* [PATCH v2 1/1] KVM: s390: pv: fix race when making a page secure
2025-02-26 12:37 [PATCH v2 0/1] KVM: s390: fix a newly introduced bug Claudio Imbrenda
@ 2025-02-26 12:37 ` Claudio Imbrenda
2025-02-26 15:05 ` David Hildenbrand
0 siblings, 1 reply; 6+ messages in thread
From: Claudio Imbrenda @ 2025-02-26 12:37 UTC (permalink / raw)
To: kvm
Cc: linux-kernel, linux-s390, frankja, borntraeger, david, nrb,
seiden, nsg, schlameuss, hca
Holding the pte lock for the page that is being converted to secure is
needed to avoid races. A previous commit removed the locking, which
caused issues. Fix by locking the pte again.
Fixes: 5cbe24350b7d ("KVM: s390: move pv gmap functions into kvm")
Reported-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
arch/s390/include/asm/uv.h | 2 +-
arch/s390/kernel/uv.c | 105 ++++++++++++++++++++++++++++++++++---
arch/s390/kvm/gmap.c | 99 +++-------------------------------
arch/s390/kvm/kvm-s390.c | 25 +++++----
4 files changed, 121 insertions(+), 110 deletions(-)
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index b11f5b6d0bd1..46fb0ef6f984 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -631,7 +631,7 @@ int uv_pin_shared(unsigned long paddr);
int uv_destroy_folio(struct folio *folio);
int uv_destroy_pte(pte_t pte);
int uv_convert_from_secure_pte(pte_t pte);
-int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb);
+int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header *uvcb);
int uv_convert_from_secure(unsigned long paddr);
int uv_convert_from_secure_folio(struct folio *folio);
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 9f05df2da2f7..6c6e81daa839 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -206,6 +206,39 @@ int uv_convert_from_secure_pte(pte_t pte)
return uv_convert_from_secure_folio(pfn_folio(pte_pfn(pte)));
}
+/**
+ * should_export_before_import - Determine whether an export is needed
+ * before an import-like operation
+ * @uvcb: the Ultravisor control block of the UVC to be performed
+ * @mm: the mm of the process
+ *
+ * Returns whether an export is needed before every import-like operation.
+ * This is needed for shared pages, which don't trigger a secure storage
+ * exception when accessed from a different guest.
+ *
+ * Although considered as one, the Unpin Page UVC is not an actual import,
+ * so it is not affected.
+ *
+ * No export is needed also when there is only one protected VM, because the
+ * page cannot belong to the wrong VM in that case (there is no "other VM"
+ * it can belong to).
+ *
+ * Return: true if an export is needed before every import, otherwise false.
+ */
+static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
+{
+ /*
+ * The misc feature indicates, among other things, that importing a
+ * shared page from a different protected VM will automatically also
+ * transfer its ownership.
+ */
+ if (uv_has_feature(BIT_UV_FEAT_MISC))
+ return false;
+ if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
+ return false;
+ return atomic_read(&mm->context.protected_count) > 1;
+}
+
/*
* Calculate the expected ref_count for a folio that would otherwise have no
* further pins. This was cribbed from similar functions in other places in
@@ -228,7 +261,7 @@ static int expected_folio_refs(struct folio *folio)
}
/**
- * make_folio_secure() - make a folio secure
+ * __make_folio_secure() - make a folio secure
* @folio: the folio to make secure
* @uvcb: the uvcb that describes the UVC to be used
*
@@ -243,14 +276,13 @@ static int expected_folio_refs(struct folio *folio)
* -EINVAL if the UVC failed for other reasons.
*
* Context: The caller must hold exactly one extra reference on the folio
- * (it's the same logic as split_folio())
+ * (it's the same logic as split_folio()), and the folio must be
+ * locked.
*/
-int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
+static int __make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
{
int expected, cc = 0;
- if (folio_test_large(folio))
- return -E2BIG;
if (folio_test_writeback(folio))
return -EBUSY;
expected = expected_folio_refs(folio) + 1;
@@ -277,7 +309,68 @@ int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
return -EAGAIN;
return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
}
-EXPORT_SYMBOL_GPL(make_folio_secure);
+
+static int make_folio_secure(struct mm_struct *mm, struct folio *folio, struct uv_cb_header *uvcb)
+{
+ int rc;
+
+ if (!folio_trylock(folio))
+ return -EAGAIN;
+ if (should_export_before_import(uvcb, mm))
+ uv_convert_from_secure(folio_to_phys(folio));
+ rc = __make_folio_secure(folio, uvcb);
+ folio_unlock(folio);
+
+ return rc;
+}
+
+static pte_t *get_locked_valid_pte(struct mm_struct *mm, unsigned long hva, spinlock_t **ptl)
+{
+ pte_t *ptep = get_locked_pte(mm, hva, ptl);
+
+ if (ptep && (pte_val(*ptep) & _PAGE_INVALID)) {
+ pte_unmap_unlock(ptep, *ptl);
+ ptep = NULL;
+ }
+ return ptep;
+}
+
+int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header *uvcb)
+{
+ struct folio *folio;
+ spinlock_t *ptelock;
+ pte_t *ptep;
+ int rc;
+
+ ptep = get_locked_valid_pte(mm, hva, &ptelock);
+ if (!ptep)
+ return -ENXIO;
+
+ folio = page_folio(pte_page(*ptep));
+ folio_get(folio);
+ /*
+ * Secure pages cannot be huge and userspace should not combine both.
+ * In case userspace does it anyway this will result in an -EFAULT for
+ * the unpack. The guest is thus never reaching secure mode.
+ * If userspace plays dirty tricks and decides to map huge pages at a
+ * later point in time, it will receive a segmentation fault or
+ * KVM_RUN will return -EFAULT.
+ */
+ if (folio_test_hugetlb(folio))
+ rc = -EFAULT;
+ else if (folio_test_large(folio))
+ rc = -E2BIG;
+ else
+ rc = make_folio_secure(mm, folio, uvcb);
+ pte_unmap_unlock(ptep, ptelock);
+
+ if (rc == -E2BIG || rc == -EBUSY)
+ rc = kvm_s390_wiggle_split_folio(mm, folio, rc == -E2BIG);
+ folio_put(folio);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(make_hva_secure);
/*
* To be called with the folio locked or with an extra reference! This will
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index 02adf151d4de..c08950b4301c 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -22,92 +22,6 @@
#include "gmap.h"
-/**
- * should_export_before_import - Determine whether an export is needed
- * before an import-like operation
- * @uvcb: the Ultravisor control block of the UVC to be performed
- * @mm: the mm of the process
- *
- * Returns whether an export is needed before every import-like operation.
- * This is needed for shared pages, which don't trigger a secure storage
- * exception when accessed from a different guest.
- *
- * Although considered as one, the Unpin Page UVC is not an actual import,
- * so it is not affected.
- *
- * No export is needed also when there is only one protected VM, because the
- * page cannot belong to the wrong VM in that case (there is no "other VM"
- * it can belong to).
- *
- * Return: true if an export is needed before every import, otherwise false.
- */
-static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
-{
- /*
- * The misc feature indicates, among other things, that importing a
- * shared page from a different protected VM will automatically also
- * transfer its ownership.
- */
- if (uv_has_feature(BIT_UV_FEAT_MISC))
- return false;
- if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
- return false;
- return atomic_read(&mm->context.protected_count) > 1;
-}
-
-static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb)
-{
- struct folio *folio = page_folio(page);
- int rc;
-
- /*
- * Secure pages cannot be huge and userspace should not combine both.
- * In case userspace does it anyway this will result in an -EFAULT for
- * the unpack. The guest is thus never reaching secure mode.
- * If userspace plays dirty tricks and decides to map huge pages at a
- * later point in time, it will receive a segmentation fault or
- * KVM_RUN will return -EFAULT.
- */
- if (folio_test_hugetlb(folio))
- return -EFAULT;
- if (folio_test_large(folio)) {
- mmap_read_unlock(gmap->mm);
- rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true);
- mmap_read_lock(gmap->mm);
- if (rc)
- return rc;
- folio = page_folio(page);
- }
-
- if (!folio_trylock(folio))
- return -EAGAIN;
- if (should_export_before_import(uvcb, gmap->mm))
- uv_convert_from_secure(folio_to_phys(folio));
- rc = make_folio_secure(folio, uvcb);
- folio_unlock(folio);
-
- /*
- * In theory a race is possible and the folio might have become
- * large again before the folio_trylock() above. In that case, no
- * action is performed and -EAGAIN is returned; the callers will
- * have to try again later.
- * In most cases this implies running the VM again, getting the same
- * exception again, and make another attempt in this function.
- * This is expected to happen extremely rarely.
- */
- if (rc == -E2BIG)
- return -EAGAIN;
- /* The folio has too many references, try to shake some off */
- if (rc == -EBUSY) {
- mmap_read_unlock(gmap->mm);
- kvm_s390_wiggle_split_folio(gmap->mm, folio, false);
- mmap_read_lock(gmap->mm);
- return -EAGAIN;
- }
-
- return rc;
-}
-
/**
* gmap_make_secure() - make one guest page secure
* @gmap: the guest gmap
@@ -120,17 +34,16 @@ static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb)
int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
{
struct kvm *kvm = gmap->private;
- struct page *page;
+ unsigned long vmaddr;
int rc = 0;
lockdep_assert_held(&kvm->srcu);
- page = gfn_to_page(kvm, gpa_to_gfn(gaddr));
- mmap_read_lock(gmap->mm);
- if (page)
- rc = __gmap_make_secure(gmap, page, uvcb);
- kvm_release_page_clean(page);
- mmap_read_unlock(gmap->mm);
+ vmaddr = gfn_to_hva(kvm, gpa_to_gfn(gaddr));
+ if (kvm_is_error_hva(vmaddr))
+ rc = -ENXIO;
+ else
+ rc = make_hva_secure(gmap->mm, vmaddr, uvcb);
return rc;
}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ebecb96bacce..020502af7dc9 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4952,6 +4952,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
{
unsigned int flags = 0;
unsigned long gaddr;
+ int rc;
gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
if (kvm_s390_cur_gmap_fault_is_write())
@@ -4961,16 +4962,6 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
case 0:
vcpu->stat.exit_null++;
break;
- case PGM_NON_SECURE_STORAGE_ACCESS:
- kvm_s390_assert_primary_as(vcpu);
- /*
- * This is normal operation; a page belonging to a protected
- * guest has not been imported yet. Try to import the page into
- * the protected guest.
- */
- if (gmap_convert_to_secure(vcpu->arch.gmap, gaddr) == -EINVAL)
- send_sig(SIGSEGV, current, 0);
- break;
case PGM_SECURE_STORAGE_ACCESS:
case PGM_SECURE_STORAGE_VIOLATION:
kvm_s390_assert_primary_as(vcpu);
@@ -4995,6 +4986,20 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
send_sig(SIGSEGV, current, 0);
}
break;
+ case PGM_NON_SECURE_STORAGE_ACCESS:
+ kvm_s390_assert_primary_as(vcpu);
+ /*
+ * This is normal operation; a page belonging to a protected
+ * guest has not been imported yet. Try to import the page into
+ * the protected guest.
+ */
+ rc = gmap_convert_to_secure(vcpu->arch.gmap, gaddr);
+ if (rc == -EINVAL)
+ send_sig(SIGSEGV, current, 0);
+ if (rc != -ENXIO)
+ break;
+ flags = FAULT_FLAG_WRITE;
+ fallthrough;
case PGM_PROTECTION:
case PGM_SEGMENT_TRANSLATION:
case PGM_PAGE_TRANSLATION:
--
2.48.1
^ permalink raw reply related [flat|nested] 6+ messages in thread