Skip to contentSkip to conversation

KVM: s390: Implement KVM_PRE_FAULT_MEMORY

PATCH Superseded Claudio Imbrenda 2 participants 7 messages May 21

Subsystems (5)
Documentation KVM Kselftest s390 +1 more subsystems

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore

Claudio Imbrenda

author maintainer
#0 lore raw

v2 cover KVM: s390: Implement KVM_PRE_FAULT_MEMORY

Implement KVM_PRE_FAULT_MEMORY on s390, and update documentation and selftests accordingly.

Faulted-in pages will be marked as accessed, unlike x86, otherwise they will trigger a minor fault when accessed. Avoiding such faults is one of the points of KVM_PRE_FAULT_MEMORY.

CCing x86 people due to changes in the documentation and the selftests

v1->v2:
* Add the crste_region3 flag in struct guest_fault to keep track of the page size used to solve a fault.
* Rewrite the s390 version of kvm_arch_vcpu_pre_fault_memory() so it looks and behaves similarly to the x86 version. No more loops, better handling of hugepage mappings, and more correct error handling.
* Remove the assertion vcpu->run->exit_reason == KVM_EXIT_IO from the selftest, as it is redundant and x86-specific.

Claudio Imbrenda (5):
KVM: s390: Track page size in struct guest_fault
KVM: s390: Implement KVM_PRE_FAULT_MEMORY
KVM: s390: Update KVM_PRE_FAULT_MEMORY API documentation
KVM: selftests: Fix pre_fault_memory_test to run on s390
KVM: selftests: Enable pre_fault_memory_test for s390

 Documentation/virt/kvm/api.rst                |  5 ++-
 arch/s390/kvm/Kconfig                         |  1 +
 arch/s390/kvm/dat.h                           |  1 +
 arch/s390/kvm/gmap.c                          |  2 +
 arch/s390/kvm/kvm-s390.c                      | 45 +++++++++++++++++++
 tools/testing/selftests/kvm/Makefile.kvm      |  1 +
 .../selftests/kvm/pre_fault_memory_test.c     |  7 +--
 7 files changed, 54 insertions(+), 8 deletions(-)
Signature · 1 line
2.54.0
author maintainer
#1 lore raw

PATCH v2 1/5 KVM: s390: Track page size in struct guest_fault

Until now, the members of struct guest_fault are always accessed while holding the required locks, and thus the ptep and crstep pointers can be dereferenced safely.

There will be some new cases where callers of kvm_s390_faultin_gfn() need to know the size of the page used to solve the fault, at which point no locks are held anymore, and dereferencing the crstep field is not possible.

Introduce a new crste_region3 flag for struct guest_fault to indicate whether the crstep used to solve the fault was a region 3 entry with FC=1 (large pud).

This allows to disambiguate all three possible scenarios:
* If ptep is not NULL, the fault was solved with a pte.
* If ptep is NULL and crste_region3 is 0, a segment entry with FC=1 (large pmd) was used.
* If ptep is NULL and crste_region3 is 1, a region 3 entry with FC=1 (large pud) was used.

---
 arch/s390/kvm/dat.h  | 1 +
 arch/s390/kvm/gmap.c | 2 ++
 2 files changed, 3 insertions(+)
arch/s390/kvm/dat.h +1 -0
index 8f8278c44879..db09b8fc34d6 100644
@@ -500,6 +500,7 @@ struct guest_fault {
 	bool write_attempt;	/* Write access attempted */
 	bool attempt_pfault;	/* Attempt a pfault first */
 	bool valid;		/* This entry contains valid data */
+	bool crste_region3;     /* Whether crstep referst to a region3 entry */
 	void (*callback)(struct guest_fault *f);
 	void *priv;
 };
arch/s390/kvm/gmap.c +2 -0
index 3c26e35af0ef..6f4143092871 100644
@@ -545,6 +545,7 @@ static int gmap_handle_minor_crste_fault(struct gmap *gmap, struct guest_fault *
 			newcrste.s.fc1.d = 1;
 			newcrste.s.fc1.sd = 1;
 		}
+		f->crste_region3 = is_pud(newcrste);
 		/* In case of races, let the slow path deal with it. */
 		return !gmap_crstep_xchg_atomic(gmap, f->crstep, oldcrste, newcrste, f->gfn);
 	}
@@ -690,6 +691,7 @@ static int _gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, int leve
 			if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val &&
 			    crste_origin_large(oldval) != crste_origin_large(newval))
 				return -EAGAIN;
+			f->crste_region3 = is_pud(newval);
 		} while (!gmap_crstep_xchg_atomic(gmap, f->crstep, oldval, newval, f->gfn));
 		if (f->callback)
 			f->callback(f);
Signature · 1 line
2.54.0
author maintainer
#2 lore raw

PATCH v2 2/5 KVM: s390: Implement KVM_PRE_FAULT_MEMORY

In reply to Claudio Imbrenda

Implement and enable the KVM_PRE_FAULT_MEMORY ioctl for s390.

Faulted-in pages will be marked as accessed, unlike x86, otherwise they will trigger a minor fault when accessed. Avoiding such faults is one of the points of KVM_PRE_FAULT_MEMORY.

---
 arch/s390/kvm/Kconfig    |  1 +
 arch/s390/kvm/kvm-s390.c | 45 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)
arch/s390/kvm/Kconfig +1 -0
index 5b835bc6a194..8d3ee17a1bcb 100644
@@ -30,6 +30,7 @@ config KVM
 	select KVM_VFIO
 	select VIRT_XFER_TO_GUEST_WORK
 	select KVM_MMU_LOCKLESS_AGING
+	select KVM_GENERIC_PRE_FAULT_MEMORY
 	help
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work
arch/s390/kvm/kvm-s390.c +45 -0

57 lines not on this page · raw message

Signature · 1 line
2.54.0
author maintainer
#3 lore raw

PATCH v2 3/5 KVM: s390: Update KVM_PRE_FAULT_MEMORY API documentation

In reply to Claudio Imbrenda

Update the API documentation for KVM_PRE_FAULT_MEMORY to account for its s390 implementation.

---
 Documentation/virt/kvm/api.rst | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
Documentation/virt/kvm/api.rst +3 -2
index 52bbbb553ce1..e7998feaa940 100644
@@ -6471,7 +6471,8 @@ Errors:
 
   ========== ===============================================================
   EINVAL     The specified `gpa` and `size` were invalid (e.g. not
-             page aligned, causes an overflow, or size is zero).
+             page aligned, causes an overflow, or size is zero), or the VM
+             is UCONTROL (s390).
   ENOENT     The specified `gpa` is outside defined memslots.
   EINTR      An unmasked signal is pending and no page was processed.
   EFAULT     The parameter address was invalid.
@@ -6494,7 +6495,7 @@ Errors:
 KVM_PRE_FAULT_MEMORY populates KVM's stage-2 page tables used to map memory
 for the current vCPU state.  KVM maps memory as if the vCPU generated a
 stage-2 read page fault, e.g. faults in memory as needed, but doesn't break
-CoW.  However, KVM does not mark any newly created stage-2 PTE as Accessed.
+CoW.  On x86, KVM does not mark any newly created stage-2 PTE as Accessed.
 
 In the case of confidential VM types where there is an initial set up of
 private guest memory before the guest is 'finalized'/measured, this ioctl
Signature · 1 line
2.54.0
author maintainer
#4 lore raw

PATCH v2 4/5 KVM: selftests: Fix pre_fault_memory_test to run on s390

In reply to Claudio Imbrenda

Add a missing #include <ucall_common.h> which is needed and otherwise not included on s390.

Remove the assertion vcpu->run->exit_reason == KVM_EXIT_IO since it is x86-specific and redundant anyway.

---
 tools/testing/selftests/kvm/pre_fault_memory_test.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)
tools/testing/selftests/kvm/pre_fault_memory_test.c +1 -6
index fcb57fd034e6..a0fcae3cb7a8 100644
@@ -11,6 +11,7 @@
 #include <kvm_util.h>
 #include <processor.h>
 #include <pthread.h>
+#include <ucall_common.h>
 
 /* Arbitrarily chosen values */
 #define TEST_SIZE		(SZ_2M + PAGE_SIZE)
@@ -167,7 +168,6 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private)
 		.type = vm_type,
 	};
 	struct kvm_vcpu *vcpu;
-	struct kvm_run *run;
 	struct kvm_vm *vm;
 	struct ucall uc;
 
@@ -193,11 +193,6 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private)
 	vcpu_args_set(vcpu, 1, gva);
 	vcpu_run(vcpu);
 
-	run = vcpu->run;
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Wanted KVM_EXIT_IO, got exit reason: %u (%s)",
-		    run->exit_reason, exit_reason_str(run->exit_reason));
-
 	switch (get_ucall(vcpu, &uc)) {
 	case UCALL_ABORT:
 		REPORT_GUEST_ASSERT(uc);
Signature · 1 line
2.54.0
author maintainer
#6 lore raw

PATCH v2 5/5 KVM: selftests: Enable pre_fault_memory_test for s390

In reply to Claudio Imbrenda

Enable the pre_fault_memory_test to run on s390.

---
 tools/testing/selftests/kvm/Makefile.kvm | 1 +
 1 file changed, 1 insertion(+)
tools/testing/selftests/kvm/Makefile.kvm +1 -0
index 9118a5a51b89..fff939db89cd 100644
@@ -210,6 +210,7 @@ TEST_GEN_PROGS_s390 += s390/keyop
 TEST_GEN_PROGS_s390 += rseq_test
 TEST_GEN_PROGS_s390 += s390/irq_routing
 TEST_GEN_PROGS_s390 += mmu_stress_test
+TEST_GEN_PROGS_s390 += pre_fault_memory_test
 
 TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON)
 TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test
Signature · 1 line
2.54.0