aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kvm')
-rw-r--r--arch/powerpc/kvm/Makefile7
-rw-r--r--arch/powerpc/kvm/book3s.c6
-rw-r--r--arch/powerpc/kvm/book3s.h1
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c9
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c333
-rw-r--r--arch/powerpc/kvm/book3s_64_vio_hv.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv.c56
-rw-r--r--arch/powerpc/kvm/book3s_hv_builtin.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv_interrupts.S3
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S187
-rw-r--r--arch/powerpc/kvm/book3s_hv_tm.c216
-rw-r--r--arch/powerpc/kvm/book3s_hv_tm_builtin.c109
-rw-r--r--arch/powerpc/kvm/book3s_pr.c10
-rw-r--r--arch/powerpc/kvm/e500_mmu_host.c2
-rw-r--r--arch/powerpc/kvm/emulate.c6
-rw-r--r--arch/powerpc/kvm/powerpc.c5
-rw-r--r--arch/powerpc/kvm/trace_pr.h15
17 files changed, 765 insertions, 204 deletions
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 85ba80de7133..4b19da8c87ae 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -74,9 +74,15 @@ kvm-hv-y += \
book3s_64_mmu_hv.o \
book3s_64_mmu_radix.o
+kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
+ book3s_hv_tm.o
+
kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
book3s_hv_rm_xics.o book3s_hv_rm_xive.o
+kvm-book3s_64-builtin-tm-objs-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
+ book3s_hv_tm_builtin.o
+
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
book3s_hv_hmi.o \
@@ -84,6 +90,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
book3s_hv_rm_mmu.o \
book3s_hv_ras.o \
book3s_hv_builtin.o \
+ $(kvm-book3s_64-builtin-tm-objs-y) \
$(kvm-book3s_64-builtin-xics-objs-y)
endif
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 234531d1bee1..97d4a112648f 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -819,12 +819,6 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new);
}
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
-{
- return kvm->arch.kvm_ops->unmap_hva(kvm, hva);
-}
-EXPORT_SYMBOL_GPL(kvm_unmap_hva);
-
int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
{
return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end);
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index d2b3ec088b8c..4ad5e287b8bc 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -14,7 +14,6 @@
extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
struct kvm_memory_slot *memslot);
-extern int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva);
extern int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start,
unsigned long end);
extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long start,
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index ef243fed2f2b..a670fa5fbe50 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -877,15 +877,6 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
return 0;
}
-int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva)
-{
- hva_handler_fn handler;
-
- handler = kvm_is_radix(kvm) ? kvm_unmap_radix : kvm_unmap_rmapp;
- kvm_handle_hva(kvm, hva, handler);
- return 0;
-}
-
int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, unsigned long end)
{
hva_handler_fn handler;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 5d9bafe9a371..a57eafec4dc2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -150,7 +150,9 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
{
int psize = MMU_BASE_PSIZE;
- if (pshift >= PMD_SHIFT)
+ if (pshift >= PUD_SHIFT)
+ psize = MMU_PAGE_1G;
+ else if (pshift >= PMD_SHIFT)
psize = MMU_PAGE_2M;
addr &= ~0xfffUL;
addr |= mmu_psize_defs[psize].ap << 5;
@@ -163,6 +165,17 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
asm volatile("ptesync": : :"memory");
}
+static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned long addr)
+{
+ unsigned long rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
+
+ asm volatile("ptesync": : :"memory");
+ /* RIC=1 PRS=0 R=1 IS=2 */
+ asm volatile(PPC_TLBIE_5(%0, %1, 1, 0, 1)
+ : : "r" (rb), "r" (kvm->arch.lpid) : "memory");
+ asm volatile("ptesync": : :"memory");
+}
+
unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
unsigned long clr, unsigned long set,
unsigned long addr, unsigned int shift)
@@ -223,9 +236,9 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
new_pud = pud_alloc_one(kvm->mm, gpa);
pmd = NULL;
- if (pud && pud_present(*pud))
+ if (pud && pud_present(*pud) && !pud_huge(*pud))
pmd = pmd_offset(pud, gpa);
- else
+ else if (level <= 1)
new_pmd = pmd_alloc_one(kvm->mm, gpa);
if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd)))
@@ -246,6 +259,50 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
new_pud = NULL;
}
pud = pud_offset(pgd, gpa);
+ if (pud_huge(*pud)) {
+ unsigned long hgpa = gpa & PUD_MASK;
+
+ /*
+ * If we raced with another CPU which has just put
+ * a 1GB pte in after we saw a pmd page, try again.
+ */
+ if (level <= 1 && !new_pmd) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
+ /* Check if we raced and someone else has set the same thing */
+ if (level == 2 && pud_raw(*pud) == pte_raw(pte)) {
+ ret = 0;
+ goto out_unlock;
+ }
+ /* Valid 1GB page here already, remove it */
+ old = kvmppc_radix_update_pte(kvm, (pte_t *)pud,
+ ~0UL, 0, hgpa, PUD_SHIFT);
+ kvmppc_radix_tlbie_page(kvm, hgpa, PUD_SHIFT);
+ if (old & _PAGE_DIRTY) {
+ unsigned long gfn = hgpa >> PAGE_SHIFT;
+ struct kvm_memory_slot *memslot;
+ memslot = gfn_to_memslot(kvm, gfn);
+ if (memslot && memslot->dirty_bitmap)
+ kvmppc_update_dirty_map(memslot,
+ gfn, PUD_SIZE);
+ }
+ }
+ if (level == 2) {
+ if (!pud_none(*pud)) {
+ /*
+ * There's a page table page here, but we wanted to
+ * install a large page, so remove and free the page
+ * table page. new_pmd will be NULL since level == 2.
+ */
+ new_pmd = pmd_offset(pud, 0);
+ pud_clear(pud);
+ kvmppc_radix_flush_pwc(kvm, gpa);
+ }
+ kvmppc_radix_set_pte_at(kvm, gpa, (pte_t *)pud, pte);
+ ret = 0;
+ goto out_unlock;
+ }
if (pud_none(*pud)) {
if (!new_pmd)
goto out_unlock;
@@ -264,6 +321,11 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
ret = -EAGAIN;
goto out_unlock;
}
+ /* Check if we raced and someone else has set the same thing */
+ if (level == 1 && pmd_raw(*pmd) == pte_raw(pte)) {
+ ret = 0;
+ goto out_unlock;
+ }
/* Valid 2MB page here already, remove it */
old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
~0UL, 0, lgpa, PMD_SHIFT);
@@ -276,35 +338,43 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
kvmppc_update_dirty_map(memslot,
gfn, PMD_SIZE);
}
- } else if (level == 1 && !pmd_none(*pmd)) {
- /*
- * There's a page table page here, but we wanted
- * to install a large page. Tell the caller and let
- * it try installing a normal page if it wants.
- */
- ret = -EBUSY;
- goto out_unlock;
}
- if (level == 0) {
- if (pmd_none(*pmd)) {
- if (!new_ptep)
- goto out_unlock;
- pmd_populate(kvm->mm, pmd, new_ptep);
- new_ptep = NULL;
- }
- ptep = pte_offset_kernel(pmd, gpa);
- if (pte_present(*ptep)) {
- /* PTE was previously valid, so invalidate it */
- old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT,
- 0, gpa, 0);
- kvmppc_radix_tlbie_page(kvm, gpa, 0);
- if (old & _PAGE_DIRTY)
- mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+ if (level == 1) {
+ if (!pmd_none(*pmd)) {
+ /*
+ * There's a page table page here, but we wanted to
+ * install a large page, so remove and free the page
+ * table page. new_ptep will be NULL since level == 1.
+ */
+ new_ptep = pte_offset_kernel(pmd, 0);
+ pmd_clear(pmd);
+ kvmppc_radix_flush_pwc(kvm, gpa);
}
- kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
- } else {
kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte);
+ ret = 0;
+ goto out_unlock;
}
+ if (pmd_none(*pmd)) {
+ if (!new_ptep)
+ goto out_unlock;
+ pmd_populate(kvm->mm, pmd, new_ptep);
+ new_ptep = NULL;
+ }
+ ptep = pte_offset_kernel(pmd, gpa);
+ if (pte_present(*ptep)) {
+ /* Check if someone else set the same thing */
+ if (pte_raw(*ptep) == pte_raw(pte)) {
+ ret = 0;
+ goto out_unlock;
+ }
+ /* PTE was previously valid, so invalidate it */
+ old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT,
+ 0, gpa, 0);
+ kvmppc_radix_tlbie_page(kvm, gpa, 0);
+ if (old & _PAGE_DIRTY)
+ mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+ }
+ kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
ret = 0;
out_unlock:
@@ -325,11 +395,11 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned long mmu_seq, pte_size;
unsigned long gpa, gfn, hva, pfn;
struct kvm_memory_slot *memslot;
- struct page *page = NULL, *pages[1];
- long ret, npages, ok;
- unsigned int writing;
- struct vm_area_struct *vma;
- unsigned long flags;
+ struct page *page = NULL;
+ long ret;
+ bool writing;
+ bool upgrade_write = false;
+ bool *upgrade_p = &upgrade_write;
pte_t pte, *ptep;
unsigned long pgflags;
unsigned int shift, level;
@@ -369,122 +439,131 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
dsisr & DSISR_ISSTORE);
}
- /* used to check for invalidations in progress */
- mmu_seq = kvm->mmu_notifier_seq;
- smp_rmb();
-
writing = (dsisr & DSISR_ISSTORE) != 0;
- hva = gfn_to_hva_memslot(memslot, gfn);
+ if (memslot->flags & KVM_MEM_READONLY) {
+ if (writing) {
+ /* give the guest a DSI */
+ dsisr = DSISR_ISSTORE | DSISR_PROTFAULT;
+ kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+ return RESUME_GUEST;
+ }
+ upgrade_p = NULL;
+ }
+
if (dsisr & DSISR_SET_RC) {
/*
* Need to set an R or C bit in the 2nd-level tables;
- * if the relevant bits aren't already set in the linux
- * page tables, fall through to do the gup_fast to
- * set them in the linux page tables too.
+ * since we are just helping out the hardware here,
+ * it is sufficient to do what the hardware does.
*/
- ok = 0;
pgflags = _PAGE_ACCESSED;
if (writing)
pgflags |= _PAGE_DIRTY;
- local_irq_save(flags);
- ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL);
- if (ptep) {
- pte = READ_ONCE(*ptep);
- if (pte_present(pte) &&
- (pte_val(pte) & pgflags) == pgflags)
- ok = 1;
- }
- local_irq_restore(flags);
- if (ok) {
- spin_lock(&kvm->mmu_lock);
- if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
- spin_unlock(&kvm->mmu_lock);
- return RESUME_GUEST;
- }
- /*
- * We are walking the secondary page table here. We can do this
- * without disabling irq.
- */
- ptep = __find_linux_pte(kvm->arch.pgtable,
- gpa, NULL, &shift);
- if (ptep && pte_present(*ptep)) {
- kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
- gpa, shift);
- spin_unlock(&kvm->mmu_lock);
- return RESUME_GUEST;
- }
- spin_unlock(&kvm->mmu_lock);
+ /*
+ * We are walking the secondary page table here. We can do this
+ * without disabling irq.
+ */
+ spin_lock(&kvm->mmu_lock);
+ ptep = __find_linux_pte(kvm->arch.pgtable,
+ gpa, NULL, &shift);
+ if (ptep && pte_present(*ptep) &&
+ (!writing || pte_write(*ptep))) {
+ kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
+ gpa, shift);
+ dsisr &= ~DSISR_SET_RC;
}
+ spin_unlock(&kvm->mmu_lock);
+ if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
+ DSISR_PROTFAULT | DSISR_SET_RC)))
+ return RESUME_GUEST;
}
- ret = -EFAULT;
- pfn = 0;
- pte_size = PAGE_SIZE;
- pgflags = _PAGE_READ | _PAGE_EXEC;
- level = 0;
- npages = get_user_pages_fast(hva, 1, writing, pages);
- if (npages < 1) {
- /* Check if it's an I/O mapping */
- down_read(&current->mm->mmap_sem);
- vma = find_vma(current->mm, hva);
- if (vma && vma->vm_start <= hva && hva < vma->vm_end &&
- (vma->vm_flags & VM_PFNMAP)) {
- pfn = vma->vm_pgoff +
- ((hva - vma->vm_start) >> PAGE_SHIFT);
- pgflags = pgprot_val(vma->vm_page_prot);
- }
- up_read(&current->mm->mmap_sem);
- if (!pfn)
- return -EFAULT;
- } else {
- page = pages[0];
+ /* used to check for invalidations in progress */
+ mmu_seq = kvm->mmu_notifier_seq;
+ smp_rmb();
+
+ /*
+ * Do a fast check first, since __gfn_to_pfn_memslot doesn't
+ * do it with !atomic && !async, which is how we call it.
+ * We always ask for write permission since the common case
+ * is that the page is writable.
+ */
+ hva = gfn_to_hva_memslot(memslot, gfn);
+ if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
pfn = page_to_pfn(page);
- if (PageCompound(page)) {
- pte_size <<= compound_order(compound_head(page));
- /* See if we can insert a 2MB large-page PTE here */
- if (pte_size >= PMD_SIZE &&
- (gpa & (PMD_SIZE - PAGE_SIZE)) ==
- (hva & (PMD_SIZE - PAGE_SIZE))) {
- level = 1;
- pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
- }
+ upgrade_write = true;
+ } else {
+ /* Call KVM generic code to do the slow-path check */
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ writing, upgrade_p);
+ if (is_error_noslot_pfn(pfn))
+ return -EFAULT;
+ page = NULL;
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ if (PageReserved(page))
+ page = NULL;
}
- /* See if we can provide write access */
- if (writing) {
- pgflags |= _PAGE_WRITE;
- } else {
- local_irq_save(flags);
- ptep = find_current_mm_pte(current->mm->pgd,
- hva, NULL, NULL);
- if (ptep && pte_write(*ptep))
- pgflags |= _PAGE_WRITE;
- local_irq_restore(flags);
+ }
+
+ /* See if we can insert a 1GB or 2MB large PTE here */
+ level = 0;
+ if (page && PageCompound(page)) {
+ pte_size = PAGE_SIZE << compound_order(compound_head(page));
+ if (pte_size >= PUD_SIZE &&
+ (gpa & (PUD_SIZE - PAGE_SIZE)) ==
+ (hva & (PUD_SIZE - PAGE_SIZE))) {
+ level = 2;
+ pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1);
+ } else if (pte_size >= PMD_SIZE &&
+ (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+ (hva & (PMD_SIZE - PAGE_SIZE))) {
+ level = 1;
+ pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
}
}
/*
* Compute the PTE value that we need to insert.
*/
- pgflags |= _PAGE_PRESENT | _PAGE_PTE | _PAGE_ACCESSED;
- if (pgflags & _PAGE_WRITE)
- pgflags |= _PAGE_DIRTY;
- pte = pfn_pte(pfn, __pgprot(pgflags));
-
- /* Allocate space in the tree and write the PTE */
- ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
- if (ret == -EBUSY) {
+ if (page) {
+ pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE |
+ _PAGE_ACCESSED;
+ if (writing || upgrade_write)
+ pgflags |= _PAGE_WRITE | _PAGE_DIRTY;
+ pte = pfn_pte(pfn, __pgprot(pgflags));
+ } else {
/*
- * There's already a PMD where wanted to install a large page;
- * for now, fall back to installing a small page.
+ * Read the PTE from the process' radix tree and use that
+ * so we get the attribute bits.
*/
- level = 0;
- pfn |= gfn & ((PMD_SIZE >> PAGE_SHIFT) - 1);
- pte = pfn_pte(pfn, __pgprot(pgflags));
- ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+ local_irq_disable();
+ ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+ pte = *ptep;
+ local_irq_enable();
+ if (shift == PUD_SHIFT &&
+ (gpa & (PUD_SIZE - PAGE_SIZE)) ==
+ (hva & (PUD_SIZE - PAGE_SIZE))) {
+ level = 2;
+ } else if (shift == PMD_SHIFT &&
+ (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+ (hva & (PMD_SIZE - PAGE_SIZE))) {
+ level = 1;
+ } else if (shift && shift != PAGE_SHIFT) {
+ /* Adjust PFN */
+ unsigned long mask = (1ul << shift) - PAGE_SIZE;
+ pte = __pte(pte_val(pte) | (hva & mask));
+ }
+ if (!(writing || upgrade_write))
+ pte = __pte(pte_val(pte) & ~ _PAGE_WRITE);
+ pte = __pte(pte_val(pte) | _PAGE_EXEC);
}
+ /* Allocate space in the tree and write the PTE */
+ ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+
if (page) {
- if (!ret && (pgflags & _PAGE_WRITE))
+ if (!ret && (pte_val(pte) & _PAGE_WRITE))
set_page_dirty_lock(page);
put_page(page);
}
@@ -662,6 +741,10 @@ void kvmppc_free_radix(struct kvm *kvm)
for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++pud) {
if (!pud_present(*pud))
continue;
+ if (pud_huge(*pud)) {
+ pud_clear(pud);
+ continue;
+ }
pmd = pmd_offset(pud, 0);
for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) {
if (pmd_is_leaf(*pmd)) {
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index c32e9bfe75b1..6651f736a0b1 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -450,7 +450,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
/*
* Synchronize with the MMU notifier callbacks in
- * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
+ * book3s_64_mmu_hv.c (kvm_unmap_hva_range_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
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9cb9448163c4..4d07fca5121c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -49,6 +49,7 @@
#include <asm/reg.h>
#include <asm/ppc-opcode.h>
#include <asm/asm-prototypes.h>
+#include <asm/debug.h>
#include <asm/disassemble.h>
#include <asm/cputable.h>
#include <asm/cacheflush.h>
@@ -170,7 +171,7 @@ static bool kvmppc_ipi_thread(int cpu)
#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
if (cpu >= 0 && cpu < nr_cpu_ids) {
- if (paca[cpu].kvm_hstate.xics_phys) {
+ if (paca_ptrs[cpu]->kvm_hstate.xics_phys) {
xics_wake_cpu(cpu);
return true;
}
@@ -498,7 +499,8 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
* use 640 bytes of the structure though, so we should accept
* clients that set a size of 640.
*/
- if (len < 640)
+ BUILD_BUG_ON(sizeof(struct lppaca) != 640);
+ if (len < sizeof(struct lppaca))
break;
vpap = &tvcpu->arch.vpa;
err = 0;
@@ -741,6 +743,8 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
case H_SET_MODE_RESOURCE_SET_DAWR:
if (!kvmppc_power8_compatible(vcpu))
return H_P2;
+ if (!ppc_breakpoint_available())
+ return H_P2;
if (mflags)
return H_UNSUPPORTED_FLAG_START;
if (value2 & DABRX_HYP)
@@ -1206,6 +1210,19 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
r = RESUME_GUEST;
}
break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+ /*
+ * This occurs for various TM-related instructions that
+ * we need to emulate on POWER9 DD2.2. We have already
+ * handled the cases where the guest was in real-suspend
+ * mode and was transitioning to transactional state.
+ */
+ r = kvmhv_p9_tm_emulation(vcpu);
+ break;
+#endif
+
case BOOK3S_INTERRUPT_HV_RM_HARD:
r = RESUME_PASSTHROUGH;
break;
@@ -1978,7 +1995,9 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
* turn off the HFSCR bit, which causes those instructions to trap.
*/
vcpu->arch.hfscr = mfspr(SPRN_HFSCR);
- if (!cpu_has_feature(CPU_FTR_TM))
+ if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+ vcpu->arch.hfscr |= HFSCR_TM;
+ else if (!cpu_has_feature(CPU_FTR_TM_COMP))
vcpu->arch.hfscr &= ~HFSCR_TM;
if (cpu_has_feature(CPU_FTR_ARCH_300))
vcpu->arch.hfscr &= ~HFSCR_MSGP;
@@ -2140,7 +2159,7 @@ static int kvmppc_grab_hwthread(int cpu)
struct paca_struct *tpaca;
long timeout = 10000;
- tpaca = &paca[cpu];
+ tpaca = paca_ptrs[cpu];
/* Ensure the thread won't go into the kernel if it wakes */
tpaca->kvm_hstate.kvm_vcpu = NULL;
@@ -2173,7 +2192,7 @@ static void kvmppc_release_hwthread(int cpu)
{
struct paca_struct *tpaca;
- tpaca = &paca[cpu];
+ tpaca = paca_ptrs[cpu];
tpaca->kvm_hstate.hwthread_req = 0;
tpaca->kvm_hstate.kvm_vcpu = NULL;
tpaca->kvm_hstate.kvm_vcore = NULL;
@@ -2239,9 +2258,10 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
vcpu->arch.thread_cpu = cpu;
cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest);
}
- tpaca = &paca[cpu];
+ tpaca = paca_ptrs[cpu];
tpaca->kvm_hstate.kvm_vcpu = vcpu;
tpaca->kvm_hstate.ptid = cpu - vc->pcpu;
+ tpaca->kvm_hstate.fake_suspend = 0;
/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
smp_wmb();
tpaca->kvm_hstate.kvm_vcore = vc;
@@ -2264,7 +2284,7 @@ static void kvmppc_wait_for_nap(int n_threads)
* for any threads that still have a non-NULL vcore ptr.
*/
for (i = 1; i < n_threads; ++i)
- if (paca[cpu + i].kvm_hstate.kvm_vcore)
+ if (paca_ptrs[cpu + i]->kvm_hstate.kvm_vcore)
break;
if (i == n_threads) {
HMT_medium();
@@ -2274,7 +2294,7 @@ static void kvmppc_wait_for_nap(int n_threads)
}
HMT_medium();
for (i = 1; i < n_threads; ++i)
- if (paca[cpu + i].kvm_hstate.kvm_vcore)
+ if (paca_ptrs[cpu + i]->kvm_hstate.kvm_vcore)
pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
}
@@ -2806,9 +2826,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
}
for (thr = 0; thr < controlled_threads; ++thr) {
- paca[pcpu + thr].kvm_hstate.tid = thr;
- paca[pcpu + thr].kvm_hstate.napping = 0;
- paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip;
+ struct paca_struct *paca = paca_ptrs[pcpu + thr];
+
+ paca->kvm_hstate.tid = thr;
+ paca->kvm_hstate.napping = 0;
+ paca->kvm_hstate.kvm_split_mode = sip;
}
/* Initiate micro-threading (split-core) on POWER8 if required */
@@ -2923,7 +2945,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
} else if (hpt_on_radix) {
/* Wait for all threads to have seen final sync */
for (thr = 1; thr < controlled_threads; ++thr) {
- while (paca[pcpu + thr].kvm_hstate.kvm_split_mode) {
+ struct paca_struct *paca = paca_ptrs[pcpu + thr];
+
+ while (paca->kvm_hstate.kvm_split_mode) {
HMT_low();
barrier();
}
@@ -4351,7 +4375,6 @@ static struct kvmppc_ops kvm_ops_hv = {
.flush_memslot = kvmppc_core_flush_memslot_hv,
.prepare_memory_region = kvmppc_core_prepare_memory_region_hv,
.commit_memory_region = kvmppc_core_commit_memory_region_hv,
- .unmap_hva = kvm_unmap_hva_hv,
.unmap_hva_range = kvm_unmap_hva_range_hv,
.age_hva = kvm_age_hva_hv,
.test_age_hva = kvm_test_age_hva_hv,
@@ -4388,7 +4411,7 @@ static int kvm_init_subcore_bitmap(void)
int node = cpu_to_node(first_cpu);
/* Ignore if it is already allocated. */
- if (paca[first_cpu].sibling_subcore_state)
+ if (paca_ptrs[first_cpu]->sibling_subcore_state)
continue;
sibling_subcore_state =
@@ -4403,7 +4426,8 @@ static int kvm_init_subcore_bitmap(void)
for (j = 0; j < threads_per_core; j++) {
int cpu = first_cpu + j;
- paca[cpu].sibling_subcore_state = sibling_subcore_state;
+ paca_ptrs[cpu]->sibling_subcore_state =
+ sibling_subcore_state;
}
}
return 0;
@@ -4430,7 +4454,7 @@ static int kvmppc_book3s_init_hv(void)
/*
* We need a way of accessing the XICS interrupt controller,
- * either directly, via paca[cpu].kvm_hstate.xics_phys, or
+ * either directly, via paca_ptrs[cpu]->kvm_hstate.xics_phys, or
* indirectly, via OPAL.
*/
#ifdef CONFIG_SMP
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 49a2c7825e04..de18299f92b7 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -251,7 +251,7 @@ void kvmhv_rm_send_ipi(int cpu)
return;
/* Else poke the target with an IPI */
- xics_phys = paca[cpu].kvm_hstate.xics_phys;
+ xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys;
if (xics_phys)
__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
else
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index dc54373c8780..0e8493033288 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -79,8 +79,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
li r5, 0
mtspr SPRN_MMCRA, r5
isync
- ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */
- lbz r5, LPPACA_PMCINUSE(r3)
+ lbz r5, PACA_PMCINUSE(r13) /* is the host using the PMU? */
cmpwi r5, 0
beq 31f /* skip if not */
mfspr r5, SPRN_MMCR1
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index f86a20270e50..bd63fa8a08b5 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -113,8 +113,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_SPRG_VDSO_WRITE,r3
/* Reload the host's PMU registers */
- ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */
- lbz r4, LPPACA_PMCINUSE(r3)
+ lbz r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
cmpwi r4, 0
beq 23f /* skip if not */
BEGIN_FTR_SECTION
@@ -786,12 +785,18 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Branch around the call if both CPU_FTR_TM and
+ * CPU_FTR_P9_TM_HV_ASSIST are off.
+ */
BEGIN_FTR_SECTION
+ b 91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
bl kvmppc_restore_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
#endif
/* Load guest PMU registers */
@@ -885,8 +890,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
ld r6, VCPU_DAWRX(r4)
ld r7, VCPU_CIABR(r4)
ld r8, VCPU_TAR(r4)
+ /*
+ * Handle broken DAWR case by not writing it. This means we
+ * can still store the DAWR register for migration.
+ */
+BEGIN_FTR_SECTION
mtspr SPRN_DAWR, r5
mtspr SPRN_DAWRX, r6
+END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
mtspr SPRN_CIABR, r7
mtspr SPRN_TAR, r8
ld r5, VCPU_IC(r4)
@@ -914,11 +925,14 @@ BEGIN_FTR_SECTION
mtspr SPRN_ACOP, r6
mtspr SPRN_CSIGR, r7
mtspr SPRN_TACR, r8
+ nop
FTR_SECTION_ELSE
/* POWER9-only registers */
ld r5, VCPU_TID(r4)
ld r6, VCPU_PSSCR(r4)
+ lbz r8, HSTATE_FAKE_SUSPEND(r13)
oris r6, r6, PSSCR_EC@h /* This makes stop trap to HV */
+ rldimi r6, r8, PSSCR_FAKE_SUSPEND_LG, 63 - PSSCR_FAKE_SUSPEND_LG
ld r7, VCPU_HFSCR(r4)
mtspr SPRN_TIDR, r5
mtspr SPRN_PSSCR, r6
@@ -1370,6 +1384,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
std r3, VCPU_CTR(r9)
std r4, VCPU_XER(r9)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* For softpatch interrupt, go off and do TM instruction emulation */
+ cmpwi r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
+ beq kvmppc_tm_emul
+#endif
+
/* If this is a page table miss then see if it's theirs or ours */
cmpwi r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
beq kvmppc_hdsi
@@ -1747,12 +1767,18 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
bl kvmppc_save_fp
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Branch around the call if both CPU_FTR_TM and
+ * CPU_FTR_P9_TM_HV_ASSIST are off.
+ */
BEGIN_FTR_SECTION
+ b 91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
bl kvmppc_save_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
#endif
/* Increment yield count if they have a VPA */
@@ -1852,6 +1878,10 @@ BEGIN_FTR_SECTION
ld r6, STACK_SLOT_DAWR(r1)
ld r7, STACK_SLOT_DAWRX(r1)
mtspr SPRN_CIABR, r5
+ /*
+ * If the DAWR doesn't work, it's ok to write these here as
+ * this value should always be zero
+ */
mtspr SPRN_DAWR, r6
mtspr SPRN_DAWRX, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
@@ -2055,6 +2085,42 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
mtlr r0
blr
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Softpatch interrupt for transactional memory emulation cases
+ * on POWER9 DD2.2. This is early in the guest exit path - we
+ * haven't saved registers or done a treclaim yet.
+ */
+kvmppc_tm_emul:
+ /* Save instruction image in HEIR */
+ mfspr r3, SPRN_HEIR
+ stw r3, VCPU_HEIR(r9)
+
+ /*
+ * The cases we want to handle here are those where the guest
+ * is in real suspend mode and is trying to transition to
+ * transactional mode.
+ */
+ lbz r0, HSTATE_FAKE_SUSPEND(r13)
+ cmpwi r0, 0 /* keep exiting guest if in fake suspend */
+ bne guest_exit_cont
+ rldicl r3, r11, 64 - MSR_TS_S_LG, 62
+ cmpwi r3, 1 /* or if not in suspend state */
+ bne guest_exit_cont
+
+ /* Call C code to do the emulation */
+ mr r3, r9
+ bl kvmhv_p9_tm_emulation_early
+ nop
+ ld r9, HSTATE_KVM_VCPU(r13)
+ li r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
+ cmpwi r3, 0
+ beq guest_exit_cont /* continue exiting if not handled */
+ ld r10, VCPU_PC(r9)
+ ld r11, VCPU_MSR(r9)
+ b fast_interrupt_c_return /* go back to guest if handled */
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
/*
* Check whether an HDSI is an HPTE not found fault or something else.
* If it is an HPTE not found fault that is due to the guest accessing
@@ -2507,8 +2573,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
li r3,0
blr
+2:
+BEGIN_FTR_SECTION
+ /* POWER9 with disabled DAWR */
+ li r3, H_HARDWARE
+ blr
+END_FTR_SECTION_IFCLR(CPU_FTR_DAWR)
/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
-2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW
+ rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW
rlwimi r5, r4, 2, DAWRX_WT
clrrdi r4, r4, 3
std r4, VCPU_DAWR(r3)
@@ -2588,13 +2660,19 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
bl kvmppc_save_fp
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Branch around the call if both CPU_FTR_TM and
+ * CPU_FTR_P9_TM_HV_ASSIST are off.
+ */
BEGIN_FTR_SECTION
+ b 91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
ld r9, HSTATE_KVM_VCPU(r13)
bl kvmppc_save_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
#endif
/*
@@ -2701,12 +2779,18 @@ kvm_end_cede:
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Branch around the call if both CPU_FTR_TM and
+ * CPU_FTR_P9_TM_HV_ASSIST are off.
+ */
BEGIN_FTR_SECTION
+ b 91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
bl kvmppc_restore_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
#endif
/* load up FP state */
@@ -3033,6 +3117,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
kvmppc_save_tm:
mflr r0
std r0, PPC_LR_STKOFF(r1)
+ stdu r1, -PPC_MIN_STKFRM(r1)
/* Turn on TM. */
mfmsr r8
@@ -3047,6 +3132,24 @@ kvmppc_save_tm:
std r1, HSTATE_HOST_R1(r13)
li r3, TM_CAUSE_KVM_RESCHED
+BEGIN_FTR_SECTION
+ lbz r0, HSTATE_FAKE_SUSPEND(r13) /* Were we fake suspended? */
+ cmpwi r0, 0
+ beq 3f
+ rldicl. r8, r8, 64 - MSR_TS_S_LG, 62 /* Did we actually hrfid? */
+ beq 4f
+BEGIN_FTR_SECTION_NESTED(96)
+ bl pnv_power9_force_smt4_catch
+END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
+ nop
+ b 6f
+3:
+ /* Emulation of the treclaim instruction needs TEXASR before treclaim */
+ mfspr r6, SPRN_TEXASR
+ std r6, VCPU_ORIG_TEXASR(r9)
+6:
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
+
/* Clear the MSR RI since r1, r13 are all going to be foobar. */
li r5, 0
mtmsrd r5, 1
@@ -3058,6 +3161,43 @@ kvmppc_save_tm:
SET_SCRATCH0(r13)
GET_PACA(r13)
std r9, PACATMSCRATCH(r13)
+
+ /* If doing TM emulation on POWER9 DD2.2, check for fake suspend mode */
+BEGIN_FTR_SECTION
+ lbz r9, HSTATE_FAKE_SUSPEND(r13)
+ cmpwi r9, 0
+ beq 2f
+ /*
+ * We were in fake suspend, so we are not going to save the
+ * register state as the guest checkpointed state (since
+ * we already have it), therefore we can now use any volatile GPR.
+ */
+ /* Reload stack pointer and TOC. */
+ ld r1, HSTATE_HOST_R1(r13)
+ ld r2, PACATOC(r13)
+ /* Set MSR RI now we have r1 and r13 back. */
+ li r5, MSR_RI
+ mtmsrd r5, 1
+ HMT_MEDIUM
+ ld r6, HSTATE_DSCR(r13)
+ mtspr SPRN_DSCR, r6
+BEGIN_FTR_SECTION_NESTED(96)
+ bl pnv_power9_force_smt4_release
+END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
+ nop
+
+4:
+ mfspr r3, SPRN_PSSCR
+ /* PSSCR_FAKE_SUSPEND is a write-only bit, but clear it anyway */
+ li r0, PSSCR_FAKE_SUSPEND
+ andc r3, r3, r0
+ mtspr SPRN_PSSCR, r3
+ ld r9, HSTATE_KVM_VCPU(r13)
+ /* Don't save TEXASR, use value from last exit in real suspend state */
+ b 11f
+2:
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
+
ld r9, HSTATE_KVM_VCPU(r13)
/* Get a few more GPRs free. */
@@ -3128,13 +3268,15 @@ kvmppc_save_tm:
* change these outside of a transaction, so they must always be
* context switched.
*/
+ mfspr r7, SPRN_TEXASR
+ std r7, VCPU_TEXASR(r9)
+11:
mfspr r5, SPRN_TFHAR
mfspr r6, SPRN_TFIAR
- mfspr r7, SPRN_TEXASR
std r5, VCPU_TFHAR(r9)
std r6, VCPU_TFIAR(r9)
- std r7, VCPU_TEXASR(r9)
+ addi r1, r1, PPC_MIN_STKFRM
ld r0, PPC_LR_STKOFF(r1)
mtlr r0
blr
@@ -3169,6 +3311,8 @@ kvmppc_restore_tm:
mtspr SPRN_TFIAR, r6
mtspr SPRN_TEXASR, r7
+ li r0, 0
+ stb r0, HSTATE_FAKE_SUSPEND(r13)
ld r5, VCPU_MSR(r4)
rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
beqlr /* TM not active in guest */
@@ -3183,6 +3327,15 @@ kvmppc_restore_tm:
mtspr SPRN_TEXASR, r7
/*
+ * If we are doing TM emulation for the guest on a POWER9 DD2,
+ * then we don't actually do a trechkpt -- we either set up
+ * fake-suspend mode, or emulate a TM rollback.
+ */
+BEGIN_FTR_SECTION
+ b .Ldo_tm_fake_load
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_HV_ASSIST)
+
+ /*
* We need to load up the checkpointed state for the guest.
* We need to do this early as it will blow away any GPRs, VSRs and
* some SPRs.
@@ -3254,10 +3407,24 @@ kvmppc_restore_tm:
/* Set the MSR RI since we have our registers back. */
li r5, MSR_RI
mtmsrd r5, 1
-
+9:
ld r0, PPC_LR_STKOFF(r1)
mtlr r0
blr
+
+.Ldo_tm_fake_load:
+ cmpwi r5, 1 /* check for suspended state */
+ bgt 10f
+ stb r5, HSTATE_FAKE_SUSPEND(r13)
+ b 9b /* and return */
+10: stdu r1, -PPC_MIN_STKFRM(r1)
+ /* guest is in transactional state, so simulate rollback */
+ mr r3, r4
+ bl kvmhv_emulate_tm_rollback
+ nop
+ ld r4, HSTATE_KVM_VCPU(r13) /* our vcpu pointer has been trashed */
+ addi r1, r1, PPC_MIN_STKFRM
+ b 9b
#endif
/*
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
new file mode 100644
index 000000000000..bf710ad3a6d7
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -0,0 +1,216 @@
+/*
+ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_book3s_64.h>
+#include <asm/reg.h>
+#include <asm/ppc-opcode.h>
+
+static void emulate_tx_failure(struct kvm_vcpu *vcpu, u64 failure_cause)
+{
+ u64 texasr, tfiar;
+ u64 msr = vcpu->arch.shregs.msr;
+
+ tfiar = vcpu->arch.pc & ~0x3ull;
+ texasr = (failure_cause << 56) | TEXASR_ABORT | TEXASR_FS | TEXASR_EXACT;
+ if (MSR_TM_SUSPENDED(vcpu->arch.shregs.msr))
+ texasr |= TEXASR_SUSP;
+ if (msr & MSR_PR) {
+ texasr |= TEXASR_PR;
+ tfiar |= 1;
+ }
+ vcpu->arch.tfiar = tfiar;
+ /* Preserve ROT and TL fields of existing TEXASR */
+ vcpu->arch.texasr = (vcpu->arch.texasr & 0x3ffffff) | texasr;
+}
+
+/*
+ * This gets called on a softpatch interrupt on POWER9 DD2.2 processors.
+ * We expect to find a TM-related instruction to be emulated. The
+ * instruction image is in vcpu->arch.emul_inst. If the guest was in
+ * TM suspended or transactional state, the checkpointed state has been
+ * reclaimed and is in the vcpu struct. The CPU is in virtual mode in
+ * host context.
+ */
+int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
+{
+ u32 instr = vcpu->arch.emul_inst;
+ u64 msr = vcpu->arch.shregs.msr;
+ u64 newmsr, bescr;
+ int ra, rs;
+
+ switch (instr & 0xfc0007ff) {
+ case PPC_INST_RFID:
+ /* XXX do we need to check for PR=0 here? */
+ newmsr = vcpu->arch.shregs.srr1;
+ /* should only get here for Sx -> T1 transition */
+ WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+ MSR_TM_TRANSACTIONAL(newmsr) &&
+ (newmsr & MSR_TM)));
+ newmsr = sanitize_msr(newmsr);
+ vcpu->arch.shregs.msr = newmsr;
+ vcpu->arch.cfar = vcpu->arch.pc - 4;
+ vcpu->arch.pc = vcpu->arch.shregs.srr0;
+ return RESUME_GUEST;
+
+ case PPC_INST_RFEBB:
+ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ /* check EBB facility is available */
+ if (!(vcpu->arch.hfscr & HFSCR_EBB)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ if ((msr & MSR_PR) && !(vcpu->arch.fscr & FSCR_EBB)) {
+ /* generate a facility unavailable interrupt */
+ vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+ ((u64)FSCR_EBB_LG << 56);
+ kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
+ return RESUME_GUEST;
+ }
+ bescr = vcpu->arch.bescr;
+ /* expect to see a S->T transition requested */
+ WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+ ((bescr >> 30) & 3) == 2));
+ bescr &= ~BESCR_GE;
+ if (instr & (1 << 11))
+ bescr |= BESCR_GE;
+ vcpu->arch.bescr = bescr;
+ msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+ vcpu->arch.shregs.msr = msr;
+ vcpu->arch.cfar = vcpu->arch.pc - 4;
+ vcpu->arch.pc = vcpu->arch.ebbrr;
+ return RESUME_GUEST;
+
+ case PPC_INST_MTMSRD:
+ /* XXX do we need to check for PR=0 here? */
+ rs = (instr >> 21) & 0x1f;
+ newmsr = kvmppc_get_gpr(vcpu, rs);
+ /* check this is a Sx -> T1 transition */
+ WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+ MSR_TM_TRANSACTIONAL(newmsr) &&
+ (newmsr & MSR_TM)));
+ /* mtmsrd doesn't change LE */
+ newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
+ newmsr = sanitize_msr(newmsr);
+ vcpu->arch.shregs.msr = newmsr;
+ return RESUME_GUEST;
+
+ case PPC_INST_TSR:
+ /* check for PR=1 and arch 2.06 bit set in PCR */
+ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ /* check for TM disabled in the HFSCR or MSR */
+ if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ if (!(msr & MSR_TM)) {
+ /* generate a facility unavailable interrupt */
+ vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+ ((u64)FSCR_TM_LG << 56);
+ kvmppc_book3s_queue_irqprio(vcpu,
+ BOOK3S_INTERRUPT_FAC_UNAVAIL);
+ return RESUME_GUEST;
+ }
+ /* Set CR0 to indicate previous transactional state */
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+ (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+ /* L=1 => tresume, L=0 => tsuspend */
+ if (instr & (1 << 21)) {
+ if (MSR_TM_SUSPENDED(msr))
+ msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+ } else {
+ if (MSR_TM_TRANSACTIONAL(msr))
+ msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
+ }
+ vcpu->arch.shregs.msr = msr;
+ return RESUME_GUEST;
+
+ case PPC_INST_TRECLAIM:
+ /* check for TM disabled in the HFSCR or MSR */
+ if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ if (!(msr & MSR_TM)) {
+ /* generate a facility unavailable interrupt */
+ vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+ ((u64)FSCR_TM_LG << 56);
+ kvmppc_book3s_queue_irqprio(vcpu,
+ BOOK3S_INTERRUPT_FAC_UNAVAIL);
+ return RESUME_GUEST;
+ }
+ /* If no transaction active, generate TM bad thing */
+ if (!MSR_TM_ACTIVE(msr)) {
+ kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+ return RESUME_GUEST;
+ }
+ /* If failure was not previously recorded, recompute TEXASR */
+ if (!(vcpu->arch.orig_texasr & TEXASR_FS)) {
+ ra = (instr >> 16) & 0x1f;
+ if (ra)
+ ra = kvmppc_get_gpr(vcpu, ra) & 0xff;
+ emulate_tx_failure(vcpu, ra);
+ }
+
+ copy_from_checkpoint(vcpu);
+
+ /* Set CR0 to indicate previous transactional state */
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+ (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+ vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+ return RESUME_GUEST;
+
+ case PPC_INST_TRECHKPT:
+ /* XXX do we need to check for PR=0 here? */
+ /* check for TM disabled in the HFSCR or MSR */
+ if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ if (!(msr & MSR_TM)) {
+ /* generate a facility unavailable interrupt */
+ vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+ ((u64)FSCR_TM_LG << 56);
+ kvmppc_book3s_queue_irqprio(vcpu,
+ BOOK3S_INTERRUPT_FAC_UNAVAIL);
+ return RESUME_GUEST;
+ }
+ /* If transaction active or TEXASR[FS] = 0, bad thing */
+ if (MSR_TM_ACTIVE(msr) || !(vcpu->arch.texasr & TEXASR_FS)) {
+ kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+ return RESUME_GUEST;
+ }
+
+ copy_to_checkpoint(vcpu);
+
+ /* Set CR0 to indicate previous transactional state */
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+ (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+ vcpu->arch.shregs.msr = msr | MSR_TS_S;
+ return RESUME_GUEST;
+ }
+
+ /* What should we do here? We didn't recognize the instruction */
+ WARN_ON_ONCE(1);
+ return RESUME_GUEST;
+}
diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c
new file mode 100644
index 000000000000..d98ccfd2b88c
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_book3s_64.h>
+#include <asm/reg.h>
+#include <asm/ppc-opcode.h>
+
+/*
+ * This handles the cases where the guest is in real suspend mode
+ * and we want to get back to the guest without dooming the transaction.
+ * The caller has checked that the guest is in real-suspend mode
+ * (MSR[TS] = S and the fake-suspend flag is not set).
+ */
+int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
+{
+ u32 instr = vcpu->arch.emul_inst;
+ u64 newmsr, msr, bescr;
+ int rs;
+
+ switch (instr & 0xfc0007ff) {
+ case PPC_INST_RFID:
+ /* XXX do we need to check for PR=0 here? */
+ newmsr = vcpu->arch.shregs.srr1;
+ /* should only get here for Sx -> T1 transition */
+ if (!(MSR_TM_TRANSACTIONAL(newmsr) && (newmsr & MSR_TM)))
+ return 0;
+ newmsr = sanitize_msr(newmsr);
+ vcpu->arch.shregs.msr = newmsr;
+ vcpu->arch.cfar = vcpu->arch.pc - 4;
+ vcpu->arch.pc = vcpu->arch.shregs.srr0;
+ return 1;
+
+ case PPC_INST_RFEBB:
+ /* check for PR=1 and arch 2.06 bit set in PCR */
+ msr = vcpu->arch.shregs.msr;
+ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206))
+ return 0;
+ /* check EBB facility is available */
+ if (!(vcpu->arch.hfscr & HFSCR_EBB) ||
+ ((msr & MSR_PR) && !(mfspr(SPRN_FSCR) & FSCR_EBB)))
+ return 0;
+ bescr = mfspr(SPRN_BESCR);
+ /* expect to see a S->T transition requested */
+ if (((bescr >> 30) & 3) != 2)
+ return 0;
+ bescr &= ~BESCR_GE;
+ if (instr & (1 << 11))
+ bescr |= BESCR_GE;
+ mtspr(SPRN_BESCR, bescr);
+ msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+ vcpu->arch.shregs.msr = msr;
+ vcpu->arch.cfar = vcpu->arch.pc - 4;
+ vcpu->arch.pc = mfspr(SPRN_EBBRR);
+ return 1;
+
+ case PPC_INST_MTMSRD:
+ /* XXX do we need to check for PR=0 here? */
+ rs = (instr >> 21) & 0x1f;
+ newmsr = kvmppc_get_gpr(vcpu, rs);
+ msr = vcpu->arch.shregs.msr;
+ /* check this is a Sx -> T1 transition */
+ if (!(MSR_TM_TRANSACTIONAL(newmsr) && (newmsr & MSR_TM)))
+ return 0;
+ /* mtmsrd doesn't change LE */
+ newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
+ newmsr = sanitize_msr(newmsr);
+ vcpu->arch.shregs.msr = newmsr;
+ return 1;
+
+ case PPC_INST_TSR:
+ /* we know the MSR has the TS field = S (0b01) here */
+ msr = vcpu->arch.shregs.msr;
+ /* check for PR=1 and arch 2.06 bit set in PCR */
+ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206))
+ return 0;
+ /* check for TM disabled in the HFSCR or MSR */
+ if (!(vcpu->arch.hfscr & HFSCR_TM) || !(msr & MSR_TM))
+ return 0;
+ /* L=1 => tresume => set TS to T (0b10) */
+ if (instr & (1 << 21))
+ vcpu->arch.shregs.msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+ /* Set CR0 to 0b0010 */
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0x20000000;
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * This is called when we are returning to a guest in TM transactional
+ * state. We roll the guest state back to the checkpointed state.
+ */
+void kvmhv_emulate_tm_rollback(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.shregs.msr &= ~MSR_TS_MASK; /* go to N state */
+ vcpu->arch.pc = vcpu->arch.tfhar;
+ copy_from_checkpoint(vcpu);
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0xa0000000;
+}
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 3ae752314b34..d3f304d06adf 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -277,15 +277,6 @@ static void do_kvm_unmap_hva(struct kvm *kvm, unsigned long start,
}
}
-static int kvm_unmap_hva_pr(struct kvm *kvm, unsigned long hva)
-{
- trace_kvm_unmap_hva(hva);
-
- do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE);
-
- return 0;
-}
-
static int kvm_unmap_hva_range_pr(struct kvm *kvm, unsigned long start,
unsigned long end)
{
@@ -1773,7 +1764,6 @@ static struct kvmppc_ops kvm_ops_pr = {
.flush_memslot = kvmppc_core_flush_memslot_pr,
.prepare_memory_region = kvmppc_core_prepare_memory_region_pr,
.commit_memory_region = kvmppc_core_commit_memory_region_pr,
- .unmap_hva = kvm_unmap_hva_pr,
.unmap_hva_range = kvm_unmap_hva_range_pr,
.age_hva = kvm_age_hva_pr,
.test_age_hva = kvm_test_age_hva_pr,
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 423b21393bc9..c878b4ffb86f 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -724,7 +724,7 @@ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
/************* MMU Notifiers *************/
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
{
trace_kvm_unmap_hva(hva);
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 4d8b4d6cebff..fa888bfc347e 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -45,12 +45,6 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
#ifdef CONFIG_PPC_BOOK3S
/* mtdec lowers the interrupt line when positive. */
kvmppc_core_dequeue_dec(vcpu);
-
- /* POWER4+ triggers a dec interrupt if the value is < 0 */
- if (vcpu->arch.dec & 0x80000000) {
- kvmppc_core_queue_dec(vcpu);
- return;
- }
#endif
#ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 52c205373986..4e387647b5af 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -646,10 +646,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = hv_enabled;
break;
#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
case KVM_CAP_PPC_HTM:
r = hv_enabled &&
- (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM_COMP);
+ (!!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
+ cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST));
break;
+#endif
default:
r = 0;
break;
diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h
index 85785a370c0e..2f9a8829552b 100644
--- a/arch/powerpc/kvm/trace_pr.h
+++ b/arch/powerpc/kvm/trace_pr.h
@@ -254,21 +254,6 @@ TRACE_EVENT(kvm_exit,
)
);
-TRACE_EVENT(kvm_unmap_hva,
- TP_PROTO(unsigned long hva),
- TP_ARGS(hva),
-
- TP_STRUCT__entry(
- __field( unsigned long, hva )
- ),
-
- TP_fast_assign(
- __entry->hva = hva;
- ),
-
- TP_printk("unmap hva 0x%lx\n", __entry->hva)
-);
-
#endif /* _TRACE_KVM_H */
/* This part must be outside protection */
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.