xen: regression and bug fixes for 4.0-rc1

- Fix two regression introduced in 4.0-rc1 affecting PV/PVH guests in
   certain configurations.
 - Prevent pvscsi frontends bypassing backend checks.
 - Allow privcmd hypercalls to be preempted even on kernel with
   voluntary preemption.  This fixes soft-lockups with long running
   toolstack hypercalls (e.g., when creating/destroying large domains).
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.12 (GNU/Linux)
 
 iQEcBAABAgAGBQJU7GDMAAoJEFxbo/MsZsTRj7AIAIFD2Dgu9p56nx6rUA6JOWP9
 2O1VlINEkggUFNCekTJ3HkAjHreC2Ir67nk1PTTfL3ZN+PqxEv+IoUF1XKJxE/G3
 0KchszK0MVnc7UBrUJWRUEpGo92iIC9QBc8MyDN6dGbfV5lT4aHB5ug/aSZqG8HV
 8ITOftfwnVE8ukOK9bSRPZRejnoRMbGUmqpr0X17sE4Zb8+LEf0iO5Yh88NEjzxM
 OD5hL3TGN5uXh6rYHS+U82M1g83G4Q7v10WIN5O96QhA6e5rVbVNsohHpL8IHY5q
 kazw7wBY//SKGCGniACYnh+vZDeNddwCz8chj6S49h272zanMleyolrUjlcMGzQ=
 =xmcy
 -----END PGP SIGNATURE-----

Merge tag 'stable/for-linus-4.0-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen bugfixes from David Vrabel:
 "Xen regression and bug fixes for 4.0-rc1

   - Fix two regressions introduced in 4.0-rc1 affecting PV/PVH guests
     in certain configurations.

   - Prevent pvscsi frontends bypassing backend checks.

   - Allow privcmd hypercalls to be preempted even on kernel with
     voluntary preemption.  This fixes soft-lockups with long running
     toolstack hypercalls (e.g., when creating/destroying large
     domains)"

* tag 'stable/for-linus-4.0-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  x86/xen: Initialize cr4 shadow for 64-bit PV(H) guests
  xen-scsiback: mark pvscsi frontend request consumed only after last read
  x86/xen: allow privcmd hypercalls to be preempted
  x86/xen: Make sure X2APIC_ENABLE bit of MSR_IA32_APICBASE is not set

arch/x86/kernel/entry_32.S

@@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback)
 ENTRY(xen_do_upcall)
 1:	mov %esp, %eax
 	call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  ret_from_intr
 	CFI_ENDPROC
 ENDPROC(xen_hypervisor_callback)

arch/x86/kernel/entry_64.S

@@ -1208,6 +1208,9 @@ ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
 	popq %rsp
 	CFI_DEF_CFA_REGISTER rsp
 	decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  error_exit
 	CFI_ENDPROC
 END(xen_do_hypervisor_callback)

arch/x86/xen/enlighten.c

@@ -1070,6 +1070,23 @@ static inline void xen_write_cr8(unsigned long val)
 	BUG_ON(val);
 }
 #endif
+
+static u64 xen_read_msr_safe(unsigned int msr, int *err)
+{
+	u64 val;
+
+	val = native_read_msr_safe(msr, err);
+	switch (msr) {
+	case MSR_IA32_APICBASE:
+#ifdef CONFIG_X86_X2APIC
+		if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
+#endif
+			val &= ~X2APIC_ENABLE;
+		break;
+	}
+	return val;
+}
+
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
@@ -1240,7 +1257,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 
 	.wbinvd = native_wbinvd,
 
-	.read_msr = native_read_msr_safe,
+	.read_msr = xen_read_msr_safe,
 	.write_msr = xen_write_msr_safe,
 
 	.read_tsc = native_read_tsc,
@@ -1741,6 +1758,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #ifdef CONFIG_X86_32
 	i386_start_kernel();
 #else
+	cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
 	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
 #endif
 }

drivers/xen/Makefile

@@ -2,7 +2,7 @@ ifeq ($(filter y, $(CONFIG_ARM) $(CONFIG_ARM64)),)
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 endif
 obj-$(CONFIG_X86)			+= fallback.o
-obj-y	+= grant-table.o features.o balloon.o manage.o
+obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o
 obj-y	+= events/
 obj-y	+= xenbus/
 

drivers/xen/preempt.c

@@ -0,0 +1,44 @@
+/*
+ * Preemptible hypercalls
+ *
+ * Copyright (C) 2014 Citrix Systems R&D ltd.
+ *
+ * This source code is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <xen/xen-ops.h>
+
+#ifndef CONFIG_PREEMPT
+
+/*
+ * Some hypercalls issued by the toolstack can take many 10s of
+ * seconds. Allow tasks running hypercalls via the privcmd driver to
+ * be voluntarily preempted even if full kernel preemption is
+ * disabled.
+ *
+ * Such preemptible hypercalls are bracketed by
+ * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
+ * calls.
+ */
+
+DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
+EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
+
+asmlinkage __visible void xen_maybe_preempt_hcall(void)
+{
+	if (unlikely(__this_cpu_read(xen_in_preemptible_hcall)
+		     && should_resched())) {
+		/*
+		 * Clear flag as we may be rescheduled on a different
+		 * cpu.
+		 */
+		__this_cpu_write(xen_in_preemptible_hcall, false);
+		_cond_resched();
+		__this_cpu_write(xen_in_preemptible_hcall, true);
+	}
+}
+#endif /* CONFIG_PREEMPT */

drivers/xen/privcmd.c

@@ -56,10 +56,12 @@ static long privcmd_ioctl_hypercall(void __user *udata)
 	if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
 		return -EFAULT;
 
+	xen_preemptible_hcall_begin();
 	ret = privcmd_call(hypercall.op,
 			   hypercall.arg[0], hypercall.arg[1],
 			   hypercall.arg[2], hypercall.arg[3],
 			   hypercall.arg[4]);
+	xen_preemptible_hcall_end();
 
 	return ret;
 }

drivers/xen/xen-scsiback.c

@@ -709,12 +709,11 @@ static int prepare_pending_reqs(struct vscsibk_info *info,
 static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 {
 	struct vscsiif_back_ring *ring = &info->ring;
-	struct vscsiif_request *ring_req;
+	struct vscsiif_request ring_req;
 	struct vscsibk_pend *pending_req;
 	RING_IDX rc, rp;
 	int err, more_to_do;
 	uint32_t result;
-	uint8_t act;
 
 	rc = ring->req_cons;
 	rp = ring->sring->req_prod;
@@ -735,11 +734,10 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 		if (!pending_req)
 			return 1;
 
-		ring_req = RING_GET_REQUEST(ring, rc);
+		ring_req = *RING_GET_REQUEST(ring, rc);
 		ring->req_cons = ++rc;
 
-		act = ring_req->act;
-		err = prepare_pending_reqs(info, ring_req, pending_req);
+		err = prepare_pending_reqs(info, &ring_req, pending_req);
 		if (err) {
 			switch (err) {
 			case -ENODEV:
@@ -755,9 +753,9 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 			return 1;
 		}
 
-		switch (act) {
+		switch (ring_req.act) {
 		case VSCSIIF_ACT_SCSI_CDB:
-			if (scsiback_gnttab_data_map(ring_req, pending_req)) {
+			if (scsiback_gnttab_data_map(&ring_req, pending_req)) {
 				scsiback_fast_flush_area(pending_req);
 				scsiback_do_resp_with_sense(NULL,
 					DRIVER_ERROR << 24, 0, pending_req);
@@ -768,7 +766,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
 			break;
 		case VSCSIIF_ACT_SCSI_ABORT:
 			scsiback_device_action(pending_req, TMR_ABORT_TASK,
-				ring_req->ref_rqid);
+				ring_req.ref_rqid);
 			break;
 		case VSCSIIF_ACT_SCSI_RESET:
 			scsiback_device_action(pending_req, TMR_LUN_RESET, 0);

include/xen/xen-ops.h

@@ -46,4 +46,30 @@ static inline efi_system_table_t __init *xen_efi_probe(void)
 }
 #endif
 
+#ifdef CONFIG_PREEMPT
+
+static inline void xen_preemptible_hcall_begin(void)
+{
+}
+
+static inline void xen_preemptible_hcall_end(void)
+{
+}
+
+#else
+
+DECLARE_PER_CPU(bool, xen_in_preemptible_hcall);
+
+static inline void xen_preemptible_hcall_begin(void)
+{
+	__this_cpu_write(xen_in_preemptible_hcall, true);
+}
+
+static inline void xen_preemptible_hcall_end(void)
+{
+	__this_cpu_write(xen_in_preemptible_hcall, false);
+}
+
+#endif /* CONFIG_PREEMPT */
+
 #endif /* INCLUDE_XEN_OPS_H */