Skip to contentSkip to conversation

Rework secure memslot dropping

PATCH In review Laurent Dufour 4 participants 13 messages Jul 21, 2020 – Jul 28, 2020

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

v2 cover Rework secure memslot dropping

When doing memory hotplug on a secure VM, the secure pages are not well cleaned from the secure device when dropping the memslot. This silent error, is then preventing the SVM to reboot properly after the following sequence of commands are run in the Qemu monitor:

device_add pc-dimm,id=dimm1,memdev=mem1
device_del dimm1
device_add pc-dimm,id=dimm1,memdev=mem1

At reboot time, when the kernel is booting again and switching to the secure mode, the page_in is failing for the pages in the memslot because the cleanup was not done properly, because the memslot is flagged as invalid during the hot unplug and thus the page fault mechanism is not triggered.

To prevent that during the memslot dropping, instead of belonging on the page fault mechanism to trigger the page out of the secured pages, it seems simpler to directly call the function doing the page out. This way the state of the memslot is not interfering on the page out process.

This series applies on top of the Ram's one titled:
"[v4 0/5] Migrate non-migrated pages of a SVM."
https://lore.kernel.org/linuxppc-dev/[email protected]/

Changes since V1:
- Rebase on top of Ram's V4 series
- Address Bharata's comment to use mmap_read_*lock().

Laurent Dufour (2):
KVM: PPC: Book3S HV: move kvmppc_svm_page_out up
KVM: PPC: Book3S HV: rework secure mem slot dropping

 arch/powerpc/kvm/book3s_hv_uvmem.c | 220 +++++++++++++++++------------
 1 file changed, 127 insertions(+), 93 deletions(-)
Signature · 1 line
2.27.0
#1 lore raw

PATCH v2 1/2 KVM: PPC: Book3S HV: move kvmppc_svm_page_out up

kvmppc_svm_page_out() will need to be called by kvmppc_uvmem_drop_pages() so move it upper in this file.

Furthermore it will be interesting to call this function when already holding the kvm->arch.uvmem_lock, so prefix the original function with __ and remove the locking in it, and introduce a wrapper which call that function with the lock held.

There is no functional change.

Cc Ram Pai <[email protected]>
Cc Bharata B Rao <[email protected]>
Cc Paul Mackerras <[email protected]>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 166 ++++++++++++++++-------------
 1 file changed, 90 insertions(+), 76 deletions(-)
arch/powerpc/kvm/book3s_hv_uvmem.c +90 -76
index a2b4d259f8b0..5a4b02d3f651 100644
@@ -526,6 +526,96 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
 	return ret;
 }
 
+/*
+ * Provision a new page on HV side and copy over the contents
+ * from secure memory using UV_PAGE_OUT uvcall.
+ * Caller must held kvm->arch.uvmem_lock.
+ */
+static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
+		unsigned long start,
+		unsigned long end, unsigned long page_shift,
+		struct kvm *kvm, unsigned long gpa)
+{
+	unsigned long src_pfn, dst_pfn = 0;
+	struct migrate_vma mig;
+	struct page *dpage, *spage;
+	struct kvmppc_uvmem_page_pvt *pvt;
+	unsigned long pfn;
+	int ret = U_SUCCESS;
+
+	memset(&mig, 0, sizeof(mig));
+	mig.vma = vma;
+	mig.start = start;
+	mig.end = end;
+	mig.src = &src_pfn;
+	mig.dst = &dst_pfn;
+	mig.src_owner = &kvmppc_uvmem_pgmap;
+
+	/* The requested page is already paged-out, nothing to do */
+	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
+		return ret;
+
+	ret = migrate_vma_setup(&mig);
+	if (ret)
+		return -1;
+
+	spage = migrate_pfn_to_page(*mig.src);
+	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
+		goto out_finalize;
+
+	if (!is_zone_device_page(spage))
+		goto out_finalize;
+
+	dpage = alloc_page_vma(GFP_HIGHUSER, vma, start);
+	if (!dpage) {
+		ret = -1;
+		goto out_finalize;
+	}
+
+	lock_page(dpage);
+	pvt = spage->zone_device_data;
+	pfn = page_to_pfn(dpage);
+
+	/*
+	 * This function is used in two cases:
+	 * - When HV touches a secure page, for which we do UV_PAGE_OUT
+	 * - When a secure page is converted to shared page, we *get*
+	 *   the page to essentially unmap the device page. In this
+	 *   case we skip page-out.
+	 */
+	if (!pvt->skip_page_out)
+		ret = uv_page_out(kvm->arch.lpid, pfn << page_shift,
+				  gpa, 0, page_shift);
+
+	if (ret = U_SUCCESS)
+		*mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
+	else {
+		unlock_page(dpage);
+		__free_page(dpage);
+		goto out_finalize;
+	}
+
+	migrate_vma_pages(&mig);
+
+out_finalize:
+	migrate_vma_finalize(&mig);
+	return ret;
+}
+
+static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
+				      unsigned long start, unsigned long end,
+				      unsigned long page_shift,
+				      struct kvm *kvm, unsigned long gpa)
+{
+	int ret;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa);
+	mutex_unlock(&kvm->arch.uvmem_lock);
+
+	return ret;
+}
+
 /*
  * Drop device pages that we maintain for the secure guest
  *
@@ -898,82 +988,6 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 	return ret;
 }
 
-/*
- * Provision a new page on HV side and copy over the contents
- * from secure memory using UV_PAGE_OUT uvcall.
- */
-static int kvmppc_svm_page_out(struct vm_area_struct *vma,
-		unsigned long start,
-		unsigned long end, unsigned long page_shift,
-		struct kvm *kvm, unsigned long gpa)
-{
-	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
-	struct page *dpage, *spage;
-	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn;
-	int ret = U_SUCCESS;
-
-	memset(&mig, 0, sizeof(mig));
-	mig.vma = vma;
-	mig.start = start;
-	mig.end = end;
-	mig.src = &src_pfn;
-	mig.dst = &dst_pfn;
-	mig.src_owner = &kvmppc_uvmem_pgmap;
-
-	mutex_lock(&kvm->arch.uvmem_lock);
-	/* The requested page is already paged-out, nothing to do */
-	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
-		goto out;
-
-	ret = migrate_vma_setup(&mig);
-	if (ret)
-		goto out;
-
-	spage = migrate_pfn_to_page(*mig.src);
-	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
-		goto out_finalize;
-
-	if (!is_zone_device_page(spage))
-		goto out_finalize;
-
-	dpage = alloc_page_vma(GFP_HIGHUSER, vma, start);
-	if (!dpage) {
-		ret = -1;
-		goto out_finalize;
-	}
-
-	lock_page(dpage);
-	pvt = spage->zone_device_data;
-	pfn = page_to_pfn(dpage);
-
-	/*
-	 * This function is used in two cases:
-	 * - When HV touches a secure page, for which we do UV_PAGE_OUT
-	 * - When a secure page is converted to shared page, we *get*
-	 *   the page to essentially unmap the device page. In this
-	 *   case we skip page-out.
-	 */
-	if (!pvt->skip_page_out)
-		ret = uv_page_out(kvm->arch.lpid, pfn << page_shift,
-				  gpa, 0, page_shift);
-
-	if (ret = U_SUCCESS)
-		*mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
-	else {
-		unlock_page(dpage);
-		__free_page(dpage);
-		goto out_finalize;
-	}
-
-	migrate_vma_pages(&mig);
-out_finalize:
-	migrate_vma_finalize(&mig);
-out:
-	mutex_unlock(&kvm->arch.uvmem_lock);
-	return ret;
-}
 
 /*
  * Fault handler callback that gets called when HV touches any page that
Signature · 1 line
2.27.0
Reviewed-by on v2 1/2
#2 lore raw

Re: [PATCH v2 1/2] KVM: PPC: Book3S HV: move kvmppc_svm_page_out up

Quoted 9 lines · Laurent Dufour

kvmppc_svm_page_out() will need to be called by kvmppc_uvmem_drop_pages() so move it upper in this file.

Furthermore it will be interesting to call this function when already holding the kvm->arch.uvmem_lock, so prefix the original function with __ and remove the locking in it, and introduce a wrapper which call that function with the lock held.

There is no functional change.

Quoted 6 lines
Cc Ram Pai <[email protected]>
Cc Bharata B Rao <[email protected]>
Cc Paul Mackerras <[email protected]>

---

RP

#3 lore raw

PATCH v2 2/2 KVM: PPC: Book3S HV: rework secure mem slot dropping

In reply to Laurent Dufour

When a secure memslot is dropped, all the pages backed in the secure device (aka really backed by secure memory by the Ultravisor) should be paged out to a normal page. Previously, this was achieved by triggering the page fault mechanism which is calling kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems simpler to directly calling it instead of triggering such a mechanism. This way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock, the call to __kvmppc_svm_page_out() is made.
As __kvmppc_svm_page_out needs the vma pointer to migrate the pages, the VMA is fetched in a lazy way, to not trigger find_vma() all the time. In addition, the mmap_sem is help in read mode during that time, not in write mode since the virual memory layout is not impacted, and kvm->arch.uvmem_lock prevents concurrent operation on the secure device.

Cc Ram Pai <[email protected]>
Cc Bharata B Rao <[email protected]>
Cc Paul Mackerras <[email protected]>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 54 ++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 17 deletions(-)
arch/powerpc/kvm/book3s_hv_uvmem.c +37 -17
index 5a4b02d3f651..ba5c7c77cc3a 100644
@@ -624,35 +624,55 @@ static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
  * fault on them, do fault time migration to replace the device PTEs in
  * QEMU page table with normal PTEs from newly allocated pages.
  */
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
 			     struct kvm *kvm, bool skip_page_out)
 {
 	int i;
 	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn, uvmem_pfn;
-	unsigned long gfn = free->base_gfn;
+	struct page *uvmem_page;
+	struct vm_area_struct *vma = NULL;
+	unsigned long uvmem_pfn, gfn;
+	unsigned long addr, end;
+
+	mmap_read_lock(kvm->mm);
+
+	addr = slot->userspace_addr;
+	end = addr + (slot->npages * PAGE_SIZE);
 
-	for (i = free->npages; i; --i, ++gfn) {
-		struct page *uvmem_page;
+	gfn = slot->base_gfn;
+	for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) {
+
+		/* Fetch the VMA if addr is not in the latest fetched one */
+		if (!vma || (addr < vma->vm_start || addr >= vma->vm_end)) {
+			vma = find_vma_intersection(kvm->mm, addr, end);
+			if (!vma ||
+			    vma->vm_start > addr || vma->vm_end < end) {
+				pr_err("Can't find VMA for gfn:0x%lx\n", gfn);
+				break;
+			}
+		}
 
 		mutex_lock(&kvm->arch.uvmem_lock);
-		if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+
+		if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+			uvmem_page = pfn_to_page(uvmem_pfn);
+			pvt = uvmem_page->zone_device_data;
+			pvt->skip_page_out = skip_page_out;
+			pvt->remove_gfn = true;
+
+			if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
+						  PAGE_SHIFT, kvm, pvt->gpa))
+				pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
+				       pvt->gpa, addr);
+		} else {
+			/* Remove the shared flag if any */
 			kvmppc_gfn_remove(gfn, kvm);
-			mutex_unlock(&kvm->arch.uvmem_lock);
-			continue;
 		}
 
-		uvmem_page = pfn_to_page(uvmem_pfn);
-		pvt = uvmem_page->zone_device_data;
-		pvt->skip_page_out = skip_page_out;
-		pvt->remove_gfn = true;
 		mutex_unlock(&kvm->arch.uvmem_lock);
-
-		pfn = gfn_to_pfn(kvm, gfn);
-		if (is_error_noslot_pfn(pfn))
-			continue;
-		kvm_release_pfn_clean(pfn);
 	}
+
+	mmap_read_unlock(kvm->mm);
 }
 
 unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
Signature · 1 line
2.27.0
Reviewed-by on v2 2/2
#4 lore raw

Re: [PATCH v2 2/2] KVM: PPC: Book3S HV: rework secure mem slot dropping

Quoted 11 lines · Laurent Dufour

When a secure memslot is dropped, all the pages backed in the secure device (aka really backed by secure memory by the Ultravisor) should be paged out to a normal page. Previously, this was achieved by triggering the page fault mechanism which is calling kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems simpler to directly calling it instead of triggering such a mechanism. This

^^ call directly instead of triggering..

Quoted 8 lines

way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock, the call to __kvmppc_svm_page_out() is made.
As __kvmppc_svm_page_out needs the vma pointer to migrate the pages, the VMA is fetched in a lazy way, to not trigger find_vma() all the time. In addition, the mmap_sem is help in read mode during that time, not in write

		          ^^ held
Quoted 4 lines

mode since the virual memory layout is not impacted, and kvm->arch.uvmem_lock prevents concurrent operation on the secure device.

Cc Ram Pai <[email protected]>

RP

#5 lore raw

Re: [PATCH v2 2/2] KVM: PPC: Book3S HV: rework secure mem slot dropping

Le 21/07/2020 à 23:37, Ram Pai a écrit :

Quoted 22 lines · Laurent Dufour
Quoted 11 lines

When a secure memslot is dropped, all the pages backed in the secure device (aka really backed by secure memory by the Ultravisor) should be paged out to a normal page. Previously, this was achieved by triggering the page fault mechanism which is calling kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems simpler to directly calling it instead of triggering such a mechanism. This

^^ call directly instead of triggering..

Quoted 8 lines

way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock, the call to __kvmppc_svm_page_out() is made.
As __kvmppc_svm_page_out needs the vma pointer to migrate the pages, the VMA is fetched in a lazy way, to not trigger find_vma() all the time. In addition, the mmap_sem is help in read mode during that time, not in write

Quoted 8 lines
		          ^^ held
Quoted 4 lines

mode since the virual memory layout is not impacted, and kvm->arch.uvmem_lock prevents concurrent operation on the secure device.

Cc Ram Pai <[email protected]>

Thanks for reviewing this series.

Regarding the wordsmithing, Paul, could you manage that when pulling the series?

Thanks,
Laurent.

#6 lore raw

Re: [PATCH v2 2/2] KVM: PPC: Book3S HV: rework secure mem slot dropping

In reply to Laurent Dufour
Quoted 44 lines · Laurent Dufour

When a secure memslot is dropped, all the pages backed in the secure device (aka really backed by secure memory by the Ultravisor) should be paged out to a normal page. Previously, this was achieved by triggering the page fault mechanism which is calling kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems simpler to directly calling it instead of triggering such a mechanism. This way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock, the call to __kvmppc_svm_page_out() is made.
As __kvmppc_svm_page_out needs the vma pointer to migrate the pages, the VMA is fetched in a lazy way, to not trigger find_vma() all the time. In addition, the mmap_sem is help in read mode during that time, not in write mode since the virual memory layout is not impacted, and kvm->arch.uvmem_lock prevents concurrent operation on the secure device.

Cc Ram Pai <[email protected]>
Cc Bharata B Rao <[email protected]>
Cc Paul Mackerras <[email protected]>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 54 ++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 17 deletions(-)
arch/powerpc/kvm/book3s_hv_uvmem.c +1 -1
index 5a4b02d3f651..ba5c7c77cc3a 100644
@@ -624,35 +624,55 @@ static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
  * fault on them, do fault time migration to replace the device PTEs in
  * QEMU page table with normal PTEs from newly allocated pages.
  */
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
 			     struct kvm *kvm, bool skip_page_out)
 {
 	int i;
 	struct kvmppc_uvmem_page_pvt *pvt;

arch/powerpc/kvm/book3s_hv_uvmem.c static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, · line 639

Quoted 10 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +8 -2
-	unsigned long pfn, uvmem_pfn;
-	unsigned long gfn = free->base_gfn;
+	struct page *uvmem_page;
+	struct vm_area_struct *vma = NULL;
+	unsigned long uvmem_pfn, gfn;
+	unsigned long addr, end;
+
+	mmap_read_lock(kvm->mm);
+
+	addr = slot->userspace_addr;

We typically use gfn_to_hva() for that, but that won't work for a memslot that is already marked INVALID which is the case here. I think it is ok to access slot->userspace_addr here of an INVALID memslot, but just thought of explictly bringing this up.

Quoted 6 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +3 -2
+	end = addr + (slot->npages * PAGE_SIZE);
 
-	for (i = free->npages; i; --i, ++gfn) {
-		struct page *uvmem_page;
+	gfn = slot->base_gfn;
+	for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) {

arch/powerpc/kvm/book3s_hv_uvmem.c static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, · line 653

Quoted 10 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +10 -0
+
+		/* Fetch the VMA if addr is not in the latest fetched one */
+		if (!vma || (addr < vma->vm_start || addr >= vma->vm_end)) {
+			vma = find_vma_intersection(kvm->mm, addr, end);
+			if (!vma ||
+			    vma->vm_start > addr || vma->vm_end < end) {
+				pr_err("Can't find VMA for gfn:0x%lx\n", gfn);
+				break;
+			}
+		}

In Ram's series, kvmppc_memslot_page_merge() also walks the VMAs spanning the memslot, but it uses a different logic for the same. Why can't these two cases use the same method to walk the VMAs? Is there anything subtly different between the two cases?

Regards,
Bharata.

#7 lore raw

Re: [PATCH v2 2/2] KVM: PPC: Book3S HV: rework secure mem slot dropping

Le 23/07/2020 à 05:36, Bharata B Rao a écrit :

Quoted 52 lines · Laurent Dufour
Quoted 51 lines

When a secure memslot is dropped, all the pages backed in the secure device (aka really backed by secure memory by the Ultravisor) should be paged out to a normal page. Previously, this was achieved by triggering the page fault mechanism which is calling kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems simpler to directly calling it instead of triggering such a mechanism. This way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock, the call to __kvmppc_svm_page_out() is made.
As __kvmppc_svm_page_out needs the vma pointer to migrate the pages, the VMA is fetched in a lazy way, to not trigger find_vma() all the time. In addition, the mmap_sem is help in read mode during that time, not in write mode since the virual memory layout is not impacted, and kvm->arch.uvmem_lock prevents concurrent operation on the secure device.

Cc Ram Pai <[email protected]>
Cc Bharata B Rao <[email protected]>
Cc Paul Mackerras <[email protected]>
---
  arch/powerpc/kvm/book3s_hv_uvmem.c | 54 ++++++++++++++++++++----------
  1 file changed, 37 insertions(+), 17 deletions(-)
arch/powerpc/kvm/book3s_hv_uvmem.c +6 -3
index 5a4b02d3f651..ba5c7c77cc3a 100644
@@ -624,35 +624,55 @@ static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
   * fault on them, do fault time migration to replace the device PTEs in
   * QEMU page table with normal PTEs from newly allocated pages.
   */
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
  			     struct kvm *kvm, bool skip_page_out)
  {
  	int i;
  	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn, uvmem_pfn;
-	unsigned long gfn = free->base_gfn;
+	struct page *uvmem_page;
+	struct vm_area_struct *vma = NULL;
+	unsigned long uvmem_pfn, gfn;
+	unsigned long addr, end;
+
Quoted 8 lines

arch/powerpc/kvm/book3s_hv_uvmem.c static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, · line 639

Quoted 3 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +3 -0
+	mmap_read_lock(kvm->mm);
+
+	addr = slot->userspace_addr;

We typically use gfn_to_hva() for that, but that won't work for a memslot that is already marked INVALID which is the case here. I think it is ok to access slot->userspace_addr here of an INVALID memslot, but just thought of explictly bringing this up.

Which explicitly mentioned above in the patch's description:

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Quoted 14 lines
Quoted 14 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +10 -2
+	end = addr + (slot->npages * PAGE_SIZE);
 
-	for (i = free->npages; i; --i, ++gfn) {
-		struct page *uvmem_page;
+	gfn = slot->base_gfn;
+	for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) {
+
+		/* Fetch the VMA if addr is not in the latest fetched one */
+		if (!vma || (addr < vma->vm_start || addr >= vma->vm_end)) {
+			vma = find_vma_intersection(kvm->mm, addr, end);
+			if (!vma ||
+			    vma->vm_start > addr || vma->vm_end < end) {
+				pr_err("Can't find VMA for gfn:0x%lx\n", gfn);
Quoted 8 lines

arch/powerpc/kvm/book3s_hv_uvmem.c static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, · line 653

Quoted 3 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +3 -0
+				break;
+			}
+		}

In Ram's series, kvmppc_memslot_page_merge() also walks the VMAs spanning the memslot, but it uses a different logic for the same. Why can't these two cases use the same method to walk the VMAs? Is there anything subtly different between the two cases?

This is probably doable. At the time I wrote that patch, the kvmppc_memslot_page_merge() was not yet introduced AFAIR.

This being said, I'd help a lot to factorize that code... I let Ram dealing with that ;)

Cheers,
Laurent.

#8 lore raw

Re: [PATCH v2 2/2] KVM: PPC: Book3S HV: rework secure mem slot dropping

Le 23/07/2020 à 14:32, Laurent Dufour a écrit :

Quoted 92 lines

Le 23/07/2020 à 05:36, Bharata B Rao a écrit :

Quoted 54 lines · Laurent Dufour
Quoted 53 lines

When a secure memslot is dropped, all the pages backed in the secure device (aka really backed by secure memory by the Ultravisor) should be paged out to a normal page. Previously, this was achieved by triggering the page fault mechanism which is calling kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems simpler to directly calling it instead of triggering such a mechanism. This way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock, the call to __kvmppc_svm_page_out() is made.
As __kvmppc_svm_page_out needs the vma pointer to migrate the pages, the VMA is fetched in a lazy way, to not trigger find_vma() all the time. In addition, the mmap_sem is help in read mode during that time, not in write mode since the virual memory layout is not impacted, and kvm->arch.uvmem_lock prevents concurrent operation on the secure device.

Cc Ram Pai <[email protected]>
Cc Bharata B Rao <[email protected]>
Cc Paul Mackerras <[email protected]>

---
  arch/powerpc/kvm/book3s_hv_uvmem.c | 54 ++++++++++++++++++++----------

  1 file changed, 37 insertions(+), 17 deletions(-)
arch/powerpc/kvm/book3s_hv_uvmem.c +6 -3
index 5a4b02d3f651..ba5c7c77cc3a 100644
@@ -624,35 +624,55 @@ static inline int kvmppc_svm_page_out(struct 
 vm_area_struct *vma,
    * fault on them, do fault time migration to replace the device PTEs in
    * QEMU page table with normal PTEs from newly allocated pages.
    */
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
                    struct kvm *kvm, bool skip_page_out)
   {
       int i;
       struct kvmppc_uvmem_page_pvt *pvt;
-    unsigned long pfn, uvmem_pfn;
-    unsigned long gfn = free->base_gfn;
+    struct page *uvmem_page;
+    struct vm_area_struct *vma = NULL;
+    unsigned long uvmem_pfn, gfn;
+    unsigned long addr, end;
+
Quoted 8 lines

arch/powerpc/kvm/book3s_hv_uvmem.c static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, · line 639

Quoted 3 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +3 -0
+    mmap_read_lock(kvm->mm);
+
+    addr = slot->userspace_addr;

We typically use gfn_to_hva() for that, but that won't work for a memslot that is already marked INVALID which is the case here. I think it is ok to access slot->userspace_addr here of an INVALID memslot, but just thought of explictly bringing this up.

Which explicitly mentioned above in the patch's description:

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Quoted 17 lines
Quoted 6 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +3 -2
+    end = addr + (slot->npages * PAGE_SIZE);
-    for (i = free->npages; i; --i, ++gfn) {
-        struct page *uvmem_page;
+    gfn = slot->base_gfn;
+    for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) {

arch/powerpc/kvm/book3s_hv_uvmem.c static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, · line 653

Quoted 10 lines
arch/powerpc/kvm/book3s_hv_uvmem.c +10 -0
+
+        /* Fetch the VMA if addr is not in the latest fetched one */
+        if (!vma || (addr < vma->vm_start || addr >= vma->vm_end)) {
+            vma = find_vma_intersection(kvm->mm, addr, end);
+            if (!vma ||
+                vma->vm_start > addr || vma->vm_end < end) {
+                pr_err("Can't find VMA for gfn:0x%lx\n", gfn);
+                break;
+            }
+        }
Quoted 4 lines

In Ram's series, kvmppc_memslot_page_merge() also walks the VMAs spanning the memslot, but it uses a different logic for the same. Why can't these two cases use the same method to walk the VMAs? Is there anything subtly different between the two cases?

Quoted 5 lines

This is probably doable. At the time I wrote that patch, the kvmppc_memslot_page_merge() was not yet introduced AFAIR.

This being said, I'd help a lot to factorize that code... I let Ram dealing with that ;)

Indeed I don't think this is relevant, the loop in kvmppc_memslot_page_merge() deals with one call (to ksm_advise) per VMA, while this code is dealing with one call per page of the VMA, which completely different.

I don't think merging the both will be a good idea.

Cheers,
Laurent.

#9 lore raw

v2 cover Rework secure memslot dropping

In reply to Laurent Dufour

From: Laurent Dufour <[email protected]>

When doing memory hotplug on a secure VM, the secure pages are not well cleaned from the secure device when dropping the memslot. This silent error, is then preventing the SVM to reboot properly after the following sequence of commands are run in the Qemu monitor:

device_add pc-dimm,id=dimm1,memdev=mem1
device_del dimm1
device_add pc-dimm,id=dimm1,memdev=mem1

At reboot time, when the kernel is booting again and switching to the secure mode, the page_in is failing for the pages in the memslot because the cleanup was not done properly, because the memslot is flagged as invalid during the hot unplug and thus the page fault mechanism is not triggered.

To prevent that during the memslot dropping, instead of belonging on the page fault mechanism to trigger the page out of the secured pages, it seems simpler to directly call the function doing the page out. This way the state of the memslot is not interfering on the page out process.

This series applies on top of the Ram's one titled:
"[v6 0/5] Migrate non-migrated pages of a SVM."

Changes since V2:
- fix to vma boundary check in kvmppc_uvmem_drop_pages().

Changes since V1:
- Rebase on top of Ram's V4 series
- Address Bharata's comment to use mmap_read_*lock().

Laurent Dufour (2):
KVM: PPC: Book3S HV: move kvmppc_svm_page_out up
KVM: PPC: Book3S HV: rework secure mem slot dropping

 arch/powerpc/kvm/book3s_hv_uvmem.c | 218 +++++++++++++++++++++----------------
 1 file changed, 125 insertions(+), 93 deletions(-)
Signature · 1 line
1.8.3.1
#10 lore raw

PATCH v2 1/2 KVM: PPC: Book3S HV: move kvmppc_svm_page_out up

From: Laurent Dufour <[email protected]>

kvmppc_svm_page_out() will need to be called by kvmppc_uvmem_drop_pages() so move it upper in this file.

Furthermore it will be interesting to call this function when already holding the kvm->arch.uvmem_lock, so prefix the original function with __ and remove the locking in it, and introduce a wrapper which call that function with the lock held.

There is no functional change.

---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 166 ++++++++++++++++++++-----------------
 1 file changed, 90 insertions(+), 76 deletions(-)
arch/powerpc/kvm/book3s_hv_uvmem.c +90 -76
index 5b917ea..565f24b 100644
@@ -497,6 +497,96 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 }
 
 /*
+ * Provision a new page on HV side and copy over the contents
+ * from secure memory using UV_PAGE_OUT uvcall.
+ * Caller must held kvm->arch.uvmem_lock.
+ */
+static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
+		unsigned long start,
+		unsigned long end, unsigned long page_shift,
+		struct kvm *kvm, unsigned long gpa)
+{
+	unsigned long src_pfn, dst_pfn = 0;
+	struct migrate_vma mig;
+	struct page *dpage, *spage;
+	struct kvmppc_uvmem_page_pvt *pvt;
+	unsigned long pfn;
+	int ret = U_SUCCESS;
+
+	memset(&mig, 0, sizeof(mig));
+	mig.vma = vma;
+	mig.start = start;
+	mig.end = end;
+	mig.src = &src_pfn;
+	mig.dst = &dst_pfn;
+	mig.src_owner = &kvmppc_uvmem_pgmap;
+
+	/* The requested page is already paged-out, nothing to do */
+	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
+		return ret;
+
+	ret = migrate_vma_setup(&mig);
+	if (ret)
+		return -1;
+
+	spage = migrate_pfn_to_page(*mig.src);
+	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
+		goto out_finalize;
+
+	if (!is_zone_device_page(spage))
+		goto out_finalize;
+
+	dpage = alloc_page_vma(GFP_HIGHUSER, vma, start);
+	if (!dpage) {
+		ret = -1;
+		goto out_finalize;
+	}
+
+	lock_page(dpage);
+	pvt = spage->zone_device_data;
+	pfn = page_to_pfn(dpage);
+
+	/*
+	 * This function is used in two cases:
+	 * - When HV touches a secure page, for which we do UV_PAGE_OUT
+	 * - When a secure page is converted to shared page, we *get*
+	 *   the page to essentially unmap the device page. In this
+	 *   case we skip page-out.
+	 */
+	if (!pvt->skip_page_out)
+		ret = uv_page_out(kvm->arch.lpid, pfn << page_shift,
+				  gpa, 0, page_shift);
+
+	if (ret = U_SUCCESS)
+		*mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
+	else {
+		unlock_page(dpage);
+		__free_page(dpage);
+		goto out_finalize;
+	}
+
+	migrate_vma_pages(&mig);
+
+out_finalize:
+	migrate_vma_finalize(&mig);
+	return ret;
+}
+
+static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
+				      unsigned long start, unsigned long end,
+				      unsigned long page_shift,
+				      struct kvm *kvm, unsigned long gpa)
+{
+	int ret;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa);
+	mutex_unlock(&kvm->arch.uvmem_lock);
+
+	return ret;
+}
+
+/*
  * Drop device pages that we maintain for the secure guest
  *
  * We first mark the pages to be skipped from UV_PAGE_OUT when there
@@ -866,82 +956,6 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 	return ret;
 }
 
-/*
- * Provision a new page on HV side and copy over the contents
- * from secure memory using UV_PAGE_OUT uvcall.
- */
-static int kvmppc_svm_page_out(struct vm_area_struct *vma,
-		unsigned long start,
-		unsigned long end, unsigned long page_shift,
-		struct kvm *kvm, unsigned long gpa)
-{
-	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
-	struct page *dpage, *spage;
-	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn;
-	int ret = U_SUCCESS;
-
-	memset(&mig, 0, sizeof(mig));
-	mig.vma = vma;
-	mig.start = start;
-	mig.end = end;
-	mig.src = &src_pfn;
-	mig.dst = &dst_pfn;
-	mig.src_owner = &kvmppc_uvmem_pgmap;
-
-	mutex_lock(&kvm->arch.uvmem_lock);
-	/* The requested page is already paged-out, nothing to do */
-	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
-		goto out;
-
-	ret = migrate_vma_setup(&mig);
-	if (ret)
-		goto out;
-
-	spage = migrate_pfn_to_page(*mig.src);
-	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
-		goto out_finalize;
-
-	if (!is_zone_device_page(spage))
-		goto out_finalize;
-
-	dpage = alloc_page_vma(GFP_HIGHUSER, vma, start);
-	if (!dpage) {
-		ret = -1;
-		goto out_finalize;
-	}
-
-	lock_page(dpage);
-	pvt = spage->zone_device_data;
-	pfn = page_to_pfn(dpage);
-
-	/*
-	 * This function is used in two cases:
-	 * - When HV touches a secure page, for which we do UV_PAGE_OUT
-	 * - When a secure page is converted to shared page, we *get*
-	 *   the page to essentially unmap the device page. In this
-	 *   case we skip page-out.
-	 */
-	if (!pvt->skip_page_out)
-		ret = uv_page_out(kvm->arch.lpid, pfn << page_shift,
-				  gpa, 0, page_shift);
-
-	if (ret = U_SUCCESS)
-		*mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
-	else {
-		unlock_page(dpage);
-		__free_page(dpage);
-		goto out_finalize;
-	}
-
-	migrate_vma_pages(&mig);
-out_finalize:
-	migrate_vma_finalize(&mig);
-out:
-	mutex_unlock(&kvm->arch.uvmem_lock);
-	return ret;
-}
 
 /*
  * Fault handler callback that gets called when HV touches any page that
Signature · 1 line
1.8.3.1
#11 lore raw

PATCH v2 2/2 KVM: PPC: Book3S HV: rework secure mem slot dropping

In reply to Ram Pai

From: Laurent Dufour <[email protected]>

When a secure memslot is dropped, all the pages backed in the secure device (aka really backed by secure memory by the Ultravisor) should be paged out to a normal page. Previously, this was achieved by triggering the page fault mechanism which is calling kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory slot is flagged as invalid and gfn_to_pfn() is then not trying to access the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems simpler to call directly instead of triggering such a mechanism. This way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock, the call to __kvmppc_svm_page_out() is made. As __kvmppc_svm_page_out needs the vma pointer to migrate the pages, the VMA is fetched in a lazy way, to not trigger find_vma() all the time. In addition, the mmap_sem is held in read mode during that time, not in write mode since the virual memory layout is not impacted, and kvm->arch.uvmem_lock prevents concurrent operation on the secure device.

Cc Ram Pai <[email protected]>
Cc Bharata B Rao <[email protected]>
Cc Paul Mackerras <[email protected]>
[modified the changelog description]
[modified check on the VMA in kvmppc_uvmem_drop_pages]
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 52 +++++++++++++++++++++++++-------------
 1 file changed, 35 insertions(+), 17 deletions(-)
arch/powerpc/kvm/book3s_hv_uvmem.c +35 -17
index 565f24b..0d49e34 100644
@@ -594,35 +594,53 @@ static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
  * fault on them, do fault time migration to replace the device PTEs in
  * QEMU page table with normal PTEs from newly allocated pages.
  */
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
 			     struct kvm *kvm, bool skip_page_out)
 {
 	int i;
 	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn, uvmem_pfn;
-	unsigned long gfn = free->base_gfn;
+	struct page *uvmem_page;
+	struct vm_area_struct *vma = NULL;
+	unsigned long uvmem_pfn, gfn;
+	unsigned long addr;
+
+	mmap_read_lock(kvm->mm);
+
+	addr = slot->userspace_addr;
 
-	for (i = free->npages; i; --i, ++gfn) {
-		struct page *uvmem_page;
+	gfn = slot->base_gfn;
+	for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) {
+
+		/* Fetch the VMA if addr is not in the latest fetched one */
+		if (!vma || addr >= vma->vm_end) {
+			vma = find_vma_intersection(kvm->mm, addr, addr+1);
+			if (!vma) {
+				pr_err("Can't find VMA for gfn:0x%lx\n", gfn);
+				break;
+			}
+		}
 
 		mutex_lock(&kvm->arch.uvmem_lock);
-		if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+
+		if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+			uvmem_page = pfn_to_page(uvmem_pfn);
+			pvt = uvmem_page->zone_device_data;
+			pvt->skip_page_out = skip_page_out;
+			pvt->remove_gfn = true;
+
+			if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
+						  PAGE_SHIFT, kvm, pvt->gpa))
+				pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
+				       pvt->gpa, addr);
+		} else {
+			/* Remove the shared flag if any */
 			kvmppc_gfn_remove(gfn, kvm);
-			mutex_unlock(&kvm->arch.uvmem_lock);
-			continue;
 		}
 
-		uvmem_page = pfn_to_page(uvmem_pfn);
-		pvt = uvmem_page->zone_device_data;
-		pvt->skip_page_out = skip_page_out;
-		pvt->remove_gfn = true;
 		mutex_unlock(&kvm->arch.uvmem_lock);
-
-		pfn = gfn_to_pfn(kvm, gfn);
-		if (is_error_noslot_pfn(pfn))
-			continue;
-		kvm_release_pfn_clean(pfn);
 	}
+
+	mmap_read_unlock(kvm->mm);
 }
 
 unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
Signature · 1 line
1.8.3.1
#12 lore raw
In reply to Ram Pai
Quoted 17 lines · Ram Pai

From: Laurent Dufour <[email protected]>

When doing memory hotplug on a secure VM, the secure pages are not well cleaned from the secure device when dropping the memslot. This silent error, is then preventing the SVM to reboot properly after the following sequence of commands are run in the Qemu monitor:

device_add pc-dimm,id=dimm1,memdev=mem1
device_del dimm1
device_add pc-dimm,id=dimm1,memdev=mem1

At reboot time, when the kernel is booting again and switching to the secure mode, the page_in is failing for the pages in the memslot because the cleanup was not done properly, because the memslot is flagged as invalid during the hot unplug and thus the page fault mechanism is not triggered.

Quoted 7 lines

To prevent that during the memslot dropping, instead of belonging on the page fault mechanism to trigger the page out of the secured pages, it seems simpler to directly call the function doing the page out. This way the state of the memslot is not interfering on the page out process.

This series applies on top of the Ram's one titled:
"[v6 0/5] Migrate non-migrated pages of a SVM."

Thanks, series applied to my kvm-ppc-next branch and pull request sent.

Paul.