* [PATCH v5 2/7] KVM: PPC: Book3S HV: Disable page merging in H_SVM_INIT_START
From: Ram Pai @ 2020-07-23 20:07 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev
Cc: ldufour, linuxram, cclaudio, bharata, sathnaga, aneesh.kumar,
sukadev, bauerman, david
In-Reply-To: <1595534844-16188-1-git-send-email-linuxram@us.ibm.com>
Page-merging of pages in memory-slots associated with a Secure VM,
is disabled in H_SVM_PAGE_IN handler.
This operation should have been done the much earlier; the moment the VM
is initiated for secure-transition. Delaying this operation, increases
the probability for those pages to acquire new references , making it
impossible to migrate those pages in H_SVM_PAGE_IN handler.
Disable page-migration in H_SVM_INIT_START handling.
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
---
Documentation/powerpc/ultravisor.rst | 1 +
arch/powerpc/kvm/book3s_hv_uvmem.c | 123 +++++++++++++++++++++++++----------
2 files changed, 89 insertions(+), 35 deletions(-)
diff --git a/Documentation/powerpc/ultravisor.rst b/Documentation/powerpc/ultravisor.rst
index df136c8..a1c8c37 100644
--- a/Documentation/powerpc/ultravisor.rst
+++ b/Documentation/powerpc/ultravisor.rst
@@ -895,6 +895,7 @@ Return values
One of the following values:
* H_SUCCESS on success.
+ * H_STATE if the VM is not in a position to switch to secure.
Description
~~~~~~~~~~~
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index e6f76bc..533b608 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -211,10 +211,79 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
return false;
}
+static int kvmppc_memslot_page_merge(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot, bool merge)
+{
+ unsigned long gfn = memslot->base_gfn;
+ unsigned long end, start = gfn_to_hva(kvm, gfn);
+ int ret = 0;
+ struct vm_area_struct *vma;
+ int merge_flag = (merge) ? MADV_MERGEABLE : MADV_UNMERGEABLE;
+
+ if (kvm_is_error_hva(start))
+ return H_STATE;
+
+ end = start + (memslot->npages << PAGE_SHIFT);
+
+ mmap_write_lock(kvm->mm);
+ do {
+ vma = find_vma_intersection(kvm->mm, start, end);
+ if (!vma) {
+ ret = H_STATE;
+ break;
+ }
+ ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
+ merge_flag, &vma->vm_flags);
+ if (ret) {
+ ret = H_STATE;
+ break;
+ }
+ start = vma->vm_end;
+ } while (end > vma->vm_end);
+
+ mmap_write_unlock(kvm->mm);
+ return ret;
+}
+
+static void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
+ kvmppc_uvmem_slot_free(kvm, memslot);
+ kvmppc_memslot_page_merge(kvm, memslot, true);
+}
+
+static int kvmppc_uvmem_memslot_create(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ int ret = H_PARAMETER;
+
+ if (kvmppc_memslot_page_merge(kvm, memslot, false))
+ return ret;
+
+ if (kvmppc_uvmem_slot_init(kvm, memslot))
+ goto out1;
+
+ ret = uv_register_mem_slot(kvm->arch.lpid,
+ memslot->base_gfn << PAGE_SHIFT,
+ memslot->npages * PAGE_SIZE,
+ 0, memslot->id);
+ if (ret < 0) {
+ ret = H_PARAMETER;
+ goto out;
+ }
+ return 0;
+out:
+ kvmppc_uvmem_slot_free(kvm, memslot);
+out1:
+ kvmppc_memslot_page_merge(kvm, memslot, true);
+ return ret;
+}
+
unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
{
struct kvm_memslots *slots;
- struct kvm_memory_slot *memslot;
+ struct kvm_memory_slot *memslot, *m;
int ret = H_SUCCESS;
int srcu_idx;
@@ -232,23 +301,24 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
return H_AUTHORITY;
srcu_idx = srcu_read_lock(&kvm->srcu);
+
+ /* register the memslot */
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
- if (kvmppc_uvmem_slot_init(kvm, memslot)) {
- ret = H_PARAMETER;
- goto out;
- }
- ret = uv_register_mem_slot(kvm->arch.lpid,
- memslot->base_gfn << PAGE_SHIFT,
- memslot->npages * PAGE_SIZE,
- 0, memslot->id);
- if (ret < 0) {
- kvmppc_uvmem_slot_free(kvm, memslot);
- ret = H_PARAMETER;
- goto out;
+ ret = kvmppc_uvmem_memslot_create(kvm, memslot);
+ if (ret)
+ break;
+ }
+
+ if (ret) {
+ slots = kvm_memslots(kvm);
+ kvm_for_each_memslot(m, slots) {
+ if (m == memslot)
+ break;
+ kvmppc_uvmem_memslot_delete(kvm, memslot);
}
}
-out:
+
srcu_read_unlock(&kvm->srcu, srcu_idx);
return ret;
}
@@ -384,7 +454,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
*/
static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
unsigned long end, unsigned long gpa, struct kvm *kvm,
- unsigned long page_shift, bool *downgrade)
+ unsigned long page_shift)
{
unsigned long src_pfn, dst_pfn = 0;
struct migrate_vma mig;
@@ -400,18 +470,6 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
mig.src = &src_pfn;
mig.dst = &dst_pfn;
- /*
- * We come here with mmap_lock write lock held just for
- * ksm_madvise(), otherwise we only need read mmap_lock.
- * Hence downgrade to read lock once ksm_madvise() is done.
- */
- ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
- MADV_UNMERGEABLE, &vma->vm_flags);
- mmap_write_downgrade(kvm->mm);
- *downgrade = true;
- if (ret)
- return ret;
-
ret = migrate_vma_setup(&mig);
if (ret)
return ret;
@@ -503,7 +561,6 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
unsigned long flags,
unsigned long page_shift)
{
- bool downgrade = false;
unsigned long start, end;
struct vm_area_struct *vma;
int srcu_idx;
@@ -524,7 +581,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
ret = H_PARAMETER;
srcu_idx = srcu_read_lock(&kvm->srcu);
- mmap_write_lock(kvm->mm);
+ mmap_read_lock(kvm->mm);
start = gfn_to_hva(kvm, gfn);
if (kvm_is_error_hva(start))
@@ -540,16 +597,12 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
if (!vma || vma->vm_start > start || vma->vm_end < end)
goto out_unlock;
- if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift,
- &downgrade))
+ if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift))
ret = H_SUCCESS;
out_unlock:
mutex_unlock(&kvm->arch.uvmem_lock);
out:
- if (downgrade)
- mmap_read_unlock(kvm->mm);
- else
- mmap_write_unlock(kvm->mm);
+ mmap_read_unlock(kvm->mm);
srcu_read_unlock(&kvm->srcu, srcu_idx);
return ret;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH v5 3/7] KVM: PPC: Book3S HV: track the state GFNs associated with secure VMs
From: Ram Pai @ 2020-07-23 20:07 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev
Cc: ldufour, linuxram, cclaudio, bharata, sathnaga, aneesh.kumar,
sukadev, bauerman, david
In-Reply-To: <1595534844-16188-1-git-send-email-linuxram@us.ibm.com>
During the life of SVM, its GFNs transition through normal, secure and
shared states. Since the kernel does not track GFNs that are shared, it
is not possible to disambiguate a shared GFN from a GFN whose PFN has
not yet been migrated to a secure-PFN. Also it is not possible to
disambiguate a secure-GFN from a GFN whose GFN has been pagedout from
the ultravisor.
The ability to identify the state of a GFN is needed to skip migration
of its PFN to secure-PFN during ESM transition.
The code is re-organized to track the states of a GFN as explained
below.
************************************************************************
1. States of a GFN
---------------
The GFN can be in one of the following states.
(a) Secure - The GFN is secure. The GFN is associated with
a Secure VM, the contents of the GFN is not accessible
to the Hypervisor. This GFN can be backed by a secure-PFN,
or can be backed by a normal-PFN with contents encrypted.
The former is true when the GFN is paged-in into the
ultravisor. The latter is true when the GFN is paged-out
of the ultravisor.
(b) Shared - The GFN is shared. The GFN is associated with a
a secure VM. The contents of the GFN is accessible to
Hypervisor. This GFN is backed by a normal-PFN and its
content is un-encrypted.
(c) Normal - The GFN is a normal. The GFN is associated with
a normal VM. The contents of the GFN is accesible to
the Hypervisor. Its content is never encrypted.
2. States of a VM.
---------------
(a) Normal VM: A VM whose contents are always accessible to
the hypervisor. All its GFNs are normal-GFNs.
(b) Secure VM: A VM whose contents are not accessible to the
hypervisor without the VM's consent. Its GFNs are
either Shared-GFN or Secure-GFNs.
(c) Transient VM: A Normal VM that is transitioning to secure VM.
The transition starts on successful return of
H_SVM_INIT_START, and ends on successful return
of H_SVM_INIT_DONE. This transient VM, can have GFNs
in any of the three states; i.e Secure-GFN, Shared-GFN,
and Normal-GFN. The VM never executes in this state
in supervisor-mode.
3. Memory slot State.
------------------
The state of a memory slot mirrors the state of the
VM the memory slot is associated with.
4. VM State transition.
--------------------
A VM always starts in Normal Mode.
H_SVM_INIT_START moves the VM into transient state. During this
time the Ultravisor may request some of its GFNs to be shared or
secured. So its GFNs can be in one of the three GFN states.
H_SVM_INIT_DONE moves the VM entirely from transient state to
secure-state. At this point any left-over normal-GFNs are
transitioned to Secure-GFN.
H_SVM_INIT_ABORT moves the transient VM back to normal VM.
All its GFNs are moved to Normal-GFNs.
UV_TERMINATE transitions the secure-VM back to normal-VM. All
the secure-GFN and shared-GFNs are tranistioned to normal-GFN
Note: The contents of the normal-GFN is undefined at this point.
5. GFN state implementation:
-------------------------
Secure GFN is associated with a secure-PFN; also called uvmem_pfn,
when the GFN is paged-in. Its pfn[] has KVMPPC_GFN_UVMEM_PFN flag
set, and contains the value of the secure-PFN.
It is associated with a normal-PFN; also called mem_pfn, when
the GFN is pagedout. Its pfn[] has KVMPPC_GFN_MEM_PFN flag set.
The value of the normal-PFN is not tracked.
Shared GFN is associated with a normal-PFN. Its pfn[] has
KVMPPC_UVMEM_SHARED_PFN flag set. The value of the normal-PFN
is not tracked.
Normal GFN is associated with normal-PFN. Its pfn[] has
no flag set. The value of the normal-PFN is not tracked.
6. Life cycle of a GFN
--------------------
--------------------------------------------------------------
| | Share | Unshare | SVM |H_SVM_INIT_DONE|
| |operation |operation | abort/ | |
| | | | terminate | |
-------------------------------------------------------------
| | | | | |
| Secure | Shared | Secure |Normal |Secure |
| | | | | |
| Shared | Shared | Secure |Normal |Shared |
| | | | | |
| Normal | Shared | Secure |Normal |Secure |
--------------------------------------------------------------
7. Life cycle of a VM
--------------------
--------------------------------------------------------------------
| | start | H_SVM_ |H_SVM_ |H_SVM_ |UV_SVM_ |
| | VM |INIT_START|INIT_DONE|INIT_ABORT |TERMINATE |
| | | | | | |
--------- ----------------------------------------------------------
| | | | | | |
| Normal | Normal | Transient|Error |Error |Normal |
| | | | | | |
| Secure | Error | Error |Error |Error |Normal |
| | | | | | |
|Transient| N/A | Error |Secure |Normal |Normal |
--------------------------------------------------------------------
************************************************************************
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Claudio Carvalho <cclaudio@linux.ibm.com>
Cc: kvm-ppc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
---
arch/powerpc/kvm/book3s_hv_uvmem.c | 191 +++++++++++++++++++++++++++++++++----
1 file changed, 172 insertions(+), 19 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 533b608..1b2b029 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -98,7 +98,127 @@
static unsigned long *kvmppc_uvmem_bitmap;
static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock);
-#define KVMPPC_UVMEM_PFN (1UL << 63)
+/*
+ * States of a GFN
+ * ---------------
+ * The GFN can be in one of the following states.
+ *
+ * (a) Secure - The GFN is secure. The GFN is associated with
+ * a Secure VM, the contents of the GFN is not accessible
+ * to the Hypervisor. This GFN can be backed by a secure-PFN,
+ * or can be backed by a normal-PFN with contents encrypted.
+ * The former is true when the GFN is paged-in into the
+ * ultravisor. The latter is true when the GFN is paged-out
+ * of the ultravisor.
+ *
+ * (b) Shared - The GFN is shared. The GFN is associated with a
+ * a secure VM. The contents of the GFN is accessible to
+ * Hypervisor. This GFN is backed by a normal-PFN and its
+ * content is un-encrypted.
+ *
+ * (c) Normal - The GFN is a normal. The GFN is associated with
+ * a normal VM. The contents of the GFN is accesible to
+ * the Hypervisor. Its content is never encrypted.
+ *
+ * States of a VM.
+ * ---------------
+ *
+ * Normal VM: A VM whose contents are always accessible to
+ * the hypervisor. All its GFNs are normal-GFNs.
+ *
+ * Secure VM: A VM whose contents are not accessible to the
+ * hypervisor without the VM's consent. Its GFNs are
+ * either Shared-GFN or Secure-GFNs.
+ *
+ * Transient VM: A Normal VM that is transitioning to secure VM.
+ * The transition starts on successful return of
+ * H_SVM_INIT_START, and ends on successful return
+ * of H_SVM_INIT_DONE. This transient VM, can have GFNs
+ * in any of the three states; i.e Secure-GFN, Shared-GFN,
+ * and Normal-GFN. The VM never executes in this state
+ * in supervisor-mode.
+ *
+ * Memory slot State.
+ * -----------------------------
+ * The state of a memory slot mirrors the state of the
+ * VM the memory slot is associated with.
+ *
+ * VM State transition.
+ * --------------------
+ *
+ * A VM always starts in Normal Mode.
+ *
+ * H_SVM_INIT_START moves the VM into transient state. During this
+ * time the Ultravisor may request some of its GFNs to be shared or
+ * secured. So its GFNs can be in one of the three GFN states.
+ *
+ * H_SVM_INIT_DONE moves the VM entirely from transient state to
+ * secure-state. At this point any left-over normal-GFNs are
+ * transitioned to Secure-GFN.
+ *
+ * H_SVM_INIT_ABORT moves the transient VM back to normal VM.
+ * All its GFNs are moved to Normal-GFNs.
+ *
+ * UV_TERMINATE transitions the secure-VM back to normal-VM. All
+ * the secure-GFN and shared-GFNs are tranistioned to normal-GFN
+ * Note: The contents of the normal-GFN is undefined at this point.
+ *
+ * GFN state implementation:
+ * -------------------------
+ *
+ * Secure GFN is associated with a secure-PFN; also called uvmem_pfn,
+ * when the GFN is paged-in. Its pfn[] has KVMPPC_GFN_UVMEM_PFN flag
+ * set, and contains the value of the secure-PFN.
+ * It is associated with a normal-PFN; also called mem_pfn, when
+ * the GFN is pagedout. Its pfn[] has KVMPPC_GFN_MEM_PFN flag set.
+ * The value of the normal-PFN is not tracked.
+ *
+ * Shared GFN is associated with a normal-PFN. Its pfn[] has
+ * KVMPPC_UVMEM_SHARED_PFN flag set. The value of the normal-PFN
+ * is not tracked.
+ *
+ * Normal GFN is associated with normal-PFN. Its pfn[] has
+ * no flag set. The value of the normal-PFN is not tracked.
+ *
+ * Life cycle of a GFN
+ * --------------------
+ *
+ * --------------------------------------------------------------
+ * | | Share | Unshare | SVM |H_SVM_INIT_DONE|
+ * | |operation |operation | abort/ | |
+ * | | | | terminate | |
+ * -------------------------------------------------------------
+ * | | | | | |
+ * | Secure | Shared | Secure |Normal |Secure |
+ * | | | | | |
+ * | Shared | Shared | Secure |Normal |Shared |
+ * | | | | | |
+ * | Normal | Shared | Secure |Normal |Secure |
+ * --------------------------------------------------------------
+ *
+ * Life cycle of a VM
+ * --------------------
+ *
+ * --------------------------------------------------------------------
+ * | | start | H_SVM_ |H_SVM_ |H_SVM_ |UV_SVM_ |
+ * | | VM |INIT_START|INIT_DONE|INIT_ABORT |TERMINATE |
+ * | | | | | | |
+ * --------- ----------------------------------------------------------
+ * | | | | | | |
+ * | Normal | Normal | Transient|Error |Error |Normal |
+ * | | | | | | |
+ * | Secure | Error | Error |Error |Error |Normal |
+ * | | | | | | |
+ * |Transient| N/A | Error |Secure |Normal |Normal |
+ * --------------------------------------------------------------------
+ */
+
+#define KVMPPC_GFN_UVMEM_PFN (1UL << 63)
+#define KVMPPC_GFN_MEM_PFN (1UL << 62)
+#define KVMPPC_GFN_SHARED (1UL << 61)
+#define KVMPPC_GFN_SECURE (KVMPPC_GFN_UVMEM_PFN | KVMPPC_GFN_MEM_PFN)
+#define KVMPPC_GFN_FLAG_MASK (KVMPPC_GFN_SECURE | KVMPPC_GFN_SHARED)
+#define KVMPPC_GFN_PFN_MASK (~KVMPPC_GFN_FLAG_MASK)
struct kvmppc_uvmem_slot {
struct list_head list;
@@ -106,11 +226,11 @@ struct kvmppc_uvmem_slot {
unsigned long base_pfn;
unsigned long *pfns;
};
-
struct kvmppc_uvmem_page_pvt {
struct kvm *kvm;
unsigned long gpa;
bool skip_page_out;
+ bool remove_gfn;
};
bool kvmppc_uvmem_available(void)
@@ -163,8 +283,8 @@ void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot)
mutex_unlock(&kvm->arch.uvmem_lock);
}
-static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn,
- struct kvm *kvm)
+static void kvmppc_mark_gfn(unsigned long gfn, struct kvm *kvm,
+ unsigned long flag, unsigned long uvmem_pfn)
{
struct kvmppc_uvmem_slot *p;
@@ -172,24 +292,41 @@ static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn,
if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
unsigned long index = gfn - p->base_pfn;
- p->pfns[index] = uvmem_pfn | KVMPPC_UVMEM_PFN;
+ if (flag == KVMPPC_GFN_UVMEM_PFN)
+ p->pfns[index] = uvmem_pfn | flag;
+ else
+ p->pfns[index] = flag;
return;
}
}
}
-static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm)
+/* mark the GFN as secure-GFN associated with @uvmem pfn device-PFN. */
+static void kvmppc_gfn_secure_uvmem_pfn(unsigned long gfn,
+ unsigned long uvmem_pfn, struct kvm *kvm)
{
- struct kvmppc_uvmem_slot *p;
+ kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_UVMEM_PFN, uvmem_pfn);
+}
- list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
- if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
- p->pfns[gfn - p->base_pfn] = 0;
- return;
- }
- }
+/* mark the GFN as secure-GFN associated with a memory-PFN. */
+static void kvmppc_gfn_secure_mem_pfn(unsigned long gfn, struct kvm *kvm)
+{
+ kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_MEM_PFN, 0);
}
+/* mark the GFN as a shared GFN. */
+static void kvmppc_gfn_shared(unsigned long gfn, struct kvm *kvm)
+{
+ kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_SHARED, 0);
+}
+
+/* mark the GFN as a non-existent GFN. */
+static void kvmppc_gfn_remove(unsigned long gfn, struct kvm *kvm)
+{
+ kvmppc_mark_gfn(gfn, kvm, 0, 0);
+}
+
+/* return true, if the GFN is a secure-GFN backed by a secure-PFN */
static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
unsigned long *uvmem_pfn)
{
@@ -199,10 +336,10 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
unsigned long index = gfn - p->base_pfn;
- if (p->pfns[index] & KVMPPC_UVMEM_PFN) {
+ if (p->pfns[index] & KVMPPC_GFN_UVMEM_PFN) {
if (uvmem_pfn)
*uvmem_pfn = p->pfns[index] &
- ~KVMPPC_UVMEM_PFN;
+ KVMPPC_GFN_PFN_MASK;
return true;
} else
return false;
@@ -354,6 +491,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
mutex_lock(&kvm->arch.uvmem_lock);
if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+ kvmppc_gfn_remove(gfn, kvm);
mutex_unlock(&kvm->arch.uvmem_lock);
continue;
}
@@ -361,6 +499,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
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);
@@ -430,7 +569,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
goto out_clear;
uvmem_pfn = bit + pfn_first;
- kvmppc_uvmem_pfn_insert(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
+ kvmppc_gfn_secure_uvmem_pfn(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
pvt->gpa = gpa;
pvt->kvm = kvm;
@@ -525,6 +664,11 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
uvmem_page = pfn_to_page(uvmem_pfn);
pvt = uvmem_page->zone_device_data;
pvt->skip_page_out = true;
+ /*
+ * do not drop the GFN. It is a valid GFN
+ * that is transitioned to a shared GFN.
+ */
+ pvt->remove_gfn = false;
}
retry:
@@ -538,12 +682,16 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
uvmem_page = pfn_to_page(uvmem_pfn);
pvt = uvmem_page->zone_device_data;
pvt->skip_page_out = true;
+ pvt->remove_gfn = false; /* it continues to be a valid GFN */
kvm_release_pfn_clean(pfn);
goto retry;
}
- if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, page_shift))
+ if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
+ page_shift)) {
+ kvmppc_gfn_shared(gfn, kvm);
ret = H_SUCCESS;
+ }
kvm_release_pfn_clean(pfn);
mutex_unlock(&kvm->arch.uvmem_lock);
out:
@@ -599,6 +747,7 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift))
ret = H_SUCCESS;
+
out_unlock:
mutex_unlock(&kvm->arch.uvmem_lock);
out:
@@ -707,7 +856,8 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
/*
* Release the device PFN back to the pool
*
- * Gets called when secure page becomes a normal page during H_SVM_PAGE_OUT.
+ * Gets called when secure GFN tranistions from a secure-PFN
+ * to a normal PFN during H_SVM_PAGE_OUT.
* Gets called with kvm->arch.uvmem_lock held.
*/
static void kvmppc_uvmem_page_free(struct page *page)
@@ -722,7 +872,10 @@ static void kvmppc_uvmem_page_free(struct page *page)
pvt = page->zone_device_data;
page->zone_device_data = NULL;
- kvmppc_uvmem_pfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+ if (pvt->remove_gfn)
+ kvmppc_gfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+ else
+ kvmppc_gfn_secure_mem_pfn(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
kfree(pvt);
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH v5 4/7] KVM: PPC: Book3S HV: in H_SVM_INIT_DONE, migrate remaining normal-GFNs to secure-GFNs.
From: Ram Pai @ 2020-07-23 20:07 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev
Cc: ldufour, linuxram, cclaudio, bharata, sathnaga, aneesh.kumar,
sukadev, bauerman, david
In-Reply-To: <1595534844-16188-1-git-send-email-linuxram@us.ibm.com>
The Ultravisor is expected to explicitly call H_SVM_PAGE_IN for all the
pages of the SVM before calling H_SVM_INIT_DONE. This causes a huge
delay in tranistioning the VM to SVM. The Ultravisor is only interested
in the pages that contain the kernel, initrd and other important data
structures. The rest contain throw-away content.
However if not all pages are requested by the Ultravisor, the Hypervisor
continues to consider the GFNs corresponding to the non-requested pages
as normal GFNs. This can lead to data-corruption and undefined behavior.
In H_SVM_INIT_DONE handler, move all the PFNs associated with the SVM's
GFNs to secure-PFNs. Skip the GFNs that are already Paged-in or Shared
or Paged-in followed by a Paged-out.
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Claudio Carvalho <cclaudio@linux.ibm.com>
Cc: kvm-ppc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
---
Documentation/powerpc/ultravisor.rst | 2 +
arch/powerpc/include/asm/kvm_book3s_uvmem.h | 2 +
arch/powerpc/kvm/book3s_hv_uvmem.c | 136 +++++++++++++++++++++++++---
3 files changed, 127 insertions(+), 13 deletions(-)
diff --git a/Documentation/powerpc/ultravisor.rst b/Documentation/powerpc/ultravisor.rst
index a1c8c37..ba6b1bf 100644
--- a/Documentation/powerpc/ultravisor.rst
+++ b/Documentation/powerpc/ultravisor.rst
@@ -934,6 +934,8 @@ Return values
* H_UNSUPPORTED if called from the wrong context (e.g.
from an SVM or before an H_SVM_INIT_START
hypercall).
+ * H_STATE if the hypervisor could not successfully
+ transition the VM to Secure VM.
Description
~~~~~~~~~~~
diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
index 9cb7d8b..f229ab5 100644
--- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h
+++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
@@ -23,6 +23,8 @@ unsigned long kvmppc_h_svm_page_out(struct kvm *kvm,
unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm);
void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
struct kvm *kvm, bool skip_page_out);
+int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot);
#else
static inline int kvmppc_uvmem_init(void)
{
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 1b2b029..43b3566 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -93,6 +93,7 @@
#include <asm/ultravisor.h>
#include <asm/mman.h>
#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s_uvmem.h>
static struct dev_pagemap kvmppc_uvmem_pgmap;
static unsigned long *kvmppc_uvmem_bitmap;
@@ -348,6 +349,41 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
return false;
}
+/*
+ * starting from *gfn search for the next available GFN that is not yet
+ * transitioned to a secure GFN. return the value of that GFN in *gfn. If a
+ * GFN is found, return true, else return false
+ *
+ * Must be called with kvm->arch.uvmem_lock held.
+ */
+static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot,
+ struct kvm *kvm, unsigned long *gfn)
+{
+ struct kvmppc_uvmem_slot *p;
+ bool ret = false;
+ unsigned long i;
+
+ list_for_each_entry(p, &kvm->arch.uvmem_pfns, list)
+ if (*gfn >= p->base_pfn && *gfn < p->base_pfn + p->nr_pfns)
+ break;
+ if (!p)
+ return ret;
+ /*
+ * The code below assumes, one to one correspondence between
+ * kvmppc_uvmem_slot and memslot.
+ */
+ for (i = *gfn; i < p->base_pfn + p->nr_pfns; i++) {
+ unsigned long index = i - p->base_pfn;
+
+ if (!(p->pfns[index] & KVMPPC_GFN_FLAG_MASK)) {
+ *gfn = i;
+ ret = true;
+ break;
+ }
+ }
+ return ret;
+}
+
static int kvmppc_memslot_page_merge(struct kvm *kvm,
const struct kvm_memory_slot *memslot, bool merge)
{
@@ -462,12 +498,40 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int srcu_idx;
+ long ret = H_SUCCESS;
+
if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
return H_UNSUPPORTED;
+ /* migrate any unmoved normal pfn to device pfns*/
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+ slots = kvm_memslots(kvm);
+ kvm_for_each_memslot(memslot, slots) {
+ ret = kvmppc_uv_migrate_mem_slot(kvm, memslot);
+ if (ret) {
+ /*
+ * The pages will remain transitioned.
+ * Its the callers responsibility to
+ * terminate the VM, which will undo
+ * all state of the VM. Till then
+ * this VM is in a erroneous state.
+ * Its KVMPPC_SECURE_INIT_DONE will
+ * remain unset.
+ */
+ ret = H_STATE;
+ goto out;
+ }
+ }
+
kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
pr_info("LPID %d went secure\n", kvm->arch.lpid);
- return H_SUCCESS;
+
+out:
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+ return ret;
}
/*
@@ -588,12 +652,14 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
}
/*
- * Alloc a PFN from private device memory pool and copy page from normal
- * memory to secure memory using UV_PAGE_IN uvcall.
+ * Alloc a PFN from private device memory pool. If @pagein is true,
+ * copy page from normal memory to secure memory using UV_PAGE_IN uvcall.
*/
-static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
- unsigned long end, unsigned long gpa, struct kvm *kvm,
- unsigned long page_shift)
+static int kvmppc_svm_page_in(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end, unsigned long gpa, struct kvm *kvm,
+ unsigned long page_shift,
+ bool pagein)
{
unsigned long src_pfn, dst_pfn = 0;
struct migrate_vma mig;
@@ -624,11 +690,16 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
goto out_finalize;
}
- pfn = *mig.src >> MIGRATE_PFN_SHIFT;
- spage = migrate_pfn_to_page(*mig.src);
- if (spage)
- uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
- page_shift);
+ if (pagein) {
+ pfn = *mig.src >> MIGRATE_PFN_SHIFT;
+ spage = migrate_pfn_to_page(*mig.src);
+ if (spage) {
+ ret = uv_page_in(kvm->arch.lpid, pfn << page_shift,
+ gpa, 0, page_shift);
+ if (ret)
+ goto out_finalize;
+ }
+ }
*mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
migrate_vma_pages(&mig);
@@ -637,6 +708,42 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
return ret;
}
+int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ unsigned long gfn = memslot->base_gfn;
+ struct vm_area_struct *vma;
+ unsigned long start, end;
+ int ret = 0;
+
+ mmap_read_lock(kvm->mm);
+ mutex_lock(&kvm->arch.uvmem_lock);
+ while (kvmppc_next_nontransitioned_gfn(memslot, kvm, &gfn)) {
+ ret = H_STATE;
+ start = gfn_to_hva(kvm, gfn);
+ if (kvm_is_error_hva(start))
+ break;
+
+ end = start + (1UL << PAGE_SHIFT);
+ vma = find_vma_intersection(kvm->mm, start, end);
+ if (!vma || vma->vm_start > start || vma->vm_end < end)
+ break;
+
+ ret = kvmppc_svm_page_in(vma, start, end,
+ (gfn << PAGE_SHIFT), kvm, PAGE_SHIFT, false);
+ if (ret) {
+ ret = H_STATE;
+ break;
+ }
+
+ /* relinquish the cpu if needed */
+ cond_resched();
+ }
+ mutex_unlock(&kvm->arch.uvmem_lock);
+ mmap_read_unlock(kvm->mm);
+ return ret;
+}
+
/*
* Shares the page with HV, thus making it a normal page.
*
@@ -745,8 +852,11 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
if (!vma || vma->vm_start > start || vma->vm_end < end)
goto out_unlock;
- if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift))
- ret = H_SUCCESS;
+ if (kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift,
+ true))
+ goto out_unlock;
+
+ ret = H_SUCCESS;
out_unlock:
mutex_unlock(&kvm->arch.uvmem_lock);
--
1.8.3.1
^ permalink raw reply related
* [PATCH v5 5/7] KVM: PPC: Book3S HV: migrate hot plugged memory
From: Ram Pai @ 2020-07-23 20:07 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev
Cc: ldufour, linuxram, cclaudio, bharata, sathnaga, aneesh.kumar,
sukadev, bauerman, david
In-Reply-To: <1595534844-16188-1-git-send-email-linuxram@us.ibm.com>
From: Laurent Dufour <ldufour@linux.ibm.com>
When a memory slot is hot plugged to a SVM, PFNs associated with the
GFNs in that slot must be migrated to the secure-PFNs, aka device-PFNs.
Call kvmppc_uv_migrate_mem_slot() to accomplish this.
Disable page-merge for all pages in the memory slot.
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
[rearranged the code, and modified the commit log]
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
arch/powerpc/include/asm/kvm_book3s_uvmem.h | 14 ++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 10 ++--------
arch/powerpc/kvm/book3s_hv_uvmem.c | 23 +++++++++++++++++++----
3 files changed, 35 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
index f229ab5..59c17ca 100644
--- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h
+++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
@@ -25,6 +25,10 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
struct kvm *kvm, bool skip_page_out);
int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
+int kvmppc_uvmem_memslot_create(struct kvm *kvm,
+ const struct kvm_memory_slot *new);
+void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+ const struct kvm_memory_slot *old);
#else
static inline int kvmppc_uvmem_init(void)
{
@@ -84,5 +88,15 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
static inline void
kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
struct kvm *kvm, bool skip_page_out) { }
+
+static inline int kvmppc_uvmem_memslot_create(struct kvm *kvm,
+ const struct kvm_memory_slot *new)
+{
+ return H_UNSUPPORTED;
+}
+
+static inline void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+ const struct kvm_memory_slot *old) { }
+
#endif /* CONFIG_PPC_UV */
#endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d331b46..b1485ca 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4515,16 +4515,10 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
switch (change) {
case KVM_MR_CREATE:
- if (kvmppc_uvmem_slot_init(kvm, new))
- return;
- uv_register_mem_slot(kvm->arch.lpid,
- new->base_gfn << PAGE_SHIFT,
- new->npages * PAGE_SIZE,
- 0, new->id);
+ kvmppc_uvmem_memslot_create(kvm, new);
break;
case KVM_MR_DELETE:
- uv_unregister_mem_slot(kvm->arch.lpid, old->id);
- kvmppc_uvmem_slot_free(kvm, old);
+ kvmppc_uvmem_memslot_delete(kvm, old);
break;
default:
/* TODO: Handle KVM_MR_MOVE */
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 43b3566..fd9ff6e 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -418,7 +418,7 @@ static int kvmppc_memslot_page_merge(struct kvm *kvm,
return ret;
}
-static void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+static void __kvmppc_uvmem_memslot_delete(struct kvm *kvm,
const struct kvm_memory_slot *memslot)
{
uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
@@ -426,7 +426,7 @@ static void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
kvmppc_memslot_page_merge(kvm, memslot, true);
}
-static int kvmppc_uvmem_memslot_create(struct kvm *kvm,
+static int __kvmppc_uvmem_memslot_create(struct kvm *kvm,
const struct kvm_memory_slot *memslot)
{
int ret = H_PARAMETER;
@@ -478,7 +478,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
/* register the memslot */
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
- ret = kvmppc_uvmem_memslot_create(kvm, memslot);
+ ret = __kvmppc_uvmem_memslot_create(kvm, memslot);
if (ret)
break;
}
@@ -488,7 +488,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
kvm_for_each_memslot(m, slots) {
if (m == memslot)
break;
- kvmppc_uvmem_memslot_delete(kvm, memslot);
+ __kvmppc_uvmem_memslot_delete(kvm, memslot);
}
}
@@ -1057,6 +1057,21 @@ int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT;
}
+int kvmppc_uvmem_memslot_create(struct kvm *kvm, const struct kvm_memory_slot *new)
+{
+ int ret = __kvmppc_uvmem_memslot_create(kvm, new);
+
+ if (!ret)
+ ret = kvmppc_uv_migrate_mem_slot(kvm, new);
+
+ return ret;
+}
+
+void kvmppc_uvmem_memslot_delete(struct kvm *kvm, const struct kvm_memory_slot *old)
+{
+ __kvmppc_uvmem_memslot_delete(kvm, old);
+}
+
static u64 kvmppc_get_secmem_size(void)
{
struct device_node *np;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v5 6/7] KVM: PPC: Book3S HV: move kvmppc_svm_page_out up
From: Ram Pai @ 2020-07-23 20:07 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev
Cc: ldufour, linuxram, cclaudio, bharata, sathnaga, aneesh.kumar,
sukadev, bauerman, david
In-Reply-To: <1595534844-16188-1-git-send-email-linuxram@us.ibm.com>
From: Laurent Dufour <ldufour@linux.ibm.com>
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 <linuxram@us.ibm.com>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
arch/powerpc/kvm/book3s_hv_uvmem.c | 166 ++++++++++++++++++++-----------------
1 file changed, 90 insertions(+), 76 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index fd9ff6e..c772e92 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -535,6 +535,96 @@ unsigned long kvmppc_h_svm_init_done(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
--
1.8.3.1
^ permalink raw reply related
* [PATCH v5 7/7] KVM: PPC: Book3S HV: rework secure mem slot dropping
From: Ram Pai @ 2020-07-23 20:07 UTC (permalink / raw)
To: kvm-ppc, linuxppc-dev
Cc: ldufour, linuxram, cclaudio, bharata, sathnaga, aneesh.kumar,
sukadev, bauerman, david
In-Reply-To: <1595534844-16188-1-git-send-email-linuxram@us.ibm.com>
From: Laurent Dufour <ldufour@linux.ibm.com>
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 <linuxram@us.ibm.com>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
[modified the changelog description]
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
arch/powerpc/kvm/book3s_hv_uvmem.c | 54 ++++++++++++++++++++++++++------------
1 file changed, 37 insertions(+), 17 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index c772e92..daffa6e 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -632,35 +632,55 @@ 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)
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH] ASoC: fsl: Replace HTTP links with HTTPS ones
From: Mark Brown @ 2020-07-23 20:19 UTC (permalink / raw)
To: perex, nicoleotsuka, Alexander A. Klimov, festevam, Xiubo.Lee,
kernel, shawnguo, tiwai, alsa-devel, linux-kernel, linux-imx,
lgirdwood, s.hauer, timur, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20200718111209.11760-1-grandmaster@al2klimov.de>
On Sat, 18 Jul 2020 13:12:09 +0200, Alexander A. Klimov wrote:
> Rationale:
> Reduces attack surface on kernel devs opening the links for MITM
> as HTTPS traffic is much harder to manipulate.
>
> Deterministic algorithm:
> For each file:
> If not .svg:
> For each line:
> If doesn't contain `\bxmlns\b`:
> For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
> If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
> If both the HTTP and HTTPS versions
> return 200 OK and serve the same content:
> Replace HTTP with HTTPS.
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
Thanks!
[1/1] ASoC: fsl: Replace HTTP links with HTTPS ones
commit: 1ce8f643ed875d754ff09bf2096dfac3b905ab80
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark
^ permalink raw reply
* Re: [PATCH 1/2] ASoC: fsl-asoc-card: Support configuring dai fmt from DT
From: Mark Brown @ 2020-07-23 20:19 UTC (permalink / raw)
To: perex, nicoleotsuka, Shengjiu Wang, festevam, Xiubo.Lee,
devicetree, tiwai, alsa-devel, lgirdwood, timur, robh+dt
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <1595302910-19688-1-git-send-email-shengjiu.wang@nxp.com>
On Tue, 21 Jul 2020 11:41:49 +0800, Shengjiu Wang wrote:
> Support same propeties as simple card for configuring fmt
> from DT.
> In order to make this change compatible with old DT, these
> properties are optional.
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
Thanks!
[1/2] ASoC: fsl-asoc-card: Support configuring dai fmt from DT
commit: 08b54b5e38e67b7e99f71b35cb8841b53e006759
[2/2] ASoC: bindings: fsl-asoc-card: Support properties for configuring dai fmt
commit: ca168352cf94bbbc523794f2a2972adcf84d8639
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark
^ permalink raw reply
* Re: [PATCH] ASoC: fsl_esai: add IRQF_SHARED for devm_request_irq
From: Mark Brown @ 2020-07-23 20:20 UTC (permalink / raw)
To: perex, nicoleotsuka, Shengjiu Wang, festevam, Xiubo.Lee, tiwai,
alsa-devel, timur
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <1595476808-28927-1-git-send-email-shengjiu.wang@nxp.com>
On Thu, 23 Jul 2020 12:00:08 +0800, Shengjiu Wang wrote:
> ESAI interfaces may share same interrupt line with EDMA on
> some platforms (e.g. i.MX8QXP, i.MX8QM).
> Add IRQF_SHARED flag to allow sharing the irq among several
> devices
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
Thanks!
[1/1] ASoC: fsl_esai: add IRQF_SHARED for devm_request_irq
commit: c8361757a712dff4db49e18b736635e367b0f473
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark
^ permalink raw reply
* Re: [PATCH v3 5/6] powerpc/pseries: implement paravirt qspinlocks for SPLPAR
From: Segher Boessenkool @ 2020-07-23 20:30 UTC (permalink / raw)
To: peterz
Cc: linux-arch, Will Deacon, Boqun Feng, linux-kernel,
Nicholas Piggin, virtualization, Ingo Molnar, kvm-ppc,
Waiman Long, linuxppc-dev
In-Reply-To: <20200723195855.GU119549@hirez.programming.kicks-ass.net>
On Thu, Jul 23, 2020 at 09:58:55PM +0200, peterz@infradead.org wrote:
> asm ("addb %[val], %b[var];"
> "cmovc %[sat], %[var];"
> : [var] "+r" (tmp)
> : [val] "ir" (val), [sat] "r" (sat)
> );
"var" (operand 0) needs an earlyclobber ("sat" is read after "var" is
written for the first time).
Segher
^ permalink raw reply
* Re: [PATCH v3 5/6] powerpc/pseries: implement paravirt qspinlocks for SPLPAR
From: Waiman Long @ 2020-07-23 21:58 UTC (permalink / raw)
To: peterz
Cc: linux-arch, Boqun Feng, virtualization, linuxppc-dev,
Nicholas Piggin, linux-kernel, Ingo Molnar, kvm-ppc, Will Deacon
In-Reply-To: <20200723195855.GU119549@hirez.programming.kicks-ass.net>
On 7/23/20 3:58 PM, peterz@infradead.org wrote:
> On Thu, Jul 23, 2020 at 03:04:13PM -0400, Waiman Long wrote:
>> On 7/23/20 2:47 PM, peterz@infradead.org wrote:
>>> On Thu, Jul 23, 2020 at 02:32:36PM -0400, Waiman Long wrote:
>>>> BTW, do you have any comment on my v2 lock holder cpu info qspinlock patch?
>>>> I will have to update the patch to fix the reported 0-day test problem, but
>>>> I want to collect other feedback before sending out v3.
>>> I want to say I hate it all, it adds instructions to a path we spend an
>>> aweful lot of time optimizing without really getting anything back for
>>> it.
>> It does add some extra instruction that may slow it down slightly, but I
>> don't agree that it gives nothing back. The cpu lock holder information can
>> be useful in analyzing crash dumps and in some debugging situation. I think
>> it can be useful in RHEL for this readon. How about an x86 config option to
>> allow distros to decide if they want to have it enabled? I will make sure
>> that it will have no performance degradation if the option is not enabled.
> Config knobs suck too; they create a maintenance burden (we get to make
> sure all the permutations works/build/etc..) and effectively nobody uses
> them, since world+dog uses what distros pick.
>
> Anyway, instead of adding a second per-cpu variable, can you see how
> horrible something like this is:
>
> unsigned char adds(unsigned char var, unsigned char val)
> {
> unsigned short sat = 0xff, tmp = var;
>
> asm ("addb %[val], %b[var];"
> "cmovc %[sat], %[var];"
> : [var] "+r" (tmp)
> : [val] "ir" (val), [sat] "r" (sat)
> );
>
> return tmp;
> }
>
> Another thing to try is, instead of threading that lockval throughout
> the thing, simply:
>
> #define _Q_LOCKED_VAL this_cpu_read_stable(cpu_sat)
>
> or combined with the above
>
> #define _Q_LOCKED_VAL adds(this_cpu_read_stable(cpu_number), 2)
>
> and see if the compiler really makes a mess of things.
>
Thanks for the suggestion. I will try that out.
Cheers,
Longman
^ permalink raw reply
* Re: [PATCH v4 03/12] powerpc/kexec_file: add helper functions for getting memory ranges
From: Thiago Jung Bauermann @ 2020-07-23 22:12 UTC (permalink / raw)
To: Hari Bathini
Cc: Pingfan Liu, Nayna Jain, Kexec-ml, Mahesh J Salgaonkar,
Mimi Zohar, lkml, linuxppc-dev, Sourabh Jain, Petr Tesarik,
Andrew Morton, Dave Young, Vivek Goyal, Eric Biederman
In-Reply-To: <159524946347.20855.15784642736087777919.stgit@hbathini.in.ibm.com>
Hari Bathini <hbathini@linux.ibm.com> writes:
> In kexec case, the kernel to be loaded uses the same memory layout as
> the running kernel. So, passing on the DT of the running kernel would
> be good enough.
>
> But in case of kdump, different memory ranges are needed to manage
> loading the kdump kernel, booting into it and exporting the elfcore
> of the crashing kernel. The ranges are exclude memory ranges, usable
> memory ranges, reserved memory ranges and crash memory ranges.
>
> Exclude memory ranges specify the list of memory ranges to avoid while
> loading kdump segments. Usable memory ranges list the memory ranges
> that could be used for booting kdump kernel. Reserved memory ranges
> list the memory regions for the loading kernel's reserve map. Crash
> memory ranges list the memory ranges to be exported as the crashing
> kernel's elfcore.
>
> Add helper functions for setting up the above mentioned memory ranges.
> This helpers facilitate in understanding the subsequent changes better
> and make it easy to setup the different memory ranges listed above, as
> and when appropriate.
>
> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
> Tested-by: Pingfan Liu <piliu@redhat.com>
Just one comment below, but regardless:
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
> +/**
> + * add_htab_mem_range - Adds htab range to the given memory ranges list,
> + * if it exists
> + * @mem_ranges: Range list to add the memory range to.
> + *
> + * Returns 0 on success, negative errno on error.
> + */
> +int add_htab_mem_range(struct crash_mem **mem_ranges)
> +{
> + if (!htab_address)
> + return 0;
> +
> + return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes);
> +}
I believe you need to surround this function with `#ifdef
CONFIG_PPC_BOOK3S_64` and `#endif` to match what is done in
<asm/kexec_ranges.h>.
--
Thiago Jung Bauermann
IBM Linux Technology Center
^ permalink raw reply
* Re: [PATCH v4 04/12] ppc64/kexec_file: avoid stomping memory used by special regions
From: Thiago Jung Bauermann @ 2020-07-23 22:19 UTC (permalink / raw)
To: Hari Bathini
Cc: Pingfan Liu, Nayna Jain, Kexec-ml, Mahesh J Salgaonkar,
Mimi Zohar, lkml, linuxppc-dev, Sourabh Jain, Petr Tesarik,
Andrew Morton, Dave Young, Vivek Goyal, Eric Biederman
In-Reply-To: <159524948081.20855.1023953568610670370.stgit@hbathini.in.ibm.com>
Hari Bathini <hbathini@linux.ibm.com> writes:
> crashkernel region could have an overlap with special memory regions
> like opal, rtas, tce-table & such. These regions are referred to as
> exclude memory ranges. Setup this ranges during image probe in order
> to avoid them while finding the buffer for different kdump segments.
> Override arch_kexec_locate_mem_hole() to locate a memory hole taking
> these ranges into account.
>
> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
--
Thiago Jung Bauermann
IBM Linux Technology Center
^ permalink raw reply
* Re: [PATCH v5 1/4] riscv: Move kernel mapping to vmalloc zone
From: Benjamin Herrenschmidt @ 2020-07-23 22:33 UTC (permalink / raw)
To: Alex Ghiti, Palmer Dabbelt
Cc: aou, linux-mm, Anup Patel, linux-kernel, Atish Patra, paulus,
zong.li, Paul Walmsley, linux-riscv, linuxppc-dev
In-Reply-To: <cade70e2-0179-2650-41c5-036679aaf30c@ghiti.fr>
On Thu, 2020-07-23 at 01:21 -0400, Alex Ghiti wrote:
> > works fine with huge pages, what is your problem there ? You rely on
> > punching small-page size holes in there ?
> >
>
> ARCH_HAS_STRICT_KERNEL_RWX prevents the use of a hugepage for the kernel
> mapping in the direct mapping as it sets different permissions to
> different part of the kernel (data, text..etc).
Ah ok, that can be solved in a couple of ways...
One is to use the linker script to ensure those sections are linked
HUGE_PAGE_SIZE appart and moved appropriately by early boot code. One
is to selectively degrade just those huge pages.
I'm not familiar with the RiscV MMU (I should probably go have a look)
but if it's a classic radix tree with huge pages at PUD/PMD level, then
you could just degrade the one(s) that cross those boundaries.
Cheers,
Ben.
^ permalink raw reply
* Re: [PATCH v4 06/12] ppc64/kexec_file: restrict memory usage of kdump kernel
From: Thiago Jung Bauermann @ 2020-07-24 0:06 UTC (permalink / raw)
To: Hari Bathini
Cc: Pingfan Liu, Nayna Jain, Kexec-ml, Mahesh J Salgaonkar,
Mimi Zohar, lkml, linuxppc-dev, Sourabh Jain, Petr Tesarik,
Andrew Morton, Dave Young, Vivek Goyal, Eric Biederman
In-Reply-To: <159524954805.20855.1164928096364700614.stgit@hbathini.in.ibm.com>
Hari Bathini <hbathini@linux.ibm.com> writes:
> Kdump kernel, used for capturing the kernel core image, is supposed
> to use only specific memory regions to avoid corrupting the image to
> be captured. The regions are crashkernel range - the memory reserved
> explicitly for kdump kernel, memory used for the tce-table, the OPAL
> region and RTAS region as applicable. Restrict kdump kernel memory
> to use only these regions by setting up usable-memory DT property.
> Also, tell the kdump kernel to run at the loaded address by setting
> the magic word at 0x5c.
>
> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
> Tested-by: Pingfan Liu <piliu@redhat.com>
> ---
>
> v3 -> v4:
> * Updated get_node_path() to be an iterative function instead of a
> recursive one.
> * Added comment explaining why low memory is added to kdump kernel's
> usable memory ranges though it doesn't fall in crashkernel region.
> * For correctness, added fdt_add_mem_rsv() for the low memory being
> added to kdump kernel's usable memory ranges.
Good idea.
> * Fixed prop pointer update in add_usable_mem_property() and changed
> duple to tuple as suggested by Thiago.
<snip>
> +/**
> + * get_node_pathlen - Get the full path length of the given node.
> + * @dn: Node.
> + *
> + * Also, counts '/' at the end of the path.
> + * For example, /memory@0 will be "/memory@0/\0" => 11 bytes.
Wouldn't this function return 10 in the case of /memory@0?
Are you saying that it should count the \0 at the end too? it's not
doing that, AFAICS.
> + *
> + * Returns the string length of the node's full path.
> + */
Maybe it's me (by analogy with strlen()), but I would expect "string
length" to not include the terminating \0. I suggest renaming the
function to something like get_node_path_size() and do s/length/size/ in
the comment above if it's supposed to count the terminating \0.
> +static int get_node_pathlen(struct device_node *dn)
> +{
> + int len = 0;
> +
> + if (!dn)
> + return 0;
> +
> + while (dn) {
> + len += strlen(dn->full_name) + 1;
> + dn = dn->parent;
> + }
> +
> + return len + 1;
> +}
> +
> +/**
> + * get_node_path - Get the full path of the given node.
> + * @node: Device node.
> + *
> + * Allocates buffer for node path. The caller must free the buffer
> + * after use.
> + *
> + * Returns buffer with path on success, NULL otherwise.
> + */
> +static char *get_node_path(struct device_node *node)
> +{
> + struct device_node *dn;
> + int len, idx, nlen;
> + char *path = NULL;
> + char end_char;
> +
> + if (!node)
> + goto err;
> +
> + /*
> + * Get the path length first and use it to iteratively build the path
> + * from node to root.
> + */
> + len = get_node_pathlen(node);
> +
> + /* Allocate memory for node path */
> + path = kzalloc(ALIGN(len, 8), GFP_KERNEL);
> + if (!path)
> + goto err;
> +
> + /*
> + * Iteratively update path from node to root by decrementing
> + * index appropriately.
> + *
> + * Also, add %NUL at the end of node & '/' at the end of all its
> + * parent nodes.
> + */
> + dn = node;
> + path[0] = '/';
> + idx = len - 1;
Here, idx is pointing to the supposed '/' at the end of the node
path ...
> + end_char = '\0';
> + while (dn->parent) {
> + path[--idx] = end_char;
.. and in the first ireation, this is writing '\0' at a place which will be
overwritten by the memcpy() below with the last character of
dn->full_name. You need to start idx with len, not len - 1.
> + end_char = '/';
> +
> + nlen = strlen(dn->full_name);
> + idx -= nlen;
> + memcpy(path + idx, dn->full_name, nlen);
> +
> + dn = dn->parent;
> + }
> +
> + return path;
> +err:
> + kfree(path);
> + return NULL;
> +}
--
Thiago Jung Bauermann
IBM Linux Technology Center
^ permalink raw reply
* [PATCH v 1/1] powerpc/64s: allow for clang's objdump differences
From: Bill Wendling @ 2020-07-24 0:16 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras
Cc: linuxppc-dev, Bill Wendling
Clang's objdump emits slightly different output from GNU's objdump,
causing a list of warnings to be emitted during relocatable builds.
E.g., clang's objdump emits this:
c000000000000004: 2c 00 00 48 b 0xc000000000000030
...
c000000000005c6c: 10 00 82 40 bf 2, 0xc000000000005c7c
while GNU objdump emits:
c000000000000004: 2c 00 00 48 b c000000000000030 <__start+0x30>
...
c000000000005c6c: 10 00 82 40 bne c000000000005c7c <masked_interrupt+0x3c>
Adjust llvm-objdump's output to remove the extraneous '0x' and convert
'bf' and 'bt' to 'bne' and 'beq' resp. to more closely match GNU
objdump's output.
Note that clang's objdump doesn't yet output the relocation symbols on
PPC.
Signed-off-by: Bill Wendling <morbo@google.com>
---
arch/powerpc/tools/unrel_branch_check.sh | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh
index 77114755dc6f..71ce86b68d18 100755
--- a/arch/powerpc/tools/unrel_branch_check.sh
+++ b/arch/powerpc/tools/unrel_branch_check.sh
@@ -31,6 +31,9 @@ grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]
grep -v '\<__start_initialization_multiplatform>' |
grep -v -e 'b.\?.\?ctr' |
grep -v -e 'b.\?.\?lr' |
+sed 's/\bbt.\?[[:space:]]*[[:digit:]][[:digit:]]*,/beq/' |
+sed 's/\bbf.\?[[:space:]]*[[:digit:]][[:digit:]]*,/bne/' |
+sed 's/[[:space:]]0x/ /' |
sed 's/://' |
awk '{ print $1 ":" $6 ":0x" $7 ":" $8 " "}'
)
^ permalink raw reply related
* Re: [PATCH v4 09/12] ppc64/kexec_file: setup backup region for kdump kernel
From: Thiago Jung Bauermann @ 2020-07-24 0:28 UTC (permalink / raw)
To: Hari Bathini
Cc: kernel test robot, Pingfan Liu, Nayna Jain, Kexec-ml,
Mahesh J Salgaonkar, Mimi Zohar, lkml, linuxppc-dev, Sourabh Jain,
Petr Tesarik, Andrew Morton, Dave Young, Vivek Goyal,
Eric Biederman
In-Reply-To: <159524964786.20855.15850644504721928289.stgit@hbathini.in.ibm.com>
Hari Bathini <hbathini@linux.ibm.com> writes:
> Though kdump kernel boots from loaded address, the first 64K bytes
> of it is copied down to real 0. So, setup a backup region to copy
> the first 64K bytes of crashed kernel, in purgatory, before booting
> into kdump kernel. Also, update reserve map with backup region and
> crashed kernel's memory to avoid kdump kernel from accidentially
> using that memory.
>
> Reported-by: kernel test robot <lkp@intel.com>
> [lkp: In v1, purgatory() declaration was missing]
> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Just one minor comment below:
> @@ -1047,13 +1120,26 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
> goto out;
> }
>
> - /* Ensure we don't touch crashed kernel's memory */
> - ret = fdt_add_mem_rsv(fdt, 0, crashk_res.start);
> + /*
> + * Ensure we don't touch crashed kernel's memory except the
> + * first 64K of RAM, which will be backed up.
> + */
> + ret = fdt_add_mem_rsv(fdt, BACKUP_SRC_SIZE,
I know BACKUP_SRC_START is 0, but please forgive my pedantry when I say
that I think it's clearer if the start address above is changed to
BACKUP_SRC_START + BACKUP_SRC_SIZE...
> + crashk_res.start - BACKUP_SRC_SIZE);
> if (ret) {
> pr_err("Error reserving crash memory: %s\n",
> fdt_strerror(ret));
> goto out;
> }
> +
> + /* Ensure backup region is not used by kdump/capture kernel */
> + ret = fdt_add_mem_rsv(fdt, image->arch.backup_start,
> + BACKUP_SRC_SIZE);
> + if (ret) {
> + pr_err("Error reserving memory for backup: %s\n",
> + fdt_strerror(ret));
> + goto out;
> + }
> }
>
> out:
--
Thiago Jung Bauermann
IBM Linux Technology Center
^ permalink raw reply
* Re: [PATCH v4 10/12] ppc64/kexec_file: prepare elfcore header for crashing kernel
From: Thiago Jung Bauermann @ 2020-07-24 0:33 UTC (permalink / raw)
To: Hari Bathini
Cc: Pingfan Liu, Nayna Jain, Kexec-ml, Mahesh J Salgaonkar,
Mimi Zohar, lkml, linuxppc-dev, Sourabh Jain, Petr Tesarik,
Andrew Morton, Dave Young, Vivek Goyal, Eric Biederman
In-Reply-To: <159524966309.20855.15216784717419378243.stgit@hbathini.in.ibm.com>
Hari Bathini <hbathini@linux.ibm.com> writes:
> Prepare elf headers for the crashing kernel's core file using
> crash_prepare_elf64_headers() and pass on this info to kdump
> kernel by updating its command line with elfcorehdr parameter.
> Also, add elfcorehdr location to reserve map to avoid it from
> being stomped on while booting.
>
> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
> Tested-by: Pingfan Liu <piliu@redhat.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
--
Thiago Jung Bauermann
IBM Linux Technology Center
^ permalink raw reply
* [PATCH] powerpc/test_emulate_sstep: Fix build error
From: Michael Ellerman @ 2020-07-24 0:41 UTC (permalink / raw)
To: linuxppc-dev
ppc64_book3e_allmodconfig fails with:
arch/powerpc/lib/test_emulate_step.c: In function 'test_pld':
arch/powerpc/lib/test_emulate_step.c:113:7: error: implicit declaration of function 'cpu_has_feature'
113 | if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
| ^~~~~~~~~~~~~~~
Add an include of cpu_has_feature.h to fix it.
Fixes: b6b54b42722a ("powerpc/sstep: Add tests for prefixed integer load/stores")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/lib/test_emulate_step.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 081b05480c47..d242e9f72e0c 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -8,6 +8,7 @@
#define pr_fmt(fmt) "emulate_step_test: " fmt
#include <linux/ptrace.h>
+#include <asm/cpu_has_feature.h>
#include <asm/sstep.h>
#include <asm/ppc-opcode.h>
#include <asm/code-patching.h>
--
2.25.1
^ permalink raw reply related
* Re: [PATCH v2 2/3] powerpc/powernv/idle: save-restore DAWR0,DAWRX0 for P10
From: Michael Neuling @ 2020-07-24 1:25 UTC (permalink / raw)
To: Pratik Rajesh Sampat, mpe, benh, paulus, ravi.bangoria, ego,
svaidy, pratik.r.sampat, linuxppc-dev, linux-kernel
In-Reply-To: <20200710052207.12003-3-psampat@linux.ibm.com>
On Fri, 2020-07-10 at 10:52 +0530, Pratik Rajesh Sampat wrote:
> Additional registers DAWR0, DAWRX0 may be lost on Power 10 for
> stop levels < 4.
> Therefore save the values of these SPRs before entering a "stop"
> state and restore their values on wakeup.
>
> Signed-off-by: Pratik Rajesh Sampat <psampat@linux.ibm.com>
> ---
> arch/powerpc/platforms/powernv/idle.c | 10 ++++++++++
> 1 file changed, 10 insertions(+)
>
> diff --git a/arch/powerpc/platforms/powernv/idle.c
> b/arch/powerpc/platforms/powernv/idle.c
> index 19d94d021357..f2e2a6a4c274 100644
> --- a/arch/powerpc/platforms/powernv/idle.c
> +++ b/arch/powerpc/platforms/powernv/idle.c
> @@ -600,6 +600,8 @@ struct p9_sprs {
> u64 iamr;
> u64 amor;
> u64 uamor;
> + u64 dawr0;
> + u64 dawrx0;
> };
>
> static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
> @@ -687,6 +689,10 @@ static unsigned long power9_idle_stop(unsigned long
> psscr, bool mmu_on)
> sprs.iamr = mfspr(SPRN_IAMR);
> sprs.amor = mfspr(SPRN_AMOR);
> sprs.uamor = mfspr(SPRN_UAMOR);
> + if (cpu_has_feature(CPU_FTR_ARCH_31)) {
Can you add a comment here saying even though DAWR0 is ARCH_30, it's only
required to be saved on 31. Otherwise this looks pretty odd.
> + sprs.dawr0 = mfspr(SPRN_DAWR0);
> + sprs.dawrx0 = mfspr(SPRN_DAWRX0);
> + }
>
> srr1 = isa300_idle_stop_mayloss(psscr); /* go idle */
>
> @@ -710,6 +716,10 @@ static unsigned long power9_idle_stop(unsigned long
> psscr, bool mmu_on)
> mtspr(SPRN_IAMR, sprs.iamr);
> mtspr(SPRN_AMOR, sprs.amor);
> mtspr(SPRN_UAMOR, sprs.uamor);
> + if (cpu_has_feature(CPU_FTR_ARCH_31)) {
> + mtspr(SPRN_DAWR0, sprs.dawr0);
> + mtspr(SPRN_DAWRX0, sprs.dawrx0);
> + }
>
> /*
> * Workaround for POWER9 DD2.0, if we lost resources, the ERAT
^ permalink raw reply
* [powerpc:merge] BUILD SUCCESS d6c13d397d6988ec3e6029cae9e80501364cf9cb
From: kernel test robot @ 2020-07-24 2:03 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git merge
branch HEAD: d6c13d397d6988ec3e6029cae9e80501364cf9cb Automatic merge of 'master', 'next' and 'fixes' (2020-07-22 23:08)
elapsed time: 2204m
configs tested: 74
configs skipped: 1
The following configs have been built successfully.
More configs may be tested in the coming days.
arm defconfig
arm allyesconfig
arm allmodconfig
arm allnoconfig
arm64 allyesconfig
arm64 defconfig
arm64 allmodconfig
arm64 allnoconfig
i386 defconfig
i386 debian-10.3
i386 allnoconfig
i386 allyesconfig
ia64 allmodconfig
ia64 defconfig
ia64 allnoconfig
ia64 allyesconfig
m68k allmodconfig
m68k allnoconfig
m68k sun3_defconfig
m68k defconfig
m68k allyesconfig
nios2 defconfig
nios2 allyesconfig
openrisc defconfig
c6x allyesconfig
c6x allnoconfig
openrisc allyesconfig
nds32 defconfig
nds32 allnoconfig
csky allyesconfig
csky defconfig
alpha defconfig
alpha allyesconfig
xtensa allyesconfig
h8300 allyesconfig
h8300 allmodconfig
xtensa defconfig
arc defconfig
arc allyesconfig
sh allmodconfig
sh allnoconfig
microblaze allnoconfig
mips allyesconfig
mips allnoconfig
mips allmodconfig
parisc allnoconfig
parisc defconfig
parisc allyesconfig
parisc allmodconfig
powerpc defconfig
powerpc allyesconfig
powerpc rhel-kconfig
powerpc allmodconfig
powerpc allnoconfig
riscv allyesconfig
riscv allnoconfig
riscv defconfig
riscv allmodconfig
s390 allyesconfig
s390 allnoconfig
s390 allmodconfig
s390 defconfig
sparc allyesconfig
sparc defconfig
sparc64 defconfig
sparc64 allnoconfig
sparc64 allyesconfig
sparc64 allmodconfig
x86_64 rhel-7.6-kselftests
x86_64 rhel-8.3
x86_64 kexec
x86_64 rhel
x86_64 lkp
x86_64 fedora-25
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* Re: [PATCH 1/2] lockdep: improve current->(hard|soft)irqs_enabled synchronisation with actual irq state
From: kernel test robot @ 2020-07-24 2:19 UTC (permalink / raw)
To: Nicholas Piggin, linux-kernel
Cc: linux-arch, kbuild-all, Peter Zijlstra, Will Deacon,
Nicholas Piggin, Alexey Kardashevskiy, Ingo Molnar, linuxppc-dev
In-Reply-To: <20200723105615.1268126-1-npiggin@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 5221 bytes --]
Hi Nicholas,
I love your patch! Yet something to improve:
[auto build test ERROR on linux/master]
[also build test ERROR on powerpc/next linus/master v5.8-rc6 next-20200723]
[cannot apply to tip/locking/core]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Nicholas-Piggin/lockdep-improve-current-hard-soft-irqs_enabled-synchronisation-with-actual-irq-state/20200723-185938
base: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 9ebcfadb0610322ac537dd7aa5d9cbc2b2894c68
config: nds32-allyesconfig (attached as .config)
compiler: nds32le-linux-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=nds32
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
In file included from include/asm-generic/bitops.h:14,
from ./arch/nds32/include/generated/asm/bitops.h:1,
from include/linux/bitops.h:29,
from include/linux/kernel.h:12,
from include/linux/list.h:9,
from include/linux/rculist.h:10,
from include/linux/pid.h:5,
from include/linux/sched.h:14,
from arch/nds32/kernel/asm-offsets.c:4:
include/linux/spinlock_api_smp.h: In function '__raw_spin_lock_irq':
>> include/linux/irqflags.h:158:31: error: implicit declaration of function 'arch_irqs_disabled'; did you mean 'raw_irqs_disabled'? [-Werror=implicit-function-declaration]
158 | #define raw_irqs_disabled() (arch_irqs_disabled())
| ^~~~~~~~~~~~~~~~~~
include/linux/irqflags.h:174:23: note: in expansion of macro 'raw_irqs_disabled'
174 | bool was_disabled = raw_irqs_disabled(); \
| ^~~~~~~~~~~~~~~~~
include/linux/spinlock_api_smp.h:126:2: note: in expansion of macro 'local_irq_disable'
126 | local_irq_disable();
| ^~~~~~~~~~~~~~~~~
cc1: some warnings being treated as errors
make[2]: *** [scripts/Makefile.build:114: arch/nds32/kernel/asm-offsets.s] Error 1
make[2]: Target '__build' not remade because of errors.
make[1]: *** [Makefile:1175: prepare0] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:185: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.
vim +158 include/linux/irqflags.h
81d68a96a398448 Steven Rostedt 2008-05-12 132
df9ee29270c11db David Howells 2010-10-07 133 /*
df9ee29270c11db David Howells 2010-10-07 134 * Wrap the arch provided IRQ routines to provide appropriate checks.
df9ee29270c11db David Howells 2010-10-07 135 */
df9ee29270c11db David Howells 2010-10-07 136 #define raw_local_irq_disable() arch_local_irq_disable()
df9ee29270c11db David Howells 2010-10-07 137 #define raw_local_irq_enable() arch_local_irq_enable()
df9ee29270c11db David Howells 2010-10-07 138 #define raw_local_irq_save(flags) \
df9ee29270c11db David Howells 2010-10-07 139 do { \
df9ee29270c11db David Howells 2010-10-07 140 typecheck(unsigned long, flags); \
df9ee29270c11db David Howells 2010-10-07 141 flags = arch_local_irq_save(); \
df9ee29270c11db David Howells 2010-10-07 142 } while (0)
df9ee29270c11db David Howells 2010-10-07 143 #define raw_local_irq_restore(flags) \
df9ee29270c11db David Howells 2010-10-07 144 do { \
df9ee29270c11db David Howells 2010-10-07 145 typecheck(unsigned long, flags); \
df9ee29270c11db David Howells 2010-10-07 146 arch_local_irq_restore(flags); \
df9ee29270c11db David Howells 2010-10-07 147 } while (0)
df9ee29270c11db David Howells 2010-10-07 148 #define raw_local_save_flags(flags) \
df9ee29270c11db David Howells 2010-10-07 149 do { \
df9ee29270c11db David Howells 2010-10-07 150 typecheck(unsigned long, flags); \
df9ee29270c11db David Howells 2010-10-07 151 flags = arch_local_save_flags(); \
df9ee29270c11db David Howells 2010-10-07 152 } while (0)
df9ee29270c11db David Howells 2010-10-07 153 #define raw_irqs_disabled_flags(flags) \
df9ee29270c11db David Howells 2010-10-07 154 ({ \
df9ee29270c11db David Howells 2010-10-07 155 typecheck(unsigned long, flags); \
df9ee29270c11db David Howells 2010-10-07 156 arch_irqs_disabled_flags(flags); \
df9ee29270c11db David Howells 2010-10-07 157 })
df9ee29270c11db David Howells 2010-10-07 @158 #define raw_irqs_disabled() (arch_irqs_disabled())
df9ee29270c11db David Howells 2010-10-07 159 #define raw_safe_halt() arch_safe_halt()
de30a2b355ea853 Ingo Molnar 2006-07-03 160
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 57470 bytes --]
^ permalink raw reply
* Re: [PATCH 2/2] lockdep: warn on redundant or incorrect irq state changes
From: kernel test robot @ 2020-07-24 2:57 UTC (permalink / raw)
To: Nicholas Piggin, linux-kernel
Cc: linux-arch, kbuild-all, Peter Zijlstra, Will Deacon,
Nicholas Piggin, Alexey Kardashevskiy, Ingo Molnar, linuxppc-dev
In-Reply-To: <20200723105615.1268126-2-npiggin@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 3086 bytes --]
Hi Nicholas,
I love your patch! Yet something to improve:
[auto build test ERROR on linux/master]
[also build test ERROR on powerpc/next linus/master v5.8-rc6]
[cannot apply to tip/locking/core next-20200723]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Nicholas-Piggin/lockdep-improve-current-hard-soft-irqs_enabled-synchronisation-with-actual-irq-state/20200723-185938
base: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 9ebcfadb0610322ac537dd7aa5d9cbc2b2894c68
config: x86_64-randconfig-a002-20200723 (attached as .config)
compiler: gcc-9 (Debian 9.3.0-14) 9.3.0
reproduce (this is a W=1 build):
# save the attached .config to linux build tree
make W=1 ARCH=x86_64
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
kernel/locking/lockdep.c: In function 'lockdep_init':
>> kernel/locking/lockdep.c:5673:9: error: 'struct task_struct' has no member named 'hardirqs_enabled'
5673 | current->hardirqs_enabled = 1;
| ^~
>> kernel/locking/lockdep.c:5674:9: error: 'struct task_struct' has no member named 'softirqs_enabled'
5674 | current->softirqs_enabled = 1;
| ^~
In file included from kernel/locking/lockdep.c:60:
At top level:
kernel/locking/lockdep_internals.h:64:28: warning: 'LOCKF_USED_IN_IRQ_READ' defined but not used [-Wunused-const-variable=]
64 | static const unsigned long LOCKF_USED_IN_IRQ_READ =
| ^~~~~~~~~~~~~~~~~~~~~~
In file included from kernel/locking/lockdep.c:60:
kernel/locking/lockdep_internals.h:58:28: warning: 'LOCKF_ENABLED_IRQ_READ' defined but not used [-Wunused-const-variable=]
58 | static const unsigned long LOCKF_ENABLED_IRQ_READ =
| ^~~~~~~~~~~~~~~~~~~~~~
In file included from kernel/locking/lockdep.c:60:
kernel/locking/lockdep_internals.h:52:28: warning: 'LOCKF_USED_IN_IRQ' defined but not used [-Wunused-const-variable=]
52 | static const unsigned long LOCKF_USED_IN_IRQ =
| ^~~~~~~~~~~~~~~~~
In file included from kernel/locking/lockdep.c:60:
kernel/locking/lockdep_internals.h:46:28: warning: 'LOCKF_ENABLED_IRQ' defined but not used [-Wunused-const-variable=]
46 | static const unsigned long LOCKF_ENABLED_IRQ =
| ^~~~~~~~~~~~~~~~~
vim +5673 kernel/locking/lockdep.c
5667
5668 printk(" per task-struct memory footprint: %zu bytes\n",
5669 sizeof(((struct task_struct *)NULL)->held_locks));
5670
5671 WARN_ON(irqs_disabled());
5672
> 5673 current->hardirqs_enabled = 1;
> 5674 current->softirqs_enabled = 1;
5675 }
5676
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 38517 bytes --]
^ permalink raw reply
* Re: [v4] powerpc/perf: Initialize power10 PMU registers in cpu setup routine
From: kernel test robot @ 2020-07-24 3:02 UTC (permalink / raw)
To: Athira Rajeev, mpe; +Cc: jniethe5, mikey, maddy, kbuild-all, linuxppc-dev
In-Reply-To: <1595489557-2047-1-git-send-email-atrajeev@linux.vnet.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 7614 bytes --]
Hi Athira,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on powerpc/next]
[also build test ERROR on v5.8-rc6 next-20200723]
[cannot apply to mpe/next scottwood/next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Athira-Rajeev/powerpc-perf-Initialize-power10-PMU-registers-in-cpu-setup-routine/20200723-153537
base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-defconfig (attached as .config)
compiler: powerpc64-linux-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=powerpc
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
arch/powerpc/kernel/cpu_setup_power.S: Assembler messages:
>> arch/powerpc/kernel/cpu_setup_power.S:244: Error: non-constant expression in ".if" statement
>> arch/powerpc/kernel/cpu_setup_power.S:244: Error: non-constant expression in ".if" statement
>> arch/powerpc/kernel/cpu_setup_power.S:243: Error: unsupported relocation against SPRN_MMCR3
vim +244 arch/powerpc/kernel/cpu_setup_power.S
14
15 /* Entry: r3 = crap, r4 = ptr to cputable entry
16 *
17 * Note that we can be called twice for pseudo-PVRs
18 */
19 _GLOBAL(__setup_cpu_power7)
20 mflr r11
21 bl __init_hvmode_206
22 mtlr r11
23 beqlr
24 li r0,0
25 mtspr SPRN_LPID,r0
26 LOAD_REG_IMMEDIATE(r0, PCR_MASK)
27 mtspr SPRN_PCR,r0
28 mfspr r3,SPRN_LPCR
29 li r4,(LPCR_LPES1 >> LPCR_LPES_SH)
30 bl __init_LPCR_ISA206
31 mtlr r11
32 blr
33
34 _GLOBAL(__restore_cpu_power7)
35 mflr r11
36 mfmsr r3
37 rldicl. r0,r3,4,63
38 beqlr
39 li r0,0
40 mtspr SPRN_LPID,r0
41 LOAD_REG_IMMEDIATE(r0, PCR_MASK)
42 mtspr SPRN_PCR,r0
43 mfspr r3,SPRN_LPCR
44 li r4,(LPCR_LPES1 >> LPCR_LPES_SH)
45 bl __init_LPCR_ISA206
46 mtlr r11
47 blr
48
49 _GLOBAL(__setup_cpu_power8)
50 mflr r11
51 bl __init_FSCR
52 bl __init_PMU
53 bl __init_PMU_ISA207
54 bl __init_hvmode_206
55 mtlr r11
56 beqlr
57 li r0,0
58 mtspr SPRN_LPID,r0
59 LOAD_REG_IMMEDIATE(r0, PCR_MASK)
60 mtspr SPRN_PCR,r0
61 mfspr r3,SPRN_LPCR
62 ori r3, r3, LPCR_PECEDH
63 li r4,0 /* LPES = 0 */
64 bl __init_LPCR_ISA206
65 bl __init_HFSCR
66 bl __init_PMU_HV
67 bl __init_PMU_HV_ISA207
68 mtlr r11
69 blr
70
71 _GLOBAL(__restore_cpu_power8)
72 mflr r11
73 bl __init_FSCR
74 bl __init_PMU
75 bl __init_PMU_ISA207
76 mfmsr r3
77 rldicl. r0,r3,4,63
78 mtlr r11
79 beqlr
80 li r0,0
81 mtspr SPRN_LPID,r0
82 LOAD_REG_IMMEDIATE(r0, PCR_MASK)
83 mtspr SPRN_PCR,r0
84 mfspr r3,SPRN_LPCR
85 ori r3, r3, LPCR_PECEDH
86 li r4,0 /* LPES = 0 */
87 bl __init_LPCR_ISA206
88 bl __init_HFSCR
89 bl __init_PMU_HV
90 bl __init_PMU_HV_ISA207
91 mtlr r11
92 blr
93
94 _GLOBAL(__setup_cpu_power10)
95 mflr r11
96 bl __init_FSCR_power10
97 bl __init_PMU
98 bl __init_PMU_ISA31
99 b 1f
100
101 _GLOBAL(__setup_cpu_power9)
102 mflr r11
103 bl __init_FSCR
104 bl __init_PMU
105 1: bl __init_hvmode_206
106 mtlr r11
107 beqlr
108 li r0,0
109 mtspr SPRN_PSSCR,r0
110 mtspr SPRN_LPID,r0
111 mtspr SPRN_PID,r0
112 LOAD_REG_IMMEDIATE(r0, PCR_MASK)
113 mtspr SPRN_PCR,r0
114 mfspr r3,SPRN_LPCR
115 LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
116 or r3, r3, r4
117 LOAD_REG_IMMEDIATE(r4, LPCR_UPRT | LPCR_HR)
118 andc r3, r3, r4
119 li r4,0 /* LPES = 0 */
120 bl __init_LPCR_ISA300
121 bl __init_HFSCR
122 bl __init_PMU_HV
123 mtlr r11
124 blr
125
126 _GLOBAL(__restore_cpu_power10)
127 mflr r11
128 bl __init_FSCR_power10
129 bl __init_PMU
130 bl __init_PMU_ISA31
131 b 1f
132
133 _GLOBAL(__restore_cpu_power9)
134 mflr r11
135 bl __init_FSCR
136 bl __init_PMU
137 1: mfmsr r3
138 rldicl. r0,r3,4,63
139 mtlr r11
140 beqlr
141 li r0,0
142 mtspr SPRN_PSSCR,r0
143 mtspr SPRN_LPID,r0
144 mtspr SPRN_PID,r0
145 LOAD_REG_IMMEDIATE(r0, PCR_MASK)
146 mtspr SPRN_PCR,r0
147 mfspr r3,SPRN_LPCR
148 LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
149 or r3, r3, r4
150 LOAD_REG_IMMEDIATE(r4, LPCR_UPRT | LPCR_HR)
151 andc r3, r3, r4
152 li r4,0 /* LPES = 0 */
153 bl __init_LPCR_ISA300
154 bl __init_HFSCR
155 bl __init_PMU_HV
156 mtlr r11
157 blr
158
159 __init_hvmode_206:
160 /* Disable CPU_FTR_HVMODE and exit if MSR:HV is not set */
161 mfmsr r3
162 rldicl. r0,r3,4,63
163 bnelr
164 ld r5,CPU_SPEC_FEATURES(r4)
165 LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE | CPU_FTR_P9_TM_HV_ASSIST)
166 andc r5,r5,r6
167 std r5,CPU_SPEC_FEATURES(r4)
168 blr
169
170 __init_LPCR_ISA206:
171 /* Setup a sane LPCR:
172 * Called with initial LPCR in R3 and desired LPES 2-bit value in R4
173 *
174 * LPES = 0b01 (HSRR0/1 used for 0x500)
175 * PECE = 0b111
176 * DPFD = 4
177 * HDICE = 0
178 * VC = 0b100 (VPM0=1, VPM1=0, ISL=0)
179 * VRMASD = 0b10000 (L=1, LP=00)
180 *
181 * Other bits untouched for now
182 */
183 li r5,0x10
184 rldimi r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5
185
186 /* POWER9 has no VRMASD */
187 __init_LPCR_ISA300:
188 rldimi r3,r4, LPCR_LPES_SH, 64-LPCR_LPES_SH-2
189 ori r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
190 li r5,4
191 rldimi r3,r5, LPCR_DPFD_SH, 64-LPCR_DPFD_SH-3
192 clrrdi r3,r3,1 /* clear HDICE */
193 li r5,4
194 rldimi r3,r5, LPCR_VC_SH, 0
195 mtspr SPRN_LPCR,r3
196 isync
197 blr
198
199 __init_FSCR_power10:
200 mfspr r3, SPRN_FSCR
201 ori r3, r3, FSCR_PREFIX
202 mtspr SPRN_FSCR, r3
203 // fall through
204
205 __init_FSCR:
206 mfspr r3,SPRN_FSCR
207 ori r3,r3,FSCR_TAR|FSCR_EBB
208 mtspr SPRN_FSCR,r3
209 blr
210
211 __init_HFSCR:
212 mfspr r3,SPRN_HFSCR
213 ori r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_BHRB|HFSCR_PM|\
214 HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB|HFSCR_MSGP
215 mtspr SPRN_HFSCR,r3
216 blr
217
218 __init_PMU_HV:
219 li r5,0
220 mtspr SPRN_MMCRC,r5
221 blr
222
223 __init_PMU_HV_ISA207:
224 li r5,0
225 mtspr SPRN_MMCRH,r5
226 blr
227
228 __init_PMU:
229 li r5,0
230 mtspr SPRN_MMCRA,r5
231 mtspr SPRN_MMCR0,r5
232 mtspr SPRN_MMCR1,r5
233 mtspr SPRN_MMCR2,r5
234 blr
235
236 __init_PMU_ISA207:
237 li r5,0
238 mtspr SPRN_MMCRS,r5
239 blr
240
241 __init_PMU_ISA31:
242 li r5,0
> 243 mtspr SPRN_MMCR3,r5
> 244 LOAD_REG_IMMEDIATE(r5, MMCRA_BHRB_DISABLE)
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 26258 bytes --]
^ permalink raw reply
* Re: [PATCH v5 7/7] KVM: PPC: Book3S HV: rework secure mem slot dropping
From: Bharata B Rao @ 2020-07-24 3:03 UTC (permalink / raw)
To: Ram Pai
Cc: ldufour, cclaudio, kvm-ppc, sathnaga, aneesh.kumar, sukadev,
linuxppc-dev, bauerman, david
In-Reply-To: <1595534844-16188-8-git-send-email-linuxram@us.ibm.com>
On Thu, Jul 23, 2020 at 01:07:24PM -0700, Ram Pai wrote:
> From: Laurent Dufour <ldufour@linux.ibm.com>
>
> 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 <linuxram@us.ibm.com>
> Cc: Bharata B Rao <bharata@linux.ibm.com>
> Cc: Paul Mackerras <paulus@ozlabs.org>
> Signed-off-by: Ram Pai <linuxram@us.ibm.com>
> [modified the changelog description]
> Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
> ---
> arch/powerpc/kvm/book3s_hv_uvmem.c | 54 ++++++++++++++++++++++++++------------
> 1 file changed, 37 insertions(+), 17 deletions(-)
>
> diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
> index c772e92..daffa6e 100644
> --- a/arch/powerpc/kvm/book3s_hv_uvmem.c
> +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
> @@ -632,35 +632,55 @@ 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;
> + }
There is a potential issue with the boundary condition check here
which I discussed with Laurent yesterday. Guess he hasn't gotten around
to look at it yet.
Regards,
Bharata.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox