summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/kvm/sys_regs.c2
-rw-r--r--arch/riscv/Kconfig3
-rw-r--r--arch/riscv/include/asm/kvm_aia.h4
-rw-r--r--arch/riscv/include/asm/kvm_host.h3
-rw-r--r--arch/riscv/include/asm/uaccess.h4
-rw-r--r--arch/riscv/kernel/ftrace.c18
-rw-r--r--arch/riscv/kernel/traps.c10
-rw-r--r--arch/riscv/kernel/traps_misaligned.c2
-rw-r--r--arch/riscv/kvm/aia.c51
-rw-r--r--arch/riscv/kvm/aia_imsic.c45
-rw-r--r--arch/riscv/kvm/vcpu.c10
-rw-r--r--arch/riscv/kvm/vcpu_timer.c16
-rwxr-xr-xarch/riscv/tools/relocs_check.sh4
-rw-r--r--arch/s390/net/bpf_jit_comp.c10
-rw-r--r--arch/x86/coco/sev/Makefile3
-rw-r--r--arch/x86/hyperv/hv_init.c1
-rw-r--r--arch/x86/hyperv/irqdomain.c69
-rw-r--r--arch/x86/hyperv/ivm.c1
-rw-r--r--arch/x86/hyperv/nested.c1
-rw-r--r--arch/x86/include/asm/mshyperv.h22
-rw-r--r--arch/x86/kvm/vmx/tdx.c9
-rw-r--r--arch/x86/kvm/x86.c4
22 files changed, 168 insertions, 124 deletions
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 76c2f0da821f..c20bd6f21e60 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2624,7 +2624,7 @@ static bool access_mdcr(struct kvm_vcpu *vcpu,
*/
if (hpmn > vcpu->kvm->arch.nr_pmu_counters) {
hpmn = vcpu->kvm->arch.nr_pmu_counters;
- u64_replace_bits(val, hpmn, MDCR_EL2_HPMN);
+ u64p_replace_bits(&val, hpmn, MDCR_EL2_HPMN);
}
__vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d71ea0f4466f..1c5544401530 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -98,6 +98,7 @@ config RISCV
select CLONE_BACKWARDS
select COMMON_CLK
select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
+ select DYNAMIC_FTRACE if FUNCTION_TRACER
select EDAC_SUPPORT
select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
@@ -162,7 +163,7 @@ config RISCV
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS
select HAVE_FUNCTION_GRAPH_FREGS
- select HAVE_FUNCTION_TRACER if !XIP_KERNEL
+ select HAVE_FUNCTION_TRACER if !XIP_KERNEL && HAVE_DYNAMIC_FTRACE
select HAVE_EBPF_JIT if MMU
select HAVE_GUP_FAST if MMU
select HAVE_FUNCTION_ARG_ACCESS_API
diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h
index 3b643b9efc07..5acce285e56e 100644
--- a/arch/riscv/include/asm/kvm_aia.h
+++ b/arch/riscv/include/asm/kvm_aia.h
@@ -87,6 +87,9 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
extern struct kvm_device_ops kvm_riscv_aia_device_ops;
+bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu);
+void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu);
int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu);
@@ -161,7 +164,6 @@ void kvm_riscv_aia_destroy_vm(struct kvm *kvm);
int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner,
void __iomem **hgei_va, phys_addr_t *hgei_pa);
void kvm_riscv_aia_free_hgei(int cpu, int hgei);
-void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable);
void kvm_riscv_aia_enable(void);
void kvm_riscv_aia_disable(void);
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 85cfebc32e4c..bcbf8b1ec115 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -306,6 +306,9 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
}
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+
#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12
void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 525e50db24f7..b88a6218b7f2 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -311,8 +311,8 @@ do { \
do { \
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \
!IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \
- __inttype(x) val = (__inttype(x))x; \
- if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(val), sizeof(*__gu_ptr))) \
+ __inttype(x) ___val = (__inttype(x))x; \
+ if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \
goto label; \
break; \
} \
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 4c6c24380cfd..8d18d6727f0f 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -14,6 +14,18 @@
#include <asm/text-patching.h>
#ifdef CONFIG_DYNAMIC_FTRACE
+void ftrace_arch_code_modify_prepare(void)
+ __acquires(&text_mutex)
+{
+ mutex_lock(&text_mutex);
+}
+
+void ftrace_arch_code_modify_post_process(void)
+ __releases(&text_mutex)
+{
+ mutex_unlock(&text_mutex);
+}
+
unsigned long ftrace_call_adjust(unsigned long addr)
{
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
@@ -29,10 +41,8 @@ unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
void arch_ftrace_update_code(int command)
{
- mutex_lock(&text_mutex);
command |= FTRACE_MAY_SLEEP;
ftrace_modify_all_code(command);
- mutex_unlock(&text_mutex);
flush_icache_all();
}
@@ -149,6 +159,8 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
unsigned int nops[2], offset;
int ret;
+ guard(mutex)(&text_mutex);
+
ret = ftrace_rec_set_nop_ops(rec);
if (ret)
return ret;
@@ -157,9 +169,7 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
nops[0] = to_auipc_t0(offset);
nops[1] = RISCV_INSN_NOP4;
- mutex_lock(&text_mutex);
ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE);
- mutex_unlock(&text_mutex);
return ret;
}
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 9c83848797a7..80230de167de 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -6,6 +6,7 @@
#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/init.h>
+#include <linux/irqflags.h>
#include <linux/randomize_kstack.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
@@ -151,7 +152,9 @@ asmlinkage __visible __trap_section void name(struct pt_regs *regs) \
{ \
if (user_mode(regs)) { \
irqentry_enter_from_user_mode(regs); \
+ local_irq_enable(); \
do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \
+ local_irq_disable(); \
irqentry_exit_to_user_mode(regs); \
} else { \
irqentry_state_t state = irqentry_nmi_enter(regs); \
@@ -173,17 +176,14 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
if (user_mode(regs)) {
irqentry_enter_from_user_mode(regs);
-
local_irq_enable();
handled = riscv_v_first_use_handler(regs);
-
- local_irq_disable();
-
if (!handled)
do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
"Oops - illegal instruction");
+ local_irq_disable();
irqentry_exit_to_user_mode(regs);
} else {
irqentry_state_t state = irqentry_nmi_enter(regs);
@@ -308,9 +308,11 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs)
{
if (user_mode(regs)) {
irqentry_enter_from_user_mode(regs);
+ local_irq_enable();
handle_break(regs);
+ local_irq_disable();
irqentry_exit_to_user_mode(regs);
} else {
irqentry_state_t state = irqentry_nmi_enter(regs);
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 93043924fe6c..f760e4fcc052 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -461,7 +461,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs)
}
if (!fp)
- SET_RD(insn, regs, val.data_ulong << shift >> shift);
+ SET_RD(insn, regs, (long)(val.data_ulong << shift) >> shift);
else if (len == 8)
set_f64_rd(insn, regs, val.data_u64);
else
diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 19afd1f23537..dad318185660 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -30,28 +30,6 @@ unsigned int kvm_riscv_aia_nr_hgei;
unsigned int kvm_riscv_aia_max_ids;
DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
-static int aia_find_hgei(struct kvm_vcpu *owner)
-{
- int i, hgei;
- unsigned long flags;
- struct aia_hgei_control *hgctrl = get_cpu_ptr(&aia_hgei);
-
- raw_spin_lock_irqsave(&hgctrl->lock, flags);
-
- hgei = -1;
- for (i = 1; i <= kvm_riscv_aia_nr_hgei; i++) {
- if (hgctrl->owners[i] == owner) {
- hgei = i;
- break;
- }
- }
-
- raw_spin_unlock_irqrestore(&hgctrl->lock, flags);
-
- put_cpu_ptr(&aia_hgei);
- return hgei;
-}
-
static inline unsigned long aia_hvictl_value(bool ext_irq_pending)
{
unsigned long hvictl;
@@ -95,7 +73,6 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu)
bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
{
- int hgei;
unsigned long seip;
if (!kvm_riscv_aia_available())
@@ -114,11 +91,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip)
return false;
- hgei = aia_find_hgei(vcpu);
- if (hgei > 0)
- return !!(ncsr_read(CSR_HGEIP) & BIT(hgei));
-
- return false;
+ return kvm_riscv_vcpu_aia_imsic_has_interrupt(vcpu);
}
void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu)
@@ -164,6 +137,9 @@ void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu)
csr_write(CSR_HVIPRIO2H, csr->hviprio2h);
#endif
}
+
+ if (kvm_riscv_aia_initialized(vcpu->kvm))
+ kvm_riscv_vcpu_aia_imsic_load(vcpu, cpu);
}
void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
@@ -174,6 +150,9 @@ void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
if (!kvm_riscv_aia_available())
return;
+ if (kvm_riscv_aia_initialized(vcpu->kvm))
+ kvm_riscv_vcpu_aia_imsic_put(vcpu);
+
if (kvm_riscv_nacl_available()) {
nsh = nacl_shmem();
csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT);
@@ -472,22 +451,6 @@ void kvm_riscv_aia_free_hgei(int cpu, int hgei)
raw_spin_unlock_irqrestore(&hgctrl->lock, flags);
}
-void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable)
-{
- int hgei;
-
- if (!kvm_riscv_aia_available())
- return;
-
- hgei = aia_find_hgei(owner);
- if (hgei > 0) {
- if (enable)
- csr_set(CSR_HGEIE, BIT(hgei));
- else
- csr_clear(CSR_HGEIE, BIT(hgei));
- }
-}
-
static irqreturn_t hgei_interrupt(int irq, void *dev_id)
{
int i;
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index 29ef9c2133a9..2ff865943ebb 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -676,6 +676,48 @@ static void imsic_swfile_update(struct kvm_vcpu *vcpu,
imsic_swfile_extirq_update(vcpu);
}
+bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+ struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+ unsigned long flags;
+ bool ret = false;
+
+ /*
+ * The IMSIC SW-file directly injects interrupt via hvip so
+ * only check for interrupt when IMSIC VS-file is being used.
+ */
+
+ read_lock_irqsave(&imsic->vsfile_lock, flags);
+ if (imsic->vsfile_cpu > -1)
+ ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei));
+ read_unlock_irqrestore(&imsic->vsfile_lock, flags);
+
+ return ret;
+}
+
+void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu)
+{
+ /*
+ * No need to explicitly clear HGEIE CSR bits because the
+ * hgei interrupt handler (aka hgei_interrupt()) will always
+ * clear it for us.
+ */
+}
+
+void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu)
+{
+ struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+ unsigned long flags;
+
+ if (!kvm_vcpu_is_blocking(vcpu))
+ return;
+
+ read_lock_irqsave(&imsic->vsfile_lock, flags);
+ if (imsic->vsfile_cpu > -1)
+ csr_set(CSR_HGEIE, BIT(imsic->vsfile_hgei));
+ read_unlock_irqrestore(&imsic->vsfile_lock, flags);
+}
+
void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu)
{
unsigned long flags;
@@ -781,6 +823,9 @@ int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu)
* producers to the new IMSIC VS-file.
*/
+ /* Ensure HGEIE CSR bit is zero before using the new IMSIC VS-file */
+ csr_clear(CSR_HGEIE, BIT(new_vsfile_hgei));
+
/* Zero-out new IMSIC VS-file */
imsic_vsfile_local_clear(new_vsfile_hgei, imsic->nr_hw_eix);
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index e0a01af426ff..0462863206ca 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -207,16 +207,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
return kvm_riscv_vcpu_timer_pending(vcpu);
}
-void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
-{
- kvm_riscv_aia_wakeon_hgei(vcpu, true);
-}
-
-void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
-{
- kvm_riscv_aia_wakeon_hgei(vcpu, false);
-}
-
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&
diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
index ff672fa71fcc..85a7262115e1 100644
--- a/arch/riscv/kvm/vcpu_timer.c
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -345,8 +345,24 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
/*
* The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync()
* upon every VM exit so no need to save here.
+ *
+ * If VS-timer expires when no VCPU running on a host CPU then
+ * WFI executed by such host CPU will be effective NOP resulting
+ * in no power savings. This is because as-per RISC-V Privileged
+ * specificaiton: "WFI is also required to resume execution for
+ * locally enabled interrupts pending at any privilege level,
+ * regardless of the global interrupt enable at each privilege
+ * level."
+ *
+ * To address the above issue, vstimecmp CSR must be set to -1UL
+ * over here when VCPU is scheduled-out or exits to user space.
*/
+ csr_write(CSR_VSTIMECMP, -1UL);
+#if defined(CONFIG_32BIT)
+ csr_write(CSR_VSTIMECMPH, -1UL);
+#endif
+
/* timer should be enabled for the remaining operations */
if (unlikely(!t->init_done))
return;
diff --git a/arch/riscv/tools/relocs_check.sh b/arch/riscv/tools/relocs_check.sh
index baeb2e7b2290..742993e6a8cb 100755
--- a/arch/riscv/tools/relocs_check.sh
+++ b/arch/riscv/tools/relocs_check.sh
@@ -14,7 +14,9 @@ bad_relocs=$(
${srctree}/scripts/relocs_check.sh "$@" |
# These relocations are okay
# R_RISCV_RELATIVE
- grep -F -w -v 'R_RISCV_RELATIVE'
+ # R_RISCV_NONE
+ grep -F -w -v 'R_RISCV_RELATIVE
+R_RISCV_NONE'
)
if [ -z "$bad_relocs" ]; then
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index c7f8313ba449..0c9a35782c83 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -566,7 +566,15 @@ static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target)
{
memcpy(plt, &bpf_plt, sizeof(*plt));
plt->ret = ret;
- plt->target = target;
+ /*
+ * (target == NULL) implies that the branch to this PLT entry was
+ * patched and became a no-op. However, some CPU could have jumped
+ * to this PLT entry before patching and may be still executing it.
+ *
+ * Since the intention in this case is to make the PLT entry a no-op,
+ * make the target point to the return label instead of NULL.
+ */
+ plt->target = target ?: ret;
}
/*
diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile
index db3255b979bd..342d79f0ab6a 100644
--- a/arch/x86/coco/sev/Makefile
+++ b/arch/x86/coco/sev/Makefile
@@ -5,5 +5,6 @@ obj-y += core.o sev-nmi.o vc-handle.o
# Clang 14 and older may fail to respect __no_sanitize_undefined when inlining
UBSAN_SANITIZE_sev-nmi.o := n
-# GCC may fail to respect __no_sanitize_address when inlining
+# GCC may fail to respect __no_sanitize_address or __no_kcsan when inlining
KASAN_SANITIZE_sev-nmi.o := n
+KCSAN_SANITIZE_sev-nmi.o := n
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 3d1d3547095a..afdbda2dd7b7 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -34,6 +34,7 @@
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
#include <linux/highmem.h>
+#include <linux/export.h>
void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 31f0d29cbc5e..090f5ac9f492 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -10,6 +10,7 @@
#include <linux/pci.h>
#include <linux/irq.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
static int hv_map_interrupt(union hv_device_id device_id, bool level,
@@ -46,7 +47,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
if (nr_bank < 0) {
local_irq_restore(flags);
pr_err("%s: unable to generate VP set\n", __func__);
- return EINVAL;
+ return -EINVAL;
}
intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
@@ -66,7 +67,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
if (!hv_result_success(status))
hv_status_err(status, "\n");
- return hv_result(status);
+ return hv_result_to_errno(status);
}
static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
@@ -88,7 +89,10 @@ static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL);
local_irq_restore(flags);
- return hv_result(status);
+ if (!hv_result_success(status))
+ hv_status_err(status, "\n");
+
+ return hv_result_to_errno(status);
}
#ifdef CONFIG_PCI_MSI
@@ -169,13 +173,34 @@ static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev)
return dev_id;
}
-static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector,
- struct hv_interrupt_entry *entry)
+/**
+ * hv_map_msi_interrupt() - "Map" the MSI IRQ in the hypervisor.
+ * @data: Describes the IRQ
+ * @out_entry: Hypervisor (MSI) interrupt entry (can be NULL)
+ *
+ * Map the IRQ in the hypervisor by issuing a MAP_DEVICE_INTERRUPT hypercall.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_map_msi_interrupt(struct irq_data *data,
+ struct hv_interrupt_entry *out_entry)
{
- union hv_device_id device_id = hv_build_pci_dev_id(dev);
+ struct irq_cfg *cfg = irqd_cfg(data);
+ struct hv_interrupt_entry dummy;
+ union hv_device_id device_id;
+ struct msi_desc *msidesc;
+ struct pci_dev *dev;
+ int cpu;
- return hv_map_interrupt(device_id, false, cpu, vector, entry);
+ msidesc = irq_data_get_msi_desc(data);
+ dev = msi_desc_to_pci_dev(msidesc);
+ device_id = hv_build_pci_dev_id(dev);
+ cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
+
+ return hv_map_interrupt(device_id, false, cpu, cfg->vector,
+ out_entry ? out_entry : &dummy);
}
+EXPORT_SYMBOL_GPL(hv_map_msi_interrupt);
static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg)
{
@@ -188,13 +213,11 @@ static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi
static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry);
static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
{
+ struct hv_interrupt_entry *stored_entry;
+ struct irq_cfg *cfg = irqd_cfg(data);
struct msi_desc *msidesc;
struct pci_dev *dev;
- struct hv_interrupt_entry out_entry, *stored_entry;
- struct irq_cfg *cfg = irqd_cfg(data);
- const cpumask_t *affinity;
- int cpu;
- u64 status;
+ int ret;
msidesc = irq_data_get_msi_desc(data);
dev = msi_desc_to_pci_dev(msidesc);
@@ -204,9 +227,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
return;
}
- affinity = irq_data_get_effective_affinity_mask(data);
- cpu = cpumask_first_and(affinity, cpu_online_mask);
-
if (data->chip_data) {
/*
* This interrupt is already mapped. Let's unmap first.
@@ -219,14 +239,12 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
stored_entry = data->chip_data;
data->chip_data = NULL;
- status = hv_unmap_msi_interrupt(dev, stored_entry);
+ ret = hv_unmap_msi_interrupt(dev, stored_entry);
kfree(stored_entry);
- if (status != HV_STATUS_SUCCESS) {
- hv_status_debug(status, "failed to unmap\n");
+ if (ret)
return;
- }
}
stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC);
@@ -235,15 +253,14 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
return;
}
- status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry);
- if (status != HV_STATUS_SUCCESS) {
+ ret = hv_map_msi_interrupt(data, stored_entry);
+ if (ret) {
kfree(stored_entry);
return;
}
- *stored_entry = out_entry;
data->chip_data = stored_entry;
- entry_to_msi_msg(&out_entry, msg);
+ entry_to_msi_msg(data->chip_data, msg);
return;
}
@@ -257,7 +274,6 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
{
struct hv_interrupt_entry old_entry;
struct msi_msg msg;
- u64 status;
if (!irqd->chip_data) {
pr_debug("%s: no chip data\n!", __func__);
@@ -270,10 +286,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
kfree(irqd->chip_data);
irqd->chip_data = NULL;
- status = hv_unmap_msi_interrupt(dev, &old_entry);
-
- if (status != HV_STATUS_SUCCESS)
- hv_status_err(status, "\n");
+ (void)hv_unmap_msi_interrupt(dev, &old_entry);
}
static void hv_msi_free_irq(struct irq_domain *domain,
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index e93a2f488ff7..ade6c665c97e 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -10,6 +10,7 @@
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/cpu.h>
+#include <linux/export.h>
#include <asm/svm.h>
#include <asm/sev.h>
#include <asm/io.h>
diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c
index 1083dc8646f9..8ccbb7c4fc27 100644
--- a/arch/x86/hyperv/nested.c
+++ b/arch/x86/hyperv/nested.c
@@ -11,6 +11,7 @@
#include <linux/types.h>
+#include <linux/export.h>
#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
#include <asm/tlbflush.h>
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index e1752ba47e67..abc4659f5809 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -112,12 +112,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
return hv_status;
}
-/* Hypercall to the L0 hypervisor */
-static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output)
-{
- return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output);
-}
-
/* Fast hypercall with 8 bytes of input and no output */
static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
{
@@ -165,13 +159,6 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
return _hv_do_fast_hypercall8(control, input1);
}
-static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1)
-{
- u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
-
- return _hv_do_fast_hypercall8(control, input1);
-}
-
/* Fast hypercall with 16 bytes of input */
static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
{
@@ -223,13 +210,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
return _hv_do_fast_hypercall16(control, input1, input2);
}
-static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2)
-{
- u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
-
- return _hv_do_fast_hypercall16(control, input1, input2);
-}
-
extern struct hv_vp_assist_page **hv_vp_assist_page;
static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
@@ -262,6 +242,8 @@ static inline void hv_apic_init(void) {}
struct irq_domain *hv_create_pci_msi_domain(void);
+int hv_map_msi_interrupt(struct irq_data *data,
+ struct hv_interrupt_entry *out_entry);
int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
struct hv_interrupt_entry *entry);
int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index f31ccdeb905b..ec79aacc446f 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -173,7 +173,6 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i
tdx_clear_unsupported_cpuid(entry);
}
-#define TDVMCALLINFO_GET_QUOTE BIT(0)
#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT BIT(1)
static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
@@ -192,7 +191,6 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
caps->cpuid.nent = td_conf->num_cpuid_config;
caps->user_tdvmcallinfo_1_r11 =
- TDVMCALLINFO_GET_QUOTE |
TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT;
for (i = 0; i < td_conf->num_cpuid_config; i++)
@@ -2271,25 +2269,26 @@ static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
struct kvm_tdx_capabilities __user *user_caps;
struct kvm_tdx_capabilities *caps = NULL;
+ u32 nr_user_entries;
int ret = 0;
/* flags is reserved for future use */
if (cmd->flags)
return -EINVAL;
- caps = kmalloc(sizeof(*caps) +
+ caps = kzalloc(sizeof(*caps) +
sizeof(struct kvm_cpuid_entry2) * td_conf->num_cpuid_config,
GFP_KERNEL);
if (!caps)
return -ENOMEM;
user_caps = u64_to_user_ptr(cmd->data);
- if (copy_from_user(caps, user_caps, sizeof(*caps))) {
+ if (get_user(nr_user_entries, &user_caps->cpuid.nent)) {
ret = -EFAULT;
goto out;
}
- if (caps->cpuid.nent < td_conf->num_cpuid_config) {
+ if (nr_user_entries < td_conf->num_cpuid_config) {
ret = -E2BIG;
goto out;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 357b9e3a6cef..93636f77c42d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6188,6 +6188,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
u32 user_tsc_khz;
r = -EINVAL;
+
+ if (vcpu->arch.guest_tsc_protected)
+ goto out;
+
user_tsc_khz = (u32)arg;
if (kvm_caps.has_tsc_control &&