xen: features and fixes for v4.15-rc1

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQEcBAABAgAGBQJaDdh4AAoJELDendYovxMvPFAH/2QjTys2ydIAdmwke4odpJ7U
 xuy7HOQCzOeZ5YsZthzCBsN90VmnDM7X7CcB8weSdjcKlXMSAWD+J1RgkL2iAJhI
 8tzIEXECrlNuz4V5mX9TmMgtPCr4qzU3fsts0pZy4fYDq1PVWDefqOwEtbpbWabb
 wRSMq/nTb9iASTMgheSC0WfhJneqtJ+J20zrzkGPCBPRFcwfppeP8/7vpkmJslBi
 eH/pfchICM4w093T/BfavnsPvhLdjgRuwVzn6+e46s4tLnZAxnLRVQ7SXZXzBORq
 /dL/qC0XH3YXdU+XfIs//giZsmLns6SxZaMr4vs6TxFtuzZBKpLtkOKo9zndvxk=
 =sZY5
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-4.15-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:
 "Xen features and fixes for v4.15-rc1

  Apart from several small fixes it contains the following features:

   - a series by Joao Martins to add vdso support of the pv clock
     interface

   - a series by Juergen Gross to add support for Xen pv guests to be
     able to run on 5 level paging hosts

   - a series by Stefano Stabellini adding the Xen pvcalls frontend
     driver using a paravirtualized socket interface"

* tag 'for-linus-4.15-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (34 commits)
  xen/pvcalls: fix potential endless loop in pvcalls-front.c
  xen/pvcalls: Add MODULE_LICENSE()
  MAINTAINERS: xen, kvm: track pvclock-abi.h changes
  x86/xen/time: setup vcpu 0 time info page
  x86/xen/time: set pvclock flags on xen_time_init()
  x86/pvclock: add setter for pvclock_pvti_cpu0_va
  ptp_kvm: probe for kvm guest availability
  xen/privcmd: remove unused variable pageidx
  xen: select grant interface version
  xen: update arch/x86/include/asm/xen/cpuid.h
  xen: add grant interface version dependent constants to gnttab_ops
  xen: limit grant v2 interface to the v1 functionality
  xen: re-introduce support for grant v2 interface
  xen: support priv-mapping in an HVM tools domain
  xen/pvcalls: remove redundant check for irq >= 0
  xen/pvcalls: fix unsigned less than zero error check
  xen/time: Return -ENODEV from xen_get_wallclock()
  xen/pvcalls-front: mark expected switch fall-through
  xen: xenbus_probe_frontend: mark expected switch fall-throughs
  xen/time: do not decrease steal time after live migration on xen
  ...
This commit is contained in:
Linus Torvalds 2017-11-16 13:06:27 -08:00
commit 051089a2ee
28 changed files with 1942 additions and 76 deletions

View File

@ -7650,6 +7650,7 @@ S: Supported
F: arch/x86/kvm/
F: arch/x86/include/uapi/asm/kvm*
F: arch/x86/include/asm/kvm*
F: arch/x86/include/asm/pvclock-abi.h
F: arch/x86/kernel/kvm.c
F: arch/x86/kernel/kvmclock.c
@ -14838,6 +14839,7 @@ F: arch/x86/xen/
F: drivers/*/xen-*front.c
F: drivers/xen/
F: arch/x86/include/asm/xen/
F: arch/x86/include/asm/pvclock-abi.h
F: include/xen/
F: include/uapi/xen/
F: Documentation/ABI/stable/sysfs-hypervisor-xen

View File

@ -45,7 +45,14 @@ void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
return;
}
int arch_gnttab_init(unsigned long nr_shared)
int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
unsigned long max_nr_gframes,
grant_status_t **__shared)
{
return -ENOSYS;
}
int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
{
return 0;
}

View File

@ -112,7 +112,7 @@ static int vvar_fault(const struct vm_special_mapping *sm,
__pa_symbol(&__vvar_page) >> PAGE_SHIFT);
} else if (sym_offset == image->sym_pvclock_page) {
struct pvclock_vsyscall_time_info *pvti =
pvclock_pvti_cpu0_va();
pvclock_get_pvti_cpu0_va();
if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
ret = vm_insert_pfn_prot(
vma,

View File

@ -5,15 +5,6 @@
#include <linux/clocksource.h>
#include <asm/pvclock-abi.h>
#ifdef CONFIG_KVM_GUEST
extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
#else
static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
{
return NULL;
}
#endif
/* some helper functions for xen and kvm pv clock sources */
u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
@ -102,4 +93,14 @@ struct pvclock_vsyscall_time_info {
#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
#ifdef CONFIG_PARAVIRT_CLOCK
void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti);
struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void);
#else
static inline struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void)
{
return NULL;
}
#endif
#endif /* _ASM_X86_PVCLOCK_H */

View File

@ -74,21 +74,43 @@
#define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD (1u<<0)
/*
* Leaf 5 (0x40000x04)
* HVM-specific features
* EAX: Features
* EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
* Leaf 4 (0x40000x03)
* Sub-leaf 0: EAX: bit 0: emulated tsc
* bit 1: host tsc is known to be reliable
* bit 2: RDTSCP instruction available
* EBX: tsc_mode: 0=default (emulate if necessary), 1=emulate,
* 2=no emulation, 3=no emulation + TSC_AUX support
* ECX: guest tsc frequency in kHz
* EDX: guest tsc incarnation (migration count)
* Sub-leaf 1: EAX: tsc offset low part
* EBX: tsc offset high part
* ECX: multiplicator for tsc->ns conversion
* EDX: shift amount for tsc->ns conversion
* Sub-leaf 2: EAX: host tsc frequency in kHz
*/
/* Virtualized APIC registers */
#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0)
/* Virtualized x2APIC accesses */
#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1)
/*
* Leaf 5 (0x40000x04)
* HVM-specific features
* Sub-leaf 0: EAX: Features
* Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
*/
#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */
#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1) /* Virtualized x2APIC accesses */
/* Memory mapped from other domains has valid IOMMU entries */
#define XEN_HVM_CPUID_IOMMU_MAPPINGS (1u << 2)
/* vcpu id is present in EBX */
#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3)
#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) /* vcpu id is present in EBX */
#define XEN_CPUID_MAX_NUM_LEAVES 4
/*
* Leaf 6 (0x40000x05)
* PV-specific parameters
* Sub-leaf 0: EAX: max available sub-leaf
* Sub-leaf 0: EBX: bits 0-7: max machine address width
*/
/* Max. address width in bits taking memory hotplug into account. */
#define XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK (0xffu << 0)
#define XEN_CPUID_MAX_NUM_LEAVES 5
#endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */

View File

@ -27,6 +27,15 @@ typedef struct xpaddr {
phys_addr_t paddr;
} xpaddr_t;
#ifdef CONFIG_X86_64
#define XEN_PHYSICAL_MASK __sme_clr((1UL << 52) - 1)
#else
#define XEN_PHYSICAL_MASK __PHYSICAL_MASK
#endif
#define XEN_PTE_MFN_MASK ((pteval_t)(((signed long)PAGE_MASK) & \
XEN_PHYSICAL_MASK))
#define XMADDR(x) ((xmaddr_t) { .maddr = (x) })
#define XPADDR(x) ((xpaddr_t) { .paddr = (x) })
@ -278,7 +287,7 @@ static inline unsigned long bfn_to_local_pfn(unsigned long mfn)
static inline unsigned long pte_mfn(pte_t pte)
{
return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
return (pte.pte & XEN_PTE_MFN_MASK) >> PAGE_SHIFT;
}
static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)

View File

@ -48,12 +48,6 @@ early_param("no-kvmclock", parse_no_kvmclock);
static struct pvclock_vsyscall_time_info *hv_clock;
static struct pvclock_wall_clock *wall_clock;
struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
{
return hv_clock;
}
EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va);
/*
* The wallclock is the time of day when we booted. Since then, some time may
* have elapsed since the hypervisor wrote the data. So we try to account for
@ -377,6 +371,7 @@ int __init kvm_setup_vsyscall_timeinfo(void)
return 1;
}
pvclock_set_pvti_cpu0_va(hv_clock);
put_cpu();
kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;

View File

@ -25,8 +25,10 @@
#include <asm/fixmap.h>
#include <asm/pvclock.h>
#include <asm/vgtod.h>
static u8 valid_flags __read_mostly = 0;
static struct pvclock_vsyscall_time_info *pvti_cpu0_va __read_mostly;
void pvclock_set_flags(u8 flags)
{
@ -144,3 +146,15 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
}
void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti)
{
WARN_ON(vclock_was_used(VCLOCK_PVCLOCK));
pvti_cpu0_va = pvti;
}
struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void)
{
return pvti_cpu0_va;
}
EXPORT_SYMBOL_GPL(pvclock_get_pvti_cpu0_va);

View File

@ -49,7 +49,7 @@
static struct gnttab_vm_area {
struct vm_struct *area;
pte_t **ptes;
} gnttab_shared_vm_area;
} gnttab_shared_vm_area, gnttab_status_vm_area;
int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
unsigned long max_nr_gframes,
@ -73,16 +73,43 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
return 0;
}
void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
unsigned long max_nr_gframes,
grant_status_t **__shared)
{
grant_status_t *shared = *__shared;
unsigned long addr;
unsigned long i;
if (shared == NULL)
*__shared = shared = gnttab_status_vm_area.area->addr;
addr = (unsigned long)shared;
for (i = 0; i < nr_gframes; i++) {
set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i],
__pte(0));
set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i],
mfn_pte(frames[i], PAGE_KERNEL));
addr += PAGE_SIZE;
}
return 0;
}
void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
{
pte_t **ptes;
unsigned long addr;
unsigned long i;
if (shared == gnttab_status_vm_area.area->addr)
ptes = gnttab_status_vm_area.ptes;
else
ptes = gnttab_shared_vm_area.ptes;
addr = (unsigned long)shared;
for (i = 0; i < nr_gframes; i++) {
set_pte_at(&init_mm, addr, ptes[i], __pte(0));
addr += PAGE_SIZE;
}
}
@ -102,12 +129,35 @@ static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
return 0;
}
int arch_gnttab_init(unsigned long nr_shared)
static void arch_gnttab_vfree(struct gnttab_vm_area *area)
{
free_vm_area(area->area);
kfree(area->ptes);
}
int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
{
int ret;
if (!xen_pv_domain())
return 0;
return arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared);
ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared);
if (ret < 0)
return ret;
/*
* Always allocate the space for the status frames in case
* we're migrated to a host with V2 support.
*/
ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status);
if (ret < 0)
goto err;
return 0;
err:
arch_gnttab_vfree(&gnttab_shared_vm_area);
return -ENOMEM;
}
#ifdef CONFIG_XEN_PVH

View File

@ -172,6 +172,9 @@ int xen_remap_domain_gfn_range(struct vm_area_struct *vma,
pgprot_t prot, unsigned domid,
struct page **pages)
{
if (xen_feature(XENFEAT_auto_translated_physmap))
return -EOPNOTSUPP;
return do_remap_gfn(vma, addr, &gfn, nr, NULL, prot, domid, pages);
}
EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_range);
@ -182,6 +185,10 @@ int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
int *err_ptr, pgprot_t prot,
unsigned domid, struct page **pages)
{
if (xen_feature(XENFEAT_auto_translated_physmap))
return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr,
prot, domid, pages);
/* We BUG_ON because it's a programmer error to pass a NULL err_ptr,
* and the consequences later is quite hard to detect what the actual
* cause of "wrong memory was mapped in".
@ -193,9 +200,12 @@ EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_array);
/* Returns: 0 success */
int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
int numpgs, struct page **pages)
int nr, struct page **pages)
{
if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
if (xen_feature(XENFEAT_auto_translated_physmap))
return xen_xlate_unmap_gfn_range(vma, nr, pages);
if (!pages)
return 0;
return -EINVAL;

View File

@ -315,7 +315,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
static pteval_t pte_mfn_to_pfn(pteval_t val)
{
if (val & _PAGE_PRESENT) {
unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
unsigned long mfn = (val & XEN_PTE_MFN_MASK) >> PAGE_SHIFT;
unsigned long pfn = mfn_to_pfn(mfn);
pteval_t flags = val & PTE_FLAGS_MASK;
@ -1721,7 +1721,7 @@ static unsigned long __init m2p(phys_addr_t maddr)
{
phys_addr_t paddr;
maddr &= PTE_PFN_MASK;
maddr &= XEN_PTE_MFN_MASK;
paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
return paddr;

View File

@ -17,6 +17,8 @@
void xen_arch_pre_suspend(void)
{
xen_save_time_memory_area();
if (xen_pv_domain())
xen_pv_pre_suspend();
}
@ -27,6 +29,8 @@ void xen_arch_post_suspend(int cancelled)
xen_pv_post_suspend(cancelled);
else
xen_hvm_post_suspend(cancelled);
xen_restore_time_memory_area();
}
static void xen_vcpu_notify_restore(void *data)

View File

@ -75,7 +75,7 @@ static void xen_get_wallclock(struct timespec *now)
static int xen_set_wallclock(const struct timespec *now)
{
return -1;
return -ENODEV;
}
static int xen_pvclock_gtod_notify(struct notifier_block *nb,
@ -371,8 +371,95 @@ static const struct pv_time_ops xen_time_ops __initconst = {
.steal_clock = xen_steal_clock,
};
static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
void xen_save_time_memory_area(void)
{
struct vcpu_register_time_memory_area t;
int ret;
if (!xen_clock)
return;
t.addr.v = NULL;
ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t);
if (ret != 0)
pr_notice("Cannot save secondary vcpu_time_info (err %d)",
ret);
else
clear_page(xen_clock);
}
void xen_restore_time_memory_area(void)
{
struct vcpu_register_time_memory_area t;
int ret;
if (!xen_clock)
return;
t.addr.v = &xen_clock->pvti;
ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t);
/*
* We don't disable VCLOCK_PVCLOCK entirely if it fails to register the
* secondary time info with Xen or if we migrated to a host without the
* necessary flags. On both of these cases what happens is either
* process seeing a zeroed out pvti or seeing no PVCLOCK_TSC_STABLE_BIT
* bit set. Userspace checks the latter and if 0, it discards the data
* in pvti and fallbacks to a system call for a reliable timestamp.
*/
if (ret != 0)
pr_notice("Cannot restore secondary vcpu_time_info (err %d)",
ret);
}
static void xen_setup_vsyscall_time_info(void)
{
struct vcpu_register_time_memory_area t;
struct pvclock_vsyscall_time_info *ti;
int ret;
ti = (struct pvclock_vsyscall_time_info *)get_zeroed_page(GFP_KERNEL);
if (!ti)
return;
t.addr.v = &ti->pvti;
ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t);
if (ret) {
pr_notice("xen: VCLOCK_PVCLOCK not supported (err %d)\n", ret);
free_page((unsigned long)ti);
return;
}
/*
* If primary time info had this bit set, secondary should too since
* it's the same data on both just different memory regions. But we
* still check it in case hypervisor is buggy.
*/
if (!(ti->pvti.flags & PVCLOCK_TSC_STABLE_BIT)) {
t.addr.v = NULL;
ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area,
0, &t);
if (!ret)
free_page((unsigned long)ti);
pr_notice("xen: VCLOCK_PVCLOCK not supported (tsc unstable)\n");
return;
}
xen_clock = ti;
pvclock_set_pvti_cpu0_va(xen_clock);
xen_clocksource.archdata.vclock_mode = VCLOCK_PVCLOCK;
}
static void __init xen_time_init(void)
{
struct pvclock_vcpu_time_info *pvti;
int cpu = smp_processor_id();
struct timespec tp;
@ -396,6 +483,16 @@ static void __init xen_time_init(void)
setup_force_cpu_cap(X86_FEATURE_TSC);
/*
* We check ahead on the primary time info if this
* bit is supported hence speeding up Xen clocksource.
*/
pvti = &__this_cpu_read(xen_vcpu)->time;
if (pvti->flags & PVCLOCK_TSC_STABLE_BIT) {
pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
xen_setup_vsyscall_time_info();
}
xen_setup_runstate_info(cpu);
xen_setup_timer(cpu);
xen_setup_cpu_clockevents();

View File

@ -70,6 +70,8 @@ void xen_setup_runstate_info(int cpu);
void xen_teardown_timer(int cpu);
u64 xen_clocksource_read(void);
void xen_setup_cpu_clockevents(void);
void xen_save_time_memory_area(void);
void xen_restore_time_memory_area(void);
void __init xen_init_time_ops(void);
void __init xen_hvm_init_time_ops(void);

View File

@ -178,8 +178,11 @@ static int __init ptp_kvm_init(void)
{
long ret;
if (!kvm_para_available())
return -ENODEV;
clock_pair_gpa = slow_virt_to_phys(&clock_pair);
hv_clock = pvclock_pvti_cpu0_va();
hv_clock = pvclock_get_pvti_cpu0_va();
if (!hv_clock)
return -ENODEV;

View File

@ -196,6 +196,17 @@ config XEN_PCIDEV_BACKEND
If in doubt, say m.
config XEN_PVCALLS_FRONTEND
tristate "XEN PV Calls frontend driver"
depends on INET && XEN
default n
select XEN_XENBUS_FRONTEND
help
Experimental frontend for the Xen PV Calls protocol
(https://xenbits.xen.org/docs/unstable/misc/pvcalls.html). It
sends a small set of POSIX calls to the backend, which
implements them.
config XEN_PVCALLS_BACKEND
bool "XEN PV Calls backend driver"
depends on INET && XEN && XEN_BACKEND

View File

@ -37,6 +37,7 @@ obj-$(CONFIG_XEN_EFI) += efi.o
obj-$(CONFIG_XEN_SCSI_BACKEND) += xen-scsiback.o
obj-$(CONFIG_XEN_AUTO_XLATE) += xlate_mmu.o
obj-$(CONFIG_XEN_PVCALLS_BACKEND) += pvcalls-back.o
obj-$(CONFIG_XEN_PVCALLS_FRONTEND) += pvcalls-front.o
xen-evtchn-y := evtchn.o
xen-gntdev-y := gntdev.o
xen-gntalloc-y := gntalloc.o

View File

@ -33,6 +33,7 @@
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
#include <linux/bootmem.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/slab.h>
@ -43,6 +44,7 @@
#include <linux/hardirq.h>
#include <linux/workqueue.h>
#include <linux/ratelimit.h>
#include <linux/moduleparam.h>
#include <xen/xen.h>
#include <xen/interface/xen.h>
@ -52,6 +54,9 @@
#include <xen/hvc-console.h>
#include <xen/swiotlb-xen.h>
#include <xen/balloon.h>
#ifdef CONFIG_X86
#include <asm/xen/cpuid.h>
#endif
#include <asm/xen/hypercall.h>
#include <asm/xen/interface.h>
@ -68,14 +73,25 @@ static int gnttab_free_count;
static grant_ref_t gnttab_free_head;
static DEFINE_SPINLOCK(gnttab_list_lock);
struct grant_frames xen_auto_xlat_grant_frames;
static unsigned int xen_gnttab_version;
module_param_named(version, xen_gnttab_version, uint, 0);
static union {
struct grant_entry_v1 *v1;
union grant_entry_v2 *v2;
void *addr;
} gnttab_shared;
/*This is a structure of function pointers for grant table*/
struct gnttab_ops {
/*
* Version of the grant interface.
*/
unsigned int version;
/*
* Grant refs per grant frame.
*/
unsigned int grefs_per_grant_frame;
/*
* Mapping a list of frames for storing grant entries. Frames parameter
* is used to store grant table address when grant table being setup,
@ -130,14 +146,15 @@ struct unmap_refs_callback_data {
static const struct gnttab_ops *gnttab_interface;
static int grant_table_version;
static int grefs_per_grant_frame;
/* This reflects status of grant entries, so act as a global value. */
static grant_status_t *grstatus;
static struct gnttab_free_callback *gnttab_free_callback_list;
static int gnttab_expand(unsigned int req_entries);
#define RPP (PAGE_SIZE / sizeof(grant_ref_t))
#define SPP (PAGE_SIZE / sizeof(grant_status_t))
static inline grant_ref_t *__gnttab_entry(grant_ref_t entry)
{
@ -210,7 +227,7 @@ static void put_free_entry(grant_ref_t ref)
}
/*
* Following applies to gnttab_update_entry_v1.
* Following applies to gnttab_update_entry_v1 and gnttab_update_entry_v2.
* Introducing a valid entry into the grant table:
* 1. Write ent->domid.
* 2. Write ent->frame:
@ -229,6 +246,15 @@ static void gnttab_update_entry_v1(grant_ref_t ref, domid_t domid,
gnttab_shared.v1[ref].flags = flags;
}
static void gnttab_update_entry_v2(grant_ref_t ref, domid_t domid,
unsigned long frame, unsigned int flags)
{
gnttab_shared.v2[ref].hdr.domid = domid;
gnttab_shared.v2[ref].full_page.frame = frame;
wmb(); /* Hypervisor concurrent accesses. */
gnttab_shared.v2[ref].hdr.flags = GTF_permit_access | flags;
}
/*
* Public grant-issuing interface functions
*/
@ -260,6 +286,11 @@ static int gnttab_query_foreign_access_v1(grant_ref_t ref)
return gnttab_shared.v1[ref].flags & (GTF_reading|GTF_writing);
}
static int gnttab_query_foreign_access_v2(grant_ref_t ref)
{
return grstatus[ref] & (GTF_reading|GTF_writing);
}
int gnttab_query_foreign_access(grant_ref_t ref)
{
return gnttab_interface->query_foreign_access(ref);
@ -282,6 +313,29 @@ static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly)
return 1;
}
static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref, int readonly)
{
gnttab_shared.v2[ref].hdr.flags = 0;
mb(); /* Concurrent access by hypervisor. */
if (grstatus[ref] & (GTF_reading|GTF_writing)) {
return 0;
} else {
/*
* The read of grstatus needs to have acquire semantics.
* On x86, reads already have that, and we just need to
* protect against compiler reorderings.
* On other architectures we may need a full barrier.
*/
#ifdef CONFIG_X86
barrier();
#else
mb();
#endif
}
return 1;
}
static inline int _gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
{
return gnttab_interface->end_foreign_access_ref(ref, readonly);
@ -442,6 +496,37 @@ static unsigned long gnttab_end_foreign_transfer_ref_v1(grant_ref_t ref)
return frame;
}
static unsigned long gnttab_end_foreign_transfer_ref_v2(grant_ref_t ref)
{
unsigned long frame;
u16 flags;
u16 *pflags;
pflags = &gnttab_shared.v2[ref].hdr.flags;
/*
* If a transfer is not even yet started, try to reclaim the grant
* reference and return failure (== 0).
*/
while (!((flags = *pflags) & GTF_transfer_committed)) {
if (sync_cmpxchg(pflags, flags, 0) == flags)
return 0;
cpu_relax();
}
/* If a transfer is in progress then wait until it is completed. */
while (!(flags & GTF_transfer_completed)) {
flags = *pflags;
cpu_relax();
}
rmb(); /* Read the frame number /after/ reading completion status. */
frame = gnttab_shared.v2[ref].full_page.frame;
BUG_ON(frame == 0);
return frame;
}
unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref)
{
return gnttab_interface->end_foreign_transfer_ref(ref);
@ -563,19 +648,26 @@ void gnttab_cancel_free_callback(struct gnttab_free_callback *callback)
}
EXPORT_SYMBOL_GPL(gnttab_cancel_free_callback);
static unsigned int gnttab_frames(unsigned int frames, unsigned int align)
{
return (frames * gnttab_interface->grefs_per_grant_frame + align - 1) /
align;
}
static int grow_gnttab_list(unsigned int more_frames)
{
unsigned int new_nr_grant_frames, extra_entries, i;
unsigned int nr_glist_frames, new_nr_glist_frames;
unsigned int grefs_per_frame;
BUG_ON(grefs_per_grant_frame == 0);
BUG_ON(gnttab_interface == NULL);
grefs_per_frame = gnttab_interface->grefs_per_grant_frame;
new_nr_grant_frames = nr_grant_frames + more_frames;
extra_entries = more_frames * grefs_per_grant_frame;
extra_entries = more_frames * grefs_per_frame;
nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
new_nr_glist_frames =
(new_nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
nr_glist_frames = gnttab_frames(nr_grant_frames, RPP);
new_nr_glist_frames = gnttab_frames(new_nr_grant_frames, RPP);
for (i = nr_glist_frames; i < new_nr_glist_frames; i++) {
gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_ATOMIC);
if (!gnttab_list[i])
@ -583,12 +675,12 @@ static int grow_gnttab_list(unsigned int more_frames)
}
for (i = grefs_per_grant_frame * nr_grant_frames;
i < grefs_per_grant_frame * new_nr_grant_frames - 1; i++)
for (i = grefs_per_frame * nr_grant_frames;
i < grefs_per_frame * new_nr_grant_frames - 1; i++)
gnttab_entry(i) = i + 1;
gnttab_entry(i) = gnttab_free_head;
gnttab_free_head = grefs_per_grant_frame * nr_grant_frames;
gnttab_free_head = grefs_per_frame * nr_grant_frames;
gnttab_free_count += extra_entries;
nr_grant_frames = new_nr_grant_frames;
@ -938,6 +1030,12 @@ int gnttab_unmap_refs_sync(struct gntab_unmap_queue_data *item)
}
EXPORT_SYMBOL_GPL(gnttab_unmap_refs_sync);
static unsigned int nr_status_frames(unsigned int nr_grant_frames)
{
BUG_ON(gnttab_interface == NULL);
return gnttab_frames(nr_grant_frames, SPP);
}
static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes)
{
int rc;
@ -955,6 +1053,55 @@ static void gnttab_unmap_frames_v1(void)
arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames);
}
static int gnttab_map_frames_v2(xen_pfn_t *frames, unsigned int nr_gframes)
{
uint64_t *sframes;
unsigned int nr_sframes;
struct gnttab_get_status_frames getframes;
int rc;
nr_sframes = nr_status_frames(nr_gframes);
/* No need for kzalloc as it is initialized in following hypercall
* GNTTABOP_get_status_frames.
*/
sframes = kmalloc_array(nr_sframes, sizeof(uint64_t), GFP_ATOMIC);
if (!sframes)
return -ENOMEM;
getframes.dom = DOMID_SELF;
getframes.nr_frames = nr_sframes;
set_xen_guest_handle(getframes.frame_list, sframes);
rc = HYPERVISOR_grant_table_op(GNTTABOP_get_status_frames,
&getframes, 1);
if (rc == -ENOSYS) {
kfree(sframes);
return -ENOSYS;
}
BUG_ON(rc || getframes.status);
rc = arch_gnttab_map_status(sframes, nr_sframes,
nr_status_frames(gnttab_max_grant_frames()),
&grstatus);
BUG_ON(rc);
kfree(sframes);
rc = arch_gnttab_map_shared(frames, nr_gframes,
gnttab_max_grant_frames(),
&gnttab_shared.addr);
BUG_ON(rc);
return 0;
}
static void gnttab_unmap_frames_v2(void)
{
arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames);
arch_gnttab_unmap(grstatus, nr_status_frames(nr_grant_frames));
}
static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
{
struct gnttab_setup_table setup;
@ -1014,6 +1161,9 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
}
static const struct gnttab_ops gnttab_v1_ops = {
.version = 1,
.grefs_per_grant_frame = XEN_PAGE_SIZE /
sizeof(struct grant_entry_v1),
.map_frames = gnttab_map_frames_v1,
.unmap_frames = gnttab_unmap_frames_v1,
.update_entry = gnttab_update_entry_v1,
@ -1022,14 +1172,56 @@ static const struct gnttab_ops gnttab_v1_ops = {
.query_foreign_access = gnttab_query_foreign_access_v1,
};
static const struct gnttab_ops gnttab_v2_ops = {
.version = 2,
.grefs_per_grant_frame = XEN_PAGE_SIZE /
sizeof(union grant_entry_v2),
.map_frames = gnttab_map_frames_v2,
.unmap_frames = gnttab_unmap_frames_v2,
.update_entry = gnttab_update_entry_v2,
.end_foreign_access_ref = gnttab_end_foreign_access_ref_v2,
.end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v2,
.query_foreign_access = gnttab_query_foreign_access_v2,
};
static bool gnttab_need_v2(void)
{
#ifdef CONFIG_X86
uint32_t base, width;
if (xen_pv_domain()) {
base = xen_cpuid_base();
if (cpuid_eax(base) < 5)
return false; /* Information not available, use V1. */
width = cpuid_ebx(base + 5) &
XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK;
return width > 32 + PAGE_SHIFT;
}
#endif
return !!(max_possible_pfn >> 32);
}
static void gnttab_request_version(void)
{
/* Only version 1 is used, which will always be available. */
grant_table_version = 1;
grefs_per_grant_frame = XEN_PAGE_SIZE / sizeof(struct grant_entry_v1);
gnttab_interface = &gnttab_v1_ops;
long rc;
struct gnttab_set_version gsv;
pr_info("Grant tables using version %d layout\n", grant_table_version);
if (gnttab_need_v2())
gsv.version = 2;
else
gsv.version = 1;
/* Boot parameter overrides automatic selection. */
if (xen_gnttab_version >= 1 && xen_gnttab_version <= 2)
gsv.version = xen_gnttab_version;
rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1);
if (rc == 0 && gsv.version == 2)
gnttab_interface = &gnttab_v2_ops;
else
gnttab_interface = &gnttab_v1_ops;
pr_info("Grant tables using version %d layout\n",
gnttab_interface->version);
}
static int gnttab_setup(void)
@ -1069,10 +1261,10 @@ static int gnttab_expand(unsigned int req_entries)
int rc;
unsigned int cur, extra;
BUG_ON(grefs_per_grant_frame == 0);
BUG_ON(gnttab_interface == NULL);
cur = nr_grant_frames;
extra = ((req_entries + (grefs_per_grant_frame-1)) /
grefs_per_grant_frame);
extra = ((req_entries + gnttab_interface->grefs_per_grant_frame - 1) /
gnttab_interface->grefs_per_grant_frame);
if (cur + extra > gnttab_max_grant_frames()) {
pr_warn_ratelimited("xen/grant-table: max_grant_frames reached"
" cur=%u extra=%u limit=%u"
@ -1104,16 +1296,16 @@ int gnttab_init(void)
/* Determine the maximum number of frames required for the
* grant reference free list on the current hypervisor.
*/
BUG_ON(grefs_per_grant_frame == 0);
BUG_ON(gnttab_interface == NULL);
max_nr_glist_frames = (max_nr_grant_frames *
grefs_per_grant_frame / RPP);
gnttab_interface->grefs_per_grant_frame / RPP);
gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *),
GFP_KERNEL);
if (gnttab_list == NULL)
return -ENOMEM;
nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
nr_glist_frames = gnttab_frames(nr_grant_frames, RPP);
for (i = 0; i < nr_glist_frames; i++) {
gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL);
if (gnttab_list[i] == NULL) {
@ -1122,7 +1314,8 @@ int gnttab_init(void)
}
}
ret = arch_gnttab_init(max_nr_grant_frames);
ret = arch_gnttab_init(max_nr_grant_frames,
nr_status_frames(max_nr_grant_frames));
if (ret < 0)
goto ini_nomem;
@ -1131,7 +1324,8 @@ int gnttab_init(void)
goto ini_nomem;
}
nr_init_grefs = nr_grant_frames * grefs_per_grant_frame;
nr_init_grefs = nr_grant_frames *
gnttab_interface->grefs_per_grant_frame;
for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++)
gnttab_entry(i) = i + 1;

View File

@ -72,18 +72,15 @@ static int xen_suspend(void *data)
}
gnttab_suspend();
xen_manage_runstate_time(-1);
xen_arch_pre_suspend();
/*
* This hypercall returns 1 if suspend was cancelled
* or the domain was merely checkpointed, and 0 if it
* is resuming in a new domain.
*/
si->cancelled = HYPERVISOR_suspend(xen_pv_domain()
? virt_to_gfn(xen_start_info)
: 0);
xen_arch_post_suspend(si->cancelled);
xen_manage_runstate_time(si->cancelled ? 1 : 0);
gnttab_resume();
if (!si->cancelled) {

View File

@ -191,13 +191,10 @@ static int traverse_pages_block(unsigned nelem, size_t size,
void *state)
{
void *pagedata;
unsigned pageidx;
int ret = 0;
BUG_ON(size > PAGE_SIZE);
pageidx = PAGE_SIZE;
while (nelem) {
int nr = (PAGE_SIZE/size);
struct page *page;

View File

@ -1238,3 +1238,7 @@ static void __exit pvcalls_back_fin(void)
}
module_exit(pvcalls_back_fin);
MODULE_DESCRIPTION("Xen PV Calls backend driver");
MODULE_AUTHOR("Stefano Stabellini <sstabellini@kernel.org>");
MODULE_LICENSE("GPL");

1278
drivers/xen/pvcalls-front.c Normal file

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,28 @@
#ifndef __PVCALLS_FRONT_H__
#define __PVCALLS_FRONT_H__
#include <linux/net.h>
int pvcalls_front_socket(struct socket *sock);
int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
int addr_len, int flags);
int pvcalls_front_bind(struct socket *sock,
struct sockaddr *addr,
int addr_len);
int pvcalls_front_listen(struct socket *sock, int backlog);
int pvcalls_front_accept(struct socket *sock,
struct socket *newsock,
int flags);
int pvcalls_front_sendmsg(struct socket *sock,
struct msghdr *msg,
size_t len);
int pvcalls_front_recvmsg(struct socket *sock,
struct msghdr *msg,
size_t len,
int flags);
unsigned int pvcalls_front_poll(struct file *file,
struct socket *sock,
poll_table *wait);
int pvcalls_front_release(struct socket *sock);
#endif

View File

@ -6,6 +6,7 @@
#include <linux/kernel_stat.h>
#include <linux/math64.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <asm/paravirt.h>
#include <asm/xen/hypervisor.h>
@ -20,6 +21,8 @@
/* runstate info updated by Xen */
static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
static DEFINE_PER_CPU(u64[4], old_runstate_time);
/* return an consistent snapshot of 64-bit time/counter value */
static u64 get64(const u64 *p)
{
@ -48,8 +51,8 @@ static u64 get64(const u64 *p)
return ret;
}
static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res,
unsigned int cpu)
static void xen_get_runstate_snapshot_cpu_delta(
struct vcpu_runstate_info *res, unsigned int cpu)
{
u64 state_time;
struct vcpu_runstate_info *state;
@ -67,6 +70,71 @@ static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res,
(state_time & XEN_RUNSTATE_UPDATE));
}
static void xen_get_runstate_snapshot_cpu(struct vcpu_runstate_info *res,
unsigned int cpu)
{
int i;
xen_get_runstate_snapshot_cpu_delta(res, cpu);
for (i = 0; i < 4; i++)
res->time[i] += per_cpu(old_runstate_time, cpu)[i];
}
void xen_manage_runstate_time(int action)
{
static struct vcpu_runstate_info *runstate_delta;
struct vcpu_runstate_info state;
int cpu, i;
switch (action) {
case -1: /* backup runstate time before suspend */
if (unlikely(runstate_delta))
pr_warn_once("%s: memory leak as runstate_delta is not NULL\n",
__func__);
runstate_delta = kmalloc_array(num_possible_cpus(),
sizeof(*runstate_delta),
GFP_ATOMIC);
if (unlikely(!runstate_delta)) {
pr_warn("%s: failed to allocate runstate_delta\n",
__func__);
return;
}
for_each_possible_cpu(cpu) {
xen_get_runstate_snapshot_cpu_delta(&state, cpu);
memcpy(runstate_delta[cpu].time, state.time,
sizeof(runstate_delta[cpu].time));
}
break;
case 0: /* backup runstate time after resume */
if (unlikely(!runstate_delta)) {
pr_warn("%s: cannot accumulate runstate time as runstate_delta is NULL\n",
__func__);
return;
}
for_each_possible_cpu(cpu) {
for (i = 0; i < 4; i++)
per_cpu(old_runstate_time, cpu)[i] +=
runstate_delta[cpu].time[i];
}
break;
default: /* do not accumulate runstate time for checkpointing */
break;
}
if (action != -1 && runstate_delta) {
kfree(runstate_delta);
runstate_delta = NULL;
}
}
/*
* Runstate accounting
*/

View File

@ -379,10 +379,12 @@ static void xenbus_reset_frontend(char *fe, char *be, int be_state)
case XenbusStateConnected:
xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosing);
xenbus_reset_wait_for_backend(be, XenbusStateClosing);
/* fall through */
case XenbusStateClosing:
xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosed);
xenbus_reset_wait_for_backend(be, XenbusStateClosed);
/* fall through */
case XenbusStateClosed:
xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateInitialising);

View File

@ -174,10 +174,13 @@ gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr,
unmap->dev_bus_addr = 0;
}
int arch_gnttab_init(unsigned long nr_shared);
int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status);
int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes,
unsigned long max_nr_gframes,
void **__shared);
int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
unsigned long max_nr_gframes,
grant_status_t **__shared);
void arch_gnttab_unmap(void *shared, unsigned long nr_gframes);
struct grant_frames {

View File

@ -178,4 +178,46 @@ DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_vcpu_info);
/* Send an NMI to the specified VCPU. @extra_arg == NULL. */
#define VCPUOP_send_nmi 11
/*
* Get the physical ID information for a pinned vcpu's underlying physical
* processor. The physical ID informmation is architecture-specific.
* On x86: id[31:0]=apic_id, id[63:32]=acpi_id.
* This command returns -EINVAL if it is not a valid operation for this VCPU.
*/
#define VCPUOP_get_physid 12 /* arg == vcpu_get_physid_t */
struct vcpu_get_physid {
uint64_t phys_id;
};
DEFINE_GUEST_HANDLE_STRUCT(vcpu_get_physid);
#define xen_vcpu_physid_to_x86_apicid(physid) ((uint32_t)(physid))
#define xen_vcpu_physid_to_x86_acpiid(physid) ((uint32_t)((physid) >> 32))
/*
* Register a memory location to get a secondary copy of the vcpu time
* parameters. The master copy still exists as part of the vcpu shared
* memory area, and this secondary copy is updated whenever the master copy
* is updated (and using the same versioning scheme for synchronisation).
*
* The intent is that this copy may be mapped (RO) into userspace so
* that usermode can compute system time using the time info and the
* tsc. Usermode will see an array of vcpu_time_info structures, one
* for each vcpu, and choose the right one by an existing mechanism
* which allows it to get the current vcpu number (such as via a
* segment limit). It can then apply the normal algorithm to compute
* system time from the tsc.
*
* @extra_arg == pointer to vcpu_register_time_info_memory_area structure.
*/
#define VCPUOP_register_vcpu_time_memory_area 13
DEFINE_GUEST_HANDLE_STRUCT(vcpu_time_info);
struct vcpu_register_time_memory_area {
union {
GUEST_HANDLE(vcpu_time_info) h;
struct pvclock_vcpu_time_info *v;
uint64_t p;
} addr;
};
DEFINE_GUEST_HANDLE_STRUCT(vcpu_register_time_memory_area);
#endif /* __XEN_PUBLIC_VCPU_H__ */

View File

@ -33,6 +33,7 @@ void xen_resume_notifier_unregister(struct notifier_block *nb);
bool xen_vcpu_stolen(int vcpu);
void xen_setup_runstate_info(int cpu);
void xen_time_setup_guest(void);
void xen_manage_runstate_time(int action);
void xen_get_runstate_snapshot(struct vcpu_runstate_info *res);
u64 xen_steal_clock(int cpu);
@ -104,6 +105,8 @@ int xen_remap_domain_gfn_range(struct vm_area_struct *vma,
struct page **pages);
int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
int numpgs, struct page **pages);
#ifdef CONFIG_XEN_AUTO_XLATE
int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
unsigned long addr,
xen_pfn_t *gfn, int nr,
@ -112,6 +115,28 @@ int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
struct page **pages);
int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma,
int nr, struct page **pages);
#else
/*
* These two functions are called from arch/x86/xen/mmu.c and so stubs
* are needed for a configuration not specifying CONFIG_XEN_AUTO_XLATE.
*/
static inline int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
unsigned long addr,
xen_pfn_t *gfn, int nr,
int *err_ptr, pgprot_t prot,
unsigned int domid,
struct page **pages)
{
return -EOPNOTSUPP;
}
static inline int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma,
int nr, struct page **pages)
{
return -EOPNOTSUPP;
}
#endif
int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr,
unsigned long nr_grant_frames);