4 files changed, 91 insertions, 16 deletions

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 8f3a4d16bb79..17a71e92a343 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -667,14 +667,14 @@ void hyperv_cleanup(void)
 	hv_hypercall_pg = NULL;
 
 	/* Reset the hypercall page */
-	hypercall_msr.as_uint64 = hv_get_register(HV_X64_MSR_HYPERCALL);
+	hypercall_msr.as_uint64 = hv_get_msr(HV_X64_MSR_HYPERCALL);
 	hypercall_msr.enable = 0;
-	hv_set_register(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	hv_set_msr(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
 	/* Reset the TSC page */
-	tsc_msr.as_uint64 = hv_get_register(HV_X64_MSR_REFERENCE_TSC);
+	tsc_msr.as_uint64 = hv_get_msr(HV_X64_MSR_REFERENCE_TSC);
 	tsc_msr.enable = 0;
-	hv_set_register(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
+	hv_set_msr(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
 }
 
 void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
index 737d6f7a6155..151e851bef09 100644
--- a/arch/x86/hyperv/hv_spinlock.c
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -16,7 +16,7 @@
 #include <asm/paravirt.h>
 #include <asm/apic.h>
 
-static bool __initdata hv_pvspin = true;
+static bool hv_pvspin __initdata = true;
 
 static void hv_qlock_kick(int cpu)
 {
@@ -64,6 +64,7 @@ __visible bool hv_vcpu_is_preempted(int vcpu)
 {
 	return false;
 }
+
 PV_CALLEE_SAVE_REGS_THUNK(hv_vcpu_is_preempted);
 
 void __init hv_init_spinlocks(void)
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 96e6c51515f5..5c7de79423b8 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -12,10 +12,16 @@
 #include <asm/i8259.h>
 #include <asm/mshyperv.h>
 #include <asm/realmode.h>
+#include <../kernel/smpboot.h>
 
 extern struct boot_params boot_params;
 static struct real_mode_header hv_vtl_real_mode_header;
 
+static bool __init hv_vtl_msi_ext_dest_id(void)
+{
+	return true;
+}
+
 void __init hv_vtl_init_platform(void)
 {
 	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
@@ -26,8 +32,9 @@ void __init hv_vtl_init_platform(void)
 	x86_init.timers.timer_init = x86_init_noop;
 
 	/* Avoid searching for BIOS MP tables */
-	x86_init.mpparse.find_smp_config = x86_init_noop;
-	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
+	x86_init.mpparse.find_mptable = x86_init_noop;
+	x86_init.mpparse.early_parse_smp_cfg = x86_init_noop;
+	x86_init.mpparse.parse_smp_cfg = x86_init_noop;
 
 	x86_platform.get_wallclock = get_rtc_noop;
 	x86_platform.set_wallclock = set_rtc_noop;
@@ -38,6 +45,8 @@ void __init hv_vtl_init_platform(void)
 	x86_platform.legacy.warm_reset = 0;
 	x86_platform.legacy.reserve_bios_regions = 0;
 	x86_platform.legacy.devices.pnpbios = 0;
+
+	x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id;
 }
 
 static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc)
@@ -57,7 +66,7 @@ static void hv_vtl_ap_entry(void)
 	((secondary_startup_64_fn)secondary_startup_64)(&boot_params, &boot_params);
 }
 
-static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored)
+static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored)
 {
 	u64 status;
 	int ret = 0;
@@ -71,7 +80,9 @@ static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored)
 	struct ldttss_desc *ldt;
 	struct desc_struct *gdt;
 
-	u64 rsp = current->thread.sp;
+	struct task_struct *idle = idle_thread_get(cpu);
+	u64 rsp = (unsigned long)idle->thread.sp;
+
 	u64 rip = (u64)&hv_vtl_ap_entry;
 
 	native_store_gdt(&gdt_ptr);
@@ -198,7 +209,15 @@ static int hv_vtl_apicid_to_vp_id(u32 apic_id)
 
 static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
 {
-	int vp_id;
+	int vp_id, cpu;
+
+	/* Find the logical CPU for the APIC ID */
+	for_each_present_cpu(cpu) {
+		if (arch_match_cpu_phys_id(cpu, apicid))
+			break;
+	}
+	if (cpu >= nr_cpu_ids)
+		return -EINVAL;
 
 	pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid);
 	vp_id = hv_vtl_apicid_to_vp_id(apicid);
@@ -212,7 +231,7 @@ static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
 		return -EINVAL;
 	}
 
-	return hv_vtl_bringup_vcpu(vp_id, start_eip);
+	return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip);
 }
 
 int __init hv_vtl_early_init(void)
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 7dcbf153ad72..768d73de0d09 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -15,6 +15,7 @@
 #include <asm/io.h>
 #include <asm/coco.h>
 #include <asm/mem_encrypt.h>
+#include <asm/set_memory.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mtrr.h>
@@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 }
 
 /*
+ * When transitioning memory between encrypted and decrypted, the caller
+ * of set_memory_encrypted() or set_memory_decrypted() is responsible for
+ * ensuring that the memory isn't in use and isn't referenced while the
+ * transition is in progress.  The transition has multiple steps, and the
+ * memory is in an inconsistent state until all steps are complete. A
+ * reference while the state is inconsistent could result in an exception
+ * that can't be cleanly fixed up.
+ *
+ * But the Linux kernel load_unaligned_zeropad() mechanism could cause a
+ * stray reference that can't be prevented by the caller, so Linux has
+ * specific code to handle this case. But when the #VC and #VE exceptions
+ * routed to a paravisor, the specific code doesn't work. To avoid this
+ * problem, mark the pages as "not present" while the transition is in
+ * progress. If load_unaligned_zeropad() causes a stray reference, a normal
+ * page fault is generated instead of #VC or #VE, and the page-fault-based
+ * handlers for load_unaligned_zeropad() resolve the reference.  When the
+ * transition is complete, hv_vtom_set_host_visibility() marks the pages
+ * as "present" again.
+ */
+static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
+{
+	return !set_memory_np(kbuffer, pagecount);
+}
+
+/*
  * hv_vtom_set_host_visibility - Set specified memory visible to host.
  *
  * In Isolation VM, all guest memory is encrypted from host and guest
@@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 	enum hv_mem_host_visibility visibility = enc ?
 			VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
 	u64 *pfn_array;
+	phys_addr_t paddr;
+	void *vaddr;
 	int ret = 0;
 	bool result = true;
 	int i, pfn;
 
 	pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
-	if (!pfn_array)
-		return false;
+	if (!pfn_array) {
+		result = false;
+		goto err_set_memory_p;
+	}
 
 	for (i = 0, pfn = 0; i < pagecount; i++) {
-		pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE);
+		/*
+		 * Use slow_virt_to_phys() because the PRESENT bit has been
+		 * temporarily cleared in the PTEs.  slow_virt_to_phys() works
+		 * without the PRESENT bit while virt_to_hvpfn() or similar
+		 * does not.
+		 */
+		vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE);
+		paddr = slow_virt_to_phys(vaddr);
+		pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT;
 		pfn++;
 
 		if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
@@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 		}
 	}
 
- err_free_pfn_array:
+err_free_pfn_array:
 	kfree(pfn_array);
+
+err_set_memory_p:
+	/*
+	 * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present()
+	 * did. Do this even if there is an error earlier in this function in
+	 * order to avoid leaving the memory range in a "broken" state. Setting
+	 * the PRESENT bits shouldn't fail, but return an error if it does.
+	 */
+	if (set_memory_p(kbuffer, pagecount))
+		result = false;
+
 	return result;
 }
 
 static bool hv_vtom_tlb_flush_required(bool private)
 {
-	return true;
+	/*
+	 * Since hv_vtom_clear_present() marks the PTEs as "not present"
+	 * and flushes the TLB, they can't be in the TLB. That makes the
+	 * flush controlled by this function redundant, so return "false".
+	 */
+	return false;
 }
 
 static bool hv_vtom_cache_flush_required(void)
@@ -608,6 +662,7 @@ void __init hv_vtom_init(void)
 	x86_platform.hyper.is_private_mmio = hv_is_private_mmio;
 	x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required;
 	x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required;
+	x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present;
 	x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility;
 
 	/* Set WB as the default cache mode. */