WSL2-Linux-Kernel/arch/powerpc/platforms/pseries/smp.c

290 строки
6.8 KiB
C
Исходник Обычный вид История

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* SMP support for pSeries machines.
*
* Dave Engebretsen, Peter Bergner, and
* Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
*
* Plus various changes from other IBM teams...
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/device.h>
#include <linux/cpu.h>
mm: reorder includes after introduction of linux/pgtable.h The replacement of <asm/pgrable.h> with <linux/pgtable.h> made the include of the latter in the middle of asm includes. Fix this up with the aid of the below script and manual adjustments here and there. import sys import re if len(sys.argv) is not 3: print "USAGE: %s <file> <header>" % (sys.argv[0]) sys.exit(1) hdr_to_move="#include <linux/%s>" % sys.argv[2] moved = False in_hdrs = False with open(sys.argv[1], "r") as f: lines = f.readlines() for _line in lines: line = _line.rstrip(' ') if line == hdr_to_move: continue if line.startswith("#include <linux/"): in_hdrs = True elif not moved and in_hdrs: moved = True print hdr_to_move print line Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200514170327.31389-4-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:32:42 +03:00
#include <linux/pgtable.h>
#include <asm/ptrace.h>
#include <linux/atomic.h>
#include <asm/irq.h>
#include <asm/page.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/smp.h>
#include <asm/paca.h>
#include <asm/machdep.h>
#include <asm/cputable.h>
#include <asm/firmware.h>
#include <asm/rtas.h>
#include <asm/vdso_datapage.h>
#include <asm/cputhreads.h>
#include <asm/xics.h>
powerpc/xive: guest exploitation of the XIVE interrupt controller This is the framework for using XIVE in a PowerVM guest. The support is very similar to the native one in a much simpler form. Each source is associated with an Event State Buffer (ESB). This is a two bit state machine which is used to trigger events. The bits are named "P" (pending) and "Q" (queued) and can be controlled by MMIO. The Guest OS registers event (or notifications) queues on which the HW will post event data for a target to notify. Instead of OPAL calls, a set of Hypervisors call are used to configure the interrupt sources and the event/notification queues of the guest: - H_INT_GET_SOURCE_INFO used to obtain the address of the MMIO page of the Event State Buffer (PQ bits) entry associated with the source. - H_INT_SET_SOURCE_CONFIG assigns a source to a "target". - H_INT_GET_SOURCE_CONFIG determines to which "target" and "priority" is assigned to a source - H_INT_GET_QUEUE_INFO returns the address of the notification management page associated with the specified "target" and "priority". - H_INT_SET_QUEUE_CONFIG sets or resets the event queue for a given "target" and "priority". It is also used to set the notification config associated with the queue, only unconditional notification for the moment. Reset is performed with a queue size of 0 and queueing is disabled in that case. - H_INT_GET_QUEUE_CONFIG returns the queue settings for a given "target" and "priority". - H_INT_RESET resets all of the partition's interrupt exploitation structures to their initial state, losing all configuration set via the hcalls H_INT_SET_SOURCE_CONFIG and H_INT_SET_QUEUE_CONFIG. - H_INT_SYNC issue a synchronisation on a source to make sure sure all notifications have reached their queue. As for XICS, the XIVE interface for the guest is described in the device tree under the "interrupt-controller" node. A couple of new properties are specific to XIVE : - "reg" contains the base address and size of the thread interrupt managnement areas (TIMA), also called rings, for the User level and for the Guest OS level. Only the Guest OS level is taken into account today. - "ibm,xive-eq-sizes" the size of the event queues. One cell per size supported, contains log2 of size, in ascending order. - "ibm,xive-lisn-ranges" the interrupt numbers ranges assigned to the guest. These are allocated using a simple bitmap. and also : - "/ibm,plat-res-int-priorities" contains a list of priorities that the hypervisor has reserved for its own use. Tested with a QEMU XIVE model for pseries and with the Power hypervisor. Signed-off-by: Cédric Le Goater <clg@kaod.org> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-08-30 22:46:11 +03:00
#include <asm/xive.h>
#include <asm/dbell.h>
#include <asm/plpar_wrappers.h>
#include <asm/code-patching.h>
#include <asm/svm.h>
#include "pseries.h"
/*
* The Primary thread of each non-boot processor was started from the OF client
* interface by prom_hold_cpus and is spinning on secondary_hold_spinloop.
*/
static cpumask_var_t of_spin_mask;
/* Query where a cpu is now. Return codes #defined in plpar_wrappers.h */
int smp_query_cpu_stopped(unsigned int pcpu)
{
int cpu_status, status;
int qcss_tok = rtas_token("query-cpu-stopped-state");
if (qcss_tok == RTAS_UNKNOWN_SERVICE) {
printk_once(KERN_INFO
"Firmware doesn't support query-cpu-stopped-state\n");
return QCSS_HARDWARE_ERROR;
}
status = rtas_call(qcss_tok, 1, 2, &cpu_status, pcpu);
if (status != 0) {
printk(KERN_ERR
"RTAS query-cpu-stopped-state failed: %i\n", status);
return status;
}
return cpu_status;
}
/**
* smp_startup_cpu() - start the given cpu
*
* At boot time, there is nothing to do for primary threads which were
* started from Open Firmware. For anything else, call RTAS with the
* appropriate start location.
*
* Returns:
* 0 - failure
* 1 - success
*/
static inline int smp_startup_cpu(unsigned int lcpu)
{
int status;
unsigned long start_here =
__pa(ppc_function_entry(generic_secondary_smp_init));
unsigned int pcpu;
int start_cpu;
if (cpumask_test_cpu(lcpu, of_spin_mask))
/* Already started by OF and sitting in spin loop */
return 1;
pcpu = get_hard_smp_processor_id(lcpu);
/* Check to see if the CPU out of FW already for kexec */
if (smp_query_cpu_stopped(pcpu) == QCSS_NOT_STOPPED){
cpumask_set_cpu(lcpu, of_spin_mask);
return 1;
}
/* Fixup atomic count: it exited inside IRQ handler. */
task_thread_info(paca_ptrs[lcpu]->__current)->preempt_count = 0;
powerpc/pseries: remove cede offline state for CPUs This effectively reverts commit 3aa565f53c39 ("powerpc/pseries: Add hooks to put the CPU into an appropriate offline state"), which added an offline mode for CPUs which uses the H_CEDE hcall instead of the architected stop-self RTAS function in order to facilitate "folding" of dedicated mode processors on PowerVM platforms to achieve energy savings. This has been the default offline mode since its introduction. There's nothing about stop-self that would prevent the hypervisor from achieving the energy savings available via H_CEDE, so the original premise of this change appears to be flawed. I also have encountered the claim that the transition to and from ceded state is much faster than stop-self/start-cpu. Certainly we would not want to use stop-self as an *idle* mode. That is what H_CEDE is for. However, this difference is insignificant in the context of Linux CPU hotplug, where the latency of an offline or online operation on current systems is on the order of 100ms, mainly attributable to all the various subsystems' cpuhp callbacks. The cede offline mode also prevents accurate accounting, as discussed before: https://lore.kernel.org/linuxppc-dev/1571740391-3251-1-git-send-email-ego@linux.vnet.ibm.com/ Unconditionally use stop-self to offline processor threads. This is the architected method for offlining CPUs on PAPR systems. The "cede_offline" boot parameter is rendered obsolete. Removing this code enables the removal of the partition suspend code which temporarily onlines all present CPUs. Fixes: 3aa565f53c39 ("powerpc/pseries: Add hooks to put the CPU into an appropriate offline state") Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com> Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200612051238.1007764-2-nathanl@linux.ibm.com
2020-06-12 08:12:21 +03:00
/*
* If the RTAS start-cpu token does not exist then presume the
* cpu is already spinning.
*/
start_cpu = rtas_token("start-cpu");
if (start_cpu == RTAS_UNKNOWN_SERVICE)
return 1;
status = rtas_call(start_cpu, 3, 1, NULL, pcpu, start_here, pcpu);
if (status != 0) {
printk(KERN_ERR "start-cpu failed: %i\n", status);
return 0;
}
return 1;
}
static void smp_setup_cpu(int cpu)
{
powerpc/xive: guest exploitation of the XIVE interrupt controller This is the framework for using XIVE in a PowerVM guest. The support is very similar to the native one in a much simpler form. Each source is associated with an Event State Buffer (ESB). This is a two bit state machine which is used to trigger events. The bits are named "P" (pending) and "Q" (queued) and can be controlled by MMIO. The Guest OS registers event (or notifications) queues on which the HW will post event data for a target to notify. Instead of OPAL calls, a set of Hypervisors call are used to configure the interrupt sources and the event/notification queues of the guest: - H_INT_GET_SOURCE_INFO used to obtain the address of the MMIO page of the Event State Buffer (PQ bits) entry associated with the source. - H_INT_SET_SOURCE_CONFIG assigns a source to a "target". - H_INT_GET_SOURCE_CONFIG determines to which "target" and "priority" is assigned to a source - H_INT_GET_QUEUE_INFO returns the address of the notification management page associated with the specified "target" and "priority". - H_INT_SET_QUEUE_CONFIG sets or resets the event queue for a given "target" and "priority". It is also used to set the notification config associated with the queue, only unconditional notification for the moment. Reset is performed with a queue size of 0 and queueing is disabled in that case. - H_INT_GET_QUEUE_CONFIG returns the queue settings for a given "target" and "priority". - H_INT_RESET resets all of the partition's interrupt exploitation structures to their initial state, losing all configuration set via the hcalls H_INT_SET_SOURCE_CONFIG and H_INT_SET_QUEUE_CONFIG. - H_INT_SYNC issue a synchronisation on a source to make sure sure all notifications have reached their queue. As for XICS, the XIVE interface for the guest is described in the device tree under the "interrupt-controller" node. A couple of new properties are specific to XIVE : - "reg" contains the base address and size of the thread interrupt managnement areas (TIMA), also called rings, for the User level and for the Guest OS level. Only the Guest OS level is taken into account today. - "ibm,xive-eq-sizes" the size of the event queues. One cell per size supported, contains log2 of size, in ascending order. - "ibm,xive-lisn-ranges" the interrupt numbers ranges assigned to the guest. These are allocated using a simple bitmap. and also : - "/ibm,plat-res-int-priorities" contains a list of priorities that the hypervisor has reserved for its own use. Tested with a QEMU XIVE model for pseries and with the Power hypervisor. Signed-off-by: Cédric Le Goater <clg@kaod.org> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-08-30 22:46:11 +03:00
if (xive_enabled())
xive_smp_setup_cpu();
else if (cpu != boot_cpuid)
xics_setup_cpu();
if (firmware_has_feature(FW_FEATURE_SPLPAR))
vpa_init(cpu);
cpumask_clear_cpu(cpu, of_spin_mask);
}
static int smp_pSeries_kick_cpu(int nr)
{
if (nr < 0 || nr >= nr_cpu_ids)
return -EINVAL;
if (!smp_startup_cpu(nr))
return -ENOENT;
/*
* The processor is currently spinning, waiting for the
* cpu_start field to become non-zero After we set cpu_start,
* the processor will continue on to secondary_start
*/
paca_ptrs[nr]->cpu_start = 1;
return 0;
}
powerpc/xive: guest exploitation of the XIVE interrupt controller This is the framework for using XIVE in a PowerVM guest. The support is very similar to the native one in a much simpler form. Each source is associated with an Event State Buffer (ESB). This is a two bit state machine which is used to trigger events. The bits are named "P" (pending) and "Q" (queued) and can be controlled by MMIO. The Guest OS registers event (or notifications) queues on which the HW will post event data for a target to notify. Instead of OPAL calls, a set of Hypervisors call are used to configure the interrupt sources and the event/notification queues of the guest: - H_INT_GET_SOURCE_INFO used to obtain the address of the MMIO page of the Event State Buffer (PQ bits) entry associated with the source. - H_INT_SET_SOURCE_CONFIG assigns a source to a "target". - H_INT_GET_SOURCE_CONFIG determines to which "target" and "priority" is assigned to a source - H_INT_GET_QUEUE_INFO returns the address of the notification management page associated with the specified "target" and "priority". - H_INT_SET_QUEUE_CONFIG sets or resets the event queue for a given "target" and "priority". It is also used to set the notification config associated with the queue, only unconditional notification for the moment. Reset is performed with a queue size of 0 and queueing is disabled in that case. - H_INT_GET_QUEUE_CONFIG returns the queue settings for a given "target" and "priority". - H_INT_RESET resets all of the partition's interrupt exploitation structures to their initial state, losing all configuration set via the hcalls H_INT_SET_SOURCE_CONFIG and H_INT_SET_QUEUE_CONFIG. - H_INT_SYNC issue a synchronisation on a source to make sure sure all notifications have reached their queue. As for XICS, the XIVE interface for the guest is described in the device tree under the "interrupt-controller" node. A couple of new properties are specific to XIVE : - "reg" contains the base address and size of the thread interrupt managnement areas (TIMA), also called rings, for the User level and for the Guest OS level. Only the Guest OS level is taken into account today. - "ibm,xive-eq-sizes" the size of the event queues. One cell per size supported, contains log2 of size, in ascending order. - "ibm,xive-lisn-ranges" the interrupt numbers ranges assigned to the guest. These are allocated using a simple bitmap. and also : - "/ibm,plat-res-int-priorities" contains a list of priorities that the hypervisor has reserved for its own use. Tested with a QEMU XIVE model for pseries and with the Power hypervisor. Signed-off-by: Cédric Le Goater <clg@kaod.org> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-08-30 22:46:11 +03:00
static int pseries_smp_prepare_cpu(int cpu)
{
if (xive_enabled())
return xive_smp_prepare_cpu(cpu);
return 0;
}
/* Cause IPI as setup by the interrupt controller (xics or xive) */
static void (*ic_cause_ipi)(int cpu) __ro_after_init;
/* Use msgsndp doorbells target is a sibling, else use interrupt controller */
static void dbell_or_ic_cause_ipi(int cpu)
{
if (doorbell_try_core_ipi(cpu))
return;
ic_cause_ipi(cpu);
}
static int pseries_cause_nmi_ipi(int cpu)
{
int hwcpu;
if (cpu == NMI_IPI_ALL_OTHERS) {
hwcpu = H_SIGNAL_SYS_RESET_ALL_OTHERS;
} else {
if (cpu < 0) {
WARN_ONCE(true, "incorrect cpu parameter %d", cpu);
return 0;
}
hwcpu = get_hard_smp_processor_id(cpu);
}
if (plpar_signal_sys_reset(hwcpu) == H_SUCCESS)
return 1;
return 0;
}
powerpc/xive: guest exploitation of the XIVE interrupt controller This is the framework for using XIVE in a PowerVM guest. The support is very similar to the native one in a much simpler form. Each source is associated with an Event State Buffer (ESB). This is a two bit state machine which is used to trigger events. The bits are named "P" (pending) and "Q" (queued) and can be controlled by MMIO. The Guest OS registers event (or notifications) queues on which the HW will post event data for a target to notify. Instead of OPAL calls, a set of Hypervisors call are used to configure the interrupt sources and the event/notification queues of the guest: - H_INT_GET_SOURCE_INFO used to obtain the address of the MMIO page of the Event State Buffer (PQ bits) entry associated with the source. - H_INT_SET_SOURCE_CONFIG assigns a source to a "target". - H_INT_GET_SOURCE_CONFIG determines to which "target" and "priority" is assigned to a source - H_INT_GET_QUEUE_INFO returns the address of the notification management page associated with the specified "target" and "priority". - H_INT_SET_QUEUE_CONFIG sets or resets the event queue for a given "target" and "priority". It is also used to set the notification config associated with the queue, only unconditional notification for the moment. Reset is performed with a queue size of 0 and queueing is disabled in that case. - H_INT_GET_QUEUE_CONFIG returns the queue settings for a given "target" and "priority". - H_INT_RESET resets all of the partition's interrupt exploitation structures to their initial state, losing all configuration set via the hcalls H_INT_SET_SOURCE_CONFIG and H_INT_SET_QUEUE_CONFIG. - H_INT_SYNC issue a synchronisation on a source to make sure sure all notifications have reached their queue. As for XICS, the XIVE interface for the guest is described in the device tree under the "interrupt-controller" node. A couple of new properties are specific to XIVE : - "reg" contains the base address and size of the thread interrupt managnement areas (TIMA), also called rings, for the User level and for the Guest OS level. Only the Guest OS level is taken into account today. - "ibm,xive-eq-sizes" the size of the event queues. One cell per size supported, contains log2 of size, in ascending order. - "ibm,xive-lisn-ranges" the interrupt numbers ranges assigned to the guest. These are allocated using a simple bitmap. and also : - "/ibm,plat-res-int-priorities" contains a list of priorities that the hypervisor has reserved for its own use. Tested with a QEMU XIVE model for pseries and with the Power hypervisor. Signed-off-by: Cédric Le Goater <clg@kaod.org> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-08-30 22:46:11 +03:00
static __init void pSeries_smp_probe(void)
{
if (xive_enabled())
xive_smp_probe();
else
xics_smp_probe();
/* No doorbell facility, must use the interrupt controller for IPIs */
if (!cpu_has_feature(CPU_FTR_DBELL))
return;
/* Doorbells can only be used for IPIs between SMT siblings */
if (!cpu_has_feature(CPU_FTR_SMT))
return;
if (is_kvm_guest()) {
/*
* KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp
* faults to the hypervisor which then reads the instruction
* from guest memory, which tends to be slower than using XIVE.
*/
if (xive_enabled())
return;
/*
* XICS hcalls aren't as fast, so we can use msgsndp (which
* also helps exercise KVM emulation), however KVM can't
* emulate secure guests because it can't read the instruction
* out of their memory.
*/
if (is_secure_guest())
return;
}
/*
* Under PowerVM, FSCR[MSGP] is enabled as guest vCPU siblings are
* gang scheduled on the same physical core, so doorbells are always
* faster than the interrupt controller, and they can be used by
* secure guests.
*/
ic_cause_ipi = smp_ops->cause_ipi;
smp_ops->cause_ipi = dbell_or_ic_cause_ipi;
powerpc/xive: guest exploitation of the XIVE interrupt controller This is the framework for using XIVE in a PowerVM guest. The support is very similar to the native one in a much simpler form. Each source is associated with an Event State Buffer (ESB). This is a two bit state machine which is used to trigger events. The bits are named "P" (pending) and "Q" (queued) and can be controlled by MMIO. The Guest OS registers event (or notifications) queues on which the HW will post event data for a target to notify. Instead of OPAL calls, a set of Hypervisors call are used to configure the interrupt sources and the event/notification queues of the guest: - H_INT_GET_SOURCE_INFO used to obtain the address of the MMIO page of the Event State Buffer (PQ bits) entry associated with the source. - H_INT_SET_SOURCE_CONFIG assigns a source to a "target". - H_INT_GET_SOURCE_CONFIG determines to which "target" and "priority" is assigned to a source - H_INT_GET_QUEUE_INFO returns the address of the notification management page associated with the specified "target" and "priority". - H_INT_SET_QUEUE_CONFIG sets or resets the event queue for a given "target" and "priority". It is also used to set the notification config associated with the queue, only unconditional notification for the moment. Reset is performed with a queue size of 0 and queueing is disabled in that case. - H_INT_GET_QUEUE_CONFIG returns the queue settings for a given "target" and "priority". - H_INT_RESET resets all of the partition's interrupt exploitation structures to their initial state, losing all configuration set via the hcalls H_INT_SET_SOURCE_CONFIG and H_INT_SET_QUEUE_CONFIG. - H_INT_SYNC issue a synchronisation on a source to make sure sure all notifications have reached their queue. As for XICS, the XIVE interface for the guest is described in the device tree under the "interrupt-controller" node. A couple of new properties are specific to XIVE : - "reg" contains the base address and size of the thread interrupt managnement areas (TIMA), also called rings, for the User level and for the Guest OS level. Only the Guest OS level is taken into account today. - "ibm,xive-eq-sizes" the size of the event queues. One cell per size supported, contains log2 of size, in ascending order. - "ibm,xive-lisn-ranges" the interrupt numbers ranges assigned to the guest. These are allocated using a simple bitmap. and also : - "/ibm,plat-res-int-priorities" contains a list of priorities that the hypervisor has reserved for its own use. Tested with a QEMU XIVE model for pseries and with the Power hypervisor. Signed-off-by: Cédric Le Goater <clg@kaod.org> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-08-30 22:46:11 +03:00
}
static struct smp_ops_t pseries_smp_ops = {
.message_pass = NULL, /* Use smp_muxed_ipi_message_pass */
.cause_ipi = NULL, /* Filled at runtime by pSeries_smp_probe() */
.cause_nmi_ipi = pseries_cause_nmi_ipi,
.probe = pSeries_smp_probe,
powerpc/xive: guest exploitation of the XIVE interrupt controller This is the framework for using XIVE in a PowerVM guest. The support is very similar to the native one in a much simpler form. Each source is associated with an Event State Buffer (ESB). This is a two bit state machine which is used to trigger events. The bits are named "P" (pending) and "Q" (queued) and can be controlled by MMIO. The Guest OS registers event (or notifications) queues on which the HW will post event data for a target to notify. Instead of OPAL calls, a set of Hypervisors call are used to configure the interrupt sources and the event/notification queues of the guest: - H_INT_GET_SOURCE_INFO used to obtain the address of the MMIO page of the Event State Buffer (PQ bits) entry associated with the source. - H_INT_SET_SOURCE_CONFIG assigns a source to a "target". - H_INT_GET_SOURCE_CONFIG determines to which "target" and "priority" is assigned to a source - H_INT_GET_QUEUE_INFO returns the address of the notification management page associated with the specified "target" and "priority". - H_INT_SET_QUEUE_CONFIG sets or resets the event queue for a given "target" and "priority". It is also used to set the notification config associated with the queue, only unconditional notification for the moment. Reset is performed with a queue size of 0 and queueing is disabled in that case. - H_INT_GET_QUEUE_CONFIG returns the queue settings for a given "target" and "priority". - H_INT_RESET resets all of the partition's interrupt exploitation structures to their initial state, losing all configuration set via the hcalls H_INT_SET_SOURCE_CONFIG and H_INT_SET_QUEUE_CONFIG. - H_INT_SYNC issue a synchronisation on a source to make sure sure all notifications have reached their queue. As for XICS, the XIVE interface for the guest is described in the device tree under the "interrupt-controller" node. A couple of new properties are specific to XIVE : - "reg" contains the base address and size of the thread interrupt managnement areas (TIMA), also called rings, for the User level and for the Guest OS level. Only the Guest OS level is taken into account today. - "ibm,xive-eq-sizes" the size of the event queues. One cell per size supported, contains log2 of size, in ascending order. - "ibm,xive-lisn-ranges" the interrupt numbers ranges assigned to the guest. These are allocated using a simple bitmap. and also : - "/ibm,plat-res-int-priorities" contains a list of priorities that the hypervisor has reserved for its own use. Tested with a QEMU XIVE model for pseries and with the Power hypervisor. Signed-off-by: Cédric Le Goater <clg@kaod.org> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-08-30 22:46:11 +03:00
.prepare_cpu = pseries_smp_prepare_cpu,
.kick_cpu = smp_pSeries_kick_cpu,
.setup_cpu = smp_setup_cpu,
.cpu_bootable = smp_generic_cpu_bootable,
};
/* This is called very early */
void __init smp_init_pseries(void)
{
int i;
pr_debug(" -> smp_init_pSeries()\n");
smp_ops = &pseries_smp_ops;
alloc_bootmem_cpumask_var(&of_spin_mask);
/*
* Mark threads which are still spinning in hold loops
*
* We know prom_init will not have started them if RTAS supports
* query-cpu-stopped-state.
*/
if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) {
if (cpu_has_feature(CPU_FTR_SMT)) {
for_each_present_cpu(i) {
if (cpu_thread_in_core(i) == 0)
cpumask_set_cpu(i, of_spin_mask);
}
} else
cpumask_copy(of_spin_mask, cpu_present_mask);
cpumask_clear_cpu(boot_cpuid, of_spin_mask);
}
/* Non-lpar has additional take/give timebase */
if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
smp_ops->give_timebase = rtas_give_timebase;
smp_ops->take_timebase = rtas_take_timebase;
}
pr_debug(" <- smp_init_pSeries()\n");
}