@@ -31,6 +31,7 @@ DECLARE_PER_CPU(cpumask_var_t, send_ipi_cpumask);
extern bool park_offline_cpus;
void smp_send_nmi_allbutself(void);
+void smp_send_init_sipi_sipi_allbutself(void);
void send_IPI_mask(const cpumask_t *, int vector);
void send_IPI_self(int vector);
@@ -1963,6 +1963,8 @@ void __init noreturn __start_xen(unsigned long mbi_p)
cpu_data[i].stack_base = cpu_alloc_stack(i);
}
+ smp_send_init_sipi_sipi_allbutself();
+
for_each_present_cpu ( i )
{
if ( (park_offline_cpus || num_online_cpus() < max_cpus) &&
@@ -425,7 +425,7 @@ void start_secondary(unsigned int cpu)
static int wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
{
- unsigned long send_status = 0, accept_status = 0;
+ unsigned long send_status = 0, accept_status = 0, sh = 0;
int maxlvt, timeout, i;
/*
@@ -445,6 +445,12 @@ static int wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
if ( tboot_in_measured_env() && !tboot_wake_ap(phys_apicid, start_eip) )
return 0;
+ /*
+ * Use destination shorthand for broadcasting IPIs during boot.
+ */
+ if ( phys_apicid == BAD_APICID )
+ sh = APIC_DEST_ALLBUT;
+
/*
* Be paranoid about clearing APIC errors.
*/
@@ -458,7 +464,7 @@ static int wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
/*
* Turn INIT on target chip via IPI
*/
- apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
+ apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT | sh,
phys_apicid);
if ( !x2apic_enabled )
@@ -475,7 +481,7 @@ static int wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
Dprintk("Deasserting INIT.\n");
- apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
+ apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT | sh, phys_apicid);
Dprintk("Waiting for send to finish...\n");
timeout = 0;
@@ -512,7 +518,7 @@ static int wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
* STARTUP IPI
* Boot on the stack
*/
- apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12), phys_apicid);
+ apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12) | sh, phys_apicid);
if ( !x2apic_enabled )
{
@@ -565,7 +571,6 @@ int alloc_cpu_id(void)
static int do_boot_cpu(int apicid, int cpu)
{
int timeout, boot_error = 0, rc = 0;
- unsigned long start_eip;
/*
* Save current MTRR state in case it was changed since early boot
@@ -573,21 +578,31 @@ static int do_boot_cpu(int apicid, int cpu)
*/
mtrr_save_state();
- start_eip = bootsym_phys(trampoline_realmode_entry);
+ /* Check if AP is already up. */
+ if ( cpu_data[cpu].cpu_state != CPU_STATE_INIT )
+ {
+ /* This grunge runs the startup process for the targeted processor. */
+ unsigned long start_eip;
+ start_eip = bootsym_phys(trampoline_realmode_entry);
- /* start_eip needs be page aligned, and below the 1M boundary. */
- if ( start_eip & ~0xff000 )
- panic("AP trampoline %#lx not suitably positioned\n", start_eip);
+ /* start_eip needs be page aligned, and below the 1M boundary. */
+ if ( start_eip & ~0xff000 )
+ panic("AP trampoline %#lx not suitably positioned\n", start_eip);
- /* So we see what's up */
- if ( opt_cpu_info )
- printk("Booting processor %d/%d eip %lx\n",
- cpu, apicid, start_eip);
+ /* So we see what's up */
+ if ( opt_cpu_info )
+ printk("AP trampoline at %lx\n", start_eip);
- /* This grunge runs the startup process for the targeted processor. */
+ /* mark "stuck" area as not stuck */
+ bootsym(trampoline_cpu_started) = 0;
+ smp_mb();
- /* Starting actual IPI sequence... */
- boot_error = wakeup_secondary_cpu(apicid, start_eip);
+ /* Starting actual IPI sequence... */
+ boot_error = wakeup_secondary_cpu(apicid, start_eip);
+ }
+
+ if ( opt_cpu_info )
+ printk("Booting processor %d/%d\n", cpu, apicid);
if ( !boot_error )
{
@@ -646,10 +661,6 @@ static int do_boot_cpu(int apicid, int cpu)
rc = -EIO;
}
- /* mark "stuck" area as not stuck */
- bootsym(trampoline_cpu_started) = 0;
- smp_mb();
-
return rc;
}
@@ -1155,6 +1166,23 @@ static struct notifier_block cpu_smpboot_nfb = {
.notifier_call = cpu_smpboot_callback
};
+void smp_send_init_sipi_sipi_allbutself(void)
+{
+ unsigned long start_eip;
+ start_eip = bootsym_phys(trampoline_realmode_entry);
+
+ /* start_eip needs be page aligned, and below the 1M boundary. */
+ if ( start_eip & ~0xff000 )
+ panic("AP trampoline %#lx not suitably positioned\n", start_eip);
+
+ /* So we see what's up */
+ if ( opt_cpu_info )
+ printk("Booting APs in parallel, eip %lx\n", start_eip);
+
+ /* Starting actual broadcast IPI sequence... */
+ wakeup_secondary_cpu(BAD_APICID, start_eip);
+}
+
void __init smp_prepare_cpus(void)
{
register_cpu_notifier(&cpu_smpboot_nfb);
Multiple delays are required when sending IPIs and waiting for responses. During boot, 4 such IPIs were sent per each AP. With this change, only one set of broadcast IPIs is sent. This reduces boot time, especially for platforms with large number of cores. Single CPU initialization is still possible, it is used for hotplug. During wakeup from S3 APs are started one by one. It should be possible to enable parallel execution there as well, but I don't have a way of properly testing it as of now. Signed-off-by: Krystian Hebel <krystian.hebel@3mdeb.com> --- xen/arch/x86/include/asm/smp.h | 1 + xen/arch/x86/setup.c | 2 + xen/arch/x86/smpboot.c | 68 ++++++++++++++++++++++++---------- 3 files changed, 51 insertions(+), 20 deletions(-)