linux_dsm_epyc7002/arch/x86/xen/smp.c

776 lines
19 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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/irq_work.h>
xen/smp: Fixup NOHZ per cpu data when onlining an offline CPU. The xen_play_dead is an undead function. When the vCPU is told to offline it ends up calling xen_play_dead wherin it calls the VCPUOP_down hypercall which offlines the vCPU. However, when the vCPU is onlined back, it resumes execution right after VCPUOP_down hypercall. That was OK (albeit the API for play_dead assumes that the CPU stays dead and never returns) but with commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down) that is no longer safe as said commit resets the ts->inidle which at the start of the cpu_idle loop was set. The net effect is that we get this warn: Broke affinity for irq 16 installing Xen timer for CPU 1 cpu 1 spinlock event irq 48 ------------[ cut here ]------------ WARNING: at /home/konrad/linux-linus/kernel/time/tick-sched.c:935 tick_nohz_idle_exit+0x195/0x1b0() Modules linked in: dm_multipath dm_mod xen_evtchn iscsi_boot_sysfs CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.10.0-rc3upstream-00068-gdcdbe33 #1 Hardware name: BIOSTAR Group N61PB-M2S/N61PB-M2S, BIOS 6.00 PG 09/03/2009 ffffffff8193b448 ffff880039da5e60 ffffffff816707c8 ffff880039da5ea0 ffffffff8108ce8b ffff880039da4010 ffff88003fa8e500 ffff880039da4010 0000000000000001 ffff880039da4000 ffff880039da4010 ffff880039da5eb0 Call Trace: [<ffffffff816707c8>] dump_stack+0x19/0x1b [<ffffffff8108ce8b>] warn_slowpath_common+0x6b/0xa0 [<ffffffff8108ced5>] warn_slowpath_null+0x15/0x20 [<ffffffff810e4745>] tick_nohz_idle_exit+0x195/0x1b0 [<ffffffff810da755>] cpu_startup_entry+0x205/0x250 [<ffffffff81661070>] cpu_bringup_and_idle+0x13/0x15 ---[ end trace 915c8c486004dda1 ]--- b/c ts_inidle is set to zero. Thomas suggested that we just add a workaround to call tick_nohz_idle_enter before returning from xen_play_dead() - and that is what this patch does and fixes the issue. We also add the stable part b/c git commit 4b0c0f294 is on the stable tree. CC: stable@vger.kernel.org Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-06-03 21:33:55 +07:00
#include <linux/tick.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/xen.h>
#include <xen/page.h>
#include <xen/events.h>
#include <xen/hvc-console.h>
#include "xen-ops.h"
#include "mmu.h"
cpumask_var_t xen_cpu_initialized_map;
struct xen_common_irq {
int irq;
char *name;
};
static DEFINE_PER_CPU(struct xen_common_irq, xen_resched_irq) = { .irq = -1 };
static DEFINE_PER_CPU(struct xen_common_irq, xen_callfunc_irq) = { .irq = -1 };
static DEFINE_PER_CPU(struct xen_common_irq, xen_callfuncsingle_irq) = { .irq = -1 };
static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 };
static DEFINE_PER_CPU(struct xen_common_irq, xen_debug_irq) = { .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);
static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id);
/*
* Reschedule call back.
*/
static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
{
inc_irq_stat(irq_resched_count);
scheduler_ipi();
return IRQ_HANDLED;
}
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 05:23:59 +07:00
static void cpu_bringup(void)
{
int cpu;
cpu_init();
touch_softlockup_watchdog();
preempt_disable();
/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
if (!xen_feature(XENFEAT_supervisor_mode_kernel)) {
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();
notify_cpu_starting(cpu);
set_cpu_online(cpu, true);
this_cpu_write(cpu_state, CPU_ONLINE);
wmb();
/* We can take interrupts now: we're officially "up". */
local_irq_enable();
wmb(); /* make sure everything is out */
}
/* Note: cpu parameter is only relevant for PVH */
static void cpu_bringup_and_idle(int cpu)
{
#ifdef CONFIG_X86_64
if (xen_feature(XENFEAT_auto_translated_physmap) &&
xen_feature(XENFEAT_supervisor_mode_kernel))
xen_setup_gdt(cpu);
#endif
cpu_bringup();
cpu_startup_entry(CPUHP_ONLINE);
}
static void xen_smp_intr_free(unsigned int cpu)
{
if (per_cpu(xen_resched_irq, cpu).irq >= 0) {
unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu).irq, NULL);
per_cpu(xen_resched_irq, cpu).irq = -1;
kfree(per_cpu(xen_resched_irq, cpu).name);
per_cpu(xen_resched_irq, cpu).name = NULL;
}
if (per_cpu(xen_callfunc_irq, cpu).irq >= 0) {
unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu).irq, NULL);
per_cpu(xen_callfunc_irq, cpu).irq = -1;
kfree(per_cpu(xen_callfunc_irq, cpu).name);
per_cpu(xen_callfunc_irq, cpu).name = NULL;
}
if (per_cpu(xen_debug_irq, cpu).irq >= 0) {
unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu).irq, NULL);
per_cpu(xen_debug_irq, cpu).irq = -1;
kfree(per_cpu(xen_debug_irq, cpu).name);
per_cpu(xen_debug_irq, cpu).name = NULL;
}
if (per_cpu(xen_callfuncsingle_irq, cpu).irq >= 0) {
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu).irq,
NULL);
per_cpu(xen_callfuncsingle_irq, cpu).irq = -1;
kfree(per_cpu(xen_callfuncsingle_irq, cpu).name);
per_cpu(xen_callfuncsingle_irq, cpu).name = NULL;
}
if (xen_hvm_domain())
return;
if (per_cpu(xen_irq_work, cpu).irq >= 0) {
unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL);
per_cpu(xen_irq_work, cpu).irq = -1;
kfree(per_cpu(xen_irq_work, cpu).name);
per_cpu(xen_irq_work, cpu).name = NULL;
}
};
static int xen_smp_intr_init(unsigned int cpu)
{
int rc;
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_PERCPU|IRQF_NOBALANCING,
resched_name,
NULL);
if (rc < 0)
goto fail;
per_cpu(xen_resched_irq, cpu).irq = rc;
per_cpu(xen_resched_irq, cpu).name = resched_name;
callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
cpu,
xen_call_function_interrupt,
IRQF_PERCPU|IRQF_NOBALANCING,
callfunc_name,
NULL);
if (rc < 0)
goto fail;
per_cpu(xen_callfunc_irq, cpu).irq = rc;
per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
IRQF_PERCPU | IRQF_NOBALANCING,
debug_name, NULL);
if (rc < 0)
goto fail;
per_cpu(xen_debug_irq, cpu).irq = rc;
per_cpu(xen_debug_irq, cpu).name = debug_name;
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_PERCPU|IRQF_NOBALANCING,
callfunc_name,
NULL);
if (rc < 0)
goto fail;
per_cpu(xen_callfuncsingle_irq, cpu).irq = rc;
per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
/*
* The IRQ worker on PVHVM goes through the native path and uses the
* IPI mechanism.
*/
if (xen_hvm_domain())
return 0;
callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
cpu,
xen_irq_work_interrupt,
IRQF_PERCPU|IRQF_NOBALANCING,
callfunc_name,
NULL);
if (rc < 0)
goto fail;
per_cpu(xen_irq_work, cpu).irq = rc;
per_cpu(xen_irq_work, cpu).name = callfunc_name;
return 0;
fail:
xen_smp_intr_free(cpu);
return rc;
}
static void __init xen_fill_possible_map(void)
{
int i, rc;
if (xen_initial_domain())
return;
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_filter_cpu_maps(void)
{
int i, rc;
xen/smp: Fix crash when booting with ACPI hotplug CPUs. When we boot on a machine that can hotplug CPUs and we are using 'dom0_max_vcpus=X' on the Xen hypervisor line to clip the amount of CPUs available to the initial domain, we get this: (XEN) Command line: com1=115200,8n1 dom0_mem=8G noreboot dom0_max_vcpus=8 sync_console mce_verbosity=verbose console=com1,vga loglvl=all guest_loglvl=all .. snip.. DMI: Intel Corporation S2600CP/S2600CP, BIOS SE5C600.86B.99.99.x032.072520111118 07/25/2011 .. snip. SMP: Allowing 64 CPUs, 32 hotplug CPUs installing Xen timer for CPU 7 cpu 7 spinlock event irq 361 NMI watchdog: disabled (cpu7): hardware events not enabled Brought up 8 CPUs .. snip.. [acpi processor finds the CPUs are not initialized and starts calling arch_register_cpu, which creates /sys/devices/system/cpu/cpu8/online] CPU 8 got hotplugged CPU 9 got hotplugged CPU 10 got hotplugged .. snip.. initcall 1_acpi_battery_init_async+0x0/0x1b returned 0 after 406 usecs calling erst_init+0x0/0x2bb @ 1 [and the scheduler sticks newly started tasks on the new CPUs, but said CPUs cannot be initialized b/c the hypervisor has limited the amount of vCPUS to 8 - as per the dom0_max_vcpus=8 flag. The spinlock tries to kick the other CPU, but the structure for that is not initialized and we crash.] BUG: unable to handle kernel paging request at fffffffffffffed8 IP: [<ffffffff81035289>] xen_spin_lock+0x29/0x60 PGD 180d067 PUD 180e067 PMD 0 Oops: 0002 [#1] SMP CPU 7 Modules linked in: Pid: 1, comm: swapper/0 Not tainted 3.4.0-rc2upstream-00001-gf5154e8 #1 Intel Corporation S2600CP/S2600CP RIP: e030:[<ffffffff81035289>] [<ffffffff81035289>] xen_spin_lock+0x29/0x60 RSP: e02b:ffff8801fb9b3a70 EFLAGS: 00010282 With this patch, we cap the amount of vCPUS that the initial domain can run, to exactly what dom0_max_vcpus=X has specified. In the future, if there is a hypercall that will allow a running domain to expand past its initial set of vCPUS, this patch should be re-evaluated. CC: stable@kernel.org Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2012-04-27 00:50:03 +07:00
unsigned int subtract = 0;
if (!xen_initial_domain())
return;
num_processors = 0;
disabled_cpus = 0;
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);
} else {
set_cpu_possible(i, false);
set_cpu_present(i, false);
xen/smp: Fix crash when booting with ACPI hotplug CPUs. When we boot on a machine that can hotplug CPUs and we are using 'dom0_max_vcpus=X' on the Xen hypervisor line to clip the amount of CPUs available to the initial domain, we get this: (XEN) Command line: com1=115200,8n1 dom0_mem=8G noreboot dom0_max_vcpus=8 sync_console mce_verbosity=verbose console=com1,vga loglvl=all guest_loglvl=all .. snip.. DMI: Intel Corporation S2600CP/S2600CP, BIOS SE5C600.86B.99.99.x032.072520111118 07/25/2011 .. snip. SMP: Allowing 64 CPUs, 32 hotplug CPUs installing Xen timer for CPU 7 cpu 7 spinlock event irq 361 NMI watchdog: disabled (cpu7): hardware events not enabled Brought up 8 CPUs .. snip.. [acpi processor finds the CPUs are not initialized and starts calling arch_register_cpu, which creates /sys/devices/system/cpu/cpu8/online] CPU 8 got hotplugged CPU 9 got hotplugged CPU 10 got hotplugged .. snip.. initcall 1_acpi_battery_init_async+0x0/0x1b returned 0 after 406 usecs calling erst_init+0x0/0x2bb @ 1 [and the scheduler sticks newly started tasks on the new CPUs, but said CPUs cannot be initialized b/c the hypervisor has limited the amount of vCPUS to 8 - as per the dom0_max_vcpus=8 flag. The spinlock tries to kick the other CPU, but the structure for that is not initialized and we crash.] BUG: unable to handle kernel paging request at fffffffffffffed8 IP: [<ffffffff81035289>] xen_spin_lock+0x29/0x60 PGD 180d067 PUD 180e067 PMD 0 Oops: 0002 [#1] SMP CPU 7 Modules linked in: Pid: 1, comm: swapper/0 Not tainted 3.4.0-rc2upstream-00001-gf5154e8 #1 Intel Corporation S2600CP/S2600CP RIP: e030:[<ffffffff81035289>] [<ffffffff81035289>] xen_spin_lock+0x29/0x60 RSP: e02b:ffff8801fb9b3a70 EFLAGS: 00010282 With this patch, we cap the amount of vCPUS that the initial domain can run, to exactly what dom0_max_vcpus=X has specified. In the future, if there is a hypercall that will allow a running domain to expand past its initial set of vCPUS, this patch should be re-evaluated. CC: stable@kernel.org Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2012-04-27 00:50:03 +07:00
subtract++;
}
}
xen/smp: Fix crash when booting with ACPI hotplug CPUs. When we boot on a machine that can hotplug CPUs and we are using 'dom0_max_vcpus=X' on the Xen hypervisor line to clip the amount of CPUs available to the initial domain, we get this: (XEN) Command line: com1=115200,8n1 dom0_mem=8G noreboot dom0_max_vcpus=8 sync_console mce_verbosity=verbose console=com1,vga loglvl=all guest_loglvl=all .. snip.. DMI: Intel Corporation S2600CP/S2600CP, BIOS SE5C600.86B.99.99.x032.072520111118 07/25/2011 .. snip. SMP: Allowing 64 CPUs, 32 hotplug CPUs installing Xen timer for CPU 7 cpu 7 spinlock event irq 361 NMI watchdog: disabled (cpu7): hardware events not enabled Brought up 8 CPUs .. snip.. [acpi processor finds the CPUs are not initialized and starts calling arch_register_cpu, which creates /sys/devices/system/cpu/cpu8/online] CPU 8 got hotplugged CPU 9 got hotplugged CPU 10 got hotplugged .. snip.. initcall 1_acpi_battery_init_async+0x0/0x1b returned 0 after 406 usecs calling erst_init+0x0/0x2bb @ 1 [and the scheduler sticks newly started tasks on the new CPUs, but said CPUs cannot be initialized b/c the hypervisor has limited the amount of vCPUS to 8 - as per the dom0_max_vcpus=8 flag. The spinlock tries to kick the other CPU, but the structure for that is not initialized and we crash.] BUG: unable to handle kernel paging request at fffffffffffffed8 IP: [<ffffffff81035289>] xen_spin_lock+0x29/0x60 PGD 180d067 PUD 180e067 PMD 0 Oops: 0002 [#1] SMP CPU 7 Modules linked in: Pid: 1, comm: swapper/0 Not tainted 3.4.0-rc2upstream-00001-gf5154e8 #1 Intel Corporation S2600CP/S2600CP RIP: e030:[<ffffffff81035289>] [<ffffffff81035289>] xen_spin_lock+0x29/0x60 RSP: e02b:ffff8801fb9b3a70 EFLAGS: 00010282 With this patch, we cap the amount of vCPUS that the initial domain can run, to exactly what dom0_max_vcpus=X has specified. In the future, if there is a hypercall that will allow a running domain to expand past its initial set of vCPUS, this patch should be re-evaluated. CC: stable@kernel.org Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2012-04-27 00:50:03 +07:00
#ifdef CONFIG_HOTPLUG_CPU
/* This is akin to using 'nr_cpus' on the Linux command line.
* Which is OK as when we use 'dom0_max_vcpus=X' we can only
* have up to X, while nr_cpu_ids is greater than X. This
* normally is not a problem, except when CPU hotplugging
* is involved and then there might be more than X CPUs
* in the guest - which will not work as there is no
* hypercall to expand the max number of VCPUs an already
* running guest has. So cap it up to X. */
if (subtract)
nr_cpu_ids = nr_cpu_ids - subtract;
#endif
}
static void __init xen_smp_prepare_boot_cpu(void)
{
BUG_ON(smp_processor_id() != 0);
native_smp_prepare_boot_cpu();
xen/smp: Update pv_lock_ops functions before alternative code starts under PVHVM Before this patch we would patch all of the pv_lock_ops sites using alternative assembler. Then later in the bootup cycle change the unlock_kick and lock_spinning to the Xen specific - without re patching. That meant that for the core of the kernel we would be running with the baremetal version of unlock_kick and lock_spinning while for modules we would have the proper Xen specific slowpaths. As most of the module uses some API from the core kernel that ended up with slowpath lockers waiting forever to be kicked (b/c they would be using the Xen specific slowpath logic). And the kick never came b/c the unlock path that was taken was the baremetal one. On PV we do not have the problem as we initialise before the alternative code kicks in. The fix is to make the updating of the pv_lock_ops function be done before the alternative code starts patching. Note that this patch fixes issues discovered by commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23. ("xen: disable PV spinlocks on HVM") wherein it mentioned PV spinlocks cannot possibly work with the current code because they are enabled after pvops patching has already been done, and because PV spinlocks use a different data structure than native spinlocks so we cannot switch between them dynamically. The first problem is solved by this patch. The second problem has been solved by commit 816434ec4a674fcdb3c2221a6dffdc8f34020550 (Merge branch 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip) P.S. There is still the commit 70dd4998cb85f0ecd6ac892cc7232abefa432efb (xen/spinlock: Disable IRQ spinlock (PV) allocation on PVHVM) to revert but that can be done later after all other bugs have been fixed. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com>
2013-08-17 01:39:56 +07:00
if (xen_pv_domain()) {
if (!xen_feature(XENFEAT_writable_page_tables))
/* 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: Fix possible user space selector corruption Due to the way kernel is initialized under Xen is possible that the ring1 selector used by the kernel for the boot cpu end up to be copied to userspace leading to segmentation fault in the userspace. Xen code in the kernel initialize no-boot cpus with correct selectors (ds and es set to __USER_DS) but the boot one keep the ring1 (passed by Xen). On task context switch (switch_to) we assume that ds, es and cs already point to __USER_DS and __KERNEL_CSso these selector are not changed. If processor is an Intel that support sysenter instruction sysenter/sysexit is used so ds and es are not restored switching back from kernel to userspace. In the case the selectors point to a ring1 instead of __USER_DS the userspace code will crash on first memory access attempt (to be precise Xen on the emulated iret used to do sysexit will detect and set ds and es to zero which lead to GPF anyway). Now if an userspace process call kernel using sysenter and get rescheduled (for me it happen on a specific init calling wait4) could happen that the ring1 selector is set to ds and es. This is quite hard to detect cause after a while these selectors are fixed (__USER_DS seems sticky). Bisecting the code commit 7076aada1040de4ed79a5977dbabdb5e5ea5e249 appears to be the first one that have this issue. Signed-off-by: Frediano Ziglio <frediano.ziglio@citrix.com> Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
2013-10-10 21:39:37 +07:00
#ifdef CONFIG_X86_32
/*
* Xen starts us with XEN_FLAT_RING1_DS, but linux code
* expects __USER_DS
*/
loadsegment(ds, __USER_DS);
loadsegment(es, __USER_DS);
#endif
xen/smp: Update pv_lock_ops functions before alternative code starts under PVHVM Before this patch we would patch all of the pv_lock_ops sites using alternative assembler. Then later in the bootup cycle change the unlock_kick and lock_spinning to the Xen specific - without re patching. That meant that for the core of the kernel we would be running with the baremetal version of unlock_kick and lock_spinning while for modules we would have the proper Xen specific slowpaths. As most of the module uses some API from the core kernel that ended up with slowpath lockers waiting forever to be kicked (b/c they would be using the Xen specific slowpath logic). And the kick never came b/c the unlock path that was taken was the baremetal one. On PV we do not have the problem as we initialise before the alternative code kicks in. The fix is to make the updating of the pv_lock_ops function be done before the alternative code starts patching. Note that this patch fixes issues discovered by commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23. ("xen: disable PV spinlocks on HVM") wherein it mentioned PV spinlocks cannot possibly work with the current code because they are enabled after pvops patching has already been done, and because PV spinlocks use a different data structure than native spinlocks so we cannot switch between them dynamically. The first problem is solved by this patch. The second problem has been solved by commit 816434ec4a674fcdb3c2221a6dffdc8f34020550 (Merge branch 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip) P.S. There is still the commit 70dd4998cb85f0ecd6ac892cc7232abefa432efb (xen/spinlock: Disable IRQ spinlock (PV) allocation on PVHVM) to revert but that can be done later after all other bugs have been fixed. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com>
2013-08-17 01:39:56 +07:00
xen_filter_cpu_maps();
xen_setup_vcpu_info_placement();
}
/*
* The alternative logic (which patches the unlock/lock) runs before
* the smp bootup up code is activated. Hence we need to set this up
* the core kernel is being patched. Otherwise we will have only
* modules patched but not core code.
*/
xen_init_spinlocks();
}
static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
{
unsigned cpu;
unsigned int i;
if (skip_ioapic_setup) {
char *m = (max_cpus == 0) ?
"The nosmp parameter is incompatible with Xen; " \
"use Xen dom0_max_vcpus=1 parameter" :
"The noapic parameter is incompatible with Xen";
xen_raw_printk(m);
panic(m);
}
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>
2008-07-08 02:07:53 +07:00
xen_init_lock_cpu(0);
smp_store_boot_cpu_info();
cpu_data(0).x86_max_cores = 1;
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
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)
set_cpu_present(cpu, true);
}
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 05:23:59 +07:00
static 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);
#ifdef CONFIG_X86_32
/* Note: PVH is not yet supported on x86_32. */
ctxt->user_regs.fs = __KERNEL_PERCPU;
ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#endif
ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
ctxt->flags = VGCF_IN_KERNEL;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
ctxt->user_regs.ds = __USER_DS;
ctxt->user_regs.es = __USER_DS;
ctxt->user_regs.ss = __KERNEL_DS;
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->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;
#else
ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
ctxt->event_callback_eip =
(unsigned long)xen_hypervisor_callback;
ctxt->failsafe_callback_eip =
(unsigned long)xen_failsafe_callback;
ctxt->user_regs.cs = __KERNEL_CS;
per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
#ifdef CONFIG_X86_32
}
#else
} else
/* N.B. The user_regs.eip (cpu_bringup_and_idle) is called with
* %rdi having the cpu number - which means are passing in
* as the first parameter the cpu. Subtle!
*/
ctxt->user_regs.rdi = cpu;
#endif
ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
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;
}
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 05:23:59 +07:00
static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
{
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>
2008-07-08 02:07:53 +07:00
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)
/* Just in case we booted with a single CPU. */
alternatives_enable_smp();
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 (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) {
current->state = TASK_UNINTERRUPTIBLE;
schedule_timeout(HZ/10);
}
xen_smp_intr_free(cpu);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
}
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 05:23:59 +07:00
static void xen_play_dead(void) /* used only with HOTPLUG_CPU */
{
play_dead_common();
HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
cpu_bringup();
xen/smp: Fixup NOHZ per cpu data when onlining an offline CPU. The xen_play_dead is an undead function. When the vCPU is told to offline it ends up calling xen_play_dead wherin it calls the VCPUOP_down hypercall which offlines the vCPU. However, when the vCPU is onlined back, it resumes execution right after VCPUOP_down hypercall. That was OK (albeit the API for play_dead assumes that the CPU stays dead and never returns) but with commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down) that is no longer safe as said commit resets the ts->inidle which at the start of the cpu_idle loop was set. The net effect is that we get this warn: Broke affinity for irq 16 installing Xen timer for CPU 1 cpu 1 spinlock event irq 48 ------------[ cut here ]------------ WARNING: at /home/konrad/linux-linus/kernel/time/tick-sched.c:935 tick_nohz_idle_exit+0x195/0x1b0() Modules linked in: dm_multipath dm_mod xen_evtchn iscsi_boot_sysfs CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.10.0-rc3upstream-00068-gdcdbe33 #1 Hardware name: BIOSTAR Group N61PB-M2S/N61PB-M2S, BIOS 6.00 PG 09/03/2009 ffffffff8193b448 ffff880039da5e60 ffffffff816707c8 ffff880039da5ea0 ffffffff8108ce8b ffff880039da4010 ffff88003fa8e500 ffff880039da4010 0000000000000001 ffff880039da4000 ffff880039da4010 ffff880039da5eb0 Call Trace: [<ffffffff816707c8>] dump_stack+0x19/0x1b [<ffffffff8108ce8b>] warn_slowpath_common+0x6b/0xa0 [<ffffffff8108ced5>] warn_slowpath_null+0x15/0x20 [<ffffffff810e4745>] tick_nohz_idle_exit+0x195/0x1b0 [<ffffffff810da755>] cpu_startup_entry+0x205/0x250 [<ffffffff81661070>] cpu_bringup_and_idle+0x13/0x15 ---[ end trace 915c8c486004dda1 ]--- b/c ts_inidle is set to zero. Thomas suggested that we just add a workaround to call tick_nohz_idle_enter before returning from xen_play_dead() - and that is what this patch does and fixes the issue. We also add the stable part b/c git commit 4b0c0f294 is on the stable tree. CC: stable@vger.kernel.org Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-06-03 21:33:55 +07:00
/*
* 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();
}
#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_stop_other_cpus(int wait)
{
smp_call_function(stop_self, NULL, wait);
}
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,
int 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 inline int xen_map_vector(int vector)
{
int xen_vector;
switch (vector) {
case RESCHEDULE_VECTOR:
xen_vector = XEN_RESCHEDULE_VECTOR;
break;
case CALL_FUNCTION_VECTOR:
xen_vector = XEN_CALL_FUNCTION_VECTOR;
break;
case CALL_FUNCTION_SINGLE_VECTOR:
xen_vector = XEN_CALL_FUNCTION_SINGLE_VECTOR;
break;
case IRQ_WORK_VECTOR:
xen_vector = XEN_IRQ_WORK_VECTOR;
break;
xen: Support 64-bit PV guest receiving NMIs This is based on a patch that Zhenzhong Duan had sent - which was missing some of the remaining pieces. The kernel has the logic to handle Xen-type-exceptions using the paravirt interface in the assembler code (see PARAVIRT_ADJUST_EXCEPTION_FRAME - pv_irq_ops.adjust_exception_frame and and INTERRUPT_RETURN - pv_cpu_ops.iret). That means the nmi handler (and other exception handlers) use the hypervisor iret. The other changes that would be neccessary for this would be to translate the NMI_VECTOR to one of the entries on the ipi_vector and make xen_send_IPI_mask_allbutself use different events. Fortunately for us commit 1db01b4903639fcfaec213701a494fe3fb2c490b (xen: Clean up apic ipi interface) implemented this and we piggyback on the cleanup such that the apic IPI interface will pass the right vector value for NMI. With this patch we can trigger NMIs within a PV guest (only tested x86_64). For this to work with normal PV guests (not initial domain) we need the domain to be able to use the APIC ops - they are already implemented to use the Xen event channels. For that to be turned on in a PV domU we need to remove the masking of X86_FEATURE_APIC. Incidentally that means kgdb will also now work within a PV guest without using the 'nokgdbroundup' workaround. Note that the 32-bit version is different and this patch does not enable that. CC: Lisa Nguyen <lisa@xenapiadmin.com> CC: Ben Guthro <benjamin.guthro@citrix.com> CC: Zhenzhong Duan <zhenzhong.duan@oracle.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> [v1: Fixed up per David Vrabel comments] Reviewed-by: Ben Guthro <benjamin.guthro@citrix.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com>
2013-07-19 22:51:31 +07:00
#ifdef CONFIG_X86_64
case NMI_VECTOR:
case APIC_DM_NMI: /* Some use that instead of NMI_VECTOR */
xen_vector = XEN_NMI_VECTOR;
break;
#endif
default:
xen_vector = -1;
printk(KERN_ERR "xen: vector 0x%x is not implemented\n",
vector);
}
return xen_vector;
}
void xen_send_IPI_mask(const struct cpumask *mask,
int vector)
{
int xen_vector = xen_map_vector(vector);
if (xen_vector >= 0)
__xen_send_IPI_mask(mask, xen_vector);
}
void xen_send_IPI_all(int vector)
{
int xen_vector = xen_map_vector(vector);
if (xen_vector >= 0)
__xen_send_IPI_mask(cpu_online_mask, xen_vector);
}
void xen_send_IPI_self(int vector)
{
int xen_vector = xen_map_vector(vector);
if (xen_vector >= 0)
xen_send_IPI_one(smp_processor_id(), xen_vector);
}
void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
int vector)
{
unsigned cpu;
unsigned int this_cpu = smp_processor_id();
int xen_vector = xen_map_vector(vector);
if (!(num_online_cpus() > 1) || (xen_vector < 0))
return;
for_each_cpu_and(cpu, mask, cpu_online_mask) {
if (this_cpu == cpu)
continue;
xen_send_IPI_one(cpu, xen_vector);
}
}
void xen_send_IPI_allbutself(int vector)
{
xen_send_IPI_mask_allbutself(cpu_online_mask, 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 irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
{
irq_enter();
irq_work_run();
inc_irq_stat(apic_irq_work_irqs);
irq_exit();
return IRQ_HANDLED;
}
static const struct smp_ops xen_smp_ops __initconst = {
.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,
.stop_other_cpus = xen_stop_other_cpus,
.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();
}
static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
{
native_smp_prepare_cpus(max_cpus);
WARN_ON(xen_smp_intr_init(0));
xen_init_lock_cpu(0);
}
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 05:23:59 +07:00
static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int rc;
xen/smp: initialize IPI vectors before marking CPU online An older PVHVM guest (v3.0 based) crashed during vCPU hot-plug with: kernel BUG at drivers/xen/events.c:1328! RCU has detected that a CPU has not entered a quiescent state within the grace period. It needs to send the CPU a reschedule IPI if it is not offline. rcu_implicit_offline_qs() does this check: /* * If the CPU is offline, it is in a quiescent state. We can * trust its state not to change because interrupts are disabled. */ if (cpu_is_offline(rdp->cpu)) { rdp->offline_fqs++; return 1; } Else the CPU is online. Send it a reschedule IPI. The CPU is in the middle of being hot-plugged and has been marked online (!cpu_is_offline()). See start_secondary(): set_cpu_online(smp_processor_id(), true); ... per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; start_secondary() then waits for the CPU bringing up the hot-plugged CPU to mark it as active: /* * Wait until the cpu which brought this one up marked it * online before enabling interrupts. If we don't do that then * we can end up waking up the softirq thread before this cpu * reached the active state, which makes the scheduler unhappy * and schedule the softirq thread on the wrong cpu. This is * only observable with forced threaded interrupts, but in * theory it could also happen w/o them. It's just way harder * to achieve. */ while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) cpu_relax(); /* enable local interrupts */ local_irq_enable(); The CPU being hot-plugged will be marked active after it has been fully initialized by the CPU managing the hot-plug. In the Xen PVHVM case xen_smp_intr_init() is called to set up the hot-plugged vCPU's XEN_RESCHEDULE_VECTOR. The hot-plugging CPU is marked online, not marked active and does not have its IPI vectors set up. rcu_implicit_offline_qs() sees the hot-plugging cpu is !cpu_is_offline() and tries to send it a reschedule IPI: This will lead to: kernel BUG at drivers/xen/events.c:1328! xen_send_IPI_one() xen_smp_send_reschedule() rcu_implicit_offline_qs() rcu_implicit_dynticks_qs() force_qs_rnp() force_quiescent_state() __rcu_process_callbacks() rcu_process_callbacks() __do_softirq() call_softirq() do_softirq() irq_exit() xen_evtchn_do_upcall() because xen_send_IPI_one() will attempt to use an uninitialized IRQ for the XEN_RESCHEDULE_VECTOR. There is at least one other place that has caused the same crash: xen_smp_send_reschedule() wake_up_idle_cpu() add_timer_on() clocksource_watchdog() call_timer_fn() run_timer_softirq() __do_softirq() call_softirq() do_softirq() irq_exit() xen_evtchn_do_upcall() xen_hvm_callback_vector() clocksource_watchdog() uses cpu_online_mask to pick the next CPU to handle a watchdog timer: /* * Cycle through CPUs to check if the CPUs stay synchronized * to each other. */ next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = cpumask_first(cpu_online_mask); watchdog_timer.expires += WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, next_cpu); This resulted in an attempt to send an IPI to a hot-plugging CPU that had not initialized its reschedule vector. One option would be to make the RCU code check to not check for CPU offline but for CPU active. As becoming active is done after a CPU is online (in older kernels). But Srivatsa pointed out that "the cpu_active vs cpu_online ordering has been completely reworked - in the online path, cpu_active is set *before* cpu_online, and also, in the cpu offline path, the cpu_active bit is reset in the CPU_DYING notification instead of CPU_DOWN_PREPARE." Drilling in this the bring-up path: "[brought up CPU].. send out a CPU_STARTING notification, and in response to that, the scheduler sets the CPU in the cpu_active_mask. Again, this mask is better left to the scheduler alone, since it has the intelligence to use it judiciously." The conclusion was that: " 1. At the IPI sender side: It is incorrect to send an IPI to an offline CPU (cpu not present in the cpu_online_mask). There are numerous places where we check this and warn/complain. 2. At the IPI receiver side: It is incorrect to let the world know of our presence (by setting ourselves in global bitmasks) until our initialization steps are complete to such an extent that we can handle the consequences (such as receiving interrupts without crashing the sender etc.) " (from Srivatsa) As the native code enables the interrupts at some point we need to be able to service them. In other words a CPU must have valid IPI vectors if it has been marked online. It doesn't need to handle the IPI (interrupts may be disabled) but needs to have valid IPI vectors because another CPU may find it in cpu_online_mask and attempt to send it an IPI. This patch will change the order of the Xen vCPU bring-up functions so that Xen vectors have been set up before start_secondary() is called. It also will not continue to bring up a Xen vCPU if xen_smp_intr_init() fails to initialize it. Orabug 13823853 Signed-off-by Chuck Anderson <chuck.anderson@oracle.com> Acked-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-08-07 05:12:19 +07:00
/*
* xen_smp_intr_init() needs to run before native_cpu_up()
* so that IPI vectors are set up on the booting CPU before
* it is marked online in native_cpu_up().
*/
rc = xen_smp_intr_init(cpu);
WARN_ON(rc);
if (!rc)
rc = native_cpu_up(cpu, tidle);
/*
* We must initialize the slowpath CPU kicker _after_ the native
* path has executed. If we initialized it before none of the
* unlocker IPI kicks would reach the booting CPU as the booting
* CPU had not set itself 'online' in cpu_online_mask. That mask
* is checked when IPIs are sent (on HVM at least).
*/
xen_init_lock_cpu(cpu);
return rc;
}
static void xen_hvm_cpu_die(unsigned int cpu)
{
xen_cpu_die(cpu);
native_cpu_die(cpu);
}
void __init xen_hvm_smp_init(void)
{
if (!xen_have_vector_callback)
return;
smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
smp_ops.cpu_up = xen_hvm_cpu_up;
smp_ops.cpu_die = xen_hvm_cpu_die;
smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
xen/smp: Update pv_lock_ops functions before alternative code starts under PVHVM Before this patch we would patch all of the pv_lock_ops sites using alternative assembler. Then later in the bootup cycle change the unlock_kick and lock_spinning to the Xen specific - without re patching. That meant that for the core of the kernel we would be running with the baremetal version of unlock_kick and lock_spinning while for modules we would have the proper Xen specific slowpaths. As most of the module uses some API from the core kernel that ended up with slowpath lockers waiting forever to be kicked (b/c they would be using the Xen specific slowpath logic). And the kick never came b/c the unlock path that was taken was the baremetal one. On PV we do not have the problem as we initialise before the alternative code kicks in. The fix is to make the updating of the pv_lock_ops function be done before the alternative code starts patching. Note that this patch fixes issues discovered by commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23. ("xen: disable PV spinlocks on HVM") wherein it mentioned PV spinlocks cannot possibly work with the current code because they are enabled after pvops patching has already been done, and because PV spinlocks use a different data structure than native spinlocks so we cannot switch between them dynamically. The first problem is solved by this patch. The second problem has been solved by commit 816434ec4a674fcdb3c2221a6dffdc8f34020550 (Merge branch 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip) P.S. There is still the commit 70dd4998cb85f0ecd6ac892cc7232abefa432efb (xen/spinlock: Disable IRQ spinlock (PV) allocation on PVHVM) to revert but that can be done later after all other bugs have been fixed. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com>
2013-08-17 01:39:56 +07:00
smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu;
}