return old == 0;
}
+static inline void unlock_hpte(__be64 *hpte, unsigned long hpte_v)
+{
+ hpte_v &= ~HPTE_V_HVLOCK;
+ asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
+ hpte[0] = cpu_to_be64(hpte_v);
+}
+
+/* Without barrier */
+static inline void __unlock_hpte(__be64 *hpte, unsigned long hpte_v)
+{
+ hpte_v &= ~HPTE_V_HVLOCK;
+ hpte[0] = cpu_to_be64(hpte_v);
+}
+
static inline int __hpte_actual_psize(unsigned int lp, int psize)
{
int i, shift;
/*
* If it's present and writable, atomically set dirty and referenced bits and
- * return the PTE, otherwise return 0. If we find a transparent hugepage
- * and if it is marked splitting we return 0;
+ * return the PTE, otherwise return 0.
*/
- static inline pte_t kvmppc_read_update_linux_pte(pte_t *ptep, int writing,
- unsigned int hugepage)
+ static inline pte_t kvmppc_read_update_linux_pte(pte_t *ptep, int writing)
{
pte_t old_pte, new_pte = __pte(0);
while (1) {
- old_pte = *ptep;
+ /*
+ * Make sure we don't reload from ptep
+ */
+ old_pte = READ_ONCE(*ptep);
/*
* wait until _PAGE_BUSY is clear then set it atomically
*/
cpu_relax();
continue;
}
- #ifdef CONFIG_TRANSPARENT_HUGEPAGE
- /* If hugepage and is trans splitting return None */
- if (unlikely(hugepage &&
- pmd_trans_splitting(pte_pmd(old_pte))))
- return __pte(0);
- #endif
/* If pte is not present return None */
if (unlikely(!(pte_val(old_pte) & _PAGE_PRESENT)))
return __pte(0);
return rcu_dereference_raw_notrace(kvm->memslots);
}
+extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
+
+extern void kvmhv_rm_send_ipi(int cpu);
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
config KVM_BOOK3S_64_HV
tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host"
- depends on KVM_BOOK3S_64
+ depends on KVM_BOOK3S_64 && PPC_POWERNV
select KVM_BOOK3S_HV_POSSIBLE
select MMU_NOTIFIER
select CMA
processor, including emulating 32-bit processors on a 64-bit
host.
+config KVM_BOOK3S_HV_EXIT_TIMING
+ bool "Detailed timing for hypervisor real-mode code"
+ depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
+ ---help---
+ Calculate time taken for each vcpu in the real-mode guest entry,
+ exit, and interrupt handling code, plus time spent in the guest
+ and in nap mode due to idle (cede) while other threads are still
+ in the guest. The total, minimum and maximum times in nanoseconds
+ together with the number of executions are reported in debugfs in
+ kvm/vm#/vcpu#/timings. The overhead is of the order of 30 - 40
+ ns per exit on POWER8.
+
+ If unsure, say N.
+
config KVM_BOOKE_HV
bool
#include <linux/srcu.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
+#include <linux/debugfs.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
long order;
mutex_lock(&kvm->lock);
- if (kvm->arch.rma_setup_done) {
- kvm->arch.rma_setup_done = 0;
- /* order rma_setup_done vs. vcpus_running */
+ if (kvm->arch.hpte_setup_done) {
+ kvm->arch.hpte_setup_done = 0;
+ /* order hpte_setup_done vs. vcpus_running */
smp_mb();
if (atomic_read(&kvm->arch.vcpus_running)) {
- kvm->arch.rma_setup_done = 1;
+ kvm->arch.hpte_setup_done = 1;
goto out;
}
}
v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
gr = kvm->arch.revmap[index].guest_rpte;
- /* Unlock the HPTE */
- asm volatile("lwsync" : : : "memory");
- hptep[0] = cpu_to_be64(v);
+ unlock_hpte(hptep, v);
preempt_enable();
gpte->eaddr = eaddr;
hpte[0] = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
hpte[1] = be64_to_cpu(hptep[1]);
hpte[2] = r = rev->guest_rpte;
- asm volatile("lwsync" : : : "memory");
- hptep[0] = cpu_to_be64(hpte[0]);
+ unlock_hpte(hptep, hpte[0]);
preempt_enable();
if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
}
/* if the guest wants write access, see if that is OK */
if (!writing && hpte_is_writable(r)) {
- unsigned int hugepage_shift;
pte_t *ptep, pte;
-
+ unsigned long flags;
/*
* We need to protect against page table destruction
- * while looking up and updating the pte.
+ * hugepage split and collapse.
*/
- rcu_read_lock_sched();
+ local_irq_save(flags);
ptep = find_linux_pte_or_hugepte(current->mm->pgd,
- hva, &hugepage_shift);
+ hva, NULL);
if (ptep) {
- pte = kvmppc_read_update_linux_pte(ptep, 1,
- hugepage_shift);
+ pte = kvmppc_read_update_linux_pte(ptep, 1);
if (pte_write(pte))
write_ok = 1;
}
- rcu_read_unlock_sched();
+ local_irq_restore(flags);
}
}
hptep[1] = cpu_to_be64(r);
eieio();
- hptep[0] = cpu_to_be64(hpte[0]);
+ __unlock_hpte(hptep, hpte[0]);
asm volatile("ptesync" : : : "memory");
preempt_enable();
if (page && hpte_is_writable(r))
return ret;
out_unlock:
- hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hptep, be64_to_cpu(hptep[0]));
preempt_enable();
goto out_put;
}
}
}
unlock_rmap(rmapp);
- hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hptep, be64_to_cpu(hptep[0]));
}
return 0;
}
}
ret = 1;
}
- hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hptep, be64_to_cpu(hptep[0]));
} while ((i = j) != head);
unlock_rmap(rmapp);
/* Now check and modify the HPTE */
if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID))) {
- /* unlock and continue */
- hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hptep, be64_to_cpu(hptep[0]));
continue;
}
npages_dirty = n;
eieio();
}
- v &= ~(HPTE_V_ABSENT | HPTE_V_HVLOCK);
+ v &= ~HPTE_V_ABSENT;
v |= HPTE_V_VALID;
- hptep[0] = cpu_to_be64(v);
+ __unlock_hpte(hptep, v);
} while ((i = j) != head);
unlock_rmap(rmapp);
r &= ~HPTE_GR_MODIFIED;
revp->guest_rpte = r;
}
- asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
- hptp[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ unlock_hpte(hptp, be64_to_cpu(hptp[0]));
preempt_enable();
if (!(valid == want_valid && (first_pass || dirty)))
ok = 0;
unsigned long tmp[2];
ssize_t nb;
long int err, ret;
- int rma_setup;
+ int hpte_setup;
if (!access_ok(VERIFY_READ, buf, count))
return -EFAULT;
/* lock out vcpus from running while we're doing this */
mutex_lock(&kvm->lock);
- rma_setup = kvm->arch.rma_setup_done;
- if (rma_setup) {
- kvm->arch.rma_setup_done = 0; /* temporarily */
- /* order rma_setup_done vs. vcpus_running */
+ hpte_setup = kvm->arch.hpte_setup_done;
+ if (hpte_setup) {
+ kvm->arch.hpte_setup_done = 0; /* temporarily */
+ /* order hpte_setup_done vs. vcpus_running */
smp_mb();
if (atomic_read(&kvm->arch.vcpus_running)) {
- kvm->arch.rma_setup_done = 1;
+ kvm->arch.hpte_setup_done = 1;
mutex_unlock(&kvm->lock);
return -EBUSY;
}
"r=%lx\n", ret, i, v, r);
goto out;
}
- if (!rma_setup && is_vrma_hpte(v)) {
+ if (!hpte_setup && is_vrma_hpte(v)) {
unsigned long psize = hpte_base_page_size(v, r);
unsigned long senc = slb_pgsize_encoding(psize);
unsigned long lpcr;
(VRMA_VSID << SLB_VSID_SHIFT_1T);
lpcr = senc << (LPCR_VRMASD_SH - 4);
kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
- rma_setup = 1;
+ hpte_setup = 1;
}
++i;
hptp += 2;
}
out:
- /* Order HPTE updates vs. rma_setup_done */
+ /* Order HPTE updates vs. hpte_setup_done */
smp_wmb();
- kvm->arch.rma_setup_done = rma_setup;
+ kvm->arch.hpte_setup_done = hpte_setup;
mutex_unlock(&kvm->lock);
if (err)
return ret;
}
+struct debugfs_htab_state {
+ struct kvm *kvm;
+ struct mutex mutex;
+ unsigned long hpt_index;
+ int chars_left;
+ int buf_index;
+ char buf[64];
+};
+
+static int debugfs_htab_open(struct inode *inode, struct file *file)
+{
+ struct kvm *kvm = inode->i_private;
+ struct debugfs_htab_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(kvm);
+ p->kvm = kvm;
+ mutex_init(&p->mutex);
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_htab_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_htab_state *p = file->private_data;
+
+ kvm_put_kvm(p->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_htab_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_htab_state *p = file->private_data;
+ ssize_t ret, r;
+ unsigned long i, n;
+ unsigned long v, hr, gr;
+ struct kvm *kvm;
+ __be64 *hptp;
+
+ ret = mutex_lock_interruptible(&p->mutex);
+ if (ret)
+ return ret;
+
+ if (p->chars_left) {
+ n = p->chars_left;
+ if (n > len)
+ n = len;
+ r = copy_to_user(buf, p->buf + p->buf_index, n);
+ n -= r;
+ p->chars_left -= n;
+ p->buf_index += n;
+ buf += n;
+ len -= n;
+ ret = n;
+ if (r) {
+ if (!n)
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+
+ kvm = p->kvm;
+ i = p->hpt_index;
+ hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+ for (; len != 0 && i < kvm->arch.hpt_npte; ++i, hptp += 2) {
+ if (!(be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT)))
+ continue;
+
+ /* lock the HPTE so it's stable and read it */
+ preempt_disable();
+ while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
+ cpu_relax();
+ v = be64_to_cpu(hptp[0]) & ~HPTE_V_HVLOCK;
+ hr = be64_to_cpu(hptp[1]);
+ gr = kvm->arch.revmap[i].guest_rpte;
+ unlock_hpte(hptp, v);
+ preempt_enable();
+
+ if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT)))
+ continue;
+
+ n = scnprintf(p->buf, sizeof(p->buf),
+ "%6lx %.16lx %.16lx %.16lx\n",
+ i, v, hr, gr);
+ p->chars_left = n;
+ if (n > len)
+ n = len;
+ r = copy_to_user(buf, p->buf, n);
+ n -= r;
+ p->chars_left -= n;
+ p->buf_index = n;
+ buf += n;
+ len -= n;
+ ret += n;
+ if (r) {
+ if (!ret)
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+ p->hpt_index = i;
+
+ out:
+ mutex_unlock(&p->mutex);
+ return ret;
+}
+
+ssize_t debugfs_htab_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_htab_fops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_htab_open,
+ .release = debugfs_htab_release,
+ .read = debugfs_htab_read,
+ .write = debugfs_htab_write,
+ .llseek = generic_file_llseek,
+};
+
+void kvmppc_mmu_debugfs_init(struct kvm *kvm)
+{
+ kvm->arch.htab_dentry = debugfs_create_file("htab", 0400,
+ kvm->arch.debugfs_dir, kvm,
+ &debugfs_htab_fops);
+}
+
void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
{
struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
{
unsigned long addr = (unsigned long) x;
pte_t *p;
-
- p = find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL);
+ /*
+ * assume we don't have huge pages in vmalloc space...
+ * So don't worry about THP collapse/split. Called
+ * Only in realmode, hence won't need irq_save/restore.
+ */
+ p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL);
if (!p || !pte_present(*p))
return NULL;
- /* assume we don't have huge pages in vmalloc space... */
addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
return __va(addr);
}
unlock_rmap(rmap);
}
- static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva,
- int writing, unsigned long *pte_sizep)
-static inline void unlock_hpte(__be64 *hpte, unsigned long hpte_v)
--{
- pte_t *ptep;
- unsigned long ps = *pte_sizep;
- unsigned int hugepage_shift;
-
- ptep = find_linux_pte_or_hugepte(pgdir, hva, &hugepage_shift);
- if (!ptep)
- return __pte(0);
- if (hugepage_shift)
- *pte_sizep = 1ul << hugepage_shift;
- else
- *pte_sizep = PAGE_SIZE;
- if (ps > *pte_sizep)
- return __pte(0);
- return kvmppc_read_update_linux_pte(ptep, writing, hugepage_shift);
- asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
- hpte[0] = cpu_to_be64(hpte_v);
--}
--
long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
long pte_index, unsigned long pteh, unsigned long ptel,
pgd_t *pgdir, bool realmode, unsigned long *pte_idx_ret)
struct revmap_entry *rev;
unsigned long g_ptel;
struct kvm_memory_slot *memslot;
- unsigned long pte_size;
+ unsigned hpage_shift;
unsigned long is_io;
unsigned long *rmap;
- pte_t pte;
+ pte_t *ptep;
unsigned int writing;
unsigned long mmu_seq;
- unsigned long rcbits;
+ unsigned long rcbits, irq_flags = 0;
psize = hpte_page_size(pteh, ptel);
if (!psize)
/* Translate to host virtual address */
hva = __gfn_to_hva_memslot(memslot, gfn);
-
- /* Look up the Linux PTE for the backing page */
- pte_size = psize;
- pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size);
- if (pte_present(pte) && !pte_protnone(pte)) {
- if (writing && !pte_write(pte))
- /* make the actual HPTE be read-only */
- ptel = hpte_make_readonly(ptel);
- is_io = hpte_cache_bits(pte_val(pte));
- pa = pte_pfn(pte) << PAGE_SHIFT;
- pa |= hva & (pte_size - 1);
- pa |= gpa & ~PAGE_MASK;
+ /*
+ * If we had a page table table change after lookup, we would
+ * retry via mmu_notifier_retry.
+ */
+ if (realmode)
+ ptep = __find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift);
+ else {
+ local_irq_save(irq_flags);
+ ptep = find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift);
}
+ if (ptep) {
+ pte_t pte;
+ unsigned int host_pte_size;
- if (pte_size < psize)
- return H_PARAMETER;
+ if (hpage_shift)
+ host_pte_size = 1ul << hpage_shift;
+ else
+ host_pte_size = PAGE_SIZE;
+ /*
+ * We should always find the guest page size
+ * to <= host page size, if host is using hugepage
+ */
+ if (host_pte_size < psize) {
+ if (!realmode)
+ local_irq_restore(flags);
+ return H_PARAMETER;
+ }
+ pte = kvmppc_read_update_linux_pte(ptep, writing);
+ if (pte_present(pte) && !pte_protnone(pte)) {
+ if (writing && !pte_write(pte))
+ /* make the actual HPTE be read-only */
+ ptel = hpte_make_readonly(ptel);
+ is_io = hpte_cache_bits(pte_val(pte));
+ pa = pte_pfn(pte) << PAGE_SHIFT;
+ pa |= hva & (host_pte_size - 1);
+ pa |= gpa & ~PAGE_MASK;
+ }
+ }
+ if (!realmode)
+ local_irq_restore(irq_flags);
ptel &= ~(HPTE_R_PP0 - psize);
ptel |= pa;
u64 pte;
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- pte = be64_to_cpu(*hpte);
+ pte = be64_to_cpu(hpte[0]);
if (!(pte & (HPTE_V_VALID | HPTE_V_ABSENT)))
break;
- *hpte &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hpte, pte);
hpte += 2;
}
if (i == 8)
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- pte = be64_to_cpu(*hpte);
+ pte = be64_to_cpu(hpte[0]);
if (pte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
- *hpte &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hpte, pte);
return H_PTEG_FULL;
}
}
/* Write the first HPTE dword, unlocking the HPTE and making it valid */
eieio();
- hpte[0] = cpu_to_be64(pteh);
+ __unlock_hpte(hpte, pteh);
asm volatile("ptesync" : : : "memory");
*pte_idx_ret = pte_index;
if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) ||
((flags & H_ANDCOND) && (pte & avpn) != 0)) {
- hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hpte, pte);
return H_NOT_FOUND;
}
be64_to_cpu(hp[0]), be64_to_cpu(hp[1]));
rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
args[j] |= rcbits << (56 - 5);
- hp[0] = 0;
+ __unlock_hpte(hp, 0);
}
}
pte = be64_to_cpu(hpte[0]);
if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
((flags & H_AVPN) && (pte & ~0x7fUL) != avpn)) {
- hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hpte, pte);
return H_NOT_FOUND;
}
/* Return with the HPTE still locked */
return (hash << 3) + (i >> 1);
- /* Unlock and move on */
- hpte[i] = cpu_to_be64(v);
+ __unlock_hpte(&hpte[i], v);
}
if (val & HPTE_V_SECONDARY)