242,6 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
break;
case VHOST_USER_SET_FEATURES:
- case VHOST_USER_SET_LOG_BASE:
case VHOST_USER_SET_PROTOCOL_FEATURES:
msg.u64 = *((__u64 *) arg);
msg.size = sizeof(m.u64);
@@ -367,6 +366,20 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
return 0;
}
+static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base)
+{
+ VhostUserMsg msg = {
+ .request = VHOST_USER_SET_LOG_BASE,
+ .flags = VHOST_USER_VERSION,
+ .u64 = base,
+ .size = sizeof(m.u64),
+ };
+
+ vhost_user_write(dev, &msg, NULL, 0);
+
+ return 0;
+}
+
static int vhost_user_init(struct vhost_dev *dev, void *opaque)
{
unsigned long long features;
@@ -453,4 +466,5 @@ const VhostOps user_ops = {
.vhost_backend_get_vq_index = vhost_user_get_vq_index,
.vhost_backend_set_vring_enable = vhost_user_set_vring_enable,
.vhost_backend_memslots_limit = vhost_user_memslots_limit,
+ .vhost_set_log_base = vhost_set_log_base,
};
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index f5ecaf0..f2b31b7 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -352,7 +352,7 @@ static inline void vhost_dev_log_resize(struct vhost_dev* dev, uint64_t size)
/* inform backend of log switching, this must be done before
releasing the current log, to ensure no logging is lost */
- r = dev->vhost_ops->vhost_call(dev, VHOST_SET_LOG_BASE, &log_base);
+ r = dev->vhost_ops->vhost_set_log_base(dev, log_base);
assert(r >= 0);
vhost_log_put(dev, true);
dev->log = log;
@@ -1167,8 +1167,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
hdev->log_size = vhost_get_log_size(hdev);
hdev->log = vhost_log_get(hdev->log_size);
log_base = (uintptr_t)hdev->log->log;
- r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_LOG_BASE,
- hdev->log_size ? &log_base : NULL);
+ r = hdev->vhost_ops->vhost_set_log_base(hdev,
+ hdev->log_size ? log_base : 0);
if (r < 0) {
r = -errno;
goto fail_log;
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 17/38] vhost-user: add vhost_user_requires_shm_log()
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (15 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 16/38] vhost: add vhost_set_log_base op Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 18/38] vhost: alloc shareable log Michael S. Tsirkin
` (21 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Check if the backend has VHOST_USER_PROTOCOL_F_LOG_SHMFD feature and
require a shared log.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/hw/virtio/vhost-backend.h | 4 ++++
hw/virtio/vhost-user.c | 14 ++++++++++++--
2 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index c903573..c33570a 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -11,6 +11,8 @@
#ifndef VHOST_BACKEND_H_
#define VHOST_BACKEND_H_
+#include <stdbool.h>
+
typedef enum VhostBackendType {
VHOST_BACKEND_TYPE_NONE = 0,
VHOST_BACKEND_TYPE_KERNEL = 1,
@@ -29,6 +31,7 @@ typedef int (*vhost_backend_set_vring_enable)(struct vhost_dev *dev, int enable)
typedef int (*vhost_backend_memslots_limit)(struct vhost_dev *dev);
typedef int (*vhost_set_log_base_op)(struct vhost_dev *dev, uint64_t base);
+typedef bool (*vhost_requires_shm_log_op)(struct vhost_dev *dev);
typedef struct VhostOps {
VhostBackendType backend_type;
@@ -39,6 +42,7 @@ typedef struct VhostOps {
vhost_backend_set_vring_enable vhost_backend_set_vring_enable;
vhost_backend_memslots_limit vhost_backend_memslots_limit;
vhost_set_log_base_op vhost_set_log_base;
+ vhost_requires_shm_log_op vhost_requires_shm_log;
} VhostOps;
extern const VhostOps user_ops;
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 5d51289..e10ce87 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -25,9 +25,10 @@
#define VHOST_MEMORY_MAX_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
-#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x1ULL
-#define VHOST_USER_PROTOCOL_F_MQ 0
+#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x3ULL
+#define VHOST_USER_PROTOCOL_F_MQ 0
+#define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1
typedef enum VhostUserRequest {
VHOST_USER_NONE = 0,
@@ -458,6 +459,14 @@ static int vhost_user_memslots_limit(struct vhost_dev *dev)
return VHOST_MEMORY_MAX_NREGIONS;
}
+static bool vhost_user_requires_shm_log(struct vhost_dev *dev)
+{
+ assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
+
+ return virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_LOG_SHMFD);
+}
+
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
.vhost_call = vhost_user_call,
@@ -467,4 +476,5 @@ const VhostOps user_ops = {
.vhost_backend_set_vring_enable = vhost_user_set_vring_enable,
.vhost_backend_memslots_limit = vhost_user_memslots_limit,
.vhost_set_log_base = vhost_set_log_base,
+ .vhost_requires_shm_log = vhost_user_requires_shm_log,
};
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 18/38] vhost: alloc shareable log
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (16 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 17/38] vhost-user: add vhost_user_requires_shm_log() Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 19/38] vhost-user: send log shm fd along with log_base Michael S. Tsirkin
` (20 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
If the backend is requires it, allocate shareable memory.
vhost_log_get() now uses 2 globals "vhost_log" and "vhost_log_shm", that
way there is a common non-shareable log and a common shareable one.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/hw/virtio/vhost.h | 3 ++-
hw/virtio/vhost.c | 57 ++++++++++++++++++++++++++++++++++++++---------
2 files changed, 49 insertions(+), 11 deletions(-)
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 080831e..6bf759f 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -31,7 +31,8 @@ typedef unsigned long vhost_log_chunk_t;
struct vhost_log {
unsigned long long size;
int refcnt;
- vhost_log_chunk_t log[0];
+ int fd;
+ vhost_log_chunk_t *log;
};
struct vhost_memory;
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index f2b31b7..aec92d4 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -18,6 +18,7 @@
#include "qemu/atomic.h"
#include "qemu/range.h"
#include "qemu/error-report.h"
+#include "qemu/memfd.h"
#include <linux/vhost.h>
#include "exec/address-spaces.h"
#include "hw/virtio/virtio-bus.h"
@@ -25,6 +26,7 @@
#include "migration/migration.h"
static struct vhost_log *vhost_log;
+static struct vhost_log *vhost_log_shm;
static unsigned int used_memslots;
static QLIST_HEAD(, vhost_dev) vhost_devices =
@@ -302,25 +304,46 @@ static uint64_t vhost_get_log_size(struct vhost_dev *dev)
}
return log_size;
}
-static struct vhost_log *vhost_log_alloc(uint64_t size)
+
+static struct vhost_log *vhost_log_alloc(uint64_t size, bool share)
{
- struct vhost_log *log = g_malloc0(sizeof *log + size * sizeof(*(log->log)));
+ struct vhost_log *log;
+ uint64_t logsize = size * sizeof(*(log->log));
+ int fd = -1;
+
+ log = g_new0(struct vhost_log, 1);
+ if (share) {
+ log->log = qemu_memfd_alloc("vhost-log", logsize,
+ F_SEAL_GROW | F_SEAL_SHRINK | F_SEAL_SEAL,
+ &fd);
+ memset(log->log, 0, logsize);
+ } else {
+ log->log = g_malloc0(logsize);
+ }
log->size = size;
log->refcnt = 1;
+ log->fd = fd;
return log;
}
-static struct vhost_log *vhost_log_get(uint64_t size)
+static struct vhost_log *vhost_log_get(uint64_t size, bool share)
{
- if (!vhost_log || vhost_log->size != size) {
- vhost_log = vhost_log_alloc(size);
+ struct vhost_log *log = share ? vhost_log_shm : vhost_log;
+
+ if (!log || log->size != size) {
+ log = vhost_log_alloc(size, share);
+ if (share) {
+ vhost_log_shm = log;
+ } else {
+ vhost_log = log;
+ }
} else {
- ++vhost_log->refcnt;
+ ++log->refcnt;
}
- return vhost_log;
+ return log;
}
static void vhost_log_put(struct vhost_dev *dev, bool sync)
@@ -337,16 +360,29 @@ static void vhost_log_put(struct vhost_dev *dev, bool sync)
if (dev->log_size && sync) {
vhost_log_sync_range(dev, 0, dev->log_size * VHOST_LOG_CHUNK - 1);
}
+
if (vhost_log == log) {
+ g_free(log->log);
vhost_log = NULL;
+ } else if (vhost_log_shm == log) {
+ qemu_memfd_free(log->log, log->size * sizeof(*(log->log)),
+ log->fd);
+ vhost_log_shm = NULL;
}
+
g_free(log);
}
}
-static inline void vhost_dev_log_resize(struct vhost_dev* dev, uint64_t size)
+static bool vhost_dev_log_is_shared(struct vhost_dev *dev)
+{
+ return dev->vhost_ops->vhost_requires_shm_log &&
+ dev->vhost_ops->vhost_requires_shm_log(dev);
+}
+
+static inline void vhost_dev_log_resize(struct vhost_dev *dev, uint64_t size)
{
- struct vhost_log *log = vhost_log_get(size);
+ struct vhost_log *log = vhost_log_get(size, vhost_dev_log_is_shared(dev));
uint64_t log_base = (uintptr_t)log->log;
int r;
@@ -1165,7 +1201,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
uint64_t log_base;
hdev->log_size = vhost_get_log_size(hdev);
- hdev->log = vhost_log_get(hdev->log_size);
+ hdev->log = vhost_log_get(hdev->log_size,
+ vhost_dev_log_is_shared(hdev));
log_base = (uintptr_t)hdev->log->log;
r = hdev->vhost_ops->vhost_set_log_base(hdev,
hdev->log_size ? log_base : 0);
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 19/38] vhost-user: send log shm fd along with log_base
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (17 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 18/38] vhost: alloc shareable log Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 20/38] vhost-user: add a migration blocker Michael S. Tsirkin
` (19 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Send the shm for the dirty pages logging if the backend supports
VHOST_USER_PROTOCOL_F_LOG_SHMFD. Wait for a reply to make sure
the old log is no longer used.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/hw/virtio/vhost-backend.h | 4 +++-
hw/virtio/vhost-backend.c | 3 ++-
hw/virtio/vhost-user.c | 27 +++++++++++++++++++++++++--
hw/virtio/vhost.c | 5 +++--
4 files changed, 33 insertions(+), 6 deletions(-)
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index c33570a..375625f 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -21,6 +21,7 @@ typedef enum VhostBackendType {
} VhostBackendType;
struct vhost_dev;
+struct vhost_log;
typedef int (*vhost_call)(struct vhost_dev *dev, unsigned long int request,
void *arg);
@@ -30,7 +31,8 @@ typedef int (*vhost_backend_get_vq_index)(struct vhost_dev *dev, int idx);
typedef int (*vhost_backend_set_vring_enable)(struct vhost_dev *dev, int enable);
typedef int (*vhost_backend_memslots_limit)(struct vhost_dev *dev);
-typedef int (*vhost_set_log_base_op)(struct vhost_dev *dev, uint64_t base);
+typedef int (*vhost_set_log_base_op)(struct vhost_dev *dev, uint64_t base,
+ struct vhost_log *log);
typedef bool (*vhost_requires_shm_log_op)(struct vhost_dev *dev);
typedef struct VhostOps {
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 5846c37..5a2f1af 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -67,7 +67,8 @@ static int vhost_kernel_memslots_limit(struct vhost_dev *dev)
return limit;
}
-static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base)
+static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base,
+ struct vhost_log *log)
{
return vhost_kernel_call(dev, VHOST_SET_LOG_BASE, &base);
}
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index e10ce87..2709c4e 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -367,8 +367,13 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
return 0;
}
-static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base)
+static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base,
+ struct vhost_log *log)
{
+ int fds[VHOST_MEMORY_MAX_NREGIONS];
+ size_t fd_num = 0;
+ bool shmfd = virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_LOG_SHMFD);
VhostUserMsg msg = {
.request = VHOST_USER_SET_LOG_BASE,
.flags = VHOST_USER_VERSION,
@@ -376,7 +381,25 @@ static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base)
.size = sizeof(m.u64),
};
- vhost_user_write(dev, &msg, NULL, 0);
+ if (shmfd && log->fd != -1) {
+ fds[fd_num++] = log->fd;
+ }
+
+ vhost_user_write(dev, &msg, fds, fd_num);
+
+ if (shmfd) {
+ msg.size = 0;
+ if (vhost_user_read(dev, &msg) < 0) {
+ return 0;
+ }
+
+ if (msg.request != VHOST_USER_SET_LOG_BASE) {
+ error_report("Received unexpected msg type. "
+ "Expected %d received %d",
+ VHOST_USER_SET_LOG_BASE, msg.request);
+ return -1;
+ }
+ }
return 0;
}
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index aec92d4..65c09bf 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -388,7 +388,7 @@ static inline void vhost_dev_log_resize(struct vhost_dev *dev, uint64_t size)
/* inform backend of log switching, this must be done before
releasing the current log, to ensure no logging is lost */
- r = dev->vhost_ops->vhost_set_log_base(dev, log_base);
+ r = dev->vhost_ops->vhost_set_log_base(dev, log_base, log);
assert(r >= 0);
vhost_log_put(dev, true);
dev->log = log;
@@ -1205,7 +1205,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
vhost_dev_log_is_shared(hdev));
log_base = (uintptr_t)hdev->log->log;
r = hdev->vhost_ops->vhost_set_log_base(hdev,
- hdev->log_size ? log_base : 0);
+ hdev->log_size ? log_base : 0,
+ hdev->log);
if (r < 0) {
r = -errno;
goto fail_log;
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 20/38] vhost-user: add a migration blocker
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (18 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 19/38] vhost-user: send log shm fd along with log_base Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 21/38] vhost: use a function for each call Michael S. Tsirkin
` (18 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
If VHOST_USER_PROTOCOL_F_LOG_SHMFD is not announced, block vhost-user
migration. The blocker is removed in vhost_dev_cleanup().
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
hw/virtio/vhost-user.c | 9 +++++++++
hw/virtio/vhost.c | 16 ++++++++++++----
2 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 2709c4e..fb3aa40 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -15,6 +15,7 @@
#include "qemu/error-report.h"
#include "qemu/sockets.h"
#include "exec/ram_addr.h"
+#include "migration/migration.h"
#include <fcntl.h>
#include <unistd.h>
@@ -442,6 +443,14 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
}
}
+ if (dev->migration_blocker == NULL &&
+ !virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_LOG_SHMFD)) {
+ error_setg(&dev->migration_blocker,
+ "Migration disabled: vhost-user backend lacks "
+ "VHOST_USER_PROTOCOL_F_LOG_SHMFD feature.");
+ }
+
return 0;
}
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 65c09bf..a553256 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -961,6 +961,8 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
uint64_t features;
int i, r;
+ hdev->migration_blocker = NULL;
+
if (vhost_set_backend_type(hdev, backend_type) < 0) {
close((uintptr_t)opaque);
return -1;
@@ -1012,12 +1014,18 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
.eventfd_del = vhost_eventfd_del,
.priority = 10
};
- hdev->migration_blocker = NULL;
- if (!(hdev->features & (0x1ULL << VHOST_F_LOG_ALL))) {
- error_setg(&hdev->migration_blocker,
- "Migration disabled: vhost lacks VHOST_F_LOG_ALL feature.");
+
+ if (hdev->migration_blocker == NULL) {
+ if (!(hdev->features & (0x1ULL << VHOST_F_LOG_ALL))) {
+ error_setg(&hdev->migration_blocker,
+ "Migration disabled: vhost lacks VHOST_F_LOG_ALL feature.");
+ }
+ }
+
+ if (hdev->migration_blocker != NULL) {
migrate_add_blocker(hdev->migration_blocker);
}
+
hdev->mem = g_malloc0(offsetof(struct vhost_memory, regions));
hdev->n_mem_sections = 0;
hdev->mem_sections = NULL;
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 21/38] vhost: use a function for each call
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (19 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 20/38] vhost-user: add a migration blocker Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-22 14:09 ` Laurent Desnogues
2015-10-21 10:27 ` [Qemu-devel] [PULL 22/38] vhost-user: document migration log Michael S. Tsirkin
` (17 subsequent siblings)
38 siblings, 1 reply; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Jason Wang, Paolo Bonzini, Thibaut Collet,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Replace the generic vhost_call() by specific functions for each
function call to help with type safety and changing arguments.
While doing this, I found that "unsigned long long" and "uint64_t" were
used interchangeably and causing compilation warnings, using uint64_t
instead, as the vhost & protocol specifies.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
[Fix enum usage and MQ - Thibaut Collet]
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/hw/virtio/vhost-backend.h | 63 ++++-
include/hw/virtio/vhost.h | 12 +-
hw/net/vhost_net.c | 16 +-
hw/scsi/vhost-scsi.c | 7 +-
hw/virtio/vhost-backend.c | 132 +++++++++-
hw/virtio/vhost-user.c | 522 ++++++++++++++++++++++----------------
hw/virtio/vhost.c | 36 +--
7 files changed, 509 insertions(+), 279 deletions(-)
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index 375625f..ad19481 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -22,28 +22,77 @@ typedef enum VhostBackendType {
struct vhost_dev;
struct vhost_log;
+struct vhost_memory;
+struct vhost_vring_file;
+struct vhost_vring_state;
+struct vhost_vring_addr;
+struct vhost_scsi_target;
-typedef int (*vhost_call)(struct vhost_dev *dev, unsigned long int request,
- void *arg);
typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque);
typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev);
-typedef int (*vhost_backend_get_vq_index)(struct vhost_dev *dev, int idx);
-typedef int (*vhost_backend_set_vring_enable)(struct vhost_dev *dev, int enable);
typedef int (*vhost_backend_memslots_limit)(struct vhost_dev *dev);
+typedef int (*vhost_net_set_backend_op)(struct vhost_dev *dev,
+ struct vhost_vring_file *file);
+typedef int (*vhost_scsi_set_endpoint_op)(struct vhost_dev *dev,
+ struct vhost_scsi_target *target);
+typedef int (*vhost_scsi_clear_endpoint_op)(struct vhost_dev *dev,
+ struct vhost_scsi_target *target);
+typedef int (*vhost_scsi_get_abi_version_op)(struct vhost_dev *dev,
+ int *version);
typedef int (*vhost_set_log_base_op)(struct vhost_dev *dev, uint64_t base,
struct vhost_log *log);
+typedef int (*vhost_set_mem_table_op)(struct vhost_dev *dev,
+ struct vhost_memory *mem);
+typedef int (*vhost_set_vring_addr_op)(struct vhost_dev *dev,
+ struct vhost_vring_addr *addr);
+typedef int (*vhost_set_vring_endian_op)(struct vhost_dev *dev,
+ struct vhost_vring_state *ring);
+typedef int (*vhost_set_vring_num_op)(struct vhost_dev *dev,
+ struct vhost_vring_state *ring);
+typedef int (*vhost_set_vring_base_op)(struct vhost_dev *dev,
+ struct vhost_vring_state *ring);
+typedef int (*vhost_get_vring_base_op)(struct vhost_dev *dev,
+ struct vhost_vring_state *ring);
+typedef int (*vhost_set_vring_kick_op)(struct vhost_dev *dev,
+ struct vhost_vring_file *file);
+typedef int (*vhost_set_vring_call_op)(struct vhost_dev *dev,
+ struct vhost_vring_file *file);
+typedef int (*vhost_set_features_op)(struct vhost_dev *dev,
+ uint64_t features);
+typedef int (*vhost_get_features_op)(struct vhost_dev *dev,
+ uint64_t *features);
+typedef int (*vhost_set_owner_op)(struct vhost_dev *dev);
+typedef int (*vhost_reset_device_op)(struct vhost_dev *dev);
+typedef int (*vhost_get_vq_index_op)(struct vhost_dev *dev, int idx);
+typedef int (*vhost_set_vring_enable_op)(struct vhost_dev *dev,
+ int enable);
typedef bool (*vhost_requires_shm_log_op)(struct vhost_dev *dev);
typedef struct VhostOps {
VhostBackendType backend_type;
- vhost_call vhost_call;
vhost_backend_init vhost_backend_init;
vhost_backend_cleanup vhost_backend_cleanup;
- vhost_backend_get_vq_index vhost_backend_get_vq_index;
- vhost_backend_set_vring_enable vhost_backend_set_vring_enable;
vhost_backend_memslots_limit vhost_backend_memslots_limit;
+ vhost_net_set_backend_op vhost_net_set_backend;
+ vhost_scsi_set_endpoint_op vhost_scsi_set_endpoint;
+ vhost_scsi_clear_endpoint_op vhost_scsi_clear_endpoint;
+ vhost_scsi_get_abi_version_op vhost_scsi_get_abi_version;
vhost_set_log_base_op vhost_set_log_base;
+ vhost_set_mem_table_op vhost_set_mem_table;
+ vhost_set_vring_addr_op vhost_set_vring_addr;
+ vhost_set_vring_endian_op vhost_set_vring_endian;
+ vhost_set_vring_num_op vhost_set_vring_num;
+ vhost_set_vring_base_op vhost_set_vring_base;
+ vhost_get_vring_base_op vhost_get_vring_base;
+ vhost_set_vring_kick_op vhost_set_vring_kick;
+ vhost_set_vring_call_op vhost_set_vring_call;
+ vhost_set_features_op vhost_set_features;
+ vhost_get_features_op vhost_get_features;
+ vhost_set_owner_op vhost_set_owner;
+ vhost_reset_device_op vhost_reset_device;
+ vhost_get_vq_index_op vhost_get_vq_index;
+ vhost_set_vring_enable_op vhost_set_vring_enable;
vhost_requires_shm_log_op vhost_requires_shm_log;
} VhostOps;
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 6bf759f..7437fd4 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -45,14 +45,14 @@ struct vhost_dev {
int nvqs;
/* the first virtqueue which would be used by this vhost dev */
int vq_index;
- unsigned long long features;
- unsigned long long acked_features;
- unsigned long long backend_features;
- unsigned long long protocol_features;
- unsigned long long max_queues;
+ uint64_t features;
+ uint64_t acked_features;
+ uint64_t backend_features;
+ uint64_t protocol_features;
+ uint64_t max_queues;
bool started;
bool log_enabled;
- unsigned long long log_size;
+ uint64_t log_size;
Error *migration_blocker;
bool memory_changed;
hwaddr mem_changed_start_addr;
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 2bce891..1ab4133 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -252,8 +252,7 @@ static int vhost_net_start_one(struct vhost_net *net,
file.fd = net->backend;
for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
const VhostOps *vhost_ops = net->dev.vhost_ops;
- r = vhost_ops->vhost_call(&net->dev, VHOST_NET_SET_BACKEND,
- &file);
+ r = vhost_ops->vhost_net_set_backend(&net->dev, &file);
if (r < 0) {
r = -errno;
goto fail;
@@ -266,8 +265,7 @@ fail:
if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP) {
while (file.index-- > 0) {
const VhostOps *vhost_ops = net->dev.vhost_ops;
- int r = vhost_ops->vhost_call(&net->dev, VHOST_NET_SET_BACKEND,
- &file);
+ int r = vhost_ops->vhost_net_set_backend(&net->dev, &file);
assert(r >= 0);
}
}
@@ -289,15 +287,13 @@ static void vhost_net_stop_one(struct vhost_net *net,
if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP) {
for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
const VhostOps *vhost_ops = net->dev.vhost_ops;
- int r = vhost_ops->vhost_call(&net->dev, VHOST_NET_SET_BACKEND,
- &file);
+ int r = vhost_ops->vhost_net_set_backend(&net->dev, &file);
assert(r >= 0);
}
} else if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) {
for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
const VhostOps *vhost_ops = net->dev.vhost_ops;
- int r = vhost_ops->vhost_call(&net->dev, VHOST_RESET_DEVICE,
- NULL);
+ int r = vhost_ops->vhost_reset_device(&net->dev);
assert(r >= 0);
}
}
@@ -428,8 +424,8 @@ int vhost_set_vring_enable(NetClientState *nc, int enable)
VHostNetState *net = get_vhost_net(nc);
const VhostOps *vhost_ops = net->dev.vhost_ops;
- if (vhost_ops->vhost_backend_set_vring_enable) {
- return vhost_ops->vhost_backend_set_vring_enable(&net->dev, enable);
+ if (vhost_ops->vhost_set_vring_enable) {
+ return vhost_ops->vhost_set_vring_enable(&net->dev, enable);
}
return 0;
diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c
index fb7983d..00cdac6 100644
--- a/hw/scsi/vhost-scsi.c
+++ b/hw/scsi/vhost-scsi.c
@@ -46,7 +46,7 @@ static int vhost_scsi_set_endpoint(VHostSCSI *s)
memset(&backend, 0, sizeof(backend));
pstrcpy(backend.vhost_wwpn, sizeof(backend.vhost_wwpn), vs->conf.wwpn);
- ret = vhost_ops->vhost_call(&s->dev, VHOST_SCSI_SET_ENDPOINT, &backend);
+ ret = vhost_ops->vhost_scsi_set_endpoint(&s->dev, &backend);
if (ret < 0) {
return -errno;
}
@@ -61,7 +61,7 @@ static void vhost_scsi_clear_endpoint(VHostSCSI *s)
memset(&backend, 0, sizeof(backend));
pstrcpy(backend.vhost_wwpn, sizeof(backend.vhost_wwpn), vs->conf.wwpn);
- vhost_ops->vhost_call(&s->dev, VHOST_SCSI_CLEAR_ENDPOINT, &backend);
+ vhost_ops->vhost_scsi_clear_endpoint(&s->dev, &backend);
}
static int vhost_scsi_start(VHostSCSI *s)
@@ -77,8 +77,7 @@ static int vhost_scsi_start(VHostSCSI *s)
return -ENOSYS;
}
- ret = vhost_ops->vhost_call(&s->dev,
- VHOST_SCSI_GET_ABI_VERSION, &abi_version);
+ ret = vhost_ops->vhost_scsi_get_abi_version(&s->dev, &abi_version);
if (ret < 0) {
return -errno;
}
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 5a2f1af..1d5f684 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -43,13 +43,6 @@ static int vhost_kernel_cleanup(struct vhost_dev *dev)
return close(fd);
}
-static int vhost_kernel_get_vq_index(struct vhost_dev *dev, int idx)
-{
- assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
-
- return idx - dev->vq_index;
-}
-
static int vhost_kernel_memslots_limit(struct vhost_dev *dev)
{
int limit = 64;
@@ -67,20 +60,135 @@ static int vhost_kernel_memslots_limit(struct vhost_dev *dev)
return limit;
}
-static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base,
- struct vhost_log *log)
+static int vhost_kernel_net_set_backend(struct vhost_dev *dev,
+ struct vhost_vring_file *file)
+{
+ return vhost_kernel_call(dev, VHOST_NET_SET_BACKEND, file);
+}
+
+static int vhost_kernel_scsi_set_endpoint(struct vhost_dev *dev,
+ struct vhost_scsi_target *target)
+{
+ return vhost_kernel_call(dev, VHOST_SCSI_SET_ENDPOINT, target);
+}
+
+static int vhost_kernel_scsi_clear_endpoint(struct vhost_dev *dev,
+ struct vhost_scsi_target *target)
+{
+ return vhost_kernel_call(dev, VHOST_SCSI_CLEAR_ENDPOINT, target);
+}
+
+static int vhost_kernel_scsi_get_abi_version(struct vhost_dev *dev, int *version)
+{
+ return vhost_kernel_call(dev, VHOST_SCSI_GET_ABI_VERSION, version);
+}
+
+static int vhost_kernel_set_log_base(struct vhost_dev *dev, uint64_t base,
+ struct vhost_log *log)
{
return vhost_kernel_call(dev, VHOST_SET_LOG_BASE, &base);
}
+static int vhost_kernel_set_mem_table(struct vhost_dev *dev,
+ struct vhost_memory *mem)
+{
+ return vhost_kernel_call(dev, VHOST_SET_MEM_TABLE, mem);
+}
+
+static int vhost_kernel_set_vring_addr(struct vhost_dev *dev,
+ struct vhost_vring_addr *addr)
+{
+ return vhost_kernel_call(dev, VHOST_SET_VRING_ADDR, addr);
+}
+
+static int vhost_kernel_set_vring_endian(struct vhost_dev *dev,
+ struct vhost_vring_state *ring)
+{
+ return vhost_kernel_call(dev, VHOST_SET_VRING_ENDIAN, ring);
+}
+
+static int vhost_kernel_set_vring_num(struct vhost_dev *dev,
+ struct vhost_vring_state *ring)
+{
+ return vhost_kernel_call(dev, VHOST_SET_VRING_NUM, ring);
+}
+
+static int vhost_kernel_set_vring_base(struct vhost_dev *dev,
+ struct vhost_vring_state *ring)
+{
+ return vhost_kernel_call(dev, VHOST_SET_VRING_BASE, ring);
+}
+
+static int vhost_kernel_get_vring_base(struct vhost_dev *dev,
+ struct vhost_vring_state *ring)
+{
+ return vhost_kernel_call(dev, VHOST_GET_VRING_BASE, ring);
+}
+
+static int vhost_kernel_set_vring_kick(struct vhost_dev *dev,
+ struct vhost_vring_file *file)
+{
+ return vhost_kernel_call(dev, VHOST_SET_VRING_KICK, file);
+}
+
+static int vhost_kernel_set_vring_call(struct vhost_dev *dev,
+ struct vhost_vring_file *file)
+{
+ return vhost_kernel_call(dev, VHOST_SET_VRING_CALL, file);
+}
+
+static int vhost_kernel_set_features(struct vhost_dev *dev,
+ uint64_t features)
+{
+ return vhost_kernel_call(dev, VHOST_SET_FEATURES, &features);
+}
+
+static int vhost_kernel_get_features(struct vhost_dev *dev,
+ uint64_t *features)
+{
+ return vhost_kernel_call(dev, VHOST_GET_FEATURES, features);
+}
+
+static int vhost_kernel_set_owner(struct vhost_dev *dev)
+{
+ return vhost_kernel_call(dev, VHOST_SET_OWNER, NULL);
+}
+
+static int vhost_kernel_reset_device(struct vhost_dev *dev)
+{
+ return vhost_kernel_call(dev, VHOST_RESET_DEVICE, NULL);
+}
+
+static int vhost_kernel_get_vq_index(struct vhost_dev *dev, int idx)
+{
+ assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
+
+ return idx - dev->vq_index;
+}
+
static const VhostOps kernel_ops = {
.backend_type = VHOST_BACKEND_TYPE_KERNEL,
- .vhost_call = vhost_kernel_call,
.vhost_backend_init = vhost_kernel_init,
.vhost_backend_cleanup = vhost_kernel_cleanup,
- .vhost_backend_get_vq_index = vhost_kernel_get_vq_index,
.vhost_backend_memslots_limit = vhost_kernel_memslots_limit,
- .vhost_set_log_base = vhost_set_log_base,
+ .vhost_net_set_backend = vhost_kernel_net_set_backend,
+ .vhost_scsi_set_endpoint = vhost_kernel_scsi_set_endpoint,
+ .vhost_scsi_clear_endpoint = vhost_kernel_scsi_clear_endpoint,
+ .vhost_scsi_get_abi_version = vhost_kernel_scsi_get_abi_version,
+ .vhost_set_log_base = vhost_kernel_set_log_base,
+ .vhost_set_mem_table = vhost_kernel_set_mem_table,
+ .vhost_set_vring_addr = vhost_kernel_set_vring_addr,
+ .vhost_set_vring_endian = vhost_kernel_set_vring_endian,
+ .vhost_set_vring_num = vhost_kernel_set_vring_num,
+ .vhost_set_vring_base = vhost_kernel_set_vring_base,
+ .vhost_get_vring_base = vhost_kernel_get_vring_base,
+ .vhost_set_vring_kick = vhost_kernel_set_vring_kick,
+ .vhost_set_vring_call = vhost_kernel_set_vring_call,
+ .vhost_set_features = vhost_kernel_set_features,
+ .vhost_get_features = vhost_kernel_get_features,
+ .vhost_set_owner = vhost_kernel_set_owner,
+ .vhost_reset_device = vhost_kernel_reset_device,
+ .vhost_get_vq_index = vhost_kernel_get_vq_index,
};
int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index fb3aa40..16d8e80 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -99,37 +99,6 @@ static bool ioeventfd_enabled(void)
return kvm_enabled() && kvm_eventfds_enabled();
}
-static unsigned long int ioctl_to_vhost_user_request[VHOST_USER_MAX] = {
- -1, /* VHOST_USER_NONE */
- VHOST_GET_FEATURES, /* VHOST_USER_GET_FEATURES */
- VHOST_SET_FEATURES, /* VHOST_USER_SET_FEATURES */
- VHOST_SET_OWNER, /* VHOST_USER_SET_OWNER */
- VHOST_RESET_DEVICE, /* VHOST_USER_RESET_DEVICE */
- VHOST_SET_MEM_TABLE, /* VHOST_USER_SET_MEM_TABLE */
- VHOST_SET_LOG_BASE, /* VHOST_USER_SET_LOG_BASE */
- VHOST_SET_LOG_FD, /* VHOST_USER_SET_LOG_FD */
- VHOST_SET_VRING_NUM, /* VHOST_USER_SET_VRING_NUM */
- VHOST_SET_VRING_ADDR, /* VHOST_USER_SET_VRING_ADDR */
- VHOST_SET_VRING_BASE, /* VHOST_USER_SET_VRING_BASE */
- VHOST_GET_VRING_BASE, /* VHOST_USER_GET_VRING_BASE */
- VHOST_SET_VRING_KICK, /* VHOST_USER_SET_VRING_KICK */
- VHOST_SET_VRING_CALL, /* VHOST_USER_SET_VRING_CALL */
- VHOST_SET_VRING_ERR /* VHOST_USER_SET_VRING_ERR */
-};
-
-static VhostUserRequest vhost_user_request_translate(unsigned long int request)
-{
- VhostUserRequest idx;
-
- for (idx = 0; idx < VHOST_USER_MAX; idx++) {
- if (ioctl_to_vhost_user_request[idx] == request) {
- break;
- }
- }
-
- return (idx == VHOST_USER_MAX) ? VHOST_USER_NONE : idx;
-}
-
static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
{
CharDriverState *chr = dev->opaque;
@@ -176,12 +145,35 @@ fail:
return -1;
}
+static bool vhost_user_one_time_request(VhostUserRequest request)
+{
+ switch (request) {
+ case VHOST_USER_SET_OWNER:
+ case VHOST_USER_RESET_DEVICE:
+ case VHOST_USER_SET_MEM_TABLE:
+ case VHOST_USER_GET_QUEUE_NUM:
+ return true;
+ default:
+ return false;
+ }
+}
+
+/* most non-init callers ignore the error */
static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg,
int *fds, int fd_num)
{
CharDriverState *chr = dev->opaque;
int size = VHOST_USER_HDR_SIZE + msg->size;
+ /*
+ * For non-vring specific requests, like VHOST_USER_SET_MEM_TABLE,
+ * we just need send it once in the first time. For later such
+ * request, we just ignore it.
+ */
+ if (vhost_user_one_time_request(msg->request) && dev->vq_index != 0) {
+ return 0;
+ }
+
if (fd_num) {
qemu_chr_fe_set_msgfds(chr, fds, fd_num);
}
@@ -190,231 +182,321 @@ static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg,
0 : -1;
}
-static bool vhost_user_one_time_request(VhostUserRequest request)
+static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base,
+ struct vhost_log *log)
{
- switch (request) {
- case VHOST_USER_SET_OWNER:
- case VHOST_USER_RESET_DEVICE:
- case VHOST_USER_SET_MEM_TABLE:
- case VHOST_USER_GET_QUEUE_NUM:
- return true;
- default:
- return false;
+ int fds[VHOST_MEMORY_MAX_NREGIONS];
+ size_t fd_num = 0;
+ bool shmfd = virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_LOG_SHMFD);
+ VhostUserMsg msg = {
+ .request = VHOST_USER_SET_LOG_BASE,
+ .flags = VHOST_USER_VERSION,
+ .u64 = base,
+ .size = sizeof(m.u64),
+ };
+
+ if (shmfd && log->fd != -1) {
+ fds[fd_num++] = log->fd;
+ }
+
+ vhost_user_write(dev, &msg, fds, fd_num);
+
+ if (shmfd) {
+ msg.size = 0;
+ if (vhost_user_read(dev, &msg) < 0) {
+ return 0;
+ }
+
+ if (msg.request != VHOST_USER_SET_LOG_BASE) {
+ error_report("Received unexpected msg type. "
+ "Expected %d received %d",
+ VHOST_USER_SET_LOG_BASE, msg.request);
+ return -1;
+ }
}
+
+ return 0;
}
-static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
- void *arg)
+static int vhost_user_set_mem_table(struct vhost_dev *dev,
+ struct vhost_memory *mem)
{
- VhostUserMsg msg;
- VhostUserRequest msg_request;
- struct vhost_vring_file *file = 0;
- int need_reply = 0;
int fds[VHOST_MEMORY_MAX_NREGIONS];
int i, fd;
size_t fd_num = 0;
+ VhostUserMsg msg = {
+ .request = VHOST_USER_SET_MEM_TABLE,
+ .flags = VHOST_USER_VERSION,
+ };
- assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
-
- /* only translate vhost ioctl requests */
- if (request > VHOST_USER_MAX) {
- msg_request = vhost_user_request_translate(request);
- } else {
- msg_request = request;
+ for (i = 0; i < dev->mem->nregions; ++i) {
+ struct vhost_memory_region *reg = dev->mem->regions + i;
+ ram_addr_t ram_addr;
+
+ assert((uintptr_t)reg->userspace_addr == reg->userspace_addr);
+ qemu_ram_addr_from_host((void *)(uintptr_t)reg->userspace_addr,
+ &ram_addr);
+ fd = qemu_get_ram_fd(ram_addr);
+ if (fd > 0) {
+ msg.memory.regions[fd_num].userspace_addr = reg->userspace_addr;
+ msg.memory.regions[fd_num].memory_size = reg->memory_size;
+ msg.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr;
+ msg.memory.regions[fd_num].mmap_offset = reg->userspace_addr -
+ (uintptr_t) qemu_get_ram_block_host_ptr(ram_addr);
+ assert(fd_num < VHOST_MEMORY_MAX_NREGIONS);
+ fds[fd_num++] = fd;
+ }
}
- /*
- * For non-vring specific requests, like VHOST_USER_SET_MEM_TABLE,
- * we just need send it once in the first time. For later such
- * request, we just ignore it.
- */
- if (vhost_user_one_time_request(msg_request) && dev->vq_index != 0) {
- return 0;
+ msg.memory.nregions = fd_num;
+
+ if (!fd_num) {
+ error_report("Failed initializing vhost-user memory map, "
+ "consider using -object memory-backend-file share=on");
+ return -1;
}
- msg.request = msg_request;
- msg.flags = VHOST_USER_VERSION;
- msg.size = 0;
+ msg.size = sizeof(m.memory.nregions);
+ msg.size += sizeof(m.memory.padding);
+ msg.size += fd_num * sizeof(VhostUserMemoryRegion);
- switch (msg_request) {
- case VHOST_USER_GET_FEATURES:
- case VHOST_USER_GET_PROTOCOL_FEATURES:
- case VHOST_USER_GET_QUEUE_NUM:
- need_reply = 1;
- break;
+ vhost_user_write(dev, &msg, fds, fd_num);
- case VHOST_USER_SET_FEATURES:
- case VHOST_USER_SET_PROTOCOL_FEATURES:
- msg.u64 = *((__u64 *) arg);
- msg.size = sizeof(m.u64);
- break;
+ return 0;
+}
- case VHOST_USER_SET_OWNER:
- case VHOST_USER_RESET_DEVICE:
- break;
+static int vhost_user_set_vring_addr(struct vhost_dev *dev,
+ struct vhost_vring_addr *addr)
+{
+ VhostUserMsg msg = {
+ .request = VHOST_USER_SET_VRING_ADDR,
+ .flags = VHOST_USER_VERSION,
+ .addr = *addr,
+ .size = sizeof(*addr),
+ };
- case VHOST_USER_SET_MEM_TABLE:
- for (i = 0; i < dev->mem->nregions; ++i) {
- struct vhost_memory_region *reg = dev->mem->regions + i;
- ram_addr_t ram_addr;
-
- assert((uintptr_t)reg->userspace_addr == reg->userspace_addr);
- qemu_ram_addr_from_host((void *)(uintptr_t)reg->userspace_addr, &ram_addr);
- fd = qemu_get_ram_fd(ram_addr);
- if (fd > 0) {
- msg.memory.regions[fd_num].userspace_addr = reg->userspace_addr;
- msg.memory.regions[fd_num].memory_size = reg->memory_size;
- msg.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr;
- msg.memory.regions[fd_num].mmap_offset = reg->userspace_addr -
- (uintptr_t) qemu_get_ram_block_host_ptr(ram_addr);
- assert(fd_num < VHOST_MEMORY_MAX_NREGIONS);
- fds[fd_num++] = fd;
- }
- }
+ vhost_user_write(dev, &msg, NULL, 0);
- msg.memory.nregions = fd_num;
+ return 0;
+}
- if (!fd_num) {
- error_report("Failed initializing vhost-user memory map, "
- "consider using -object memory-backend-file share=on");
- return -1;
- }
+static int vhost_user_set_vring_endian(struct vhost_dev *dev,
+ struct vhost_vring_state *ring)
+{
+ error_report("vhost-user trying to send unhandled ioctl");
+ return -1;
+}
- msg.size = sizeof(m.memory.nregions);
- msg.size += sizeof(m.memory.padding);
- msg.size += fd_num * sizeof(VhostUserMemoryRegion);
-
- break;
-
- case VHOST_USER_SET_LOG_FD:
- fds[fd_num++] = *((int *) arg);
- break;
-
- case VHOST_USER_SET_VRING_NUM:
- case VHOST_USER_SET_VRING_BASE:
- case VHOST_USER_SET_VRING_ENABLE:
- memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
- msg.size = sizeof(m.state);
- break;
-
- case VHOST_USER_GET_VRING_BASE:
- memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
- msg.size = sizeof(m.state);
- need_reply = 1;
- break;
-
- case VHOST_USER_SET_VRING_ADDR:
- memcpy(&msg.addr, arg, sizeof(struct vhost_vring_addr));
- msg.size = sizeof(m.addr);
- break;
-
- case VHOST_USER_SET_VRING_KICK:
- case VHOST_USER_SET_VRING_CALL:
- case VHOST_USER_SET_VRING_ERR:
- file = arg;
- msg.u64 = file->index & VHOST_USER_VRING_IDX_MASK;
- msg.size = sizeof(m.u64);
- if (ioeventfd_enabled() && file->fd > 0) {
- fds[fd_num++] = file->fd;
- } else {
- msg.u64 |= VHOST_USER_VRING_NOFD_MASK;
- }
- break;
- default:
- error_report("vhost-user trying to send unhandled ioctl");
+static int vhost_set_vring(struct vhost_dev *dev,
+ unsigned long int request,
+ struct vhost_vring_state *ring)
+{
+ VhostUserMsg msg = {
+ .request = request,
+ .flags = VHOST_USER_VERSION,
+ .state = *ring,
+ .size = sizeof(*ring),
+ };
+
+ vhost_user_write(dev, &msg, NULL, 0);
+
+ return 0;
+}
+
+static int vhost_user_set_vring_num(struct vhost_dev *dev,
+ struct vhost_vring_state *ring)
+{
+ return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring);
+}
+
+static int vhost_user_set_vring_base(struct vhost_dev *dev,
+ struct vhost_vring_state *ring)
+{
+ return vhost_set_vring(dev, VHOST_USER_SET_VRING_BASE, ring);
+}
+
+static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable)
+{
+ struct vhost_vring_state state = {
+ .index = dev->vq_index,
+ .num = enable,
+ };
+
+ if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ))) {
return -1;
- break;
}
- if (vhost_user_write(dev, &msg, fds, fd_num) < 0) {
+ return vhost_set_vring(dev, VHOST_USER_SET_VRING_ENABLE, &state);
+}
+
+
+static int vhost_user_get_vring_base(struct vhost_dev *dev,
+ struct vhost_vring_state *ring)
+{
+ VhostUserMsg msg = {
+ .request = VHOST_USER_GET_VRING_BASE,
+ .flags = VHOST_USER_VERSION,
+ .state = *ring,
+ .size = sizeof(*ring),
+ };
+
+ vhost_user_write(dev, &msg, NULL, 0);
+
+ if (vhost_user_read(dev, &msg) < 0) {
return 0;
}
- if (need_reply) {
- if (vhost_user_read(dev, &msg) < 0) {
- return 0;
- }
-
- if (msg_request != msg.request) {
- error_report("Received unexpected msg type."
- " Expected %d received %d", msg_request, msg.request);
- return -1;
- }
+ if (msg.request != VHOST_USER_GET_VRING_BASE) {
+ error_report("Received unexpected msg type. Expected %d received %d",
+ VHOST_USER_GET_VRING_BASE, msg.request);
+ return -1;
+ }
- switch (msg_request) {
- case VHOST_USER_GET_FEATURES:
- case VHOST_USER_GET_PROTOCOL_FEATURES:
- case VHOST_USER_GET_QUEUE_NUM:
- if (msg.size != sizeof(m.u64)) {
- error_report("Received bad msg size.");
- return -1;
- }
- *((__u64 *) arg) = msg.u64;
- break;
- case VHOST_USER_GET_VRING_BASE:
- if (msg.size != sizeof(m.state)) {
- error_report("Received bad msg size.");
- return -1;
- }
- memcpy(arg, &msg.state, sizeof(struct vhost_vring_state));
- break;
- default:
- error_report("Received unexpected msg type.");
- return -1;
- break;
- }
+ if (msg.size != sizeof(m.state)) {
+ error_report("Received bad msg size.");
+ return -1;
}
+ *ring = msg.state;
+
return 0;
}
-static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base,
- struct vhost_log *log)
+static int vhost_set_vring_file(struct vhost_dev *dev,
+ VhostUserRequest request,
+ struct vhost_vring_file *file)
{
int fds[VHOST_MEMORY_MAX_NREGIONS];
size_t fd_num = 0;
- bool shmfd = virtio_has_feature(dev->protocol_features,
- VHOST_USER_PROTOCOL_F_LOG_SHMFD);
VhostUserMsg msg = {
- .request = VHOST_USER_SET_LOG_BASE,
+ .request = request,
.flags = VHOST_USER_VERSION,
- .u64 = base,
+ .u64 = file->index & VHOST_USER_VRING_IDX_MASK,
.size = sizeof(m.u64),
};
- if (shmfd && log->fd != -1) {
- fds[fd_num++] = log->fd;
+ if (ioeventfd_enabled() && file->fd > 0) {
+ fds[fd_num++] = file->fd;
+ } else {
+ msg.u64 |= VHOST_USER_VRING_NOFD_MASK;
}
vhost_user_write(dev, &msg, fds, fd_num);
- if (shmfd) {
- msg.size = 0;
- if (vhost_user_read(dev, &msg) < 0) {
- return 0;
- }
+ return 0;
+}
- if (msg.request != VHOST_USER_SET_LOG_BASE) {
- error_report("Received unexpected msg type. "
- "Expected %d received %d",
- VHOST_USER_SET_LOG_BASE, msg.request);
- return -1;
- }
+static int vhost_user_set_vring_kick(struct vhost_dev *dev,
+ struct vhost_vring_file *file)
+{
+ return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_KICK, file);
+}
+
+static int vhost_user_set_vring_call(struct vhost_dev *dev,
+ struct vhost_vring_file *file)
+{
+ return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_CALL, file);
+}
+
+static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64)
+{
+ VhostUserMsg msg = {
+ .request = request,
+ .flags = VHOST_USER_VERSION,
+ .u64 = u64,
+ .size = sizeof(m.u64),
+ };
+
+ vhost_user_write(dev, &msg, NULL, 0);
+
+ return 0;
+}
+
+static int vhost_user_set_features(struct vhost_dev *dev,
+ uint64_t features)
+{
+ return vhost_user_set_u64(dev, VHOST_USER_SET_FEATURES, features);
+}
+
+static int vhost_user_set_protocol_features(struct vhost_dev *dev,
+ uint64_t features)
+{
+ return vhost_user_set_u64(dev, VHOST_USER_SET_PROTOCOL_FEATURES, features);
+}
+
+static int vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64)
+{
+ VhostUserMsg msg = {
+ .request = request,
+ .flags = VHOST_USER_VERSION,
+ };
+
+ if (vhost_user_one_time_request(request) && dev->vq_index != 0) {
+ return 0;
}
+ vhost_user_write(dev, &msg, NULL, 0);
+
+ if (vhost_user_read(dev, &msg) < 0) {
+ return 0;
+ }
+
+ if (msg.request != request) {
+ error_report("Received unexpected msg type. Expected %d received %d",
+ request, msg.request);
+ return -1;
+ }
+
+ if (msg.size != sizeof(m.u64)) {
+ error_report("Received bad msg size.");
+ return -1;
+ }
+
+ *u64 = msg.u64;
+
+ return 0;
+}
+
+static int vhost_user_get_features(struct vhost_dev *dev, uint64_t *features)
+{
+ return vhost_user_get_u64(dev, VHOST_USER_GET_FEATURES, features);
+}
+
+static int vhost_user_set_owner(struct vhost_dev *dev)
+{
+ VhostUserMsg msg = {
+ .request = VHOST_USER_SET_OWNER,
+ .flags = VHOST_USER_VERSION,
+ };
+
+ vhost_user_write(dev, &msg, NULL, 0);
+
+ return 0;
+}
+
+static int vhost_user_reset_device(struct vhost_dev *dev)
+{
+ VhostUserMsg msg = {
+ .request = VHOST_USER_RESET_DEVICE,
+ .flags = VHOST_USER_VERSION,
+ };
+
+ vhost_user_write(dev, &msg, NULL, 0);
+
return 0;
}
static int vhost_user_init(struct vhost_dev *dev, void *opaque)
{
- unsigned long long features;
+ uint64_t features;
int err;
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
dev->opaque = opaque;
- err = vhost_user_call(dev, VHOST_USER_GET_FEATURES, &features);
+ err = vhost_user_get_features(dev, &features);
if (err < 0) {
return err;
}
@@ -422,21 +504,22 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
if (virtio_has_feature(features, VHOST_USER_F_PROTOCOL_FEATURES)) {
dev->backend_features |= 1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
- err = vhost_user_call(dev, VHOST_USER_GET_PROTOCOL_FEATURES, &features);
+ err = vhost_user_get_u64(dev, VHOST_USER_GET_PROTOCOL_FEATURES,
+ &features);
if (err < 0) {
return err;
}
dev->protocol_features = features & VHOST_USER_PROTOCOL_FEATURE_MASK;
- err = vhost_user_call(dev, VHOST_USER_SET_PROTOCOL_FEATURES,
- &dev->protocol_features);
+ err = vhost_user_set_protocol_features(dev, dev->protocol_features);
if (err < 0) {
return err;
}
/* query the max queues we support if backend supports Multiple Queue */
if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ)) {
- err = vhost_user_call(dev, VHOST_USER_GET_QUEUE_NUM, &dev->max_queues);
+ err = vhost_user_get_u64(dev, VHOST_USER_GET_QUEUE_NUM,
+ &dev->max_queues);
if (err < 0) {
return err;
}
@@ -454,22 +537,6 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
return 0;
}
-static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable)
-{
- struct vhost_vring_state state = {
- .index = dev->vq_index,
- .num = enable,
- };
-
- assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
-
- if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ))) {
- return -1;
- }
-
- return vhost_user_call(dev, VHOST_USER_SET_VRING_ENABLE, &state);
-}
-
static int vhost_user_cleanup(struct vhost_dev *dev)
{
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
@@ -501,12 +568,23 @@ static bool vhost_user_requires_shm_log(struct vhost_dev *dev)
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
- .vhost_call = vhost_user_call,
.vhost_backend_init = vhost_user_init,
.vhost_backend_cleanup = vhost_user_cleanup,
- .vhost_backend_get_vq_index = vhost_user_get_vq_index,
- .vhost_backend_set_vring_enable = vhost_user_set_vring_enable,
.vhost_backend_memslots_limit = vhost_user_memslots_limit,
- .vhost_set_log_base = vhost_set_log_base,
+ .vhost_set_log_base = vhost_user_set_log_base,
+ .vhost_set_mem_table = vhost_user_set_mem_table,
+ .vhost_set_vring_addr = vhost_user_set_vring_addr,
+ .vhost_set_vring_endian = vhost_user_set_vring_endian,
+ .vhost_set_vring_num = vhost_user_set_vring_num,
+ .vhost_set_vring_base = vhost_user_set_vring_base,
+ .vhost_get_vring_base = vhost_user_get_vring_base,
+ .vhost_set_vring_kick = vhost_user_set_vring_kick,
+ .vhost_set_vring_call = vhost_user_set_vring_call,
+ .vhost_set_features = vhost_user_set_features,
+ .vhost_get_features = vhost_user_get_features,
+ .vhost_set_owner = vhost_user_set_owner,
+ .vhost_reset_device = vhost_user_reset_device,
+ .vhost_get_vq_index = vhost_user_get_vq_index,
+ .vhost_set_vring_enable = vhost_user_set_vring_enable,
.vhost_requires_shm_log = vhost_user_requires_shm_log,
};
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index a553256..2e78e4b 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -555,7 +555,7 @@ static void vhost_commit(MemoryListener *listener)
}
if (!dev->log_enabled) {
- r = dev->vhost_ops->vhost_call(dev, VHOST_SET_MEM_TABLE, dev->mem);
+ r = dev->vhost_ops->vhost_set_mem_table(dev, dev->mem);
assert(r >= 0);
dev->memory_changed = false;
return;
@@ -568,7 +568,7 @@ static void vhost_commit(MemoryListener *listener)
if (dev->log_size < log_size) {
vhost_dev_log_resize(dev, log_size + VHOST_LOG_BUFFER);
}
- r = dev->vhost_ops->vhost_call(dev, VHOST_SET_MEM_TABLE, dev->mem);
+ r = dev->vhost_ops->vhost_set_mem_table(dev, dev->mem);
assert(r >= 0);
/* To log less, can only decrease log size after table update. */
if (dev->log_size > log_size + VHOST_LOG_BUFFER) {
@@ -636,7 +636,7 @@ static int vhost_virtqueue_set_addr(struct vhost_dev *dev,
.log_guest_addr = vq->used_phys,
.flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0,
};
- int r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_ADDR, &addr);
+ int r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr);
if (r < 0) {
return -errno;
}
@@ -650,7 +650,7 @@ static int vhost_dev_set_features(struct vhost_dev *dev, bool enable_log)
if (enable_log) {
features |= 0x1ULL << VHOST_F_LOG_ALL;
}
- r = dev->vhost_ops->vhost_call(dev, VHOST_SET_FEATURES, &features);
+ r = dev->vhost_ops->vhost_set_features(dev, features);
return r < 0 ? -errno : 0;
}
@@ -755,7 +755,7 @@ static int vhost_virtqueue_set_vring_endian_legacy(struct vhost_dev *dev,
.num = is_big_endian
};
- if (!dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_ENDIAN, &s)) {
+ if (!dev->vhost_ops->vhost_set_vring_endian(dev, &s)) {
return 0;
}
@@ -774,7 +774,7 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
{
hwaddr s, l, a;
int r;
- int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, idx);
+ int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, idx);
struct vhost_vring_file file = {
.index = vhost_vq_index
};
@@ -785,13 +785,13 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
vq->num = state.num = virtio_queue_get_num(vdev, idx);
- r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_NUM, &state);
+ r = dev->vhost_ops->vhost_set_vring_num(dev, &state);
if (r) {
return -errno;
}
state.num = virtio_queue_get_last_avail_idx(vdev, idx);
- r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_BASE, &state);
+ r = dev->vhost_ops->vhost_set_vring_base(dev, &state);
if (r) {
return -errno;
}
@@ -843,7 +843,7 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
}
file.fd = event_notifier_get_fd(virtio_queue_get_host_notifier(vvq));
- r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_KICK, &file);
+ r = dev->vhost_ops->vhost_set_vring_kick(dev, &file);
if (r) {
r = -errno;
goto fail_kick;
@@ -876,13 +876,13 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev,
struct vhost_virtqueue *vq,
unsigned idx)
{
- int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, idx);
+ int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, idx);
struct vhost_vring_state state = {
.index = vhost_vq_index,
};
int r;
- r = dev->vhost_ops->vhost_call(dev, VHOST_GET_VRING_BASE, &state);
+ r = dev->vhost_ops->vhost_get_vring_base(dev, &state);
if (r < 0) {
fprintf(stderr, "vhost VQ %d ring restore failed: %d\n", idx, r);
fflush(stderr);
@@ -929,7 +929,7 @@ static void vhost_eventfd_del(MemoryListener *listener,
static int vhost_virtqueue_init(struct vhost_dev *dev,
struct vhost_virtqueue *vq, int n)
{
- int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, n);
+ int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, n);
struct vhost_vring_file file = {
.index = vhost_vq_index,
};
@@ -939,7 +939,7 @@ static int vhost_virtqueue_init(struct vhost_dev *dev,
}
file.fd = event_notifier_get_fd(&vq->masked_notifier);
- r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_CALL, &file);
+ r = dev->vhost_ops->vhost_set_vring_call(dev, &file);
if (r) {
r = -errno;
goto fail_call;
@@ -981,12 +981,12 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
}
QLIST_INSERT_HEAD(&vhost_devices, hdev, entry);
- r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_OWNER, NULL);
+ r = hdev->vhost_ops->vhost_set_owner(hdev);
if (r < 0) {
goto fail;
}
- r = hdev->vhost_ops->vhost_call(hdev, VHOST_GET_FEATURES, &features);
+ r = hdev->vhost_ops->vhost_get_features(hdev, &features);
if (r < 0) {
goto fail;
}
@@ -1147,8 +1147,8 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n,
file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq));
}
- file.index = hdev->vhost_ops->vhost_backend_get_vq_index(hdev, n);
- r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_VRING_CALL, &file);
+ file.index = hdev->vhost_ops->vhost_get_vq_index(hdev, n);
+ r = hdev->vhost_ops->vhost_set_vring_call(hdev, &file);
assert(r >= 0);
}
@@ -1190,7 +1190,7 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
if (r < 0) {
goto fail_features;
}
- r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_MEM_TABLE, hdev->mem);
+ r = hdev->vhost_ops->vhost_set_mem_table(hdev, hdev->mem);
if (r < 0) {
r = -errno;
goto fail_mem;
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* Re: [Qemu-devel] [PULL 21/38] vhost: use a function for each call
2015-10-21 10:27 ` [Qemu-devel] [PULL 21/38] vhost: use a function for each call Michael S. Tsirkin
@ 2015-10-22 14:09 ` Laurent Desnogues
2015-10-22 14:17 ` Michael S. Tsirkin
0 siblings, 1 reply; 45+ messages in thread
From: Laurent Desnogues @ 2015-10-22 14:09 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Peter Maydell, Thibaut Collet, Jason Wang, qemu-devel,
Paolo Bonzini, Marc-André Lureau
Hello,
There are some errors with gcc 4.4.7 due to the use of an anonymous
union in VhostUserMsg in declarations with initialization. Please see
below.
Thanks.
On Wed, Oct 21, 2015 at 12:27 PM, Michael S. Tsirkin <mst@redhat.com> wrote:
> From: Marc-André Lureau <marcandre.lureau@redhat.com>
>
> Replace the generic vhost_call() by specific functions for each
> function call to help with type safety and changing arguments.
>
> While doing this, I found that "unsigned long long" and "uint64_t" were
> used interchangeably and causing compilation warnings, using uint64_t
> instead, as the vhost & protocol specifies.
>
> Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
> [Fix enum usage and MQ - Thibaut Collet]
> Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
> Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
> ---
> include/hw/virtio/vhost-backend.h | 63 ++++-
> include/hw/virtio/vhost.h | 12 +-
> hw/net/vhost_net.c | 16 +-
> hw/scsi/vhost-scsi.c | 7 +-
> hw/virtio/vhost-backend.c | 132 +++++++++-
> hw/virtio/vhost-user.c | 522 ++++++++++++++++++++++----------------
> hw/virtio/vhost.c | 36 +--
> 7 files changed, 509 insertions(+), 279 deletions(-)
>
[...]
> diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
> index fb3aa40..16d8e80 100644
> --- a/hw/virtio/vhost-user.c
> +++ b/hw/virtio/vhost-user.c
[...]
> @@ -190,231 +182,321 @@ static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg,
> 0 : -1;
> }
>
> -static bool vhost_user_one_time_request(VhostUserRequest request)
> +static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base,
> + struct vhost_log *log)
> {
> - switch (request) {
> - case VHOST_USER_SET_OWNER:
> - case VHOST_USER_RESET_DEVICE:
> - case VHOST_USER_SET_MEM_TABLE:
> - case VHOST_USER_GET_QUEUE_NUM:
> - return true;
> - default:
> - return false;
> + int fds[VHOST_MEMORY_MAX_NREGIONS];
> + size_t fd_num = 0;
> + bool shmfd = virtio_has_feature(dev->protocol_features,
> + VHOST_USER_PROTOCOL_F_LOG_SHMFD);
> + VhostUserMsg msg = {
> + .request = VHOST_USER_SET_LOG_BASE,
> + .flags = VHOST_USER_VERSION,
> + .u64 = base,
gcc 4.4.7 on CentOS 6.7 doesn't like this use of anonymous union.
> + .size = sizeof(m.u64),
> + };
> +
> + if (shmfd && log->fd != -1) {
> + fds[fd_num++] = log->fd;
> + }
> +
> + vhost_user_write(dev, &msg, fds, fd_num);
> +
> + if (shmfd) {
> + msg.size = 0;
> + if (vhost_user_read(dev, &msg) < 0) {
> + return 0;
> + }
> +
> + if (msg.request != VHOST_USER_SET_LOG_BASE) {
> + error_report("Received unexpected msg type. "
> + "Expected %d received %d",
> + VHOST_USER_SET_LOG_BASE, msg.request);
> + return -1;
> + }
> }
> +
> + return 0;
> }
>
> -static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
> - void *arg)
> +static int vhost_user_set_mem_table(struct vhost_dev *dev,
> + struct vhost_memory *mem)
> {
> - VhostUserMsg msg;
> - VhostUserRequest msg_request;
> - struct vhost_vring_file *file = 0;
> - int need_reply = 0;
> int fds[VHOST_MEMORY_MAX_NREGIONS];
> int i, fd;
> size_t fd_num = 0;
> + VhostUserMsg msg = {
> + .request = VHOST_USER_SET_MEM_TABLE,
> + .flags = VHOST_USER_VERSION,
> + };
>
> - assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
> -
> - /* only translate vhost ioctl requests */
> - if (request > VHOST_USER_MAX) {
> - msg_request = vhost_user_request_translate(request);
> - } else {
> - msg_request = request;
> + for (i = 0; i < dev->mem->nregions; ++i) {
> + struct vhost_memory_region *reg = dev->mem->regions + i;
> + ram_addr_t ram_addr;
> +
> + assert((uintptr_t)reg->userspace_addr == reg->userspace_addr);
> + qemu_ram_addr_from_host((void *)(uintptr_t)reg->userspace_addr,
> + &ram_addr);
> + fd = qemu_get_ram_fd(ram_addr);
> + if (fd > 0) {
> + msg.memory.regions[fd_num].userspace_addr = reg->userspace_addr;
> + msg.memory.regions[fd_num].memory_size = reg->memory_size;
> + msg.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr;
> + msg.memory.regions[fd_num].mmap_offset = reg->userspace_addr -
> + (uintptr_t) qemu_get_ram_block_host_ptr(ram_addr);
> + assert(fd_num < VHOST_MEMORY_MAX_NREGIONS);
> + fds[fd_num++] = fd;
> + }
> }
>
> - /*
> - * For non-vring specific requests, like VHOST_USER_SET_MEM_TABLE,
> - * we just need send it once in the first time. For later such
> - * request, we just ignore it.
> - */
> - if (vhost_user_one_time_request(msg_request) && dev->vq_index != 0) {
> - return 0;
> + msg.memory.nregions = fd_num;
> +
> + if (!fd_num) {
> + error_report("Failed initializing vhost-user memory map, "
> + "consider using -object memory-backend-file share=on");
> + return -1;
> }
>
> - msg.request = msg_request;
> - msg.flags = VHOST_USER_VERSION;
> - msg.size = 0;
> + msg.size = sizeof(m.memory.nregions);
> + msg.size += sizeof(m.memory.padding);
> + msg.size += fd_num * sizeof(VhostUserMemoryRegion);
>
> - switch (msg_request) {
> - case VHOST_USER_GET_FEATURES:
> - case VHOST_USER_GET_PROTOCOL_FEATURES:
> - case VHOST_USER_GET_QUEUE_NUM:
> - need_reply = 1;
> - break;
> + vhost_user_write(dev, &msg, fds, fd_num);
>
> - case VHOST_USER_SET_FEATURES:
> - case VHOST_USER_SET_PROTOCOL_FEATURES:
> - msg.u64 = *((__u64 *) arg);
> - msg.size = sizeof(m.u64);
> - break;
> + return 0;
> +}
>
> - case VHOST_USER_SET_OWNER:
> - case VHOST_USER_RESET_DEVICE:
> - break;
> +static int vhost_user_set_vring_addr(struct vhost_dev *dev,
> + struct vhost_vring_addr *addr)
> +{
> + VhostUserMsg msg = {
> + .request = VHOST_USER_SET_VRING_ADDR,
> + .flags = VHOST_USER_VERSION,
> + .addr = *addr,
Ditto.
> + .size = sizeof(*addr),
> + };
>
> - case VHOST_USER_SET_MEM_TABLE:
> - for (i = 0; i < dev->mem->nregions; ++i) {
> - struct vhost_memory_region *reg = dev->mem->regions + i;
> - ram_addr_t ram_addr;
> -
> - assert((uintptr_t)reg->userspace_addr == reg->userspace_addr);
> - qemu_ram_addr_from_host((void *)(uintptr_t)reg->userspace_addr, &ram_addr);
> - fd = qemu_get_ram_fd(ram_addr);
> - if (fd > 0) {
> - msg.memory.regions[fd_num].userspace_addr = reg->userspace_addr;
> - msg.memory.regions[fd_num].memory_size = reg->memory_size;
> - msg.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr;
> - msg.memory.regions[fd_num].mmap_offset = reg->userspace_addr -
> - (uintptr_t) qemu_get_ram_block_host_ptr(ram_addr);
> - assert(fd_num < VHOST_MEMORY_MAX_NREGIONS);
> - fds[fd_num++] = fd;
> - }
> - }
> + vhost_user_write(dev, &msg, NULL, 0);
>
> - msg.memory.nregions = fd_num;
> + return 0;
> +}
>
> - if (!fd_num) {
> - error_report("Failed initializing vhost-user memory map, "
> - "consider using -object memory-backend-file share=on");
> - return -1;
> - }
> +static int vhost_user_set_vring_endian(struct vhost_dev *dev,
> + struct vhost_vring_state *ring)
> +{
> + error_report("vhost-user trying to send unhandled ioctl");
> + return -1;
> +}
>
> - msg.size = sizeof(m.memory.nregions);
> - msg.size += sizeof(m.memory.padding);
> - msg.size += fd_num * sizeof(VhostUserMemoryRegion);
> -
> - break;
> -
> - case VHOST_USER_SET_LOG_FD:
> - fds[fd_num++] = *((int *) arg);
> - break;
> -
> - case VHOST_USER_SET_VRING_NUM:
> - case VHOST_USER_SET_VRING_BASE:
> - case VHOST_USER_SET_VRING_ENABLE:
> - memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
> - msg.size = sizeof(m.state);
> - break;
> -
> - case VHOST_USER_GET_VRING_BASE:
> - memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
> - msg.size = sizeof(m.state);
> - need_reply = 1;
> - break;
> -
> - case VHOST_USER_SET_VRING_ADDR:
> - memcpy(&msg.addr, arg, sizeof(struct vhost_vring_addr));
> - msg.size = sizeof(m.addr);
> - break;
> -
> - case VHOST_USER_SET_VRING_KICK:
> - case VHOST_USER_SET_VRING_CALL:
> - case VHOST_USER_SET_VRING_ERR:
> - file = arg;
> - msg.u64 = file->index & VHOST_USER_VRING_IDX_MASK;
> - msg.size = sizeof(m.u64);
> - if (ioeventfd_enabled() && file->fd > 0) {
> - fds[fd_num++] = file->fd;
> - } else {
> - msg.u64 |= VHOST_USER_VRING_NOFD_MASK;
> - }
> - break;
> - default:
> - error_report("vhost-user trying to send unhandled ioctl");
> +static int vhost_set_vring(struct vhost_dev *dev,
> + unsigned long int request,
> + struct vhost_vring_state *ring)
> +{
> + VhostUserMsg msg = {
> + .request = request,
> + .flags = VHOST_USER_VERSION,
> + .state = *ring,
Ditto.
> + .size = sizeof(*ring),
> + };
> +
> + vhost_user_write(dev, &msg, NULL, 0);
> +
> + return 0;
> +}
> +
> +static int vhost_user_set_vring_num(struct vhost_dev *dev,
> + struct vhost_vring_state *ring)
> +{
> + return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring);
> +}
> +
> +static int vhost_user_set_vring_base(struct vhost_dev *dev,
> + struct vhost_vring_state *ring)
> +{
> + return vhost_set_vring(dev, VHOST_USER_SET_VRING_BASE, ring);
> +}
> +
> +static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable)
> +{
> + struct vhost_vring_state state = {
> + .index = dev->vq_index,
> + .num = enable,
> + };
> +
> + if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ))) {
> return -1;
> - break;
> }
>
> - if (vhost_user_write(dev, &msg, fds, fd_num) < 0) {
> + return vhost_set_vring(dev, VHOST_USER_SET_VRING_ENABLE, &state);
> +}
> +
> +
> +static int vhost_user_get_vring_base(struct vhost_dev *dev,
> + struct vhost_vring_state *ring)
> +{
> + VhostUserMsg msg = {
> + .request = VHOST_USER_GET_VRING_BASE,
> + .flags = VHOST_USER_VERSION,
> + .state = *ring,
Ditto.
> + .size = sizeof(*ring),
> + };
> +
> + vhost_user_write(dev, &msg, NULL, 0);
> +
> + if (vhost_user_read(dev, &msg) < 0) {
> return 0;
> }
>
> - if (need_reply) {
> - if (vhost_user_read(dev, &msg) < 0) {
> - return 0;
> - }
> -
> - if (msg_request != msg.request) {
> - error_report("Received unexpected msg type."
> - " Expected %d received %d", msg_request, msg.request);
> - return -1;
> - }
> + if (msg.request != VHOST_USER_GET_VRING_BASE) {
> + error_report("Received unexpected msg type. Expected %d received %d",
> + VHOST_USER_GET_VRING_BASE, msg.request);
> + return -1;
> + }
>
> - switch (msg_request) {
> - case VHOST_USER_GET_FEATURES:
> - case VHOST_USER_GET_PROTOCOL_FEATURES:
> - case VHOST_USER_GET_QUEUE_NUM:
> - if (msg.size != sizeof(m.u64)) {
> - error_report("Received bad msg size.");
> - return -1;
> - }
> - *((__u64 *) arg) = msg.u64;
> - break;
> - case VHOST_USER_GET_VRING_BASE:
> - if (msg.size != sizeof(m.state)) {
> - error_report("Received bad msg size.");
> - return -1;
> - }
> - memcpy(arg, &msg.state, sizeof(struct vhost_vring_state));
> - break;
> - default:
> - error_report("Received unexpected msg type.");
> - return -1;
> - break;
> - }
> + if (msg.size != sizeof(m.state)) {
> + error_report("Received bad msg size.");
> + return -1;
> }
>
> + *ring = msg.state;
> +
> return 0;
> }
>
> -static int vhost_set_log_base(struct vhost_dev *dev, uint64_t base,
> - struct vhost_log *log)
> +static int vhost_set_vring_file(struct vhost_dev *dev,
> + VhostUserRequest request,
> + struct vhost_vring_file *file)
> {
> int fds[VHOST_MEMORY_MAX_NREGIONS];
> size_t fd_num = 0;
> - bool shmfd = virtio_has_feature(dev->protocol_features,
> - VHOST_USER_PROTOCOL_F_LOG_SHMFD);
> VhostUserMsg msg = {
> - .request = VHOST_USER_SET_LOG_BASE,
> + .request = request,
> .flags = VHOST_USER_VERSION,
> - .u64 = base,
> + .u64 = file->index & VHOST_USER_VRING_IDX_MASK,
Ditto.
> .size = sizeof(m.u64),
> };
>
> - if (shmfd && log->fd != -1) {
> - fds[fd_num++] = log->fd;
> + if (ioeventfd_enabled() && file->fd > 0) {
> + fds[fd_num++] = file->fd;
> + } else {
> + msg.u64 |= VHOST_USER_VRING_NOFD_MASK;
> }
>
> vhost_user_write(dev, &msg, fds, fd_num);
>
> - if (shmfd) {
> - msg.size = 0;
> - if (vhost_user_read(dev, &msg) < 0) {
> - return 0;
> - }
> + return 0;
> +}
>
> - if (msg.request != VHOST_USER_SET_LOG_BASE) {
> - error_report("Received unexpected msg type. "
> - "Expected %d received %d",
> - VHOST_USER_SET_LOG_BASE, msg.request);
> - return -1;
> - }
> +static int vhost_user_set_vring_kick(struct vhost_dev *dev,
> + struct vhost_vring_file *file)
> +{
> + return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_KICK, file);
> +}
> +
> +static int vhost_user_set_vring_call(struct vhost_dev *dev,
> + struct vhost_vring_file *file)
> +{
> + return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_CALL, file);
> +}
> +
> +static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64)
> +{
> + VhostUserMsg msg = {
> + .request = request,
> + .flags = VHOST_USER_VERSION,
> + .u64 = u64,
Ditto.
Thanks,
Laurent
> + .size = sizeof(m.u64),
> + };
> +
> + vhost_user_write(dev, &msg, NULL, 0);
> +
> + return 0;
> +}
> +
> +static int vhost_user_set_features(struct vhost_dev *dev,
> + uint64_t features)
> +{
> + return vhost_user_set_u64(dev, VHOST_USER_SET_FEATURES, features);
> +}
> +
> +static int vhost_user_set_protocol_features(struct vhost_dev *dev,
> + uint64_t features)
> +{
> + return vhost_user_set_u64(dev, VHOST_USER_SET_PROTOCOL_FEATURES, features);
> +}
> +
> +static int vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64)
> +{
> + VhostUserMsg msg = {
> + .request = request,
> + .flags = VHOST_USER_VERSION,
> + };
> +
> + if (vhost_user_one_time_request(request) && dev->vq_index != 0) {
> + return 0;
> }
>
> + vhost_user_write(dev, &msg, NULL, 0);
> +
> + if (vhost_user_read(dev, &msg) < 0) {
> + return 0;
> + }
> +
> + if (msg.request != request) {
> + error_report("Received unexpected msg type. Expected %d received %d",
> + request, msg.request);
> + return -1;
> + }
> +
> + if (msg.size != sizeof(m.u64)) {
> + error_report("Received bad msg size.");
> + return -1;
> + }
> +
> + *u64 = msg.u64;
> +
> + return 0;
> +}
> +
> +static int vhost_user_get_features(struct vhost_dev *dev, uint64_t *features)
> +{
> + return vhost_user_get_u64(dev, VHOST_USER_GET_FEATURES, features);
> +}
> +
> +static int vhost_user_set_owner(struct vhost_dev *dev)
> +{
> + VhostUserMsg msg = {
> + .request = VHOST_USER_SET_OWNER,
> + .flags = VHOST_USER_VERSION,
> + };
> +
> + vhost_user_write(dev, &msg, NULL, 0);
> +
> + return 0;
> +}
> +
> +static int vhost_user_reset_device(struct vhost_dev *dev)
> +{
> + VhostUserMsg msg = {
> + .request = VHOST_USER_RESET_DEVICE,
> + .flags = VHOST_USER_VERSION,
> + };
> +
> + vhost_user_write(dev, &msg, NULL, 0);
> +
> return 0;
> }
>
> static int vhost_user_init(struct vhost_dev *dev, void *opaque)
> {
> - unsigned long long features;
> + uint64_t features;
> int err;
>
> assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
>
> dev->opaque = opaque;
>
> - err = vhost_user_call(dev, VHOST_USER_GET_FEATURES, &features);
> + err = vhost_user_get_features(dev, &features);
> if (err < 0) {
> return err;
> }
> @@ -422,21 +504,22 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
> if (virtio_has_feature(features, VHOST_USER_F_PROTOCOL_FEATURES)) {
> dev->backend_features |= 1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
>
> - err = vhost_user_call(dev, VHOST_USER_GET_PROTOCOL_FEATURES, &features);
> + err = vhost_user_get_u64(dev, VHOST_USER_GET_PROTOCOL_FEATURES,
> + &features);
> if (err < 0) {
> return err;
> }
>
> dev->protocol_features = features & VHOST_USER_PROTOCOL_FEATURE_MASK;
> - err = vhost_user_call(dev, VHOST_USER_SET_PROTOCOL_FEATURES,
> - &dev->protocol_features);
> + err = vhost_user_set_protocol_features(dev, dev->protocol_features);
> if (err < 0) {
> return err;
> }
>
> /* query the max queues we support if backend supports Multiple Queue */
> if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ)) {
> - err = vhost_user_call(dev, VHOST_USER_GET_QUEUE_NUM, &dev->max_queues);
> + err = vhost_user_get_u64(dev, VHOST_USER_GET_QUEUE_NUM,
> + &dev->max_queues);
> if (err < 0) {
> return err;
> }
> @@ -454,22 +537,6 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
> return 0;
> }
>
> -static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable)
> -{
> - struct vhost_vring_state state = {
> - .index = dev->vq_index,
> - .num = enable,
> - };
> -
> - assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
> -
> - if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ))) {
> - return -1;
> - }
> -
> - return vhost_user_call(dev, VHOST_USER_SET_VRING_ENABLE, &state);
> -}
> -
> static int vhost_user_cleanup(struct vhost_dev *dev)
> {
> assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
> @@ -501,12 +568,23 @@ static bool vhost_user_requires_shm_log(struct vhost_dev *dev)
>
> const VhostOps user_ops = {
> .backend_type = VHOST_BACKEND_TYPE_USER,
> - .vhost_call = vhost_user_call,
> .vhost_backend_init = vhost_user_init,
> .vhost_backend_cleanup = vhost_user_cleanup,
> - .vhost_backend_get_vq_index = vhost_user_get_vq_index,
> - .vhost_backend_set_vring_enable = vhost_user_set_vring_enable,
> .vhost_backend_memslots_limit = vhost_user_memslots_limit,
> - .vhost_set_log_base = vhost_set_log_base,
> + .vhost_set_log_base = vhost_user_set_log_base,
> + .vhost_set_mem_table = vhost_user_set_mem_table,
> + .vhost_set_vring_addr = vhost_user_set_vring_addr,
> + .vhost_set_vring_endian = vhost_user_set_vring_endian,
> + .vhost_set_vring_num = vhost_user_set_vring_num,
> + .vhost_set_vring_base = vhost_user_set_vring_base,
> + .vhost_get_vring_base = vhost_user_get_vring_base,
> + .vhost_set_vring_kick = vhost_user_set_vring_kick,
> + .vhost_set_vring_call = vhost_user_set_vring_call,
> + .vhost_set_features = vhost_user_set_features,
> + .vhost_get_features = vhost_user_get_features,
> + .vhost_set_owner = vhost_user_set_owner,
> + .vhost_reset_device = vhost_user_reset_device,
> + .vhost_get_vq_index = vhost_user_get_vq_index,
> + .vhost_set_vring_enable = vhost_user_set_vring_enable,
> .vhost_requires_shm_log = vhost_user_requires_shm_log,
> };
^ permalink raw reply [flat|nested] 45+ messages in thread* Re: [Qemu-devel] [PULL 21/38] vhost: use a function for each call
2015-10-22 14:09 ` Laurent Desnogues
@ 2015-10-22 14:17 ` Michael S. Tsirkin
0 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-22 14:17 UTC (permalink / raw)
To: Laurent Desnogues
Cc: Peter Maydell, Thibaut Collet, Jason Wang, qemu-devel,
Paolo Bonzini, Marc-André Lureau
On Thu, Oct 22, 2015 at 04:09:30PM +0200, Laurent Desnogues wrote:
> Hello,
>
> There are some errors with gcc 4.4.7 due to the use of an anonymous
> union in VhostUserMsg in declarations with initialization. Please see
> below.
>
> Thanks.
I don't have this system: want to send a patch?
^ permalink raw reply [flat|nested] 45+ messages in thread
* [Qemu-devel] [PULL 22/38] vhost-user: document migration log
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (20 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 21/38] vhost: use a function for each call Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 23/38] net: add trace_vhost_user_event Michael S. Tsirkin
` (16 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Yuanhan Liu, Thibaut Collet, Nikolay Nikolaev,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Changchun Ouyang
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
docs/specs/vhost-user.txt | 48 +++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 46 insertions(+), 2 deletions(-)
diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt
index 4eadad1..e0292a0 100644
--- a/docs/specs/vhost-user.txt
+++ b/docs/specs/vhost-user.txt
@@ -115,11 +115,13 @@ the ones that do:
* VHOST_GET_FEATURES
* VHOST_GET_PROTOCOL_FEATURES
* VHOST_GET_VRING_BASE
+ * VHOST_SET_LOG_BASE (if VHOST_USER_PROTOCOL_F_LOG_SHMFD)
There are several messages that the master sends with file descriptors passed
in the ancillary data:
* VHOST_SET_MEM_TABLE
+ * VHOST_SET_LOG_BASE (if VHOST_USER_PROTOCOL_F_LOG_SHMFD)
* VHOST_SET_LOG_FD
* VHOST_SET_VRING_KICK
* VHOST_SET_VRING_CALL
@@ -140,8 +142,7 @@ Multiple queue support
Multiple queue is treated as a protocol extension, hence the slave has to
implement protocol features first. The multiple queues feature is supported
-only when the protocol feature VHOST_USER_PROTOCOL_F_MQ (bit 0) is set:
-#define VHOST_USER_PROTOCOL_F_MQ 0
+only when the protocol feature VHOST_USER_PROTOCOL_F_MQ (bit 0) is set.
The max number of queues the slave supports can be queried with message
VHOST_USER_GET_PROTOCOL_FEATURES. Master should stop when the number of
@@ -152,6 +153,48 @@ queue in the sent message to identify a specified queue. One queue pair
is enabled initially. More queues are enabled dynamically, by sending
message VHOST_USER_SET_VRING_ENABLE.
+Migration
+---------
+
+During live migration, the master may need to track the modifications
+the slave makes to the memory mapped regions. The client should mark
+the dirty pages in a log. Once it complies to this logging, it may
+declare the VHOST_F_LOG_ALL vhost feature.
+
+All the modifications to memory pointed by vring "descriptor" should
+be marked. Modifications to "used" vring should be marked if
+VHOST_VRING_F_LOG is part of ring's features.
+
+Dirty pages are of size:
+#define VHOST_LOG_PAGE 0x1000
+
+The log memory fd is provided in the ancillary data of
+VHOST_USER_SET_LOG_BASE message when the slave has
+VHOST_USER_PROTOCOL_F_LOG_SHMFD protocol feature.
+
+The size of the log may be computed by using all the known guest
+addresses. The log covers from address 0 to the maximum of guest
+regions. In pseudo-code, to mark page at "addr" as dirty:
+
+page = addr / VHOST_LOG_PAGE
+log[page / 8] |= 1 << page % 8
+
+Use atomic operations, as the log may be concurrently manipulated.
+
+VHOST_USER_SET_LOG_FD is an optional message with an eventfd in
+ancillary data, it may be used to inform the master that the log has
+been modified.
+
+Once the source has finished migration, VHOST_USER_RESET_OWNER message
+will be sent by the source. No further update must be done before the
+destination takes over with new regions & rings.
+
+Protocol features
+-----------------
+
+#define VHOST_USER_PROTOCOL_F_MQ 0
+#define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1
+
Message types
-------------
@@ -236,6 +279,7 @@ Message types
Id: 6
Equivalent ioctl: VHOST_SET_LOG_BASE
Master payload: u64
+ Slave payload: N/A
Sets the logging base address.
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 23/38] net: add trace_vhost_user_event
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (21 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 22/38] vhost-user: document migration log Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 24/38] vhost user: add support of live migration Michael S. Tsirkin
` (15 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Jason Wang, Thibaut Collet,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Replace error_report() and use tracing instead. It's not an error to get
a connection or a disconnection, so silence this and trace it instead.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
net/vhost-user.c | 4 ++--
trace-events | 3 +++
2 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/net/vhost-user.c b/net/vhost-user.c
index 8f354eb..9b38431 100644
--- a/net/vhost-user.c
+++ b/net/vhost-user.c
@@ -15,6 +15,7 @@
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qmp-commands.h"
+#include "trace.h"
typedef struct VhostUserState {
NetClientState nc;
@@ -148,18 +149,17 @@ static void net_vhost_user_event(void *opaque, int event)
NET_CLIENT_OPTIONS_KIND_NIC,
MAX_QUEUE_NUM);
s = DO_UPCAST(VhostUserState, nc, ncs[0]);
+ trace_vhost_user_event(s->chr->label, event);
switch (event) {
case CHR_EVENT_OPENED:
if (vhost_user_start(queues, ncs) < 0) {
exit(1);
}
qmp_set_link(name, true, &err);
- error_report("chardev \"%s\" went up", s->chr->label);
break;
case CHR_EVENT_CLOSED:
qmp_set_link(name, true, &err);
vhost_user_stop(queues, ncs);
- error_report("chardev \"%s\" went down", s->chr->label);
break;
}
diff --git a/trace-events b/trace-events
index a0ddc6b..f237c7f 100644
--- a/trace-events
+++ b/trace-events
@@ -1705,3 +1705,6 @@ qcrypto_tls_creds_x509_load_cert_list(void *creds, const char *file) "TLS creds
# crypto/tlssession.c
qcrypto_tls_session_new(void *session, void *creds, const char *hostname, const char *aclname, int endpoint) "TLS session new session=%p creds=%p hostname=%s aclname=%s endpoint=%d"
+
+# net/vhost-user.c
+vhost_user_event(const char *chr, int event) "chr: %s got event: %d"
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 24/38] vhost user: add support of live migration
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (22 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 23/38] net: add trace_vhost_user_event Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:27 ` [Qemu-devel] [PULL 25/38] vhost user: add rarp sending after live migration for legacy guest Michael S. Tsirkin
` (14 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel; +Cc: Peter Maydell, Jason Wang, Thibaut Collet
From: Thibaut Collet <thibaut.collet@6wind.com>
Some vhost user backends are able to support live migration.
To provide this service the following features must be added:
1. Add the VIRTIO_NET_F_GUEST_ANNOUNCE capability to vhost-net when netdev
backend is vhost-user.
2. Provide a nop receive callback to vhost-user.
This callback is called by:
* qemu_announce_self after a migration to send fake RARP to avoid network
outage for peers talking to the migrated guest.
- For guest with GUEST_ANNOUNCE capabilities, guest already sends GARP
when the bit VIRTIO_NET_S_ANNOUNCE is set.
=> These packets must be discarded.
- For guest without GUEST_ANNOUNCE capabilities, migration termination
is notified when the guest sends packets.
=> These packets can be discarded.
* virtio_net_tx_bh with a dummy boot to send fake bootp/dhcp request.
BIOS guest manages virtio driver to send 4 bootp/dhcp request in case of
dummy boot.
=> These packets must be discarded.
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
hw/net/vhost_net.c | 2 ++
net/vhost-user.c | 12 ++++++++++--
2 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 1ab4133..840f443 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -85,6 +85,8 @@ static const int user_feature_bits[] = {
VIRTIO_NET_F_CTRL_MAC_ADDR,
VIRTIO_NET_F_CTRL_GUEST_OFFLOADS,
+ VIRTIO_NET_F_GUEST_ANNOUNCE,
+
VIRTIO_NET_F_MQ,
VHOST_INVALID_FEATURE_BIT
diff --git a/net/vhost-user.c b/net/vhost-user.c
index 9b38431..b067524 100644
--- a/net/vhost-user.c
+++ b/net/vhost-user.c
@@ -103,6 +103,15 @@ err:
return -1;
}
+static ssize_t vhost_user_receive(NetClientState *nc, const uint8_t *buf,
+ size_t size)
+{
+ /* Discard the request that is received and managed by backend
+ * by an other way.
+ */
+ return size;
+}
+
static void vhost_user_cleanup(NetClientState *nc)
{
VhostUserState *s = DO_UPCAST(VhostUserState, nc, nc);
@@ -132,6 +141,7 @@ static bool vhost_user_has_ufo(NetClientState *nc)
static NetClientInfo net_vhost_user_info = {
.type = NET_CLIENT_OPTIONS_KIND_VHOST_USER,
.size = sizeof(VhostUserState),
+ .receive = vhost_user_receive,
.cleanup = vhost_user_cleanup,
.has_vnet_hdr = vhost_user_has_vnet_hdr,
.has_ufo = vhost_user_has_ufo,
@@ -182,8 +192,6 @@ static int net_vhost_user_init(NetClientState *peer, const char *device,
snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user%d to %s",
i, chr->label);
- /* We don't provide a receive callback */
- nc->receive_disabled = 1;
nc->queue_index = i;
s = DO_UPCAST(VhostUserState, nc, nc);
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 25/38] vhost user: add rarp sending after live migration for legacy guest
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (23 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 24/38] vhost user: add support of live migration Michael S. Tsirkin
@ 2015-10-21 10:27 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 26/38] vhost-user: use an enum helper for features mask Michael S. Tsirkin
` (13 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:27 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Jason Wang, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Thibaut Collet
From: Thibaut Collet <thibaut.collet@6wind.com>
A new vhost user message is added to allow QEMU to ask to vhost user backend to
broadcast a fake RARP after live migration for guest without GUEST_ANNOUNCE
capability.
This new message is sent only if the backend supports the new
VHOST_USER_PROTOCOL_F_RARP protocol feature.
The payload of this new message is the MAC address of the guest (not known by
the backend). The MAC address is copied in the first 6 bytes of a u64 to avoid
to create a new payload message type.
This new message has no equivalent ioctl so a new callback is added in the
userOps structure to send the request.
Upon reception of this new message the vhost user backend must generate and
broadcast a fake RARP request to notify the migration is terminated.
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
[Rebased and fixed checkpatch errors - Marc-André]
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/hw/virtio/vhost-backend.h | 3 +++
include/net/vhost_net.h | 1 +
hw/net/vhost_net.c | 17 +++++++++++++++++
hw/virtio/vhost-user.c | 32 +++++++++++++++++++++++++++++++-
net/vhost-user.c | 24 ++++++++++++++++++++++--
docs/specs/vhost-user.txt | 15 +++++++++++++++
6 files changed, 89 insertions(+), 3 deletions(-)
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index ad19481..c59cc81 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -68,6 +68,8 @@ typedef int (*vhost_get_vq_index_op)(struct vhost_dev *dev, int idx);
typedef int (*vhost_set_vring_enable_op)(struct vhost_dev *dev,
int enable);
typedef bool (*vhost_requires_shm_log_op)(struct vhost_dev *dev);
+typedef int (*vhost_migration_done_op)(struct vhost_dev *dev,
+ char *mac_addr);
typedef struct VhostOps {
VhostBackendType backend_type;
@@ -94,6 +96,7 @@ typedef struct VhostOps {
vhost_get_vq_index_op vhost_get_vq_index;
vhost_set_vring_enable_op vhost_set_vring_enable;
vhost_requires_shm_log_op vhost_requires_shm_log;
+ vhost_migration_done_op vhost_migration_done;
} VhostOps;
extern const VhostOps user_ops;
diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h
index 0188c4d..3389b41 100644
--- a/include/net/vhost_net.h
+++ b/include/net/vhost_net.h
@@ -27,6 +27,7 @@ void vhost_net_ack_features(VHostNetState *net, uint64_t features);
bool vhost_net_virtqueue_pending(VHostNetState *net, int n);
void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
int idx, bool mask);
+int vhost_net_notify_migration_done(VHostNetState *net, char* mac_addr);
VHostNetState *get_vhost_net(NetClientState *nc);
int vhost_set_vring_enable(NetClientState * nc, int enable);
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 840f443..d91b7b1 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -388,6 +388,18 @@ void vhost_net_cleanup(struct vhost_net *net)
g_free(net);
}
+int vhost_net_notify_migration_done(struct vhost_net *net, char* mac_addr)
+{
+ const VhostOps *vhost_ops = net->dev.vhost_ops;
+ int r = -1;
+
+ if (vhost_ops->vhost_migration_done) {
+ r = vhost_ops->vhost_migration_done(&net->dev, mac_addr);
+ }
+
+ return r;
+}
+
bool vhost_net_virtqueue_pending(VHostNetState *net, int idx)
{
return vhost_virtqueue_pending(&net->dev, idx);
@@ -479,6 +491,11 @@ void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
{
}
+int vhost_net_notify_migration_done(struct vhost_net *net, char* mac_addr)
+{
+ return -1;
+}
+
VHostNetState *get_vhost_net(NetClientState *nc)
{
return 0;
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 16d8e80..d804c5f 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -10,6 +10,7 @@
#include "hw/virtio/vhost.h"
#include "hw/virtio/vhost-backend.h"
+#include "hw/virtio/virtio-net.h"
#include "sysemu/char.h"
#include "sysemu/kvm.h"
#include "qemu/error-report.h"
@@ -27,9 +28,10 @@
#define VHOST_MEMORY_MAX_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
-#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x3ULL
+#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x7ULL
#define VHOST_USER_PROTOCOL_F_MQ 0
#define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1
+#define VHOST_USER_PROTOCOL_F_RARP 2
typedef enum VhostUserRequest {
VHOST_USER_NONE = 0,
@@ -51,6 +53,7 @@ typedef enum VhostUserRequest {
VHOST_USER_SET_PROTOCOL_FEATURES = 16,
VHOST_USER_GET_QUEUE_NUM = 17,
VHOST_USER_SET_VRING_ENABLE = 18,
+ VHOST_USER_SEND_RARP = 19,
VHOST_USER_MAX
} VhostUserRequest;
@@ -566,6 +569,32 @@ static bool vhost_user_requires_shm_log(struct vhost_dev *dev)
VHOST_USER_PROTOCOL_F_LOG_SHMFD);
}
+static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr)
+{
+ VhostUserMsg msg = { 0 };
+ int err;
+
+ assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
+
+ /* If guest supports GUEST_ANNOUNCE do nothing */
+ if (virtio_has_feature(dev->acked_features, VIRTIO_NET_F_GUEST_ANNOUNCE)) {
+ return 0;
+ }
+
+ /* if backend supports VHOST_USER_PROTOCOL_F_RARP ask it to send the RARP */
+ if (virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_RARP)) {
+ msg.request = VHOST_USER_SEND_RARP;
+ msg.flags = VHOST_USER_VERSION;
+ memcpy((char *)&msg.u64, mac_addr, 6);
+ msg.size = sizeof(m.u64);
+
+ err = vhost_user_write(dev, &msg, NULL, 0);
+ return err;
+ }
+ return -1;
+}
+
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
.vhost_backend_init = vhost_user_init,
@@ -587,4 +616,5 @@ const VhostOps user_ops = {
.vhost_get_vq_index = vhost_user_get_vq_index,
.vhost_set_vring_enable = vhost_user_set_vring_enable,
.vhost_requires_shm_log = vhost_user_requires_shm_log,
+ .vhost_migration_done = vhost_user_migration_done,
};
diff --git a/net/vhost-user.c b/net/vhost-user.c
index b067524..17b5c2a 100644
--- a/net/vhost-user.c
+++ b/net/vhost-user.c
@@ -106,9 +106,29 @@ err:
static ssize_t vhost_user_receive(NetClientState *nc, const uint8_t *buf,
size_t size)
{
- /* Discard the request that is received and managed by backend
- * by an other way.
+ /* In case of RARP (message size is 60) notify backup to send a fake RARP.
+ This fake RARP will be sent by backend only for guest
+ without GUEST_ANNOUNCE capability.
*/
+ if (size == 60) {
+ VhostUserState *s = DO_UPCAST(VhostUserState, nc, nc);
+ int r;
+ static int display_rarp_failure = 1;
+ char mac_addr[6];
+
+ /* extract guest mac address from the RARP message */
+ memcpy(mac_addr, &buf[6], 6);
+
+ r = vhost_net_notify_migration_done(s->vhost_net, mac_addr);
+
+ if ((r != 0) && (display_rarp_failure)) {
+ fprintf(stderr,
+ "Vhost user backend fails to broadcast fake RARP\n");
+ fflush(stderr);
+ display_rarp_failure = 0;
+ }
+ }
+
return size;
}
diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt
index e0292a0..e0d71e2 100644
--- a/docs/specs/vhost-user.txt
+++ b/docs/specs/vhost-user.txt
@@ -194,6 +194,7 @@ Protocol features
#define VHOST_USER_PROTOCOL_F_MQ 0
#define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1
+#define VHOST_USER_PROTOCOL_F_RARP 2
Message types
-------------
@@ -381,3 +382,17 @@ Message types
Master payload: vring state description
Signal slave to enable or disable corresponding vring.
+
+ * VHOST_USER_SEND_RARP
+
+ Id: 19
+ Equivalent ioctl: N/A
+ Master payload: u64
+
+ Ask vhost user backend to broadcast a fake RARP to notify the migration
+ is terminated for guest that does not support GUEST_ANNOUNCE.
+ Only legal if feature bit VHOST_USER_F_PROTOCOL_FEATURES is present in
+ VHOST_USER_GET_FEATURES and protocol feature bit VHOST_USER_PROTOCOL_F_RARP
+ is present in VHOST_USER_GET_PROTOCOL_FEATURES.
+ The first 6 bytes of the payload contain the mac address of the guest to
+ allow the vhost user backend to construct and broadcast the fake RARP.
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 26/38] vhost-user: use an enum helper for features mask
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (24 preceding siblings ...)
2015-10-21 10:27 ` [Qemu-devel] [PULL 25/38] vhost user: add rarp sending after live migration for legacy guest Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 27/38] vhost: add migration block if memfd failed Michael S. Tsirkin
` (12 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=, Thibaut Collet
From: Thibaut Collet <thibaut.collet@6wind.com>
The VHOST_USER_PROTOCOL_FEATURE_MASK will be automatically updated when
adding new features to the enum.
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
[Adapted from mailing list discussion - Marc-André]
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
hw/virtio/vhost-user.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index d804c5f..78442ba 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -28,10 +28,15 @@
#define VHOST_MEMORY_MAX_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
-#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x7ULL
-#define VHOST_USER_PROTOCOL_F_MQ 0
-#define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1
-#define VHOST_USER_PROTOCOL_F_RARP 2
+enum VhostUserProtocolFeature {
+ VHOST_USER_PROTOCOL_F_MQ = 0,
+ VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1,
+ VHOST_USER_PROTOCOL_F_RARP = 2,
+
+ VHOST_USER_PROTOCOL_F_MAX
+};
+
+#define VHOST_USER_PROTOCOL_FEATURE_MASK ((1 << VHOST_USER_PROTOCOL_F_MAX) - 1)
typedef enum VhostUserRequest {
VHOST_USER_NONE = 0,
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 27/38] vhost: add migration block if memfd failed
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (25 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 26/38] vhost-user: use an enum helper for features mask Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 28/38] vhost-user-test: move wait_for_fds() out Michael S. Tsirkin
` (11 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
include/qemu/memfd.h | 2 ++
hw/virtio/vhost.c | 3 +++
util/memfd.c | 22 ++++++++++++++++++++++
3 files changed, 27 insertions(+)
diff --git a/include/qemu/memfd.h b/include/qemu/memfd.h
index 950fb88..53858ed 100644
--- a/include/qemu/memfd.h
+++ b/include/qemu/memfd.h
@@ -2,6 +2,7 @@
#define QEMU_MEMFD_H
#include "config-host.h"
+#include <stdbool.h>
#ifndef F_LINUX_SPECIFIC_BASE
#define F_LINUX_SPECIFIC_BASE 1024
@@ -20,5 +21,6 @@
void *qemu_memfd_alloc(const char *name, size_t size, unsigned int seals,
int *fd);
void qemu_memfd_free(void *ptr, size_t size, int fd);
+bool qemu_memfd_check(void);
#endif /* QEMU_MEMFD_H */
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 2e78e4b..feeaaa4 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -1019,6 +1019,9 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
if (!(hdev->features & (0x1ULL << VHOST_F_LOG_ALL))) {
error_setg(&hdev->migration_blocker,
"Migration disabled: vhost lacks VHOST_F_LOG_ALL feature.");
+ } else if (!qemu_memfd_check()) {
+ error_setg(&hdev->migration_blocker,
+ "Migration disabled: failed to allocate shared memory");
}
}
diff --git a/util/memfd.c b/util/memfd.c
index 4b23765..7c40691 100644
--- a/util/memfd.c
+++ b/util/memfd.c
@@ -138,3 +138,25 @@ void qemu_memfd_free(void *ptr, size_t size, int fd)
close(fd);
}
}
+
+enum {
+ MEMFD_KO,
+ MEMFD_OK,
+ MEMFD_TODO
+};
+
+bool qemu_memfd_check(void)
+{
+ static int memfd_check = MEMFD_TODO;
+
+ if (memfd_check == MEMFD_TODO) {
+ int fd;
+ void *ptr;
+
+ ptr = qemu_memfd_alloc("test", 4096, 0, &fd);
+ memfd_check = ptr ? MEMFD_OK : MEMFD_KO;
+ qemu_memfd_free(ptr, 4096, fd);
+ }
+
+ return memfd_check == MEMFD_OK;
+}
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 28/38] vhost-user-test: move wait_for_fds() out
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (26 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 27/38] vhost: add migration block if memfd failed Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 29/38] vhost-user-test: remove useless static check Michael S. Tsirkin
` (10 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Marcel Apfelbaum, Peter Maydell, Yuanhan Liu, Thibaut Collet,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
This function is a precondition for most vhost-user tests.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
tests/vhost-user-test.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c
index 56df5cc..827c0c4 100644
--- a/tests/vhost-user-test.c
+++ b/tests/vhost-user-test.c
@@ -126,12 +126,9 @@ static gboolean g_cond_wait_until(CompatGCond cond, CompatGMutex mutex,
}
#endif
-static void read_guest_mem(void)
+static void wait_for_fds(void)
{
- uint32_t *guest_mem;
gint64 end_time;
- int i, j;
- size_t size;
g_mutex_lock(&data_mutex);
@@ -148,6 +145,19 @@ static void read_guest_mem(void)
g_assert_cmpint(fds_num, >, 0);
g_assert_cmpint(fds_num, ==, memory.nregions);
+ g_mutex_unlock(&data_mutex);
+}
+
+static void read_guest_mem(void)
+{
+ uint32_t *guest_mem;
+ int i, j;
+ size_t size;
+
+ wait_for_fds();
+
+ g_mutex_lock(&data_mutex);
+
/* iterate all regions */
for (i = 0; i < fds_num; i++) {
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 29/38] vhost-user-test: remove useless static check
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (27 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 28/38] vhost-user-test: move wait_for_fds() out Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 30/38] vhost-user-test: wrap server in TestServer struct Michael S. Tsirkin
` (9 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Yuanhan Liu, Paolo Bonzini, Thibaut Collet,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
tests/vhost-user-test.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c
index 827c0c4..4be5583 100644
--- a/tests/vhost-user-test.c
+++ b/tests/vhost-user-test.c
@@ -186,7 +186,6 @@ static void read_guest_mem(void)
munmap(guest_mem, memory.regions[i].memory_size);
}
- g_assert_cmpint(1, ==, 1);
g_mutex_unlock(&data_mutex);
}
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 30/38] vhost-user-test: wrap server in TestServer struct
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (28 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 29/38] vhost-user-test: remove useless static check Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 31/38] vhost-user-test: learn to tweak various qemu arguments Michael S. Tsirkin
` (8 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Marcel Apfelbaum, Peter Maydell, Yuanhan Liu, Thibaut Collet,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
In the coming patches, a test will use several servers
simultaneously. Wrap the server in a struct, out of the global scope.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
tests/vhost-user-test.c | 139 +++++++++++++++++++++++++++++++-----------------
1 file changed, 89 insertions(+), 50 deletions(-)
diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c
index 4be5583..034d89b 100644
--- a/tests/vhost-user-test.c
+++ b/tests/vhost-user-test.c
@@ -108,10 +108,16 @@ static VhostUserMsg m __attribute__ ((unused));
#define VHOST_USER_VERSION (0x1)
/*****************************************************************************/
-int fds_num = 0, fds[VHOST_MEMORY_MAX_NREGIONS];
-static VhostUserMemory memory;
-static CompatGMutex data_mutex;
-static CompatGCond data_cond;
+typedef struct TestServer {
+ gchar *socket_path;
+ gchar *chr_name;
+ CharDriverState *chr;
+ int fds_num;
+ int fds[VHOST_MEMORY_MAX_NREGIONS];
+ VhostUserMemory memory;
+ GMutex data_mutex;
+ GCond data_cond;
+} TestServer;
#if !GLIB_CHECK_VERSION(2, 32, 0)
static gboolean g_cond_wait_until(CompatGCond cond, CompatGMutex mutex,
@@ -126,67 +132,68 @@ static gboolean g_cond_wait_until(CompatGCond cond, CompatGMutex mutex,
}
#endif
-static void wait_for_fds(void)
+static void wait_for_fds(TestServer *s)
{
gint64 end_time;
- g_mutex_lock(&data_mutex);
+ g_mutex_lock(&s->data_mutex);
end_time = g_get_monotonic_time() + 5 * G_TIME_SPAN_SECOND;
- while (!fds_num) {
- if (!g_cond_wait_until(&data_cond, &data_mutex, end_time)) {
+ while (!s->fds_num) {
+ if (!g_cond_wait_until(&s->data_cond, &s->data_mutex, end_time)) {
/* timeout has passed */
- g_assert(fds_num);
+ g_assert(s->fds_num);
break;
}
}
/* check for sanity */
- g_assert_cmpint(fds_num, >, 0);
- g_assert_cmpint(fds_num, ==, memory.nregions);
+ g_assert_cmpint(s->fds_num, >, 0);
+ g_assert_cmpint(s->fds_num, ==, s->memory.nregions);
- g_mutex_unlock(&data_mutex);
+ g_mutex_unlock(&s->data_mutex);
}
-static void read_guest_mem(void)
+static void read_guest_mem(TestServer *s)
{
uint32_t *guest_mem;
int i, j;
size_t size;
- wait_for_fds();
+ wait_for_fds(s);
- g_mutex_lock(&data_mutex);
+ g_mutex_lock(&s->data_mutex);
/* iterate all regions */
- for (i = 0; i < fds_num; i++) {
+ for (i = 0; i < s->fds_num; i++) {
/* We'll check only the region statring at 0x0*/
- if (memory.regions[i].guest_phys_addr != 0x0) {
+ if (s->memory.regions[i].guest_phys_addr != 0x0) {
continue;
}
- g_assert_cmpint(memory.regions[i].memory_size, >, 1024);
+ g_assert_cmpint(s->memory.regions[i].memory_size, >, 1024);
- size = memory.regions[i].memory_size + memory.regions[i].mmap_offset;
+ size = s->memory.regions[i].memory_size +
+ s->memory.regions[i].mmap_offset;
guest_mem = mmap(0, size, PROT_READ | PROT_WRITE,
- MAP_SHARED, fds[i], 0);
+ MAP_SHARED, s->fds[i], 0);
g_assert(guest_mem != MAP_FAILED);
- guest_mem += (memory.regions[i].mmap_offset / sizeof(*guest_mem));
+ guest_mem += (s->memory.regions[i].mmap_offset / sizeof(*guest_mem));
for (j = 0; j < 256; j++) {
- uint32_t a = readl(memory.regions[i].guest_phys_addr + j*4);
+ uint32_t a = readl(s->memory.regions[i].guest_phys_addr + j*4);
uint32_t b = guest_mem[j];
g_assert_cmpint(a, ==, b);
}
- munmap(guest_mem, memory.regions[i].memory_size);
+ munmap(guest_mem, s->memory.regions[i].memory_size);
}
- g_mutex_unlock(&data_mutex);
+ g_mutex_unlock(&s->data_mutex);
}
static void *thread_function(void *data)
@@ -204,7 +211,8 @@ static int chr_can_read(void *opaque)
static void chr_read(void *opaque, const uint8_t *buf, int size)
{
- CharDriverState *chr = opaque;
+ TestServer *s = opaque;
+ CharDriverState *chr = s->chr;
VhostUserMsg msg;
uint8_t *p = (uint8_t *) &msg;
int fd;
@@ -214,12 +222,12 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
return;
}
- g_mutex_lock(&data_mutex);
+ g_mutex_lock(&s->data_mutex);
memcpy(p, buf, VHOST_USER_HDR_SIZE);
if (msg.size) {
p += VHOST_USER_HDR_SIZE;
- qemu_chr_fe_read_all(chr, p, msg.size);
+ g_assert_cmpint(qemu_chr_fe_read_all(chr, p, msg.size), ==, msg.size);
}
switch (msg.request) {
@@ -257,11 +265,11 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
case VHOST_USER_SET_MEM_TABLE:
/* received the mem table */
- memcpy(&memory, &msg.memory, sizeof(msg.memory));
- fds_num = qemu_chr_fe_get_msgfds(chr, fds, sizeof(fds) / sizeof(int));
+ memcpy(&s->memory, &msg.memory, sizeof(msg.memory));
+ s->fds_num = qemu_chr_fe_get_msgfds(chr, s->fds, G_N_ELEMENTS(s->fds));
/* signal the test that it can continue */
- g_cond_signal(&data_cond);
+ g_cond_signal(&s->data_cond);
break;
case VHOST_USER_SET_VRING_KICK:
@@ -278,7 +286,8 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
default:
break;
}
- g_mutex_unlock(&data_mutex);
+
+ g_mutex_unlock(&s->data_mutex);
}
static const char *init_hugepagefs(const char *path)
@@ -308,14 +317,52 @@ static const char *init_hugepagefs(const char *path)
return path;
}
+static TestServer *test_server_new(const gchar *tmpfs, const gchar *name)
+{
+ TestServer *server = g_new0(TestServer, 1);
+ gchar *chr_path;
+
+ server->socket_path = g_strdup_printf("%s/%s.sock", tmpfs, name);
+
+ chr_path = g_strdup_printf("unix:%s,server,nowait", server->socket_path);
+ server->chr_name = g_strdup_printf("chr-%s", name);
+ server->chr = qemu_chr_new(server->chr_name, chr_path, NULL);
+ g_free(chr_path);
+
+ qemu_chr_add_handlers(server->chr, chr_can_read, chr_read, NULL, server);
+
+ g_mutex_init(&server->data_mutex);
+ g_cond_init(&server->data_cond);
+
+ return server;
+}
+
+#define GET_QEMU_CMD(s, root) \
+ g_strdup_printf(QEMU_CMD, (root), (s)->socket_path)
+
+
+static void test_server_free(TestServer *server)
+{
+ int i;
+
+ qemu_chr_delete(server->chr);
+
+ for (i = 0; i < server->fds_num; i++) {
+ close(server->fds[i]);
+ }
+
+ unlink(server->socket_path);
+ g_free(server->socket_path);
+
+ g_free(server);
+}
+
int main(int argc, char **argv)
{
QTestState *s = NULL;
- CharDriverState *chr = NULL;
+ TestServer *server = NULL;
const char *hugefs;
- char *socket_path = 0;
- char *qemu_cmd = 0;
- char *chr_path = 0;
+ char *qemu_cmd = NULL;
int ret;
char template[] = "/tmp/vhost-test-XXXXXX";
const char *tmpfs;
@@ -324,10 +371,11 @@ int main(int argc, char **argv)
g_test_init(&argc, &argv, NULL);
module_call_init(MODULE_INIT_QOM);
+ qemu_add_opts(&qemu_chardev_opts);
tmpfs = mkdtemp(template);
if (!tmpfs) {
- g_test_message("mkdtemp on path (%s): %s\n", template, strerror(errno));
+ g_test_message("mkdtemp on path (%s): %s\n", template, strerror(errno));
}
g_assert(tmpfs);
@@ -339,25 +387,17 @@ int main(int argc, char **argv)
root = tmpfs;
}
- socket_path = g_strdup_printf("%s/vhost.sock", tmpfs);
-
- /* create char dev and add read handlers */
- qemu_add_opts(&qemu_chardev_opts);
- chr_path = g_strdup_printf("unix:%s,server,nowait", socket_path);
- chr = qemu_chr_new("chr0", chr_path, NULL);
- g_free(chr_path);
- qemu_chr_add_handlers(chr, chr_can_read, chr_read, NULL, chr);
+ server = test_server_new(tmpfs, "test");
/* run the main loop thread so the chardev may operate */
- g_mutex_init(&data_mutex);
- g_cond_init(&data_cond);
g_thread_new(NULL, thread_function, NULL);
- qemu_cmd = g_strdup_printf(QEMU_CMD, root, socket_path);
+ qemu_cmd = GET_QEMU_CMD(server, root);
+
s = qtest_start(qemu_cmd);
g_free(qemu_cmd);
- qtest_add_func("/vhost-user/read-guest-mem", read_guest_mem);
+ qtest_add_data_func("/vhost-user/read-guest-mem", server, read_guest_mem);
ret = g_test_run();
@@ -366,8 +406,7 @@ int main(int argc, char **argv)
}
/* cleanup */
- unlink(socket_path);
- g_free(socket_path);
+ test_server_free(server);
ret = rmdir(tmpfs);
if (ret != 0) {
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 31/38] vhost-user-test: learn to tweak various qemu arguments
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (29 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 30/38] vhost-user-test: wrap server in TestServer struct Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 32/38] vhost-user-test: add live-migration test Michael S. Tsirkin
` (7 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Yuanhan Liu, Thibaut Collet, Gonglei,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Paolo Bonzini
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Add a new macro to make the qemu command line with other
values of memory size, and specific chardev id.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
tests/vhost-user-test.c | 25 +++++++++++++++----------
1 file changed, 15 insertions(+), 10 deletions(-)
diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c
index 034d89b..791d849 100644
--- a/tests/vhost-user-test.c
+++ b/tests/vhost-user-test.c
@@ -30,10 +30,10 @@
#endif
#define QEMU_CMD_ACCEL " -machine accel=tcg"
-#define QEMU_CMD_MEM " -m 512 -object memory-backend-file,id=mem,size=512M,"\
+#define QEMU_CMD_MEM " -m %d -object memory-backend-file,id=mem,size=%dM,"\
"mem-path=%s,share=on -numa node,memdev=mem"
-#define QEMU_CMD_CHR " -chardev socket,id=chr0,path=%s"
-#define QEMU_CMD_NETDEV " -netdev vhost-user,id=net0,chardev=chr0,vhostforce"
+#define QEMU_CMD_CHR " -chardev socket,id=%s,path=%s"
+#define QEMU_CMD_NETDEV " -netdev vhost-user,id=net0,chardev=%s,vhostforce"
#define QEMU_CMD_NET " -device virtio-net-pci,netdev=net0 "
#define QEMU_CMD_ROM " -option-rom ../pc-bios/pxe-virtio.rom"
@@ -132,6 +132,9 @@ static gboolean g_cond_wait_until(CompatGCond cond, CompatGMutex mutex,
}
#endif
+static const char *tmpfs;
+static const char *root;
+
static void wait_for_fds(TestServer *s)
{
gint64 end_time;
@@ -317,7 +320,7 @@ static const char *init_hugepagefs(const char *path)
return path;
}
-static TestServer *test_server_new(const gchar *tmpfs, const gchar *name)
+static TestServer *test_server_new(const gchar *name)
{
TestServer *server = g_new0(TestServer, 1);
gchar *chr_path;
@@ -337,9 +340,13 @@ static TestServer *test_server_new(const gchar *tmpfs, const gchar *name)
return server;
}
-#define GET_QEMU_CMD(s, root) \
- g_strdup_printf(QEMU_CMD, (root), (s)->socket_path)
+#define GET_QEMU_CMD(s) \
+ g_strdup_printf(QEMU_CMD, 512, 512, (root), (s)->chr_name, \
+ (s)->socket_path, (s)->chr_name)
+#define GET_QEMU_CMDE(s, mem, extra, ...) \
+ g_strdup_printf(QEMU_CMD extra, (mem), (mem), (root), (s)->chr_name, \
+ (s)->socket_path, (s)->chr_name, ##__VA_ARGS__)
static void test_server_free(TestServer *server)
{
@@ -365,8 +372,6 @@ int main(int argc, char **argv)
char *qemu_cmd = NULL;
int ret;
char template[] = "/tmp/vhost-test-XXXXXX";
- const char *tmpfs;
- const char *root;
g_test_init(&argc, &argv, NULL);
@@ -387,12 +392,12 @@ int main(int argc, char **argv)
root = tmpfs;
}
- server = test_server_new(tmpfs, "test");
+ server = test_server_new("test");
/* run the main loop thread so the chardev may operate */
g_thread_new(NULL, thread_function, NULL);
- qemu_cmd = GET_QEMU_CMD(server, root);
+ qemu_cmd = GET_QEMU_CMD(server);
s = qtest_start(qemu_cmd);
g_free(qemu_cmd);
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 32/38] vhost-user-test: add live-migration test
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (30 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 31/38] vhost-user-test: learn to tweak various qemu arguments Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 33/38] vhost-user-test: check ownership during migration Michael S. Tsirkin
` (6 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Yuanhan Liu, Gonglei, Thibaut Collet,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Marc-André Lureau <marcandre.lureau@redhat.com>
This test checks that the log fd is given to the migration source, and
mark dirty pages during migration.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
tests/vhost-user-test.c | 171 +++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 169 insertions(+), 2 deletions(-)
diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c
index 791d849..ef22e3e 100644
--- a/tests/vhost-user-test.c
+++ b/tests/vhost-user-test.c
@@ -12,6 +12,7 @@
#include "libqtest.h"
#include "qemu/option.h"
+#include "qemu/range.h"
#include "sysemu/char.h"
#include "sysemu/sysemu.h"
@@ -47,6 +48,9 @@
#define VHOST_MEMORY_MAX_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
+#define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1
+
+#define VHOST_LOG_PAGE 0x1000
typedef enum VhostUserRequest {
VHOST_USER_NONE = 0,
@@ -117,6 +121,7 @@ typedef struct TestServer {
VhostUserMemory memory;
GMutex data_mutex;
GCond data_cond;
+ int log_fd;
} TestServer;
#if !GLIB_CHECK_VERSION(2, 32, 0)
@@ -238,7 +243,8 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
/* send back features to qemu */
msg.flags |= VHOST_USER_REPLY_MASK;
msg.size = sizeof(m.u64);
- msg.u64 = 0x1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
+ msg.u64 = 0x1ULL << VHOST_F_LOG_ALL |
+ 0x1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
p = (uint8_t *) &msg;
qemu_chr_fe_write_all(chr, p, VHOST_USER_HDR_SIZE + msg.size);
break;
@@ -252,7 +258,7 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
/* send back features to qemu */
msg.flags |= VHOST_USER_REPLY_MASK;
msg.size = sizeof(m.u64);
- msg.u64 = 0;
+ msg.u64 = 1 << VHOST_USER_PROTOCOL_F_LOG_SHMFD;
p = (uint8_t *) &msg;
qemu_chr_fe_write_all(chr, p, VHOST_USER_HDR_SIZE + msg.size);
break;
@@ -286,6 +292,21 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
*/
qemu_set_nonblock(fd);
break;
+
+ case VHOST_USER_SET_LOG_BASE:
+ if (s->log_fd != -1) {
+ close(s->log_fd);
+ s->log_fd = -1;
+ }
+ qemu_chr_fe_get_msgfds(chr, &s->log_fd, 1);
+ msg.flags |= VHOST_USER_REPLY_MASK;
+ msg.size = 0;
+ p = (uint8_t *) &msg;
+ qemu_chr_fe_write_all(chr, p, VHOST_USER_HDR_SIZE);
+
+ g_cond_signal(&s->data_cond);
+ break;
+
default:
break;
}
@@ -337,6 +358,8 @@ static TestServer *test_server_new(const gchar *name)
g_mutex_init(&server->data_mutex);
g_cond_init(&server->data_cond);
+ server->log_fd = -1;
+
return server;
}
@@ -358,12 +381,155 @@ static void test_server_free(TestServer *server)
close(server->fds[i]);
}
+ if (server->log_fd != -1) {
+ close(server->log_fd);
+ }
+
unlink(server->socket_path);
g_free(server->socket_path);
+
+ g_free(server->chr_name);
g_free(server);
}
+static void wait_for_log_fd(TestServer *s)
+{
+ gint64 end_time;
+
+ g_mutex_lock(&s->data_mutex);
+ end_time = g_get_monotonic_time() + 5 * G_TIME_SPAN_SECOND;
+ while (s->log_fd == -1) {
+ if (!g_cond_wait_until(&s->data_cond, &s->data_mutex, end_time)) {
+ /* timeout has passed */
+ g_assert(s->log_fd != -1);
+ break;
+ }
+ }
+
+ g_mutex_unlock(&s->data_mutex);
+}
+
+static void write_guest_mem(TestServer *s, uint32 seed)
+{
+ uint32_t *guest_mem;
+ int i, j;
+ size_t size;
+
+ wait_for_fds(s);
+
+ /* iterate all regions */
+ for (i = 0; i < s->fds_num; i++) {
+
+ /* We'll write only the region statring at 0x0 */
+ if (s->memory.regions[i].guest_phys_addr != 0x0) {
+ continue;
+ }
+
+ g_assert_cmpint(s->memory.regions[i].memory_size, >, 1024);
+
+ size = s->memory.regions[i].memory_size +
+ s->memory.regions[i].mmap_offset;
+
+ guest_mem = mmap(0, size, PROT_READ | PROT_WRITE,
+ MAP_SHARED, s->fds[i], 0);
+
+ g_assert(guest_mem != MAP_FAILED);
+ guest_mem += (s->memory.regions[i].mmap_offset / sizeof(*guest_mem));
+
+ for (j = 0; j < 256; j++) {
+ guest_mem[j] = seed + j;
+ }
+
+ munmap(guest_mem, s->memory.regions[i].memory_size);
+ break;
+ }
+}
+
+static guint64 get_log_size(TestServer *s)
+{
+ guint64 log_size = 0;
+ int i;
+
+ for (i = 0; i < s->memory.nregions; ++i) {
+ VhostUserMemoryRegion *reg = &s->memory.regions[i];
+ guint64 last = range_get_last(reg->guest_phys_addr,
+ reg->memory_size);
+ log_size = MAX(log_size, last / (8 * VHOST_LOG_PAGE) + 1);
+ }
+
+ return log_size;
+}
+
+static void test_migrate(void)
+{
+ TestServer *s = test_server_new("src");
+ TestServer *dest = test_server_new("dest");
+ const char *uri = "tcp:127.0.0.1:1234";
+ QTestState *global = global_qtest, *from, *to;
+ gchar *cmd;
+ QDict *rsp;
+ guint8 *log;
+ guint64 size;
+
+ cmd = GET_QEMU_CMDE(s, 2, "");
+ from = qtest_start(cmd);
+ g_free(cmd);
+
+ wait_for_fds(s);
+ size = get_log_size(s);
+ g_assert_cmpint(size, ==, (2 * 1024 * 1024) / (VHOST_LOG_PAGE * 8));
+
+ cmd = GET_QEMU_CMDE(dest, 2, " -incoming %s", uri);
+ to = qtest_init(cmd);
+ g_free(cmd);
+
+ /* slow down migration to have time to fiddle with log */
+ /* TODO: qtest could learn to break on some places */
+ rsp = qmp("{ 'execute': 'migrate_set_speed',"
+ "'arguments': { 'value': 10 } }");
+ g_assert(qdict_haskey(rsp, "return"));
+ QDECREF(rsp);
+
+ cmd = g_strdup_printf("{ 'execute': 'migrate',"
+ "'arguments': { 'uri': '%s' } }",
+ uri);
+ rsp = qmp(cmd);
+ g_free(cmd);
+ g_assert(qdict_haskey(rsp, "return"));
+ QDECREF(rsp);
+
+ wait_for_log_fd(s);
+
+ log = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, s->log_fd, 0);
+ g_assert(log != MAP_FAILED);
+
+ /* modify first page */
+ write_guest_mem(s, 0x42);
+ log[0] = 1;
+ munmap(log, size);
+
+ /* speed things up */
+ rsp = qmp("{ 'execute': 'migrate_set_speed',"
+ "'arguments': { 'value': 0 } }");
+ g_assert(qdict_haskey(rsp, "return"));
+ QDECREF(rsp);
+
+ qmp_eventwait("STOP");
+
+ global_qtest = to;
+ qmp_eventwait("RESUME");
+
+ read_guest_mem(dest);
+
+ qtest_quit(to);
+ test_server_free(dest);
+ qtest_quit(from);
+ test_server_free(s);
+
+ global_qtest = global;
+}
+
int main(int argc, char **argv)
{
QTestState *s = NULL;
@@ -403,6 +569,7 @@ int main(int argc, char **argv)
g_free(qemu_cmd);
qtest_add_data_func("/vhost-user/read-guest-mem", server, read_guest_mem);
+ qtest_add_func("/vhost-user/migrate", test_migrate);
ret = g_test_run();
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 33/38] vhost-user-test: check ownership during migration
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (31 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 32/38] vhost-user-test: add live-migration test Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 34/38] seccomp: add memfd_create to whitelist Michael S. Tsirkin
` (5 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Yuanhan Liu, Thibaut Collet, Gonglei,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=,
Paolo Bonzini
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Check that backend source and destination do not have simultaneous
ownership during migration.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
tests/vhost-user-test.c | 38 ++++++++++++++++++++++++++++++++++++++
1 file changed, 38 insertions(+)
diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c
index ef22e3e..a74c934 100644
--- a/tests/vhost-user-test.c
+++ b/tests/vhost-user-test.c
@@ -307,6 +307,10 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
g_cond_signal(&s->data_cond);
break;
+ case VHOST_USER_RESET_DEVICE:
+ s->fds_num = 0;
+ break;
+
default:
break;
}
@@ -461,12 +465,37 @@ static guint64 get_log_size(TestServer *s)
return log_size;
}
+typedef struct TestMigrateSource {
+ GSource source;
+ TestServer *src;
+ TestServer *dest;
+} TestMigrateSource;
+
+static gboolean
+test_migrate_source_check(GSource *source)
+{
+ TestMigrateSource *t = (TestMigrateSource *)source;
+ gboolean overlap = t->src->fds_num > 0 && t->dest->fds_num > 0;
+
+ g_assert(!overlap);
+
+ return FALSE;
+}
+
+GSourceFuncs test_migrate_source_funcs = {
+ NULL,
+ test_migrate_source_check,
+ NULL,
+ NULL
+};
+
static void test_migrate(void)
{
TestServer *s = test_server_new("src");
TestServer *dest = test_server_new("dest");
const char *uri = "tcp:127.0.0.1:1234";
QTestState *global = global_qtest, *from, *to;
+ GSource *source;
gchar *cmd;
QDict *rsp;
guint8 *log;
@@ -484,6 +513,12 @@ static void test_migrate(void)
to = qtest_init(cmd);
g_free(cmd);
+ source = g_source_new(&test_migrate_source_funcs,
+ sizeof(TestMigrateSource));
+ ((TestMigrateSource *)source)->src = s;
+ ((TestMigrateSource *)source)->dest = dest;
+ g_source_attach(source, NULL);
+
/* slow down migration to have time to fiddle with log */
/* TODO: qtest could learn to break on some places */
rsp = qmp("{ 'execute': 'migrate_set_speed',"
@@ -522,6 +557,9 @@ static void test_migrate(void)
read_guest_mem(dest);
+ g_source_destroy(source);
+ g_source_unref(source);
+
qtest_quit(to);
test_server_free(dest);
qtest_quit(from);
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 34/38] seccomp: add memfd_create to whitelist
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (32 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 33/38] vhost-user-test: check ownership during migration Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 35/38] piix: fix resource leak reported by Coverity Michael S. Tsirkin
` (4 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Thibaut Collet, Eduardo Otubo,
=?UTF-8?q?Marc-Andr=C3=A9=20Lureau?=
From: Eduardo Otubo <eduardo.otubo@profitbricks.com>
This is used by memfd code.
Signed-off-by: Eduardo Otubo <eduardo.otubo@profitbricks.com>
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Thibaut Collet <thibaut.collet@6wind.com>
---
qemu-seccomp.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/qemu-seccomp.c b/qemu-seccomp.c
index f9de0d3..80d034a 100644
--- a/qemu-seccomp.c
+++ b/qemu-seccomp.c
@@ -237,7 +237,8 @@ static const struct QemuSeccompSyscall seccomp_whitelist[] = {
{ SCMP_SYS(fadvise64), 240 },
{ SCMP_SYS(inotify_init1), 240 },
{ SCMP_SYS(inotify_add_watch), 240 },
- { SCMP_SYS(mbind), 240 }
+ { SCMP_SYS(mbind), 240 },
+ { SCMP_SYS(memfd_create), 240 }
};
int seccomp_start(void)
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 35/38] piix: fix resource leak reported by Coverity
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (33 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 34/38] seccomp: add memfd_create to whitelist Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 36/38] vhost: set the correct queue index in case of migration with multiqueue Michael S. Tsirkin
` (3 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel; +Cc: Peter Maydell, zhanghailiang, Stefan Hajnoczi
From: zhanghailiang <zhang.zhanghailiang@huawei.com>
config_fd should be closed before return, or there will
be a resource leak error.
Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
hw/pci-host/piix.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/hw/pci-host/piix.c b/hw/pci-host/piix.c
index 1fb71c8..7b2fbf9 100644
--- a/hw/pci-host/piix.c
+++ b/hw/pci-host/piix.c
@@ -764,6 +764,7 @@ static int host_pci_config_read(int pos, int len, uint32_t val)
/* Access real host bridge. */
int rc = snprintf(path, size, "/sys/bus/pci/devices/%04x:%02x:%02x.%d/%s",
0, 0, 0, 0, "config");
+ int ret = 0;
if (rc >= size || rc < 0) {
return -ENODEV;
@@ -775,16 +776,18 @@ static int host_pci_config_read(int pos, int len, uint32_t val)
}
if (lseek(config_fd, pos, SEEK_SET) != pos) {
- return -errno;
+ ret = -errno;
+ goto out;
}
do {
rc = read(config_fd, (uint8_t *)&val, len);
} while (rc < 0 && (errno == EINTR || errno == EAGAIN));
if (rc != len) {
- return -errno;
+ ret = -errno;
}
-
- return 0;
+out:
+ close(config_fd);
+ return ret;
}
static int igd_pt_i440fx_initfn(struct PCIDevice *pci_dev)
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 36/38] vhost: set the correct queue index in case of migration with multiqueue
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (34 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 35/38] piix: fix resource leak reported by Coverity Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 37/38] i386: keep cpu_model field in MachineState uptodate Michael S. Tsirkin
` (2 subsequent siblings)
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel; +Cc: Peter Maydell, qemu-stable, Thibaut Collet
From: Thibaut Collet <thibaut.collet@6wind.com>
When a live migration is started the log address to mark dirty pages is provided
to the vhost backend through the vhost_dev_set_log function.
This function is called for each queue pairs but the queue index is wrongly set:
always set to the first queue pair. Then vhost backend lost descriptor addresses
of the queue pairs greater than 1 and behaviour of the vhost backend is
unpredictable.
The queue index is computed by taking account of the vq_index (to retrieve the
queue pair index) and calling the vhost_get_vq_index method of the backend.
Signed-off-by: Thibaut Collet <thibaut.collet@6wind.com>
Cc: qemu-stable@nongnu.org
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
hw/virtio/vhost.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index feeaaa4..de29968 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -656,13 +656,14 @@ static int vhost_dev_set_features(struct vhost_dev *dev, bool enable_log)
static int vhost_dev_set_log(struct vhost_dev *dev, bool enable_log)
{
- int r, t, i;
+ int r, t, i, idx;
r = vhost_dev_set_features(dev, enable_log);
if (r < 0) {
goto err_features;
}
for (i = 0; i < dev->nvqs; ++i) {
- r = vhost_virtqueue_set_addr(dev, dev->vqs + i, i,
+ idx = dev->vhost_ops->vhost_get_vq_index(dev, dev->vq_index + i);
+ r = vhost_virtqueue_set_addr(dev, dev->vqs + i, idx,
enable_log);
if (r < 0) {
goto err_vq;
@@ -671,7 +672,8 @@ static int vhost_dev_set_log(struct vhost_dev *dev, bool enable_log)
return 0;
err_vq:
for (; i >= 0; --i) {
- t = vhost_virtqueue_set_addr(dev, dev->vqs + i, i,
+ idx = dev->vhost_ops->vhost_get_vq_index(dev, dev->vq_index + i);
+ t = vhost_virtqueue_set_addr(dev, dev->vqs + i, idx,
dev->log_enabled);
assert(t >= 0);
}
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 37/38] i386: keep cpu_model field in MachineState uptodate
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (35 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 36/38] vhost: set the correct queue index in case of migration with multiqueue Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 10:28 ` [Qemu-devel] [PULL 38/38] hw/isa/lpc_ich9: inject the SMI on the VCPU that is writing to APM_CNT Michael S. Tsirkin
2015-10-21 14:06 ` [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Peter Maydell
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Zhu Guihua, Eduardo Habkost, Marcel Apfelbaum,
Paolo Bonzini, =?UTF-8?q?Andreas=20F=C3=A4rber?=,
Richard Henderson
From: Zhu Guihua <zhugh.fnst@cn.fujitsu.com>
Update cpu_model in MachineState for i386, so that the field can be used
for cpu hotplug, instead of using a static variable.
This patch is rebased on the latest master.
Signed-off-by: Zhu Guihua <zhugh.fnst@cn.fujitsu.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Acked-by: Andreas Färber <afaerber@suse.de>
---
include/hw/i386/pc.h | 2 +-
hw/i386/pc.c | 17 ++++++++---------
hw/i386/pc_piix.c | 2 +-
hw/i386/pc_q35.c | 2 +-
4 files changed, 11 insertions(+), 12 deletions(-)
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 0503485..c5961d7 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -168,7 +168,7 @@ bool pc_machine_is_smm_enabled(PCMachineState *pcms);
void pc_register_ferr_irq(qemu_irq irq);
void pc_acpi_smi_interrupt(void *opaque, int irq, int level);
-void pc_cpus_init(const char *cpu_model);
+void pc_cpus_init(PCMachineState *pcms);
void pc_hot_add_cpu(const int64_t id, Error **errp);
void pc_acpi_init(const char *default_dsdt);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 682867a..208f553 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1077,11 +1077,10 @@ out:
return cpu;
}
-static const char *current_cpu_model;
-
void pc_hot_add_cpu(const int64_t id, Error **errp)
{
X86CPU *cpu;
+ MachineState *machine = MACHINE(qdev_get_machine());
int64_t apic_id = x86_cpu_apic_id_from_index(id);
Error *local_err = NULL;
@@ -1109,7 +1108,7 @@ void pc_hot_add_cpu(const int64_t id, Error **errp)
return;
}
- cpu = pc_new_cpu(current_cpu_model, apic_id, &local_err);
+ cpu = pc_new_cpu(machine->cpu_model, apic_id, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
@@ -1117,22 +1116,22 @@ void pc_hot_add_cpu(const int64_t id, Error **errp)
object_unref(OBJECT(cpu));
}
-void pc_cpus_init(const char *cpu_model)
+void pc_cpus_init(PCMachineState *pcms)
{
int i;
X86CPU *cpu = NULL;
+ MachineState *machine = MACHINE(pcms);
Error *error = NULL;
unsigned long apic_id_limit;
/* init CPUs */
- if (cpu_model == NULL) {
+ if (machine->cpu_model == NULL) {
#ifdef TARGET_X86_64
- cpu_model = "qemu64";
+ machine->cpu_model = "qemu64";
#else
- cpu_model = "qemu32";
+ machine->cpu_model = "qemu32";
#endif
}
- current_cpu_model = cpu_model;
apic_id_limit = pc_apic_id_limit(max_cpus);
if (apic_id_limit > ACPI_CPU_HOTPLUG_ID_LIMIT) {
@@ -1142,7 +1141,7 @@ void pc_cpus_init(const char *cpu_model)
}
for (i = 0; i < smp_cpus; i++) {
- cpu = pc_new_cpu(cpu_model, x86_cpu_apic_id_from_index(i),
+ cpu = pc_new_cpu(machine->cpu_model, x86_cpu_apic_id_from_index(i),
&error);
if (error) {
error_report_err(error);
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index ae7bbeb..0eacde1 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -139,7 +139,7 @@ static void pc_init1(MachineState *machine,
exit(1);
}
- pc_cpus_init(machine->cpu_model);
+ pc_cpus_init(pcms);
if (kvm_enabled() && kvmclock_enabled) {
kvmclock_create();
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 19e6670..3744abd 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -128,7 +128,7 @@ static void pc_q35_init(MachineState *machine)
exit(1);
}
- pc_cpus_init(machine->cpu_model);
+ pc_cpus_init(pcms);
pc_acpi_init("q35-acpi-dsdt.aml");
kvmclock_create();
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* [Qemu-devel] [PULL 38/38] hw/isa/lpc_ich9: inject the SMI on the VCPU that is writing to APM_CNT
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (36 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 37/38] i386: keep cpu_model field in MachineState uptodate Michael S. Tsirkin
@ 2015-10-21 10:28 ` Michael S. Tsirkin
2015-10-21 14:06 ` [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Peter Maydell
38 siblings, 0 replies; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-21 10:28 UTC (permalink / raw)
To: qemu-devel
Cc: Peter Maydell, Jordan Justen, Gerd Hoffmann, Michael Kinney,
Paolo Bonzini, Laszlo Ersek
From: Laszlo Ersek <lersek@redhat.com>
Commit 4d00636e97b7 ("ich9: Add the lpc chip", Nov 14 2012) added the
ich9_apm_ctrl_changed() ioport write callback function such that it would
inject the SMI, in response to a write to the APM_CNT register, on the
first CPU, invariably.
Since this register is used by guest code to trigger an SMI synchronously,
the interrupt should be injected on the VCPU that is performing the write.
apm_ioport_writeb() is the .write callback of the "apm_ops"
MemoryRegionOps [hw/isa/apm.c]; it is parametrized to call
ich9_apm_ctrl_changed() by ich9_lpc_init() [hw/isa/lpc_ich9.c], via
apm_init(). Therefore this change affects no other board.
ich9_generate_smi() is an unrelated function that is called by the TCO
watchdog; a watchdog is likely in its right to (asynchronously) inject
interrupts on the first CPU only.
This patch allows the combined edk2/OVMF SMM driver stack to work with
multiple VCPUs on TCG, using both qemu-system-i386 and qemu-system-x86_64.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Jordan Justen <jordan.l.justen@intel.com>
Cc: Michael Kinney <michael.d.kinney@intel.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
hw/isa/lpc_ich9.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/isa/lpc_ich9.c b/hw/isa/lpc_ich9.c
index 360699f..1ffc803 100644
--- a/hw/isa/lpc_ich9.c
+++ b/hw/isa/lpc_ich9.c
@@ -394,7 +394,7 @@ static void ich9_apm_ctrl_changed(uint32_t val, void *arg)
/* SMI_EN = PMBASE + 30. SMI control and enable register */
if (lpc->pm.smi_en & ICH9_PMIO_SMI_EN_APMC_EN) {
- cpu_interrupt(first_cpu, CPU_INTERRUPT_SMI);
+ cpu_interrupt(current_cpu, CPU_INTERRUPT_SMI);
}
}
--
MST
^ permalink raw reply related [flat|nested] 45+ messages in thread* Re: [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups
2015-10-21 10:26 [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Michael S. Tsirkin
` (37 preceding siblings ...)
2015-10-21 10:28 ` [Qemu-devel] [PULL 38/38] hw/isa/lpc_ich9: inject the SMI on the VCPU that is writing to APM_CNT Michael S. Tsirkin
@ 2015-10-21 14:06 ` Peter Maydell
2015-10-22 11:40 ` Michael S. Tsirkin
38 siblings, 1 reply; 45+ messages in thread
From: Peter Maydell @ 2015-10-21 14:06 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: QEMU Developers
On 21 October 2015 at 11:26, Michael S. Tsirkin <mst@redhat.com> wrote:
> The following changes since commit 6d57410a79d51d92673c54f26624b44f27fa6214:
>
> Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20151016' into staging (2015-10-17 12:31:33 +0100)
>
> are available in the git repository at:
>
> git://git.kernel.org/pub/scm/virt/kvm/mst/qemu.git tags/for_upstream
>
> for you to fetch changes up to 4f53cd7788185f437a4275df6456eb60b90d4837:
>
> hw/isa/lpc_ich9: inject the SMI on the VCPU that is writing to APM_CNT (2015-10-21 13:24:49 +0300)
>
> ----------------------------------------------------------------
> vhost, pc, virtio features, fixes, cleanups
>
> New features:
> VT-d support for devices behind a bridge
> vhost-user migration support
>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
>
> ----------------------------------------------------------------
Test failure on 64-bit ARM and 32-bit ARM:
TEST: tests/vhost-user-test... (pid=28701)
Warning: path not on HugeTLBFS: /tmp/vhost-test-pLQQzA
qemu-system-i386: -netdev
vhost-user,id=net0,chardev=chr-test,vhostforce: vhost-net support is
not compiled in
qemu-system-i386: -netdev
vhost-user,id=net0,chardev=chr-test,vhostforce: failed to init
vhost_net for queue 0
Broken pipe
FAIL: tests/vhost-user-test
My clang build gives this:
Warning: path not on HugeTLBFS: /tmp/vhost-test-EFF6ul
/home/petmay01/linaro/qemu-for-merges/target-i386/translate.c:2421:26:
runtime error: left shift of negative value -8
Warning: path not on HugeTLBFS: /tmp/vhost-test-EFF6ul
/home/petmay01/linaro/qemu-for-merges/target-i386/translate.c:2421:26:
runtime error: left shift of negative value -8
Warning: path not on HugeTLBFS: /tmp/vhost-test-EFF6ul
/home/petmay01/linaro/qemu-for-merges/target-i386/translate.c:2421:26:
runtime error: left shift of negative value -8
The tests pass, but I'd prefer it if our tests
didn't print out random warnings in the non-verbose
case if possible; it makes it hard to sift out
"this is a problem" from "this test has always
been grumpy". (Alternatively, if "path not on HugeTLBFS"
is a problem then the test should fail.)
The negative-shift stuff is clang's undefined
sanitizer; the code in question has been doing a
"-8 << s->dflag" since at least 2013, so this is just
your test code exercising something it hadn't before.
Sanitizer issues aren't currently something I'm
requiring pull requests to deal with, so we can fix
this one later.
thanks
-- PMM
^ permalink raw reply [flat|nested] 45+ messages in thread* Re: [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups
2015-10-21 14:06 ` [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups Peter Maydell
@ 2015-10-22 11:40 ` Michael S. Tsirkin
2015-10-22 12:33 ` Peter Maydell
0 siblings, 1 reply; 45+ messages in thread
From: Michael S. Tsirkin @ 2015-10-22 11:40 UTC (permalink / raw)
To: Peter Maydell; +Cc: QEMU Developers
On Wed, Oct 21, 2015 at 03:06:57PM +0100, Peter Maydell wrote:
> On 21 October 2015 at 11:26, Michael S. Tsirkin <mst@redhat.com> wrote:
> > The following changes since commit 6d57410a79d51d92673c54f26624b44f27fa6214:
> >
> > Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20151016' into staging (2015-10-17 12:31:33 +0100)
> >
> > are available in the git repository at:
> >
> > git://git.kernel.org/pub/scm/virt/kvm/mst/qemu.git tags/for_upstream
> >
> > for you to fetch changes up to 4f53cd7788185f437a4275df6456eb60b90d4837:
> >
> > hw/isa/lpc_ich9: inject the SMI on the VCPU that is writing to APM_CNT (2015-10-21 13:24:49 +0300)
> >
> > ----------------------------------------------------------------
> > vhost, pc, virtio features, fixes, cleanups
> >
> > New features:
> > VT-d support for devices behind a bridge
> > vhost-user migration support
> >
> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> >
> > ----------------------------------------------------------------
>
> Test failure on 64-bit ARM and 32-bit ARM:
>
> TEST: tests/vhost-user-test... (pid=28701)
> Warning: path not on HugeTLBFS: /tmp/vhost-test-pLQQzA
> qemu-system-i386: -netdev
> vhost-user,id=net0,chardev=chr-test,vhostforce: vhost-net support is
> not compiled in
> qemu-system-i386: -netdev
> vhost-user,id=net0,chardev=chr-test,vhostforce: failed to init
> vhost_net for queue 0
>
> Broken pipe
> FAIL: tests/vhost-user-test
Sorry about that.
I rebased and dropped the offending patch.
tag moved to 3c23402d4032f69af44a87fdb8019ad3229a4f31
Not resending full pull request since that is the only change.
> My clang build gives this:
>
> Warning: path not on HugeTLBFS: /tmp/vhost-test-EFF6ul
> /home/petmay01/linaro/qemu-for-merges/target-i386/translate.c:2421:26:
> runtime error: left shift of negative value -8
> Warning: path not on HugeTLBFS: /tmp/vhost-test-EFF6ul
> /home/petmay01/linaro/qemu-for-merges/target-i386/translate.c:2421:26:
> runtime error: left shift of negative value -8
> Warning: path not on HugeTLBFS: /tmp/vhost-test-EFF6ul
> /home/petmay01/linaro/qemu-for-merges/target-i386/translate.c:2421:26:
> runtime error: left shift of negative value -8
>
> The tests pass, but I'd prefer it if our tests
> didn't print out random warnings in the non-verbose
> case if possible; it makes it hard to sift out
> "this is a problem" from "this test has always
> been grumpy". (Alternatively, if "path not on HugeTLBFS"
> is a problem then the test should fail.)
>
> The negative-shift stuff is clang's undefined
> sanitizer; the code in question has been doing a
> "-8 << s->dflag" since at least 2013, so this is just
> your test code exercising something it hadn't before.
> Sanitizer issues aren't currently something I'm
> requiring pull requests to deal with, so we can fix
> this one later.
>
> thanks
> -- PMM
^ permalink raw reply [flat|nested] 45+ messages in thread
* Re: [Qemu-devel] [PULL 00/38] vhost, pc, virtio features, fixes, cleanups
2015-10-22 11:40 ` Michael S. Tsirkin
@ 2015-10-22 12:33 ` Peter Maydell
0 siblings, 0 replies; 45+ messages in thread
From: Peter Maydell @ 2015-10-22 12:33 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: QEMU Developers
On 22 October 2015 at 12:40, Michael S. Tsirkin <mst@redhat.com> wrote:
> On Wed, Oct 21, 2015 at 03:06:57PM +0100, Peter Maydell wrote:
>> On 21 October 2015 at 11:26, Michael S. Tsirkin <mst@redhat.com> wrote:
>> > The following changes since commit 6d57410a79d51d92673c54f26624b44f27fa6214:
>> >
>> > Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20151016' into staging (2015-10-17 12:31:33 +0100)
>> >
>> > are available in the git repository at:
>> >
>> > git://git.kernel.org/pub/scm/virt/kvm/mst/qemu.git tags/for_upstream
>> >
>> > for you to fetch changes up to 4f53cd7788185f437a4275df6456eb60b90d4837:
>> >
>> > hw/isa/lpc_ich9: inject the SMI on the VCPU that is writing to APM_CNT (2015-10-21 13:24:49 +0300)
>> >
>> > ----------------------------------------------------------------
>> > vhost, pc, virtio features, fixes, cleanups
>> >
>> > New features:
>> > VT-d support for devices behind a bridge
>> > vhost-user migration support
>> >
>> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
>> >
>> > ----------------------------------------------------------------
>>
>> Test failure on 64-bit ARM and 32-bit ARM:
>>
>> TEST: tests/vhost-user-test... (pid=28701)
>> Warning: path not on HugeTLBFS: /tmp/vhost-test-pLQQzA
>> qemu-system-i386: -netdev
>> vhost-user,id=net0,chardev=chr-test,vhostforce: vhost-net support is
>> not compiled in
>> qemu-system-i386: -netdev
>> vhost-user,id=net0,chardev=chr-test,vhostforce: failed to init
>> vhost_net for queue 0
>>
>> Broken pipe
>> FAIL: tests/vhost-user-test
>
> Sorry about that.
>
> I rebased and dropped the offending patch.
>
> tag moved to 3c23402d4032f69af44a87fdb8019ad3229a4f31
>
> Not resending full pull request since that is the only change.
Applied, thanks.
-- PMM
^ permalink raw reply [flat|nested] 45+ messages in thread