aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig5
-rw-r--r--arch/x86/include/asm/xen/page.h31
-rw-r--r--arch/x86/kernel/cpu/perf_event.c12
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c5
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c1
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c10
-rw-r--r--arch/x86/kernel/entry_64.S15
-rw-r--r--arch/x86/kernel/microcode_amd.c1
-rw-r--r--arch/x86/kernel/reboot.c18
-rw-r--r--arch/x86/kernel/smpboot.c3
-rw-r--r--arch/x86/kernel/sysfb_simplefb.c4
-rw-r--r--arch/x86/kvm/emulate.c14
-rw-r--r--arch/x86/kvm/paging_tmpl.h20
-rw-r--r--arch/x86/kvm/vmx.c15
-rw-r--r--arch/x86/pci/mmconfig-shared.c7
-rw-r--r--arch/x86/platform/efi/efi.c11
-rw-r--r--arch/x86/xen/p2m.c10
-rw-r--r--arch/x86/xen/spinlock.c26
18 files changed, 148 insertions, 60 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e241a1930c98..ee2fb9d37745 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -481,11 +481,12 @@ config X86_INTEL_LPSS
bool "Intel Low Power Subsystem Support"
depends on ACPI
select COMMON_CLK
+ select PINCTRL
---help---
Select to build support for Intel Low Power Subsystem such as
found on Intel Lynxpoint PCH. Selecting this option enables
- things like clock tree (common clock framework) which are needed
- by the LPSS peripheral drivers.
+ things like clock tree (common clock framework) and pincontrol
+ which are needed by the LPSS peripheral drivers.
config X86_RDC321X
bool "RDC R-321x SoC"
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fbc09b7..b913915e8e63 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
}
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
{
unsigned long pfn;
- int ret = 0;
+ int ret;
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
- if (unlikely(mfn >= machine_to_phys_nr)) {
- pfn = ~0;
- goto try_override;
- }
- pfn = 0;
+ if (unlikely(mfn >= machine_to_phys_nr))
+ return ~0;
+
/*
* The array access can fail (e.g., device space beyond end of RAM).
* In such cases it doesn't matter what we return (we return garbage),
* but we must handle the fault without crashing!
*/
ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
- /* ret might be < 0 if there are no entries in the m2p for mfn */
if (ret < 0)
- pfn = ~0;
- else if (get_phys_to_machine(pfn) != mfn)
+ return ~0;
+
+ return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+ unsigned long pfn;
+
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return mfn;
+
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) != mfn) {
/*
* If this appears to be a foreign mfn (because the pfn
* doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@ try_override:
* m2p_find_override_pfn returns ~0 if it doesn't find anything.
*/
pfn = m2p_find_override_pfn(mfn, ~0);
+ }
/*
* pfn is ~0 if there are no entries in the m2p for mfn or if the
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8355c84b9729..897783b3302a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void)
err = amd_pmu_init();
break;
default:
- return 0;
+ err = -ENOTSUPP;
}
if (err != 0) {
pr_cont("no PMU driver, software events only.\n");
@@ -1883,9 +1883,9 @@ static struct pmu pmu = {
void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
- userpg->cap_usr_time = 0;
- userpg->cap_usr_time_zero = 0;
- userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+ userpg->cap_user_time = 0;
+ userpg->cap_user_time_zero = 0;
+ userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
userpg->pmc_width = x86_pmu.cntval_bits;
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
return;
- userpg->cap_usr_time = 1;
+ userpg->cap_user_time = 1;
userpg->time_mult = this_cpu_read(cyc2ns);
userpg->time_shift = CYC2NS_SCALE_FACTOR;
userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
if (sched_clock_stable && !check_tsc_disabled()) {
- userpg->cap_usr_time_zero = 1;
+ userpg->cap_user_time_zero = 1;
userpg->time_zero = this_cpu_read(cyc2ns_offset);
}
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index c62d88396ad5..f31a1655d1ff 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -899,8 +899,8 @@ static __initconst const u64 atom_hw_cache_event_ids
static struct extra_reg intel_slm_extra_regs[] __read_mostly =
{
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
- INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffff, RSP_0),
- INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffff, RSP_1),
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1),
EVENT_EXTRA_END
};
@@ -2325,6 +2325,7 @@ __init int intel_pmu_init(void)
break;
case 55: /* Atom 22nm "Silvermont" */
+ case 77: /* Avoton "Silvermont" */
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 63438aad177f..ab3ba1c1b7dd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -584,6 +584,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
EVENT_CONSTRAINT_END
};
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 8ed44589b0e4..4118f9f68315 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2706,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
box->hrtimer.function = uncore_pmu_hrtimer;
}
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
+static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node)
{
struct intel_uncore_box *box;
int i, size;
size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
- box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu));
+ box = kzalloc_node(size, GFP_KERNEL, node);
if (!box)
return NULL;
@@ -3031,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
struct intel_uncore_box *fake_box;
int ret = -EINVAL, n;
- fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+ fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
if (!fake_box)
return -ENOMEM;
@@ -3294,7 +3294,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
}
type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
- box = uncore_alloc_box(type, 0);
+ box = uncore_alloc_box(type, NUMA_NO_NODE);
if (!box)
return -ENOMEM;
@@ -3499,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
if (pmu->func_id < 0)
pmu->func_id = j;
- box = uncore_alloc_box(type, cpu);
+ box = uncore_alloc_box(type, cpu_to_node(cpu));
if (!box)
return -ENOMEM;
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1b69951a81e2..b077f4cc225a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -487,21 +487,6 @@ ENDPROC(native_usergs_sysret64)
TRACE_IRQS_OFF
.endm
-ENTRY(save_rest)
- PARTIAL_FRAME 1 (REST_SKIP+8)
- movq 5*8+16(%rsp), %r11 /* save return address */
- movq_cfi rbx, RBX+16
- movq_cfi rbp, RBP+16
- movq_cfi r12, R12+16
- movq_cfi r13, R13+16
- movq_cfi r14, R14+16
- movq_cfi r15, R15+16
- movq %r11, 8(%rsp) /* return address */
- FIXUP_TOP_OF_STACK %r11, 16
- ret
- CFI_ENDPROC
-END(save_rest)
-
/* save complete stack frame */
.pushsection .kprobes.text, "ax"
ENTRY(save_paranoid)
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7123b5df479d..af99f71aeb7f 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -216,6 +216,7 @@ int apply_microcode_amd(int cpu)
/* need to apply patch? */
if (rev >= mc_amd->hdr.patch_id) {
c->microcode = rev;
+ uci->cpu_sig.rev = rev;
return 0;
}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 563ed91e6faa..e643e744e4d8 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -352,12 +352,28 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
},
{ /* Handle problems with rebooting on the Precision M6600. */
.callback = set_pci_reboot,
- .ident = "Dell OptiPlex 990",
+ .ident = "Dell Precision M6600",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
},
},
+ { /* Handle problems with rebooting on the Dell PowerEdge C6100. */
+ .callback = set_pci_reboot,
+ .ident = "Dell PowerEdge C6100",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+ },
+ },
+ { /* Some C6100 machines were shipped with vendor being 'Dell'. */
+ .callback = set_pci_reboot,
+ .ident = "Dell PowerEdge C6100",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+ },
+ },
{ }
};
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index aecc98a93d1b..6cacab671f9b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -653,6 +653,7 @@ static void announce_cpu(int cpu, int apicid)
{
static int current_node = -1;
int node = early_cpu_to_node(cpu);
+ int max_cpu_present = find_last_bit(cpumask_bits(cpu_present_mask), NR_CPUS);
if (system_state == SYSTEM_BOOTING) {
if (node != current_node) {
@@ -661,7 +662,7 @@ static void announce_cpu(int cpu, int apicid)
current_node = node;
pr_info("Booting Node %3d, Processors ", node);
}
- pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " OK\n" : "");
+ pr_cont(" #%4d%s", cpu, cpu == max_cpu_present ? " OK\n" : "");
return;
} else
pr_info("Booting Node %d Processor %d APIC 0x%x\n",
diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c
index 22513e96b012..86179d409893 100644
--- a/arch/x86/kernel/sysfb_simplefb.c
+++ b/arch/x86/kernel/sysfb_simplefb.c
@@ -72,14 +72,14 @@ __init int create_simplefb(const struct screen_info *si,
* the part that is occupied by the framebuffer */
len = mode->height * mode->stride;
len = PAGE_ALIGN(len);
- if (len > si->lfb_size << 16) {
+ if (len > (u64)si->lfb_size << 16) {
printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
return -EINVAL;
}
/* setup IORESOURCE_MEM as framebuffer memory */
memset(&res, 0, sizeof(res));
- res.flags = IORESOURCE_MEM;
+ res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
res.name = simplefb_resname;
res.start = si->lfb_base;
res.end = si->lfb_base + len - 1;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2bc1e81045b0..ddc3f3d2afdb 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2025,6 +2025,17 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
return rc;
}
+static int em_ret_far_imm(struct x86_emulate_ctxt *ctxt)
+{
+ int rc;
+
+ rc = em_ret_far(ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ rsp_increment(ctxt, ctxt->src.val);
+ return X86EMUL_CONTINUE;
+}
+
static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
{
/* Save real source value, then compare EAX against destination. */
@@ -3763,7 +3774,8 @@ static const struct opcode opcode_table[256] = {
G(ByteOp, group11), G(0, group11),
/* 0xC8 - 0xCF */
I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave),
- N, I(ImplicitOps | Stack, em_ret_far),
+ I(ImplicitOps | Stack | SrcImmU16, em_ret_far_imm),
+ I(ImplicitOps | Stack, em_ret_far),
D(ImplicitOps), DI(SrcImmByte, intn),
D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret),
/* 0xD0 - 0xD7 */
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 043330159179..ad75d77999d0 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -99,6 +99,7 @@ struct guest_walker {
pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
+ bool pte_writable[PT_MAX_FULL_LEVELS];
unsigned pt_access;
unsigned pte_access;
gfn_t gfn;
@@ -235,6 +236,22 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
if (pte == orig_pte)
continue;
+ /*
+ * If the slot is read-only, simply do not process the accessed
+ * and dirty bits. This is the correct thing to do if the slot
+ * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+ * are only supported if the accessed and dirty bits are already
+ * set in the ROM (so that MMIO writes are never needed).
+ *
+ * Note that NPT does not allow this at all and faults, since
+ * it always wants nested page table entries for the guest
+ * page tables to be writable. And EPT works but will simply
+ * overwrite the read-only memory to set the accessed and dirty
+ * bits.
+ */
+ if (unlikely(!walker->pte_writable[level - 1]))
+ continue;
+
ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
if (ret)
return ret;
@@ -309,7 +326,8 @@ retry_walk:
goto error;
real_gfn = gpa_to_gfn(real_gfn);
- host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+ host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+ &walker->pte_writable[walker->level - 1]);
if (unlikely(kvm_is_error_hva(host_addr)))
goto error;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1f1da43ff2a2..3b8e7459dd4d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5339,6 +5339,17 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
return 0;
}
+ /*
+ * EPT violation happened while executing iret from NMI,
+ * "blocked by NMI" bit has to be set before next VM entry.
+ * There are errata that may cause this bit to not be set:
+ * AAK134, BY25.
+ */
+ if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+ cpu_has_virtual_nmis() &&
+ (exit_qualification & INTR_INFO_UNBLOCK_NMI))
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
+
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
trace_kvm_page_fault(gpa, exit_qualification);
@@ -7766,6 +7777,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+ __clear_bit(VCPU_EXREG_PDPTR,
+ (unsigned long *)&vcpu->arch.regs_avail);
+ __clear_bit(VCPU_EXREG_PDPTR,
+ (unsigned long *)&vcpu->arch.regs_dirty);
}
kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 5596c7bdd327..082e88129712 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -700,7 +700,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed)
return -ENODEV;
- if (start > end || !addr)
+ if (start > end)
return -EINVAL;
mutex_lock(&pci_mmcfg_lock);
@@ -716,6 +716,11 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
return -EEXIST;
}
+ if (!addr) {
+ mutex_unlock(&pci_mmcfg_lock);
+ return -EINVAL;
+ }
+
rc = -EBUSY;
cfg = pci_mmconfig_alloc(seg, start, end, addr);
if (cfg == NULL) {
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 90f6ed127096..c7e22ab29a5a 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -912,10 +912,13 @@ void __init efi_enter_virtual_mode(void)
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
md = p;
- if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
- md->type != EFI_BOOT_SERVICES_CODE &&
- md->type != EFI_BOOT_SERVICES_DATA)
- continue;
+ if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
+#ifdef CONFIG_X86_64
+ if (md->type != EFI_BOOT_SERVICES_CODE &&
+ md->type != EFI_BOOT_SERVICES_DATA)
+#endif
+ continue;
+ }
size = md->num_pages << EFI_PAGE_SHIFT;
end = md->phys_addr + size;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8b901e8d782d..a61c7d5811be 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -879,7 +879,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
- int ret = 0;
pfn = page_to_pfn(page);
if (!PageHighMem(page)) {
@@ -926,8 +925,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
* frontend pages while they are being shared with the backend,
* because mfn_to_pfn (that ends up being called by GUPF) will
* return the backend pfn rather than the frontend pfn. */
- ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
- if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) == mfn)
set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
return 0;
@@ -942,7 +941,6 @@ int m2p_remove_override(struct page *page,
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
- int ret = 0;
pfn = page_to_pfn(page);
mfn = get_phys_to_machine(pfn);
@@ -1029,8 +1027,8 @@ int m2p_remove_override(struct page *page,
* the original pfn causes mfn_to_pfn(mfn) to return the frontend
* pfn again. */
mfn &= ~FOREIGN_FRAME_BIT;
- ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
- if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
m2p_find_override(mfn) == NULL)
set_phys_to_machine(pfn, mfn);
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 253f63fceea1..be6b86078957 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -259,6 +259,14 @@ void xen_uninit_lock_cpu(int cpu)
}
+/*
+ * Our init of PV spinlocks is split in two init functions due to us
+ * using paravirt patching and jump labels patching and having to do
+ * all of this before SMP code is invoked.
+ *
+ * The paravirt patching needs to be done _before_ the alternative asm code
+ * is started, otherwise we would not patch the core kernel code.
+ */
void __init xen_init_spinlocks(void)
{
@@ -267,12 +275,26 @@ void __init xen_init_spinlocks(void)
return;
}
- static_key_slow_inc(&paravirt_ticketlocks_enabled);
-
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
pv_lock_ops.unlock_kick = xen_unlock_kick;
}
+/*
+ * While the jump_label init code needs to happend _after_ the jump labels are
+ * enabled and before SMP is started. Hence we use pre-SMP initcall level
+ * init. We cannot do it in xen_init_spinlocks as that is done before
+ * jump labels are activated.
+ */
+static __init int xen_init_spinlocks_jump(void)
+{
+ if (!xen_pvspin)
+ return 0;
+
+ static_key_slow_inc(&paravirt_ticketlocks_enabled);
+ return 0;
+}
+early_initcall(xen_init_spinlocks_jump);
+
static __init int xen_parse_nopvspin(char *arg)
{
xen_pvspin = false;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.