linux/arch/x86/xen/smp.c

486 lines
11 KiB
C
Raw Normal View History

/*
* Xen SMP support
*
* This file implements the Xen versions of smp_ops. SMP under Xen is
* very straightforward. Bringing a CPU up is simply a matter of
* loading its initial context and setting it running.
*
* IPIs are handled through the Xen event mechanism.
*
* Because virtual CPUs can be scheduled onto any real CPU, there's no
* useful topology information for the kernel to make use of. As a
* result, all CPUs are treated as if they're single-core and
* single-threaded.
*/
#include <linux/sched.h>
#include <linux/err.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/smp.h>
#include <asm/paravirt.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
#include <asm/cpu.h>
#include <xen/interface/xen.h>
#include <xen/interface/vcpu.h>
#include <asm/xen/interface.h>
#include <asm/xen/hypercall.h>
#include <xen/page.h>
#include <xen/events.h>
#include "xen-ops.h"
#include "mmu.h"
cpumask_var_t xen_cpu_initialized_map;
static DEFINE_PER_CPU(int, xen_resched_irq);
static DEFINE_PER_CPU(int, xen_callfunc_irq);
static DEFINE_PER_CPU(int, xen_callfuncsingle_irq);
static DEFINE_PER_CPU(int, xen_debug_irq) = -1;
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
/*
* Reschedule call back. Nothing to do,
* all the work is done automatically when
* we return from the interrupt.
*/
static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
{
inc_irq_stat(irq_resched_count);
return IRQ_HANDLED;
}
static __cpuinit void cpu_bringup(void)
{
int cpu = smp_processor_id();
cpu_init();
touch_softlockup_watchdog();
preempt_disable();
xen_enable_sysenter();
xen_enable_syscall();
cpu = smp_processor_id();
smp_store_cpu_info(cpu);
cpu_data(cpu).x86_max_cores = 1;
set_cpu_sibling_map(cpu);
xen_setup_cpu_clockevents();
set_cpu_online(cpu, true);
percpu_write(cpu_state, CPU_ONLINE);
wmb();
/* We can take interrupts now: we're officially "up". */
local_irq_enable();
wmb(); /* make sure everything is out */
}
static __cpuinit void cpu_bringup_and_idle(void)
{
cpu_bringup();
cpu_idle();
}
static int xen_smp_intr_init(unsigned int cpu)
{
int rc;
const char *resched_name, *callfunc_name, *debug_name;
resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
cpu,
xen_reschedule_interrupt,
IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
resched_name,
NULL);
if (rc < 0)
goto fail;
per_cpu(xen_resched_irq, cpu) = rc;
callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
cpu,
xen_call_function_interrupt,
IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
callfunc_name,
NULL);
if (rc < 0)
goto fail;
per_cpu(xen_callfunc_irq, cpu) = rc;
debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
IRQF_DISABLED | IRQF_PERCPU | IRQF_NOBALANCING,
debug_name, NULL);
if (rc < 0)
goto fail;
per_cpu(xen_debug_irq, cpu) = rc;
callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
cpu,
xen_call_function_single_interrupt,
IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
callfunc_name,
NULL);
if (rc < 0)
goto fail;
per_cpu(xen_callfuncsingle_irq, cpu) = rc;
return 0;
fail:
if (per_cpu(xen_resched_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
if (per_cpu(xen_callfunc_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
if (per_cpu(xen_debug_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu),
NULL);
return rc;
}
static void __init xen_fill_possible_map(void)
{
int i, rc;
for (i = 0; i < nr_cpu_ids; i++) {
rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
if (rc >= 0) {
num_processors++;
set_cpu_possible(i, true);
}
}
}
static void __init xen_smp_prepare_boot_cpu(void)
{
BUG_ON(smp_processor_id() != 0);
native_smp_prepare_boot_cpu();
/* We've switched to the "real" per-cpu gdt, so make sure the
old memory can be recycled */
make_lowmem_page_readwrite(xen_initial_gdt);
xen_setup_vcpu_info_placement();
}
static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
{
unsigned cpu;
xen: implement Xen-specific spinlocks The standard ticket spinlocks are very expensive in a virtual environment, because their performance depends on Xen's scheduler giving vcpus time in the order that they're supposed to take the spinlock. This implements a Xen-specific spinlock, which should be much more efficient. The fast-path is essentially the old Linux-x86 locks, using a single lock byte. The locker decrements the byte; if the result is 0, then they have the lock. If the lock is negative, then locker must spin until the lock is positive again. When there's contention, the locker spin for 2^16[*] iterations waiting to get the lock. If it fails to get the lock in that time, it adds itself to the contention count in the lock and blocks on a per-cpu event channel. When unlocking the spinlock, the locker looks to see if there's anyone blocked waiting for the lock by checking for a non-zero waiter count. If there's a waiter, it traverses the per-cpu "lock_spinners" variable, which contains which lock each CPU is waiting on. It picks one CPU waiting on the lock and sends it an event to wake it up. This allows efficient fast-path spinlock operation, while allowing spinning vcpus to give up their processor time while waiting for a contended lock. [*] 2^16 iterations is threshold at which 98% locks have been taken according to Thomas Friebel's Xen Summit talk "Preventing Guests from Spinning Around". Therefore, we'd expect the lock and unlock slow paths will only be entered 2% of the time. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <clameter@linux-foundation.org> Cc: Petr Tesarik <ptesarik@suse.cz> Cc: Virtualization <virtualization@lists.linux-foundation.org> Cc: Xen devel <xen-devel@lists.xensource.com> Cc: Thomas Friebel <thomas.friebel@amd.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-07 19:07:53 +00:00
xen_init_lock_cpu(0);
smp_store_cpu_info(0);
cpu_data(0).x86_max_cores = 1;
set_cpu_sibling_map(0);
if (xen_smp_intr_init(0))
BUG();
if (!alloc_cpumask_var(&xen_cpu_initialized_map, GFP_KERNEL))
panic("could not allocate xen_cpu_initialized_map\n");
cpumask_copy(xen_cpu_initialized_map, cpumask_of(0));
/* Restrict the possible_map according to max_cpus. */
while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
continue;
set_cpu_possible(cpu, false);
}
for_each_possible_cpu (cpu) {
struct task_struct *idle;
if (cpu == 0)
continue;
idle = fork_idle(cpu);
if (IS_ERR(idle))
panic("failed fork for CPU %d", cpu);
set_cpu_present(cpu, true);
}
}
static __cpuinit int
cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
{
struct vcpu_guest_context *ctxt;
struct desc_struct *gdt;
unsigned long gdt_mfn;
if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
return 0;
ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
if (ctxt == NULL)
return -ENOMEM;
gdt = get_cpu_gdt_table(cpu);
ctxt->flags = VGCF_IN_KERNEL;
ctxt->user_regs.ds = __USER_DS;
ctxt->user_regs.es = __USER_DS;
ctxt->user_regs.ss = __KERNEL_DS;
#ifdef CONFIG_X86_32
ctxt->user_regs.fs = __KERNEL_PERCPU;
ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#else
ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
xen_copy_trap_info(ctxt->trap_ctxt);
ctxt->ldt_ents = 0;
BUG_ON((unsigned long)gdt & ~PAGE_MASK);
gdt_mfn = arbitrary_virt_to_mfn(gdt);
make_lowmem_page_readonly(gdt);
make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
ctxt->gdt_frames[0] = gdt_mfn;
ctxt->gdt_ents = GDT_ENTRIES;
ctxt->user_regs.cs = __KERNEL_CS;
ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
ctxt->kernel_ss = __KERNEL_DS;
ctxt->kernel_sp = idle->thread.sp0;
#ifdef CONFIG_X86_32
ctxt->event_callback_cs = __KERNEL_CS;
ctxt->failsafe_callback_cs = __KERNEL_CS;
#endif
ctxt->event_callback_eip = (unsigned long)xen_hypervisor_callback;
ctxt->failsafe_callback_eip = (unsigned long)xen_failsafe_callback;
per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));
if (HYPERVISOR_vcpu_op(VCPUOP_initialise, cpu, ctxt))
BUG();
kfree(ctxt);
return 0;
}
static int __cpuinit xen_cpu_up(unsigned int cpu)
{
struct task_struct *idle = idle_task(cpu);
int rc;
per_cpu(current_task, cpu) = idle;
#ifdef CONFIG_X86_32
irq_ctx_init(cpu);
#else
clear_tsk_thread_flag(idle, TIF_FORK);
per_cpu(kernel_stack, cpu) =
(unsigned long)task_stack_page(idle) -
KERNEL_STACK_OFFSET + THREAD_SIZE;
#endif
xen_setup_runstate_info(cpu);
xen_setup_timer(cpu);
xen: implement Xen-specific spinlocks The standard ticket spinlocks are very expensive in a virtual environment, because their performance depends on Xen's scheduler giving vcpus time in the order that they're supposed to take the spinlock. This implements a Xen-specific spinlock, which should be much more efficient. The fast-path is essentially the old Linux-x86 locks, using a single lock byte. The locker decrements the byte; if the result is 0, then they have the lock. If the lock is negative, then locker must spin until the lock is positive again. When there's contention, the locker spin for 2^16[*] iterations waiting to get the lock. If it fails to get the lock in that time, it adds itself to the contention count in the lock and blocks on a per-cpu event channel. When unlocking the spinlock, the locker looks to see if there's anyone blocked waiting for the lock by checking for a non-zero waiter count. If there's a waiter, it traverses the per-cpu "lock_spinners" variable, which contains which lock each CPU is waiting on. It picks one CPU waiting on the lock and sends it an event to wake it up. This allows efficient fast-path spinlock operation, while allowing spinning vcpus to give up their processor time while waiting for a contended lock. [*] 2^16 iterations is threshold at which 98% locks have been taken according to Thomas Friebel's Xen Summit talk "Preventing Guests from Spinning Around". Therefore, we'd expect the lock and unlock slow paths will only be entered 2% of the time. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <clameter@linux-foundation.org> Cc: Petr Tesarik <ptesarik@suse.cz> Cc: Virtualization <virtualization@lists.linux-foundation.org> Cc: Xen devel <xen-devel@lists.xensource.com> Cc: Thomas Friebel <thomas.friebel@amd.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-07 19:07:53 +00:00
xen_init_lock_cpu(cpu);
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
/* make sure interrupts start blocked */
per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;
rc = cpu_initialize_context(cpu, idle);
if (rc)
return rc;
if (num_online_cpus() == 1)
alternatives_smp_switch(1);
rc = xen_smp_intr_init(cpu);
if (rc)
return rc;
rc = HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL);
BUG_ON(rc);
while(per_cpu(cpu_state, cpu) != CPU_ONLINE) {
HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
barrier();
}
return 0;
}
static void xen_smp_cpus_done(unsigned int max_cpus)
{
}
#ifdef CONFIG_HOTPLUG_CPU
static int xen_cpu_disable(void)
{
unsigned int cpu = smp_processor_id();
if (cpu == 0)
return -EBUSY;
cpu_disable_common();
load_cr3(swapper_pg_dir);
return 0;
}
static void xen_cpu_die(unsigned int cpu)
{
while (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) {
current->state = TASK_UNINTERRUPTIBLE;
schedule_timeout(HZ/10);
}
unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
if (num_online_cpus() == 1)
alternatives_smp_switch(0);
}
static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
{
play_dead_common();
HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
cpu_bringup();
}
#else /* !CONFIG_HOTPLUG_CPU */
static int xen_cpu_disable(void)
{
return -ENOSYS;
}
static void xen_cpu_die(unsigned int cpu)
{
BUG();
}
static void xen_play_dead(void)
{
BUG();
}
#endif
static void stop_self(void *v)
{
int cpu = smp_processor_id();
/* make sure we're not pinning something down */
load_cr3(swapper_pg_dir);
/* should set up a minimal gdt */
set_cpu_online(cpu, false);
HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL);
BUG();
}
static void xen_smp_send_stop(void)
{
smp_call_function(stop_self, NULL, 0);
}
static void xen_smp_send_reschedule(int cpu)
{
xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
}
static void xen_send_IPI_mask(const struct cpumask *mask,
enum ipi_vector vector)
{
unsigned cpu;
for_each_cpu_and(cpu, mask, cpu_online_mask)
xen_send_IPI_one(cpu, vector);
}
static void xen_smp_send_call_function_ipi(const struct cpumask *mask)
{
int cpu;
xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
/* Make sure other vcpus get a chance to run if they need to. */
for_each_cpu(cpu, mask) {
if (xen_vcpu_stolen(cpu)) {
HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
break;
}
}
}
static void xen_smp_send_call_function_single_ipi(int cpu)
{
xen_send_IPI_mask(cpumask_of(cpu),
XEN_CALL_FUNCTION_SINGLE_VECTOR);
}
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
{
irq_enter();
generic_smp_call_function_interrupt();
inc_irq_stat(irq_call_count);
irq_exit();
return IRQ_HANDLED;
}
static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
{
irq_enter();
generic_smp_call_function_single_interrupt();
inc_irq_stat(irq_call_count);
irq_exit();
return IRQ_HANDLED;
}
static const struct smp_ops xen_smp_ops __initdata = {
.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu,
.smp_prepare_cpus = xen_smp_prepare_cpus,
.smp_cpus_done = xen_smp_cpus_done,
.cpu_up = xen_cpu_up,
.cpu_die = xen_cpu_die,
.cpu_disable = xen_cpu_disable,
.play_dead = xen_play_dead,
.smp_send_stop = xen_smp_send_stop,
.smp_send_reschedule = xen_smp_send_reschedule,
.send_call_func_ipi = xen_smp_send_call_function_ipi,
.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi,
};
void __init xen_smp_init(void)
{
smp_ops = xen_smp_ops;
xen_fill_possible_map();
xen: implement Xen-specific spinlocks The standard ticket spinlocks are very expensive in a virtual environment, because their performance depends on Xen's scheduler giving vcpus time in the order that they're supposed to take the spinlock. This implements a Xen-specific spinlock, which should be much more efficient. The fast-path is essentially the old Linux-x86 locks, using a single lock byte. The locker decrements the byte; if the result is 0, then they have the lock. If the lock is negative, then locker must spin until the lock is positive again. When there's contention, the locker spin for 2^16[*] iterations waiting to get the lock. If it fails to get the lock in that time, it adds itself to the contention count in the lock and blocks on a per-cpu event channel. When unlocking the spinlock, the locker looks to see if there's anyone blocked waiting for the lock by checking for a non-zero waiter count. If there's a waiter, it traverses the per-cpu "lock_spinners" variable, which contains which lock each CPU is waiting on. It picks one CPU waiting on the lock and sends it an event to wake it up. This allows efficient fast-path spinlock operation, while allowing spinning vcpus to give up their processor time while waiting for a contended lock. [*] 2^16 iterations is threshold at which 98% locks have been taken according to Thomas Friebel's Xen Summit talk "Preventing Guests from Spinning Around". Therefore, we'd expect the lock and unlock slow paths will only be entered 2% of the time. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Lameter <clameter@linux-foundation.org> Cc: Petr Tesarik <ptesarik@suse.cz> Cc: Virtualization <virtualization@lists.linux-foundation.org> Cc: Xen devel <xen-devel@lists.xensource.com> Cc: Thomas Friebel <thomas.friebel@amd.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-07 19:07:53 +00:00
xen_init_spinlocks();
}