* [PATCH v4 15/32] KVM: PPC: Book3S HV: Refactor radix page fault handler
From: Paul Mackerras @ 2018-10-04 11:55 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
The radix page fault handler accounts for all cases, including just
needing to insert a pte. This breaks it up into separate functions for
the two main cases; setting rc and inserting a pte.
This allows us to make the setting of rc and inserting of a pte
generic for any pgtable, not specific to the one for this guest.
[paulus@ozlabs.org - reduced diffs from previous code]
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_64_mmu_radix.c | 210 +++++++++++++++++++--------------
1 file changed, 123 insertions(+), 87 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index f2976f4..47f2b18 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -400,8 +400,9 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
*/
#define PTE_BITS_MUST_MATCH (~(_PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED))
-static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
- unsigned int level, unsigned long mmu_seq)
+static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
+ unsigned long gpa, unsigned int level,
+ unsigned long mmu_seq)
{
pgd_t *pgd;
pud_t *pud, *new_pud = NULL;
@@ -410,7 +411,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
int ret;
/* Traverse the guest's 2nd-level tree, allocate new levels needed */
- pgd = kvm->arch.pgtable + pgd_index(gpa);
+ pgd = pgtable + pgd_index(gpa);
pud = NULL;
if (pgd_present(*pgd))
pud = pud_offset(pgd, gpa);
@@ -565,95 +566,49 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
return ret;
}
-int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
- unsigned long ea, unsigned long dsisr)
+static bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
+ bool writing, unsigned long gpa)
+{
+ unsigned long pgflags;
+ unsigned int shift;
+ pte_t *ptep;
+
+ /*
+ * Need to set an R or C bit in the 2nd-level tables;
+ * since we are just helping out the hardware here,
+ * it is sufficient to do what the hardware does.
+ */
+ pgflags = _PAGE_ACCESSED;
+ if (writing)
+ pgflags |= _PAGE_DIRTY;
+ /*
+ * We are walking the secondary (partition-scoped) page table here.
+ * We can do this without disabling irq because the Linux MM
+ * subsystem doesn't do THP splits and collapses on this tree.
+ */
+ ptep = __find_linux_pte(pgtable, gpa, NULL, &shift);
+ if (ptep && pte_present(*ptep) && (!writing || pte_write(*ptep))) {
+ kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, gpa, shift);
+ return true;
+ }
+ return false;
+}
+
+static int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
+ unsigned long gpa,
+ struct kvm_memory_slot *memslot,
+ bool writing, bool kvm_ro,
+ pte_t *inserted_pte, unsigned int *levelp)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long mmu_seq;
- unsigned long gpa, gfn, hva;
- struct kvm_memory_slot *memslot;
struct page *page = NULL;
- long ret;
- bool writing;
+ unsigned long mmu_seq;
+ unsigned long hva, gfn = gpa >> PAGE_SHIFT;
bool upgrade_write = false;
bool *upgrade_p = &upgrade_write;
pte_t pte, *ptep;
- unsigned long pgflags;
unsigned int shift, level;
-
- /* Check for unusual errors */
- if (dsisr & DSISR_UNSUPP_MMU) {
- pr_err("KVM: Got unsupported MMU fault\n");
- return -EFAULT;
- }
- if (dsisr & DSISR_BADACCESS) {
- /* Reflect to the guest as DSI */
- pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
- kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
- return RESUME_GUEST;
- }
-
- /* Translate the logical address and get the page */
- gpa = vcpu->arch.fault_gpa & ~0xfffUL;
- gpa &= ~0xF000000000000000ul;
- gfn = gpa >> PAGE_SHIFT;
- if (!(dsisr & DSISR_PRTABLE_FAULT))
- gpa |= ea & 0xfff;
- memslot = gfn_to_memslot(kvm, gfn);
-
- /* No memslot means it's an emulated MMIO region */
- if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
- if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
- DSISR_SET_RC)) {
- /*
- * Bad address in guest page table tree, or other
- * unusual error - reflect it to the guest as DSI.
- */
- kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
- return RESUME_GUEST;
- }
- return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
- dsisr & DSISR_ISSTORE);
- }
-
- writing = (dsisr & DSISR_ISSTORE) != 0;
- if (memslot->flags & KVM_MEM_READONLY) {
- if (writing) {
- /* give the guest a DSI */
- dsisr = DSISR_ISSTORE | DSISR_PROTFAULT;
- kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
- return RESUME_GUEST;
- }
- upgrade_p = NULL;
- }
-
- if (dsisr & DSISR_SET_RC) {
- /*
- * Need to set an R or C bit in the 2nd-level tables;
- * since we are just helping out the hardware here,
- * it is sufficient to do what the hardware does.
- */
- pgflags = _PAGE_ACCESSED;
- if (writing)
- pgflags |= _PAGE_DIRTY;
- /*
- * We are walking the secondary page table here. We can do this
- * without disabling irq.
- */
- spin_lock(&kvm->mmu_lock);
- ptep = __find_linux_pte(kvm->arch.pgtable,
- gpa, NULL, &shift);
- if (ptep && pte_present(*ptep) &&
- (!writing || pte_write(*ptep))) {
- kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
- gpa, shift);
- dsisr &= ~DSISR_SET_RC;
- }
- spin_unlock(&kvm->mmu_lock);
- if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
- DSISR_PROTFAULT | DSISR_SET_RC)))
- return RESUME_GUEST;
- }
+ int ret;
/* used to check for invalidations in progress */
mmu_seq = kvm->mmu_notifier_seq;
@@ -666,7 +621,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
* is that the page is writable.
*/
hva = gfn_to_hva_memslot(memslot, gfn);
- if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
+ if (!kvm_ro && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
upgrade_write = true;
} else {
unsigned long pfn;
@@ -724,7 +679,12 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
}
/* Allocate space in the tree and write the PTE */
- ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+ ret = kvmppc_create_pte(kvm, kvm->arch.pgtable, pte, gpa, level,
+ mmu_seq);
+ if (inserted_pte)
+ *inserted_pte = pte;
+ if (levelp)
+ *levelp = level;
if (page) {
if (!ret && (pte_val(pte) & _PAGE_WRITE))
@@ -732,6 +692,82 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
put_page(page);
}
+ return ret;
+}
+
+int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned long ea, unsigned long dsisr)
+{
+ struct kvm *kvm = vcpu->kvm;
+ unsigned long gpa, gfn;
+ struct kvm_memory_slot *memslot;
+ long ret;
+ bool writing = !!(dsisr & DSISR_ISSTORE);
+ bool kvm_ro = false;
+
+ /* Check for unusual errors */
+ if (dsisr & DSISR_UNSUPP_MMU) {
+ pr_err("KVM: Got unsupported MMU fault\n");
+ return -EFAULT;
+ }
+ if (dsisr & DSISR_BADACCESS) {
+ /* Reflect to the guest as DSI */
+ pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
+ kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+ return RESUME_GUEST;
+ }
+
+ /* Translate the logical address */
+ gpa = vcpu->arch.fault_gpa & ~0xfffUL;
+ gpa &= ~0xF000000000000000ul;
+ gfn = gpa >> PAGE_SHIFT;
+ if (!(dsisr & DSISR_PRTABLE_FAULT))
+ gpa |= ea & 0xfff;
+
+ /* Get the corresponding memslot */
+ memslot = gfn_to_memslot(kvm, gfn);
+
+ /* No memslot means it's an emulated MMIO region */
+ if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+ if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
+ DSISR_SET_RC)) {
+ /*
+ * Bad address in guest page table tree, or other
+ * unusual error - reflect it to the guest as DSI.
+ */
+ kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+ return RESUME_GUEST;
+ }
+ return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, writing);
+ }
+
+ if (memslot->flags & KVM_MEM_READONLY) {
+ if (writing) {
+ /* give the guest a DSI */
+ kvmppc_core_queue_data_storage(vcpu, ea, DSISR_ISSTORE |
+ DSISR_PROTFAULT);
+ return RESUME_GUEST;
+ }
+ kvm_ro = true;
+ }
+
+ /* Failed to set the reference/change bits */
+ if (dsisr & DSISR_SET_RC) {
+ spin_lock(&kvm->mmu_lock);
+ if (kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable,
+ writing, gpa))
+ dsisr &= ~DSISR_SET_RC;
+ spin_unlock(&kvm->mmu_lock);
+
+ if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
+ DSISR_PROTFAULT | DSISR_SET_RC)))
+ return RESUME_GUEST;
+ }
+
+ /* Try to insert a pte */
+ ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot, writing,
+ kvm_ro, NULL, NULL);
+
if (ret == 0 || ret == -EAGAIN)
ret = RESUME_GUEST;
return ret;
--
2.7.4
^ permalink raw reply related
* [PATCH v4 16/32] KVM: PPC: Book3S HV: Use kvmppc_unmap_pte() in kvm_unmap_radix()
From: Paul Mackerras @ 2018-10-04 11:55 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
kvmppc_unmap_pte() does a sequence of operations that are open-coded in
kvm_unmap_radix(). This extends kvmppc_unmap_pte() a little so that it
can be used by kvm_unmap_radix(), and makes kvm_unmap_radix() call it.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_64_mmu_radix.c | 33 +++++++++++++--------------------
1 file changed, 13 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 47f2b18..bd06a95 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -240,19 +240,22 @@ static void kvmppc_pmd_free(pmd_t *pmdp)
}
static void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
- unsigned long gpa, unsigned int shift)
+ unsigned long gpa, unsigned int shift,
+ struct kvm_memory_slot *memslot)
{
- unsigned long page_size = 1ul << shift;
unsigned long old;
old = kvmppc_radix_update_pte(kvm, pte, ~0UL, 0, gpa, shift);
kvmppc_radix_tlbie_page(kvm, gpa, shift);
if (old & _PAGE_DIRTY) {
unsigned long gfn = gpa >> PAGE_SHIFT;
- struct kvm_memory_slot *memslot;
+ unsigned long page_size = PAGE_SIZE;
- memslot = gfn_to_memslot(kvm, gfn);
+ if (shift)
+ page_size = 1ul << shift;
+ if (!memslot)
+ memslot = gfn_to_memslot(kvm, gfn);
if (memslot && memslot->dirty_bitmap)
kvmppc_update_dirty_map(memslot, gfn, page_size);
}
@@ -282,7 +285,7 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full)
WARN_ON_ONCE(1);
kvmppc_unmap_pte(kvm, p,
pte_pfn(*p) << PAGE_SHIFT,
- PAGE_SHIFT);
+ PAGE_SHIFT, NULL);
}
}
@@ -304,7 +307,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full)
WARN_ON_ONCE(1);
kvmppc_unmap_pte(kvm, (pte_t *)p,
pte_pfn(*(pte_t *)p) << PAGE_SHIFT,
- PMD_SHIFT);
+ PMD_SHIFT, NULL);
}
} else {
pte_t *pte;
@@ -468,7 +471,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
goto out_unlock;
}
/* Valid 1GB page here already, remove it */
- kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT);
+ kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT, NULL);
}
if (level == 2) {
if (!pud_none(*pud)) {
@@ -517,7 +520,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
goto out_unlock;
}
/* Valid 2MB page here already, remove it */
- kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT);
+ kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT, NULL);
}
if (level == 1) {
if (!pmd_none(*pmd)) {
@@ -780,20 +783,10 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
pte_t *ptep;
unsigned long gpa = gfn << PAGE_SHIFT;
unsigned int shift;
- unsigned long old;
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
- if (ptep && pte_present(*ptep)) {
- old = kvmppc_radix_update_pte(kvm, ptep, ~0UL, 0,
- gpa, shift);
- kvmppc_radix_tlbie_page(kvm, gpa, shift);
- if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) {
- unsigned long psize = PAGE_SIZE;
- if (shift)
- psize = 1ul << shift;
- kvmppc_update_dirty_map(memslot, gfn, psize);
- }
- }
+ if (ptep && pte_present(*ptep))
+ kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot);
return 0;
}
--
2.7.4
^ permalink raw reply related
* [PATCH v4 17/32] KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization
From: Paul Mackerras @ 2018-10-04 11:55 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
This starts the process of adding the code to support nested HV-style
virtualization. It defines a new H_SET_PARTITION_TABLE hypercall which
a nested hypervisor can use to set the base address and size of a
partition table in its memory (analogous to the PTCR register).
On the host (level 0 hypervisor) side, the H_SET_PARTITION_TABLE
hypercall from the guest is handled by code that saves the virtual
PTCR value for the guest.
This also adds code for creating and destroying nested guests and for
reading the partition table entry for a nested guest from L1 memory.
Each nested guest has its own shadow LPID value, different in general
from the LPID value used by the nested hypervisor to refer to it. The
shadow LPID value is allocated at nested guest creation time.
Nested hypervisor functionality is only available for a radix guest,
which therefore means a radix host on a POWER9 (or later) processor.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/hvcall.h | 5 +
arch/powerpc/include/asm/kvm_book3s.h | 10 +-
arch/powerpc/include/asm/kvm_book3s_64.h | 33 ++++
arch/powerpc/include/asm/kvm_book3s_asm.h | 3 +
arch/powerpc/include/asm/kvm_host.h | 5 +
arch/powerpc/kvm/Makefile | 3 +-
arch/powerpc/kvm/book3s_hv.c | 27 ++-
arch/powerpc/kvm/book3s_hv_nested.c | 298 ++++++++++++++++++++++++++++++
8 files changed, 377 insertions(+), 7 deletions(-)
create mode 100644 arch/powerpc/kvm/book3s_hv_nested.c
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index a0b17f9..c95c651 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -322,6 +322,11 @@
#define H_GET_24X7_DATA 0xF07C
#define H_GET_PERF_COUNTER_INFO 0xF080
+/* Platform-specific hcalls used for nested HV KVM */
+#define H_SET_PARTITION_TABLE 0xF800
+#define H_ENTER_NESTED 0xF804
+#define H_TLB_INVALIDATE 0xF808
+
/* Values for 2nd argument to H_SET_MODE */
#define H_SET_MODE_RESOURCE_SET_CIABR 1
#define H_SET_MODE_RESOURCE_SET_DAWR 2
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 91c9779..43f212e 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -274,6 +274,13 @@ static inline void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu) {}
static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {}
#endif
+long kvmhv_nested_init(void);
+void kvmhv_nested_exit(void);
+void kvmhv_vm_nested_init(struct kvm *kvm);
+long kvmhv_set_partition_table(struct kvm_vcpu *vcpu);
+void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1);
+void kvmhv_release_all_nested(struct kvm *kvm);
+
void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
extern int kvm_irq_bypass;
@@ -387,9 +394,6 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu);
/* TO = 31 for unconditional trap */
#define INS_TW 0x7fe00008
-/* LPIDs we support with this build -- runtime limit may be lower */
-#define KVMPPC_NR_LPIDS (LPID_RSVD + 1)
-
#define SPLIT_HACK_MASK 0xff000000
#define SPLIT_HACK_OFFS 0xfb000000
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 5c0e2d9..6d67b6a 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -23,6 +23,39 @@
#include <linux/string.h>
#include <asm/bitops.h>
#include <asm/book3s/64/mmu-hash.h>
+#include <asm/cpu_has_feature.h>
+
+#ifdef CONFIG_PPC_PSERIES
+static inline bool kvmhv_on_pseries(void)
+{
+ return !cpu_has_feature(CPU_FTR_HVMODE);
+}
+#else
+static inline bool kvmhv_on_pseries(void)
+{
+ return false;
+}
+#endif
+
+/*
+ * Structure for a nested guest, that is, for a guest that is managed by
+ * one of our guests.
+ */
+struct kvm_nested_guest {
+ struct kvm *l1_host; /* L1 VM that owns this nested guest */
+ int l1_lpid; /* lpid L1 guest thinks this guest is */
+ int shadow_lpid; /* real lpid of this nested guest */
+ pgd_t *shadow_pgtable; /* our page table for this guest */
+ u64 l1_gr_to_hr; /* L1's addr of part'n-scoped table */
+ u64 process_table; /* process table entry for this guest */
+ long refcnt; /* number of pointers to this struct */
+ struct mutex tlb_lock; /* serialize page faults and tlbies */
+ struct kvm_nested_guest *next;
+};
+
+struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
+ bool create);
+void kvmhv_put_nested(struct kvm_nested_guest *gp);
/* Power architecture requires HPT is at least 256kiB, at most 64TiB */
#define PPC_MIN_HPT_ORDER 18
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index d978fdf..eb3ba63 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -25,6 +25,9 @@
#define XICS_MFRR 0xc
#define XICS_IPI 2 /* interrupt source # for IPIs */
+/* LPIDs we support with this build -- runtime limit may be lower */
+#define KVMPPC_NR_LPIDS (LPID_RSVD + 1)
+
/* Maximum number of threads per physical core */
#define MAX_SMT_THREADS 8
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c9cc42f..c35d4f2 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -46,6 +46,7 @@
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
#include <asm/kvm_book3s_asm.h> /* for MAX_SMT_THREADS */
#define KVM_MAX_VCPU_ID (MAX_SMT_THREADS * KVM_MAX_VCORES)
+#define KVM_MAX_NESTED_GUESTS KVMPPC_NR_LPIDS
#else
#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS
@@ -287,6 +288,7 @@ struct kvm_arch {
u8 radix;
u8 fwnmi_enabled;
bool threads_indep;
+ bool nested_enable;
pgd_t *pgtable;
u64 process_table;
struct dentry *debugfs_dir;
@@ -312,6 +314,9 @@ struct kvm_arch {
#endif
struct kvmppc_ops *kvm_ops;
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ u64 l1_ptcr;
+ int max_nested_lpid;
+ struct kvm_nested_guest *nested_guests[KVM_MAX_NESTED_GUESTS];
/* This array can grow quite large, keep it at the end */
struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
#endif
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index f872c04..e814f40 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -75,7 +75,8 @@ kvm-hv-y += \
book3s_hv.o \
book3s_hv_interrupts.o \
book3s_64_mmu_hv.o \
- book3s_64_mmu_radix.o
+ book3s_64_mmu_radix.o \
+ book3s_hv_nested.o
kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
book3s_hv_tm.o
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ca0e4f4..ca2529e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -934,6 +934,19 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
if (ret == H_TOO_HARD)
return RESUME_HOST;
break;
+
+ case H_SET_PARTITION_TABLE:
+ ret = H_FUNCTION;
+ if (vcpu->kvm->arch.nested_enable)
+ ret = kvmhv_set_partition_table(vcpu);
+ break;
+ case H_ENTER_NESTED:
+ ret = H_FUNCTION;
+ break;
+ case H_TLB_INVALIDATE:
+ ret = H_FUNCTION;
+ break;
+
default:
return RESUME_HOST;
}
@@ -4149,8 +4162,7 @@ void kvmppc_setup_partition_table(struct kvm *kvm)
__pa(kvm->arch.pgtable) | RADIX_PGD_INDEX_SIZE;
dw1 = PATB_GR | kvm->arch.process_table;
}
-
- mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1);
+ kvmhv_set_ptbl_entry(kvm->arch.lpid, dw0, dw1);
}
/*
@@ -4366,6 +4378,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
kvmppc_alloc_host_rm_ops();
+ kvmhv_vm_nested_init(kvm);
+
/*
* Since we don't flush the TLB when tearing down a VM,
* and this lpid might have previously been used,
@@ -4509,8 +4523,10 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
/* Perform global invalidation and return lpid to the pool */
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (kvm->arch.nested_enable)
+ kvmhv_release_all_nested(kvm);
kvm->arch.process_table = 0;
- kvmppc_setup_partition_table(kvm);
+ kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
}
kvmppc_free_lpid(kvm->arch.lpid);
@@ -4981,6 +4997,10 @@ static int kvmppc_book3s_init_hv(void)
if (r < 0)
return -ENODEV;
+ r = kvmhv_nested_init();
+ if (r)
+ return r;
+
r = kvm_init_subcore_bitmap();
if (r)
return r;
@@ -5039,6 +5059,7 @@ static void kvmppc_book3s_exit_hv(void)
if (kvmppc_radix_possible())
kvmppc_radix_exit();
kvmppc_hv_ops = NULL;
+ kvmhv_nested_exit();
}
module_init(kvmppc_book3s_init_hv);
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
new file mode 100644
index 0000000..b5e4611
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2018
+ * Authors Suraj Jitindar Singh <sjitindarsingh@gmail.com>
+ * Paul Mackerras <paulus@ozlabs.org>
+ *
+ * Description: KVM functions specific to running nested KVM-HV guests
+ * on Book3S processors (specifically POWER9 and later).
+ */
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+
+static struct patb_entry *pseries_partition_tb;
+
+static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp);
+
+long kvmhv_nested_init(void)
+{
+ long int ptb_order;
+ unsigned long ptcr;
+ long rc;
+
+ if (!kvmhv_on_pseries())
+ return 0;
+ if (!radix_enabled())
+ return -ENODEV;
+
+ /* find log base 2 of KVMPPC_NR_LPIDS, rounding up */
+ ptb_order = __ilog2(KVMPPC_NR_LPIDS - 1) + 1;
+ if (ptb_order < 8)
+ ptb_order = 8;
+ pseries_partition_tb = kmalloc(sizeof(struct patb_entry) << ptb_order,
+ GFP_KERNEL);
+ if (!pseries_partition_tb) {
+ pr_err("kvm-hv: failed to allocated nested partition table\n");
+ return -ENOMEM;
+ }
+
+ ptcr = __pa(pseries_partition_tb) | (ptb_order - 8);
+ rc = plpar_hcall_norets(H_SET_PARTITION_TABLE, ptcr);
+ if (rc != H_SUCCESS) {
+ pr_err("kvm-hv: Parent hypervisor does not support nesting (rc=%ld)\n",
+ rc);
+ kfree(pseries_partition_tb);
+ pseries_partition_tb = NULL;
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+void kvmhv_nested_exit(void)
+{
+ /*
+ * N.B. the kvmhv_on_pseries() test is there because it enables
+ * the compiler to remove the call to plpar_hcall_norets()
+ * when CONFIG_PPC_PSERIES=n.
+ */
+ if (kvmhv_on_pseries() && pseries_partition_tb) {
+ plpar_hcall_norets(H_SET_PARTITION_TABLE, 0);
+ kfree(pseries_partition_tb);
+ pseries_partition_tb = NULL;
+ }
+}
+
+void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1)
+{
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ mmu_partition_table_set_entry(lpid, dw0, dw1);
+ } else {
+ pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
+ pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+ }
+}
+
+static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)
+{
+ unsigned long dw0;
+
+ dw0 = PATB_HR | radix__get_tree_size() |
+ __pa(gp->shadow_pgtable) | RADIX_PGD_INDEX_SIZE;
+ kvmhv_set_ptbl_entry(gp->shadow_lpid, dw0, gp->process_table);
+}
+
+void kvmhv_vm_nested_init(struct kvm *kvm)
+{
+ kvm->arch.max_nested_lpid = -1;
+}
+
+/*
+ * Handle the H_SET_PARTITION_TABLE hcall.
+ * r4 = guest real address of partition table + log_2(size) - 12
+ * (formatted as for the PTCR).
+ */
+long kvmhv_set_partition_table(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ unsigned long ptcr = kvmppc_get_gpr(vcpu, 4);
+ int srcu_idx;
+ long ret = H_SUCCESS;
+
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+ /*
+ * Limit the partition table to 4096 entries (because that's what
+ * hardware supports), and check the base address.
+ */
+ if ((ptcr & PRTS_MASK) > 12 - 8 ||
+ !kvm_is_visible_gfn(vcpu->kvm, (ptcr & PRTB_MASK) >> PAGE_SHIFT))
+ ret = H_PARAMETER;
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+ if (ret == H_SUCCESS)
+ kvm->arch.l1_ptcr = ptcr;
+ return ret;
+}
+
+/*
+ * Reload the partition table entry for a guest.
+ * Caller must hold gp->tlb_lock.
+ */
+static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
+{
+ int ret;
+ struct patb_entry ptbl_entry;
+ unsigned long ptbl_addr;
+ struct kvm *kvm = gp->l1_host;
+
+ ret = -EFAULT;
+ ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4);
+ if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8)))
+ ret = kvm_read_guest(kvm, ptbl_addr,
+ &ptbl_entry, sizeof(ptbl_entry));
+ if (ret) {
+ gp->l1_gr_to_hr = 0;
+ gp->process_table = 0;
+ } else {
+ gp->l1_gr_to_hr = be64_to_cpu(ptbl_entry.patb0);
+ gp->process_table = be64_to_cpu(ptbl_entry.patb1);
+ }
+ kvmhv_set_nested_ptbl(gp);
+}
+
+struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
+{
+ struct kvm_nested_guest *gp;
+ long shadow_lpid;
+
+ gp = kzalloc(sizeof(*gp), GFP_KERNEL);
+ if (!gp)
+ return NULL;
+ gp->l1_host = kvm;
+ gp->l1_lpid = lpid;
+ mutex_init(&gp->tlb_lock);
+ gp->shadow_pgtable = pgd_alloc(kvm->mm);
+ if (!gp->shadow_pgtable)
+ goto out_free;
+ shadow_lpid = kvmppc_alloc_lpid();
+ if (shadow_lpid < 0)
+ goto out_free2;
+ gp->shadow_lpid = shadow_lpid;
+
+ return gp;
+
+ out_free2:
+ pgd_free(kvm->mm, gp->shadow_pgtable);
+ out_free:
+ kfree(gp);
+ return NULL;
+}
+
+/*
+ * Free up any resources allocated for a nested guest.
+ */
+static void kvmhv_release_nested(struct kvm_nested_guest *gp)
+{
+ kvmhv_set_ptbl_entry(gp->shadow_lpid, 0, 0);
+ kvmppc_free_lpid(gp->shadow_lpid);
+ if (gp->shadow_pgtable)
+ pgd_free(gp->l1_host->mm, gp->shadow_pgtable);
+ kfree(gp);
+}
+
+static void kvmhv_remove_nested(struct kvm_nested_guest *gp)
+{
+ struct kvm *kvm = gp->l1_host;
+ int lpid = gp->l1_lpid;
+ long ref;
+
+ spin_lock(&kvm->mmu_lock);
+ if (gp == kvm->arch.nested_guests[lpid]) {
+ kvm->arch.nested_guests[lpid] = NULL;
+ if (lpid == kvm->arch.max_nested_lpid) {
+ while (--lpid >= 0 && !kvm->arch.nested_guests[lpid])
+ ;
+ kvm->arch.max_nested_lpid = lpid;
+ }
+ --gp->refcnt;
+ }
+ ref = gp->refcnt;
+ spin_unlock(&kvm->mmu_lock);
+ if (ref == 0)
+ kvmhv_release_nested(gp);
+}
+
+/*
+ * Free up all nested resources allocated for this guest.
+ */
+void kvmhv_release_all_nested(struct kvm *kvm)
+{
+ int i;
+ struct kvm_nested_guest *gp;
+ struct kvm_nested_guest *freelist = NULL;
+
+ spin_lock(&kvm->mmu_lock);
+ for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
+ gp = kvm->arch.nested_guests[i];
+ if (!gp)
+ continue;
+ kvm->arch.nested_guests[i] = NULL;
+ if (--gp->refcnt == 0) {
+ gp->next = freelist;
+ freelist = gp;
+ }
+ }
+ kvm->arch.max_nested_lpid = -1;
+ spin_unlock(&kvm->mmu_lock);
+ while ((gp = freelist) != NULL) {
+ freelist = gp->next;
+ kvmhv_release_nested(gp);
+ }
+}
+
+/* caller must hold gp->tlb_lock */
+void kvmhv_flush_nested(struct kvm_nested_guest *gp)
+{
+ kvmhv_update_ptbl_cache(gp);
+ if (gp->l1_gr_to_hr == 0)
+ kvmhv_remove_nested(gp);
+}
+
+struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
+ bool create)
+{
+ struct kvm_nested_guest *gp, *newgp;
+
+ if (l1_lpid >= KVM_MAX_NESTED_GUESTS ||
+ l1_lpid >= (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 12 - 4)))
+ return NULL;
+
+ spin_lock(&kvm->mmu_lock);
+ gp = kvm->arch.nested_guests[l1_lpid];
+ if (gp)
+ ++gp->refcnt;
+ spin_unlock(&kvm->mmu_lock);
+
+ if (gp || !create)
+ return gp;
+
+ newgp = kvmhv_alloc_nested(kvm, l1_lpid);
+ if (!newgp)
+ return NULL;
+ spin_lock(&kvm->mmu_lock);
+ if (kvm->arch.nested_guests[l1_lpid]) {
+ /* someone else beat us to it */
+ gp = kvm->arch.nested_guests[l1_lpid];
+ } else {
+ kvm->arch.nested_guests[l1_lpid] = newgp;
+ ++newgp->refcnt;
+ gp = newgp;
+ newgp = NULL;
+ if (l1_lpid > kvm->arch.max_nested_lpid)
+ kvm->arch.max_nested_lpid = l1_lpid;
+ }
+ ++gp->refcnt;
+ spin_unlock(&kvm->mmu_lock);
+
+ if (newgp)
+ kvmhv_release_nested(newgp);
+
+ return gp;
+}
+
+void kvmhv_put_nested(struct kvm_nested_guest *gp)
+{
+ struct kvm *kvm = gp->l1_host;
+ long ref;
+
+ spin_lock(&kvm->mmu_lock);
+ ref = --gp->refcnt;
+ spin_unlock(&kvm->mmu_lock);
+ if (ref == 0)
+ kvmhv_release_nested(gp);
+}
--
2.7.4
^ permalink raw reply related
* [PATCH v4 18/32] KVM: PPC: Book3S HV: Nested guest entry via hypercall
From: Paul Mackerras @ 2018-10-04 11:55 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
This adds a new hypercall, H_ENTER_NESTED, which is used by a nested
hypervisor to enter one of its nested guests. The hypercall supplies
register values in two structs. Those values are copied by the level 0
(L0) hypervisor (the one which is running in hypervisor mode) into the
vcpu struct of the L1 guest, and then the guest is run until an
interrupt or error occurs which needs to be reported to L1 via the
hypercall return value.
Currently this assumes that the L0 and L1 hypervisors are the same
endianness, and the structs passed as arguments are in native
endianness. If they are of different endianness, the version number
check will fail and the hcall will be rejected.
Nested hypervisors do not support indep_threads_mode=N, so this adds
code to print a warning message if the administrator has set
indep_threads_mode=N, and treat it as Y.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/hvcall.h | 36 +++++
arch/powerpc/include/asm/kvm_book3s.h | 7 +
arch/powerpc/include/asm/kvm_host.h | 5 +
arch/powerpc/kernel/asm-offsets.c | 1 +
arch/powerpc/kvm/book3s_hv.c | 214 ++++++++++++++++++++++++-----
arch/powerpc/kvm/book3s_hv_nested.c | 230 ++++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 ++
7 files changed, 471 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index c95c651..45e8789 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -466,6 +466,42 @@ struct h_cpu_char_result {
u64 behaviour;
};
+/* Register state for entering a nested guest with H_ENTER_NESTED */
+struct hv_guest_state {
+ u64 version; /* version of this structure layout */
+ u32 lpid;
+ u32 vcpu_token;
+ /* These registers are hypervisor privileged (at least for writing) */
+ u64 lpcr;
+ u64 pcr;
+ u64 amor;
+ u64 dpdes;
+ u64 hfscr;
+ s64 tb_offset;
+ u64 dawr0;
+ u64 dawrx0;
+ u64 ciabr;
+ u64 hdec_expiry;
+ u64 purr;
+ u64 spurr;
+ u64 ic;
+ u64 vtb;
+ u64 hdar;
+ u64 hdsisr;
+ u64 heir;
+ u64 asdr;
+ /* These are OS privileged but need to be set late in guest entry */
+ u64 srr0;
+ u64 srr1;
+ u64 sprg[4];
+ u64 pidr;
+ u64 cfar;
+ u64 ppr;
+};
+
+/* Latest version of hv_guest_state structure */
+#define HV_GUEST_STATE_VERSION 1
+
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_HVCALL_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 43f212e..093fd70 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -280,6 +280,13 @@ void kvmhv_vm_nested_init(struct kvm *kvm);
long kvmhv_set_partition_table(struct kvm_vcpu *vcpu);
void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1);
void kvmhv_release_all_nested(struct kvm *kvm);
+long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
+int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu,
+ u64 time_limit, unsigned long lpcr);
+void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
+void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
+ struct hv_guest_state *hr);
+long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu);
void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c35d4f2..ceb9f20 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -95,6 +95,7 @@ struct dtl_entry;
struct kvmppc_vcpu_book3s;
struct kvmppc_book3s_shadow_vcpu;
+struct kvm_nested_guest;
struct kvm_vm_stat {
ulong remote_tlb_flush;
@@ -786,6 +787,10 @@ struct kvm_vcpu_arch {
u32 emul_inst;
u32 online;
+
+ /* For support of nested guests */
+ struct kvm_nested_guest *nested;
+ u32 nested_vcpu_id;
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 7c3738d..d0abcbb 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -503,6 +503,7 @@ int main(void)
OFFSET(VCPU_VPA, kvm_vcpu, arch.vpa.pinned_addr);
OFFSET(VCPU_VPA_DIRTY, kvm_vcpu, arch.vpa.dirty);
OFFSET(VCPU_HEIR, kvm_vcpu, arch.emul_inst);
+ OFFSET(VCPU_NESTED, kvm_vcpu, arch.nested);
OFFSET(VCPU_CPU, kvm_vcpu, cpu);
OFFSET(VCPU_THREAD_CPU, kvm_vcpu, arch.thread_cpu);
#endif
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ca2529e..9900fd8 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -942,6 +942,13 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
break;
case H_ENTER_NESTED:
ret = H_FUNCTION;
+ if (!vcpu->kvm->arch.nested_enable)
+ break;
+ ret = kvmhv_enter_nested_guest(vcpu);
+ if (ret == H_INTERRUPT) {
+ kvmppc_set_gpr(vcpu, 3, 0);
+ return -EINTR;
+ }
break;
case H_TLB_INVALIDATE:
ret = H_FUNCTION;
@@ -1272,6 +1279,104 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
return r;
}
+static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
+{
+ int r;
+ int srcu_idx;
+
+ vcpu->stat.sum_exits++;
+
+ /*
+ * This can happen if an interrupt occurs in the last stages
+ * of guest entry or the first stages of guest exit (i.e. after
+ * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV
+ * and before setting it to KVM_GUEST_MODE_HOST_HV).
+ * That can happen due to a bug, or due to a machine check
+ * occurring at just the wrong time.
+ */
+ if (vcpu->arch.shregs.msr & MSR_HV) {
+ pr_emerg("KVM trap in HV mode while nested!\n");
+ pr_emerg("trap=0x%x | pc=0x%lx | msr=0x%llx\n",
+ vcpu->arch.trap, kvmppc_get_pc(vcpu),
+ vcpu->arch.shregs.msr);
+ kvmppc_dump_regs(vcpu);
+ return RESUME_HOST;
+ }
+ switch (vcpu->arch.trap) {
+ /* We're good on these - the host merely wanted to get our attention */
+ case BOOK3S_INTERRUPT_HV_DECREMENTER:
+ vcpu->stat.dec_exits++;
+ r = RESUME_GUEST;
+ break;
+ case BOOK3S_INTERRUPT_EXTERNAL:
+ vcpu->stat.ext_intr_exits++;
+ r = RESUME_HOST;
+ break;
+ case BOOK3S_INTERRUPT_H_DOORBELL:
+ case BOOK3S_INTERRUPT_H_VIRT:
+ vcpu->stat.ext_intr_exits++;
+ r = RESUME_GUEST;
+ break;
+ /* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/
+ case BOOK3S_INTERRUPT_HMI:
+ case BOOK3S_INTERRUPT_PERFMON:
+ case BOOK3S_INTERRUPT_SYSTEM_RESET:
+ r = RESUME_GUEST;
+ break;
+ case BOOK3S_INTERRUPT_MACHINE_CHECK:
+ /* Pass the machine check to the L1 guest */
+ r = RESUME_HOST;
+ /* Print the MCE event to host console. */
+ machine_check_print_event_info(&vcpu->arch.mce_evt, false);
+ break;
+ /*
+ * We get these next two if the guest accesses a page which it thinks
+ * it has mapped but which is not actually present, either because
+ * it is for an emulated I/O device or because the corresonding
+ * host page has been paged out.
+ */
+ case BOOK3S_INTERRUPT_H_DATA_STORAGE:
+ srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ r = kvmhv_nested_page_fault(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+ break;
+ case BOOK3S_INTERRUPT_H_INST_STORAGE:
+ vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
+ vcpu->arch.fault_dsisr = kvmppc_get_msr(vcpu) &
+ DSISR_SRR1_MATCH_64S;
+ if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
+ vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
+ srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ r = kvmhv_nested_page_fault(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+ break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+ /*
+ * This occurs for various TM-related instructions that
+ * we need to emulate on POWER9 DD2.2. We have already
+ * handled the cases where the guest was in real-suspend
+ * mode and was transitioning to transactional state.
+ */
+ r = kvmhv_p9_tm_emulation(vcpu);
+ break;
+#endif
+
+ case BOOK3S_INTERRUPT_HV_RM_HARD:
+ vcpu->arch.trap = 0;
+ r = RESUME_GUEST;
+ if (!xive_enabled())
+ kvmppc_xics_rm_complete(vcpu, 0);
+ break;
+ default:
+ r = RESUME_HOST;
+ break;
+ }
+
+ return r;
+}
+
static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
@@ -3098,7 +3203,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
/*
* Load up hypervisor-mode registers on P9.
*/
-static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit)
+static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
+ unsigned long lpcr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
s64 hdec;
@@ -3155,7 +3261,7 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit)
mtspr(SPRN_AMOR, ~0UL);
- mtspr(SPRN_LPCR, vc->lpcr);
+ mtspr(SPRN_LPCR, lpcr);
isync();
kvmppc_xive_push_vcpu(vcpu);
@@ -3225,7 +3331,8 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit)
* Virtual-mode guest entry for POWER9 and later when the host and
* guest are both using the radix MMU. The LPIDR has already been set.
*/
-int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit)
+int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
+ unsigned long lpcr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
unsigned long host_dscr = mfspr(SPRN_DSCR);
@@ -3289,14 +3396,32 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit)
mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb());
- if (vcpu->arch.doorbell_request) {
- vc->dpdes = 1;
- smp_wmb();
- vcpu->arch.doorbell_request = 0;
+ if (kvmhv_on_pseries()) {
+ /* call our hypervisor to load up HV regs and go */
+ struct hv_guest_state hvregs;
+
+ kvmhv_save_hv_regs(vcpu, &hvregs);
+ hvregs.lpcr = lpcr;
+ vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
+ hvregs.version = HV_GUEST_STATE_VERSION;
+ if (vcpu->arch.nested) {
+ hvregs.lpid = vcpu->arch.nested->shadow_lpid;
+ hvregs.vcpu_token = vcpu->arch.nested_vcpu_id;
+ } else {
+ hvregs.lpid = vcpu->kvm->arch.lpid;
+ hvregs.vcpu_token = vcpu->vcpu_id;
+ }
+ hvregs.hdec_expiry = time_limit;
+ trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs),
+ __pa(&vcpu->arch.regs));
+ kvmhv_restore_hv_return_state(vcpu, &hvregs);
+ vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
+ vcpu->arch.shregs.dar = mfspr(SPRN_DAR);
+ vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);
+ } else {
+ trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr);
}
- trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit);
-
vcpu->arch.slb_max = 0;
dec = mfspr(SPRN_DEC);
tb = mftb();
@@ -3535,6 +3660,11 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
trace_kvmppc_vcore_wakeup(do_sleep, block_ns);
}
+/*
+ * This never fails for a radix guest, as none of the operations it does
+ * for a radix guest can fail or have a way to report failure.
+ * kvmhv_run_single_vcpu() relies on this fact.
+ */
static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu)
{
int r = 0;
@@ -3684,12 +3814,15 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
return vcpu->arch.ret;
}
-static int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
- struct kvm_vcpu *vcpu, u64 time_limit)
+int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
+ struct kvm_vcpu *vcpu, u64 time_limit,
+ unsigned long lpcr)
{
int trap, r, pcpu, pcpu0;
int srcu_idx;
struct kvmppc_vcore *vc;
+ struct kvm_nested_guest *nested = vcpu->arch.nested;
+ unsigned long lpid;
trace_kvmppc_run_vcpu_enter(vcpu);
@@ -3710,16 +3843,8 @@ static int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
vc->runner = vcpu;
/* See if the MMU is ready to go */
- if (!vcpu->kvm->arch.mmu_ready) {
- r = kvmhv_setup_mmu(vcpu);
- if (r) {
- kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
- kvm_run->fail_entry.
- hardware_entry_failure_reason = 0;
- vcpu->arch.ret = r;
- goto out;
- }
- }
+ if (!vcpu->kvm->arch.mmu_ready)
+ kvmhv_setup_mmu(vcpu);
if (need_resched())
cond_resched();
@@ -3741,7 +3866,22 @@ static int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
if (lazy_irq_pending() || need_resched() || !vcpu->kvm->arch.mmu_ready)
goto out;
- kvmppc_core_prepare_to_enter(vcpu);
+ if (!nested) {
+ kvmppc_core_prepare_to_enter(vcpu);
+ if (vcpu->arch.doorbell_request) {
+ vc->dpdes = 1;
+ smp_wmb();
+ vcpu->arch.doorbell_request = 0;
+ }
+ if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
+ &vcpu->arch.pending_exceptions))
+ lpcr |= LPCR_MER;
+ } else if (vcpu->arch.pending_exceptions ||
+ vcpu->arch.doorbell_request ||
+ xive_interrupt_pending(vcpu)) {
+ vcpu->arch.ret = RESUME_HOST;
+ goto out;
+ }
kvmppc_clear_host_core(pcpu);
@@ -3755,7 +3895,10 @@ static int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
vc->vcore_state = VCORE_RUNNING;
trace_kvmppc_run_core(vc, 0);
- mtspr(SPRN_LPID, vc->kvm->arch.lpid);
+ lpid = vc->kvm->arch.lpid;
+ if (nested)
+ lpid = nested->shadow_lpid;
+ mtspr(SPRN_LPID, lpid);
isync();
/* See comment above in kvmppc_run_core() about this */
@@ -3764,7 +3907,7 @@ static int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
pcpu0 &= ~0x3UL;
if (cpumask_test_cpu(pcpu0, &vc->kvm->arch.need_tlb_flush)) {
- radix__local_flush_tlb_lpid_guest(vc->kvm->arch.lpid);
+ radix__local_flush_tlb_lpid_guest(lpid);
/* Clear the bit after the TLB flush */
cpumask_clear_cpu(pcpu0, &vc->kvm->arch.need_tlb_flush);
}
@@ -3776,7 +3919,7 @@ static int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
this_cpu_disable_ftrace();
- trap = kvmhv_p9_guest_entry(vcpu, time_limit);
+ trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr);
vcpu->arch.trap = trap;
this_cpu_enable_ftrace();
@@ -3801,8 +3944,12 @@ static int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
trace_kvm_guest_exit(vcpu);
r = RESUME_GUEST;
- if (trap)
- r = kvmppc_handle_exit_hv(kvm_run, vcpu, current);
+ if (trap) {
+ if (!nested)
+ r = kvmppc_handle_exit_hv(kvm_run, vcpu, current);
+ else
+ r = kvmppc_handle_nested_exit(vcpu);
+ }
vcpu->arch.ret = r;
if (is_kvmppc_resume_guest(r) && vcpu->arch.ceded &&
@@ -3917,7 +4064,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
do {
if (kvm->arch.threads_indep && kvm_is_radix(kvm))
- r = kvmhv_run_single_vcpu(run, vcpu, ~(u64)0);
+ r = kvmhv_run_single_vcpu(run, vcpu, ~(u64)0,
+ vcpu->arch.vcore->lpcr);
else
r = kvmppc_run_vcpu(run, vcpu);
@@ -4467,8 +4615,14 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
* On POWER9, we only need to do this if the "indep_threads_mode"
* module parameter has been set to N.
*/
- if (cpu_has_feature(CPU_FTR_ARCH_300))
- kvm->arch.threads_indep = indep_threads_mode;
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) {
+ pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n");
+ kvm->arch.threads_indep = true;
+ } else {
+ kvm->arch.threads_indep = indep_threads_mode;
+ }
+ }
if (!kvm->arch.threads_indep)
kvm_hv_vm_activated();
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index b5e4611..ade38dc 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -20,6 +20,231 @@ static struct patb_entry *pseries_partition_tb;
static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp);
+void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+ hr->pcr = vc->pcr;
+ hr->dpdes = vc->dpdes;
+ hr->hfscr = vcpu->arch.hfscr;
+ hr->tb_offset = vc->tb_offset;
+ hr->dawr0 = vcpu->arch.dawr;
+ hr->dawrx0 = vcpu->arch.dawrx;
+ hr->ciabr = vcpu->arch.ciabr;
+ hr->purr = vcpu->arch.purr;
+ hr->spurr = vcpu->arch.spurr;
+ hr->ic = vcpu->arch.ic;
+ hr->vtb = vc->vtb;
+ hr->srr0 = vcpu->arch.shregs.srr0;
+ hr->srr1 = vcpu->arch.shregs.srr1;
+ hr->sprg[0] = vcpu->arch.shregs.sprg0;
+ hr->sprg[1] = vcpu->arch.shregs.sprg1;
+ hr->sprg[2] = vcpu->arch.shregs.sprg2;
+ hr->sprg[3] = vcpu->arch.shregs.sprg3;
+ hr->pidr = vcpu->arch.pid;
+ hr->cfar = vcpu->arch.cfar;
+ hr->ppr = vcpu->arch.ppr;
+}
+
+static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
+ struct hv_guest_state *hr)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+ hr->dpdes = vc->dpdes;
+ hr->hfscr = vcpu->arch.hfscr;
+ hr->purr = vcpu->arch.purr;
+ hr->spurr = vcpu->arch.spurr;
+ hr->ic = vcpu->arch.ic;
+ hr->vtb = vc->vtb;
+ hr->srr0 = vcpu->arch.shregs.srr0;
+ hr->srr1 = vcpu->arch.shregs.srr1;
+ hr->sprg[0] = vcpu->arch.shregs.sprg0;
+ hr->sprg[1] = vcpu->arch.shregs.sprg1;
+ hr->sprg[2] = vcpu->arch.shregs.sprg2;
+ hr->sprg[3] = vcpu->arch.shregs.sprg3;
+ hr->pidr = vcpu->arch.pid;
+ hr->cfar = vcpu->arch.cfar;
+ hr->ppr = vcpu->arch.ppr;
+ switch (trap) {
+ case BOOK3S_INTERRUPT_H_DATA_STORAGE:
+ hr->hdar = vcpu->arch.fault_dar;
+ hr->hdsisr = vcpu->arch.fault_dsisr;
+ hr->asdr = vcpu->arch.fault_gpa;
+ break;
+ case BOOK3S_INTERRUPT_H_INST_STORAGE:
+ hr->asdr = vcpu->arch.fault_gpa;
+ break;
+ case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
+ hr->heir = vcpu->arch.emul_inst;
+ break;
+ }
+}
+
+static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+ vc->pcr = hr->pcr;
+ vc->dpdes = hr->dpdes;
+ vcpu->arch.hfscr = hr->hfscr;
+ vcpu->arch.dawr = hr->dawr0;
+ vcpu->arch.dawrx = hr->dawrx0;
+ vcpu->arch.ciabr = hr->ciabr;
+ vcpu->arch.purr = hr->purr;
+ vcpu->arch.spurr = hr->spurr;
+ vcpu->arch.ic = hr->ic;
+ vc->vtb = hr->vtb;
+ vcpu->arch.shregs.srr0 = hr->srr0;
+ vcpu->arch.shregs.srr1 = hr->srr1;
+ vcpu->arch.shregs.sprg0 = hr->sprg[0];
+ vcpu->arch.shregs.sprg1 = hr->sprg[1];
+ vcpu->arch.shregs.sprg2 = hr->sprg[2];
+ vcpu->arch.shregs.sprg3 = hr->sprg[3];
+ vcpu->arch.pid = hr->pidr;
+ vcpu->arch.cfar = hr->cfar;
+ vcpu->arch.ppr = hr->ppr;
+}
+
+void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
+ struct hv_guest_state *hr)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+ vc->dpdes = hr->dpdes;
+ vcpu->arch.hfscr = hr->hfscr;
+ vcpu->arch.purr = hr->purr;
+ vcpu->arch.spurr = hr->spurr;
+ vcpu->arch.ic = hr->ic;
+ vc->vtb = hr->vtb;
+ vcpu->arch.fault_dar = hr->hdar;
+ vcpu->arch.fault_dsisr = hr->hdsisr;
+ vcpu->arch.fault_gpa = hr->asdr;
+ vcpu->arch.emul_inst = hr->heir;
+ vcpu->arch.shregs.srr0 = hr->srr0;
+ vcpu->arch.shregs.srr1 = hr->srr1;
+ vcpu->arch.shregs.sprg0 = hr->sprg[0];
+ vcpu->arch.shregs.sprg1 = hr->sprg[1];
+ vcpu->arch.shregs.sprg2 = hr->sprg[2];
+ vcpu->arch.shregs.sprg3 = hr->sprg[3];
+ vcpu->arch.pid = hr->pidr;
+ vcpu->arch.cfar = hr->cfar;
+ vcpu->arch.ppr = hr->ppr;
+}
+
+long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
+{
+ long int err, r;
+ struct kvm_nested_guest *l2;
+ struct pt_regs l2_regs, saved_l1_regs;
+ struct hv_guest_state l2_hv, saved_l1_hv;
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ u64 hv_ptr, regs_ptr;
+ u64 hdec_exp;
+ s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
+ u64 mask;
+ unsigned long lpcr;
+
+ if (vcpu->kvm->arch.l1_ptcr == 0)
+ return H_NOT_AVAILABLE;
+
+ /* copy parameters in */
+ hv_ptr = kvmppc_get_gpr(vcpu, 4);
+ err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv,
+ sizeof(struct hv_guest_state));
+ if (err)
+ return H_PARAMETER;
+ if (l2_hv.version != HV_GUEST_STATE_VERSION)
+ return H_P2;
+
+ regs_ptr = kvmppc_get_gpr(vcpu, 5);
+ err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
+ sizeof(struct pt_regs));
+ if (err)
+ return H_PARAMETER;
+
+ /* translate lpid */
+ l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true);
+ if (!l2)
+ return H_PARAMETER;
+ if (!l2->l1_gr_to_hr) {
+ mutex_lock(&l2->tlb_lock);
+ kvmhv_update_ptbl_cache(l2);
+ mutex_unlock(&l2->tlb_lock);
+ }
+
+ /* save l1 values of things */
+ vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
+ saved_l1_regs = vcpu->arch.regs;
+ kvmhv_save_hv_regs(vcpu, &saved_l1_hv);
+
+ /* convert TB values/offsets to host (L0) values */
+ hdec_exp = l2_hv.hdec_expiry - vc->tb_offset;
+ vc->tb_offset += l2_hv.tb_offset;
+
+ /* set L1 state to L2 state */
+ vcpu->arch.nested = l2;
+ vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
+ vcpu->arch.regs = l2_regs;
+ vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
+ mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
+ LPCR_LPES | LPCR_MER;
+ lpcr = (vc->lpcr & ~mask) | (l2_hv.lpcr & mask);
+ restore_hv_regs(vcpu, &l2_hv);
+
+ vcpu->arch.ret = RESUME_GUEST;
+ vcpu->arch.trap = 0;
+ do {
+ if (mftb() >= hdec_exp) {
+ vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER;
+ r = RESUME_HOST;
+ break;
+ }
+ r = kvmhv_run_single_vcpu(vcpu->arch.kvm_run, vcpu, hdec_exp,
+ lpcr);
+ } while (is_kvmppc_resume_guest(r));
+
+ /* save L2 state for return */
+ l2_regs = vcpu->arch.regs;
+ l2_regs.msr = vcpu->arch.shregs.msr;
+ delta_purr = vcpu->arch.purr - l2_hv.purr;
+ delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
+ delta_ic = vcpu->arch.ic - l2_hv.ic;
+ delta_vtb = vc->vtb - l2_hv.vtb;
+ save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);
+
+ /* restore L1 state */
+ vcpu->arch.nested = NULL;
+ vcpu->arch.regs = saved_l1_regs;
+ vcpu->arch.shregs.msr = saved_l1_regs.msr & ~MSR_TS_MASK;
+ /* set L1 MSR TS field according to L2 transaction state */
+ if (l2_regs.msr & MSR_TS_MASK)
+ vcpu->arch.shregs.msr |= MSR_TS_S;
+ vc->tb_offset = saved_l1_hv.tb_offset;
+ restore_hv_regs(vcpu, &saved_l1_hv);
+ vcpu->arch.purr += delta_purr;
+ vcpu->arch.spurr += delta_spurr;
+ vcpu->arch.ic += delta_ic;
+ vc->vtb += delta_vtb;
+
+ kvmhv_put_nested(l2);
+
+ /* copy l2_hv_state and regs back to guest */
+ err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
+ sizeof(struct hv_guest_state));
+ if (err)
+ return H_AUTHORITY;
+ err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
+ sizeof(struct pt_regs));
+ if (err)
+ return H_AUTHORITY;
+
+ if (r == -EINTR)
+ return H_INTERRUPT;
+
+ return vcpu->arch.trap;
+}
+
long kvmhv_nested_init(void)
{
long int ptb_order;
@@ -296,3 +521,8 @@ void kvmhv_put_nested(struct kvm_nested_guest *gp)
if (ref == 0)
kvmhv_release_nested(gp);
}
+
+long kvmhv_nested_page_fault(struct kvm_vcpu *vcpu)
+{
+ return RESUME_HOST;
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 83efc13..8da73ea 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1393,6 +1393,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
BEGIN_FTR_SECTION
PPC_MSGSYNC
lwsync
+ /* always exit if we're running a nested guest */
+ ld r0, VCPU_NESTED(r9)
+ cmpdi r0, 0
+ bne guest_exit_cont
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
lbz r0, HSTATE_HOST_IPI(r13)
cmpwi r0, 0
@@ -2199,6 +2203,10 @@ hcall_try_real_mode:
andi. r0,r11,MSR_PR
/* sc 1 from userspace - reflect to guest syscall */
bne sc_1_fast_return
+ /* sc 1 from nested guest - give it to L1 to handle */
+ ld r0, VCPU_NESTED(r9)
+ cmpdi r0, 0
+ bne guest_exit_cont
clrrdi r3,r3,2
cmpldi r3,hcall_real_table_end - hcall_real_table
bge guest_exit_cont
--
2.7.4
^ permalink raw reply related
* [PATCH v4 19/32] KVM: PPC: Book3S HV: Use XICS hypercalls when running as a nested hypervisor
From: Paul Mackerras @ 2018-10-04 11:55 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
This adds code to call the H_IPI and H_EOI hypercalls when we are
running as a nested hypervisor (i.e. without the CPU_FTR_HVMODE cpu
feature) and we would otherwise access the XICS interrupt controller
directly or via an OPAL call.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 7 +++++-
arch/powerpc/kvm/book3s_hv_builtin.c | 44 +++++++++++++++++++++++++++++-------
arch/powerpc/kvm/book3s_hv_rm_xics.c | 8 +++++++
3 files changed, 50 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9900fd8..a7cb310 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -173,6 +173,10 @@ static bool kvmppc_ipi_thread(int cpu)
{
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+ /* If we're a nested hypervisor, fall back to ordinary IPIs for now */
+ if (kvmhv_on_pseries())
+ return false;
+
/* On POWER9 we can use msgsnd to IPI any cpu */
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
msg |= get_hard_smp_processor_id(cpu);
@@ -5165,7 +5169,8 @@ static int kvmppc_book3s_init_hv(void)
* indirectly, via OPAL.
*/
#ifdef CONFIG_SMP
- if (!xive_enabled() && !local_paca->kvm_hstate.xics_phys) {
+ if (!xive_enabled() && !kvmhv_on_pseries() &&
+ !local_paca->kvm_hstate.xics_phys) {
struct device_node *np;
np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index ccfea5b..a71e2fc 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -231,6 +231,15 @@ void kvmhv_rm_send_ipi(int cpu)
void __iomem *xics_phys;
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+ /* For a nested hypervisor, use the XICS via hcall */
+ if (kvmhv_on_pseries()) {
+ unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+ plpar_hcall_raw(H_IPI, retbuf, get_hard_smp_processor_id(cpu),
+ IPI_PRIORITY);
+ return;
+ }
+
/* On POWER9 we can use msgsnd for any destination cpu. */
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
msg |= get_hard_smp_processor_id(cpu);
@@ -460,12 +469,19 @@ static long kvmppc_read_one_intr(bool *again)
return 1;
/* Now read the interrupt from the ICP */
- xics_phys = local_paca->kvm_hstate.xics_phys;
- rc = 0;
- if (!xics_phys)
- rc = opal_int_get_xirr(&xirr, false);
- else
- xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
+ if (kvmhv_on_pseries()) {
+ unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+ rc = plpar_hcall_raw(H_XIRR, retbuf, 0xFF);
+ xirr = cpu_to_be32(retbuf[0]);
+ } else {
+ xics_phys = local_paca->kvm_hstate.xics_phys;
+ rc = 0;
+ if (!xics_phys)
+ rc = opal_int_get_xirr(&xirr, false);
+ else
+ xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
+ }
if (rc < 0)
return 1;
@@ -494,7 +510,13 @@ static long kvmppc_read_one_intr(bool *again)
*/
if (xisr == XICS_IPI) {
rc = 0;
- if (xics_phys) {
+ if (kvmhv_on_pseries()) {
+ unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+ plpar_hcall_raw(H_IPI, retbuf,
+ hard_smp_processor_id(), 0xff);
+ plpar_hcall_raw(H_EOI, retbuf, h_xirr);
+ } else if (xics_phys) {
__raw_rm_writeb(0xff, xics_phys + XICS_MFRR);
__raw_rm_writel(xirr, xics_phys + XICS_XIRR);
} else {
@@ -520,7 +542,13 @@ static long kvmppc_read_one_intr(bool *again)
/* We raced with the host,
* we need to resend that IPI, bummer
*/
- if (xics_phys)
+ if (kvmhv_on_pseries()) {
+ unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+ plpar_hcall_raw(H_IPI, retbuf,
+ hard_smp_processor_id(),
+ IPI_PRIORITY);
+ } else if (xics_phys)
__raw_rm_writeb(IPI_PRIORITY,
xics_phys + XICS_MFRR);
else
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 8b9f356..b3f5786 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -767,6 +767,14 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
void __iomem *xics_phys;
int64_t rc;
+ if (kvmhv_on_pseries()) {
+ unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+ iosync();
+ plpar_hcall_raw(H_EOI, retbuf, hwirq);
+ return;
+ }
+
rc = pnv_opal_pci_msi_eoi(c, hwirq);
if (rc)
--
2.7.4
^ permalink raw reply related
* [PATCH v4 20/32] KVM: PPC: Book3S HV: Handle hypercalls correctly when nested
From: Paul Mackerras @ 2018-10-04 11:55 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
When we are running as a nested hypervisor, we use a hypercall to
enter the guest rather than code in book3s_hv_rmhandlers.S. This means
that the hypercall handlers listed in hcall_real_table never get called.
There are some hypercalls that are handled there and not in
kvmppc_pseries_do_hcall(), which therefore won't get processed for
a nested guest.
To fix this, we add cases to kvmppc_pseries_do_hcall() to handle those
hypercalls, with the following exceptions:
- The HPT hypercalls (H_ENTER, H_REMOVE, etc.) are not handled because
we only support radix mode for nested guests.
- H_CEDE has to be handled specially because the cede logic in
kvmhv_run_single_vcpu assumes that it has been processed by the time
that kvmhv_p9_guest_entry() returns. Therefore we put a special
case for H_CEDE in kvmhv_p9_guest_entry().
For the XICS hypercalls, if real-mode processing is enabled, then the
virtual-mode handlers assume that they are being called only to finish
up the operation. Therefore we turn off the real-mode flag in the XICS
code when running as a nested hypervisor.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/asm-prototypes.h | 4 +++
arch/powerpc/kvm/book3s_hv.c | 43 +++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 ++
arch/powerpc/kvm/book3s_xics.c | 3 ++-
4 files changed, 51 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 5c9b00c..c55ba3b 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -167,4 +167,8 @@ void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu);
int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu);
+long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr);
+long kvmppc_h_set_xdabr(struct kvm_vcpu *vcpu, unsigned long dabr,
+ unsigned long dabrx);
+
#endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a7cb310..134d7c7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -50,6 +50,7 @@
#include <asm/reg.h>
#include <asm/ppc-opcode.h>
#include <asm/asm-prototypes.h>
+#include <asm/archrandom.h>
#include <asm/debug.h>
#include <asm/disassemble.h>
#include <asm/cputable.h>
@@ -915,6 +916,19 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
break;
}
return RESUME_HOST;
+ case H_SET_DABR:
+ ret = kvmppc_h_set_dabr(vcpu, kvmppc_get_gpr(vcpu, 4));
+ break;
+ case H_SET_XDABR:
+ ret = kvmppc_h_set_xdabr(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5));
+ break;
+ case H_GET_TCE:
+ ret = kvmppc_h_get_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
case H_PUT_TCE:
ret = kvmppc_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5),
@@ -938,6 +952,10 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
if (ret == H_TOO_HARD)
return RESUME_HOST;
break;
+ case H_RANDOM:
+ if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4]))
+ ret = H_HARDWARE;
+ break;
case H_SET_PARTITION_TABLE:
ret = H_FUNCTION;
@@ -966,6 +984,24 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
return RESUME_GUEST;
}
+/*
+ * Handle H_CEDE in the nested virtualization case where we haven't
+ * called the real-mode hcall handlers in book3s_hv_rmhandlers.S.
+ * This has to be done early, not in kvmppc_pseries_do_hcall(), so
+ * that the cede logic in kvmppc_run_single_vcpu() works properly.
+ */
+static void kvmppc_nested_cede(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.shregs.msr |= MSR_EE;
+ vcpu->arch.ceded = 1;
+ smp_mb();
+ if (vcpu->arch.prodded) {
+ vcpu->arch.prodded = 0;
+ smp_mb();
+ vcpu->arch.ceded = 0;
+ }
+}
+
static int kvmppc_hcall_impl_hv(unsigned long cmd)
{
switch (cmd) {
@@ -3422,6 +3458,13 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
vcpu->arch.shregs.dar = mfspr(SPRN_DAR);
vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);
+
+ /* H_CEDE has to be handled now, not later */
+ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
+ kvmppc_get_gpr(vcpu, 3) == H_CEDE) {
+ kvmppc_nested_cede(vcpu);
+ trap = 0;
+ }
} else {
trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr);
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 8da73ea..d8b26be 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -2466,6 +2466,7 @@ hcall_real_table:
hcall_real_table_end:
_GLOBAL(kvmppc_h_set_xdabr)
+EXPORT_SYMBOL_GPL(kvmppc_h_set_xdabr)
andi. r0, r5, DABRX_USER | DABRX_KERNEL
beq 6f
li r0, DABRX_USER | DABRX_KERNEL | DABRX_BTI
@@ -2475,6 +2476,7 @@ _GLOBAL(kvmppc_h_set_xdabr)
blr
_GLOBAL(kvmppc_h_set_dabr)
+EXPORT_SYMBOL_GPL(kvmppc_h_set_dabr)
li r5, DABRX_USER | DABRX_KERNEL
3:
BEGIN_FTR_SECTION
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index d9ba1b0..b0b2bfc 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1390,7 +1390,8 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
}
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+ if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+ cpu_has_feature(CPU_FTR_HVMODE)) {
/* Enable real mode support */
xics->real_mode = ENABLE_REALMODE;
xics->real_mode_dbg = DEBUG_REALMODE;
--
2.7.4
^ permalink raw reply related
* [PATCH v4 21/32] KVM: PPC: Book3S HV: Handle page fault for a nested guest
From: Paul Mackerras @ 2018-10-04 11:55 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Consider a normal (L1) guest running under the main hypervisor (L0),
and then a nested guest (L2) running under the L1 guest which is acting
as a nested hypervisor. L0 has page tables to map the address space for
L1 providing the translation from L1 real address -> L0 real address;
L1
|
| (L1 -> L0)
|
----> L0
There are also page tables in L1 used to map the address space for L2
providing the translation from L2 real address -> L1 read address. Since
the hardware can only walk a single level of page table, we need to
maintain in L0 a "shadow_pgtable" for L2 which provides the translation
from L2 real address -> L0 real address. Which looks like;
L2 L2
| |
| (L2 -> L1) |
| |
----> L1 | (L2 -> L0)
| |
| (L1 -> L0) |
| |
----> L0 --------> L0
When a page fault occurs while running a nested (L2) guest we need to
insert a pte into this "shadow_pgtable" for the L2 -> L0 mapping. To
do this we need to:
1. Walk the pgtable in L1 memory to find the L2 -> L1 mapping, and
provide a page fault to L1 if this mapping doesn't exist.
2. Use our L1 -> L0 pgtable to convert this L1 address to an L0 address,
or try to insert a pte for that mapping if it doesn't exist.
3. Now we have a L2 -> L0 mapping, insert this into our shadow_pgtable
Once this mapping exists we can take rc faults when hardware is unable
to automatically set the reference and change bits in the pte. On these
we need to:
1. Check the rc bits on the L2 -> L1 pte match, and otherwise reflect
the fault down to L1.
2. Set the rc bits in the L1 -> L0 pte which corresponds to the same
host page.
3. Set the rc bits in the L2 -> L0 pte.
As we reuse a large number of functions in book3s_64_mmu_radix.c for
this we also needed to refactor a number of these functions to take
an lpid parameter so that the correct lpid is used for tlb invalidations.
The functionality however has remained the same.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
.../powerpc/include/asm/book3s/64/tlbflush-radix.h | 1 +
arch/powerpc/include/asm/kvm_book3s.h | 17 ++
arch/powerpc/include/asm/kvm_book3s_64.h | 4 +
arch/powerpc/include/asm/kvm_host.h | 2 +
arch/powerpc/kvm/book3s_64_mmu_radix.c | 194 ++++++------
arch/powerpc/kvm/book3s_hv_nested.c | 332 ++++++++++++++++++++-
arch/powerpc/mm/tlb-radix.c | 9 +
7 files changed, 473 insertions(+), 86 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 1154a6d..671316f 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -53,6 +53,7 @@ extern void radix__flush_tlb_lpid_page(unsigned int lpid,
unsigned long addr,
unsigned long page_size);
extern void radix__flush_pwc_lpid(unsigned int lpid);
+extern void radix__flush_tlb_lpid(unsigned int lpid);
extern void radix__local_flush_tlb_lpid(unsigned int lpid);
extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid);
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 093fd70..63f7ccf 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -188,17 +188,34 @@ extern int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hc);
extern int kvmppc_book3s_radix_page_fault(struct kvm_run *run,
struct kvm_vcpu *vcpu,
unsigned long ea, unsigned long dsisr);
+extern int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
+ struct kvmppc_pte *gpte, u64 root,
+ u64 *pte_ret_p);
extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_pte *gpte, u64 table,
int table_index, u64 *pte_ret_p);
extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_pte *gpte, bool data, bool iswrite);
+extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
+ bool writing, unsigned long gpa,
+ unsigned int lpid);
+extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
+ unsigned long gpa,
+ struct kvm_memory_slot *memslot,
+ bool writing, bool kvm_ro,
+ pte_t *inserted_pte, unsigned int *levelp);
extern int kvmppc_init_vm_radix(struct kvm *kvm);
extern void kvmppc_free_radix(struct kvm *kvm);
+extern void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd,
+ unsigned int lpid);
extern int kvmppc_radix_init(void);
extern void kvmppc_radix_exit(void);
extern int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long gfn);
+extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
+ unsigned long gpa, unsigned int shift,
+ struct kvm_memory_slot *memslot,
+ unsigned int lpid);
extern int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long gfn);
extern int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 6d67b6a..5496152 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -549,6 +549,10 @@ static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
+ unsigned long gpa, unsigned int level,
+ unsigned long mmu_seq, unsigned int lpid);
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index ceb9f20..fac6f63 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -367,7 +367,9 @@ struct kvmppc_pte {
bool may_write : 1;
bool may_execute : 1;
unsigned long wimg;
+ unsigned long rc;
u8 page_size; /* MMU_PAGE_xxx */
+ u8 page_shift;
};
struct kvmppc_mmu {
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index bd06a95..c4b1a9e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -29,43 +29,16 @@
*/
static int p9_supported_radix_bits[4] = { 5, 9, 9, 13 };
-/*
- * Used to walk a partition or process table radix tree in guest memory
- * Note: We exploit the fact that a partition table and a process
- * table have the same layout, a partition-scoped page table and a
- * process-scoped page table have the same layout, and the 2nd
- * doubleword of a partition table entry has the same layout as
- * the PTCR register.
- */
-int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
- struct kvmppc_pte *gpte, u64 table,
- int table_index, u64 *pte_ret_p)
+int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
+ struct kvmppc_pte *gpte, u64 root,
+ u64 *pte_ret_p)
{
struct kvm *kvm = vcpu->kvm;
int ret, level, ps;
- unsigned long ptbl, root;
- unsigned long rts, bits, offset;
- unsigned long size, index;
- struct prtb_entry entry;
+ unsigned long rts, bits, offset, index;
u64 pte, base, gpa;
__be64 rpte;
- if ((table & PRTS_MASK) > 24)
- return -EINVAL;
- size = 1ul << ((table & PRTS_MASK) + 12);
-
- /* Is the table big enough to contain this entry? */
- if ((table_index * sizeof(entry)) >= size)
- return -EINVAL;
-
- /* Read the table to find the root of the radix tree */
- ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry));
- ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry));
- if (ret)
- return ret;
-
- /* Root is stored in the first double word */
- root = be64_to_cpu(entry.prtb0);
rts = ((root & RTS1_MASK) >> (RTS1_SHIFT - 3)) |
((root & RTS2_MASK) >> RTS2_SHIFT);
bits = root & RPDS_MASK;
@@ -79,6 +52,7 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
/* Walk each level of the radix tree */
for (level = 3; level >= 0; --level) {
+ u64 addr;
/* Check a valid size */
if (level && bits != p9_supported_radix_bits[level])
return -EINVAL;
@@ -90,10 +64,13 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
if (base & ((1UL << (bits + 3)) - 1))
return -EINVAL;
/* Read the entry from guest memory */
- ret = kvm_read_guest(kvm, base + (index * sizeof(rpte)),
- &rpte, sizeof(rpte));
- if (ret)
+ addr = base + (index * sizeof(rpte));
+ ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte));
+ if (ret) {
+ if (pte_ret_p)
+ *pte_ret_p = addr;
return ret;
+ }
pte = __be64_to_cpu(rpte);
if (!(pte & _PAGE_PRESENT))
return -ENOENT;
@@ -119,6 +96,7 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
if (offset == mmu_psize_defs[ps].shift)
break;
gpte->page_size = ps;
+ gpte->page_shift = offset;
gpte->eaddr = eaddr;
gpte->raddr = gpa;
@@ -128,12 +106,51 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
gpte->may_write = !!(pte & _PAGE_WRITE);
gpte->may_execute = !!(pte & _PAGE_EXEC);
+ gpte->rc = pte & (_PAGE_ACCESSED | _PAGE_DIRTY);
+
if (pte_ret_p)
*pte_ret_p = pte;
return 0;
}
+/*
+ * Used to walk a partition or process table radix tree in guest memory
+ * Note: We exploit the fact that a partition table and a process
+ * table have the same layout, a partition-scoped page table and a
+ * process-scoped page table have the same layout, and the 2nd
+ * doubleword of a partition table entry has the same layout as
+ * the PTCR register.
+ */
+int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
+ struct kvmppc_pte *gpte, u64 table,
+ int table_index, u64 *pte_ret_p)
+{
+ struct kvm *kvm = vcpu->kvm;
+ int ret;
+ unsigned long size, ptbl, root;
+ struct prtb_entry entry;
+
+ if ((table & PRTS_MASK) > 24)
+ return -EINVAL;
+ size = 1ul << ((table & PRTS_MASK) + 12);
+
+ /* Is the table big enough to contain this entry? */
+ if ((table_index * sizeof(entry)) >= size)
+ return -EINVAL;
+
+ /* Read the table to find the root of the radix tree */
+ ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry));
+ ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry));
+ if (ret)
+ return ret;
+
+ /* Root is stored in the first double word */
+ root = be64_to_cpu(entry.prtb0);
+
+ return kvmppc_mmu_walk_radix_tree(vcpu, eaddr, gpte, root, pte_ret_p);
+}
+
int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_pte *gpte, bool data, bool iswrite)
{
@@ -181,7 +198,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
}
static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
- unsigned int pshift)
+ unsigned int pshift, unsigned int lpid)
{
unsigned long psize = PAGE_SIZE;
@@ -189,12 +206,12 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
psize = 1UL << pshift;
addr &= ~(psize - 1);
- radix__flush_tlb_lpid_page(kvm->arch.lpid, addr, psize);
+ radix__flush_tlb_lpid_page(lpid, addr, psize);
}
-static void kvmppc_radix_flush_pwc(struct kvm *kvm)
+static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
{
- radix__flush_pwc_lpid(kvm->arch.lpid);
+ radix__flush_pwc_lpid(lpid);
}
static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
@@ -239,16 +256,17 @@ static void kvmppc_pmd_free(pmd_t *pmdp)
kmem_cache_free(kvm_pmd_cache, pmdp);
}
-static void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
- unsigned long gpa, unsigned int shift,
- struct kvm_memory_slot *memslot)
+void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
+ unsigned long gpa, unsigned int shift,
+ struct kvm_memory_slot *memslot,
+ unsigned int lpid)
{
unsigned long old;
old = kvmppc_radix_update_pte(kvm, pte, ~0UL, 0, gpa, shift);
- kvmppc_radix_tlbie_page(kvm, gpa, shift);
- if (old & _PAGE_DIRTY) {
+ kvmppc_radix_tlbie_page(kvm, gpa, shift, lpid);
+ if ((old & _PAGE_DIRTY) && (lpid == kvm->arch.lpid)) {
unsigned long gfn = gpa >> PAGE_SHIFT;
unsigned long page_size = PAGE_SIZE;
@@ -271,7 +289,8 @@ static void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
* and emit a warning if encountered, but there may already be data
* corruption due to the unexpected mappings.
*/
-static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full)
+static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
+ unsigned int lpid)
{
if (full) {
memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE);
@@ -285,14 +304,15 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full)
WARN_ON_ONCE(1);
kvmppc_unmap_pte(kvm, p,
pte_pfn(*p) << PAGE_SHIFT,
- PAGE_SHIFT, NULL);
+ PAGE_SHIFT, NULL, lpid);
}
}
kvmppc_pte_free(pte);
}
-static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full)
+static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
+ unsigned int lpid)
{
unsigned long im;
pmd_t *p = pmd;
@@ -307,20 +327,21 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full)
WARN_ON_ONCE(1);
kvmppc_unmap_pte(kvm, (pte_t *)p,
pte_pfn(*(pte_t *)p) << PAGE_SHIFT,
- PMD_SHIFT, NULL);
+ PMD_SHIFT, NULL, lpid);
}
} else {
pte_t *pte;
pte = pte_offset_map(p, 0);
- kvmppc_unmap_free_pte(kvm, pte, full);
+ kvmppc_unmap_free_pte(kvm, pte, full, lpid);
pmd_clear(p);
}
}
kvmppc_pmd_free(pmd);
}
-static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud)
+static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
+ unsigned int lpid)
{
unsigned long iu;
pud_t *p = pud;
@@ -334,36 +355,40 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud)
pmd_t *pmd;
pmd = pmd_offset(p, 0);
- kvmppc_unmap_free_pmd(kvm, pmd, true);
+ kvmppc_unmap_free_pmd(kvm, pmd, true, lpid);
pud_clear(p);
}
}
pud_free(kvm->mm, pud);
}
-void kvmppc_free_radix(struct kvm *kvm)
+void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, unsigned int lpid)
{
unsigned long ig;
- pgd_t *pgd;
- if (!kvm->arch.pgtable)
- return;
- pgd = kvm->arch.pgtable;
for (ig = 0; ig < PTRS_PER_PGD; ++ig, ++pgd) {
pud_t *pud;
if (!pgd_present(*pgd))
continue;
pud = pud_offset(pgd, 0);
- kvmppc_unmap_free_pud(kvm, pud);
+ kvmppc_unmap_free_pud(kvm, pud, lpid);
pgd_clear(pgd);
}
- pgd_free(kvm->mm, kvm->arch.pgtable);
- kvm->arch.pgtable = NULL;
+}
+
+void kvmppc_free_radix(struct kvm *kvm)
+{
+ if (kvm->arch.pgtable) {
+ kvmppc_free_pgtable_radix(kvm, kvm->arch.pgtable,
+ kvm->arch.lpid);
+ pgd_free(kvm->mm, kvm->arch.pgtable);
+ kvm->arch.pgtable = NULL;
+ }
}
static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
- unsigned long gpa)
+ unsigned long gpa, unsigned int lpid)
{
pte_t *pte = pte_offset_kernel(pmd, 0);
@@ -373,13 +398,13 @@ static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
* flushing the PWC again.
*/
pmd_clear(pmd);
- kvmppc_radix_flush_pwc(kvm);
+ kvmppc_radix_flush_pwc(kvm, lpid);
- kvmppc_unmap_free_pte(kvm, pte, false);
+ kvmppc_unmap_free_pte(kvm, pte, false, lpid);
}
static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
- unsigned long gpa)
+ unsigned long gpa, unsigned int lpid)
{
pmd_t *pmd = pmd_offset(pud, 0);
@@ -389,9 +414,9 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
* so can be freed without flushing the PWC again.
*/
pud_clear(pud);
- kvmppc_radix_flush_pwc(kvm);
+ kvmppc_radix_flush_pwc(kvm, lpid);
- kvmppc_unmap_free_pmd(kvm, pmd, false);
+ kvmppc_unmap_free_pmd(kvm, pmd, false, lpid);
}
/*
@@ -403,9 +428,9 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
*/
#define PTE_BITS_MUST_MATCH (~(_PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED))
-static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
- unsigned long gpa, unsigned int level,
- unsigned long mmu_seq)
+int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
+ unsigned long gpa, unsigned int level,
+ unsigned long mmu_seq, unsigned int lpid)
{
pgd_t *pgd;
pud_t *pud, *new_pud = NULL;
@@ -471,7 +496,8 @@ static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
goto out_unlock;
}
/* Valid 1GB page here already, remove it */
- kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT, NULL);
+ kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT, NULL,
+ lpid);
}
if (level == 2) {
if (!pud_none(*pud)) {
@@ -480,7 +506,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
* install a large page, so remove and free the page
* table page.
*/
- kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa);
+ kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa, lpid);
}
kvmppc_radix_set_pte_at(kvm, gpa, (pte_t *)pud, pte);
ret = 0;
@@ -506,7 +532,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
WARN_ON_ONCE((pmd_val(*pmd) ^ pte_val(pte)) &
PTE_BITS_MUST_MATCH);
kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
- 0, pte_val(pte), lgpa, PMD_SHIFT);
+ 0, pte_val(pte), lgpa, PMD_SHIFT);
ret = 0;
goto out_unlock;
}
@@ -520,7 +546,8 @@ static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
goto out_unlock;
}
/* Valid 2MB page here already, remove it */
- kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT, NULL);
+ kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT, NULL,
+ lpid);
}
if (level == 1) {
if (!pmd_none(*pmd)) {
@@ -529,7 +556,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
* install a large page, so remove and free the page
* table page.
*/
- kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa);
+ kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa, lpid);
}
kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte);
ret = 0;
@@ -569,8 +596,8 @@ static int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
return ret;
}
-static bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
- bool writing, unsigned long gpa)
+bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable, bool writing,
+ unsigned long gpa, unsigned int lpid)
{
unsigned long pgflags;
unsigned int shift;
@@ -597,11 +624,11 @@ static bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
return false;
}
-static int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
- unsigned long gpa,
- struct kvm_memory_slot *memslot,
- bool writing, bool kvm_ro,
- pte_t *inserted_pte, unsigned int *levelp)
+int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
+ unsigned long gpa,
+ struct kvm_memory_slot *memslot,
+ bool writing, bool kvm_ro,
+ pte_t *inserted_pte, unsigned int *levelp)
{
struct kvm *kvm = vcpu->kvm;
struct page *page = NULL;
@@ -683,7 +710,7 @@ static int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
/* Allocate space in the tree and write the PTE */
ret = kvmppc_create_pte(kvm, kvm->arch.pgtable, pte, gpa, level,
- mmu_seq);
+ mmu_seq, kvm->arch.lpid);
if (inserted_pte)
*inserted_pte = pte;
if (levelp)
@@ -758,7 +785,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
if (dsisr & DSISR_SET_RC) {
spin_lock(&kvm->mmu_lock);
if (kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable,
- writing, gpa))
+ writing, gpa, kvm->arch.lpid))
dsisr &= ~DSISR_SET_RC;
spin_unlock(&kvm->mmu_lock);
@@ -786,7 +813,8 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep))
- kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot);
+ kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
+ kvm->arch.lpid);
return 0;
}
@@ -841,7 +869,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
ret = 1 << (shift - PAGE_SHIFT);
kvmppc_radix_update_pte(kvm, ptep, _PAGE_DIRTY, 0,
gpa, shift);
- kvmppc_radix_tlbie_page(kvm, gpa, shift);
+ kvmppc_radix_tlbie_page(kvm, gpa, shift, kvm->arch.lpid);
}
return ret;
}
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index ade38dc..9c04242 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -12,9 +12,12 @@
#include <linux/kvm_host.h>
#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
#include <asm/mmu.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
+#include <asm/pte-walk.h>
+#include <asm/reg.h>
static struct patb_entry *pseries_partition_tb;
@@ -403,10 +406,20 @@ struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
*/
static void kvmhv_release_nested(struct kvm_nested_guest *gp)
{
+ struct kvm *kvm = gp->l1_host;
+
+ if (gp->shadow_pgtable) {
+ /*
+ * No vcpu is using this struct and no call to
+ * kvmhv_get_nested can find this struct,
+ * so we don't need to hold kvm->mmu_lock.
+ */
+ kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
+ gp->shadow_lpid);
+ pgd_free(kvm->mm, gp->shadow_pgtable);
+ }
kvmhv_set_ptbl_entry(gp->shadow_lpid, 0, 0);
kvmppc_free_lpid(gp->shadow_lpid);
- if (gp->shadow_pgtable)
- pgd_free(gp->l1_host->mm, gp->shadow_pgtable);
kfree(gp);
}
@@ -463,6 +476,12 @@ void kvmhv_release_all_nested(struct kvm *kvm)
/* caller must hold gp->tlb_lock */
void kvmhv_flush_nested(struct kvm_nested_guest *gp)
{
+ struct kvm *kvm = gp->l1_host;
+
+ spin_lock(&kvm->mmu_lock);
+ kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable, gp->shadow_lpid);
+ spin_unlock(&kvm->mmu_lock);
+ radix__flush_tlb_lpid(gp->shadow_lpid);
kvmhv_update_ptbl_cache(gp);
if (gp->l1_gr_to_hr == 0)
kvmhv_remove_nested(gp);
@@ -522,7 +541,314 @@ void kvmhv_put_nested(struct kvm_nested_guest *gp)
kvmhv_release_nested(gp);
}
-long kvmhv_nested_page_fault(struct kvm_vcpu *vcpu)
+static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu,
+ struct kvm_nested_guest *gp,
+ long gpa, int *shift_ret)
+{
+ struct kvm *kvm = vcpu->kvm;
+ bool ret = false;
+ pte_t *ptep;
+ int shift;
+
+ spin_lock(&kvm->mmu_lock);
+ ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
+ if (!shift)
+ shift = PAGE_SHIFT;
+ if (ptep && pte_present(*ptep)) {
+ kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
+ ret = true;
+ }
+ spin_unlock(&kvm->mmu_lock);
+
+ if (shift_ret)
+ *shift_ret = shift;
+ return ret;
+}
+
+/* Used to convert a nested guest real address to a L1 guest real address */
+static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
+ struct kvm_nested_guest *gp,
+ unsigned long n_gpa, unsigned long dsisr,
+ struct kvmppc_pte *gpte_p)
{
+ u64 fault_addr, flags = dsisr & DSISR_ISSTORE;
+ int ret;
+
+ ret = kvmppc_mmu_walk_radix_tree(vcpu, n_gpa, gpte_p, gp->l1_gr_to_hr,
+ &fault_addr);
+
+ if (ret) {
+ /* We didn't find a pte */
+ if (ret == -EINVAL) {
+ /* Unsupported mmu config */
+ flags |= DSISR_UNSUPP_MMU;
+ } else if (ret == -ENOENT) {
+ /* No translation found */
+ flags |= DSISR_NOHPTE;
+ } else if (ret == -EFAULT) {
+ /* Couldn't access L1 real address */
+ flags |= DSISR_PRTABLE_FAULT;
+ vcpu->arch.fault_gpa = fault_addr;
+ } else {
+ /* Unknown error */
+ return ret;
+ }
+ goto forward_to_l1;
+ } else {
+ /* We found a pte -> check permissions */
+ if (dsisr & DSISR_ISSTORE) {
+ /* Can we write? */
+ if (!gpte_p->may_write) {
+ flags |= DSISR_PROTFAULT;
+ goto forward_to_l1;
+ }
+ } else if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
+ /* Can we execute? */
+ if (!gpte_p->may_execute) {
+ flags |= SRR1_ISI_N_OR_G;
+ goto forward_to_l1;
+ }
+ } else {
+ /* Can we read? */
+ if (!gpte_p->may_read && !gpte_p->may_write) {
+ flags |= DSISR_PROTFAULT;
+ goto forward_to_l1;
+ }
+ }
+ }
+
+ return 0;
+
+forward_to_l1:
+ vcpu->arch.fault_dsisr = flags;
+ if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
+ vcpu->arch.shregs.msr &= ~0x783f0000ul;
+ vcpu->arch.shregs.msr |= flags;
+ }
return RESUME_HOST;
}
+
+static long kvmhv_handle_nested_set_rc(struct kvm_vcpu *vcpu,
+ struct kvm_nested_guest *gp,
+ unsigned long n_gpa,
+ struct kvmppc_pte gpte,
+ unsigned long dsisr)
+{
+ struct kvm *kvm = vcpu->kvm;
+ bool writing = !!(dsisr & DSISR_ISSTORE);
+ u64 pgflags;
+ bool ret;
+
+ /* Are the rc bits set in the L1 partition scoped pte? */
+ pgflags = _PAGE_ACCESSED;
+ if (writing)
+ pgflags |= _PAGE_DIRTY;
+ if (pgflags & ~gpte.rc)
+ return RESUME_HOST;
+
+ spin_lock(&kvm->mmu_lock);
+ /* Set the rc bit in the pte of our (L0) pgtable for the L1 guest */
+ ret = kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable, writing,
+ gpte.raddr, kvm->arch.lpid);
+ spin_unlock(&kvm->mmu_lock);
+ if (!ret)
+ return -EINVAL;
+
+ /* Set the rc bit in the pte of the shadow_pgtable for the nest guest */
+ ret = kvmppc_hv_handle_set_rc(kvm, gp->shadow_pgtable, writing, n_gpa,
+ gp->shadow_lpid);
+ if (!ret)
+ return -EINVAL;
+ return 0;
+}
+
+static inline int kvmppc_radix_level_to_shift(int level)
+{
+ switch (level) {
+ case 2:
+ return PUD_SHIFT;
+ case 1:
+ return PMD_SHIFT;
+ default:
+ return PAGE_SHIFT;
+ }
+}
+
+static inline int kvmppc_radix_shift_to_level(int shift)
+{
+ if (shift == PUD_SHIFT)
+ return 2;
+ if (shift == PMD_SHIFT)
+ return 1;
+ if (shift == PAGE_SHIFT)
+ return 0;
+ WARN_ON_ONCE(1);
+ return 0;
+}
+
+/* called with gp->tlb_lock held */
+static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
+ struct kvm_nested_guest *gp)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_memory_slot *memslot;
+ struct kvmppc_pte gpte;
+ pte_t pte, *pte_p;
+ unsigned long mmu_seq;
+ unsigned long dsisr = vcpu->arch.fault_dsisr;
+ unsigned long ea = vcpu->arch.fault_dar;
+ unsigned long n_gpa, gpa, gfn, perm = 0UL;
+ unsigned int shift, l1_shift, level;
+ bool writing = !!(dsisr & DSISR_ISSTORE);
+ bool kvm_ro = false;
+ long int ret;
+
+ if (!gp->l1_gr_to_hr) {
+ kvmhv_update_ptbl_cache(gp);
+ if (!gp->l1_gr_to_hr)
+ return RESUME_HOST;
+ }
+
+ /* Convert the nested guest real address into a L1 guest real address */
+
+ n_gpa = vcpu->arch.fault_gpa & ~0xF000000000000FFFULL;
+ if (!(dsisr & DSISR_PRTABLE_FAULT))
+ n_gpa |= ea & 0xFFF;
+ ret = kvmhv_translate_addr_nested(vcpu, gp, n_gpa, dsisr, &gpte);
+
+ /*
+ * If the hardware found a translation but we don't now have a usable
+ * translation in the l1 partition-scoped tree, remove the shadow pte
+ * and let the guest retry.
+ */
+ if (ret == RESUME_HOST &&
+ (dsisr & (DSISR_PROTFAULT | DSISR_BADACCESS | DSISR_NOEXEC_OR_G |
+ DSISR_BAD_COPYPASTE)))
+ goto inval;
+ if (ret)
+ return ret;
+
+ /* Failed to set the reference/change bits */
+ if (dsisr & DSISR_SET_RC) {
+ ret = kvmhv_handle_nested_set_rc(vcpu, gp, n_gpa, gpte, dsisr);
+ if (ret == RESUME_HOST)
+ return ret;
+ if (ret)
+ goto inval;
+ dsisr &= ~DSISR_SET_RC;
+ if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
+ DSISR_PROTFAULT)))
+ return RESUME_GUEST;
+ }
+
+ /*
+ * We took an HISI or HDSI while we were running a nested guest which
+ * means we have no partition scoped translation for that. This means
+ * we need to insert a pte for the mapping into our shadow_pgtable.
+ */
+
+ l1_shift = gpte.page_shift;
+ if (l1_shift < PAGE_SHIFT) {
+ /* We don't support l1 using a page size smaller than our own */
+ pr_err("KVM: L1 guest page shift (%d) less than our own (%d)\n",
+ l1_shift, PAGE_SHIFT);
+ return -EINVAL;
+ }
+ gpa = gpte.raddr;
+ gfn = gpa >> PAGE_SHIFT;
+
+ /* 1. Get the corresponding host memslot */
+
+ memslot = gfn_to_memslot(kvm, gfn);
+ if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+ if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS)) {
+ /* unusual error -> reflect to the guest as a DSI */
+ kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+ return RESUME_GUEST;
+ }
+ /* passthrough of emulated MMIO case... */
+ pr_err("emulated MMIO passthrough?\n");
+ return -EINVAL;
+ }
+ if (memslot->flags & KVM_MEM_READONLY) {
+ if (writing) {
+ /* Give the guest a DSI */
+ kvmppc_core_queue_data_storage(vcpu, ea,
+ DSISR_ISSTORE | DSISR_PROTFAULT);
+ return RESUME_GUEST;
+ }
+ kvm_ro = true;
+ }
+
+ /* 2. Find the host pte for this L1 guest real address */
+
+ /* Used to check for invalidations in progress */
+ mmu_seq = kvm->mmu_notifier_seq;
+ smp_rmb();
+
+ /* See if can find translation in our partition scoped tables for L1 */
+ pte = __pte(0);
+ spin_lock(&kvm->mmu_lock);
+ pte_p = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
+ if (!shift)
+ shift = PAGE_SHIFT;
+ if (pte_p)
+ pte = *pte_p;
+ spin_unlock(&kvm->mmu_lock);
+
+ if (!pte_present(pte) || (writing && !(pte_val(pte) & _PAGE_WRITE))) {
+ /* No suitable pte found -> try to insert a mapping */
+ ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot,
+ writing, kvm_ro, &pte, &level);
+ if (ret == -EAGAIN)
+ return RESUME_GUEST;
+ else if (ret)
+ return ret;
+ shift = kvmppc_radix_level_to_shift(level);
+ }
+
+ /* 3. Compute the pte we need to insert for nest_gpa -> host r_addr */
+
+ /* The permissions is the combination of the host and l1 guest ptes */
+ perm |= gpte.may_read ? 0UL : _PAGE_READ;
+ perm |= gpte.may_write ? 0UL : _PAGE_WRITE;
+ perm |= gpte.may_execute ? 0UL : _PAGE_EXEC;
+ pte = __pte(pte_val(pte) & ~perm);
+
+ /* What size pte can we insert? */
+ if (shift > l1_shift) {
+ u64 mask;
+ unsigned int actual_shift = PAGE_SHIFT;
+ if (PMD_SHIFT < l1_shift)
+ actual_shift = PMD_SHIFT;
+ mask = (1UL << shift) - (1UL << actual_shift);
+ pte = __pte(pte_val(pte) | (gpa & mask));
+ shift = actual_shift;
+ }
+ level = kvmppc_radix_shift_to_level(shift);
+ n_gpa &= ~((1UL << shift) - 1);
+
+ /* 4. Insert the pte into our shadow_pgtable */
+
+ ret = kvmppc_create_pte(kvm, gp->shadow_pgtable, pte, n_gpa, level,
+ mmu_seq, gp->shadow_lpid);
+ if (ret == -EAGAIN)
+ ret = RESUME_GUEST; /* Let the guest try again */
+
+ return ret;
+
+ inval:
+ kvmhv_invalidate_shadow_pte(vcpu, gp, n_gpa, NULL);
+ return RESUME_GUEST;
+}
+
+long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu)
+{
+ struct kvm_nested_guest *gp = vcpu->arch.nested;
+ long int ret;
+
+ mutex_lock(&gp->tlb_lock);
+ ret = __kvmhv_nested_page_fault(vcpu, gp);
+ mutex_unlock(&gp->tlb_lock);
+ return ret;
+}
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index fef3e1e..4c4dfc4 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -833,6 +833,15 @@ EXPORT_SYMBOL_GPL(radix__flush_pwc_lpid);
/*
* Flush partition scoped translations from LPID (=LPIDR)
*/
+void radix__flush_tlb_lpid(unsigned int lpid)
+{
+ _tlbie_lpid(lpid, RIC_FLUSH_ALL);
+}
+EXPORT_SYMBOL_GPL(radix__flush_tlb_lpid);
+
+/*
+ * Flush partition scoped translations from LPID (=LPIDR)
+ */
void radix__local_flush_tlb_lpid(unsigned int lpid)
{
_tlbiel_lpid(lpid, RIC_FLUSH_ALL);
--
2.7.4
^ permalink raw reply related
* [PATCH v4 22/32] KVM: PPC: Book3S HV: Introduce rmap to track nested guest mappings
From: Paul Mackerras @ 2018-10-04 11:55 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
When a host (L0) page which is mapped into a (L1) guest is in turn
mapped through to a nested (L2) guest we keep a reverse mapping (rmap)
so that these mappings can be retrieved later.
Whenever we create an entry in a shadow_pgtable for a nested guest we
create a corresponding rmap entry and add it to the list for the
L1 guest memslot at the index of the L1 guest page it maps. This means
at the L1 guest memslot we end up with lists of rmaps.
When we are notified of a host page being invalidated which has been
mapped through to a (L1) guest, we can then walk the rmap list for that
guest page, and find and invalidate all of the corresponding
shadow_pgtable entries.
In order to reduce memory consumption, we compress the information for
each rmap entry down to 52 bits -- 12 bits for the LPID and 40 bits
for the guest real page frame number -- which will fit in a single
unsigned long. To avoid a scenario where a guest can trigger
unbounded memory allocations, we scan the list when adding an entry to
see if there is already an entry with the contents we need. This can
occur, because we don't ever remove entries from the middle of a list.
A struct nested guest rmap is a list pointer and an rmap entry;
----------------
| next pointer |
----------------
| rmap entry |
----------------
Thus the rmap pointer for each guest frame number in the memslot can be
either NULL, a single entry, or a pointer to a list of nested rmap entries.
gfn memslot rmap array
-------------------------
0 | NULL | (no rmap entry)
-------------------------
1 | single rmap entry | (rmap entry with low bit set)
-------------------------
2 | list head pointer | (list of rmap entries)
-------------------------
The final entry always has the lowest bit set and is stored in the next
pointer of the last list entry, or as a single rmap entry.
With a list of rmap entries looking like;
----------------- ----------------- -------------------------
| list head ptr | ----> | next pointer | ----> | single rmap entry |
----------------- ----------------- -------------------------
| rmap entry | | rmap entry |
----------------- -------------------------
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_book3s.h | 3 +
arch/powerpc/include/asm/kvm_book3s_64.h | 70 ++++++++++++++++-
arch/powerpc/kvm/book3s_64_mmu_radix.c | 44 +++++++----
arch/powerpc/kvm/book3s_hv.c | 1 +
arch/powerpc/kvm/book3s_hv_nested.c | 130 ++++++++++++++++++++++++++++++-
5 files changed, 233 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 63f7ccf..d7aeb6f 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -196,6 +196,9 @@ extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
int table_index, u64 *pte_ret_p);
extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_pte *gpte, bool data, bool iswrite);
+extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
+ unsigned int shift, struct kvm_memory_slot *memslot,
+ unsigned int lpid);
extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
bool writing, unsigned long gpa,
unsigned int lpid);
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 5496152..a02f0b3 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -53,6 +53,66 @@ struct kvm_nested_guest {
struct kvm_nested_guest *next;
};
+/*
+ * We define a nested rmap entry as a single 64-bit quantity
+ * 0xFFF0000000000000 12-bit lpid field
+ * 0x000FFFFFFFFFF000 40-bit guest 4k page frame number
+ * 0x0000000000000001 1-bit single entry flag
+ */
+#define RMAP_NESTED_LPID_MASK 0xFFF0000000000000UL
+#define RMAP_NESTED_LPID_SHIFT (52)
+#define RMAP_NESTED_GPA_MASK 0x000FFFFFFFFFF000UL
+#define RMAP_NESTED_IS_SINGLE_ENTRY 0x0000000000000001UL
+
+/* Structure for a nested guest rmap entry */
+struct rmap_nested {
+ struct llist_node list;
+ u64 rmap;
+};
+
+/*
+ * for_each_nest_rmap_safe - iterate over the list of nested rmap entries
+ * safe against removal of the list entry or NULL list
+ * @pos: a (struct rmap_nested *) to use as a loop cursor
+ * @node: pointer to the first entry
+ * NOTE: this can be NULL
+ * @rmapp: an (unsigned long *) in which to return the rmap entries on each
+ * iteration
+ * NOTE: this must point to already allocated memory
+ *
+ * The nested_rmap is a llist of (struct rmap_nested) entries pointed to by the
+ * rmap entry in the memslot. The list is always terminated by a "single entry"
+ * stored in the list element of the final entry of the llist. If there is ONLY
+ * a single entry then this is itself in the rmap entry of the memslot, not a
+ * llist head pointer.
+ *
+ * Note that the iterator below assumes that a nested rmap entry is always
+ * non-zero. This is true for our usage because the LPID field is always
+ * non-zero (zero is reserved for the host).
+ *
+ * This should be used to iterate over the list of rmap_nested entries with
+ * processing done on the u64 rmap value given by each iteration. This is safe
+ * against removal of list entries and it is always safe to call free on (pos).
+ *
+ * e.g.
+ * struct rmap_nested *cursor;
+ * struct llist_node *first;
+ * unsigned long rmap;
+ * for_each_nest_rmap_safe(cursor, first, &rmap) {
+ * do_something(rmap);
+ * free(cursor);
+ * }
+ */
+#define for_each_nest_rmap_safe(pos, node, rmapp) \
+ for ((pos) = llist_entry((node), typeof(*(pos)), list); \
+ (node) && \
+ (*(rmapp) = ((RMAP_NESTED_IS_SINGLE_ENTRY & ((u64) (node))) ? \
+ ((u64) (node)) : ((pos)->rmap))) && \
+ (((node) = ((RMAP_NESTED_IS_SINGLE_ENTRY & ((u64) (node))) ? \
+ ((struct llist_node *) ((pos) = NULL)) : \
+ (pos)->list.next)), true); \
+ (pos) = llist_entry((node), typeof(*(pos)), list))
+
struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
bool create);
void kvmhv_put_nested(struct kvm_nested_guest *gp);
@@ -551,7 +611,15 @@ static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
unsigned long gpa, unsigned int level,
- unsigned long mmu_seq, unsigned int lpid);
+ unsigned long mmu_seq, unsigned int lpid,
+ unsigned long *rmapp, struct rmap_nested **n_rmap);
+extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
+ struct rmap_nested **n_rmap);
+extern void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
+ unsigned long gpa, unsigned long hpa,
+ unsigned long nbytes);
+extern void kvmhv_free_memslot_nest_rmap(struct kvm_memory_slot *free);
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index c4b1a9e..4c1eccb 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -256,27 +256,38 @@ static void kvmppc_pmd_free(pmd_t *pmdp)
kmem_cache_free(kvm_pmd_cache, pmdp);
}
-void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
- unsigned long gpa, unsigned int shift,
- struct kvm_memory_slot *memslot,
+/* Called with kvm->mmu_lock held */
+void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
+ unsigned int shift, struct kvm_memory_slot *memslot,
unsigned int lpid)
{
unsigned long old;
+ unsigned long gfn = gpa >> PAGE_SHIFT;
+ unsigned long page_size = PAGE_SIZE;
+ unsigned long hpa;
old = kvmppc_radix_update_pte(kvm, pte, ~0UL, 0, gpa, shift);
kvmppc_radix_tlbie_page(kvm, gpa, shift, lpid);
- if ((old & _PAGE_DIRTY) && (lpid == kvm->arch.lpid)) {
- unsigned long gfn = gpa >> PAGE_SHIFT;
- unsigned long page_size = PAGE_SIZE;
- if (shift)
- page_size = 1ul << shift;
+ /* The following only applies to L1 entries */
+ if (lpid != kvm->arch.lpid)
+ return;
+
+ if (!memslot) {
+ memslot = gfn_to_memslot(kvm, gfn);
if (!memslot)
- memslot = gfn_to_memslot(kvm, gfn);
- if (memslot && memslot->dirty_bitmap)
- kvmppc_update_dirty_map(memslot, gfn, page_size);
+ return;
}
+ if (shift)
+ page_size = 1ul << shift;
+
+ gpa &= ~(page_size - 1);
+ hpa = old & PTE_RPN_MASK;
+ kvmhv_remove_nest_rmap_range(kvm, memslot, gpa, hpa, page_size);
+
+ if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap)
+ kvmppc_update_dirty_map(memslot, gfn, page_size);
}
/*
@@ -430,7 +441,8 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
unsigned long gpa, unsigned int level,
- unsigned long mmu_seq, unsigned int lpid)
+ unsigned long mmu_seq, unsigned int lpid,
+ unsigned long *rmapp, struct rmap_nested **n_rmap)
{
pgd_t *pgd;
pud_t *pud, *new_pud = NULL;
@@ -509,6 +521,8 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa, lpid);
}
kvmppc_radix_set_pte_at(kvm, gpa, (pte_t *)pud, pte);
+ if (rmapp && n_rmap)
+ kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
ret = 0;
goto out_unlock;
}
@@ -559,6 +573,8 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa, lpid);
}
kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte);
+ if (rmapp && n_rmap)
+ kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
ret = 0;
goto out_unlock;
}
@@ -583,6 +599,8 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
goto out_unlock;
}
kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
+ if (rmapp && n_rmap)
+ kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
ret = 0;
out_unlock:
@@ -710,7 +728,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
/* Allocate space in the tree and write the PTE */
ret = kvmppc_create_pte(kvm, kvm->arch.pgtable, pte, gpa, level,
- mmu_seq, kvm->arch.lpid);
+ mmu_seq, kvm->arch.lpid, NULL, NULL);
if (inserted_pte)
*inserted_pte = pte;
if (levelp)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 134d7c7..2d8209a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4269,6 +4269,7 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
if (!dont || free->arch.rmap != dont->arch.rmap) {
+ kvmhv_free_memslot_nest_rmap(free);
vfree(free->arch.rmap);
free->arch.rmap = NULL;
}
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 9c04242..3947aa5 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -10,6 +10,7 @@
#include <linux/kernel.h>
#include <linux/kvm_host.h>
+#include <linux/llist.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
@@ -541,6 +542,123 @@ void kvmhv_put_nested(struct kvm_nested_guest *gp)
kvmhv_release_nested(gp);
}
+static struct kvm_nested_guest *kvmhv_find_nested(struct kvm *kvm, int lpid)
+{
+ if (lpid > kvm->arch.max_nested_lpid)
+ return NULL;
+ return kvm->arch.nested_guests[lpid];
+}
+
+static inline bool kvmhv_n_rmap_is_equal(u64 rmap_1, u64 rmap_2)
+{
+ return !((rmap_1 ^ rmap_2) & (RMAP_NESTED_LPID_MASK |
+ RMAP_NESTED_GPA_MASK));
+}
+
+void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
+ struct rmap_nested **n_rmap)
+{
+ struct llist_node *entry = ((struct llist_head *) rmapp)->first;
+ struct rmap_nested *cursor;
+ u64 rmap, new_rmap = (*n_rmap)->rmap;
+
+ /* Are there any existing entries? */
+ if (!(*rmapp)) {
+ /* No -> use the rmap as a single entry */
+ *rmapp = new_rmap | RMAP_NESTED_IS_SINGLE_ENTRY;
+ return;
+ }
+
+ /* Do any entries match what we're trying to insert? */
+ for_each_nest_rmap_safe(cursor, entry, &rmap) {
+ if (kvmhv_n_rmap_is_equal(rmap, new_rmap))
+ return;
+ }
+
+ /* Do we need to create a list or just add the new entry? */
+ rmap = *rmapp;
+ if (rmap & RMAP_NESTED_IS_SINGLE_ENTRY) /* Not previously a list */
+ *rmapp = 0UL;
+ llist_add(&((*n_rmap)->list), (struct llist_head *) rmapp);
+ if (rmap & RMAP_NESTED_IS_SINGLE_ENTRY) /* Not previously a list */
+ (*n_rmap)->list.next = (struct llist_node *) rmap;
+
+ /* Set NULL so not freed by caller */
+ *n_rmap = NULL;
+}
+
+static void kvmhv_remove_nest_rmap(struct kvm *kvm, u64 n_rmap,
+ unsigned long hpa, unsigned long mask)
+{
+ struct kvm_nested_guest *gp;
+ unsigned long gpa;
+ unsigned int shift, lpid;
+ pte_t *ptep;
+
+ gpa = n_rmap & RMAP_NESTED_GPA_MASK;
+ lpid = (n_rmap & RMAP_NESTED_LPID_MASK) >> RMAP_NESTED_LPID_SHIFT;
+ gp = kvmhv_find_nested(kvm, lpid);
+ if (!gp)
+ return;
+
+ /* Find and invalidate the pte */
+ ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
+ /* Don't spuriously invalidate ptes if the pfn has changed */
+ if (ptep && pte_present(*ptep) && ((pte_val(*ptep) & mask) == hpa))
+ kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
+}
+
+static void kvmhv_remove_nest_rmap_list(struct kvm *kvm, unsigned long *rmapp,
+ unsigned long hpa, unsigned long mask)
+{
+ struct llist_node *entry = llist_del_all((struct llist_head *) rmapp);
+ struct rmap_nested *cursor;
+ unsigned long rmap;
+
+ for_each_nest_rmap_safe(cursor, entry, &rmap) {
+ kvmhv_remove_nest_rmap(kvm, rmap, hpa, mask);
+ kfree(cursor);
+ }
+}
+
+/* called with kvm->mmu_lock held */
+void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
+ unsigned long gpa, unsigned long hpa,
+ unsigned long nbytes)
+{
+ unsigned long gfn, end_gfn;
+ unsigned long addr_mask;
+
+ if (!memslot)
+ return;
+ gfn = (gpa >> PAGE_SHIFT) - memslot->base_gfn;
+ end_gfn = gfn + (nbytes >> PAGE_SHIFT);
+
+ addr_mask = PTE_RPN_MASK & ~(nbytes - 1);
+ hpa &= addr_mask;
+
+ for (; gfn < end_gfn; gfn++) {
+ unsigned long *rmap = &memslot->arch.rmap[gfn];
+ kvmhv_remove_nest_rmap_list(kvm, rmap, hpa, addr_mask);
+ }
+}
+
+void kvmhv_free_memslot_nest_rmap(struct kvm_memory_slot *free)
+{
+ unsigned long page;
+
+ for (page = 0; page < free->npages; page++) {
+ unsigned long rmap, *rmapp = &free->arch.rmap[page];
+ struct rmap_nested *cursor;
+ struct llist_node *entry;
+
+ entry = llist_del_all((struct llist_head *) rmapp);
+ for_each_nest_rmap_safe(cursor, entry, &rmap)
+ kfree(cursor);
+ }
+}
+
static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu,
struct kvm_nested_guest *gp,
long gpa, int *shift_ret)
@@ -692,11 +810,13 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
{
struct kvm *kvm = vcpu->kvm;
struct kvm_memory_slot *memslot;
+ struct rmap_nested *n_rmap;
struct kvmppc_pte gpte;
pte_t pte, *pte_p;
unsigned long mmu_seq;
unsigned long dsisr = vcpu->arch.fault_dsisr;
unsigned long ea = vcpu->arch.fault_dar;
+ unsigned long *rmapp;
unsigned long n_gpa, gpa, gfn, perm = 0UL;
unsigned int shift, l1_shift, level;
bool writing = !!(dsisr & DSISR_ISSTORE);
@@ -830,8 +950,16 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
/* 4. Insert the pte into our shadow_pgtable */
+ n_rmap = kzalloc(sizeof(*n_rmap), GFP_KERNEL);
+ if (!n_rmap)
+ return RESUME_GUEST; /* Let the guest try again */
+ n_rmap->rmap = (n_gpa & RMAP_NESTED_GPA_MASK) |
+ (((unsigned long) gp->l1_lpid) << RMAP_NESTED_LPID_SHIFT);
+ rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
ret = kvmppc_create_pte(kvm, gp->shadow_pgtable, pte, n_gpa, level,
- mmu_seq, gp->shadow_lpid);
+ mmu_seq, gp->shadow_lpid, rmapp, &n_rmap);
+ if (n_rmap)
+ kfree(n_rmap);
if (ret == -EAGAIN)
ret = RESUME_GUEST; /* Let the guest try again */
--
2.7.4
^ permalink raw reply related
* [PATCH v4 23/32] KVM: PPC: Book3S HV: Implement H_TLB_INVALIDATE hcall
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
When running a nested (L2) guest the guest (L1) hypervisor will use
the H_TLB_INVALIDATE hcall when it needs to change the partition
scoped page tables or the partition table which it manages. It will
use this hcall in the situations where it would use a partition-scoped
tlbie instruction if it were running in hypervisor mode.
The H_TLB_INVALIDATE hcall can invalidate different scopes:
Invalidate TLB for a given target address:
- This invalidates a single L2 -> L1 pte
- We need to invalidate any L2 -> L0 shadow_pgtable ptes which map the L2
address space which is being invalidated. This is because a single
L2 -> L1 pte may have been mapped with more than one pte in the
L2 -> L0 page tables.
Invalidate the entire TLB for a given LPID or for all LPIDs:
- Invalidate the entire shadow_pgtable for a given nested guest, or
for all nested guests.
Invalidate the PWC (page walk cache) for a given LPID or for all LPIDs:
- We don't cache the PWC, so nothing to do.
Invalidate the entire TLB, PWC and partition table for a given/all LPIDs:
- Here we re-read the partition table entry and remove the nested state
for any nested guest for which the first doubleword of the partition
table entry is now zero.
The H_TLB_INVALIDATE hcall takes as parameters the tlbie instruction
word (of which only the RIC, PRS and R fields are used), the rS value
(giving the lpid, where required) and the rB value (giving the IS, AP
and EPN values).
[paulus@ozlabs.org - adapted to having the partition table in guest
memory, added the H_TLB_INVALIDATE implementation, removed tlbie
instruction emulation, reworded the commit message.]
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 12 ++
arch/powerpc/include/asm/kvm_book3s.h | 1 +
arch/powerpc/include/asm/ppc-opcode.h | 1 +
arch/powerpc/kvm/book3s_emulate.c | 1 -
arch/powerpc/kvm/book3s_hv.c | 3 +
arch/powerpc/kvm/book3s_hv_nested.c | 196 +++++++++++++++++++++++++-
6 files changed, 212 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index b3520b5..66db23e 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -203,6 +203,18 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
BUG();
}
+static inline unsigned int ap_to_shift(unsigned long ap)
+{
+ int psize;
+
+ for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+ if (mmu_psize_defs[psize].ap == ap)
+ return mmu_psize_defs[psize].shift;
+ }
+
+ return -1;
+}
+
static inline unsigned long get_sllp_encoding(int psize)
{
unsigned long sllp;
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index d7aeb6f..09f8e9b 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -301,6 +301,7 @@ long kvmhv_set_partition_table(struct kvm_vcpu *vcpu);
void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1);
void kvmhv_release_all_nested(struct kvm *kvm);
long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
+long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu,
u64 time_limit, unsigned long lpcr);
void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 665af14..6093bc8 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -104,6 +104,7 @@
#define OP_31_XOP_LHZUX 311
#define OP_31_XOP_MSGSNDP 142
#define OP_31_XOP_MSGCLRP 174
+#define OP_31_XOP_TLBIE 306
#define OP_31_XOP_MFSPR 339
#define OP_31_XOP_LWAX 341
#define OP_31_XOP_LHAX 343
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 2654df2..8c7e933 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -36,7 +36,6 @@
#define OP_31_XOP_MTSR 210
#define OP_31_XOP_MTSRIN 242
#define OP_31_XOP_TLBIEL 274
-#define OP_31_XOP_TLBIE 306
/* Opcode is officially reserved, reuse it as sc 1 when sc 1 doesn't trap */
#define OP_31_XOP_FAKE_SC1 308
#define OP_31_XOP_SLBMTE 402
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2d8209a..ba58883 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -974,6 +974,9 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
break;
case H_TLB_INVALIDATE:
ret = H_FUNCTION;
+ if (!vcpu->kvm->arch.nested_enable)
+ break;
+ ret = kvmhv_do_nested_tlbie(vcpu);
break;
default:
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 3947aa5..26151e8 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -475,7 +475,7 @@ void kvmhv_release_all_nested(struct kvm *kvm)
}
/* caller must hold gp->tlb_lock */
-void kvmhv_flush_nested(struct kvm_nested_guest *gp)
+static void kvmhv_flush_nested(struct kvm_nested_guest *gp)
{
struct kvm *kvm = gp->l1_host;
@@ -683,6 +683,200 @@ static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu,
return ret;
}
+static inline int get_ric(unsigned int instr)
+{
+ return (instr >> 18) & 0x3;
+}
+
+static inline int get_prs(unsigned int instr)
+{
+ return (instr >> 17) & 0x1;
+}
+
+static inline int get_r(unsigned int instr)
+{
+ return (instr >> 16) & 0x1;
+}
+
+static inline int get_lpid(unsigned long r_val)
+{
+ return r_val & 0xffffffff;
+}
+
+static inline int get_is(unsigned long r_val)
+{
+ return (r_val >> 10) & 0x3;
+}
+
+static inline int get_ap(unsigned long r_val)
+{
+ return (r_val >> 5) & 0x7;
+}
+
+static inline long get_epn(unsigned long r_val)
+{
+ return r_val >> 12;
+}
+
+static int kvmhv_emulate_tlbie_tlb_addr(struct kvm_vcpu *vcpu, int lpid,
+ int ap, long epn)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_nested_guest *gp;
+ long npages;
+ int shift;
+ unsigned long addr;
+
+ shift = ap_to_shift(ap);
+ addr = epn << 12;
+ if (shift < 0)
+ /* Invalid ap encoding */
+ return -EINVAL;
+
+ addr &= ~((1UL << shift) - 1);
+ npages = 1UL << (shift - PAGE_SHIFT);
+
+ gp = kvmhv_get_nested(kvm, lpid, false);
+ if (!gp) /* No such guest -> nothing to do */
+ return 0;
+ mutex_lock(&gp->tlb_lock);
+
+ /* There may be more than one host page backing this single guest pte */
+ do {
+ kvmhv_invalidate_shadow_pte(vcpu, gp, addr, &shift);
+
+ npages -= 1UL << (shift - PAGE_SHIFT);
+ addr += 1UL << shift;
+ } while (npages > 0);
+
+ mutex_unlock(&gp->tlb_lock);
+ kvmhv_put_nested(gp);
+ return 0;
+}
+
+static void kvmhv_emulate_tlbie_lpid(struct kvm_vcpu *vcpu,
+ struct kvm_nested_guest *gp, int ric)
+{
+ struct kvm *kvm = vcpu->kvm;
+
+ mutex_lock(&gp->tlb_lock);
+ switch (ric) {
+ case 0:
+ /* Invalidate TLB */
+ spin_lock(&kvm->mmu_lock);
+ kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
+ gp->shadow_lpid);
+ radix__flush_tlb_lpid(gp->shadow_lpid);
+ spin_unlock(&kvm->mmu_lock);
+ break;
+ case 1:
+ /*
+ * Invalidate PWC
+ * We don't cache this -> nothing to do
+ */
+ break;
+ case 2:
+ /* Invalidate TLB, PWC and caching of partition table entries */
+ kvmhv_flush_nested(gp);
+ break;
+ default:
+ break;
+ }
+ mutex_unlock(&gp->tlb_lock);
+}
+
+static void kvmhv_emulate_tlbie_all_lpid(struct kvm_vcpu *vcpu, int ric)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_nested_guest *gp;
+ int i;
+
+ spin_lock(&kvm->mmu_lock);
+ for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
+ gp = kvm->arch.nested_guests[i];
+ if (gp) {
+ spin_unlock(&kvm->mmu_lock);
+ kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
+ spin_lock(&kvm->mmu_lock);
+ }
+ }
+ spin_unlock(&kvm->mmu_lock);
+}
+
+static int kvmhv_emulate_priv_tlbie(struct kvm_vcpu *vcpu, unsigned int instr,
+ unsigned long rsval, unsigned long rbval)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_nested_guest *gp;
+ int r, ric, prs, is, ap;
+ int lpid;
+ long epn;
+ int ret = 0;
+
+ ric = get_ric(instr);
+ prs = get_prs(instr);
+ r = get_r(instr);
+ lpid = get_lpid(rsval);
+ is = get_is(rbval);
+
+ /*
+ * These cases are invalid and are not handled:
+ * r != 1 -> Only radix supported
+ * prs == 1 -> Not HV privileged
+ * ric == 3 -> No cluster bombs for radix
+ * is == 1 -> Partition scoped translations not associated with pid
+ * (!is) && (ric == 1 || ric == 2) -> Not supported by ISA
+ */
+ if ((!r) || (prs) || (ric == 3) || (is == 1) ||
+ ((!is) && (ric == 1 || ric == 2)))
+ return -EINVAL;
+
+ switch (is) {
+ case 0:
+ /*
+ * We know ric == 0
+ * Invalidate TLB for a given target address
+ */
+ epn = get_epn(rbval);
+ ap = get_ap(rbval);
+ ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap, epn);
+ break;
+ case 2:
+ /* Invalidate matching LPID */
+ gp = kvmhv_get_nested(kvm, lpid, false);
+ if (gp) {
+ kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
+ kvmhv_put_nested(gp);
+ }
+ break;
+ case 3:
+ /* Invalidate ALL LPIDs */
+ kvmhv_emulate_tlbie_all_lpid(vcpu, ric);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * This handles the H_TLB_INVALIDATE hcall.
+ * Parameters are (r4) tlbie instruction code, (r5) rS contents,
+ * (r6) rB contents.
+ */
+long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
+{
+ int ret;
+
+ ret = kvmhv_emulate_priv_tlbie(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6));
+ if (ret)
+ return H_PARAMETER;
+ return H_SUCCESS;
+}
+
/* Used to convert a nested guest real address to a L1 guest real address */
static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
struct kvm_nested_guest *gp,
--
2.7.4
^ permalink raw reply related
* [PATCH v4 24/32] KVM: PPC: Book3S HV: Use hypercalls for TLB invalidation when nested
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
This adds code to call the H_TLB_INVALIDATE hypercall when running as
a guest, in the cases where we need to invalidate TLBs (or other MMU
caches) as part of managing the mappings for a nested guest. Calling
H_TLB_INVALIDATE lets the nested hypervisor inform the parent
hypervisor about changes to partition-scoped page tables or the
partition table without needing to do hypervisor-privileged tlbie
instructions.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 5 +++++
arch/powerpc/kvm/book3s_64_mmu_radix.c | 30 ++++++++++++++++++++++++++++--
arch/powerpc/kvm/book3s_hv_nested.c | 30 ++++++++++++++++++++++++------
3 files changed, 57 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index a02f0b3..aa5bf85 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -24,6 +24,7 @@
#include <asm/bitops.h>
#include <asm/book3s/64/mmu-hash.h>
#include <asm/cpu_has_feature.h>
+#include <asm/ppc-opcode.h>
#ifdef CONFIG_PPC_PSERIES
static inline bool kvmhv_on_pseries(void)
@@ -117,6 +118,10 @@ struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
bool create);
void kvmhv_put_nested(struct kvm_nested_guest *gp);
+/* Encoding of first parameter for H_TLB_INVALIDATE */
+#define H_TLBIE_P1_ENC(ric, prs, r) (___PPC_RIC(ric) | ___PPC_PRS(prs) | \
+ ___PPC_R(r))
+
/* Power architecture requires HPT is at least 256kiB, at most 64TiB */
#define PPC_MIN_HPT_ORDER 18
#define PPC_MAX_HPT_ORDER 46
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 4c1eccb..ae0e3ed 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -201,17 +201,43 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
unsigned int pshift, unsigned int lpid)
{
unsigned long psize = PAGE_SIZE;
+ int psi;
+ long rc;
+ unsigned long rb;
if (pshift)
psize = 1UL << pshift;
+ else
+ pshift = PAGE_SHIFT;
addr &= ~(psize - 1);
- radix__flush_tlb_lpid_page(lpid, addr, psize);
+
+ if (!kvmhv_on_pseries()) {
+ radix__flush_tlb_lpid_page(lpid, addr, psize);
+ return;
+ }
+
+ psi = shift_to_mmu_psize(pshift);
+ rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
+ rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
+ lpid, rb);
+ if (rc)
+ pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
}
static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
{
- radix__flush_pwc_lpid(lpid);
+ long rc;
+
+ if (!kvmhv_on_pseries()) {
+ radix__flush_pwc_lpid(lpid);
+ return;
+ }
+
+ rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
+ lpid, TLBIEL_INVAL_SET_LPID);
+ if (rc)
+ pr_err("KVM: TLB PWC invalidation hcall failed, rc=%ld\n", rc);
}
static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 26151e8..35f8111 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -298,14 +298,32 @@ void kvmhv_nested_exit(void)
}
}
+static void kvmhv_flush_lpid(unsigned int lpid)
+{
+ long rc;
+
+ if (!kvmhv_on_pseries()) {
+ radix__flush_tlb_lpid(lpid);
+ return;
+ }
+
+ rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
+ lpid, TLBIEL_INVAL_SET_LPID);
+ if (rc)
+ pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
+}
+
void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1)
{
- if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ if (!kvmhv_on_pseries()) {
mmu_partition_table_set_entry(lpid, dw0, dw1);
- } else {
- pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
- pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+ return;
}
+
+ pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
+ pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+ /* L0 will do the necessary barriers */
+ kvmhv_flush_lpid(lpid);
}
static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)
@@ -482,7 +500,7 @@ static void kvmhv_flush_nested(struct kvm_nested_guest *gp)
spin_lock(&kvm->mmu_lock);
kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable, gp->shadow_lpid);
spin_unlock(&kvm->mmu_lock);
- radix__flush_tlb_lpid(gp->shadow_lpid);
+ kvmhv_flush_lpid(gp->shadow_lpid);
kvmhv_update_ptbl_cache(gp);
if (gp->l1_gr_to_hr == 0)
kvmhv_remove_nested(gp);
@@ -766,7 +784,7 @@ static void kvmhv_emulate_tlbie_lpid(struct kvm_vcpu *vcpu,
spin_lock(&kvm->mmu_lock);
kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
gp->shadow_lpid);
- radix__flush_tlb_lpid(gp->shadow_lpid);
+ kvmhv_flush_lpid(gp->shadow_lpid);
spin_unlock(&kvm->mmu_lock);
break;
case 1:
--
2.7.4
^ permalink raw reply related
* [PATCH v4 25/32] KVM: PPC: Book3S HV: Invalidate TLB when nested vcpu moves physical cpu
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
This is only done at level 0, since only level 0 knows which physical
CPU a vcpu is running on. This does for nested guests what L0 already
did for its own guests, which is to flush the TLB on a pCPU when it
goes to run a vCPU there, and there is another vCPU in the same VM
which previously ran on this pCPU and has now started to run on another
pCPU. This is to handle the situation where the other vCPU touched
a mapping, moved to another pCPU and did a tlbiel (local-only tlbie)
on that new pCPU and thus left behind a stale TLB entry on this pCPU.
This introduces a limit on the the vcpu_token values used in the
H_ENTER_NESTED hcall -- they must now be less than NR_CPUS.
[paulus@ozlabs.org - made prev_cpu array be unsigned short[] to reduce
memory consumption.]
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 3 +
arch/powerpc/kvm/book3s_hv.c | 101 +++++++++++++++++++------------
arch/powerpc/kvm/book3s_hv_nested.c | 5 ++
3 files changed, 71 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index aa5bf85..1e96027 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -52,6 +52,9 @@ struct kvm_nested_guest {
long refcnt; /* number of pointers to this struct */
struct mutex tlb_lock; /* serialize page faults and tlbies */
struct kvm_nested_guest *next;
+ cpumask_t need_tlb_flush;
+ cpumask_t cpu_in_guest;
+ unsigned short prev_cpu[NR_CPUS];
};
/*
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ba58883..53a967ea 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2397,10 +2397,18 @@ static void kvmppc_release_hwthread(int cpu)
static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
{
+ struct kvm_nested_guest *nested = vcpu->arch.nested;
+ cpumask_t *cpu_in_guest;
int i;
cpu = cpu_first_thread_sibling(cpu);
- cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush);
+ if (nested) {
+ cpumask_set_cpu(cpu, &nested->need_tlb_flush);
+ cpu_in_guest = &nested->cpu_in_guest;
+ } else {
+ cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush);
+ cpu_in_guest = &kvm->arch.cpu_in_guest;
+ }
/*
* Make sure setting of bit in need_tlb_flush precedes
* testing of cpu_in_guest bits. The matching barrier on
@@ -2408,13 +2416,23 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
*/
smp_mb();
for (i = 0; i < threads_per_core; ++i)
- if (cpumask_test_cpu(cpu + i, &kvm->arch.cpu_in_guest))
+ if (cpumask_test_cpu(cpu + i, cpu_in_guest))
smp_call_function_single(cpu + i, do_nothing, NULL, 1);
}
static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
{
+ struct kvm_nested_guest *nested = vcpu->arch.nested;
struct kvm *kvm = vcpu->kvm;
+ int prev_cpu;
+
+ if (!cpu_has_feature(CPU_FTR_HVMODE))
+ return;
+
+ if (nested)
+ prev_cpu = nested->prev_cpu[vcpu->arch.nested_vcpu_id];
+ else
+ prev_cpu = vcpu->arch.prev_cpu;
/*
* With radix, the guest can do TLB invalidations itself,
@@ -2428,12 +2446,46 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
* ran to flush the TLB. The TLB is shared between threads,
* so we use a single bit in .need_tlb_flush for all 4 threads.
*/
- if (vcpu->arch.prev_cpu != pcpu) {
- if (vcpu->arch.prev_cpu >= 0 &&
- cpu_first_thread_sibling(vcpu->arch.prev_cpu) !=
+ if (prev_cpu != pcpu) {
+ if (prev_cpu >= 0 &&
+ cpu_first_thread_sibling(prev_cpu) !=
cpu_first_thread_sibling(pcpu))
- radix_flush_cpu(kvm, vcpu->arch.prev_cpu, vcpu);
- vcpu->arch.prev_cpu = pcpu;
+ radix_flush_cpu(kvm, prev_cpu, vcpu);
+ if (nested)
+ nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu;
+ else
+ vcpu->arch.prev_cpu = pcpu;
+ }
+}
+
+static void kvmppc_radix_check_need_tlb_flush(struct kvm *kvm, int pcpu,
+ struct kvm_nested_guest *nested)
+{
+ cpumask_t *need_tlb_flush;
+ int lpid;
+
+ if (!cpu_has_feature(CPU_FTR_HVMODE))
+ return;
+
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ pcpu &= ~0x3UL;
+
+ if (nested) {
+ lpid = nested->shadow_lpid;
+ need_tlb_flush = &nested->need_tlb_flush;
+ } else {
+ lpid = kvm->arch.lpid;
+ need_tlb_flush = &kvm->arch.need_tlb_flush;
+ }
+
+ mtspr(SPRN_LPID, lpid);
+ isync();
+ smp_mb();
+
+ if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
+ radix__local_flush_tlb_lpid_guest(lpid);
+ /* Clear the bit after the TLB flush */
+ cpumask_clear_cpu(pcpu, need_tlb_flush);
}
}
@@ -3127,8 +3179,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
spin_unlock(&core_info.vc[sub]->lock);
if (kvm_is_radix(vc->kvm)) {
- int tmp = pcpu;
-
/*
* Do we need to flush the process scoped TLB for the LPAR?
*
@@ -3139,17 +3189,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
*
* Hash must be flushed in realmode in order to use tlbiel.
*/
- mtspr(SPRN_LPID, vc->kvm->arch.lpid);
- isync();
-
- if (cpu_has_feature(CPU_FTR_ARCH_300))
- tmp &= ~0x3UL;
-
- if (cpumask_test_cpu(tmp, &vc->kvm->arch.need_tlb_flush)) {
- radix__local_flush_tlb_lpid_guest(vc->kvm->arch.lpid);
- /* Clear the bit after the TLB flush */
- cpumask_clear_cpu(tmp, &vc->kvm->arch.need_tlb_flush);
- }
+ kvmppc_radix_check_need_tlb_flush(vc->kvm, pcpu, NULL);
}
/*
@@ -3868,11 +3908,10 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
struct kvm_vcpu *vcpu, u64 time_limit,
unsigned long lpcr)
{
- int trap, r, pcpu, pcpu0;
+ int trap, r, pcpu;
int srcu_idx;
struct kvmppc_vcore *vc;
struct kvm_nested_guest *nested = vcpu->arch.nested;
- unsigned long lpid;
trace_kvmppc_run_vcpu_enter(vcpu);
@@ -3945,22 +3984,8 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
vc->vcore_state = VCORE_RUNNING;
trace_kvmppc_run_core(vc, 0);
- lpid = vc->kvm->arch.lpid;
- if (nested)
- lpid = nested->shadow_lpid;
- mtspr(SPRN_LPID, lpid);
- isync();
-
- /* See comment above in kvmppc_run_core() about this */
- pcpu0 = pcpu;
- if (cpu_has_feature(CPU_FTR_ARCH_300))
- pcpu0 &= ~0x3UL;
-
- if (cpumask_test_cpu(pcpu0, &vc->kvm->arch.need_tlb_flush)) {
- radix__local_flush_tlb_lpid_guest(lpid);
- /* Clear the bit after the TLB flush */
- cpumask_clear_cpu(pcpu0, &vc->kvm->arch.need_tlb_flush);
- }
+ if (cpu_has_feature(CPU_FTR_HVMODE))
+ kvmppc_radix_check_need_tlb_flush(vc->kvm, pcpu, nested);
trace_hardirqs_on();
guest_enter_irqoff();
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 35f8111..1a8c40d 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -167,6 +167,9 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
if (err)
return H_PARAMETER;
+ if (l2_hv.vcpu_token >= NR_CPUS)
+ return H_PARAMETER;
+
/* translate lpid */
l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true);
if (!l2)
@@ -411,6 +414,8 @@ struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
goto out_free2;
gp->shadow_lpid = shadow_lpid;
+ memset(gp->prev_cpu, -1, sizeof(gp->prev_cpu));
+
return gp;
out_free2:
--
2.7.4
^ permalink raw reply related
* [PATCH v4 26/32] KVM: PPC: Book3S HV: Don't access HFSCR, LPIDR or LPCR when running nested
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
When running as a nested hypervisor, this avoids reading hypervisor
privileged registers (specifically HFSCR, LPIDR and LPCR) at startup;
instead reasonable default values are used. This also avoids writing
LPIDR in the single-vcpu entry/exit path.
Also, this removes the check for CPU_FTR_HVMODE in kvmppc_mmu_hv_init()
since its only caller already checks this.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_64_mmu_hv.c | 7 +++----
arch/powerpc/kvm/book3s_hv.c | 33 +++++++++++++++++++++------------
2 files changed, 24 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 68e14af..c615617 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -268,14 +268,13 @@ int kvmppc_mmu_hv_init(void)
{
unsigned long host_lpid, rsvd_lpid;
- if (!cpu_has_feature(CPU_FTR_HVMODE))
- return -EINVAL;
-
if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE))
return -EINVAL;
/* POWER7 has 10-bit LPIDs (12-bit in POWER8) */
- host_lpid = mfspr(SPRN_LPID);
+ host_lpid = 0;
+ if (cpu_has_feature(CPU_FTR_HVMODE))
+ host_lpid = mfspr(SPRN_LPID);
rsvd_lpid = LPID_RSVD;
kvmppc_init_lpid(rsvd_lpid + 1);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 53a967ea..4da9564 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2174,15 +2174,18 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
* Set the default HFSCR for the guest from the host value.
* This value is only used on POWER9.
* On POWER9, we want to virtualize the doorbell facility, so we
- * turn off the HFSCR bit, which causes those instructions to trap.
+ * don't set the HFSCR_MSGP bit, and that causes those instructions
+ * to trap and then we emulate them.
*/
- vcpu->arch.hfscr = mfspr(SPRN_HFSCR);
- if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+ vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB |
+ HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP;
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ vcpu->arch.hfscr &= mfspr(SPRN_HFSCR);
+ if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+ vcpu->arch.hfscr |= HFSCR_TM;
+ }
+ if (cpu_has_feature(CPU_FTR_TM_COMP))
vcpu->arch.hfscr |= HFSCR_TM;
- else if (!cpu_has_feature(CPU_FTR_TM_COMP))
- vcpu->arch.hfscr &= ~HFSCR_TM;
- if (cpu_has_feature(CPU_FTR_ARCH_300))
- vcpu->arch.hfscr &= ~HFSCR_MSGP;
kvmppc_mmu_book3s_hv_init(vcpu);
@@ -4001,8 +4004,10 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
- mtspr(SPRN_LPID, vc->kvm->arch.host_lpid);
- isync();
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ mtspr(SPRN_LPID, vc->kvm->arch.host_lpid);
+ isync();
+ }
trace_hardirqs_off();
set_irq_happened(trap);
@@ -4622,9 +4627,13 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
/* Init LPCR for virtual RMA mode */
- kvm->arch.host_lpid = mfspr(SPRN_LPID);
- kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
- lpcr &= LPCR_PECE | LPCR_LPES;
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ kvm->arch.host_lpid = mfspr(SPRN_LPID);
+ kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
+ lpcr &= LPCR_PECE | LPCR_LPES;
+ } else {
+ lpcr = 0;
+ }
lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
LPCR_VPM0 | LPCR_VPM1;
kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
--
2.7.4
^ permalink raw reply related
* [PATCH v4 28/32] KVM: PPC: Book3S HV: Sanitise hv_regs on nested guest entry
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
restore_hv_regs() is used to copy the hv_regs L1 wants to set to run the
nested (L2) guest into the vcpu structure. We need to sanitise these
values to ensure we don't let the L1 guest hypervisor do things we don't
want it to.
We don't let data address watchpoints or completed instruction address
breakpoints be set to match in hypervisor state.
We also don't let L1 enable features in the hypervisor facility status
and control register (HFSCR) for L2 which we have disabled for L1. That
is L2 will get the subset of features which the L0 hypervisor has
enabled for L1 and the features L1 wants to enable for L2. This could
mean we give L1 a hypervisor facility unavailable interrupt for a
facility it thinks it has enabled, however it shouldn't have enabled a
facility it itself doesn't have for the L2 guest.
We sanitise the registers when copying in the L2 hv_regs. We don't need
to sanitise when copying back the L1 hv_regs since these shouldn't be
able to contain invalid values as they're just what was copied out.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/reg.h | 1 +
arch/powerpc/kvm/book3s_hv_nested.c | 17 +++++++++++++++++
2 files changed, 18 insertions(+)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 6fda746..c9069897 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -415,6 +415,7 @@
#define HFSCR_DSCR __MASK(FSCR_DSCR_LG)
#define HFSCR_VECVSX __MASK(FSCR_VECVSX_LG)
#define HFSCR_FP __MASK(FSCR_FP_LG)
+#define HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56) /* interrupt cause */
#define SPRN_TAR 0x32f /* Target Address Register */
#define SPRN_LPCR 0x13E /* LPAR Control Register */
#define LPCR_VPM0 ASM_CONST(0x8000000000000000)
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 1a8c40d..f54f779 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -85,6 +85,22 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
}
}
+static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+{
+ /*
+ * Don't let L1 enable features for L2 which we've disabled for L1,
+ * but preserve the interrupt cause field.
+ */
+ hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
+
+ /* Don't let data address watchpoint match in hypervisor state */
+ hr->dawrx0 &= ~DAWRX_HYP;
+
+ /* Don't let completed instruction address breakpt match in HV state */
+ if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+ hr->ciabr &= ~CIABR_PRIV;
+}
+
static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -197,6 +213,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
LPCR_LPES | LPCR_MER;
lpcr = (vc->lpcr & ~mask) | (l2_hv.lpcr & mask);
+ sanitise_hv_regs(vcpu, &l2_hv);
restore_hv_regs(vcpu, &l2_hv);
vcpu->arch.ret = RESUME_GUEST;
--
2.7.4
^ permalink raw reply related
* [PATCH v4 27/32] KVM: PPC: Book3S HV: Add one-reg interface to virtual PTCR register
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
This adds a one-reg register identifier which can be used to read and
set the virtual PTCR for the guest. This register identifies the
address and size of the virtual partition table for the guest, which
contains information about the nested guests under this guest.
Migrating this value is the only extra requirement for migrating a
guest which has nested guests (assuming of course that the destination
host supports nested virtualization in the kvm-hv module).
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
Documentation/virtual/kvm/api.txt | 1 +
arch/powerpc/include/uapi/asm/kvm.h | 1 +
arch/powerpc/kvm/book3s_hv.c | 6 ++++++
3 files changed, 8 insertions(+)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index c664064..017d851 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1922,6 +1922,7 @@ registers, find a list below:
PPC | KVM_REG_PPC_TIDR | 64
PPC | KVM_REG_PPC_PSSCR | 64
PPC | KVM_REG_PPC_DEC_EXPIRY | 64
+ PPC | KVM_REG_PPC_PTCR | 64
PPC | KVM_REG_PPC_TM_GPR0 | 64
...
PPC | KVM_REG_PPC_TM_GPR31 | 64
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 1b32b56..8c876c1 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -634,6 +634,7 @@ struct kvm_ppc_cpu_char {
#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
+#define KVM_REG_PPC_PTCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 4da9564..7561c99 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1710,6 +1710,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_ONLINE:
*val = get_reg_val(id, vcpu->arch.online);
break;
+ case KVM_REG_PPC_PTCR:
+ *val = get_reg_val(id, vcpu->kvm->arch.l1_ptcr);
+ break;
default:
r = -EINVAL;
break;
@@ -1941,6 +1944,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
atomic_dec(&vcpu->arch.vcore->online_count);
vcpu->arch.online = i;
break;
+ case KVM_REG_PPC_PTCR:
+ vcpu->kvm->arch.l1_ptcr = set_reg_val(id, *val);
+ break;
default:
r = -EINVAL;
break;
--
2.7.4
^ permalink raw reply related
* [PATCH v4 29/32] KVM: PPC: Book3S HV: Handle differing endianness for H_ENTER_NESTED
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
The hcall H_ENTER_NESTED takes two parameters: the address in L1 guest
memory of a hv_regs struct and the address of a pt_regs struct. The
hcall requests the L0 hypervisor to use the register values in these
structs to run a L2 guest and to return the exit state of the L2 guest
in these structs. These are in the endianness of the L1 guest, rather
than being always big-endian as is usually the case for PAPR
hypercalls.
This is convenient because it means that the L1 guest can pass the
address of the regs field in its kvm_vcpu_arch struct. This also
improves performance slightly by avoiding the need for two copies of
the pt_regs struct.
When reading/writing these structures, this patch handles the case
where the endianness of the L1 guest differs from that of the L0
hypervisor, by byteswapping the structures after reading and before
writing them back.
Since all the fields of the pt_regs are of the same type, i.e.,
unsigned long, we treat it as an array of unsigned longs. The fields
of struct hv_guest_state are not all the same, so its fields are
byteswapped individually.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv_nested.c | 51 ++++++++++++++++++++++++++++++++++++-
1 file changed, 50 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index f54f779..8c0da00 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -50,6 +50,48 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
hr->ppr = vcpu->arch.ppr;
}
+static void byteswap_pt_regs(struct pt_regs *regs)
+{
+ unsigned long *addr = (unsigned long *) regs;
+
+ for (; addr < ((unsigned long *) (regs + 1)); addr++)
+ *addr = swab64(*addr);
+}
+
+static void byteswap_hv_regs(struct hv_guest_state *hr)
+{
+ hr->version = swab64(hr->version);
+ hr->lpid = swab32(hr->lpid);
+ hr->vcpu_token = swab32(hr->vcpu_token);
+ hr->lpcr = swab64(hr->lpcr);
+ hr->pcr = swab64(hr->pcr);
+ hr->amor = swab64(hr->amor);
+ hr->dpdes = swab64(hr->dpdes);
+ hr->hfscr = swab64(hr->hfscr);
+ hr->tb_offset = swab64(hr->tb_offset);
+ hr->dawr0 = swab64(hr->dawr0);
+ hr->dawrx0 = swab64(hr->dawrx0);
+ hr->ciabr = swab64(hr->ciabr);
+ hr->hdec_expiry = swab64(hr->hdec_expiry);
+ hr->purr = swab64(hr->purr);
+ hr->spurr = swab64(hr->spurr);
+ hr->ic = swab64(hr->ic);
+ hr->vtb = swab64(hr->vtb);
+ hr->hdar = swab64(hr->hdar);
+ hr->hdsisr = swab64(hr->hdsisr);
+ hr->heir = swab64(hr->heir);
+ hr->asdr = swab64(hr->asdr);
+ hr->srr0 = swab64(hr->srr0);
+ hr->srr1 = swab64(hr->srr1);
+ hr->sprg[0] = swab64(hr->sprg[0]);
+ hr->sprg[1] = swab64(hr->sprg[1]);
+ hr->sprg[2] = swab64(hr->sprg[2]);
+ hr->sprg[3] = swab64(hr->sprg[3]);
+ hr->pidr = swab64(hr->pidr);
+ hr->cfar = swab64(hr->cfar);
+ hr->ppr = swab64(hr->ppr);
+}
+
static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
struct hv_guest_state *hr)
{
@@ -174,6 +216,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
sizeof(struct hv_guest_state));
if (err)
return H_PARAMETER;
+ if (kvmppc_need_byteswap(vcpu))
+ byteswap_hv_regs(&l2_hv);
if (l2_hv.version != HV_GUEST_STATE_VERSION)
return H_P2;
@@ -182,7 +226,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
sizeof(struct pt_regs));
if (err)
return H_PARAMETER;
-
+ if (kvmppc_need_byteswap(vcpu))
+ byteswap_pt_regs(&l2_regs);
if (l2_hv.vcpu_token >= NR_CPUS)
return H_PARAMETER;
@@ -254,6 +299,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
kvmhv_put_nested(l2);
/* copy l2_hv_state and regs back to guest */
+ if (kvmppc_need_byteswap(vcpu)) {
+ byteswap_hv_regs(&l2_hv);
+ byteswap_pt_regs(&l2_regs);
+ }
err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
sizeof(struct hv_guest_state));
if (err)
--
2.7.4
^ permalink raw reply related
* [PATCH v4 30/32] KVM: PPC: Book3S HV: Allow HV module to load without hypervisor mode
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
With this, the KVM-HV module can be loaded in a guest running under
KVM-HV, and if the hypervisor supports nested virtualization, this
guest can now act as a nested hypervisor and run nested guests.
This also adds some checks to inform userspace that HPT guests are not
supported by nested hypervisors, and to prevent userspace from
configuring a guest to use HPT mode.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 20 ++++++++++++++++----
1 file changed, 16 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7561c99..7f89b22 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4214,6 +4214,10 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
{
struct kvm_ppc_one_seg_page_size *sps;
+ /* If we're a nested hypervisor, we only support radix guests */
+ if (kvmhv_on_pseries())
+ return -EINVAL;
+
/*
* POWER7, POWER8 and POWER9 all support 32 storage keys for data.
* POWER7 doesn't support keys for instruction accesses,
@@ -4799,11 +4803,15 @@ static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn,
static int kvmppc_core_check_processor_compat_hv(void)
{
- if (!cpu_has_feature(CPU_FTR_HVMODE) ||
- !cpu_has_feature(CPU_FTR_ARCH_206))
- return -EIO;
+ if (cpu_has_feature(CPU_FTR_HVMODE) &&
+ cpu_has_feature(CPU_FTR_ARCH_206))
+ return 0;
- return 0;
+ /* POWER9 in radix mode is capable of being a nested hypervisor. */
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled())
+ return 0;
+
+ return -EIO;
}
#ifdef CONFIG_KVM_XICS
@@ -5121,6 +5129,10 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
if (radix && !radix_enabled())
return -EINVAL;
+ /* If we're a nested hypervisor, we currently only support radix */
+ if (kvmhv_on_pseries() && !radix)
+ return -EINVAL;
+
mutex_lock(&kvm->lock);
if (radix != kvm_is_radix(kvm)) {
if (kvm->arch.mmu_ready) {
--
2.7.4
^ permalink raw reply related
* [PATCH v4 31/32] KVM: PPC: Book3S HV: Add nested shadow page tables to debugfs
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
This adds a list of valid shadow PTEs for each nested guest to
the 'radix' file for the guest in debugfs. This can be useful for
debugging.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 1 +
arch/powerpc/kvm/book3s_64_mmu_radix.c | 39 +++++++++++++++++++++++++++++---
arch/powerpc/kvm/book3s_hv_nested.c | 15 ++++++++++++
3 files changed, 52 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 1e96027..d11f73c 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -120,6 +120,7 @@ struct rmap_nested {
struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
bool create);
void kvmhv_put_nested(struct kvm_nested_guest *gp);
+int kvmhv_nested_next_lpid(struct kvm *kvm, int lpid);
/* Encoding of first parameter for H_TLB_INVALIDATE */
#define H_TLBIE_P1_ENC(ric, prs, r) (___PPC_RIC(ric) | ___PPC_PRS(prs) | \
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index ae0e3ed..43b21e8 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -1002,6 +1002,7 @@ struct debugfs_radix_state {
struct kvm *kvm;
struct mutex mutex;
unsigned long gpa;
+ int lpid;
int chars_left;
int buf_index;
char buf[128];
@@ -1043,6 +1044,7 @@ static ssize_t debugfs_radix_read(struct file *file, char __user *buf,
struct kvm *kvm;
unsigned long gpa;
pgd_t *pgt;
+ struct kvm_nested_guest *nested;
pgd_t pgd, *pgdp;
pud_t pud, *pudp;
pmd_t pmd, *pmdp;
@@ -1077,10 +1079,39 @@ static ssize_t debugfs_radix_read(struct file *file, char __user *buf,
}
gpa = p->gpa;
- pgt = kvm->arch.pgtable;
- while (len != 0 && gpa < RADIX_PGTABLE_RANGE) {
+ nested = NULL;
+ pgt = NULL;
+ while (len != 0 && p->lpid >= 0) {
+ if (gpa >= RADIX_PGTABLE_RANGE) {
+ gpa = 0;
+ pgt = NULL;
+ if (nested) {
+ kvmhv_put_nested(nested);
+ nested = NULL;
+ }
+ p->lpid = kvmhv_nested_next_lpid(kvm, p->lpid);
+ p->hdr = 0;
+ if (p->lpid < 0)
+ break;
+ }
+ if (!pgt) {
+ if (p->lpid == 0) {
+ pgt = kvm->arch.pgtable;
+ } else {
+ nested = kvmhv_get_nested(kvm, p->lpid, false);
+ if (!nested) {
+ gpa = RADIX_PGTABLE_RANGE;
+ continue;
+ }
+ pgt = nested->shadow_pgtable;
+ }
+ }
+ n = 0;
if (!p->hdr) {
- n = scnprintf(p->buf, sizeof(p->buf),
+ if (p->lpid > 0)
+ n = scnprintf(p->buf, sizeof(p->buf),
+ "\nNested LPID %d: ", p->lpid);
+ n += scnprintf(p->buf + n, sizeof(p->buf) - n,
"pgdir: %lx\n", (unsigned long)pgt);
p->hdr = 1;
goto copy;
@@ -1146,6 +1177,8 @@ static ssize_t debugfs_radix_read(struct file *file, char __user *buf,
}
}
p->gpa = gpa;
+ if (nested)
+ kvmhv_put_nested(nested);
out:
mutex_unlock(&p->mutex);
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 8c0da00..75b461d0 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -1263,3 +1263,18 @@ long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu)
mutex_unlock(&gp->tlb_lock);
return ret;
}
+
+int kvmhv_nested_next_lpid(struct kvm *kvm, int lpid)
+{
+ int ret = -1;
+
+ spin_lock(&kvm->mmu_lock);
+ while (++lpid <= kvm->arch.max_nested_lpid) {
+ if (kvm->arch.nested_guests[lpid]) {
+ ret = lpid;
+ break;
+ }
+ }
+ spin_unlock(&kvm->mmu_lock);
+ return ret;
+}
--
2.7.4
^ permalink raw reply related
* [PATCH v4 32/32] KVM: PPC: Book3S HV: Add a VM capability to enable nested virtualization
From: Paul Mackerras @ 2018-10-04 11:56 UTC (permalink / raw)
To: kvm, kvm-ppc; +Cc: linuxppc-dev, David Gibson
In-Reply-To: <1538654169-15602-1-git-send-email-paulus@ozlabs.org>
With this, userspace can enable a KVM-HV guest to run nested guests
under it.
The administrator can control whether any nested guests can be run;
setting the "nested" module parameter to false prevents any guests
becoming nested hypervisors (that is, any attempt to enable the nested
capability on a guest will fail). Guests which are already nested
hypervisors will continue to be so.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
Documentation/virtual/kvm/api.txt | 14 ++++++++++++++
arch/powerpc/include/asm/kvm_ppc.h | 1 +
arch/powerpc/kvm/book3s_hv.c | 19 +++++++++++++++++++
arch/powerpc/kvm/powerpc.c | 12 ++++++++++++
include/uapi/linux/kvm.h | 1 +
5 files changed, 47 insertions(+)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 017d851..a2d4832 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4522,6 +4522,20 @@ hpage module parameter is not set to 1, -EINVAL is returned.
While it is generally possible to create a huge page backed VM without
this capability, the VM will not be able to run.
+7.15 KVM_CAP_PPC_NESTED_HV
+
+Architectures: ppc
+Parameters: enable flag (0 to disable, non-zero to enable)
+Returns: 0 on success, -EINVAL when the implementation doesn't support
+nested-HV virtualization.
+
+HV-KVM on POWER9 and later systems allows for "nested-HV"
+virtualization, which provides a way for a guest VM to run guests that
+can run using the CPU's supervisor mode (privileged non-hypervisor
+state). Enabling this capability on a VM depends on the CPU having
+the necessary functionality and on the facility being enabled with a
+kvm-hv module parameter.
+
8. Other capabilities.
----------------------
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 245e564..80f0091 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -327,6 +327,7 @@ struct kvmppc_ops {
int (*set_smt_mode)(struct kvm *kvm, unsigned long mode,
unsigned long flags);
void (*giveup_ext)(struct kvm_vcpu *vcpu, ulong msr);
+ int (*enable_nested)(struct kvm *kvm, bool enable);
};
extern struct kvmppc_ops *kvmppc_hv_ops;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7f89b22..d3cc013 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -118,6 +118,11 @@ module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect, 0644);
MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
#endif
+/* If set, guests are allowed to create and control nested guests */
+static bool nested = true;
+module_param(nested, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(nested, "Enable nested virtualization (only on POWER9)");
+
/* If set, the threads on each CPU core have to be in the same MMU mode */
static bool no_mixing_hpt_and_radix;
@@ -5165,6 +5170,19 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
return err;
}
+static int kvmhv_enable_nested(struct kvm *kvm, bool enable)
+{
+ if (!nested)
+ return -EPERM;
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ return -ENODEV;
+
+ /* kvm == NULL means the caller is testing if the capability exists */
+ if (kvm)
+ kvm->arch.nested_enable = enable;
+ return 0;
+}
+
static struct kvmppc_ops kvm_ops_hv = {
.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
@@ -5204,6 +5222,7 @@ static struct kvmppc_ops kvm_ops_hv = {
.configure_mmu = kvmhv_configure_mmu,
.get_rmmu_info = kvmhv_get_rmmu_info,
.set_smt_mode = kvmhv_set_smt_mode,
+ .enable_nested = kvmhv_enable_nested,
};
static int kvm_init_subcore_bitmap(void)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index eba5756..449ae1d 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -596,6 +596,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_PPC_MMU_HASH_V3:
r = !!(hv_enabled && cpu_has_feature(CPU_FTR_ARCH_300));
break;
+ case KVM_CAP_PPC_NESTED_HV:
+ r = !!(hv_enabled && kvmppc_hv_ops->enable_nested &&
+ !kvmppc_hv_ops->enable_nested(NULL, false));
+ break;
#endif
case KVM_CAP_SYNC_MMU:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -2114,6 +2118,14 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
r = kvm->arch.kvm_ops->set_smt_mode(kvm, mode, flags);
break;
}
+
+ case KVM_CAP_PPC_NESTED_HV:
+ r = -EINVAL;
+ if (!is_kvmppc_hv_enabled(kvm) ||
+ !kvm->arch.kvm_ops->enable_nested)
+ break;
+ r = kvm->arch.kvm_ops->enable_nested(kvm, !!cap->args[0]);
+ break;
#endif
default:
r = -EINVAL;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 07548de..a6d5a46 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -952,6 +952,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_S390_HPAGE_1M 156
#define KVM_CAP_NESTED_STATE 157
#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_PPC_NESTED_HV 160
#ifdef KVM_CAP_IRQ_ROUTING
--
2.7.4
^ permalink raw reply related
* Re: [PATCH 1/7] macintosh: Use common code to access RTC
From: Geert Uytterhoeven @ 2018-10-04 13:05 UTC (permalink / raw)
To: Finn Thain
Cc: Arnd Bergmann, Linux Kernel Mailing List, linux-m68k,
Paul Mackerras, linuxppc-dev
In-Reply-To: <7a0748d8cd97964a99879a0b9f1c0243c677c7c3.1536709753.git.fthain@telegraphics.com.au>
On Wed, Sep 12, 2018 at 2:18 AM Finn Thain <fthain@telegraphics.com.au> wrote:
> Now that the 68k Mac port has adopted the via-pmu driver, the same RTC
> code can be shared between m68k and powerpc. Replace duplicated code in
> arch/powerpc and arch/m68k with common RTC accessors for Cuda and PMU.
>
> Drop the problematic WARN_ON which was introduced in commit 22db552b50fa
> ("powerpc/powermac: Fix rtc read/write functions").
>
> Tested-by: Stan Johnson <userm57@yahoo.com>
> Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
^ permalink raw reply
* [PATCH v4 0/6] arm64: dts: NXP: add basic dts file for LX2160A SoC
From: Vabhav Sharma @ 2018-10-04 1:03 UTC (permalink / raw)
To: sudeep.holla, oss, linux-kernel, devicetree, robh+dt,
mark.rutland, linuxppc-dev, linux-arm-kernel, mturquette, sboyd,
rjw, viresh.kumar, linux-clk, linux-pm, linux-kernel-owner,
catalin.marinas, will.deacon, gregkh, arnd, kstewart,
yamada.masahiro, leoyang.li, shawnguo
Cc: pankaj.bansal, udit.kumar, linux, Vabhav Sharma, V.Sethi
Changes for v4:
-Updated bindings for lx2160a clockgen and dcfg
-Modified commit message for lx2160a clockgen changes
-Updated interrupt property with macro definition
-Added required enable-method property to each core node with psci value
-Removed unused node syscon in device tree
-Removed blank lines in device tree fsl-lx2160a.dtsi
-Updated uart node compatible sbsa-uart first
-Added and defined vcc-supply property to temperature sensor node in
device tree fsl-lx2160a-rdb.dts
Changes for v3:
-Split clockgen support patch into below two patches:
- a)Updated array size of cmux_to_group[] with NUM_CMUX+1 to include -1
terminator and p4080 cmux_to_group[] array with -1 terminator
- b)Add clockgen support for lx2160a
Changes for v2:
- Modified cmux_to_group array to include -1 terminator
- Revert NUM_CMUX to original value 8 from 16
- Remove “As LX2160A is 16 core, so modified value for NUM_CMUX”
in patch "[PATCH 3/5] drivers: clk-qoriq: Add clockgen support for
lx2160a" description
- Populated cache properties for L1 and L2 cache in lx2160a device-tree.
- Removed reboot node from lx2160a device-tree as PSCI is implemented.
- Removed incorrect comment for timer node interrupt property in
lx2160a device-tree.
- Modified pmu node compatible property from "arm,armv8-pmuv3" to
"arm,cortex-a72-pmu" in lx2160a device-tree
- Non-standard aliases removed in lx2160a rdb board device-tree
- Updated i2c child nodes to generic name in lx2160a rdb device-tree.
Changes for v1:
- Add compatible string for LX2160A clockgen support
- Add compatible string to initialize LX2160A guts driver
- Add compatible string for LX2160A support in dt-bindings
- Add dts file to enable support for LX2160A SoC and LX2160A RDB
(Reference design board)
Vabhav Sharma (4):
dt-bindings: arm64: add compatible for LX2160A
soc/fsl/guts: Add compatible string for LX2160A
arm64: dts: add QorIQ LX2160A SoC support
arm64: dts: add LX2160ARDB board support
Yogesh Gaur (2):
clk: qoriq: increase array size of cmux_to_group
clk: qoriq: Add clockgen support for lx2160a
Documentation/devicetree/bindings/arm/fsl.txt | 14 +-
.../devicetree/bindings/clock/qoriq-clock.txt | 1 +
arch/arm64/boot/dts/freescale/Makefile | 1 +
arch/arm64/boot/dts/freescale/fsl-lx2160a-rdb.dts | 100 +++
arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 702 +++++++++++++++++++++
drivers/clk/clk-qoriq.c | 16 +-
drivers/cpufreq/qoriq-cpufreq.c | 1 +
drivers/soc/fsl/guts.c | 1 +
8 files changed, 833 insertions(+), 3 deletions(-)
create mode 100644 arch/arm64/boot/dts/freescale/fsl-lx2160a-rdb.dts
create mode 100644 arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
--
2.7.4
^ permalink raw reply
* [PATCH v4 1/6] dt-bindings: arm64: add compatible for LX2160A
From: Vabhav Sharma @ 2018-10-04 1:03 UTC (permalink / raw)
To: sudeep.holla, oss, linux-kernel, devicetree, robh+dt,
mark.rutland, linuxppc-dev, linux-arm-kernel, mturquette, sboyd,
rjw, viresh.kumar, linux-clk, linux-pm, linux-kernel-owner,
catalin.marinas, will.deacon, gregkh, arnd, kstewart,
yamada.masahiro, leoyang.li, shawnguo
Cc: pankaj.bansal, udit.kumar, linux, Vabhav Sharma, V.Sethi
In-Reply-To: <1538615031-7507-1-git-send-email-vabhav.sharma@nxp.com>
Add compatible for LX2160A SoC,QDS and RDB board
Add lx2160a compatible for clockgen and dcfg
Signed-off-by: Vabhav Sharma <vabhav.sharma@nxp.com>
Reviewed-by: Rob Herring <robh@kernel.org>
---
Documentation/devicetree/bindings/arm/fsl.txt | 14 +++++++++++++-
Documentation/devicetree/bindings/clock/qoriq-clock.txt | 1 +
2 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/arm/fsl.txt b/Documentation/devicetree/bindings/arm/fsl.txt
index cdb9dd7..4f5d55b 100644
--- a/Documentation/devicetree/bindings/arm/fsl.txt
+++ b/Documentation/devicetree/bindings/arm/fsl.txt
@@ -126,7 +126,7 @@ core start address and release the secondary core from holdoff and startup.
- compatible: Should contain a chip-specific compatible string,
Chip-specific strings are of the form "fsl,<chip>-dcfg",
The following <chip>s are known to be supported:
- ls1012a, ls1021a, ls1043a, ls1046a, ls2080a.
+ ls1012a, ls1021a, ls1043a, ls1046a, ls2080a, lx2160a.
- reg : should contain base address and length of DCFG memory-mapped registers
@@ -218,3 +218,15 @@ Required root node properties:
LS2088A ARMv8 based RDB Board
Required root node properties:
- compatible = "fsl,ls2088a-rdb", "fsl,ls2088a";
+
+LX2160A SoC
+Required root node properties:
+ - compatible = "fsl,lx2160a";
+
+LX2160A ARMv8 based QDS Board
+Required root node properties:
+ - compatible = "fsl,lx2160a-qds", "fsl,lx2160a";
+
+LX2160A ARMv8 based RDB Board
+Required root node properties:
+ - compatible = "fsl,lx2160a-rdb", "fsl,lx2160a";
diff --git a/Documentation/devicetree/bindings/clock/qoriq-clock.txt b/Documentation/devicetree/bindings/clock/qoriq-clock.txt
index 97f46ad..3fb9995 100644
--- a/Documentation/devicetree/bindings/clock/qoriq-clock.txt
+++ b/Documentation/devicetree/bindings/clock/qoriq-clock.txt
@@ -37,6 +37,7 @@ Required properties:
* "fsl,ls1046a-clockgen"
* "fsl,ls1088a-clockgen"
* "fsl,ls2080a-clockgen"
+ * "fsl,lx2160a-clockgen"
Chassis-version clock strings include:
* "fsl,qoriq-clockgen-1.0": for chassis 1.0 clocks
* "fsl,qoriq-clockgen-2.0": for chassis 2.0 clocks
--
2.7.4
^ permalink raw reply related
* [PATCH v4 2/6] soc/fsl/guts: Add compatible string for LX2160A
From: Vabhav Sharma @ 2018-10-04 1:03 UTC (permalink / raw)
To: sudeep.holla, oss, linux-kernel, devicetree, robh+dt,
mark.rutland, linuxppc-dev, linux-arm-kernel, mturquette, sboyd,
rjw, viresh.kumar, linux-clk, linux-pm, linux-kernel-owner,
catalin.marinas, will.deacon, gregkh, arnd, kstewart,
yamada.masahiro, leoyang.li, shawnguo
Cc: pankaj.bansal, udit.kumar, linux, Vabhav Sharma, V.Sethi
In-Reply-To: <1538615031-7507-1-git-send-email-vabhav.sharma@nxp.com>
Adding compatible string "lx2160a-dcfg" to
initialize guts driver for lx2160
Signed-off-by: Vabhav Sharma <vabhav.sharma@nxp.com>
---
drivers/soc/fsl/guts.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/soc/fsl/guts.c b/drivers/soc/fsl/guts.c
index 302e0c8..5e1e633 100644
--- a/drivers/soc/fsl/guts.c
+++ b/drivers/soc/fsl/guts.c
@@ -222,6 +222,7 @@ static const struct of_device_id fsl_guts_of_match[] = {
{ .compatible = "fsl,ls1088a-dcfg", },
{ .compatible = "fsl,ls1012a-dcfg", },
{ .compatible = "fsl,ls1046a-dcfg", },
+ { .compatible = "fsl,lx2160a-dcfg", },
{}
};
MODULE_DEVICE_TABLE(of, fsl_guts_of_match);
--
2.7.4
^ permalink raw reply related
* [PATCH v4 3/6] clk: qoriq: increase array size of cmux_to_group
From: Vabhav Sharma @ 2018-10-04 1:03 UTC (permalink / raw)
To: sudeep.holla, oss, linux-kernel, devicetree, robh+dt,
mark.rutland, linuxppc-dev, linux-arm-kernel, mturquette, sboyd,
rjw, viresh.kumar, linux-clk, linux-pm, linux-kernel-owner,
catalin.marinas, will.deacon, gregkh, arnd, kstewart,
yamada.masahiro, leoyang.li, shawnguo
Cc: Yogesh Gaur, udit.kumar, pankaj.bansal, linux, V.Sethi,
Vabhav Sharma
In-Reply-To: <1538615031-7507-1-git-send-email-vabhav.sharma@nxp.com>
From: Yogesh Gaur <yogeshnarayan.gaur@nxp.com>
Increase size of cmux_to_group array, to accomdate entry of
-1 termination.
Added -1, terminated, entry for 4080_cmux_grpX.
Signed-off-by: Yogesh Gaur <yogeshnarayan.gaur@nxp.com>
Signed-off-by: Vabhav Sharma <vabhav.sharma@nxp.com>
---
drivers/clk/clk-qoriq.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index 3a1812f..e152bfb 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -79,7 +79,7 @@ struct clockgen_chipinfo {
const struct clockgen_muxinfo *cmux_groups[2];
const struct clockgen_muxinfo *hwaccel[NUM_HWACCEL];
void (*init_periph)(struct clockgen *cg);
- int cmux_to_group[NUM_CMUX]; /* -1 terminates if fewer than NUM_CMUX */
+ int cmux_to_group[NUM_CMUX+1]; /* array should be -1 terminated */
u32 pll_mask; /* 1 << n bit set if PLL n is valid */
u32 flags; /* CG_xxx */
};
@@ -601,7 +601,7 @@ static const struct clockgen_chipinfo chipinfo[] = {
&p4080_cmux_grp1, &p4080_cmux_grp2
},
.cmux_to_group = {
- 0, 0, 0, 0, 1, 1, 1, 1
+ 0, 0, 0, 0, 1, 1, 1, 1, -1
},
.pll_mask = 0x1f,
},
--
2.7.4
^ permalink raw reply related
* [PATCH v4 4/6] clk: qoriq: Add clockgen support for lx2160a
From: Vabhav Sharma @ 2018-10-04 1:03 UTC (permalink / raw)
To: sudeep.holla, oss, linux-kernel, devicetree, robh+dt,
mark.rutland, linuxppc-dev, linux-arm-kernel, mturquette, sboyd,
rjw, viresh.kumar, linux-clk, linux-pm, linux-kernel-owner,
catalin.marinas, will.deacon, gregkh, arnd, kstewart,
yamada.masahiro, leoyang.li, shawnguo
Cc: Yogesh Gaur, Tang Yuantian, udit.kumar, pankaj.bansal, linux,
V.Sethi, Vabhav Sharma
In-Reply-To: <1538615031-7507-1-git-send-email-vabhav.sharma@nxp.com>
From: Yogesh Gaur <yogeshnarayan.gaur@nxp.com>
Add clockgen support for lx2160a.
Added entry for compat 'fsl,lx2160a-clockgen'.
Signed-off-by: Tang Yuantian <andy.tang@nxp.com>
Signed-off-by: Yogesh Gaur <yogeshnarayan.gaur@nxp.com>
Signed-off-by: Vabhav Sharma <vabhav.sharma@nxp.com>
Acked-by: Stephen Boyd <sboyd@kernel.org>
---
drivers/clk/clk-qoriq.c | 12 ++++++++++++
drivers/cpufreq/qoriq-cpufreq.c | 1 +
2 files changed, 13 insertions(+)
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index e152bfb..99675de 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -570,6 +570,17 @@ static const struct clockgen_chipinfo chipinfo[] = {
.flags = CG_VER3 | CG_LITTLE_ENDIAN,
},
{
+ .compat = "fsl,lx2160a-clockgen",
+ .cmux_groups = {
+ &clockgen2_cmux_cga12, &clockgen2_cmux_cgb
+ },
+ .cmux_to_group = {
+ 0, 0, 0, 0, 1, 1, 1, 1, -1
+ },
+ .pll_mask = 0x37,
+ .flags = CG_VER3 | CG_LITTLE_ENDIAN,
+ },
+ {
.compat = "fsl,p2041-clockgen",
.guts_compat = "fsl,qoriq-device-config-1.0",
.init_periph = p2041_init_periph,
@@ -1424,6 +1435,7 @@ CLK_OF_DECLARE(qoriq_clockgen_ls1043a, "fsl,ls1043a-clockgen", clockgen_init);
CLK_OF_DECLARE(qoriq_clockgen_ls1046a, "fsl,ls1046a-clockgen", clockgen_init);
CLK_OF_DECLARE(qoriq_clockgen_ls1088a, "fsl,ls1088a-clockgen", clockgen_init);
CLK_OF_DECLARE(qoriq_clockgen_ls2080a, "fsl,ls2080a-clockgen", clockgen_init);
+CLK_OF_DECLARE(qoriq_clockgen_lx2160a, "fsl,lx2160a-clockgen", clockgen_init);
/* Legacy nodes */
CLK_OF_DECLARE(qoriq_sysclk_1, "fsl,qoriq-sysclk-1.0", sysclk_init);
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 3d773f6..83921b7 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -295,6 +295,7 @@ static const struct of_device_id node_matches[] __initconst = {
{ .compatible = "fsl,ls1046a-clockgen", },
{ .compatible = "fsl,ls1088a-clockgen", },
{ .compatible = "fsl,ls2080a-clockgen", },
+ { .compatible = "fsl,lx2160a-clockgen", },
{ .compatible = "fsl,p4080-clockgen", },
{ .compatible = "fsl,qoriq-clockgen-1.0", },
{ .compatible = "fsl,qoriq-clockgen-2.0", },
--
2.7.4
^ permalink raw reply related
* [PATCH v4 5/6] arm64: dts: add QorIQ LX2160A SoC support
From: Vabhav Sharma @ 2018-10-04 1:03 UTC (permalink / raw)
To: sudeep.holla, oss, linux-kernel, devicetree, robh+dt,
mark.rutland, linuxppc-dev, linux-arm-kernel, mturquette, sboyd,
rjw, viresh.kumar, linux-clk, linux-pm, linux-kernel-owner,
catalin.marinas, will.deacon, gregkh, arnd, kstewart,
yamada.masahiro, leoyang.li, shawnguo
Cc: Yogesh Gaur, udit.kumar, Priyanka Jain, pankaj.bansal,
Zhang Ying-22455, linux, Ramneek Mehresh, V.Sethi, Vabhav Sharma,
Nipun Gupta, Sriram Dash
In-Reply-To: <1538615031-7507-1-git-send-email-vabhav.sharma@nxp.com>
LX2160A SoC is based on Layerscape Chassis Generation 3.2 Architecture.
LX2160A features an advanced 16 64-bit ARM v8 CortexA72 processor cores
in 8 cluster, CCN508, GICv3,two 64-bit DDR4 memory controller, 8 I2C
controllers, 3 dspi, 2 esdhc,2 USB 3.0, mmu 500, 3 SATA, 4 PL011 SBSA
UARTs etc.
Signed-off-by: Ramneek Mehresh <ramneek.mehresh@nxp.com>
Signed-off-by: Zhang Ying-22455 <ying.zhang22455@nxp.com>
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
Signed-off-by: Priyanka Jain <priyanka.jain@nxp.com>
Signed-off-by: Yogesh Gaur <yogeshnarayan.gaur@nxp.com>
Signed-off-by: Sriram Dash <sriram.dash@nxp.com>
Signed-off-by: Vabhav Sharma <vabhav.sharma@nxp.com>
---
arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 702 +++++++++++++++++++++++++
1 file changed, 702 insertions(+)
create mode 100644 arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
new file mode 100644
index 0000000..c758268
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -0,0 +1,702 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Device Tree Include file for Layerscape-LX2160A family SoC.
+//
+// Copyright 2018 NXP
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/memreserve/ 0x80000000 0x00010000;
+
+/ {
+ compatible = "fsl,lx2160a";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ // 8 clusters having 2 Cortex-A72 cores each
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x0>;
+ clocks = <&clockgen 1 0>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster0_l2>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x1>;
+ clocks = <&clockgen 1 0>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster0_l2>;
+ };
+
+ cpu@100 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x100>;
+ clocks = <&clockgen 1 1>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster1_l2>;
+ };
+
+ cpu@101 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x101>;
+ clocks = <&clockgen 1 1>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster1_l2>;
+ };
+
+ cpu@200 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x200>;
+ clocks = <&clockgen 1 2>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster2_l2>;
+ };
+
+ cpu@201 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x201>;
+ clocks = <&clockgen 1 2>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster2_l2>;
+ };
+
+ cpu@300 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x300>;
+ clocks = <&clockgen 1 3>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster3_l2>;
+ };
+
+ cpu@301 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x301>;
+ clocks = <&clockgen 1 3>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster3_l2>;
+ };
+
+ cpu@400 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x400>;
+ clocks = <&clockgen 1 4>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster4_l2>;
+ };
+
+ cpu@401 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x401>;
+ clocks = <&clockgen 1 4>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster4_l2>;
+ };
+
+ cpu@500 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x500>;
+ clocks = <&clockgen 1 5>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster5_l2>;
+ };
+
+ cpu@501 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x501>;
+ clocks = <&clockgen 1 5>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster5_l2>;
+ };
+
+ cpu@600 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x600>;
+ clocks = <&clockgen 1 6>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster6_l2>;
+ };
+
+ cpu@601 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x601>;
+ clocks = <&clockgen 1 6>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster6_l2>;
+ };
+
+ cpu@700 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x700>;
+ clocks = <&clockgen 1 7>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster7_l2>;
+ };
+
+ cpu@701 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a72";
+ enable-method = "psci";
+ reg = <0x701>;
+ clocks = <&clockgen 1 7>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <128>;
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <192>;
+ next-level-cache = <&cluster7_l2>;
+ };
+
+ cluster0_l2: l2-cache0 {
+ compatible = "cache";
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-level = <2>;
+ };
+
+ cluster1_l2: l2-cache1 {
+ compatible = "cache";
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-level = <2>;
+ };
+
+ cluster2_l2: l2-cache2 {
+ compatible = "cache";
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-level = <2>;
+ };
+
+ cluster3_l2: l2-cache3 {
+ compatible = "cache";
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-level = <2>;
+ };
+
+ cluster4_l2: l2-cache4 {
+ compatible = "cache";
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-level = <2>;
+ };
+
+ cluster5_l2: l2-cache5 {
+ compatible = "cache";
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-level = <2>;
+ };
+
+ cluster6_l2: l2-cache6 {
+ compatible = "cache";
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-level = <2>;
+ };
+
+ cluster7_l2: l2-cache7 {
+ compatible = "cache";
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-level = <2>;
+ };
+ };
+
+ gic: interrupt-controller@6000000 {
+ compatible = "arm,gic-v3";
+ reg = <0x0 0x06000000 0 0x10000>, // GIC Dist
+ <0x0 0x06200000 0 0x200000>, // GICR (RD_base +
+ // SGI_base)
+ <0x0 0x0c0c0000 0 0x2000>, // GICC
+ <0x0 0x0c0d0000 0 0x1000>, // GICH
+ <0x0 0x0c0e0000 0 0x20000>; // GICV
+ #interrupt-cells = <3>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+ interrupt-controller;
+ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+
+ its: gic-its@6020000 {
+ compatible = "arm,gic-v3-its";
+ msi-controller;
+ reg = <0x0 0x6020000 0 0x20000>;
+ };
+ };
+
+ timer {
+ compatible = "arm,armv8-timer";
+ interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_PPI 10 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ pmu {
+ compatible = "arm,cortex-a72-pmu";
+ interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>;
+ };
+
+ psci {
+ compatible = "arm,psci-0.2";
+ method = "smc";
+ };
+
+ memory@80000000 {
+ // DRAM space - 1, size : 2 GB DRAM
+ device_type = "memory";
+ reg = <0x00000000 0x80000000 0 0x80000000>;
+ };
+
+ ddr1: memory-controller@1080000 {
+ compatible = "fsl,qoriq-memory-controller";
+ reg = <0x0 0x1080000 0x0 0x1000>;
+ interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
+ little-endian;
+ };
+
+ ddr2: memory-controller@1090000 {
+ compatible = "fsl,qoriq-memory-controller";
+ reg = <0x0 0x1090000 0x0 0x1000>;
+ interrupts = <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>;
+ little-endian;
+ };
+
+ sysclk: sysclk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <100000000>;
+ clock-output-names = "sysclk";
+ };
+
+ soc {
+ compatible = "simple-bus";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ clockgen: clocking@1300000 {
+ compatible = "fsl,lx2160a-clockgen";
+ reg = <0 0x1300000 0 0xa0000>;
+ #clock-cells = <2>;
+ clocks = <&sysclk>;
+ };
+
+ crypto: crypto@8000000 {
+ compatible = "fsl,sec-v5.0", "fsl,sec-v4.0";
+ fsl,sec-era = <10>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <0x0 0x00 0x8000000 0x100000>;
+ reg = <0x00 0x8000000 0x0 0x100000>;
+ interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
+ status = "disabled";
+
+ sec_jr0: jr@10000 {
+ compatible = "fsl,sec-v5.0-job-ring",
+ "fsl,sec-v4.0-job-ring";
+ reg = <0x10000 0x10000>;
+ interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ sec_jr1: jr@20000 {
+ compatible = "fsl,sec-v5.0-job-ring",
+ "fsl,sec-v4.0-job-ring";
+ reg = <0x20000 0x10000>;
+ interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ sec_jr2: jr@30000 {
+ compatible = "fsl,sec-v5.0-job-ring",
+ "fsl,sec-v4.0-job-ring";
+ reg = <0x30000 0x10000>;
+ interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ sec_jr3: jr@40000 {
+ compatible = "fsl,sec-v5.0-job-ring",
+ "fsl,sec-v4.0-job-ring";
+ reg = <0x40000 0x10000>;
+ interrupts = <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+ };
+ };
+
+ dcfg: dcfg@1e00000 {
+ compatible = "fsl,lx2160a-dcfg", "syscon";
+ reg = <0x0 0x1e00000 0x0 0x10000>;
+ little-endian;
+ };
+
+ gpio0: gpio@2300000 {
+ compatible = "fsl,qoriq-gpio";
+ reg = <0x0 0x2300000 0x0 0x10000>;
+ interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
+ gpio-controller;
+ little-endian;
+ #gpio-cells = <2>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ };
+
+ gpio1: gpio@2310000 {
+ compatible = "fsl,qoriq-gpio";
+ reg = <0x0 0x2310000 0x0 0x10000>;
+ interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
+ gpio-controller;
+ little-endian;
+ #gpio-cells = <2>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ };
+
+ gpio2: gpio@2320000 {
+ compatible = "fsl,qoriq-gpio";
+ reg = <0x0 0x2320000 0x0 0x10000>;
+ interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+ gpio-controller;
+ little-endian;
+ #gpio-cells = <2>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ };
+
+ gpio3: gpio@2330000 {
+ compatible = "fsl,qoriq-gpio";
+ reg = <0x0 0x2330000 0x0 0x10000>;
+ interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+ gpio-controller;
+ little-endian;
+ #gpio-cells = <2>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ };
+
+ i2c0: i2c@2000000 {
+ compatible = "fsl,vf610-i2c";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x2000000 0x0 0x10000>;
+ interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+ clock-names = "i2c";
+ clocks = <&clockgen 4 7>;
+ fsl-scl-gpio = <&gpio2 15 0>;
+ status = "disabled";
+ };
+
+ i2c1: i2c@2010000 {
+ compatible = "fsl,vf610-i2c";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x2010000 0x0 0x10000>;
+ interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+ clock-names = "i2c";
+ clocks = <&clockgen 4 7>;
+ status = "disabled";
+ };
+
+ i2c2: i2c@2020000 {
+ compatible = "fsl,vf610-i2c";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x2020000 0x0 0x10000>;
+ interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+ clock-names = "i2c";
+ clocks = <&clockgen 4 7>;
+ status = "disabled";
+ };
+
+ i2c3: i2c@2030000 {
+ compatible = "fsl,vf610-i2c";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x2030000 0x0 0x10000>;
+ interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+ clock-names = "i2c";
+ clocks = <&clockgen 4 7>;
+ status = "disabled";
+ };
+
+ i2c4: i2c@2040000 {
+ compatible = "fsl,vf610-i2c";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x2040000 0x0 0x10000>;
+ interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
+ clock-names = "i2c";
+ clocks = <&clockgen 4 7>;
+ fsl-scl-gpio = <&gpio2 16 0>;
+ status = "disabled";
+ };
+
+ i2c5: i2c@2050000 {
+ compatible = "fsl,vf610-i2c";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x2050000 0x0 0x10000>;
+ interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
+ clock-names = "i2c";
+ clocks = <&clockgen 4 7>;
+ status = "disabled";
+ };
+
+ i2c6: i2c@2060000 {
+ compatible = "fsl,vf610-i2c";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x2060000 0x0 0x10000>;
+ interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+ clock-names = "i2c";
+ clocks = <&clockgen 4 7>;
+ status = "disabled";
+ };
+
+ i2c7: i2c@2070000 {
+ compatible = "fsl,vf610-i2c";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x2070000 0x0 0x10000>;
+ interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+ clock-names = "i2c";
+ clocks = <&clockgen 4 7>;
+ status = "disabled";
+ };
+
+ uart0: serial@21c0000 {
+ device_type = "serial";
+ compatible = "arm,sbsa-uart","arm,pl011";
+ reg = <0x0 0x21c0000 0x0 0x1000>;
+ interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+ current-speed = <115200>;
+ status = "disabled";
+ };
+
+ uart1: serial@21d0000 {
+ device_type = "serial";
+ compatible = "arm,sbsa-uart","arm,pl011";
+ reg = <0x0 0x21d0000 0x0 0x1000>;
+ interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+ current-speed = <115200>;
+ status = "disabled";
+ };
+
+ uart2: serial@21e0000 {
+ device_type = "serial";
+ compatible = "arm,sbsa-uart","arm,pl011";
+ reg = <0x0 0x21e0000 0x0 0x1000>;
+ interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
+ current-speed = <115200>;
+ status = "disabled";
+ };
+
+ uart3: serial@21f0000 {
+ device_type = "serial";
+ compatible = "arm,sbsa-uart","arm,pl011";
+ reg = <0x0 0x21f0000 0x0 0x1000>;
+ interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+ current-speed = <115200>;
+ status = "disabled";
+ };
+
+ smmu: iommu@5000000 {
+ compatible = "arm,mmu-500";
+ reg = <0 0x5000000 0 0x800000>;
+ #iommu-cells = <1>;
+ #global-interrupts = <14>;
+ interrupts = <0 13 4>, // global secure fault
+ <0 14 4>, // combined secure interrupt
+ <0 15 4>, // global non-secure fault
+ <0 16 4>, // combined non-secure interrupt
+ // performance counter interrupts 0-9
+ <0 211 4>, <0 212 4>,
+ <0 213 4>, <0 214 4>,
+ <0 215 4>, <0 216 4>,
+ <0 217 4>, <0 218 4>,
+ <0 219 4>, <0 220 4>,
+ // per context interrupt, 64 interrupts
+ <0 146 4>, <0 147 4>,
+ <0 148 4>, <0 149 4>,
+ <0 150 4>, <0 151 4>,
+ <0 152 4>, <0 153 4>,
+ <0 154 4>, <0 155 4>,
+ <0 156 4>, <0 157 4>,
+ <0 158 4>, <0 159 4>,
+ <0 160 4>, <0 161 4>,
+ <0 162 4>, <0 163 4>,
+ <0 164 4>, <0 165 4>,
+ <0 166 4>, <0 167 4>,
+ <0 168 4>, <0 169 4>,
+ <0 170 4>, <0 171 4>,
+ <0 172 4>, <0 173 4>,
+ <0 174 4>, <0 175 4>,
+ <0 176 4>, <0 177 4>,
+ <0 178 4>, <0 179 4>,
+ <0 180 4>, <0 181 4>,
+ <0 182 4>, <0 183 4>,
+ <0 184 4>, <0 185 4>,
+ <0 186 4>, <0 187 4>,
+ <0 188 4>, <0 189 4>,
+ <0 190 4>, <0 191 4>,
+ <0 192 4>, <0 193 4>,
+ <0 194 4>, <0 195 4>,
+ <0 196 4>, <0 197 4>,
+ <0 198 4>, <0 199 4>,
+ <0 200 4>, <0 201 4>,
+ <0 202 4>, <0 203 4>,
+ <0 204 4>, <0 205 4>,
+ <0 206 4>, <0 207 4>,
+ <0 208 4>, <0 209 4>;
+ dma-coherent;
+ };
+
+ usb0: usb3@3100000 {
+ compatible = "snps,dwc3";
+ reg = <0x0 0x3100000 0x0 0x10000>;
+ interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
+ dr_mode = "host";
+ snps,quirk-frame-length-adjustment = <0x20>;
+ snps,dis_rxdet_inp3_quirk;
+ status = "disabled";
+ };
+
+ usb1: usb3@3110000 {
+ compatible = "snps,dwc3";
+ reg = <0x0 0x3110000 0x0 0x10000>;
+ interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
+ dr_mode = "host";
+ snps,quirk-frame-length-adjustment = <0x20>;
+ snps,dis_rxdet_inp3_quirk;
+ status = "disabled";
+ };
+
+ watchdog@23a0000 {
+ compatible = "arm,sbsa-gwdt";
+ reg = <0x0 0x23a0000 0 0x1000>,
+ <0x0 0x2390000 0 0x1000>;
+ interrupts = <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
+ timeout-sec = <30>;
+ };
+ };
+};
--
2.7.4
^ permalink raw reply related
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