S: Maintained
W: http://btrfs.wiki.kernel.org/
Q: http://patchwork.kernel.org/project/linux-btrfs/list/
+ C: irc://irc.libera.chat/btrfs
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git
F: Documentation/filesystems/btrfs.rst
F: fs/btrfs/
FANOTIFY
M: Jan Kara <jack@suse.cz>
R: Amir Goldstein <amir73il@gmail.com>
+ R: Matthew Bobrowski <repnop@google.com>
L: linux-fsdevel@vger.kernel.org
S: Maintained
F: fs/notify/fanotify/
F: arch/arm64/include/uapi/asm/kvm*
F: arch/arm64/kvm/
F: include/kvm/arm_*
+F: tools/testing/selftests/kvm/*/aarch64/
+F: tools/testing/selftests/kvm/aarch64/
KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)
M: Huacai Chen <chenhuacai@kernel.org>
NFC SUBSYSTEM
M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
- L: linux-nfc@lists.01.org (moderated for non-subscribers)
+ L: linux-nfc@lists.01.org (subscribers-only)
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/nfc/
NFC VIRTUAL NCI DEVICE DRIVER
M: Bongsu Jeon <bongsu.jeon@samsung.com>
L: netdev@vger.kernel.org
- L: linux-nfc@lists.01.org (moderated for non-subscribers)
+ L: linux-nfc@lists.01.org (subscribers-only)
S: Supported
F: drivers/nfc/virtual_ncidev.c
F: tools/testing/selftests/nci/
NXP-NCI NFC DRIVER
R: Charles Gorand <charles.gorand@effinnov.com>
- L: linux-nfc@lists.01.org (moderated for non-subscribers)
+ L: linux-nfc@lists.01.org (subscribers-only)
S: Supported
F: drivers/nfc/nxp-nci
PCI ENDPOINT SUBSYSTEM
M: Kishon Vijay Abraham I <kishon@ti.com>
M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ R: Krzysztof Wilczyński <kw@linux.com>
L: linux-pci@vger.kernel.org
S: Supported
F: Documentation/PCI/endpoint/*
PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
R: Rob Herring <robh@kernel.org>
+ R: Krzysztof Wilczyński <kw@linux.com>
L: linux-pci@vger.kernel.org
S: Supported
Q: http://patchwork.ozlabs.org/project/linux-pci/list/
SAMSUNG S3FWRN5 NFC DRIVER
M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
M: Krzysztof Opasiak <k.opasiak@samsung.com>
- L: linux-nfc@lists.01.org (moderated for non-subscribers)
+ L: linux-nfc@lists.01.org (subscribers-only)
S: Maintained
F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml
F: drivers/nfc/s3fwrn5
SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
M: Karsten Graul <kgraul@linux.ibm.com>
+ M: Guvenc Gulce <guvenc@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
TI TRF7970A NFC DRIVER
M: Mark Greer <mgreer@animalcreek.com>
L: linux-wireless@vger.kernel.org
- L: linux-nfc@lists.01.org (moderated for non-subscribers)
+ L: linux-nfc@lists.01.org (subscribers-only)
S: Supported
F: Documentation/devicetree/bindings/net/nfc/trf7970a.txt
F: drivers/nfc/trf7970a.c
F: drivers/usb/host/isp116x*
F: include/linux/usb/isp116x.h
+ USB ISP1760 DRIVER
+ M: Rui Miguel Silva <rui.silva@linaro.org>
+ L: linux-usb@vger.kernel.org
+ S: Maintained
+ F: drivers/usb/isp1760/*
+ F: Documentation/devicetree/bindings/usb/nxp,isp1760.yaml
+
USB LAN78XX ETHERNET DRIVER
M: Woojung Huh <woojung.huh@microchip.com>
M: UNGLinuxDriver@microchip.com
#include <asm/pte-walk.h>
/* Translate address of a vmalloc'd thing to a linear map address */
- static void *real_vmalloc_addr(void *x)
+ static void *real_vmalloc_addr(void *addr)
{
- unsigned long addr = (unsigned long) x;
- pte_t *p;
- /*
- * assume we don't have huge pages in vmalloc space...
- * So don't worry about THP collapse/split. Called
- * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore.
- */
- p = find_init_mm_pte(addr, NULL);
- if (!p || !pte_present(*p))
- return NULL;
- addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
- return __va(addr);
+ return __va(ppc_find_vmap_phys((unsigned long)addr));
}
/* Return 1 if we need to do a global tlbie, 0 if we can use tlbiel */
else
global = 1;
+ /* LPID has been switched to host if in virt mode so can't do local */
+ if (!global && (mfmsr() & (MSR_IR|MSR_DR)))
+ global = 1;
+
if (!global) {
/* any other core might now have stale TLB entries... */
smp_wmb();
* so use the bit for the first thread to represent the core.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
- cpu = cpu_first_thread_sibling(cpu);
+ cpu = cpu_first_tlb_thread_sibling(cpu);
cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush);
}
vcpu->arch.pgdir, true,
&vcpu->arch.regs.gpr[4]);
}
+EXPORT_SYMBOL_GPL(kvmppc_h_enter);
#ifdef __BIG_ENDIAN__
#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token))
return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn,
&vcpu->arch.regs.gpr[4]);
}
+EXPORT_SYMBOL_GPL(kvmppc_h_remove);
long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
{
return ret;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_bulk_remove);
long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index, unsigned long avpn)
return H_SUCCESS;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_protect);
long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
}
return H_SUCCESS;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_read);
long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
return ret;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_clear_ref);
long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
return ret;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_clear_mod);
static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long mmu_seq,
unsigned long gpa, int writing, unsigned long *hpa,
return -1; /* send fault up to host kernel mode */
}
+EXPORT_SYMBOL_GPL(kvmppc_hpte_hv_fault);
/* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */
static refcount_t *ppi_nmi_refs;
-static struct gic_kvm_info gic_v3_kvm_info;
+static struct gic_kvm_info gic_v3_kvm_info __initdata;
static DEFINE_PER_CPU(bool, has_rss);
#define MPIDR_RS(mpidr) (((mpidr) & 0xF0UL) >> 4)
nmi_exit();
}
+ static u32 do_read_iar(struct pt_regs *regs)
+ {
+ u32 iar;
+
+ if (gic_supports_nmi() && unlikely(!interrupts_enabled(regs))) {
+ u64 pmr;
+
+ /*
+ * We were in a context with IRQs disabled. However, the
+ * entry code has set PMR to a value that allows any
+ * interrupt to be acknowledged, and not just NMIs. This can
+ * lead to surprising effects if the NMI has been retired in
+ * the meantime, and that there is an IRQ pending. The IRQ
+ * would then be taken in NMI context, something that nobody
+ * wants to debug twice.
+ *
+ * Until we sort this, drop PMR again to a level that will
+ * actually only allow NMIs before reading IAR, and then
+ * restore it to what it was.
+ */
+ pmr = gic_read_pmr();
+ gic_pmr_mask_irqs();
+ isb();
+
+ iar = gic_read_iar();
+
+ gic_write_pmr(pmr);
+ } else {
+ iar = gic_read_iar();
+ }
+
+ return iar;
+ }
+
static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
u32 irqnr;
- irqnr = gic_read_iar();
+ irqnr = do_read_iar(regs);
/* Check for special IDs first */
if ((irqnr >= 1020 && irqnr <= 1023))
gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
- gic_set_kvm_info(&gic_v3_kvm_info);
+ vgic_set_kvm_info(&gic_v3_kvm_info);
}
static int __init gic_of_init(struct device_node *node, struct device_node *parent)
gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
- gic_set_kvm_info(&gic_v3_kvm_info);
+ vgic_set_kvm_info(&gic_v3_kvm_info);
}
static int __init
/* Minimum allocated guest virtual and physical addresses */
#define KVM_UTIL_MIN_VADDR 0x2000
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
#define DEFAULT_GUEST_PHY_PAGES 512
#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000
VM_MODE_P40V48_64K,
VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
VM_MODE_P47V64_4K,
+ VM_MODE_P44V64_4K,
NUM_VM_MODES,
};
#elif defined(__s390x__)
- #define VM_MODE_DEFAULT VM_MODE_P47V64_4K
+ #define VM_MODE_DEFAULT VM_MODE_P44V64_4K
#define MIN_PAGE_SHIFT 12U
#define ptes_per_page(page_size) ((page_size) / 16)
int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
size_t len);
-void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
- uint32_t data_memslot, uint32_t pgd_memslot);
+void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename);
void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid);
-vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
- uint32_t data_memslot, uint32_t pgd_memslot);
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
+vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
+vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);
+
void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- unsigned int npages, uint32_t pgd_memslot);
+ unsigned int npages);
void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
const char *exit_reason_str(unsigned int exit_reason);
-void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot);
+void virt_pgd_alloc(struct kvm_vm *vm);
/*
* VM Virtual Page Map
* Within @vm, creates a virtual translation for the page starting
* at @vaddr to the page starting at @paddr.
*/
-void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- uint32_t memslot);
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr);
vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
uint32_t memslot);
vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
vm_paddr_t paddr_min, uint32_t memslot);
+vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
/*
* Create a VM with reasonable defaults
UCALL_SYNC,
UCALL_ABORT,
UCALL_DONE,
+ UCALL_UNHANDLED,
};
#define UCALL_MAX_ARGS 6
ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage)
#define GUEST_DONE() ucall(UCALL_DONE, 0)
-#define __GUEST_ASSERT(_condition, _nargs, _args...) do { \
- if (!(_condition)) \
- ucall(UCALL_ABORT, 2 + _nargs, \
- "Failed guest assert: " \
- #_condition, __LINE__, _args); \
+#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do { \
+ if (!(_condition)) \
+ ucall(UCALL_ABORT, 2 + _nargs, \
+ "Failed guest assert: " \
+ _condstr, __LINE__, _args); \
} while (0)
#define GUEST_ASSERT(_condition) \
- __GUEST_ASSERT((_condition), 0, 0)
+ __GUEST_ASSERT(_condition, #_condition, 0, 0)
#define GUEST_ASSERT_1(_condition, arg1) \
- __GUEST_ASSERT((_condition), 1, (arg1))
+ __GUEST_ASSERT(_condition, #_condition, 1, (arg1))
#define GUEST_ASSERT_2(_condition, arg1, arg2) \
- __GUEST_ASSERT((_condition), 2, (arg1), (arg2))
+ __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2))
#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \
- __GUEST_ASSERT((_condition), 3, (arg1), (arg2), (arg3))
+ __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3))
#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \
- __GUEST_ASSERT((_condition), 4, (arg1), (arg2), (arg3), (arg4))
+ __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4))
+
+#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b)
+
+int vm_get_stats_fd(struct kvm_vm *vm);
+int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid);
#endif /* SELFTEST_KVM_UTIL_H */
[VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
[VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
[VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
+ [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
};
_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
{ 40, 48, 0x10000, 16 },
{ 0, 0, 0x1000, 12 },
{ 47, 64, 0x1000, 12 },
+ { 44, 64, 0x1000, 12 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
case VM_MODE_P47V64_4K:
vm->pgtable_levels = 5;
break;
+ case VM_MODE_P44V64_4K:
+ vm->pgtable_levels = 5;
+ break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
}
pages = vm_adjust_num_guest_pages(mode, pages);
vm = vm_create(mode, pages, O_RDWR);
- kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+ kvm_vm_elf_load(vm, program_invocation_name);
#ifdef __x86_64__
vm_create_irqchip(vm);
uint32_t vcpuid = vcpuids ? vcpuids[i] : i;
vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-#ifdef __x86_64__
- vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
-#endif
}
return vm;
* a unique set of pages, with the minimum real allocation being at least
* a page.
*/
-vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
- uint32_t data_memslot, uint32_t pgd_memslot)
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
{
uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
- virt_pgd_alloc(vm, pgd_memslot);
+ virt_pgd_alloc(vm);
vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages,
- KVM_UTIL_MIN_PFN * vm->page_size,
- data_memslot);
+ KVM_UTIL_MIN_PFN * vm->page_size, 0);
/*
* Find an unused range of virtual page addresses of at least
for (vm_vaddr_t vaddr = vaddr_start; pages > 0;
pages--, vaddr += vm->page_size, paddr += vm->page_size) {
- virt_pg_map(vm, vaddr, paddr, pgd_memslot);
+ virt_pg_map(vm, vaddr, paddr);
sparsebit_set(vm->vpages_mapped,
vaddr >> vm->page_shift);
}
/*
+ * VM Virtual Address Allocate Pages
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Starting guest virtual address
+ *
+ * Allocates at least N system pages worth of bytes within the virtual address
+ * space of the vm.
+ */
+vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages)
+{
+ return vm_vaddr_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR);
+}
+
+/*
+ * VM Virtual Address Allocate Page
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Starting guest virtual address
+ *
+ * Allocates at least one system page worth of bytes within the virtual address
+ * space of the vm.
+ */
+vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm)
+{
+ return vm_vaddr_alloc_pages(vm, 1);
+}
+
+/*
* Map a range of VM virtual address to the VM's physical address
*
* Input Args:
* @npages starting at @vaddr to the page range starting at @paddr.
*/
void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- unsigned int npages, uint32_t pgd_memslot)
+ unsigned int npages)
{
size_t page_size = vm->page_size;
size_t size = npages * page_size;
TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
while (npages--) {
- virt_pg_map(vm, vaddr, paddr, pgd_memslot);
+ virt_pg_map(vm, vaddr, paddr);
vaddr += page_size;
paddr += page_size;
}
return vm_phy_pages_alloc(vm, 1, paddr_min, memslot);
}
+/* Arbitrary minimum physical address used for virtual translation tables. */
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm)
+{
+ return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+}
+
/*
* Address Guest Virtual to Host Virtual
*
n = DIV_ROUND_UP(size, vm_guest_mode_params[mode].page_size);
return vm_adjust_num_guest_pages(mode, n);
}
+
+int vm_get_stats_fd(struct kvm_vm *vm)
+{
+ return ioctl(vm->fd, KVM_GET_STATS_FD, NULL);
+}
+
+int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+ return ioctl(vcpu->fd, KVM_GET_STATS_FD, NULL);
+}
gpa = vm_phy_pages_alloc(vm, 2, MEM_REGION_GPA, MEM_REGION_SLOT);
TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
- virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 2, 0);
+ virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 2);
/* Ditto for the host mapping so that both pages can be zeroed. */
hva = addr_gpa2hva(vm, MEM_REGION_GPA);
pr_info("Adding slots 0..%i, each memory region with %dK size\n",
(max_mem_slots - 1), MEM_REGION_SIZE >> 10);
- mem = mmap(NULL, MEM_REGION_SIZE * max_mem_slots + alignment,
- PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
TEST_ASSERT(ret == -1 && errno == EINVAL,
"Adding one more memory slot should fail with EINVAL");
- munmap(mem, MEM_REGION_SIZE * max_mem_slots + alignment);
+ munmap(mem, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment);
munmap(mem_extra, MEM_REGION_SIZE);
kvm_vm_free(vm);
}
#include <linux/io.h>
#include <linux/lockdep.h>
#include <linux/kthread.h>
+#include <linux/suspend.h>
#include <asm/processor.h>
#include <asm/ioctl.h>
struct dentry *kvm_debugfs_dir;
EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
-static int kvm_debugfs_num_entries;
static const struct file_operations stat_fops_per_vm;
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
*/
if (!kvm_arch_flush_remote_tlb(kvm)
|| kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
- ++kvm->stat.remote_tlb_flush;
+ ++kvm->stat.generic.remote_tlb_flush;
cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
}
EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
+#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
+static int kvm_pm_notifier_call(struct notifier_block *bl,
+ unsigned long state,
+ void *unused)
+{
+ struct kvm *kvm = container_of(bl, struct kvm, pm_notifier);
+
+ return kvm_arch_pm_notifier(kvm, state);
+}
+
+static void kvm_init_pm_notifier(struct kvm *kvm)
+{
+ kvm->pm_notifier.notifier_call = kvm_pm_notifier_call;
+ /* Suspend KVM before we suspend ftrace, RCU, etc. */
+ kvm->pm_notifier.priority = INT_MAX;
+ register_pm_notifier(&kvm->pm_notifier);
+}
+
+static void kvm_destroy_pm_notifier(struct kvm *kvm)
+{
+ unregister_pm_notifier(&kvm->pm_notifier);
+}
+#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */
+static void kvm_init_pm_notifier(struct kvm *kvm)
+{
+}
+
+static void kvm_destroy_pm_notifier(struct kvm *kvm)
+{
+}
+#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */
+
static struct kvm_memslots *kvm_alloc_memslots(void)
{
int i;
kvfree(slots);
}
+static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc)
+{
+ switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) {
+ case KVM_STATS_TYPE_INSTANT:
+ return 0444;
+ case KVM_STATS_TYPE_CUMULATIVE:
+ case KVM_STATS_TYPE_PEAK:
+ default:
+ return 0644;
+ }
+}
+
+
static void kvm_destroy_vm_debugfs(struct kvm *kvm)
{
int i;
+ int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
+ kvm_vcpu_stats_header.num_desc;
if (!kvm->debugfs_dentry)
return;
{
char dir_name[ITOA_MAX_LEN * 2];
struct kvm_stat_data *stat_data;
- struct kvm_stats_debugfs_item *p;
+ const struct _kvm_stats_desc *pdesc;
+ int i;
+ int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
+ kvm_vcpu_stats_header.num_desc;
if (!debugfs_initialized())
return 0;
if (!kvm->debugfs_stat_data)
return -ENOMEM;
- for (p = debugfs_entries; p->name; p++) {
+ for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vm_stats_desc[i];
+ stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
+ if (!stat_data)
+ return -ENOMEM;
+
+ stat_data->kvm = kvm;
+ stat_data->desc = pdesc;
+ stat_data->kind = KVM_STAT_VM;
+ kvm->debugfs_stat_data[i] = stat_data;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm->debugfs_dentry, stat_data,
+ &stat_fops_per_vm);
+ }
+
+ for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vcpu_stats_desc[i];
stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
if (!stat_data)
return -ENOMEM;
stat_data->kvm = kvm;
- stat_data->dbgfs_item = p;
- kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
- debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p),
+ stat_data->desc = pdesc;
+ stat_data->kind = KVM_STAT_VCPU;
+ kvm->debugfs_stat_data[i] = stat_data;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
kvm->debugfs_dentry, stat_data,
&stat_fops_per_vm);
}
mutex_init(&kvm->lock);
mutex_init(&kvm->irq_lock);
mutex_init(&kvm->slots_lock);
+ mutex_init(&kvm->slots_arch_lock);
INIT_LIST_HEAD(&kvm->devices);
BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
mutex_unlock(&kvm_lock);
preempt_notifier_inc();
+ kvm_init_pm_notifier(kvm);
return kvm;
int i;
struct mm_struct *mm = kvm->mm;
+ kvm_destroy_pm_notifier(kvm);
kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
kvm_destroy_vm_debugfs(kvm);
kvm_arch_sync_events(kvm);
slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
rcu_assign_pointer(kvm->memslots[as_id], slots);
+
+ /*
+ * Acquired in kvm_set_memslot. Must be released before synchronize
+ * SRCU below in order to avoid deadlock with another thread
+ * acquiring the slots_arch_lock in an srcu critical section.
+ */
+ mutex_unlock(&kvm->slots_arch_lock);
+
synchronize_srcu_expedited(&kvm->srcu);
/*
return old_memslots;
}
+static size_t kvm_memslots_size(int slots)
+{
+ return sizeof(struct kvm_memslots) +
+ (sizeof(struct kvm_memory_slot) * slots);
+}
+
+static void kvm_copy_memslots(struct kvm_memslots *to,
+ struct kvm_memslots *from)
+{
+ memcpy(to, from, kvm_memslots_size(from->used_slots));
+}
+
/*
* Note, at a minimum, the current number of used slots must be allocated, even
* when deleting a memslot, as we need a complete duplicate of the memslots for
enum kvm_mr_change change)
{
struct kvm_memslots *slots;
- size_t old_size, new_size;
-
- old_size = sizeof(struct kvm_memslots) +
- (sizeof(struct kvm_memory_slot) * old->used_slots);
+ size_t new_size;
if (change == KVM_MR_CREATE)
- new_size = old_size + sizeof(struct kvm_memory_slot);
+ new_size = kvm_memslots_size(old->used_slots + 1);
else
- new_size = old_size;
+ new_size = kvm_memslots_size(old->used_slots);
slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT);
if (likely(slots))
- memcpy(slots, old, old_size);
+ kvm_copy_memslots(slots, old);
return slots;
}
struct kvm_memslots *slots;
int r;
+ /*
+ * Released in install_new_memslots.
+ *
+ * Must be held from before the current memslots are copied until
+ * after the new memslots are installed with rcu_assign_pointer,
+ * then released before the synchronize srcu in install_new_memslots.
+ *
+ * When modifying memslots outside of the slots_lock, must be held
+ * before reading the pointer to the current memslots until after all
+ * changes to those memslots are complete.
+ *
+ * These rules ensure that installing new memslots does not lose
+ * changes made to the previous memslots.
+ */
+ mutex_lock(&kvm->slots_arch_lock);
+
slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change);
- if (!slots)
+ if (!slots) {
+ mutex_unlock(&kvm->slots_arch_lock);
return -ENOMEM;
+ }
if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
/*
slot->flags |= KVM_MEMSLOT_INVALID;
/*
- * We can re-use the old memslots, the only difference from the
- * newly installed memslots is the invalid flag, which will get
- * dropped by update_memslots anyway. We'll also revert to the
- * old memslots if preparing the new memory region fails.
+ * We can re-use the memory from the old memslots.
+ * It will be overwritten with a copy of the new memslots
+ * after reacquiring the slots_arch_lock below.
*/
slots = install_new_memslots(kvm, as_id, slots);
* - kvm_is_visible_gfn (mmu_check_root)
*/
kvm_arch_flush_shadow_memslot(kvm, slot);
+
+ /* Released in install_new_memslots. */
+ mutex_lock(&kvm->slots_arch_lock);
+
+ /*
+ * The arch-specific fields of the memslots could have changed
+ * between releasing the slots_arch_lock in
+ * install_new_memslots and here, so get a fresh copy of the
+ * slots.
+ */
+ kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id));
}
r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
return 0;
out_slots:
- if (change == KVM_MR_DELETE || change == KVM_MR_MOVE)
+ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+ slot = id_to_memslot(slots, old->id);
+ slot->flags &= ~KVM_MEMSLOT_INVALID;
slots = install_new_memslots(kvm, as_id, slots);
+ } else {
+ mutex_unlock(&kvm->slots_arch_lock);
+ }
kvfree(slots);
return r;
}
return true;
}
+ static int kvm_try_get_pfn(kvm_pfn_t pfn)
+ {
+ if (kvm_is_reserved_pfn(pfn))
+ return 1;
+ return get_page_unless_zero(pfn_to_page(pfn));
+ }
+
static int hva_to_pfn_remapped(struct vm_area_struct *vma,
unsigned long addr, bool *async,
bool write_fault, bool *writable,
* Whoever called remap_pfn_range is also going to call e.g.
* unmap_mapping_range before the underlying pages are freed,
* causing a call to our MMU notifier.
+ *
+ * Certain IO or PFNMAP mappings can be backed with valid
+ * struct pages, but be allocated without refcounting e.g.,
+ * tail pages of non-compound higher order allocations, which
+ * would then underflow the refcount when the caller does the
+ * required put_page. Don't allow those pages here.
*/
- kvm_get_pfn(pfn);
+ if (!kvm_try_get_pfn(pfn))
+ r = -EFAULT;
out:
pte_unmap_unlock(ptep, ptl);
*p_pfn = pfn;
- return 0;
+
+ return r;
}
/*
update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited)
{
if (waited)
- vcpu->stat.halt_poll_fail_ns += poll_ns;
+ vcpu->stat.generic.halt_poll_fail_ns += poll_ns;
else
- vcpu->stat.halt_poll_success_ns += poll_ns;
+ vcpu->stat.generic.halt_poll_success_ns += poll_ns;
}
/*
if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) {
ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
- ++vcpu->stat.halt_attempted_poll;
+ ++vcpu->stat.generic.halt_attempted_poll;
do {
/*
* This sets KVM_REQ_UNHALT if an interrupt
* arrives.
*/
if (kvm_vcpu_check_block(vcpu) < 0) {
- ++vcpu->stat.halt_successful_poll;
+ ++vcpu->stat.generic.halt_successful_poll;
if (!vcpu_valid_wakeup(vcpu))
- ++vcpu->stat.halt_poll_invalid;
+ ++vcpu->stat.generic.halt_poll_invalid;
goto out;
}
poll_end = cur = ktime_get();
waitp = kvm_arch_vcpu_get_wait(vcpu);
if (rcuwait_wake_up(waitp)) {
WRITE_ONCE(vcpu->ready, true);
- ++vcpu->stat.halt_wakeup;
+ ++vcpu->stat.generic.halt_wakeup;
return true;
}
vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus);
BUG_ON(kvm->vcpus[vcpu->vcpu_idx]);
+ /* Fill the stats id string for the vcpu */
+ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d",
+ task_pid_nr(current), id);
+
/* Now it's all set up, let userspace reach it */
kvm_get_kvm(kvm);
r = create_vcpu_fd(vcpu);
return 0;
}
+static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer,
+ size_t size, loff_t *offset)
+{
+ struct kvm_vcpu *vcpu = file->private_data;
+
+ return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header,
+ &kvm_vcpu_stats_desc[0], &vcpu->stat,
+ sizeof(vcpu->stat), user_buffer, size, offset);
+}
+
+static const struct file_operations kvm_vcpu_stats_fops = {
+ .read = kvm_vcpu_stats_read,
+ .llseek = noop_llseek,
+};
+
+static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
+{
+ int fd;
+ struct file *file;
+ char name[15 + ITOA_MAX_LEN + 1];
+
+ snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id);
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ file = anon_inode_getfile(name, &kvm_vcpu_stats_fops, vcpu, O_RDONLY);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ return PTR_ERR(file);
+ }
+ file->f_mode |= FMODE_PREAD;
+ fd_install(fd, file);
+
+ return fd;
+}
+
static long kvm_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu);
break;
}
+ case KVM_GET_STATS_FD: {
+ r = kvm_vcpu_ioctl_get_stats_fd(vcpu);
+ break;
+ }
default:
r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
}
#else
return 0;
#endif
+ case KVM_CAP_BINARY_STATS_FD:
+ return 1;
default:
break;
}
}
}
+static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer,
+ size_t size, loff_t *offset)
+{
+ struct kvm *kvm = file->private_data;
+
+ return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header,
+ &kvm_vm_stats_desc[0], &kvm->stat,
+ sizeof(kvm->stat), user_buffer, size, offset);
+}
+
+static const struct file_operations kvm_vm_stats_fops = {
+ .read = kvm_vm_stats_read,
+ .llseek = noop_llseek,
+};
+
+static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
+{
+ int fd;
+ struct file *file;
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ file = anon_inode_getfile("kvm-vm-stats",
+ &kvm_vm_stats_fops, kvm, O_RDONLY);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ return PTR_ERR(file);
+ }
+ file->f_mode |= FMODE_PREAD;
+ fd_install(fd, file);
+
+ return fd;
+}
+
static long kvm_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
case KVM_RESET_DIRTY_RINGS:
r = kvm_vm_ioctl_reset_dirty_pages(kvm);
break;
+ case KVM_GET_STATS_FD:
+ r = kvm_vm_ioctl_get_stats_fd(kvm);
+ break;
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
if (r < 0)
goto put_kvm;
+ snprintf(kvm->stats_id, sizeof(kvm->stats_id),
+ "kvm-%d", task_pid_nr(current));
+
file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
if (IS_ERR(file)) {
put_unused_fd(r);
return -ENOENT;
if (simple_attr_open(inode, file, get,
- KVM_DBGFS_GET_MODE(stat_data->dbgfs_item) & 0222
+ kvm_stats_debugfs_mode(stat_data->desc) & 0222
? set : NULL,
fmt)) {
kvm_put_kvm(stat_data->kvm);
static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val)
{
- *val = *(ulong *)((void *)kvm + offset);
+ *val = *(u64 *)((void *)(&kvm->stat) + offset);
return 0;
}
static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset)
{
- *(ulong *)((void *)kvm + offset) = 0;
+ *(u64 *)((void *)(&kvm->stat) + offset) = 0;
return 0;
}
*val = 0;
kvm_for_each_vcpu(i, vcpu, kvm)
- *val += *(u64 *)((void *)vcpu + offset);
+ *val += *(u64 *)((void *)(&vcpu->stat) + offset);
return 0;
}
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
- *(u64 *)((void *)vcpu + offset) = 0;
+ *(u64 *)((void *)(&vcpu->stat) + offset) = 0;
return 0;
}
int r = -EFAULT;
struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
- switch (stat_data->dbgfs_item->kind) {
+ switch (stat_data->kind) {
case KVM_STAT_VM:
r = kvm_get_stat_per_vm(stat_data->kvm,
- stat_data->dbgfs_item->offset, val);
+ stat_data->desc->desc.offset, val);
break;
case KVM_STAT_VCPU:
r = kvm_get_stat_per_vcpu(stat_data->kvm,
- stat_data->dbgfs_item->offset, val);
+ stat_data->desc->desc.offset, val);
break;
}
if (val)
return -EINVAL;
- switch (stat_data->dbgfs_item->kind) {
+ switch (stat_data->kind) {
case KVM_STAT_VM:
r = kvm_clear_stat_per_vm(stat_data->kvm,
- stat_data->dbgfs_item->offset);
+ stat_data->desc->desc.offset);
break;
case KVM_STAT_VCPU:
r = kvm_clear_stat_per_vcpu(stat_data->kvm,
- stat_data->dbgfs_item->offset);
+ stat_data->desc->desc.offset);
break;
}
}
DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n");
static int vcpu_stat_get(void *_offset, u64 *val)
{
DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear,
"%llu\n");
-
-static const struct file_operations *stat_fops[] = {
- [KVM_STAT_VCPU] = &vcpu_stat_fops,
- [KVM_STAT_VM] = &vm_stat_fops,
-};
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n");
static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
{
static void kvm_init_debug(void)
{
- struct kvm_stats_debugfs_item *p;
+ const struct file_operations *fops;
+ const struct _kvm_stats_desc *pdesc;
+ int i;
kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
- kvm_debugfs_num_entries = 0;
- for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
- debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p),
- kvm_debugfs_dir, (void *)(long)p->offset,
- stat_fops[p->kind]);
+ for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vm_stats_desc[i];
+ if (kvm_stats_debugfs_mode(pdesc) & 0222)
+ fops = &vm_stat_fops;
+ else
+ fops = &vm_stat_readonly_fops;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm_debugfs_dir,
+ (void *)(long)pdesc->desc.offset, fops);
+ }
+
+ for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vcpu_stats_desc[i];
+ if (kvm_stats_debugfs_mode(pdesc) & 0222)
+ fops = &vcpu_stat_fops;
+ else
+ fops = &vcpu_stat_readonly_fops;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm_debugfs_dir,
+ (void *)(long)pdesc->desc.offset, fops);
}
}
kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align,
SLAB_ACCOUNT,
offsetof(struct kvm_vcpu, arch),
- sizeof_field(struct kvm_vcpu, arch),
+ offsetofend(struct kvm_vcpu, stats_id)
+ - offsetof(struct kvm_vcpu, arch),
NULL);
if (!kvm_vcpu_cache) {
r = -ENOMEM;