aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/kvm')
-rw-r--r--arch/arm/kvm/Kconfig2
-rw-r--r--arch/arm/kvm/arm.c11
-rw-r--r--arch/arm/kvm/coproc.c84
-rw-r--r--arch/arm/kvm/coproc.h14
-rw-r--r--arch/arm/kvm/coproc_a15.c2
-rw-r--r--arch/arm/kvm/coproc_a7.c2
-rw-r--r--arch/arm/kvm/guest.c1
-rw-r--r--arch/arm/kvm/handle_exit.c10
-rw-r--r--arch/arm/kvm/interrupts.S11
-rw-r--r--arch/arm/kvm/interrupts_head.S21
-rw-r--r--arch/arm/kvm/mmu.c125
-rw-r--r--arch/arm/kvm/psci.c235
12 files changed, 445 insertions, 73 deletions
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 466bd299b1a..4be5bb150bd 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -23,7 +23,7 @@ config KVM
select HAVE_KVM_CPU_RELAX_INTERCEPT
select KVM_MMIO
select KVM_ARM_HOST
- depends on ARM_VIRT_EXT && ARM_LPAE
+ depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN
---help---
Support hosting virtualized guest machines. You will also
need to select one or more of the processor modules below.
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1d8248ea566..3c82b37c0f9 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -197,6 +197,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
case KVM_CAP_ONE_REG:
case KVM_CAP_ARM_PSCI:
+ case KVM_CAP_ARM_PSCI_0_2:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
@@ -878,7 +879,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
unsigned long cmd,
void *v)
{
- if (cmd == CPU_PM_EXIT) {
+ if (cmd == CPU_PM_EXIT &&
+ __hyp_get_vectors() == hyp_default_vectors) {
cpu_init_hyp_mode(NULL);
return NOTIFY_OK;
}
@@ -1050,21 +1052,26 @@ int kvm_arch_init(void *opaque)
}
}
+ cpu_notifier_register_begin();
+
err = init_hyp_mode();
if (err)
goto out_err;
- err = register_cpu_notifier(&hyp_init_cpu_nb);
+ err = __register_cpu_notifier(&hyp_init_cpu_nb);
if (err) {
kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
goto out_err;
}
+ cpu_notifier_register_done();
+
hyp_cpu_pm_init();
kvm_coproc_table_init();
return 0;
out_err:
+ cpu_notifier_register_done();
return err;
}
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 78c0885d650..c58a35116f6 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -23,6 +23,7 @@
#include <asm/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
#include <trace/events/kvm.h>
@@ -205,6 +206,44 @@ done:
}
/*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r)
+{
+ BUG_ON(!p->is_write);
+
+ vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
+ if (p->is_64bit)
+ vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
+
+ return true;
+}
+
+/*
+ * SCTLR accessor. Only called as long as HCR_TVM is set. If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ *
+ * Used by the cpu-specific code.
+ */
+bool access_sctlr(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r)
+{
+ access_vm_reg(vcpu, p, r);
+
+ if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */
+ vcpu->arch.hcr &= ~HCR_TVM;
+ stage2_flush_vm(vcpu->kvm);
+ }
+
+ return true;
+}
+
+/*
* We could trap ID_DFR0 and tell the guest we don't support performance
* monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was
* NAKed, so it will read the PMCR anyway.
@@ -261,33 +300,36 @@ static const struct coproc_reg cp15_regs[] = {
{ CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32,
NULL, reset_val, c1_CPACR, 0x00000000 },
- /* TTBR0/TTBR1: swapped by interrupt.S. */
- { CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
- { CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
-
- /* TTBCR: swapped by interrupt.S. */
+ /* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */
+ { CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 },
+ { CRn(2), CRm( 0), Op1( 0), Op2( 0), is32,
+ access_vm_reg, reset_unknown, c2_TTBR0 },
+ { CRn(2), CRm( 0), Op1( 0), Op2( 1), is32,
+ access_vm_reg, reset_unknown, c2_TTBR1 },
{ CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32,
- NULL, reset_val, c2_TTBCR, 0x00000000 },
+ access_vm_reg, reset_val, c2_TTBCR, 0x00000000 },
+ { CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 },
+
/* DACR: swapped by interrupt.S. */
{ CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c3_DACR },
+ access_vm_reg, reset_unknown, c3_DACR },
/* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */
{ CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c5_DFSR },
+ access_vm_reg, reset_unknown, c5_DFSR },
{ CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32,
- NULL, reset_unknown, c5_IFSR },
+ access_vm_reg, reset_unknown, c5_IFSR },
{ CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c5_ADFSR },
+ access_vm_reg, reset_unknown, c5_ADFSR },
{ CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32,
- NULL, reset_unknown, c5_AIFSR },
+ access_vm_reg, reset_unknown, c5_AIFSR },
/* DFAR/IFAR: swapped by interrupt.S. */
{ CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c6_DFAR },
+ access_vm_reg, reset_unknown, c6_DFAR },
{ CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32,
- NULL, reset_unknown, c6_IFAR },
+ access_vm_reg, reset_unknown, c6_IFAR },
/* PAR swapped by interrupt.S */
{ CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
@@ -324,9 +366,15 @@ static const struct coproc_reg cp15_regs[] = {
/* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */
{ CRn(10), CRm( 2), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c10_PRRR},
+ access_vm_reg, reset_unknown, c10_PRRR},
{ CRn(10), CRm( 2), Op1( 0), Op2( 1), is32,
- NULL, reset_unknown, c10_NMRR},
+ access_vm_reg, reset_unknown, c10_NMRR},
+
+ /* AMAIR0/AMAIR1: swapped by interrupt.S. */
+ { CRn(10), CRm( 3), Op1( 0), Op2( 0), is32,
+ access_vm_reg, reset_unknown, c10_AMAIR0},
+ { CRn(10), CRm( 3), Op1( 0), Op2( 1), is32,
+ access_vm_reg, reset_unknown, c10_AMAIR1},
/* VBAR: swapped by interrupt.S. */
{ CRn(12), CRm( 0), Op1( 0), Op2( 0), is32,
@@ -334,7 +382,7 @@ static const struct coproc_reg cp15_regs[] = {
/* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */
{ CRn(13), CRm( 0), Op1( 0), Op2( 1), is32,
- NULL, reset_val, c13_CID, 0x00000000 },
+ access_vm_reg, reset_val, c13_CID, 0x00000000 },
{ CRn(13), CRm( 0), Op1( 0), Op2( 2), is32,
NULL, reset_unknown, c13_TID_URW },
{ CRn(13), CRm( 0), Op1( 0), Op2( 3), is32,
@@ -443,7 +491,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
struct coproc_params params;
- params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
+ params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf;
params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0);
params.is_64bit = true;
@@ -451,7 +499,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf;
params.Op2 = 0;
params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
- params.CRn = 0;
+ params.CRm = 0;
return emulate_cp15(vcpu, &params);
}
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index 0461d5c8d3d..1a44bbe3964 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -58,8 +58,8 @@ static inline void print_cp_instr(const struct coproc_params *p)
{
/* Look, we even formatted it for you to paste into the table! */
if (p->is_64bit) {
- kvm_pr_unimpl(" { CRm(%2lu), Op1(%2lu), is64, func_%s },\n",
- p->CRm, p->Op1, p->is_write ? "write" : "read");
+ kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n",
+ p->CRn, p->Op1, p->is_write ? "write" : "read");
} else {
kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32,"
" func_%s },\n",
@@ -135,13 +135,13 @@ static inline int cmp_reg(const struct coproc_reg *i1,
return -1;
if (i1->CRn != i2->CRn)
return i1->CRn - i2->CRn;
- if (i1->is_64 != i2->is_64)
- return i2->is_64 - i1->is_64;
if (i1->CRm != i2->CRm)
return i1->CRm - i2->CRm;
if (i1->Op1 != i2->Op1)
return i1->Op1 - i2->Op1;
- return i1->Op2 - i2->Op2;
+ if (i1->Op2 != i2->Op2)
+ return i1->Op2 - i2->Op2;
+ return i2->is_64 - i1->is_64;
}
@@ -153,4 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
#define is64 .is_64 = true
#define is32 .is_64 = false
+bool access_sctlr(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r);
+
#endif /* __ARM_KVM_COPROC_LOCAL_H__ */
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index bb0cac1410c..e6f4ae48bda 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -34,7 +34,7 @@
static const struct coproc_reg a15_regs[] = {
/* SCTLR: swapped by interrupt.S. */
{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_val, c1_SCTLR, 0x00C50078 },
+ access_sctlr, reset_val, c1_SCTLR, 0x00C50078 },
};
static struct kvm_coproc_target_table a15_target_table = {
diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c
index 1df76733158..17fc7cd479d 100644
--- a/arch/arm/kvm/coproc_a7.c
+++ b/arch/arm/kvm/coproc_a7.c
@@ -37,7 +37,7 @@
static const struct coproc_reg a7_regs[] = {
/* SCTLR: swapped by interrupt.S. */
{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_val, c1_SCTLR, 0x00C50878 },
+ access_sctlr, reset_val, c1_SCTLR, 0x00C50878 },
};
static struct kvm_coproc_target_table a7_target_table = {
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 2786eae10c0..b23a59c1c52 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -38,6 +38,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.hcr = HCR_GUEST_MASK;
return 0;
}
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 0de91fc6de0..4c979d466cc 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -38,14 +38,18 @@ static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
+ int ret;
+
trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
kvm_vcpu_hvc_get_imm(vcpu));
- if (kvm_psci_call(vcpu))
+ ret = kvm_psci_call(vcpu);
+ if (ret < 0) {
+ kvm_inject_undefined(vcpu);
return 1;
+ }
- kvm_inject_undefined(vcpu);
- return 1;
+ return ret;
}
static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc15539bad..0d68d407306 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@ after_vfp_restore:
* in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are
* passed in r0 and r1.
*
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
* The calling convention follows the standard AAPCS:
* r0 - r3: caller save
* r12: caller save
@@ -363,6 +367,11 @@ hyp_hvc:
host_switch_to_hyp:
pop {r0, r1, r2}
+ /* Check for __hyp_get_vectors */
+ cmp r0, #-1
+ mrceq p15, 4, r0, c12, c0, 0 @ get HVBAR
+ beq 1f
+
push {lr}
mrs lr, SPSR
push {lr}
@@ -378,7 +387,7 @@ THUMB( orr lr, #1)
pop {lr}
msr SPSR_csxf, lr
pop {lr}
- eret
+1: eret
guest_trap:
load_vcpu @ Load VCPU pointer to r0
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 6f18695a09c..76af9302557 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -303,13 +303,17 @@ vcpu .req r0 @ vcpu pointer always in r0
mrc p15, 0, r2, c14, c1, 0 @ CNTKCTL
mrrc p15, 0, r4, r5, c7 @ PAR
+ mrc p15, 0, r6, c10, c3, 0 @ AMAIR0
+ mrc p15, 0, r7, c10, c3, 1 @ AMAIR1
.if \store_to_vcpu == 0
- push {r2,r4-r5}
+ push {r2,r4-r7}
.else
str r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
add r12, vcpu, #CP15_OFFSET(c7_PAR)
strd r4, r5, [r12]
+ str r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+ str r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
.endif
.endm
@@ -322,15 +326,19 @@ vcpu .req r0 @ vcpu pointer always in r0
*/
.macro write_cp15_state read_from_vcpu
.if \read_from_vcpu == 0
- pop {r2,r4-r5}
+ pop {r2,r4-r7}
.else
ldr r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
add r12, vcpu, #CP15_OFFSET(c7_PAR)
ldrd r4, r5, [r12]
+ ldr r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+ ldr r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
.endif
mcr p15, 0, r2, c14, c1, 0 @ CNTKCTL
mcrr p15, 0, r4, r5, c7 @ PAR
+ mcr p15, 0, r6, c10, c3, 0 @ AMAIR0
+ mcr p15, 0, r7, c10, c3, 1 @ AMAIR1
.if \read_from_vcpu == 0
pop {r2-r12}
@@ -597,17 +605,14 @@ vcpu .req r0 @ vcpu pointer always in r0
/* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
.macro configure_hyp_role operation
- mrc p15, 4, r2, c1, c1, 0 @ HCR
- bic r2, r2, #HCR_VIRT_EXCP_MASK
- ldr r3, =HCR_GUEST_MASK
.if \operation == vmentry
- orr r2, r2, r3
+ ldr r2, [vcpu, #VCPU_HCR]
ldr r3, [vcpu, #VCPU_IRQ_LINES]
orr r2, r2, r3
.else
- bic r2, r2, r3
+ mov r2, #0
.endif
- mcr p15, 4, r2, c1, c1, 0
+ mcr p15, 4, r2, c1, c1, 0 @ HCR
.endm
.macro load_vcpu
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 7789857d147..16f804938b8 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -42,6 +42,8 @@ static unsigned long hyp_idmap_start;
static unsigned long hyp_idmap_end;
static phys_addr_t hyp_idmap_vector;
+#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+
#define kvm_pmd_huge(_x) (pmd_huge(_x) || pmd_trans_huge(_x))
static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
@@ -144,8 +146,9 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
while (addr < end) {
pgd = pgdp + pgd_index(addr);
pud = pud_offset(pgd, addr);
+ pte = NULL;
if (pud_none(*pud)) {
- addr = pud_addr_end(addr, end);
+ addr = kvm_pud_addr_end(addr, end);
continue;
}
@@ -155,13 +158,13 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
* move on.
*/
clear_pud_entry(kvm, pud, addr);
- addr = pud_addr_end(addr, end);
+ addr = kvm_pud_addr_end(addr, end);
continue;
}
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
- addr = pmd_addr_end(addr, end);
+ addr = kvm_pmd_addr_end(addr, end);
continue;
}
@@ -174,12 +177,12 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
/*
* If the pmd entry is to be cleared, walk back up the ladder
*/
- if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
+ if (kvm_pmd_huge(*pmd) || (pte && page_empty(pte))) {
clear_pmd_entry(kvm, pmd, addr);
- next = pmd_addr_end(addr, end);
+ next = kvm_pmd_addr_end(addr, end);
if (page_empty(pmd) && !page_empty(pud)) {
clear_pud_entry(kvm, pud, addr);
- next = pud_addr_end(addr, end);
+ next = kvm_pud_addr_end(addr, end);
}
}
@@ -187,6 +190,99 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
}
}
+static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+ phys_addr_t addr, phys_addr_t end)
+{
+ pte_t *pte;
+
+ pte = pte_offset_kernel(pmd, addr);
+ do {
+ if (!pte_none(*pte)) {
+ hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+ kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
+ }
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+ phys_addr_t addr, phys_addr_t end)
+{
+ pmd_t *pmd;
+ phys_addr_t next;
+
+ pmd = pmd_offset(pud, addr);
+ do {
+ next = kvm_pmd_addr_end(addr, end);
+ if (!pmd_none(*pmd)) {
+ if (kvm_pmd_huge(*pmd)) {
+ hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+ kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE);
+ } else {
+ stage2_flush_ptes(kvm, pmd, addr, next);
+ }
+ }
+ } while (pmd++, addr = next, addr != end);
+}
+
+static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
+ phys_addr_t addr, phys_addr_t end)
+{
+ pud_t *pud;
+ phys_addr_t next;
+
+ pud = pud_offset(pgd, addr);
+ do {
+ next = kvm_pud_addr_end(addr, end);
+ if (!pud_none(*pud)) {
+ if (pud_huge(*pud)) {
+ hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+ kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE);
+ } else {
+ stage2_flush_pmds(kvm, pud, addr, next);
+ }
+ }
+ } while (pud++, addr = next, addr != end);
+}
+
+static void stage2_flush_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *memslot)
+{
+ phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+ phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
+ phys_addr_t next;
+ pgd_t *pgd;
+
+ pgd = kvm->arch.pgd + pgd_index(addr);
+ do {
+ next = kvm_pgd_addr_end(addr, end);
+ stage2_flush_puds(kvm, pgd, addr, next);
+ } while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * stage2_flush_vm - Invalidate cache for pages mapped in stage 2
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the stage 2 page tables and invalidate any cache lines
+ * backing memory already mapped to the VM.
+ */
+void stage2_flush_vm(struct kvm *kvm)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+
+ slots = kvm_memslots(kvm);
+ kvm_for_each_memslot(memslot, slots)
+ stage2_flush_memslot(kvm, memslot);
+
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+}
+
/**
* free_boot_hyp_pgd - free HYP boot page tables
*
@@ -199,14 +295,14 @@ void free_boot_hyp_pgd(void)
if (boot_hyp_pgd) {
unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
- kfree(boot_hyp_pgd);
+ free_pages((unsigned long)boot_hyp_pgd, pgd_order);
boot_hyp_pgd = NULL;
}
if (hyp_pgd)
unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
- kfree(init_bounce_page);
+ free_page((unsigned long)init_bounce_page);
init_bounce_page = NULL;
mutex_unlock(&kvm_hyp_pgd_mutex);
@@ -236,7 +332,7 @@ void free_hyp_pgds(void)
for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
- kfree(hyp_pgd);
+ free_pages((unsigned long)hyp_pgd, pgd_order);
hyp_pgd = NULL;
}
@@ -715,7 +811,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
kvm_set_s2pmd_writable(&new_pmd);
kvm_set_pfn_dirty(pfn);
}
- coherent_icache_guest_page(kvm, hva & PMD_MASK, PMD_SIZE);
+ coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
} else {
pte_t new_pte = pfn_pte(pfn, PAGE_S2);
@@ -723,7 +819,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
kvm_set_s2pte_writable(&new_pte);
kvm_set_pfn_dirty(pfn);
}
- coherent_icache_guest_page(kvm, hva, PAGE_SIZE);
+ coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false);
}
@@ -930,7 +1026,7 @@ int kvm_mmu_init(void)
size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
phys_addr_t phys_base;
- init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ init_bounce_page = (void *)__get_free_page(GFP_KERNEL);
if (!init_bounce_page) {
kvm_err("Couldn't allocate HYP init bounce page\n");
err = -ENOMEM;
@@ -956,8 +1052,9 @@ int kvm_mmu_init(void)
(unsigned long)phys_base);
}
- hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
- boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+ hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+ boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+
if (!hyp_pgd || !boot_hyp_pgd) {
kvm_err("Hyp mode PGD not allocated\n");
err = -ENOMEM;
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 448f60e8d23..09cf37737ee 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -27,6 +27,36 @@
* as described in ARM document number ARM DEN 0022A.
*/
+#define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
+
+static unsigned long psci_affinity_mask(unsigned long affinity_level)
+{
+ if (affinity_level <= 3)
+ return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level);
+
+ return 0;
+}
+
+static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
+{
+ /*
+ * NOTE: For simplicity, we make VCPU suspend emulation to be
+ * same-as WFI (Wait-for-interrupt) emulation.
+ *
+ * This means for KVM the wakeup events are interrupts and
+ * this is consistent with intended use of StateID as described
+ * in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A).
+ *
+ * Further, we also treat power-down request to be same as
+ * stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2
+ * specification (ARM DEN 0022A). This means all suspend states
+ * for KVM will preserve the register state.
+ */
+ kvm_vcpu_block(vcpu);
+
+ return PSCI_RET_SUCCESS;
+}
+
static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
{
vcpu->arch.pause = true;
@@ -38,6 +68,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
struct kvm_vcpu *vcpu = NULL, *tmp;
wait_queue_head_t *wq;
unsigned long cpu_id;
+ unsigned long context_id;
unsigned long mpidr;
phys_addr_t target_pc;
int i;
@@ -58,10 +89,17 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
* Make sure the caller requested a valid CPU and that the CPU is
* turned off.
*/
- if (!vcpu || !vcpu->arch.pause)
- return KVM_PSCI_RET_INVAL;
+ if (!vcpu)
+ return PSCI_RET_INVALID_PARAMS;
+ if (!vcpu->arch.pause) {
+ if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+ return PSCI_RET_ALREADY_ON;
+ else
+ return PSCI_RET_INVALID_PARAMS;
+ }
target_pc = *vcpu_reg(source_vcpu, 2);
+ context_id = *vcpu_reg(source_vcpu, 3);
kvm_reset_vcpu(vcpu);
@@ -76,26 +114,160 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
kvm_vcpu_set_be(vcpu);
*vcpu_pc(vcpu) = target_pc;
+ /*
+ * NOTE: We always update r0 (or x0) because for PSCI v0.1
+ * the general puspose registers are undefined upon CPU_ON.
+ */
+ *vcpu_reg(vcpu, 0) = context_id;
vcpu->arch.pause = false;
smp_mb(); /* Make sure the above is visible */
wq = kvm_arch_vcpu_wq(vcpu);
wake_up_interruptible(wq);
- return KVM_PSCI_RET_SUCCESS;
+ return PSCI_RET_SUCCESS;
}
-/**
- * kvm_psci_call - handle PSCI call if r0 value is in range
- * @vcpu: Pointer to the VCPU struct
- *
- * Handle PSCI calls from guests through traps from HVC instructions.
- * The calling convention is similar to SMC calls to the secure world where
- * the function number is placed in r0 and this function returns true if the
- * function number specified in r0 is withing the PSCI range, and false
- * otherwise.
- */
-bool kvm_psci_call(struct kvm_vcpu *vcpu)
+static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
+{
+ int i;
+ unsigned long mpidr;
+ unsigned long target_affinity;
+ unsigned long target_affinity_mask;
+ unsigned long lowest_affinity_level;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_vcpu *tmp;
+
+ target_affinity = *vcpu_reg(vcpu, 1);
+ lowest_affinity_level = *vcpu_reg(vcpu, 2);
+
+ /* Determine target affinity mask */
+ target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
+ if (!target_affinity_mask)
+ return PSCI_RET_INVALID_PARAMS;
+
+ /* Ignore other bits of target affinity */
+ target_affinity &= target_affinity_mask;
+
+ /*
+ * If one or more VCPU matching target affinity are running
+ * then ON else OFF
+ */
+ kvm_for_each_vcpu(i, tmp, kvm) {
+ mpidr = kvm_vcpu_get_mpidr(tmp);
+ if (((mpidr & target_affinity_mask) == target_affinity) &&
+ !tmp->arch.pause) {
+ return PSCI_0_2_AFFINITY_LEVEL_ON;
+ }
+ }
+
+ return PSCI_0_2_AFFINITY_LEVEL_OFF;
+}
+
+static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
+{
+ memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
+ vcpu->run->system_event.type = type;
+ vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+}
+
+static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
+{
+ kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN);
+}
+
+static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
+{
+ kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
+}
+
+int kvm_psci_version(struct kvm_vcpu *vcpu)
+{
+ if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+ return KVM_ARM_PSCI_0_2;
+
+ return KVM_ARM_PSCI_0_1;
+}
+
+static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
+{
+ int ret = 1;
+ unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+ unsigned long val;
+
+ switch (psci_fn) {
+ case PSCI_0_2_FN_PSCI_VERSION:
+ /*
+ * Bits[31:16] = Major Version = 0
+ * Bits[15:0] = Minor Version = 2
+ */
+ val = 2;
+ break;
+ case PSCI_0_2_FN_CPU_SUSPEND:
+ case PSCI_0_2_FN64_CPU_SUSPEND:
+ val = kvm_psci_vcpu_suspend(vcpu);
+ break;
+ case PSCI_0_2_FN_CPU_OFF:
+ kvm_psci_vcpu_off(vcpu);
+ val = PSCI_RET_SUCCESS;
+ break;
+ case PSCI_0_2_FN_CPU_ON:
+ case PSCI_0_2_FN64_CPU_ON:
+ val = kvm_psci_vcpu_on(vcpu);
+ break;
+ case PSCI_0_2_FN_AFFINITY_INFO:
+ case PSCI_0_2_FN64_AFFINITY_INFO:
+ val = kvm_psci_vcpu_affinity_info(vcpu);
+ break;
+ case PSCI_0_2_FN_MIGRATE:
+ case PSCI_0_2_FN64_MIGRATE:
+ val = PSCI_RET_NOT_SUPPORTED;
+ break;
+ case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+ /*
+ * Trusted OS is MP hence does not require migration
+ * or
+ * Trusted OS is not present
+ */
+ val = PSCI_0_2_TOS_MP;
+ break;
+ case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
+ case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
+ val = PSCI_RET_NOT_SUPPORTED;
+ break;
+ case PSCI_0_2_FN_SYSTEM_OFF:
+ kvm_psci_system_off(vcpu);
+ /*
+ * We should'nt be going back to guest VCPU after
+ * receiving SYSTEM_OFF request.
+ *
+ * If user space accidently/deliberately resumes
+ * guest VCPU after SYSTEM_OFF request then guest
+ * VCPU should see internal failure from PSCI return
+ * value. To achieve this, we preload r0 (or x0) with
+ * PSCI return value INTERNAL_FAILURE.
+ */
+ val = PSCI_RET_INTERNAL_FAILURE;
+ ret = 0;
+ break;
+ case PSCI_0_2_FN_SYSTEM_RESET:
+ kvm_psci_system_reset(vcpu);
+ /*
+ * Same reason as SYSTEM_OFF for preloading r0 (or x0)
+ * with PSCI return value INTERNAL_FAILURE.
+ */
+ val = PSCI_RET_INTERNAL_FAILURE;
+ ret = 0;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ *vcpu_reg(vcpu, 0) = val;
+ return ret;
+}
+
+static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
{
unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
unsigned long val;
@@ -103,20 +275,45 @@ bool kvm_psci_call(struct kvm_vcpu *vcpu)
switch (psci_fn) {
case KVM_PSCI_FN_CPU_OFF:
kvm_psci_vcpu_off(vcpu);
- val = KVM_PSCI_RET_SUCCESS;
+ val = PSCI_RET_SUCCESS;
break;
case KVM_PSCI_FN_CPU_ON:
val = kvm_psci_vcpu_on(vcpu);
break;
case KVM_PSCI_FN_CPU_SUSPEND:
case KVM_PSCI_FN_MIGRATE:
- val = KVM_PSCI_RET_NI;
+ val = PSCI_RET_NOT_SUPPORTED;
break;
-
default:
- return false;
+ return -EINVAL;
}
*vcpu_reg(vcpu, 0) = val;
- return true;
+ return 1;
+}
+
+/**
+ * kvm_psci_call - handle PSCI call if r0 value is in range
+ * @vcpu: Pointer to the VCPU struct
+ *
+ * Handle PSCI calls from guests through traps from HVC instructions.
+ * The calling convention is similar to SMC calls to the secure world
+ * where the function number is placed in r0.
+ *
+ * This function returns: > 0 (success), 0 (success but exit to user
+ * space), and < 0 (errors)
+ *
+ * Errors:
+ * -EINVAL: Unrecognized PSCI function
+ */
+int kvm_psci_call(struct kvm_vcpu *vcpu)
+{
+ switch (kvm_psci_version(vcpu)) {
+ case KVM_ARM_PSCI_0_2:
+ return kvm_psci_0_2_call(vcpu);
+ case KVM_ARM_PSCI_0_1:
+ return kvm_psci_0_1_call(vcpu);
+ default:
+ return -EINVAL;
+ };
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 21:20:54 +0000