Merge tag 'for-linus-6.1-rc1-tag' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - Some minor typo fixes

 - A fix of the Xen pcifront driver for supporting the device model to
   run in a Linux stub domain

 - A cleanup of the pcifront driver

 - A series to enable grant-based virtio with Xen on x86

 - A cleanup of Xen PV guests to distinguish between safe and faulting
   MSR accesses

 - Two fixes of the Xen gntdev driver

 - Two fixes of the new xen grant DMA driver

* tag 'for-linus-6.1-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: Kconfig: Fix spelling mistake "Maxmium" -> "Maximum"
  xen/pv: support selecting safe/unsafe msr accesses
  xen/pv: refactor msr access functions to support safe and unsafe accesses
  xen/pv: fix vendor checks for pmu emulation
  xen/pv: add fault recovery control to pmu msr accesses
  xen/virtio: enable grant based virtio on x86
  xen/virtio: use dom0 as default backend for CONFIG_XEN_VIRTIO_FORCE_GRANT
  xen/virtio: restructure xen grant dma setup
  xen/pcifront: move xenstore config scanning into sub-function
  xen/gntdev: Accommodate VMA splitting
  xen/gntdev: Prevent leaking grants
  xen/virtio: Fix potential deadlock when accessing xen_grant_dma_devices
  xen/virtio: Fix n_pages calculation in xen_grant_dma_map(unmap)_page()
  xen/xenbus: Fix spelling mistake "hardward" -> "hardware"
  xen-pcifront: Handle missed Connected state

Documentation/admin-guide/kernel-parameters.txt

@@ -6851,6 +6851,12 @@
 			Crash from Xen panic notifier, without executing late
 			panic() code such as dumping handler.
 
+	xen_msr_safe=	[X86,XEN]
+			Format: <bool>
+			Select whether to always use non-faulting (safe) MSR
+			access functions when running as Xen PV guest. The
+			default value is controlled by CONFIG_XEN_PV_MSR_SAFE.
+
 	xen_nopvspin	[X86,XEN]
 			Disables the qspinlock slowpath using Xen PV optimizations.
 			This parameter is obsoleted by "nopvspin" parameter, which

arch/x86/xen/Kconfig

@@ -92,3 +92,12 @@ config XEN_DOM0
 	select X86_X2APIC if XEN_PVH && X86_64
 	help
 	  Support running as a Xen Dom0 guest.
+
+config XEN_PV_MSR_SAFE
+	bool "Always use safe MSR accesses in PV guests"
+	default y
+	depends on XEN_PV
+	help
+	  Use safe (not faulting) MSR access functions even if the MSR access
+	  should not fault anyway.
+	  The default can be changed by using the "xen_msr_safe" boot parameter.

arch/x86/xen/enlighten_hvm.c

@@ -212,7 +212,7 @@ static void __init xen_hvm_guest_init(void)
 		return;
 
 	if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT))
-		virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
+		virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc);
 
 	init_hvm_pv_info();
 

arch/x86/xen/enlighten_pv.c

@@ -108,11 +108,21 @@ struct tls_descs {
  */
 static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
 
+static __read_mostly bool xen_msr_safe = IS_ENABLED(CONFIG_XEN_PV_MSR_SAFE);
+
+static int __init parse_xen_msr_safe(char *str)
+{
+	if (str)
+		return strtobool(str, &xen_msr_safe);
+	return -EINVAL;
+}
+early_param("xen_msr_safe", parse_xen_msr_safe);
+
 static void __init xen_pv_init_platform(void)
 {
 	/* PV guests can't operate virtio devices without grants. */
 	if (IS_ENABLED(CONFIG_XEN_VIRTIO))
-		virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
+		virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc);
 
 	populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP));
 
@@ -917,14 +927,18 @@ static void xen_write_cr4(unsigned long cr4)
 	native_write_cr4(cr4);
 }
 
-static u64 xen_read_msr_safe(unsigned int msr, int *err)
+static u64 xen_do_read_msr(unsigned int msr, int *err)
 {
-	u64 val;
+	u64 val = 0;	/* Avoid uninitialized value for safe variant. */
 
 	if (pmu_msr_read(msr, &val, err))
 		return val;
 
-	val = native_read_msr_safe(msr, err);
+	if (err)
+		val = native_read_msr_safe(msr, err);
+	else
+		val = native_read_msr(msr);
+
 	switch (msr) {
 	case MSR_IA32_APICBASE:
 		val &= ~X2APIC_ENABLE;
@@ -933,23 +947,39 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 	return val;
 }
 
-static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
+static void set_seg(unsigned int which, unsigned int low, unsigned int high,
+		    int *err)
 {
-	int ret;
-	unsigned int which;
-	u64 base;
+	u64 base = ((u64)high << 32) | low;
 
-	ret = 0;
+	if (HYPERVISOR_set_segment_base(which, base) == 0)
+		return;
 
+	if (err)
+		*err = -EIO;
+	else
+		WARN(1, "Xen set_segment_base(%u, %llx) failed\n", which, base);
+}
+
+/*
+ * Support write_msr_safe() and write_msr() semantics.
+ * With err == NULL write_msr() semantics are selected.
+ * Supplying an err pointer requires err to be pre-initialized with 0.
+ */
+static void xen_do_write_msr(unsigned int msr, unsigned int low,
+			     unsigned int high, int *err)
+{
 	switch (msr) {
-	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
-	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
-	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;
-
-	set:
-		base = ((u64)high << 32) | low;
-		if (HYPERVISOR_set_segment_base(which, base) != 0)
-			ret = -EIO;
+	case MSR_FS_BASE:
+		set_seg(SEGBASE_FS, low, high, err);
+		break;
+
+	case MSR_KERNEL_GS_BASE:
+		set_seg(SEGBASE_GS_USER, low, high, err);
+		break;
+
+	case MSR_GS_BASE:
+		set_seg(SEGBASE_GS_KERNEL, low, high, err);
 		break;
 
 	case MSR_STAR:
@@ -965,31 +995,42 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		break;
 
 	default:
-		if (!pmu_msr_write(msr, low, high, &ret))
-			ret = native_write_msr_safe(msr, low, high);
+		if (!pmu_msr_write(msr, low, high, err)) {
+			if (err)
+				*err = native_write_msr_safe(msr, low, high);
+			else
+				native_write_msr(msr, low, high);
+		}
 	}
+}
 
-	return ret;
+static u64 xen_read_msr_safe(unsigned int msr, int *err)
+{
+	return xen_do_read_msr(msr, err);
+}
+
+static int xen_write_msr_safe(unsigned int msr, unsigned int low,
+			      unsigned int high)
+{
+	int err = 0;
+
+	xen_do_write_msr(msr, low, high, &err);
+
+	return err;
 }
 
 static u64 xen_read_msr(unsigned int msr)
 {
-	/*
-	 * This will silently swallow a #GP from RDMSR.  It may be worth
-	 * changing that.
-	 */
 	int err;
 
-	return xen_read_msr_safe(msr, &err);
+	return xen_do_read_msr(msr, xen_msr_safe ? &err : NULL);
 }
 
 static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
 {
-	/*
-	 * This will silently swallow a #GP from WRMSR.  It may be worth
-	 * changing that.
-	 */
-	xen_write_msr_safe(msr, low, high);
+	int err;
+
+	xen_do_write_msr(msr, low, high, xen_msr_safe ? &err : NULL);
 }
 
 /* This is called once we have the cpu_possible_mask */

arch/x86/xen/pmu.c

@@ -131,6 +131,10 @@ static inline uint32_t get_fam15h_addr(u32 addr)
 
 static inline bool is_amd_pmu_msr(unsigned int msr)
 {
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
+		return false;
+
 	if ((msr >= MSR_F15H_PERF_CTL &&
 	     msr < MSR_F15H_PERF_CTR + (amd_num_counters * 2)) ||
 	    (msr >= MSR_K7_EVNTSEL0 &&
@@ -140,10 +144,15 @@ static inline bool is_amd_pmu_msr(unsigned int msr)
 	return false;
 }
 
-static int is_intel_pmu_msr(u32 msr_index, int *type, int *index)
+static bool is_intel_pmu_msr(u32 msr_index, int *type, int *index)
 {
 	u32 msr_index_pmc;
 
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
+		return false;
+
 	switch (msr_index) {
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 	case MSR_IA32_DS_AREA:
@@ -290,48 +299,52 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
 	return false;
 }
 
+static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read,
+				 bool *emul)
+{
+	int type, index;
+
+	if (is_amd_pmu_msr(msr))
+		*emul = xen_amd_pmu_emulate(msr, val, is_read);
+	else if (is_intel_pmu_msr(msr, &type, &index))
+		*emul = xen_intel_pmu_emulate(msr, val, type, index, is_read);
+	else
+		return false;
+
+	return true;
+}
+
 bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err)
 {
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
-		if (is_amd_pmu_msr(msr)) {
-			if (!xen_amd_pmu_emulate(msr, val, 1))
-				*val = native_read_msr_safe(msr, err);
-			return true;
-		}
-	} else {
-		int type, index;
+	bool emulated;
 
-		if (is_intel_pmu_msr(msr, &type, &index)) {
-			if (!xen_intel_pmu_emulate(msr, val, type, index, 1))
-				*val = native_read_msr_safe(msr, err);
-			return true;
-		}
+	if (!pmu_msr_chk_emulated(msr, val, true, &emulated))
+		return false;
+
+	if (!emulated) {
+		*val = err ? native_read_msr_safe(msr, err)
+			   : native_read_msr(msr);
 	}
 
-	return false;
+	return true;
 }
 
 bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err)
 {
 	uint64_t val = ((uint64_t)high << 32) | low;
+	bool emulated;
 
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
-		if (is_amd_pmu_msr(msr)) {
-			if (!xen_amd_pmu_emulate(msr, &val, 0))
-				*err = native_write_msr_safe(msr, low, high);
-			return true;
-		}
-	} else {
-		int type, index;
+	if (!pmu_msr_chk_emulated(msr, &val, false, &emulated))
+		return false;
 
-		if (is_intel_pmu_msr(msr, &type, &index)) {
-			if (!xen_intel_pmu_emulate(msr, &val, type, index, 0))
-				*err = native_write_msr_safe(msr, low, high);
-			return true;
-		}
+	if (!emulated) {
+		if (err)
+			*err = native_write_msr_safe(msr, low, high);
+		else
+			native_write_msr(msr, low, high);
 	}
 
-	return false;
+	return true;
 }
 
 static unsigned long long xen_amd_read_pmc(int counter)