struct list_head list;
struct kvm *kvm;
u64 liobn;
- u32 window_size;
+ struct rcu_head rcu;
+ u32 page_shift;
+ u64 offset; /* in pages */
+ u64 size; /* window size in pages */
struct page *pages[0];
};
struct list_head runnable_threads;
struct list_head preempt_list;
spinlock_t lock;
- wait_queue_head_t wq;
+ struct swait_queue_head wq;
spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */
u64 stolen_tb;
u64 preempt_tb;
u8 prodded;
u32 last_inst;
- wait_queue_head_t *wqp;
+ struct swait_queue_head *wqp;
struct kvmppc_vcore *vcore;
int ret;
int trap;
void generic_set_cpu_dead(unsigned int cpu);
void generic_set_cpu_up(unsigned int cpu);
int generic_check_cpu_restart(unsigned int cpu);
+int is_cpu_dead(unsigned int cpu);
+#else
+#define generic_set_cpu_up(i) do { } while (0)
#endif
#ifdef CONFIG_PPC64
#define PPC_MSG_TICK_BROADCAST 2
#define PPC_MSG_DEBUGGER_BREAK 3
+ /* This is only used by the powernv kernel */
+ #define PPC_MSG_RM_HOST_ACTION 4
+
/* for irq controllers that have dedicated ipis per message (4) */
extern int smp_request_message_ipi(int virq, int message);
extern const char *smp_ipi_name[];
/* for irq controllers with only a single ipi */
extern void smp_muxed_ipi_set_data(int cpu, unsigned long data);
extern void smp_muxed_ipi_message_pass(int cpu, int msg);
+ extern void smp_muxed_ipi_set_message(int cpu, int msg);
extern irqreturn_t smp_ipi_demux(void);
void smp_init_pSeries(void);
extern unsigned long __secondary_hold_spinloop;
extern unsigned long __secondary_hold_acknowledge;
extern char __secondary_hold;
+extern unsigned int booting_thread_hwid;
extern void __early_start(void);
#endif /* __ASSEMBLY__ */
/*
- * Common definitions accross all variants of ICP and ICS interrupt
+ * Common definitions across all variants of ICP and ICS interrupt
* controllers.
*/
#ifdef CONFIG_PPC_ICP_NATIVE
extern int icp_native_init(void);
extern void icp_native_flush_interrupt(void);
+ extern void icp_native_cause_ipi_rm(int cpu);
#else
static inline int icp_native_init(void) { return -ENODEV; }
#endif
#ifdef CONFIG_PPC_SMP_MUXED_IPI
struct cpu_messages {
- int messages; /* current messages */
+ long messages; /* current messages */
unsigned long data; /* data for cause ipi */
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message);
info->data = data;
}
- void smp_muxed_ipi_message_pass(int cpu, int msg)
+ void smp_muxed_ipi_set_message(int cpu, int msg)
{
struct cpu_messages *info = &per_cpu(ipi_message, cpu);
char *message = (char *)&info->messages;
*/
smp_mb();
message[msg] = 1;
+ }
+
+ void smp_muxed_ipi_message_pass(int cpu, int msg)
+ {
+ struct cpu_messages *info = &per_cpu(ipi_message, cpu);
+
+ smp_muxed_ipi_set_message(cpu, msg);
/*
* cause_ipi functions are required to include a full barrier
* before doing whatever causes the IPI.
}
#ifdef __BIG_ENDIAN__
- #define IPI_MESSAGE(A) (1 << (24 - 8 * (A)))
+ #define IPI_MESSAGE(A) (1uL << ((BITS_PER_LONG - 8) - 8 * (A)))
#else
- #define IPI_MESSAGE(A) (1 << (8 * (A)))
+ #define IPI_MESSAGE(A) (1uL << (8 * (A)))
#endif
irqreturn_t smp_ipi_demux(void)
{
struct cpu_messages *info = this_cpu_ptr(&ipi_message);
- unsigned int all;
+ unsigned long all;
mb(); /* order any irq clear */
do {
all = xchg(&info->messages, 0);
+ #if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
+ /*
+ * Must check for PPC_MSG_RM_HOST_ACTION messages
+ * before PPC_MSG_CALL_FUNCTION messages because when
+ * a VM is destroyed, we call kick_all_cpus_sync()
+ * to ensure that any pending PPC_MSG_RM_HOST_ACTION
+ * messages have completed before we free any VCPUs.
+ */
+ if (all & IPI_MESSAGE(PPC_MSG_RM_HOST_ACTION))
+ kvmppc_xics_ipi_action();
+ #endif
if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION))
generic_smp_call_function_interrupt();
if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
for (i = 0; i < 100; i++) {
smp_rmb();
- if (per_cpu(cpu_state, cpu) == CPU_DEAD)
+ if (is_cpu_dead(cpu))
return;
msleep(100);
}
return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
}
+int is_cpu_dead(unsigned int cpu)
+{
+ return per_cpu(cpu_state, cpu) == CPU_DEAD;
+}
+
static bool secondaries_inhibited(void)
{
return kvm_hv_mode_active();
local_irq_enable();
- cpu_startup_entry(CPUHP_ONLINE);
+ cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
BUG();
}
*
* Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
* Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ * Copyright 2016 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com>
*/
#include <linux/types.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
-#include <asm/mmu-hash64.h>
+#include <asm/book3s/64/mmu-hash.h>
#include <asm/hvcall.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#include <asm/kvm_host.h>
#include <asm/udbg.h>
+ #include <asm/iommu.h>
+ #include <asm/tce.h>
- #define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64))
+ static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
+ {
+ return ALIGN(iommu_pages * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
+ }
- static long kvmppc_stt_npages(unsigned long window_size)
+ static unsigned long kvmppc_stt_pages(unsigned long tce_pages)
{
- return ALIGN((window_size >> SPAPR_TCE_SHIFT)
- * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
+ unsigned long stt_bytes = sizeof(struct kvmppc_spapr_tce_table) +
+ (tce_pages * sizeof(struct page *));
+
+ return tce_pages + ALIGN(stt_bytes, PAGE_SIZE) / PAGE_SIZE;
}
- static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
+ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
{
- struct kvm *kvm = stt->kvm;
- int i;
+ long ret = 0;
- mutex_lock(&kvm->lock);
- list_del(&stt->list);
- for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
+ if (!current || !current->mm)
+ return ret; /* process exited */
+
+ down_write(¤t->mm->mmap_sem);
+
+ if (inc) {
+ unsigned long locked, lock_limit;
+
+ locked = current->mm->locked_vm + stt_pages;
+ lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+ ret = -ENOMEM;
+ else
+ current->mm->locked_vm += stt_pages;
+ } else {
+ if (WARN_ON_ONCE(stt_pages > current->mm->locked_vm))
+ stt_pages = current->mm->locked_vm;
+
+ current->mm->locked_vm -= stt_pages;
+ }
+
+ pr_debug("[%d] RLIMIT_MEMLOCK KVM %c%ld %ld/%ld%s\n", current->pid,
+ inc ? '+' : '-',
+ stt_pages << PAGE_SHIFT,
+ current->mm->locked_vm << PAGE_SHIFT,
+ rlimit(RLIMIT_MEMLOCK),
+ ret ? " - exceeded" : "");
+
+ up_write(¤t->mm->mmap_sem);
+
+ return ret;
+ }
+
+ static void release_spapr_tce_table(struct rcu_head *head)
+ {
+ struct kvmppc_spapr_tce_table *stt = container_of(head,
+ struct kvmppc_spapr_tce_table, rcu);
+ unsigned long i, npages = kvmppc_tce_pages(stt->size);
+
+ for (i = 0; i < npages; i++)
__free_page(stt->pages[i]);
- kfree(stt);
- mutex_unlock(&kvm->lock);
- kvm_put_kvm(kvm);
+ kfree(stt);
}
static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data;
struct page *page;
- if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size))
+ if (vmf->pgoff >= kvmppc_tce_pages(stt->size))
return VM_FAULT_SIGBUS;
page = stt->pages[vmf->pgoff];
{
struct kvmppc_spapr_tce_table *stt = filp->private_data;
- release_spapr_tce_table(stt);
+ list_del_rcu(&stt->list);
+
+ kvm_put_kvm(stt->kvm);
+
+ kvmppc_account_memlimit(
+ kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
+ call_rcu(&stt->rcu, release_spapr_tce_table);
+
return 0;
}
};
long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
- struct kvm_create_spapr_tce *args)
+ struct kvm_create_spapr_tce_64 *args)
{
struct kvmppc_spapr_tce_table *stt = NULL;
- long npages;
+ unsigned long npages, size;
int ret = -ENOMEM;
int i;
+ if (!args->size)
+ return -EINVAL;
+
/* Check this LIOBN hasn't been previously allocated */
list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
if (stt->liobn == args->liobn)
return -EBUSY;
}
- npages = kvmppc_stt_npages(args->window_size);
+ size = args->size;
+ npages = kvmppc_tce_pages(size);
+ ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
+ if (ret) {
+ stt = NULL;
+ goto fail;
+ }
stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
GFP_KERNEL);
goto fail;
stt->liobn = args->liobn;
- stt->window_size = args->window_size;
+ stt->page_shift = args->page_shift;
+ stt->offset = args->offset;
+ stt->size = size;
stt->kvm = kvm;
for (i = 0; i < npages; i++) {
kvm_get_kvm(kvm);
mutex_lock(&kvm->lock);
- list_add(&stt->list, &kvm->arch.spapr_tce_tables);
+ list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
mutex_unlock(&kvm->lock);
}
return ret;
}
+
+ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_list, unsigned long npages)
+ {
+ struct kvmppc_spapr_tce_table *stt;
+ long i, ret = H_SUCCESS, idx;
+ unsigned long entry, ua = 0;
+ u64 __user *tces, tce;
+
+ stt = kvmppc_find_table(vcpu, liobn);
+ if (!stt)
+ return H_TOO_HARD;
+
+ entry = ioba >> stt->page_shift;
+ /*
+ * SPAPR spec says that the maximum size of the list is 512 TCEs
+ * so the whole table fits in 4K page
+ */
+ if (npages > 512)
+ return H_PARAMETER;
+
+ if (tce_list & (SZ_4K - 1))
+ return H_PARAMETER;
+
+ ret = kvmppc_ioba_validate(stt, ioba, npages);
+ if (ret != H_SUCCESS)
+ return ret;
+
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL)) {
+ ret = H_TOO_HARD;
+ goto unlock_exit;
+ }
+ tces = (u64 __user *) ua;
+
+ for (i = 0; i < npages; ++i) {
+ if (get_user(tce, tces + i)) {
+ ret = H_TOO_HARD;
+ goto unlock_exit;
+ }
+ tce = be64_to_cpu(tce);
+
+ ret = kvmppc_tce_validate(stt, tce);
+ if (ret != H_SUCCESS)
+ goto unlock_exit;
+
+ kvmppc_tce_put(stt, entry + i, tce);
+ }
+
+ unlock_exit:
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+ return ret;
+ }
+ EXPORT_SYMBOL_GPL(kvmppc_h_put_tce_indirect);
*
* Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
* Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ * Copyright 2016 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com>
*/
#include <linux/types.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
-#include <asm/mmu-hash64.h>
+#include <asm/book3s/64/mmu-hash.h>
+ #include <asm/mmu_context.h>
#include <asm/hvcall.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#include <asm/kvm_host.h>
#include <asm/udbg.h>
+ #include <asm/iommu.h>
+ #include <asm/tce.h>
+ #include <asm/iommu.h>
#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64))
- /* WARNING: This will be called in real-mode on HV KVM and virtual
+ /*
+ * Finds a TCE table descriptor by LIOBN.
+ *
+ * WARNING: This will be called in real or virtual mode on HV KVM and virtual
* mode on PR KVM
*/
- long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
- unsigned long ioba, unsigned long tce)
+ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu,
+ unsigned long liobn)
{
struct kvm *kvm = vcpu->kvm;
struct kvmppc_spapr_tce_table *stt;
+ list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list)
+ if (stt->liobn == liobn)
+ return stt;
+
+ return NULL;
+ }
+ EXPORT_SYMBOL_GPL(kvmppc_find_table);
+
+ /*
+ * Validates IO address.
+ *
+ * WARNING: This will be called in real-mode on HV KVM and virtual
+ * mode on PR KVM
+ */
+ long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
+ unsigned long ioba, unsigned long npages)
+ {
+ unsigned long mask = (1ULL << stt->page_shift) - 1;
+ unsigned long idx = ioba >> stt->page_shift;
+
+ if ((ioba & mask) || (idx < stt->offset) ||
+ (idx - stt->offset + npages > stt->size) ||
+ (idx + npages < idx))
+ return H_PARAMETER;
+
+ return H_SUCCESS;
+ }
+ EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
+
+ /*
+ * Validates TCE address.
+ * At the moment flags and page mask are validated.
+ * As the host kernel does not access those addresses (just puts them
+ * to the table and user space is supposed to process them), we can skip
+ * checking other things (such as TCE is a guest RAM address or the page
+ * was actually allocated).
+ *
+ * WARNING: This will be called in real-mode on HV KVM and virtual
+ * mode on PR KVM
+ */
+ long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce)
+ {
+ unsigned long page_mask = ~((1ULL << stt->page_shift) - 1);
+ unsigned long mask = ~(page_mask | TCE_PCI_WRITE | TCE_PCI_READ);
+
+ if (tce & mask)
+ return H_PARAMETER;
+
+ return H_SUCCESS;
+ }
+ EXPORT_SYMBOL_GPL(kvmppc_tce_validate);
+
+ /* Note on the use of page_address() in real mode,
+ *
+ * It is safe to use page_address() in real mode on ppc64 because
+ * page_address() is always defined as lowmem_page_address()
+ * which returns __va(PFN_PHYS(page_to_pfn(page))) which is arithmetic
+ * operation and does not access page struct.
+ *
+ * Theoretically page_address() could be defined different
+ * but either WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL
+ * would have to be enabled.
+ * WANT_PAGE_VIRTUAL is never enabled on ppc32/ppc64,
+ * HASHED_PAGE_VIRTUAL could be enabled for ppc32 only and only
+ * if CONFIG_HIGHMEM is defined. As CONFIG_SPARSEMEM_VMEMMAP
+ * is not expected to be enabled on ppc32, page_address()
+ * is safe for ppc32 as well.
+ *
+ * WARNING: This will be called in real-mode on HV KVM and virtual
+ * mode on PR KVM
+ */
+ static u64 *kvmppc_page_address(struct page *page)
+ {
+ #if defined(HASHED_PAGE_VIRTUAL) || defined(WANT_PAGE_VIRTUAL)
+ #error TODO: fix to avoid page_address() here
+ #endif
+ return (u64 *) page_address(page);
+ }
+
+ /*
+ * Handles TCE requests for emulated devices.
+ * Puts guest TCE values to the table and expects user space to convert them.
+ * Called in both real and virtual modes.
+ * Cannot fail so kvmppc_tce_validate must be called before it.
+ *
+ * WARNING: This will be called in real-mode on HV KVM and virtual
+ * mode on PR KVM
+ */
+ void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+ unsigned long idx, unsigned long tce)
+ {
+ struct page *page;
+ u64 *tbl;
+
+ idx -= stt->offset;
+ page = stt->pages[idx / TCES_PER_PAGE];
+ tbl = kvmppc_page_address(page);
+
+ tbl[idx % TCES_PER_PAGE] = tce;
+ }
+ EXPORT_SYMBOL_GPL(kvmppc_tce_put);
+
+ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
+ unsigned long *ua, unsigned long **prmap)
+ {
+ unsigned long gfn = gpa >> PAGE_SHIFT;
+ struct kvm_memory_slot *memslot;
+
+ memslot = search_memslots(kvm_memslots(kvm), gfn);
+ if (!memslot)
+ return -EINVAL;
+
+ *ua = __gfn_to_hva_memslot(memslot, gfn) |
+ (gpa & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ if (prmap)
+ *prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
+ #endif
+
+ return 0;
+ }
+ EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
+
+ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+ unsigned long ioba, unsigned long tce)
+ {
+ struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+ long ret;
+
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */
- list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
- if (stt->liobn == liobn) {
- unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
- struct page *page;
- u64 *tbl;
-
- /* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p window_size=0x%x\n", */
- /* liobn, stt, stt->window_size); */
- if (ioba >= stt->window_size)
- return H_PARAMETER;
-
- page = stt->pages[idx / TCES_PER_PAGE];
- tbl = (u64 *)page_address(page);
-
- /* FIXME: Need to validate the TCE itself */
- /* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */
- tbl[idx % TCES_PER_PAGE] = tce;
- return H_SUCCESS;
- }
- }
+ if (!stt)
+ return H_TOO_HARD;
+
+ ret = kvmppc_ioba_validate(stt, ioba, 1);
+ if (ret != H_SUCCESS)
+ return ret;
- /* Didn't find the liobn, punt it to userspace */
- return H_TOO_HARD;
+ ret = kvmppc_tce_validate(stt, tce);
+ if (ret != H_SUCCESS)
+ return ret;
+
+ kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+
+ return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
- long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
- unsigned long ioba)
+ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
+ unsigned long ua, unsigned long *phpa)
+ {
+ pte_t *ptep, pte;
+ unsigned shift = 0;
+
+ ptep = __find_linux_pte_or_hugepte(vcpu->arch.pgdir, ua, NULL, &shift);
+ if (!ptep || !pte_present(*ptep))
+ return -ENXIO;
+ pte = *ptep;
+
+ if (!shift)
+ shift = PAGE_SHIFT;
+
+ /* Avoid handling anything potentially complicated in realmode */
+ if (shift > PAGE_SHIFT)
+ return -EAGAIN;
+
+ if (!pte_young(pte))
+ return -EAGAIN;
+
+ *phpa = (pte_pfn(pte) << PAGE_SHIFT) | (ua & ((1ULL << shift) - 1)) |
+ (ua & ~PAGE_MASK);
+
+ return 0;
+ }
+
+ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_list, unsigned long npages)
{
- struct kvm *kvm = vcpu->kvm;
struct kvmppc_spapr_tce_table *stt;
+ long i, ret = H_SUCCESS;
+ unsigned long tces, entry, ua = 0;
+ unsigned long *rmap = NULL;
+
+ stt = kvmppc_find_table(vcpu, liobn);
+ if (!stt)
+ return H_TOO_HARD;
+
+ entry = ioba >> stt->page_shift;
+ /*
+ * The spec says that the maximum size of the list is 512 TCEs
+ * so the whole table addressed resides in 4K page
+ */
+ if (npages > 512)
+ return H_PARAMETER;
+
+ if (tce_list & (SZ_4K - 1))
+ return H_PARAMETER;
+
+ ret = kvmppc_ioba_validate(stt, ioba, npages);
+ if (ret != H_SUCCESS)
+ return ret;
- list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
- if (stt->liobn == liobn) {
- unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
- struct page *page;
- u64 *tbl;
+ if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+ return H_TOO_HARD;
- if (ioba >= stt->window_size)
- return H_PARAMETER;
+ rmap = (void *) vmalloc_to_phys(rmap);
- page = stt->pages[idx / TCES_PER_PAGE];
- tbl = (u64 *)page_address(page);
+ /*
+ * Synchronize with the MMU notifier callbacks in
+ * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
+ * While we have the rmap lock, code running on other CPUs
+ * cannot finish unmapping the host real page that backs
+ * this guest real page, so we are OK to access the host
+ * real page.
+ */
+ lock_rmap(rmap);
+ if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
+ ret = H_TOO_HARD;
+ goto unlock_exit;
+ }
+
+ for (i = 0; i < npages; ++i) {
+ unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
+
+ ret = kvmppc_tce_validate(stt, tce);
+ if (ret != H_SUCCESS)
+ goto unlock_exit;
- vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
- return H_SUCCESS;
- }
+ kvmppc_tce_put(stt, entry + i, tce);
}
- /* Didn't find the liobn, punt it to userspace */
- return H_TOO_HARD;
+ unlock_exit:
+ unlock_rmap(rmap);
+
+ return ret;
+ }
+
+ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+ unsigned long liobn, unsigned long ioba,
+ unsigned long tce_value, unsigned long npages)
+ {
+ struct kvmppc_spapr_tce_table *stt;
+ long i, ret;
+
+ stt = kvmppc_find_table(vcpu, liobn);
+ if (!stt)
+ return H_TOO_HARD;
+
+ ret = kvmppc_ioba_validate(stt, ioba, npages);
+ if (ret != H_SUCCESS)
+ return ret;
+
+ /* Check permission bits only to allow userspace poison TCE for debug */
+ if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
+ return H_PARAMETER;
+
+ for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
+ kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
+
+ return H_SUCCESS;
+ }
+ EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce);
+
+ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+ unsigned long ioba)
+ {
+ struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+ long ret;
+ unsigned long idx;
+ struct page *page;
+ u64 *tbl;
+
+ if (!stt)
+ return H_TOO_HARD;
+
+ ret = kvmppc_ioba_validate(stt, ioba, 1);
+ if (ret != H_SUCCESS)
+ return ret;
+
+ idx = (ioba >> stt->page_shift) - stt->offset;
+ page = stt->pages[idx / TCES_PER_PAGE];
+ tbl = (u64 *)page_address(page);
+
+ vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
+
+ return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);
+
+ #endif /* KVM_BOOK3S_HV_POSSIBLE */
module_param(target_smt_mode, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
+ #ifdef CONFIG_KVM_XICS
+ static struct kernel_param_ops module_param_ops = {
+ .set = param_set_int,
+ .get = param_get_int,
+ };
+
+ module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
+ S_IRUGO | S_IWUSR);
+ MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
+ #endif
+
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
int cpu;
- wait_queue_head_t *wqp;
+ struct swait_queue_head *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
- if (waitqueue_active(wqp)) {
- wake_up_interruptible(wqp);
+ if (swait_active(wqp)) {
+ swake_up(wqp);
++vcpu->stat.halt_wakeup;
}
tvcpu->arch.prodded = 1;
smp_mb();
if (vcpu->arch.ceded) {
- if (waitqueue_active(&vcpu->wq)) {
- wake_up_interruptible(&vcpu->wq);
+ if (swait_active(&vcpu->wq)) {
+ swake_up(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
if (kvmppc_xics_enabled(vcpu)) {
ret = kvmppc_xics_hcall(vcpu, req);
break;
- } /* fallthrough */
+ }
+ return RESUME_HOST;
+ case H_PUT_TCE:
+ ret = kvmppc_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_PUT_TCE_INDIRECT:
+ ret = kvmppc_h_put_tce_indirect(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6),
+ kvmppc_get_gpr(vcpu, 7));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_STUFF_TCE:
+ ret = kvmppc_h_stuff_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6),
+ kvmppc_get_gpr(vcpu, 7));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
default:
return RESUME_HOST;
}
INIT_LIST_HEAD(&vcore->runnable_threads);
spin_lock_init(&vcore->lock);
spin_lock_init(&vcore->stoltb_lock);
- init_waitqueue_head(&vcore->wq);
+ init_swait_queue_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
vcore->lpcr = kvm->arch.lpcr;
vcore->first_vcpuid = core * threads_per_subcore;
spin_unlock(&vc->lock);
}
+ /*
+ * Clear core from the list of active host cores as we are about to
+ * enter the guest. Only do this if it is the primary thread of the
+ * core (not if a subcore) that is entering the guest.
+ */
+ static inline void kvmppc_clear_host_core(int cpu)
+ {
+ int core;
+
+ if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
+ return;
+ /*
+ * Memory barrier can be omitted here as we will do a smp_wmb()
+ * later in kvmppc_start_thread and we need ensure that state is
+ * visible to other CPUs only after we enter guest.
+ */
+ core = cpu >> threads_shift;
+ kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0;
+ }
+
+ /*
+ * Advertise this core as an active host core since we exited the guest
+ * Only need to do this if it is the primary thread of the core that is
+ * exiting.
+ */
+ static inline void kvmppc_set_host_core(int cpu)
+ {
+ int core;
+
+ if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
+ return;
+
+ /*
+ * Memory barrier can be omitted here because we do a spin_unlock
+ * immediately after this which provides the memory barrier.
+ */
+ core = cpu >> threads_shift;
+ kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1;
+ }
+
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
}
}
+ kvmppc_clear_host_core(pcpu);
+
/* Start all the threads */
active = 0;
for (sub = 0; sub < core_info.n_subcores; ++sub) {
kvmppc_ipi_thread(pcpu + i);
}
+ kvmppc_set_host_core(pcpu);
+
spin_unlock(&vc->lock);
/* make sure updates to secondary vcpu structs are visible now */
{
struct kvm_vcpu *vcpu;
int do_sleep = 1;
+ DECLARE_SWAITQUEUE(wait);
- DEFINE_WAIT(wait);
-
- prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
/*
* Check one last time for pending exceptions and ceded state after
}
if (!do_sleep) {
- finish_wait(&vc->wq, &wait);
+ finish_swait(&vc->wq, &wait);
return;
}
trace_kvmppc_vcore_blocked(vc, 0);
spin_unlock(&vc->lock);
schedule();
- finish_wait(&vc->wq, &wait);
+ finish_swait(&vc->wq, &wait);
spin_lock(&vc->lock);
vc->vcore_state = VCORE_INACTIVE;
trace_kvmppc_vcore_blocked(vc, 1);
kvmppc_start_thread(vcpu, vc);
trace_kvm_guest_enter(vcpu);
} else if (vc->vcore_state == VCORE_SLEEPING) {
- wake_up(&vc->wq);
+ swake_up(&vc->wq);
}
}
goto out_srcu;
}
+ #ifdef CONFIG_KVM_XICS
+ static int kvmppc_cpu_notify(struct notifier_block *self, unsigned long action,
+ void *hcpu)
+ {
+ unsigned long cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+ kvmppc_set_host_core(cpu);
+ break;
+
+ #ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
+ kvmppc_clear_host_core(cpu);
+ break;
+ #endif
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+ }
+
+ static struct notifier_block kvmppc_cpu_notifier = {
+ .notifier_call = kvmppc_cpu_notify,
+ };
+
+ /*
+ * Allocate a per-core structure for managing state about which cores are
+ * running in the host versus the guest and for exchanging data between
+ * real mode KVM and CPU running in the host.
+ * This is only done for the first VM.
+ * The allocated structure stays even if all VMs have stopped.
+ * It is only freed when the kvm-hv module is unloaded.
+ * It's OK for this routine to fail, we just don't support host
+ * core operations like redirecting H_IPI wakeups.
+ */
+ void kvmppc_alloc_host_rm_ops(void)
+ {
+ struct kvmppc_host_rm_ops *ops;
+ unsigned long l_ops;
+ int cpu, core;
+ int size;
+
+ /* Not the first time here ? */
+ if (kvmppc_host_rm_ops_hv != NULL)
+ return;
+
+ ops = kzalloc(sizeof(struct kvmppc_host_rm_ops), GFP_KERNEL);
+ if (!ops)
+ return;
+
+ size = cpu_nr_cores() * sizeof(struct kvmppc_host_rm_core);
+ ops->rm_core = kzalloc(size, GFP_KERNEL);
+
+ if (!ops->rm_core) {
+ kfree(ops);
+ return;
+ }
+
+ get_online_cpus();
+
+ for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) {
+ if (!cpu_online(cpu))
+ continue;
+
+ core = cpu >> threads_shift;
+ ops->rm_core[core].rm_state.in_host = 1;
+ }
+
+ ops->vcpu_kick = kvmppc_fast_vcpu_kick_hv;
+
+ /*
+ * Make the contents of the kvmppc_host_rm_ops structure visible
+ * to other CPUs before we assign it to the global variable.
+ * Do an atomic assignment (no locks used here), but if someone
+ * beats us to it, just free our copy and return.
+ */
+ smp_wmb();
+ l_ops = (unsigned long) ops;
+
+ if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) {
+ put_online_cpus();
+ kfree(ops->rm_core);
+ kfree(ops);
+ return;
+ }
+
+ register_cpu_notifier(&kvmppc_cpu_notifier);
+
+ put_online_cpus();
+ }
+
+ void kvmppc_free_host_rm_ops(void)
+ {
+ if (kvmppc_host_rm_ops_hv) {
+ unregister_cpu_notifier(&kvmppc_cpu_notifier);
+ kfree(kvmppc_host_rm_ops_hv->rm_core);
+ kfree(kvmppc_host_rm_ops_hv);
+ kvmppc_host_rm_ops_hv = NULL;
+ }
+ }
+ #endif
+
static int kvmppc_core_init_vm_hv(struct kvm *kvm)
{
unsigned long lpcr, lpid;
return -ENOMEM;
kvm->arch.lpid = lpid;
+ kvmppc_alloc_host_rm_ops();
+
/*
* Since we don't flush the TLB when tearing down a VM,
* and this lpid might have previously been used,
static void kvmppc_book3s_exit_hv(void)
{
+ kvmppc_free_host_rm_ops();
kvmppc_hv_ops = NULL;
}
#include <asm/asm-offsets.h>
#include <asm/exception-64s.h>
#include <asm/kvm_book3s_asm.h>
-#include <asm/mmu-hash64.h>
+#include <asm/book3s/64/mmu-hash.h>
#include <asm/tm.h>
#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
.long 0 /* 0x12c */
.long 0 /* 0x130 */
.long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
- .long 0 /* 0x138 */
- .long 0 /* 0x13c */
+ .long DOTSYM(kvmppc_h_stuff_tce) - hcall_real_table
+ .long DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table
.long 0 /* 0x140 */
.long 0 /* 0x144 */
.long 0 /* 0x148 */
__u8 data[256];
} __packed;
- struct kvm_s390_vregs {
- __vector128 vrs[32];
- __u8 reserved200[512]; /* for future vector expansion */
- } __packed;
-
struct sie_page {
struct kvm_s390_sie_block sie_block;
__u8 reserved200[1024]; /* 0x0200 */
struct kvm_s390_itdb itdb; /* 0x0600 */
- __u8 reserved700[1280]; /* 0x0700 */
- struct kvm_s390_vregs vregs; /* 0x0c00 */
+ __u8 reserved700[2304]; /* 0x0700 */
} __packed;
struct kvm_vcpu_stat {
struct kvm_s390_local_interrupt {
spinlock_t lock;
struct kvm_s390_float_interrupt *float_int;
- wait_queue_head_t *wq;
+ struct swait_queue_head *wq;
atomic_t *cpuflags;
DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
struct kvm_s390_irq_payload irq;
set_intercept_indicators_stop(vcpu);
}
- static u16 get_ilc(struct kvm_vcpu *vcpu)
- {
- switch (vcpu->arch.sie_block->icptcode) {
- case ICPT_INST:
- case ICPT_INSTPROGI:
- case ICPT_OPEREXC:
- case ICPT_PARTEXEC:
- case ICPT_IOINST:
- /* last instruction only stored for these icptcodes */
- return insn_length(vcpu->arch.sie_block->ipa >> 8);
- case ICPT_PROGI:
- return vcpu->arch.sie_block->pgmilc;
- default:
- return 0;
- }
- }
-
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_pgm_info pgm_info;
int rc = 0, nullifying = false;
- u16 ilc = get_ilc(vcpu);
+ u16 ilen;
spin_lock(&li->lock);
pgm_info = li->irq.pgm;
memset(&li->irq.pgm, 0, sizeof(pgm_info));
spin_unlock(&li->lock);
- VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
- pgm_info.code, ilc);
+ ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK;
+ VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d",
+ pgm_info.code, ilen);
vcpu->stat.deliver_program_int++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
pgm_info.code, 0);
(u8 *) __LC_PER_ACCESS_ID);
}
- if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
- kvm_s390_rewind_psw(vcpu, ilc);
+ if (nullifying && !(pgm_info.flags & KVM_S390_PGM_FLAGS_NO_REWIND))
+ kvm_s390_rewind_psw(vcpu, ilen);
- rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
+ /* bit 1+2 of the target are the ilc, so we can directly use ilen */
+ rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC);
rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
(u64 *) __LC_LAST_BREAK);
rc |= put_guest_lc(vcpu, pgm_info.code,
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
- if (waitqueue_active(&vcpu->wq)) {
+ if (swait_active(&vcpu->wq)) {
/*
* The vcpu gave up the cpu voluntarily, mark it as a good
* yield-candidate.
*/
vcpu->preempted = true;
- wake_up_interruptible(&vcpu->wq);
+ swake_up(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
irq->u.pgm.code, 0);
+ if (!(irq->u.pgm.flags & KVM_S390_PGM_FLAGS_ILC_VALID)) {
+ /* auto detection if no valid ILC was given */
+ irq->u.pgm.flags &= ~KVM_S390_PGM_FLAGS_ILC_MASK;
+ irq->u.pgm.flags |= kvm_s390_get_ilen(vcpu);
+ irq->u.pgm.flags |= KVM_S390_PGM_FLAGS_ILC_VALID;
+ }
+
if (irq->u.pgm.code == PGM_PER) {
li->irq.pgm.code |= PGM_PER;
+ li->irq.pgm.flags = irq->u.pgm.flags;
/* only modify PER related information */
li->irq.pgm.per_address = irq->u.pgm.per_address;
li->irq.pgm.per_code = irq->u.pgm.per_code;
} else if (!(irq->u.pgm.code & PGM_PER)) {
li->irq.pgm.code = (li->irq.pgm.code & PGM_PER) |
irq->u.pgm.code;
+ li->irq.pgm.flags = irq->u.pgm.flags;
/* only modify non-PER information */
li->irq.pgm.trans_exc_code = irq->u.pgm.trans_exc_code;
li->irq.pgm.mon_code = irq->u.pgm.mon_code;
struct kvm_cpuid_entry2 *feat;
u32 v = APIC_VERSION;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return;
feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
{
- int highest_irr;
-
/* This may race with setting of irr in __apic_accept_irq() and
* value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq
* will cause vmexit immediately and the value will be recalculated
* on the next vmentry.
*/
- if (!kvm_vcpu_has_lapic(vcpu))
- return 0;
- highest_irr = apic_find_highest_irr(vcpu->arch.apic);
-
- return highest_irr;
+ return apic_find_highest_irr(vcpu->arch.apic);
}
static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
int vector, int level, int trig_mode,
- unsigned long *dest_map);
+ struct dest_map *dest_map);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
- unsigned long *dest_map)
+ struct dest_map *dest_map)
{
struct kvm_lapic *apic = vcpu->arch.apic;
}
}
+ int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
+ const unsigned long *bitmap, u32 bitmap_size)
+ {
+ u32 mod;
+ int i, idx = -1;
+
+ mod = vector % dest_vcpus;
+
+ for (i = 0; i <= mod; i++) {
+ idx = find_next_bit(bitmap, bitmap_size, idx + 1);
+ BUG_ON(idx == bitmap_size);
+ }
+
+ return idx;
+ }
+
+ static void kvm_apic_disabled_lapic_found(struct kvm *kvm)
+ {
+ if (!kvm->arch.disabled_lapic_found) {
+ kvm->arch.disabled_lapic_found = true;
+ printk(KERN_INFO
+ "Disabled LAPIC found during irq injection\n");
+ }
+ }
+
bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
- struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map)
+ struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map)
{
struct kvm_apic_map *map;
unsigned long bitmap = 1;
dst = map->logical_map[cid];
- if (kvm_lowest_prio_delivery(irq)) {
+ if (!kvm_lowest_prio_delivery(irq))
+ goto set_irq;
+
+ if (!kvm_vector_hashing_enabled()) {
int l = -1;
for_each_set_bit(i, &bitmap, 16) {
if (!dst[i])
continue;
if (l < 0)
l = i;
- else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
+ else if (kvm_apic_compare_prio(dst[i]->vcpu,
+ dst[l]->vcpu) < 0)
l = i;
}
-
bitmap = (l >= 0) ? 1 << l : 0;
+ } else {
+ int idx;
+ unsigned int dest_vcpus;
+
+ dest_vcpus = hweight16(bitmap);
+ if (dest_vcpus == 0)
+ goto out;
+
+ idx = kvm_vector_to_index(irq->vector,
+ dest_vcpus, &bitmap, 16);
+
+ if (!dst[idx]) {
+ kvm_apic_disabled_lapic_found(kvm);
+ goto out;
+ }
+
+ bitmap = (idx >= 0) ? 1 << idx : 0;
}
}
+ set_irq:
for_each_set_bit(i, &bitmap, 16) {
if (!dst[i])
continue;
return ret;
}
+ /*
+ * This routine tries to handler interrupts in posted mode, here is how
+ * it deals with different cases:
+ * - For single-destination interrupts, handle it in posted mode
+ * - Else if vector hashing is enabled and it is a lowest-priority
+ * interrupt, handle it in posted mode and use the following mechanism
+ * to find the destinaiton vCPU.
+ * 1. For lowest-priority interrupts, store all the possible
+ * destination vCPUs in an array.
+ * 2. Use "guest vector % max number of destination vCPUs" to find
+ * the right destination vCPU in the array for the lowest-priority
+ * interrupt.
+ * - Otherwise, use remapped mode to inject the interrupt.
+ */
bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu)
{
if (cid >= ARRAY_SIZE(map->logical_map))
goto out;
- for_each_set_bit(i, &bitmap, 16) {
- dst = map->logical_map[cid][i];
- if (++r == 2)
+ if (kvm_vector_hashing_enabled() &&
+ kvm_lowest_prio_delivery(irq)) {
+ int idx;
+ unsigned int dest_vcpus;
+
+ dest_vcpus = hweight16(bitmap);
+ if (dest_vcpus == 0)
goto out;
- }
- if (dst && kvm_apic_present(dst->vcpu))
+ idx = kvm_vector_to_index(irq->vector, dest_vcpus,
+ &bitmap, 16);
+
+ dst = map->logical_map[cid][idx];
+ if (!dst) {
+ kvm_apic_disabled_lapic_found(kvm);
+ goto out;
+ }
+
*dest_vcpu = dst->vcpu;
- else
- goto out;
+ } else {
+ for_each_set_bit(i, &bitmap, 16) {
+ dst = map->logical_map[cid][i];
+ if (++r == 2)
+ goto out;
+ }
+
+ if (dst && kvm_apic_present(dst->vcpu))
+ *dest_vcpu = dst->vcpu;
+ else
+ goto out;
+ }
}
ret = true;
*/
static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
int vector, int level, int trig_mode,
- unsigned long *dest_map)
+ struct dest_map *dest_map)
{
int result = 0;
struct kvm_vcpu *vcpu = apic->vcpu;
result = 1;
- if (dest_map)
- __set_bit(vcpu->vcpu_id, dest_map);
+ if (dest_map) {
+ __set_bit(vcpu->vcpu_id, dest_map->map);
+ dest_map->vectors[vcpu->vcpu_id] = vector;
+ }
if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) {
if (trig_mode)
static void apic_timer_expired(struct kvm_lapic *apic)
{
struct kvm_vcpu *vcpu = apic->vcpu;
- wait_queue_head_t *q = &vcpu->wq;
+ struct swait_queue_head *q = &vcpu->wq;
struct kvm_timer *ktimer = &apic->lapic_timer;
if (atomic_read(&apic->lapic_timer.pending))
atomic_inc(&apic->lapic_timer.pending);
kvm_set_pending_timer(vcpu);
- if (waitqueue_active(q))
- wake_up_interruptible(q);
+ if (swait_active(q))
+ swake_up(q);
if (apic_lvtt_tscdeadline(apic))
ktimer->expired_tscdeadline = ktimer->tscdeadline;
struct kvm_lapic *apic = vcpu->arch.apic;
u64 guest_tsc, tsc_deadline;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return;
if (apic->lapic_timer.expired_tscdeadline == 0)
void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
{
- if (kvm_vcpu_has_lapic(vcpu))
- apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
+ apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
}
EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+ if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
apic_lvtt_period(apic))
return 0;
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+ if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
apic_lvtt_period(apic))
return;
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu))
- return;
-
apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
| (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4));
}
{
u64 tpr;
- if (!kvm_vcpu_has_lapic(vcpu))
- return 0;
-
tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI);
return (tpr & 0xf0) >> 4;
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (kvm_vcpu_has_lapic(vcpu) && apic_enabled(apic) &&
- apic_lvt_enabled(apic, APIC_LVTT))
+ if (apic_enabled(apic) && apic_lvt_enabled(apic, APIC_LVTT))
return atomic_read(&apic->lapic_timer.pending);
return 0;
struct kvm_lapic *apic = vcpu->arch.apic;
int highest_irr;
- if (!kvm_vcpu_has_lapic(vcpu) || !apic_enabled(apic))
+ if (!apic_enabled(apic))
return -1;
apic_update_ppr(apic);
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu))
- return;
-
if (atomic_read(&apic->lapic_timer.pending) > 0) {
kvm_apic_local_deliver(apic, APIC_LVTT);
if (apic_lvtt_tscdeadline(apic))
{
struct hrtimer *timer;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return;
timer = &vcpu->arch.apic->lapic_timer.timer;
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return 1;
/* if this is ICR write vector before command */
struct kvm_lapic *apic = vcpu->arch.apic;
u32 low, high = 0;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return 1;
if (apic_reg_read(apic, reg, 4, &low))
u8 sipi_vector;
unsigned long pe;
- if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
+ if (!lapic_in_kernel(vcpu) || !apic->pending_events)
return;
/*
#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/vmx.h>
+ #include <asm/kvm_page_track.h>
/*
* When setting this variable to true it enables Two-Dimensional-Paging
static bool spte_has_volatile_bits(u64 spte)
{
/*
- * Always atomicly update spte if it can be updated
+ * Always atomically update spte if it can be updated
* out of mmu-lock, it can ensure dirty bit is not lost,
* also, it can help us to get a stable is_writable_pte()
* to ensure tlb flush is not missed.
/*
* For the spte updated out of mmu-lock is safe, since
- * we always atomicly update it, see the comments in
+ * we always atomically update it, see the comments in
* spte_has_volatile_bits().
*/
if (spte_is_locklessly_modifiable(old_spte) &&
return &slot->arch.lpage_info[level - 2][idx];
}
+ static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot,
+ gfn_t gfn, int count)
+ {
+ struct kvm_lpage_info *linfo;
+ int i;
+
+ for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
+ linfo = lpage_info_slot(gfn, slot, i);
+ linfo->disallow_lpage += count;
+ WARN_ON(linfo->disallow_lpage < 0);
+ }
+ }
+
+ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
+ {
+ update_gfn_disallow_lpage_count(slot, gfn, 1);
+ }
+
+ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
+ {
+ update_gfn_disallow_lpage_count(slot, gfn, -1);
+ }
+
static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
- struct kvm_lpage_info *linfo;
gfn_t gfn;
- int i;
+ kvm->arch.indirect_shadow_pages++;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
- for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
- linfo = lpage_info_slot(gfn, slot, i);
- linfo->write_count += 1;
- }
- kvm->arch.indirect_shadow_pages++;
+
+ /* the non-leaf shadow pages are keeping readonly. */
+ if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+ return kvm_slot_page_track_add_page(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
+ kvm_mmu_gfn_disallow_lpage(slot, gfn);
}
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
- struct kvm_lpage_info *linfo;
gfn_t gfn;
- int i;
+ kvm->arch.indirect_shadow_pages--;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
- for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
- linfo = lpage_info_slot(gfn, slot, i);
- linfo->write_count -= 1;
- WARN_ON(linfo->write_count < 0);
- }
- kvm->arch.indirect_shadow_pages--;
+ if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+ return kvm_slot_page_track_remove_page(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
+ kvm_mmu_gfn_allow_lpage(slot, gfn);
}
- static int __has_wrprotected_page(gfn_t gfn, int level,
- struct kvm_memory_slot *slot)
+ static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
+ struct kvm_memory_slot *slot)
{
struct kvm_lpage_info *linfo;
if (slot) {
linfo = lpage_info_slot(gfn, slot, level);
- return linfo->write_count;
+ return !!linfo->disallow_lpage;
}
- return 1;
+ return true;
}
- static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
+ static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
+ int level)
{
struct kvm_memory_slot *slot;
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
- return __has_wrprotected_page(gfn, level, slot);
+ return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
}
static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
- if (__has_wrprotected_page(large_gfn, level, slot))
+ if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot))
break;
return level - 1;
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
- static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
+ struct kvm_memory_slot *slot, u64 gfn)
{
- struct kvm_memory_slot *slot;
struct kvm_rmap_head *rmap_head;
int i;
bool write_protected = false;
- slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-
for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
rmap_head = __gfn_to_rmap(gfn, i, slot);
- write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true);
+ write_protected |= __rmap_write_protect(kvm, rmap_head, true);
}
return write_protected;
}
+ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+ {
+ struct kvm_memory_slot *slot;
+
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn);
+ }
+
static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
u64 *sptep;
return nr_unsync_leaf;
}
+ #define INVALID_INDEX (-1)
+
static int mmu_unsync_walk(struct kvm_mmu_page *sp,
struct kvm_mmu_pages *pvec)
{
+ pvec->nr = 0;
if (!sp->unsync_children)
return 0;
- mmu_pages_add(pvec, sp, 0);
+ mmu_pages_add(pvec, sp, INVALID_INDEX);
return __mmu_unsync_walk(sp, pvec);
}
}
struct mmu_page_path {
- struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1];
- unsigned int idx[PT64_ROOT_LEVEL-1];
+ struct kvm_mmu_page *parent[PT64_ROOT_LEVEL];
+ unsigned int idx[PT64_ROOT_LEVEL];
};
#define for_each_sp(pvec, sp, parents, i) \
- for (i = mmu_pages_next(&pvec, &parents, -1), \
- sp = pvec.page[i].sp; \
+ for (i = mmu_pages_first(&pvec, &parents); \
i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \
i = mmu_pages_next(&pvec, &parents, i))
for (n = i+1; n < pvec->nr; n++) {
struct kvm_mmu_page *sp = pvec->page[n].sp;
+ unsigned idx = pvec->page[n].idx;
+ int level = sp->role.level;
- if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
- parents->idx[0] = pvec->page[n].idx;
- return n;
- }
+ parents->idx[level-1] = idx;
+ if (level == PT_PAGE_TABLE_LEVEL)
+ break;
- parents->parent[sp->role.level-2] = sp;
- parents->idx[sp->role.level-1] = pvec->page[n].idx;
+ parents->parent[level-2] = sp;
}
return n;
}
+ static int mmu_pages_first(struct kvm_mmu_pages *pvec,
+ struct mmu_page_path *parents)
+ {
+ struct kvm_mmu_page *sp;
+ int level;
+
+ if (pvec->nr == 0)
+ return 0;
+
+ WARN_ON(pvec->page[0].idx != INVALID_INDEX);
+
+ sp = pvec->page[0].sp;
+ level = sp->role.level;
+ WARN_ON(level == PT_PAGE_TABLE_LEVEL);
+
+ parents->parent[level-2] = sp;
+
+ /* Also set up a sentinel. Further entries in pvec are all
+ * children of sp, so this element is never overwritten.
+ */
+ parents->parent[level-1] = NULL;
+ return mmu_pages_next(pvec, parents, 0);
+ }
+
static void mmu_pages_clear_parents(struct mmu_page_path *parents)
{
struct kvm_mmu_page *sp;
do {
unsigned int idx = parents->idx[level];
-
sp = parents->parent[level];
if (!sp)
return;
+ WARN_ON(idx == INVALID_INDEX);
clear_unsync_child_bit(sp, idx);
level++;
- } while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children);
- }
-
- static void kvm_mmu_pages_init(struct kvm_mmu_page *parent,
- struct mmu_page_path *parents,
- struct kvm_mmu_pages *pvec)
- {
- parents->parent[parent->role.level-1] = NULL;
- pvec->nr = 0;
+ } while (!sp->unsync_children);
}
static void mmu_sync_children(struct kvm_vcpu *vcpu,
struct kvm_mmu_pages pages;
LIST_HEAD(invalid_list);
- kvm_mmu_pages_init(parent, &parents, &pages);
while (mmu_unsync_walk(parent, &pages)) {
bool protected = false;
}
kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
cond_resched_lock(&vcpu->kvm->mmu_lock);
- kvm_mmu_pages_init(parent, &parents, &pages);
}
}
static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
{
- sp->write_flooding_count = 0;
+ atomic_set(&sp->write_flooding_count, 0);
}
static void clear_sp_write_flooding_count(u64 *spte)
hlist_add_head(&sp->hash_link,
&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
if (!direct) {
- if (rmap_write_protect(vcpu, gfn))
+ /*
+ * we should do write protection before syncing pages
+ * otherwise the content of the synced shadow page may
+ * be inconsistent with guest page table.
+ */
+ account_shadowed(vcpu->kvm, sp);
+ if (level == PT_PAGE_TABLE_LEVEL &&
+ rmap_write_protect(vcpu, gfn))
kvm_flush_remote_tlbs(vcpu->kvm);
+
if (level > PT_PAGE_TABLE_LEVEL && need_sync)
kvm_sync_pages(vcpu, gfn);
-
- account_shadowed(vcpu->kvm, sp);
}
sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
clear_page(sp->spt);
if (parent->role.level == PT_PAGE_TABLE_LEVEL)
return 0;
- kvm_mmu_pages_init(parent, &parents, &pages);
while (mmu_unsync_walk(parent, &pages)) {
struct kvm_mmu_page *sp;
mmu_pages_clear_parents(&parents);
zapped++;
}
- kvm_mmu_pages_init(parent, &parents, &pages);
}
return zapped;
if (list_empty(&kvm->arch.active_mmu_pages))
return false;
- sp = list_entry(kvm->arch.active_mmu_pages.prev,
- struct kvm_mmu_page, link);
+ sp = list_last_entry(&kvm->arch.active_mmu_pages,
+ struct kvm_mmu_page, link);
kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
return true;
}
EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
- static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
trace_kvm_mmu_unsync_page(sp);
++vcpu->kvm->stat.mmu_unsync;
kvm_mmu_mark_parents_unsync(sp);
}
- static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
+ static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
+ bool can_unsync)
{
- struct kvm_mmu_page *s;
-
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
- if (s->unsync)
- continue;
- WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
- __kvm_unsync_page(vcpu, s);
- }
- }
+ struct kvm_mmu_page *sp;
- static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
- bool can_unsync)
- {
- struct kvm_mmu_page *s;
- bool need_unsync = false;
+ if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
+ return true;
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
+ for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (!can_unsync)
- return 1;
+ return true;
- if (s->role.level != PT_PAGE_TABLE_LEVEL)
- return 1;
+ if (sp->unsync)
+ continue;
- if (!s->unsync)
- need_unsync = true;
+ WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
+ kvm_unsync_page(vcpu, sp);
}
- if (need_unsync)
- kvm_unsync_pages(vcpu, gfn);
- return 0;
+
+ return false;
}
static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
* be fixed if guest refault.
*/
if (level > PT_PAGE_TABLE_LEVEL &&
- has_wrprotected_page(vcpu, gfn, level))
+ mmu_gfn_lpage_is_disallowed(vcpu, gfn, level))
goto done;
spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
level == PT_PAGE_TABLE_LEVEL &&
PageTransCompound(pfn_to_page(pfn)) &&
- !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
+ !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
unsigned long mask;
/*
* mmu_notifier_retry was successful and we hold the
static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
kvm_pfn_t pfn, unsigned access, int *ret_val)
{
- bool ret = true;
-
/* The pfn is invalid, report the error! */
if (unlikely(is_error_pfn(pfn))) {
*ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
- goto exit;
+ return true;
}
if (unlikely(is_noslot_pfn(pfn)))
vcpu_cache_mmio_info(vcpu, gva, gfn, access);
- ret = false;
- exit:
- return ret;
+ return false;
}
static bool page_fault_can_be_fast(u32 error_code)
return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
}
- static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
if (direct)
return vcpu_match_mmio_gpa(vcpu, addr);
u64 spte;
bool reserved;
- if (quickly_check_mmio_pf(vcpu, addr, direct))
+ if (mmio_info_in_cache(vcpu, addr, direct))
return RET_MMIO_PF_EMULATE;
reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
}
EXPORT_SYMBOL_GPL(handle_mmio_page_fault);
+ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
+ u32 error_code, gfn_t gfn)
+ {
+ if (unlikely(error_code & PFERR_RSVD_MASK))
+ return false;
+
+ if (!(error_code & PFERR_PRESENT_MASK) ||
+ !(error_code & PFERR_WRITE_MASK))
+ return false;
+
+ /*
+ * guest is writing the page which is write tracked which can
+ * not be fixed by page fault handler.
+ */
+ if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
+ return true;
+
+ return false;
+ }
+
+ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
+ {
+ struct kvm_shadow_walk_iterator iterator;
+ u64 spte;
+
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return;
+
+ walk_shadow_page_lockless_begin(vcpu);
+ for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
+ clear_sp_write_flooding_count(iterator.sptep);
+ if (!is_shadow_present_pte(spte))
+ break;
+ }
+ walk_shadow_page_lockless_end(vcpu);
+ }
+
static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
u32 error_code, bool prefault)
{
- gfn_t gfn;
+ gfn_t gfn = gva >> PAGE_SHIFT;
int r;
pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
- if (unlikely(error_code & PFERR_RSVD_MASK)) {
- r = handle_mmio_page_fault(vcpu, gva, true);
-
- if (likely(r != RET_MMIO_PF_INVALID))
- return r;
- }
+ if (page_fault_handle_page_track(vcpu, error_code, gfn))
+ return 1;
r = mmu_topup_memory_caches(vcpu);
if (r)
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
- gfn = gva >> PAGE_SHIFT;
return nonpaging_map(vcpu, gva & PAGE_MASK,
error_code, gfn, prefault);
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
- if (unlikely(error_code & PFERR_RSVD_MASK)) {
- r = handle_mmio_page_fault(vcpu, gpa, true);
-
- if (likely(r != RET_MMIO_PF_INVALID))
- return r;
- }
+ if (page_fault_handle_page_track(vcpu, error_code, gfn))
+ return 1;
r = mmu_topup_memory_caches(vcpu);
if (r)
if (sp->role.level == PT_PAGE_TABLE_LEVEL)
return false;
- return ++sp->write_flooding_count >= 3;
+ atomic_inc(&sp->write_flooding_count);
+ return atomic_read(&sp->write_flooding_count) >= 3;
}
/*
return spte;
}
- void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *new, int bytes)
+ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+ const u8 *new, int bytes)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm_mmu_page *sp;
kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
}
- static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr)
- {
- if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu))
- return vcpu_match_mmio_gpa(vcpu, addr);
-
- return vcpu_match_mmio_gva(vcpu, addr);
- }
-
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
void *insn, int insn_len)
{
int r, emulation_type = EMULTYPE_RETRY;
enum emulation_result er;
+ bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu);
+
+ if (unlikely(error_code & PFERR_RSVD_MASK)) {
+ r = handle_mmio_page_fault(vcpu, cr2, direct);
+ if (r == RET_MMIO_PF_EMULATE) {
+ emulation_type = 0;
+ goto emulate;
+ }
+ if (r == RET_MMIO_PF_RETRY)
+ return 1;
+ if (r < 0)
+ return r;
+ }
r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
if (r < 0)
- goto out;
-
- if (!r) {
- r = 1;
- goto out;
- }
+ return r;
+ if (!r)
+ return 1;
- if (is_mmio_page_fault(vcpu, cr2))
+ if (mmio_info_in_cache(vcpu, cr2, direct))
emulation_type = 0;
-
+ emulate:
er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
switch (er) {
default:
BUG();
}
- out:
- return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
init_kvm_mmu(vcpu);
}
+ void kvm_mmu_init_vm(struct kvm *kvm)
+ {
+ struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+ node->track_write = kvm_mmu_pte_write;
+ kvm_page_track_register_notifier(kvm, node);
+ }
+
+ void kvm_mmu_uninit_vm(struct kvm *kvm)
+ {
+ struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+ kvm_page_track_unregister_notifier(kvm, node);
+ }
+
/* The return value indicates if tlb flush on all vcpus is needed. */
typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
return ret;
kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
- walker->ptes[level] = pte;
+ walker->ptes[level - 1] = pte;
}
return 0;
}
pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
- if (unlikely(error_code & PFERR_RSVD_MASK)) {
- r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu));
- if (likely(r != RET_MMIO_PF_INVALID))
- return r;
-
- /*
- * page fault with PFEC.RSVD = 1 is caused by shadow
- * page fault, should not be used to walk guest page
- * table.
- */
- error_code &= ~PFERR_RSVD_MASK;
- };
-
r = mmu_topup_memory_caches(vcpu);
if (r)
return r;
+ /*
+ * If PFEC.RSVD is set, this is a shadow page fault.
+ * The bit needs to be cleared before walking guest page tables.
+ */
+ error_code &= ~PFERR_RSVD_MASK;
+
/*
* Look up the guest pte for the faulting address.
*/
return 0;
}
+ if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) {
+ shadow_page_table_clear_flood(vcpu, addr);
+ return 1;
+ }
+
vcpu->arch.write_fault_to_shadow_pgtable = false;
is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
/* Support for PML */
#define PML_ENTITY_NUM 512
struct page *pml_pg;
+
+ u64 current_tsc_ratio;
};
enum segment_cache_field {
MSR_EFER, MSR_TSC_AUX, MSR_STAR,
};
- static inline bool is_page_fault(u32 intr_info)
+ static inline bool is_exception_n(u32 intr_info, u8 vector)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
+ (INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+ }
+
+ static inline bool is_debug(u32 intr_info)
+ {
+ return is_exception_n(intr_info, DB_VECTOR);
+ }
+
+ static inline bool is_breakpoint(u32 intr_info)
+ {
+ return is_exception_n(intr_info, BP_VECTOR);
+ }
+
+ static inline bool is_page_fault(u32 intr_info)
+ {
+ return is_exception_n(intr_info, PF_VECTOR);
}
static inline bool is_no_device(u32 intr_info)
{
- return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
- INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
+ return is_exception_n(intr_info, NM_VECTOR);
}
static inline bool is_invalid_opcode(u32 intr_info)
{
- return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
- INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+ return is_exception_n(intr_info, UD_VECTOR);
}
static inline bool is_external_interrupt(u32 intr_info)
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
- /* Setup TSC multiplier */
- if (cpu_has_vmx_tsc_scaling())
- vmcs_write64(TSC_MULTIPLIER,
- vcpu->arch.tsc_scaling_ratio);
-
vmx->loaded_vmcs->cpu = cpu;
}
+ /* Setup TSC multiplier */
+ if (kvm_has_tsc_control &&
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
+ vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+ }
+
vmx_vcpu_pi_load(vcpu, cpu);
}
return kvm_set_cr4(vcpu, val);
}
-/* called to set cr0 as approriate for clts instruction exit. */
+/* called to set cr0 as appropriate for clts instruction exit. */
static void handle_clts(struct kvm_vcpu *vcpu)
{
if (is_guest_mode(vcpu)) {
}
if (vcpu->guest_debug == 0) {
- u32 cpu_based_vm_exec_control;
-
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_MOV_DR_EXITING);
/*
* No more DR vmexits; force a reload of the debug registers
static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
{
- u32 cpu_based_vm_exec_control;
-
get_debugreg(vcpu->arch.db[0], 0);
get_debugreg(vcpu->arch.db[1], 1);
get_debugreg(vcpu->arch.db[2], 2);
vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
-
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+ vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING);
}
static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
static int handle_vmcall(struct kvm_vcpu *vcpu)
{
- kvm_emulate_hypercall(vcpu);
- return 1;
+ return kvm_emulate_hypercall(vcpu);
}
static int handle_invd(struct kvm_vcpu *vcpu)
if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
/* Recycle the least recently used VMCS. */
- item = list_entry(vmx->nested.vmcs02_pool.prev,
- struct vmcs02_list, list);
+ item = list_last_entry(&vmx->nested.vmcs02_pool,
+ struct vmcs02_list, list);
item->vmptr = vmx->nested.current_vmptr;
list_move(&item->list, &vmx->nested.vmcs02_pool);
return &item->vmcs02;
/* The value to write might be 32 or 64 bits, depending on L1's long
* mode, and eventually we need to write that into a field of several
* possible lengths. The code below first zero-extends the value to 64
- * bit (field_value), and then copies only the approriate number of
+ * bit (field_value), and then copies only the appropriate number of
* bits into the vmcs12 field.
*/
u64 field_value = 0;
else if (is_no_device(intr_info) &&
!(vmcs12->guest_cr0 & X86_CR0_TS))
return false;
+ else if (is_debug(intr_info) &&
+ vcpu->guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+ return false;
+ else if (is_breakpoint(intr_info) &&
+ vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+ return false;
return vmcs12->exception_bitmap &
(1u << (intr_info & INTR_INFO_VECTOR_MASK));
case EXIT_REASON_EXTERNAL_INTERRUPT:
static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
{
u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+ register void *__sp asm(_ASM_SP);
/*
* If external interrupt exists, IF bit is set in rflags/eflags on the
"call *%[entry]\n\t"
:
#ifdef CONFIG_X86_64
- [sp]"=&r"(tmp)
+ [sp]"=&r"(tmp),
#endif
+ "+r"(__sp)
:
[entry]"r"(entry),
[ss]"i"(__KERNEL_DS),
*/
kvm_set_msi_irq(e, &irq);
- if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu))
+ if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+ /*
+ * Make sure the IRTE is in remapped mode if
+ * we don't handle it in posted mode.
+ */
+ ret = irq_set_vcpu_affinity(host_irq, NULL);
+ if (ret < 0) {
+ printk(KERN_INFO
+ "failed to back to remapped mode, irq: %u\n",
+ host_irq);
+ goto out;
+ }
+
continue;
+ }
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
- trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi,
+ trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
if (set)
unsigned int __read_mostly lapic_timer_advance_ns = 0;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+ static bool __read_mostly vector_hashing = true;
+ module_param(vector_hashing, bool, S_IRUGO);
+
static bool __read_mostly backwards_tsc_observed = false;
#define KVM_NR_SHARED_MSRS 16
static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
{
- uint32_t quotient, remainder;
-
- /* Don't try to replace with do_div(), this one calculates
- * "(dividend << 32) / divisor" */
- __asm__ ( "divl %4"
- : "=a" (quotient), "=d" (remainder)
- : "0" (0), "1" (dividend), "r" (divisor) );
- return quotient;
+ do_shl32_div32(dividend, divisor);
+ return dividend;
}
- static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
+ static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz,
s8 *pshift, u32 *pmultiplier)
{
uint64_t scaled64;
uint64_t tps64;
uint32_t tps32;
- tps64 = base_khz * 1000LL;
- scaled64 = scaled_khz * 1000LL;
+ tps64 = base_hz;
+ scaled64 = scaled_hz;
while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
tps64 >>= 1;
shift--;
*pshift = shift;
*pmultiplier = div_frac(scaled64, tps32);
- pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n",
- __func__, base_khz, scaled_khz, shift, *pmultiplier);
+ pr_debug("%s: base_hz %llu => %llu, shift %d, mul %u\n",
+ __func__, base_hz, scaled_hz, shift, *pmultiplier);
}
#ifdef CONFIG_X86_64
return 0;
}
- static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
+ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
{
u32 thresh_lo, thresh_hi;
int use_scaling = 0;
/* tsc_khz can be zero if TSC calibration fails */
- if (this_tsc_khz == 0) {
+ if (user_tsc_khz == 0) {
/* set tsc_scaling_ratio to a safe value */
vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
return -1;
}
/* Compute a scale to convert nanoseconds in TSC cycles */
- kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
+ kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC,
&vcpu->arch.virtual_tsc_shift,
&vcpu->arch.virtual_tsc_mult);
- vcpu->arch.virtual_tsc_khz = this_tsc_khz;
+ vcpu->arch.virtual_tsc_khz = user_tsc_khz;
/*
* Compute the variation in TSC rate which is acceptable
*/
thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm);
thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm);
- if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) {
- pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi);
+ if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) {
+ pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi);
use_scaling = 1;
}
- return set_tsc_khz(vcpu, this_tsc_khz, use_scaling);
+ return set_tsc_khz(vcpu, user_tsc_khz, use_scaling);
}
static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
/*
* GCC likes to generate cmov here, but this branch is extremely
- * predictable (it's just a funciton of time and the likely is
+ * predictable (it's just a function of time and the likely is
* very likely) and there's a data dependence, so force GCC
* to generate a branch instead. I don't barrier() because
* we don't actually need a barrier, and if this function
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
- unsigned long flags, this_tsc_khz, tgt_tsc_khz;
+ unsigned long flags, tgt_tsc_khz;
struct kvm_vcpu_arch *vcpu = &v->arch;
struct kvm_arch *ka = &v->kvm->arch;
s64 kernel_ns;
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
- if (unlikely(this_tsc_khz == 0)) {
+ tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
+ if (unlikely(tgt_tsc_khz == 0)) {
local_irq_restore(flags);
kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
return 1;
if (!vcpu->pv_time_enabled)
return 0;
- if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
- tgt_tsc_khz = kvm_has_tsc_control ?
- vcpu->virtual_tsc_khz : this_tsc_khz;
- kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz,
+ if (kvm_has_tsc_control)
+ tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);
+
+ if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
+ kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
&vcpu->hv_clock.tsc_shift,
&vcpu->hv_clock.tsc_to_system_mul);
- vcpu->hw_tsc_khz = this_tsc_khz;
+ vcpu->hw_tsc_khz = tgt_tsc_khz;
}
/* With all the info we got, fill in the values */
}
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+ vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR &&
- kvm_vcpu_has_lapic(vcpu))
+ lapic_in_kernel(vcpu))
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
else
vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
- if (kvm_vcpu_has_lapic(vcpu)) {
+ if (lapic_in_kernel(vcpu)) {
if (events->smi.latched_init)
set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
else
switch (ioctl) {
case KVM_GET_LAPIC: {
r = -EINVAL;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
goto out;
u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
}
case KVM_SET_LAPIC: {
r = -EINVAL;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
goto out;
u.lapic = memdup_user(argp, sizeof(*u.lapic));
if (IS_ERR(u.lapic))
static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state;
+
+ BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels));
+
+ mutex_lock(&kps->lock);
+ memcpy(ps, &kps->channels, sizeof(*ps));
+ mutex_unlock(&kps->lock);
return 0;
}
static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
int i;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ mutex_lock(&pit->pit_state.lock);
+ memcpy(&pit->pit_state.channels, ps, sizeof(*ps));
for (i = 0; i < 3; i++)
- kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ kvm_pit_load_count(pit, i, ps->channels[i].count, 0);
+ mutex_unlock(&pit->pit_state.lock);
return 0;
}
int start = 0;
int i;
u32 prev_legacy, cur_legacy;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ mutex_lock(&pit->pit_state.lock);
+ prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
if (!prev_legacy && cur_legacy)
start = 1;
- memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
- sizeof(kvm->arch.vpit->pit_state.channels));
- kvm->arch.vpit->pit_state.flags = ps->flags;
+ memcpy(&pit->pit_state.channels, &ps->channels,
+ sizeof(pit->pit_state.channels));
+ pit->pit_state.flags = ps->flags;
for (i = 0; i < 3; i++)
- kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count,
+ kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count,
start && i == 0);
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ mutex_unlock(&pit->pit_state.lock);
return 0;
}
static int kvm_vm_ioctl_reinject(struct kvm *kvm,
struct kvm_reinject_control *control)
{
- if (!kvm->arch.vpit)
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ if (!pit)
return -ENXIO;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- kvm->arch.vpit->pit_state.reinject = control->pit_reinject;
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+
+ /* pit->pit_state.lock was overloaded to prevent userspace from getting
+ * an inconsistent state after running multiple KVM_REINJECT_CONTROL
+ * ioctls in parallel. Use a separate lock if that ioctl isn't rare.
+ */
+ mutex_lock(&pit->pit_state.lock);
+ kvm_pit_set_reinject(pit, control->pit_reinject);
+ mutex_unlock(&pit->pit_state.lock);
+
return 0;
}
do {
n = min(len, 8);
- if (!(vcpu->arch.apic &&
+ if (!(lapic_in_kernel(vcpu) &&
!kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v))
&& kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v))
break;
do {
n = min(len, 8);
- if (!(vcpu->arch.apic &&
+ if (!(lapic_in_kernel(vcpu) &&
!kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev,
addr, n, v))
&& kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes);
if (ret < 0)
return 0;
- kvm_mmu_pte_write(vcpu, gpa, val, bytes);
+ kvm_page_track_write(vcpu, gpa, val, bytes);
return 1;
}
return X86EMUL_CMPXCHG_FAILED;
kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
- kvm_mmu_pte_write(vcpu, gpa, new, bytes);
+ kvm_page_track_write(vcpu, gpa, new, bytes);
return X86EMUL_CONTINUE;
if (!kvm_x86_ops->update_cr8_intercept)
return;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
return;
if (vcpu->arch.apicv_active)
* KVM_DEBUGREG_WONT_EXIT again.
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
- int i;
-
WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
kvm_x86_ops->sync_dirty_debug_regs(vcpu);
- for (i = 0; i < KVM_NR_DB_REGS; i++)
- vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+ kvm_update_dr0123(vcpu);
+ kvm_update_dr6(vcpu);
+ kvm_update_dr7(vcpu);
+ vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
}
/*
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- if (!kvm_vcpu_has_lapic(vcpu) &&
+ if (!lapic_in_kernel(vcpu) &&
mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
return -EINVAL;
}
struct static_key kvm_no_apic_vcpu __read_mostly;
+ EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu);
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
+ kvm_page_track_init(kvm);
+ kvm_mmu_init_vm(kvm);
+
return 0;
}
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+ kvm_mmu_uninit_vm(kvm);
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
free->arch.lpage_info[i - 1] = NULL;
}
}
+
+ kvm_page_track_free_memslot(free, dont);
}
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
int i;
for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+ struct kvm_lpage_info *linfo;
unsigned long ugfn;
int lpages;
int level = i + 1;
if (i == 0)
continue;
- slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages *
- sizeof(*slot->arch.lpage_info[i - 1]));
- if (!slot->arch.lpage_info[i - 1])
+ linfo = kvm_kvzalloc(lpages * sizeof(*linfo));
+ if (!linfo)
goto out_free;
+ slot->arch.lpage_info[i - 1] = linfo;
+
if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i - 1][0].write_count = 1;
+ linfo[0].disallow_lpage = 1;
if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1;
+ linfo[lpages - 1].disallow_lpage = 1;
ugfn = slot->userspace_addr >> PAGE_SHIFT;
/*
* If the gfn and userspace address are not aligned wrt each
unsigned long j;
for (j = 0; j < lpages; ++j)
- slot->arch.lpage_info[i - 1][j].write_count = 1;
+ linfo[j].disallow_lpage = 1;
}
}
+ if (kvm_page_track_create_memslot(slot, npages))
+ goto out_free;
+
return 0;
out_free:
return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set);
}
+ bool kvm_vector_hashing_enabled(void)
+ {
+ return vector_hashing;
+ }
+ EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
+
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
might_sleep();
- get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL);
+ /*
+ * This work is run asynchromously to the task which owns
+ * mm and might be done in another context, so we must
+ * use FOLL_REMOTE.
+ */
+ __get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL, FOLL_REMOTE);
+
kvm_async_page_present_sync(vcpu, apf);
spin_lock(&vcpu->async_pf.lock);
* This memory barrier pairs with prepare_to_wait's set_current_state()
*/
smp_mb();
- if (waitqueue_active(&vcpu->wq))
- wake_up_interruptible(&vcpu->wq);
+ if (swait_active(&vcpu->wq))
+ swake_up(&vcpu->wq);
mmput(mm);
kvm_put_kvm(vcpu->kvm);
/* cancel outstanding work queue item */
while (!list_empty(&vcpu->async_pf.queue)) {
struct kvm_async_pf *work =
- list_entry(vcpu->async_pf.queue.next,
- typeof(*work), queue);
+ list_first_entry(&vcpu->async_pf.queue,
+ typeof(*work), queue);
list_del(&work->queue);
#ifdef CONFIG_KVM_ASYNC_PF_SYNC
spin_lock(&vcpu->async_pf.lock);
while (!list_empty(&vcpu->async_pf.done)) {
struct kvm_async_pf *work =
- list_entry(vcpu->async_pf.done.next,
- typeof(*work), link);
+ list_first_entry(&vcpu->async_pf.done,
+ typeof(*work), link);
list_del(&work->link);
kmem_cache_free(async_pf_cache, work);
}
* do alloc nowait since if we are going to sleep anyway we
* may as well sleep faulting in page
*/
- work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT);
+ work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN);
if (!work)
return 0;
/* Default doubles per-vcpu halt_poll_ns. */
static unsigned int halt_poll_ns_grow = 2;
- module_param(halt_poll_ns_grow, int, S_IRUGO);
+ module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR);
/* Default resets per-vcpu halt_poll_ns . */
static unsigned int halt_poll_ns_shrink;
- module_param(halt_poll_ns_shrink, int, S_IRUGO);
+ module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR);
/*
* Ordering of locks:
vcpu->kvm = kvm;
vcpu->vcpu_id = id;
vcpu->pid = NULL;
- vcpu->halt_poll_ns = 0;
- init_waitqueue_head(&vcpu->wq);
+ init_swait_queue_head(&vcpu->wq);
kvm_async_pf_vcpu_init(vcpu);
vcpu->pre_pcpu = -1;
static void kvm_destroy_devices(struct kvm *kvm)
{
- struct list_head *node, *tmp;
+ struct kvm_device *dev, *tmp;
- list_for_each_safe(node, tmp, &kvm->devices) {
- struct kvm_device *dev =
- list_entry(node, struct kvm_device, vm_node);
-
- list_del(node);
+ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
+ list_del(&dev->vm_node);
dev->ops->destroy(dev);
}
}
return gfn_to_hva_memslot_prot(slot, gfn, writable);
}
-static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, int write, struct page **page)
+static int get_user_page_nowait(unsigned long start, int write,
+ struct page **page)
{
int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET;
if (write)
flags |= FOLL_WRITE;
- return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL);
+ return __get_user_pages(current, current->mm, start, 1, flags, page,
+ NULL, NULL);
}
static inline int check_user_page_hwpoison(unsigned long addr)
if (async) {
down_read(¤t->mm->mmap_sem);
- npages = get_user_page_nowait(current, current->mm,
- addr, write_fault, page);
+ npages = get_user_page_nowait(addr, write_fault, page);
up_read(¤t->mm->mmap_sem);
} else
npages = __get_user_pages_unlocked(current, current->mm, addr, 1,
{
unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
- if (addr == KVM_HVA_ERR_RO_BAD)
+ if (addr == KVM_HVA_ERR_RO_BAD) {
+ if (writable)
+ *writable = false;
return KVM_PFN_ERR_RO_FAULT;
+ }
- if (kvm_is_error_hva(addr))
+ if (kvm_is_error_hva(addr)) {
+ if (writable)
+ *writable = false;
return KVM_PFN_NOSLOT;
+ }
/* Do not map writable pfn in the readonly memslot. */
if (writable && memslot_is_readonly(slot)) {
static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
{
- int old, val;
+ unsigned int old, val, grow;
old = val = vcpu->halt_poll_ns;
+ grow = READ_ONCE(halt_poll_ns_grow);
/* 10us base */
- if (val == 0 && halt_poll_ns_grow)
+ if (val == 0 && grow)
val = 10000;
else
- val *= halt_poll_ns_grow;
+ val *= grow;
vcpu->halt_poll_ns = val;
trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old);
static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
{
- int old, val;
+ unsigned int old, val, shrink;
old = val = vcpu->halt_poll_ns;
- if (halt_poll_ns_shrink == 0)
+ shrink = READ_ONCE(halt_poll_ns_shrink);
+ if (shrink == 0)
val = 0;
else
- val /= halt_poll_ns_shrink;
+ val /= shrink;
vcpu->halt_poll_ns = val;
trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old);
void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
ktime_t start, cur;
- DEFINE_WAIT(wait);
+ DECLARE_SWAITQUEUE(wait);
bool waited = false;
u64 block_ns;
kvm_arch_vcpu_blocking(vcpu);
for (;;) {
- prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
if (kvm_vcpu_check_block(vcpu) < 0)
break;
schedule();
}
- finish_wait(&vcpu->wq, &wait);
+ finish_swait(&vcpu->wq, &wait);
cur = ktime_get();
kvm_arch_vcpu_unblocking(vcpu);
{
int me;
int cpu = vcpu->cpu;
- wait_queue_head_t *wqp;
+ struct swait_queue_head *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
- if (waitqueue_active(wqp)) {
- wake_up_interruptible(wqp);
+ if (swait_active(wqp)) {
+ swake_up(wqp);
++vcpu->stat.halt_wakeup;
}
continue;
if (vcpu == me)
continue;
- if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+ if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;