Commit 239451e9 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'for-linus-6.3-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip 

Pull xen updates from Juergen Gross:

 - help deprecate the /proc/xen files by making the related information
   available via sysfs

 - mark the Xen variants of play_dead "noreturn"

 - support a shared Xen platform interrupt

 - several small cleanups and fixes

* tag 'for-linus-6.3-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: sysfs: make kobj_type structure constant
  x86/Xen: drop leftover VM-assist uses
  xen: Replace one-element array with flexible-array member
  xen/grant-dma-iommu: Implement a dummy probe_device() callback
  xen/pvcalls-back: fix permanently masked event channel
  xen: Allow platform PCI interrupt to be shared
  x86/xen/time: prefer tsc as clocksource when it is invariant
  x86/xen: mark xen_pv_play_dead() as __noreturn
  x86/xen: don't let xen_pv_play_dead() return
  drivers/xen/hypervisor: Expose Xen SIF flags to userspace
parents b8878e5a 4ecc96cb

Documentation/ABI/stable/sysfs-hypervisor-xen

+13 −0
Original line number Diff line number Diff line
@@ -120,3 +120,16 @@ Contact: xen-devel@lists.xenproject.org 
Description:	If running under Xen:

		The Xen version is in the format <major>.<minor><extra>

		This is the <minor> part of it.



What:		/sys/hypervisor/start_flags/*

Date:		March 2023

KernelVersion:	6.3.0

Contact:	xen-devel@lists.xenproject.org

Description:	If running under Xen:

		All bits in Xen's start-flags are represented as

		boolean files, returning '1' if set, '0' otherwise.

		This takes the place of the defunct /proc/xen/capabilities,

		which would contain "control_d" on dom0, and be empty

		otherwise.  This flag is now exposed as "initdomain" in

		addition to the "privileged" flag; all other possible flags

		are accessible as "unknownXX".

arch/x86/xen/setup.c

+0 −4
Original line number Diff line number Diff line
@@ -934,12 +934,8 @@ void xen_enable_syscall(void) 


static void __init xen_pvmmu_arch_setup(void)

{

	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);

	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);



	HYPERVISOR_vm_assist(VMASST_CMD_enable,

			     VMASST_TYPE_pae_extended_cr3);



	if (register_callback(CALLBACKTYPE_event,

			      xen_asm_exc_xen_hypervisor_callback) ||

	    register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback))

arch/x86/xen/smp.h

+2 −0
Original line number Diff line number Diff line
@@ -21,6 +21,8 @@ void xen_smp_send_reschedule(int cpu); 
void xen_smp_send_call_function_ipi(const struct cpumask *mask);

void xen_smp_send_call_function_single_ipi(int cpu);



void __noreturn xen_cpu_bringup_again(unsigned long stack);



struct xen_common_irq {

	int irq;

	char *name;

arch/x86/xen/smp_pv.c

+4 −13
Original line number Diff line number Diff line
@@ -381,21 +381,12 @@ static void xen_pv_cpu_die(unsigned int cpu) 
	}

}



static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */

static void __noreturn xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */

{

	play_dead_common();

	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL);

	cpu_bringup();

	/*

	 * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)

	 * clears certain data that the cpu_idle loop (which called us

	 * and that we return from) expects. The only way to get that

	 * data back is to call:

	 */

	tick_nohz_idle_enter();

	tick_nohz_idle_stop_tick_protected();



	cpuhp_online_idle(CPUHP_AP_ONLINE_IDLE);

	xen_cpu_bringup_again((unsigned long)task_pt_regs(current));

	BUG();

}



#else /* !CONFIG_HOTPLUG_CPU */
@@ -409,7 +400,7 @@ static void xen_pv_cpu_die(unsigned int cpu) 
	BUG();

}



static void xen_pv_play_dead(void)

static void __noreturn xen_pv_play_dead(void)

{

	BUG();

}

arch/x86/xen/time.c

+37 −1
Original line number Diff line number Diff line
@@ -482,15 +482,51 @@ static void xen_setup_vsyscall_time_info(void) 
	xen_clocksource.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;

}



/*

 * Check if it is possible to safely use the tsc as a clocksource.  This is

 * only true if the hypervisor notifies the guest that its tsc is invariant,

 * the tsc is stable, and the tsc instruction will never be emulated.

 */

static int __init xen_tsc_safe_clocksource(void)

{

	u32 eax, ebx, ecx, edx;



	if (!(boot_cpu_has(X86_FEATURE_CONSTANT_TSC)))

		return 0;



	if (!(boot_cpu_has(X86_FEATURE_NONSTOP_TSC)))

		return 0;



	if (check_tsc_unstable())

		return 0;



	/* Leaf 4, sub-leaf 0 (0x40000x03) */

	cpuid_count(xen_cpuid_base() + 3, 0, &eax, &ebx, &ecx, &edx);



	/* tsc_mode = no_emulate (2) */

	if (ebx != 2)

		return 0;



	return 1;

}



static void __init xen_time_init(void)

{

	struct pvclock_vcpu_time_info *pvti;

	int cpu = smp_processor_id();

	struct timespec64 tp;



	/* As Dom0 is never moved, no penalty on using TSC there */

	/*

	 * As Dom0 is never moved, no penalty on using TSC there.

	 *

	 * If it is possible for the guest to determine that the tsc is a safe

	 * clocksource, then set xen_clocksource rating below that of the tsc

	 * so that the system prefers tsc instead.

	 */

	if (xen_initial_domain())

		xen_clocksource.rating = 275;

	else if (xen_tsc_safe_clocksource())

		xen_clocksource.rating = 299;



	clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC);