linux/arch/x86/kernel/apic/x2apic_cluster.c

245 lines
5.7 KiB
C
Raw Normal View History

#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/dmar.h>
#include <asm/smp.h>
#include <asm/apic.h>
#include <asm/ipi.h>
static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
return x2apic_enabled();
}
x86: Fix MSI-X initialization by using online_mask for x2apic target_cpus found a system where x2apic reports an MSI-X irq initialization failure: [ 302.859446] igbvf 0000:81:10.4: enabling device (0000 -> 0002) [ 302.874369] igbvf 0000:81:10.4: using 64bit DMA mask [ 302.879023] igbvf 0000:81:10.4: using 64bit consistent DMA mask [ 302.894386] igbvf 0000:81:10.4: enabling bus mastering [ 302.898171] igbvf 0000:81:10.4: setting latency timer to 64 [ 302.914050] reserve_memtype added 0xefb08000-0xefb0c000, track uncached-minus, req uncached-minus, ret uncached-minus [ 302.933839] reserve_memtype added 0xefb28000-0xefb29000, track uncached-minus, req uncached-minus, ret uncached-minus [ 302.940367] alloc irq_desc for 265 on node 4 [ 302.956874] alloc kstat_irqs on node 4 [ 302.959452] alloc irq_2_iommu on node 0 [ 302.974328] igbvf 0000:81:10.4: irq 265 for MSI/MSI-X [ 302.977778] alloc irq_desc for 266 on node 4 [ 302.980347] alloc kstat_irqs on node 4 [ 302.995312] free_memtype request 0xefb28000-0xefb29000 [ 302.998816] igbvf 0000:81:10.4: Failed to initialize MSI-X interrupts. ... it turns out that when trying to enable MSI-X, __assign_irq_vector(new, cfg_new, apic->target_cpus()) can not get vector because for x2apic target-cpus returns cpumask_of(0) Update that to online_mask like xapic. Signed-off-by: Yinghai Lu <yinghai@kernel.org> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> LKML-Reference: <4A785AFF.3050902@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-04 15:59:59 +00:00
/*
* need to use more than cpu 0, because we need more vectors when
* MSI-X are used.
*/
static const struct cpumask *x2apic_target_cpus(void)
{
x86: Fix MSI-X initialization by using online_mask for x2apic target_cpus found a system where x2apic reports an MSI-X irq initialization failure: [ 302.859446] igbvf 0000:81:10.4: enabling device (0000 -> 0002) [ 302.874369] igbvf 0000:81:10.4: using 64bit DMA mask [ 302.879023] igbvf 0000:81:10.4: using 64bit consistent DMA mask [ 302.894386] igbvf 0000:81:10.4: enabling bus mastering [ 302.898171] igbvf 0000:81:10.4: setting latency timer to 64 [ 302.914050] reserve_memtype added 0xefb08000-0xefb0c000, track uncached-minus, req uncached-minus, ret uncached-minus [ 302.933839] reserve_memtype added 0xefb28000-0xefb29000, track uncached-minus, req uncached-minus, ret uncached-minus [ 302.940367] alloc irq_desc for 265 on node 4 [ 302.956874] alloc kstat_irqs on node 4 [ 302.959452] alloc irq_2_iommu on node 0 [ 302.974328] igbvf 0000:81:10.4: irq 265 for MSI/MSI-X [ 302.977778] alloc irq_desc for 266 on node 4 [ 302.980347] alloc kstat_irqs on node 4 [ 302.995312] free_memtype request 0xefb28000-0xefb29000 [ 302.998816] igbvf 0000:81:10.4: Failed to initialize MSI-X interrupts. ... it turns out that when trying to enable MSI-X, __assign_irq_vector(new, cfg_new, apic->target_cpus()) can not get vector because for x2apic target-cpus returns cpumask_of(0) Update that to online_mask like xapic. Signed-off-by: Yinghai Lu <yinghai@kernel.org> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> LKML-Reference: <4A785AFF.3050902@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-04 15:59:59 +00:00
return cpu_online_mask;
}
/*
* for now each logical cpu is in its own vector allocation domain.
*/
static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)
{
cpumask_clear(retmask);
cpumask_set_cpu(cpu, retmask);
}
static void
__x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest)
{
unsigned long cfg;
cfg = __prepare_ICR(0, vector, dest);
/*
* send the IPI.
*/
native_x2apic_icr_write(cfg, apicid);
}
/*
* for now, we send the IPI's one by one in the cpumask.
* TBD: Based on the cpu mask, we can send the IPI's to the cluster group
* at once. We have 16 cpu's in a cluster. This will minimize IPI register
* writes.
*/
static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
{
unsigned long query_cpu;
unsigned long flags;
x2apic_wrmsr_fence();
local_irq_save(flags);
for_each_cpu(query_cpu, mask) {
__x2apic_send_IPI_dest(
per_cpu(x86_cpu_to_logical_apicid, query_cpu),
vector, apic->dest_logical);
}
local_irq_restore(flags);
}
static void
x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
{
unsigned long this_cpu = smp_processor_id();
unsigned long query_cpu;
unsigned long flags;
x2apic_wrmsr_fence();
local_irq_save(flags);
for_each_cpu(query_cpu, mask) {
if (query_cpu == this_cpu)
continue;
__x2apic_send_IPI_dest(
per_cpu(x86_cpu_to_logical_apicid, query_cpu),
vector, apic->dest_logical);
}
local_irq_restore(flags);
}
static void x2apic_send_IPI_allbutself(int vector)
{
unsigned long this_cpu = smp_processor_id();
unsigned long query_cpu;
unsigned long flags;
x2apic_wrmsr_fence();
local_irq_save(flags);
for_each_online_cpu(query_cpu) {
if (query_cpu == this_cpu)
continue;
__x2apic_send_IPI_dest(
per_cpu(x86_cpu_to_logical_apicid, query_cpu),
vector, apic->dest_logical);
}
local_irq_restore(flags);
}
static void x2apic_send_IPI_all(int vector)
{
x2apic_send_IPI_mask(cpu_online_mask, vector);
}
static int x2apic_apic_id_registered(void)
{
return 1;
}
static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask)
{
/*
* We're using fixed IRQ delivery, can only return one logical APIC ID.
* May as well be the first.
*/
int cpu = cpumask_first(cpumask);
if ((unsigned)cpu < nr_cpu_ids)
return per_cpu(x86_cpu_to_logical_apicid, cpu);
else
return BAD_APICID;
}
static unsigned int
x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
const struct cpumask *andmask)
{
int cpu;
/*
* We're using fixed IRQ delivery, can only return one logical APIC ID.
* May as well be the first.
*/
for_each_cpu_and(cpu, cpumask, andmask) {
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
}
x86, irq: Allow 0xff for /proc/irq/[n]/smp_affinity on an 8-cpu system John Blackwood reported: > on an older Dell PowerEdge 6650 system with 8 cpus (4 are hyper-threaded), > and 32 bit (x86) kernel, once you change the irq smp_affinity of an irq > to be less than all cpus in the system, you can never change really the > irq smp_affinity back to be all cpus in the system (0xff) again, > even though no error status is returned on the "/bin/echo ff > > /proc/irq/[n]/smp_affinity" operation. > > This is due to that fact that BAD_APICID has the same value as > all cpus (0xff) on 32bit kernels, and thus the value returned from > set_desc_affinity() via the cpu_mask_to_apicid_and() function is treated > as a failure in set_ioapic_affinity_irq_desc(), and no affinity changes > are made. set_desc_affinity() is already checking if the incoming cpu mask intersects with the cpu online mask or not. So there is no need for the apic op cpu_mask_to_apicid_and() to check again and return BAD_APICID. Remove the BAD_APICID return value from cpu_mask_to_apicid_and() and also fix set_desc_affinity() to return -1 instead of using BAD_APICID to represent error conditions (as cpu_mask_to_apicid_and() can return logical or physical apicid values and BAD_APICID is really to represent bad physical apic id). Reported-by: John Blackwood <john.blackwood@ccur.com> Root-caused-by: John Blackwood <john.blackwood@ccur.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> LKML-Reference: <1261103386.2535.409.camel@sbs-t61> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-18 02:29:46 +00:00
return per_cpu(x86_cpu_to_logical_apicid, cpu);
}
static unsigned int x2apic_cluster_phys_get_apic_id(unsigned long x)
{
unsigned int id;
id = x;
return id;
}
static unsigned long set_apic_id(unsigned int id)
{
unsigned long x;
x = id;
return x;
}
static int x2apic_cluster_phys_pkg_id(int initial_apicid, int index_msb)
{
x86: Don't use current_cpu_data in x2apic phys_pkg_id One system has socket 1 come up as BSP. kexeced kernel reports BSP as: [ 1.524550] Initializing cgroup subsys cpuacct [ 1.536064] initial_apicid:20 [ 1.537135] ht_mask_width:1 [ 1.538128] core_select_mask:f [ 1.539126] core_plus_mask_width:5 [ 1.558479] CPU: Physical Processor ID: 0 [ 1.559501] CPU: Processor Core ID: 0 [ 1.560539] CPU: L1 I cache: 32K, L1 D cache: 32K [ 1.579098] CPU: L2 cache: 256K [ 1.580085] CPU: L3 cache: 24576K [ 1.581108] CPU 0/0x20 -> Node 0 [ 1.596193] CPU 0 microcode level: 0xffff0008 It doesn't have correct physical processor id and will get an error: [ 38.840859] CPU0 attaching sched-domain: [ 38.848287] domain 0: span 0,8,72 level SIBLING [ 38.851151] groups: 0 8 72 [ 38.858137] domain 1: span 0,8-15,72-79 level MC [ 38.868944] groups: 0,8,72 9,73 10,74 11,75 12,76 13,77 14,78 15,79 [ 38.881383] ERROR: parent span is not a superset of domain->span [ 38.890724] domain 2: span 0-7,64-71 level CPU [ 38.899237] ERROR: domain->groups does not contain CPU0 [ 38.909229] groups: 8-15,72-79 [ 38.912547] ERROR: groups don't span domain->span [ 38.919665] domain 3: span 0-127 level NODE [ 38.930739] groups: 0-7,64-71 8-15,72-79 16-23,80-87 24-31,88-95 32-39,96-103 40-47,104-111 48-55,112-119 56-63,120-127 it turns out: we can not use current_cpu_data in phys_pgd_id for x2apic. identify_boot_cpu() is called by check_bugs() before smp_prepare_cpus() and till smp_prepare_cpus() current_cpu_data for bsp is assigned with boot_cpu_data. Just make phys_pkg_id for x2apic is aligned to xapic. Signed-off-by: Yinghai Lu <yinghai@kernel.org> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <4A6ADD0D.10002@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-25 10:23:09 +00:00
return initial_apicid >> index_msb;
}
static void x2apic_send_IPI_self(int vector)
{
apic_write(APIC_SELF_IPI, vector);
}
static void init_x2apic_ldr(void)
{
int cpu = smp_processor_id();
per_cpu(x86_cpu_to_logical_apicid, cpu) = apic_read(APIC_LDR);
}
struct apic apic_x2apic_cluster = {
.name = "cluster x2apic",
.probe = NULL,
.acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
.apic_id_registered = x2apic_apic_id_registered,
.irq_delivery_mode = dest_LowestPrio,
.irq_dest_mode = 1, /* logical */
.target_cpus = x2apic_target_cpus,
.disable_esr = 0,
.dest_logical = APIC_DEST_LOGICAL,
.check_apicid_used = NULL,
.check_apicid_present = NULL,
.vector_allocation_domain = x2apic_vector_allocation_domain,
.init_apic_ldr = init_x2apic_ldr,
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
.apicid_to_node = NULL,
.cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,
.check_phys_apicid_present = default_check_phys_apicid_present,
.enable_apic_mode = NULL,
.phys_pkg_id = x2apic_cluster_phys_pkg_id,
.mps_oem_check = NULL,
.get_apic_id = x2apic_cluster_phys_get_apic_id,
.set_apic_id = set_apic_id,
.apic_id_mask = 0xFFFFFFFFu,
.cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
.cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
.send_IPI_mask = x2apic_send_IPI_mask,
.send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
.send_IPI_allbutself = x2apic_send_IPI_allbutself,
.send_IPI_all = x2apic_send_IPI_all,
.send_IPI_self = x2apic_send_IPI_self,
.trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW,
.trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH,
.wait_for_init_deassert = NULL,
.smp_callin_clear_local_apic = NULL,
.inquire_remote_apic = NULL,
.read = native_apic_msr_read,
.write = native_apic_msr_write,
.icr_read = native_x2apic_icr_read,
.icr_write = native_x2apic_icr_write,
.wait_icr_idle = native_x2apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_x2apic_wait_icr_idle,
};