summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorAndré Fabian Silva Delgado <emulatorman@parabola.nu>2016-03-08 21:17:20 -0300
committerAndré Fabian Silva Delgado <emulatorman@parabola.nu>2016-03-08 21:17:20 -0300
commiteccbe858ce6412b96fc7cb32eb23a3592f64e5f6 (patch)
treeed4f0e52d266bffc68a5b68afcfe69882b917efb /arch/x86
parent0c1ac6822620b9868cfad5b4c2c223c6cd6fbfd8 (diff)
Linux-libre 4.4.4-gnupck-4.4.4-gnu
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/entry/entry_64_compat.S1
-rw-r--r--arch/x86/include/asm/irq.h5
-rw-r--r--arch/x86/kernel/apic/io_apic.c6
-rw-r--r--arch/x86/kernel/apic/vector.c221
-rw-r--r--arch/x86/kernel/irq.c11
-rw-r--r--arch/x86/kvm/emulate.c4
-rw-r--r--arch/x86/kvm/paging_tmpl.h2
-rw-r--r--arch/x86/kvm/x86.c1
-rw-r--r--arch/x86/mm/mpx.c2
9 files changed, 169 insertions, 84 deletions
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 6a1ae3751..15cfebaa7 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -267,6 +267,7 @@ ENTRY(entry_INT80_compat)
* Interrupts are off on entry.
*/
PARAVIRT_ADJUST_EXCEPTION_FRAME
+ ASM_CLAC /* Do this early to minimize exposure */
SWAPGS
/*
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 881b47686..e7de5c9a4 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu);
#define __ARCH_HAS_DO_SOFTIRQ
+struct irq_desc;
+
#ifdef CONFIG_HOTPLUG_CPU
#include <linux/cpumask.h>
extern int check_irq_vectors_for_cpu_disable(void);
extern void fixup_irqs(void);
-extern void irq_force_complete_move(int);
+extern void irq_force_complete_move(struct irq_desc *desc);
#endif
#ifdef CONFIG_HAVE_KVM
@@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
extern void (*x86_platform_ipi_callback)(void);
extern void native_init_IRQ(void);
-struct irq_desc;
extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs);
extern __visible unsigned int do_IRQ(struct pt_regs *regs);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f25321894..fdb0fbfb1 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void)
{
int pin, ioapic, irq, irq_entry;
const struct cpumask *mask;
+ struct irq_desc *desc;
struct irq_data *idata;
struct irq_chip *chip;
@@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void)
if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq))
continue;
- idata = irq_get_irq_data(irq);
+ desc = irq_to_desc(irq);
+ raw_spin_lock_irq(&desc->lock);
+ idata = irq_desc_get_irq_data(desc);
/*
* Honour affinities which have been set in early boot
@@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void)
/* Might be lapic_chip for irq 0 */
if (chip->irq_set_affinity)
chip->irq_set_affinity(idata, mask, false);
+ raw_spin_unlock_irq(&desc->lock);
}
}
#endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 861bc59c8..a35f6b547 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -30,7 +30,7 @@ struct apic_chip_data {
struct irq_domain *x86_vector_domain;
static DEFINE_RAW_SPINLOCK(vector_lock);
-static cpumask_var_t vector_cpumask;
+static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask;
static struct irq_chip lapic_controller;
#ifdef CONFIG_X86_IO_APIC
static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
@@ -116,35 +116,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d,
*/
static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
static int current_offset = VECTOR_OFFSET_START % 16;
- int cpu, err;
+ int cpu, vector;
- if (d->move_in_progress)
+ /*
+ * If there is still a move in progress or the previous move has not
+ * been cleaned up completely, tell the caller to come back later.
+ */
+ if (d->move_in_progress ||
+ cpumask_intersects(d->old_domain, cpu_online_mask))
return -EBUSY;
/* Only try and allocate irqs on cpus that are present */
- err = -ENOSPC;
cpumask_clear(d->old_domain);
+ cpumask_clear(searched_cpumask);
cpu = cpumask_first_and(mask, cpu_online_mask);
while (cpu < nr_cpu_ids) {
- int new_cpu, vector, offset;
+ int new_cpu, offset;
+ /* Get the possible target cpus for @mask/@cpu from the apic */
apic->vector_allocation_domain(cpu, vector_cpumask, mask);
+ /*
+ * Clear the offline cpus from @vector_cpumask for searching
+ * and verify whether the result overlaps with @mask. If true,
+ * then the call to apic->cpu_mask_to_apicid_and() will
+ * succeed as well. If not, no point in trying to find a
+ * vector in this mask.
+ */
+ cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask);
+ if (!cpumask_intersects(vector_searchmask, mask))
+ goto next_cpu;
+
if (cpumask_subset(vector_cpumask, d->domain)) {
- err = 0;
if (cpumask_equal(vector_cpumask, d->domain))
- break;
+ goto success;
/*
- * New cpumask using the vector is a proper subset of
- * the current in use mask. So cleanup the vector
- * allocation for the members that are not used anymore.
+ * Mark the cpus which are not longer in the mask for
+ * cleanup.
*/
- cpumask_andnot(d->old_domain, d->domain,
- vector_cpumask);
- d->move_in_progress =
- cpumask_intersects(d->old_domain, cpu_online_mask);
- cpumask_and(d->domain, d->domain, vector_cpumask);
- break;
+ cpumask_andnot(d->old_domain, d->domain, vector_cpumask);
+ vector = d->cfg.vector;
+ goto update;
}
vector = current_vector;
@@ -156,45 +168,60 @@ next:
vector = FIRST_EXTERNAL_VECTOR + offset;
}
- if (unlikely(current_vector == vector)) {
- cpumask_or(d->old_domain, d->old_domain,
- vector_cpumask);
- cpumask_andnot(vector_cpumask, mask, d->old_domain);
- cpu = cpumask_first_and(vector_cpumask,
- cpu_online_mask);
- continue;
- }
+ /* If the search wrapped around, try the next cpu */
+ if (unlikely(current_vector == vector))
+ goto next_cpu;
if (test_bit(vector, used_vectors))
goto next;
- for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
+ for_each_cpu(new_cpu, vector_searchmask) {
if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
goto next;
}
/* Found one! */
current_vector = vector;
current_offset = offset;
- if (d->cfg.vector) {
+ /* Schedule the old vector for cleanup on all cpus */
+ if (d->cfg.vector)
cpumask_copy(d->old_domain, d->domain);
- d->move_in_progress =
- cpumask_intersects(d->old_domain, cpu_online_mask);
- }
- for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
+ for_each_cpu(new_cpu, vector_searchmask)
per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
- d->cfg.vector = vector;
- cpumask_copy(d->domain, vector_cpumask);
- err = 0;
- break;
- }
+ goto update;
- if (!err) {
- /* cache destination APIC IDs into cfg->dest_apicid */
- err = apic->cpu_mask_to_apicid_and(mask, d->domain,
- &d->cfg.dest_apicid);
+next_cpu:
+ /*
+ * We exclude the current @vector_cpumask from the requested
+ * @mask and try again with the next online cpu in the
+ * result. We cannot modify @mask, so we use @vector_cpumask
+ * as a temporary buffer here as it will be reassigned when
+ * calling apic->vector_allocation_domain() above.
+ */
+ cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask);
+ cpumask_andnot(vector_cpumask, mask, searched_cpumask);
+ cpu = cpumask_first_and(vector_cpumask, cpu_online_mask);
+ continue;
}
+ return -ENOSPC;
- return err;
+update:
+ /*
+ * Exclude offline cpus from the cleanup mask and set the
+ * move_in_progress flag when the result is not empty.
+ */
+ cpumask_and(d->old_domain, d->old_domain, cpu_online_mask);
+ d->move_in_progress = !cpumask_empty(d->old_domain);
+ d->cfg.vector = vector;
+ cpumask_copy(d->domain, vector_cpumask);
+success:
+ /*
+ * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail
+ * as we already established, that mask & d->domain & cpu_online_mask
+ * is not empty.
+ */
+ BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain,
+ &d->cfg.dest_apicid));
+ return 0;
}
static int assign_irq_vector(int irq, struct apic_chip_data *data,
@@ -224,10 +251,8 @@ static int assign_irq_vector_policy(int irq, int node,
static void clear_irq_vector(int irq, struct apic_chip_data *data)
{
struct irq_desc *desc;
- unsigned long flags;
int cpu, vector;
- raw_spin_lock_irqsave(&vector_lock, flags);
BUG_ON(!data->cfg.vector);
vector = data->cfg.vector;
@@ -237,10 +262,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
data->cfg.vector = 0;
cpumask_clear(data->domain);
- if (likely(!data->move_in_progress)) {
- raw_spin_unlock_irqrestore(&vector_lock, flags);
+ /*
+ * If move is in progress or the old_domain mask is not empty,
+ * i.e. the cleanup IPI has not been processed yet, we need to remove
+ * the old references to desc from all cpus vector tables.
+ */
+ if (!data->move_in_progress && cpumask_empty(data->old_domain))
return;
- }
desc = irq_to_desc(irq);
for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
@@ -253,7 +281,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
}
}
data->move_in_progress = 0;
- raw_spin_unlock_irqrestore(&vector_lock, flags);
}
void init_irq_alloc_info(struct irq_alloc_info *info,
@@ -274,19 +301,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
static void x86_vector_free_irqs(struct irq_domain *domain,
unsigned int virq, unsigned int nr_irqs)
{
+ struct apic_chip_data *apic_data;
struct irq_data *irq_data;
+ unsigned long flags;
int i;
for (i = 0; i < nr_irqs; i++) {
irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
if (irq_data && irq_data->chip_data) {
+ raw_spin_lock_irqsave(&vector_lock, flags);
clear_irq_vector(virq + i, irq_data->chip_data);
- free_apic_chip_data(irq_data->chip_data);
+ apic_data = irq_data->chip_data;
+ irq_domain_reset_irq_data(irq_data);
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
+ free_apic_chip_data(apic_data);
#ifdef CONFIG_X86_IO_APIC
if (virq + i < nr_legacy_irqs())
legacy_irq_data[virq + i] = NULL;
#endif
- irq_domain_reset_irq_data(irq_data);
}
}
}
@@ -404,6 +436,8 @@ int __init arch_early_irq_init(void)
arch_init_htirq_domain(x86_vector_domain);
BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL));
return arch_early_ioapic_init();
}
@@ -492,14 +526,7 @@ static int apic_set_affinity(struct irq_data *irq_data,
return -EINVAL;
err = assign_irq_vector(irq, data, dest);
- if (err) {
- if (assign_irq_vector(irq, data,
- irq_data_get_affinity_mask(irq_data)))
- pr_err("Failed to recover vector for irq %d\n", irq);
- return err;
- }
-
- return IRQ_SET_MASK_OK;
+ return err ? err : IRQ_SET_MASK_OK;
}
static struct irq_chip lapic_controller = {
@@ -511,20 +538,12 @@ static struct irq_chip lapic_controller = {
#ifdef CONFIG_SMP
static void __send_cleanup_vector(struct apic_chip_data *data)
{
- cpumask_var_t cleanup_mask;
-
- if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
- unsigned int i;
-
- for_each_cpu_and(i, data->old_domain, cpu_online_mask)
- apic->send_IPI_mask(cpumask_of(i),
- IRQ_MOVE_CLEANUP_VECTOR);
- } else {
- cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
- apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
- free_cpumask_var(cleanup_mask);
- }
+ raw_spin_lock(&vector_lock);
+ cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
data->move_in_progress = 0;
+ if (!cpumask_empty(data->old_domain))
+ apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR);
+ raw_spin_unlock(&vector_lock);
}
void send_cleanup_vector(struct irq_cfg *cfg)
@@ -568,12 +587,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
goto unlock;
/*
- * Check if the irq migration is in progress. If so, we
- * haven't received the cleanup request yet for this irq.
+ * Nothing to cleanup if irq migration is in progress
+ * or this cpu is not set in the cleanup mask.
*/
- if (data->move_in_progress)
+ if (data->move_in_progress ||
+ !cpumask_test_cpu(me, data->old_domain))
goto unlock;
+ /*
+ * We have two cases to handle here:
+ * 1) vector is unchanged but the target mask got reduced
+ * 2) vector and the target mask has changed
+ *
+ * #1 is obvious, but in #2 we have two vectors with the same
+ * irq descriptor: the old and the new vector. So we need to
+ * make sure that we only cleanup the old vector. The new
+ * vector has the current @vector number in the config and
+ * this cpu is part of the target mask. We better leave that
+ * one alone.
+ */
if (vector == data->cfg.vector &&
cpumask_test_cpu(me, data->domain))
goto unlock;
@@ -591,6 +623,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
goto unlock;
}
__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+ cpumask_clear_cpu(me, data->old_domain);
unlock:
raw_spin_unlock(&desc->lock);
}
@@ -619,12 +652,48 @@ void irq_complete_move(struct irq_cfg *cfg)
__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
}
-void irq_force_complete_move(int irq)
+/*
+ * Called with @desc->lock held and interrupts disabled.
+ */
+void irq_force_complete_move(struct irq_desc *desc)
{
- struct irq_cfg *cfg = irq_cfg(irq);
+ struct irq_data *irqdata = irq_desc_get_irq_data(desc);
+ struct apic_chip_data *data = apic_chip_data(irqdata);
+ struct irq_cfg *cfg = data ? &data->cfg : NULL;
- if (cfg)
- __irq_complete_move(cfg, cfg->vector);
+ if (!cfg)
+ return;
+
+ __irq_complete_move(cfg, cfg->vector);
+
+ /*
+ * This is tricky. If the cleanup of @data->old_domain has not been
+ * done yet, then the following setaffinity call will fail with
+ * -EBUSY. This can leave the interrupt in a stale state.
+ *
+ * The cleanup cannot make progress because we hold @desc->lock. So in
+ * case @data->old_domain is not yet cleaned up, we need to drop the
+ * lock and acquire it again. @desc cannot go away, because the
+ * hotplug code holds the sparse irq lock.
+ */
+ raw_spin_lock(&vector_lock);
+ /* Clean out all offline cpus (including ourself) first. */
+ cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
+ while (!cpumask_empty(data->old_domain)) {
+ raw_spin_unlock(&vector_lock);
+ raw_spin_unlock(&desc->lock);
+ cpu_relax();
+ raw_spin_lock(&desc->lock);
+ /*
+ * Reevaluate apic_chip_data. It might have been cleared after
+ * we dropped @desc->lock.
+ */
+ data = apic_chip_data(irqdata);
+ if (!data)
+ return;
+ raw_spin_lock(&vector_lock);
+ }
+ raw_spin_unlock(&vector_lock);
}
#endif
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index f8062aaf5..61521dc19 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -462,7 +462,7 @@ void fixup_irqs(void)
* non intr-remapping case, we can't wait till this interrupt
* arrives at this cpu before completing the irq move.
*/
- irq_force_complete_move(irq);
+ irq_force_complete_move(desc);
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
break_affinity = 1;
@@ -470,6 +470,15 @@ void fixup_irqs(void)
}
chip = irq_data_get_irq_chip(data);
+ /*
+ * The interrupt descriptor might have been cleaned up
+ * already, but it is not yet removed from the radix tree
+ */
+ if (!chip) {
+ raw_spin_unlock(&desc->lock);
+ continue;
+ }
+
if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
chip->irq_mask(data);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1505587d0..b9b09fec1 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
u16 sel;
la = seg_base(ctxt, addr.seg) + addr.ea;
- *linear = la;
*max_size = 0;
switch (mode) {
case X86EMUL_MODE_PROT64:
+ *linear = la;
if (is_noncanonical_address(la))
goto bad;
@@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
goto bad;
break;
default:
+ *linear = la = (u32)la;
usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL,
addr.seg);
if (!usable)
@@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
if (size > *max_size)
goto bad;
}
- la &= (u32)-1;
break;
}
if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 3058a22a6..7be8a2513 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -249,7 +249,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
return ret;
kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
- walker->ptes[level] = pte;
+ walker->ptes[level - 1] = pte;
}
return 0;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a2ed8904..6ef3856aa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2736,6 +2736,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
}
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+ vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index b2fd67da1..ef05755a1 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
break;
}
- if (regno > nr_registers) {
+ if (regno >= nr_registers) {
WARN_ONCE(1, "decoded an instruction with an invalid register");
return -EINVAL;
}