From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
To: kvm-ppc@vger.kernel.org
Cc: paulus@ozlabs.org, kvm@vger.kernel.org
Subject: [PATCH 01/23] KVM: PPC: Book3S HV: Use __gfn_to_pfn_memslot in HPT page fault handler
Date: Mon, 26 Aug 2019 16:20:47 +1000 [thread overview]
Message-ID: <20190826062109.7573-2-sjitindarsingh@gmail.com> (raw)
In-Reply-To: <20190826062109.7573-1-sjitindarsingh@gmail.com>
From: Paul Mackerras <paulus@ozlabs.org>
This makes the same changes in the page fault handler for HPT guests
that commits 31c8b0d0694a ("KVM: PPC: Book3S HV: Use __gfn_to_pfn_memslot()
in page fault handler", 2018-03-01), 71d29f43b633 ("KVM: PPC: Book3S HV:
Don't use compound_order to determine host mapping size", 2018-09-11)
and 6579804c4317 ("KVM: PPC: Book3S HV: Avoid crash from THP collapse
during radix page fault", 2018-10-04) made for the page fault handler
for radix guests.
In summary, where we used to call get_user_pages_fast() and then do
special handling for VM_PFNMAP vmas, we now call __get_user_pages_fast()
and then __gfn_to_pfn_memslot() if that fails, followed by reading the
Linux PTE to get the host PFN, host page size and mapping attributes.
This also brings in the change from SetPageDirty() to set_page_dirty_lock()
which was done for the radix page fault handler in commit c3856aeb2940
("KVM: PPC: Book3S HV: Fix handling of large pages in radix page fault
handler", 2018-02-23).
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_64_mmu_hv.c | 118 +++++++++++++++++-------------------
1 file changed, 57 insertions(+), 61 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 9a75f0e1933b..a485bb018193 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -497,17 +497,18 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
__be64 *hptep;
unsigned long mmu_seq, psize, pte_size;
unsigned long gpa_base, gfn_base;
- unsigned long gpa, gfn, hva, pfn;
+ unsigned long gpa, gfn, hva, pfn, hpa;
struct kvm_memory_slot *memslot;
unsigned long *rmap;
struct revmap_entry *rev;
- struct page *page, *pages[1];
- long index, ret, npages;
+ struct page *page;
+ long index, ret;
bool is_ci;
- unsigned int writing, write_ok;
- struct vm_area_struct *vma;
+ bool writing, write_ok;
+ unsigned int shift;
unsigned long rcbits;
long mmio_update;
+ pte_t pte, *ptep;
if (kvm_is_radix(kvm))
return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr);
@@ -581,59 +582,62 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
smp_rmb();
ret = -EFAULT;
- is_ci = false;
- pfn = 0;
page = NULL;
- pte_size = PAGE_SIZE;
writing = (dsisr & DSISR_ISSTORE) != 0;
/* If writing != 0, then the HPTE must allow writing, if we get here */
write_ok = writing;
hva = gfn_to_hva_memslot(memslot, gfn);
- npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages);
- if (npages < 1) {
- /* Check if it's an I/O mapping */
- down_read(¤t->mm->mmap_sem);
- vma = find_vma(current->mm, hva);
- if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end &&
- (vma->vm_flags & VM_PFNMAP)) {
- pfn = vma->vm_pgoff +
- ((hva - vma->vm_start) >> PAGE_SHIFT);
- pte_size = psize;
- is_ci = pte_ci(__pte((pgprot_val(vma->vm_page_prot))));
- write_ok = vma->vm_flags & VM_WRITE;
- }
- up_read(¤t->mm->mmap_sem);
- if (!pfn)
- goto out_put;
+
+ /*
+ * 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.
+ */
+ if (__get_user_pages_fast(hva, 1, 1, &page) == 1) {
+ write_ok = true;
} else {
- page = pages[0];
- pfn = page_to_pfn(page);
- if (PageHuge(page)) {
- page = compound_head(page);
- pte_size <<= compound_order(page);
- }
- /* if the guest wants write access, see if that is OK */
- if (!writing && hpte_is_writable(r)) {
- pte_t *ptep, pte;
- unsigned long flags;
- /*
- * We need to protect against page table destruction
- * hugepage split and collapse.
- */
- local_irq_save(flags);
- ptep = find_current_mm_pte(current->mm->pgd,
- hva, NULL, NULL);
- if (ptep) {
- pte = kvmppc_read_update_linux_pte(ptep, 1);
- if (__pte_write(pte))
- write_ok = 1;
- }
- local_irq_restore(flags);
+ /* Call KVM generic code to do the slow-path check */
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ writing, &write_ok);
+ if (is_error_noslot_pfn(pfn))
+ return -EFAULT;
+ page = NULL;
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ if (PageReserved(page))
+ page = NULL;
}
}
+ /*
+ * Read the PTE from the process' radix tree and use that
+ * so we get the shift and attribute bits.
+ */
+ local_irq_disable();
+ ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+ /*
+ * If the PTE disappeared temporarily due to a THP
+ * collapse, just return and let the guest try again.
+ */
+ if (!ptep) {
+ local_irq_enable();
+ if (page)
+ put_page(page);
+ return RESUME_GUEST;
+ }
+ pte = *ptep;
+ local_irq_enable();
+ hpa = pte_pfn(pte) << PAGE_SHIFT;
+ pte_size = PAGE_SIZE;
+ if (shift)
+ pte_size = 1ul << shift;
+ is_ci = pte_ci(pte);
+
if (psize > pte_size)
goto out_put;
+ if (pte_size > psize)
+ hpa |= hva & (pte_size - psize);
/* Check WIMG vs. the actual page we're accessing */
if (!hpte_cache_flags_ok(r, is_ci)) {
@@ -647,14 +651,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
}
/*
- * Set the HPTE to point to pfn.
- * Since the pfn is at PAGE_SIZE granularity, make sure we
+ * Set the HPTE to point to hpa.
+ * Since the hpa is at PAGE_SIZE granularity, make sure we
* don't mask out lower-order bits if psize < PAGE_SIZE.
*/
if (psize < PAGE_SIZE)
psize = PAGE_SIZE;
- r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) |
- ((pfn << PAGE_SHIFT) & ~(psize - 1));
+ r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) | hpa;
if (hpte_is_writable(r) && !write_ok)
r = hpte_make_readonly(r);
ret = RESUME_GUEST;
@@ -719,20 +722,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
asm volatile("ptesync" : : : "memory");
preempt_enable();
if (page && hpte_is_writable(r))
- SetPageDirty(page);
+ set_page_dirty_lock(page);
out_put:
trace_kvm_page_fault_exit(vcpu, hpte, ret);
- if (page) {
- /*
- * We drop pages[0] here, not page because page might
- * have been set to the head page of a compound, but
- * we have to drop the reference on the correct tail
- * page to match the get inside gup()
- */
- put_page(pages[0]);
- }
+ if (page)
+ put_page(page);
return ret;
out_unlock:
--
2.13.6
next prev parent reply other threads:[~2019-08-26 6:21 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-26 6:20 [PATCH 00/23] KVM: PPC: BOok3S HV: Support for nested HPT guests Suraj Jitindar Singh
2019-08-26 6:20 ` Suraj Jitindar Singh [this message]
2019-08-26 6:20 ` [PATCH 02/23] KVM: PPC: Book3S HV: Increment mmu_notifier_seq when modifying radix pte rc bits Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 03/23] KVM: PPC: Book3S HV: Nested: Don't allow hash guests to run nested guests Suraj Jitindar Singh
2019-10-23 4:47 ` Paul Mackerras
2019-08-26 6:20 ` [PATCH 04/23] KVM: PPC: Book3S HV: Handle making H_ENTER_NESTED hcall in a separate function Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 05/23] KVM: PPC: Book3S HV: Enable calling kvmppc_hpte_hv_fault in virtual mode Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 06/23] KVM: PPC: Book3S HV: Allow hpt manipulation hcalls to be called " Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 07/23] KVM: PPC: Book3S HV: Make kvmppc_invalidate_hpte() take lpid not a kvm struct Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 08/23] KVM: PPC: Book3S HV: Nested: Allow pseries hypervisor to run hpt nested guest Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 09/23] KVM: PPC: Book3S HV: Nested: Improve comments and naming of nest rmap functions Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 10/23] KVM: PPC: Book3S HV: Nested: Increase gpa field in nest rmap to 46 bits Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 11/23] KVM: PPC: Book3S HV: Nested: Remove single nest rmap entries Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 12/23] KVM: PPC: Book3S HV: Nested: add kvmhv_remove_all_nested_rmap_lpid() Suraj Jitindar Singh
2019-08-26 6:20 ` [PATCH 13/23] KVM: PPC: Book3S HV: Nested: Infrastructure for nested hpt guest setup Suraj Jitindar Singh
2019-10-24 3:43 ` Paul Mackerras
2019-08-26 6:21 ` [PATCH 14/23] KVM: PPC: Book3S HV: Nested: Context switch slb for nested hpt guest Suraj Jitindar Singh
2019-10-24 4:48 ` Paul Mackerras
2019-08-26 6:21 ` [PATCH 15/23] KVM: PPC: Book3S HV: Store lpcr and hdec_exp in the vcpu struct Suraj Jitindar Singh
2019-08-26 6:21 ` [PATCH 16/23] KVM: PPC: Book3S HV: Nested: Make kvmppc_run_vcpu() entry path nested capable Suraj Jitindar Singh
2019-08-26 6:21 ` [PATCH 17/23] KVM: PPC: Book3S HV: Nested: Rename kvmhv_xlate_addr_nested_radix Suraj Jitindar Singh
2019-08-26 6:21 ` [PATCH 18/23] KVM: PPC: Book3S HV: Separate out hashing from kvmppc_hv_find_lock_hpte() Suraj Jitindar Singh
2019-08-26 6:21 ` [PATCH 19/23] KVM: PPC: Book3S HV: Nested: Implement nested hpt mmu translation Suraj Jitindar Singh
2019-08-26 6:21 ` [PATCH 20/23] KVM: PPC: Book3S HV: Nested: Handle tlbie hcall for nested hpt guest Suraj Jitindar Singh
2019-08-26 6:21 ` [PATCH 21/23] KVM: PPC: Book3S HV: Nested: Implement nest rmap invalidations for hpt guests Suraj Jitindar Singh
2019-08-26 6:21 ` [PATCH 22/23] KVM: PPC: Book3S HV: Nested: Enable nested " Suraj Jitindar Singh
2019-08-26 6:21 ` [PATCH 23/23] KVM: PPC: Book3S HV: Add nested hpt pte information to debugfs Suraj Jitindar Singh
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=20190826062109.7573-2-sjitindarsingh@gmail.com \
--to=sjitindarsingh@gmail.com \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=paulus@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).