From: Paul Mackerras <paulus@ozlabs.org>
To: kvm@vger.kernel.org, kvm-ppc@vger.kernel.org
Cc: linuxppc-dev@ozlabs.org, David Gibson <david@gibson.dropbear.id.au>
Subject: [PATCH v4 15/32] KVM: PPC: Book3S HV: Refactor radix page fault handler
Date: Thu, 4 Oct 2018 21:55:52 +1000 [thread overview]
Message-ID: <1538654169-15602-16-git-send-email-paulus@ozlabs.org> (raw)
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
The radix page fault handler accounts for all cases, including just
needing to insert a pte. This breaks it up into separate functions for
the two main cases; setting rc and inserting a pte.
This allows us to make the setting of rc and inserting of a pte
generic for any pgtable, not specific to the one for this guest.
[paulus@ozlabs.org - reduced diffs from previous code]
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_64_mmu_radix.c | 210 +++++++++++++++++++--------------
1 file changed, 123 insertions(+), 87 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index f2976f4..47f2b18 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -400,8 +400,9 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
*/
#define PTE_BITS_MUST_MATCH (~(_PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED))
-static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
- unsigned int level, unsigned long mmu_seq)
+static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
+ unsigned long gpa, unsigned int level,
+ unsigned long mmu_seq)
{
pgd_t *pgd;
pud_t *pud, *new_pud = NULL;
@@ -410,7 +411,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
int ret;
/* Traverse the guest's 2nd-level tree, allocate new levels needed */
- pgd = kvm->arch.pgtable + pgd_index(gpa);
+ pgd = pgtable + pgd_index(gpa);
pud = NULL;
if (pgd_present(*pgd))
pud = pud_offset(pgd, gpa);
@@ -565,95 +566,49 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
return ret;
}
-int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
- unsigned long ea, unsigned long dsisr)
+static bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
+ bool writing, unsigned long gpa)
+{
+ unsigned long pgflags;
+ unsigned int shift;
+ pte_t *ptep;
+
+ /*
+ * Need to set an R or C bit in the 2nd-level tables;
+ * since we are just helping out the hardware here,
+ * it is sufficient to do what the hardware does.
+ */
+ pgflags = _PAGE_ACCESSED;
+ if (writing)
+ pgflags |= _PAGE_DIRTY;
+ /*
+ * We are walking the secondary (partition-scoped) page table here.
+ * We can do this without disabling irq because the Linux MM
+ * subsystem doesn't do THP splits and collapses on this tree.
+ */
+ ptep = __find_linux_pte(pgtable, gpa, NULL, &shift);
+ if (ptep && pte_present(*ptep) && (!writing || pte_write(*ptep))) {
+ kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, gpa, shift);
+ return true;
+ }
+ return false;
+}
+
+static int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
+ unsigned long gpa,
+ struct kvm_memory_slot *memslot,
+ bool writing, bool kvm_ro,
+ pte_t *inserted_pte, unsigned int *levelp)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long mmu_seq;
- unsigned long gpa, gfn, hva;
- struct kvm_memory_slot *memslot;
struct page *page = NULL;
- long ret;
- bool writing;
+ unsigned long mmu_seq;
+ unsigned long hva, gfn = gpa >> PAGE_SHIFT;
bool upgrade_write = false;
bool *upgrade_p = &upgrade_write;
pte_t pte, *ptep;
- unsigned long pgflags;
unsigned int shift, level;
-
- /* Check for unusual errors */
- if (dsisr & DSISR_UNSUPP_MMU) {
- pr_err("KVM: Got unsupported MMU fault\n");
- return -EFAULT;
- }
- if (dsisr & DSISR_BADACCESS) {
- /* Reflect to the guest as DSI */
- pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
- kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
- return RESUME_GUEST;
- }
-
- /* Translate the logical address and get the page */
- gpa = vcpu->arch.fault_gpa & ~0xfffUL;
- gpa &= ~0xF000000000000000ul;
- gfn = gpa >> PAGE_SHIFT;
- if (!(dsisr & DSISR_PRTABLE_FAULT))
- gpa |= ea & 0xfff;
- memslot = gfn_to_memslot(kvm, gfn);
-
- /* No memslot means it's an emulated MMIO region */
- if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
- if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
- DSISR_SET_RC)) {
- /*
- * Bad address in guest page table tree, or other
- * unusual error - reflect it to the guest as DSI.
- */
- kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
- return RESUME_GUEST;
- }
- return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
- dsisr & DSISR_ISSTORE);
- }
-
- writing = (dsisr & DSISR_ISSTORE) != 0;
- 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;
- * since we are just helping out the hardware here,
- * it is sufficient to do what the hardware does.
- */
- pgflags = _PAGE_ACCESSED;
- if (writing)
- pgflags |= _PAGE_DIRTY;
- /*
- * 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;
- }
+ int ret;
/* used to check for invalidations in progress */
mmu_seq = kvm->mmu_notifier_seq;
@@ -666,7 +621,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
* 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) {
+ if (!kvm_ro && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
upgrade_write = true;
} else {
unsigned long pfn;
@@ -724,7 +679,12 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
}
/* Allocate space in the tree and write the PTE */
- ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+ ret = kvmppc_create_pte(kvm, kvm->arch.pgtable, pte, gpa, level,
+ mmu_seq);
+ if (inserted_pte)
+ *inserted_pte = pte;
+ if (levelp)
+ *levelp = level;
if (page) {
if (!ret && (pte_val(pte) & _PAGE_WRITE))
@@ -732,6 +692,82 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
put_page(page);
}
+ return ret;
+}
+
+int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned long ea, unsigned long dsisr)
+{
+ struct kvm *kvm = vcpu->kvm;
+ unsigned long gpa, gfn;
+ struct kvm_memory_slot *memslot;
+ long ret;
+ bool writing = !!(dsisr & DSISR_ISSTORE);
+ bool kvm_ro = false;
+
+ /* Check for unusual errors */
+ if (dsisr & DSISR_UNSUPP_MMU) {
+ pr_err("KVM: Got unsupported MMU fault\n");
+ return -EFAULT;
+ }
+ if (dsisr & DSISR_BADACCESS) {
+ /* Reflect to the guest as DSI */
+ pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
+ kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+ return RESUME_GUEST;
+ }
+
+ /* Translate the logical address */
+ gpa = vcpu->arch.fault_gpa & ~0xfffUL;
+ gpa &= ~0xF000000000000000ul;
+ gfn = gpa >> PAGE_SHIFT;
+ if (!(dsisr & DSISR_PRTABLE_FAULT))
+ gpa |= ea & 0xfff;
+
+ /* Get the corresponding memslot */
+ memslot = gfn_to_memslot(kvm, gfn);
+
+ /* No memslot means it's an emulated MMIO region */
+ if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+ if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
+ DSISR_SET_RC)) {
+ /*
+ * Bad address in guest page table tree, or other
+ * unusual error - reflect it to the guest as DSI.
+ */
+ kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+ return RESUME_GUEST;
+ }
+ return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, writing);
+ }
+
+ if (memslot->flags & KVM_MEM_READONLY) {
+ if (writing) {
+ /* give the guest a DSI */
+ kvmppc_core_queue_data_storage(vcpu, ea, DSISR_ISSTORE |
+ DSISR_PROTFAULT);
+ return RESUME_GUEST;
+ }
+ kvm_ro = true;
+ }
+
+ /* Failed to set the reference/change bits */
+ if (dsisr & DSISR_SET_RC) {
+ spin_lock(&kvm->mmu_lock);
+ if (kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable,
+ writing, gpa))
+ 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;
+ }
+
+ /* Try to insert a pte */
+ ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot, writing,
+ kvm_ro, NULL, NULL);
+
if (ret == 0 || ret == -EAGAIN)
ret = RESUME_GUEST;
return ret;
--
2.7.4
next prev parent reply other threads:[~2018-10-04 12:42 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-04 11:55 [PATCH v4 00/32] KVM: PPC: Book3S HV: Nested HV virtualization Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 01/32] powerpc: Turn off CPU_FTR_P9_TM_HV_ASSIST in non-hypervisor mode Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 02/32] KVM: PPC: Book3S: Simplify external interrupt handling Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 03/32] KVM: PPC: Book3S HV: Remove left-over code in XICS-on-XIVE emulation Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 04/32] KVM: PPC: Book3S HV: Move interrupt delivery on guest entry to C code Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 05/32] KVM: PPC: Book3S HV: Extract PMU save/restore operations as C-callable functions Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 06/32] KVM: PPC: Book3S HV: Simplify real-mode interrupt handling Paul Mackerras
2018-10-05 4:18 ` David Gibson
2018-10-04 11:55 ` [PATCH v4 07/32] KVM: PPC: Book3S: Rework TM save/restore code and make it C-callable Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 08/32] KVM: PPC: Book3S HV: Call kvmppc_handle_exit_hv() with vcore unlocked Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 09/32] KVM: PPC: Book3S HV: Streamlined guest entry/exit path on P9 for radix guests Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 10/32] KVM: PPC: Book3S HV: Handle hypervisor instruction faults better Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 11/32] KVM: PPC: Book3S HV: Add a debugfs file to dump radix mappings Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 12/32] KVM: PPC: Use ccr field in pt_regs struct embedded in vcpu struct Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 13/32] KVM: PPC: Book3S HV: Clear partition table entry on vm teardown Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 14/32] KVM: PPC: Book3S HV: Make kvmppc_mmu_radix_xlate process/partition table agnostic Paul Mackerras
2018-10-04 11:55 ` Paul Mackerras [this message]
2018-10-04 11:55 ` [PATCH v4 16/32] KVM: PPC: Book3S HV: Use kvmppc_unmap_pte() in kvm_unmap_radix() Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 17/32] KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization Paul Mackerras
2018-10-05 4:12 ` David Gibson
2018-10-04 11:55 ` [PATCH v4 18/32] KVM: PPC: Book3S HV: Nested guest entry via hypercall Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 19/32] KVM: PPC: Book3S HV: Use XICS hypercalls when running as a nested hypervisor Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 20/32] KVM: PPC: Book3S HV: Handle hypercalls correctly when nested Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 21/32] KVM: PPC: Book3S HV: Handle page fault for a nested guest Paul Mackerras
2018-10-04 11:55 ` [PATCH v4 22/32] KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings Paul Mackerras
2018-10-05 2:49 ` David Gibson
2018-10-04 11:56 ` [PATCH v4 23/32] KVM: PPC: Book3S HV: Implement H_TLB_INVALIDATE hcall Paul Mackerras
2018-10-05 3:40 ` David Gibson
2018-10-04 11:56 ` [PATCH v4 24/32] KVM: PPC: Book3S HV: Use hypercalls for TLB invalidation when nested Paul Mackerras
2018-10-05 3:45 ` David Gibson
2018-10-04 11:56 ` [PATCH v4 25/32] KVM: PPC: Book3S HV: Invalidate TLB when nested vcpu moves physical cpu Paul Mackerras
2018-10-05 4:09 ` David Gibson
2018-10-05 4:23 ` Paul Mackerras
2018-10-05 4:54 ` David Gibson
2018-10-05 5:32 ` Paul Mackerras
2018-10-08 2:02 ` David Gibson
2018-10-04 11:56 ` [PATCH v4 26/32] KVM: PPC: Book3S HV: Don't access HFSCR, LPIDR or LPCR when running nested Paul Mackerras
2018-10-04 11:56 ` [PATCH v4 27/32] KVM: PPC: Book3S HV: Add one-reg interface to virtual PTCR register Paul Mackerras
2018-10-04 11:56 ` [PATCH v4 28/32] KVM: PPC: Book3S HV: Sanitise hv_regs on nested guest entry Paul Mackerras
2018-10-04 11:56 ` [PATCH v4 29/32] KVM: PPC: Book3S HV: Handle differing endianness for H_ENTER_NESTED Paul Mackerras
2018-10-04 11:56 ` [PATCH v4 30/32] KVM: PPC: Book3S HV: Allow HV module to load without hypervisor mode Paul Mackerras
2018-10-05 3:05 ` David Gibson
2018-10-04 11:56 ` [PATCH v4 31/32] KVM: PPC: Book3S HV: Add nested shadow page tables to debugfs Paul Mackerras
2018-10-04 11:56 ` [PATCH v4 32/32] KVM: PPC: Book3S HV: Add a VM capability to enable nested virtualization Paul Mackerras
2018-10-05 3:06 ` David Gibson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1538654169-15602-16-git-send-email-paulus@ozlabs.org \
--to=paulus@ozlabs.org \
--cc=david@gibson.dropbear.id.au \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linuxppc-dev@ozlabs.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).