summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig3
-rw-r--r--arch/x86/Kconfig.debug18
-rw-r--r--arch/x86/entry/entry_64_compat.S1
-rw-r--r--arch/x86/entry/vdso/vdso2c.h2
-rw-r--r--arch/x86/include/asm/cacheflush.h6
-rw-r--r--arch/x86/include/asm/irq.h5
-rw-r--r--arch/x86/include/asm/kvm_para.h7
-rw-r--r--arch/x86/include/asm/sections.h2
-rw-r--r--arch/x86/kernel/acpi/sleep.c7
-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/ftrace.c6
-rw-r--r--arch/x86/kernel/irq.c11
-rw-r--r--arch/x86/kernel/kgdb.c8
-rw-r--r--arch/x86/kernel/test_nx.c2
-rw-r--r--arch/x86/kernel/test_rodata.c2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S25
-rw-r--r--arch/x86/kvm/emulate.c4
-rw-r--r--arch/x86/kvm/mmu.c4
-rw-r--r--arch/x86/kvm/paging_tmpl.h2
-rw-r--r--arch/x86/kvm/vmx.c57
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--arch/x86/mm/init_32.c3
-rw-r--r--arch/x86/mm/init_64.c3
-rw-r--r--arch/x86/mm/mpx.c2
-rw-r--r--arch/x86/mm/pageattr.c16
26 files changed, 257 insertions, 174 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 136ddb36a046..d57eca6b3777 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -306,6 +306,9 @@ config ARCH_SUPPORTS_UPROBES
config FIX_EARLYCON_MEM
def_bool y
+config DEBUG_RODATA
+ def_bool y
+
config PGTABLE_LEVELS
int
default 4 if X86_64
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 137dfa96aa14..1f6c306a9a00 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -91,28 +91,16 @@ config EFI_PGT_DUMP
issues with the mapping of the EFI runtime regions into that
table.
-config DEBUG_RODATA
- bool "Write protect kernel read-only data structures"
- default y
- depends on DEBUG_KERNEL
- ---help---
- Mark the kernel read-only data as write-protected in the pagetables,
- in order to catch accidental (and incorrect) writes to such const
- data. This is recommended so that we can catch kernel bugs sooner.
- If in doubt, say "Y".
-
config DEBUG_RODATA_TEST
- bool "Testcase for the DEBUG_RODATA feature"
- depends on DEBUG_RODATA
+ bool "Testcase for the marking rodata read-only"
default y
---help---
- This option enables a testcase for the DEBUG_RODATA
- feature as well as for the change_page_attr() infrastructure.
+ This option enables a testcase for the setting rodata read-only
+ as well as for the change_page_attr() infrastructure.
If in doubt, say "N"
config DEBUG_WX
bool "Warn on W+X mappings at boot"
- depends on DEBUG_RODATA
select X86_PTDUMP_CORE
---help---
Generate a warning if any W+X mappings are found at boot.
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 6a1ae3751e82..15cfebaa7688 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/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 0224987556ce..3f69326ed545 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -140,7 +140,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
fprintf(outfile, "#include <asm/vdso.h>\n");
fprintf(outfile, "\n");
fprintf(outfile,
- "static unsigned char raw_data[%lu] __page_aligned_data = {",
+ "static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {",
mapping_size);
for (j = 0; j < stripped_len; j++) {
if (j % 10 == 0)
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index e63aa38e85fb..61518cf79437 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -91,16 +91,10 @@ void clflush_cache_range(void *addr, unsigned int size);
#define mmio_flush_range(addr, size) clflush_cache_range(addr, size)
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
extern const int rodata_test_data;
extern int kernel_set_to_readonly;
void set_kernel_text_rw(void);
void set_kernel_text_ro(void);
-#else
-static inline void set_kernel_text_rw(void) { }
-static inline void set_kernel_text_ro(void) { }
-#endif
#ifdef CONFIG_DEBUG_RODATA_TEST
int rodata_test(void);
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 881b4768644a..e7de5c9a4fbd 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/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c1adf33fdd0d..bc62e7cbf1b1 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -17,15 +17,8 @@ static inline bool kvm_check_and_clear_guest_paused(void)
}
#endif /* CONFIG_KVM_GUEST */
-#ifdef CONFIG_DEBUG_RODATA
#define KVM_HYPERCALL \
ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
-#else
-/* On AMD processors, vmcall will generate a trap that we will
- * then rewrite to the appropriate instruction.
- */
-#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
-#endif
/* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
* instruction. The hypervisor may replace it with something else but only the
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 0a5242428659..13b6cdd0af57 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -7,7 +7,7 @@
extern char __brk_base[], __brk_limit[];
extern struct exception_table_entry __stop___ex_table[];
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
extern char __end_rodata_hpage_align[];
#endif
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index d1daead5fcdd..adb3eaf8fe2a 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -16,6 +16,7 @@
#include <asm/cacheflush.h>
#include <asm/realmode.h>
+#include <linux/ftrace.h>
#include "../../realmode/rm/wakeup.h"
#include "sleep.h"
@@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void)
saved_magic = 0x123456789abcdef0L;
#endif /* CONFIG_64BIT */
+ /*
+ * Pause/unpause graph tracing around do_suspend_lowlevel as it has
+ * inconsistent call/return info after it jumps to the wakeup vector.
+ */
+ pause_graph_tracing();
do_suspend_lowlevel();
+ unpause_graph_tracing();
return 0;
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f25321894ad2..fdb0fbfb1197 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 861bc59c8f25..a35f6b5473f4 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/ftrace.c b/arch/x86/kernel/ftrace.c
index 311bcf338f07..eb6bd34582c6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -81,9 +81,9 @@ within(unsigned long addr, unsigned long start, unsigned long end)
static unsigned long text_ip_addr(unsigned long ip)
{
/*
- * On x86_64, kernel text mappings are mapped read-only with
- * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
- * of the kernel text mapping to modify the kernel text.
+ * On x86_64, kernel text mappings are mapped read-only, so we use
+ * the kernel identity mapping instead of the kernel text mapping
+ * to modify the kernel text.
*
* For 32bit kernels, these mappings are same and we can use
* kernel identity mapping to modify code.
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index f8062aaf5df9..61521dc19c10 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/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 44256a62702b..ed15cd486d06 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -750,9 +750,7 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
{
int err;
-#ifdef CONFIG_DEBUG_RODATA
char opc[BREAK_INSTR_SIZE];
-#endif /* CONFIG_DEBUG_RODATA */
bpt->type = BP_BREAKPOINT;
err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
@@ -761,7 +759,6 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
return err;
err = probe_kernel_write((char *)bpt->bpt_addr,
arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
-#ifdef CONFIG_DEBUG_RODATA
if (!err)
return err;
/*
@@ -778,13 +775,12 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
return -EINVAL;
bpt->type = BP_POKE_BREAKPOINT;
-#endif /* CONFIG_DEBUG_RODATA */
+
return err;
}
int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
{
-#ifdef CONFIG_DEBUG_RODATA
int err;
char opc[BREAK_INSTR_SIZE];
@@ -801,8 +797,8 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
goto knl_write;
return err;
+
knl_write:
-#endif /* CONFIG_DEBUG_RODATA */
return probe_kernel_write((char *)bpt->bpt_addr,
(char *)bpt->saved_instr, BREAK_INSTR_SIZE);
}
diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c
index 3f92ce07e525..27538f183c3b 100644
--- a/arch/x86/kernel/test_nx.c
+++ b/arch/x86/kernel/test_nx.c
@@ -142,7 +142,6 @@ static int test_NX(void)
* by the error message
*/
-#ifdef CONFIG_DEBUG_RODATA
/* Test 3: Check if the .rodata section is executable */
if (rodata_test_data != 0xC3) {
printk(KERN_ERR "test_nx: .rodata marker has invalid value\n");
@@ -151,7 +150,6 @@ static int test_NX(void)
printk(KERN_ERR "test_nx: .rodata section is executable\n");
ret = -ENODEV;
}
-#endif
#if 0
/* Test 4: Check if the .data section of a module is executable */
diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c
index 5ecbfe5099da..cb4a01b41e27 100644
--- a/arch/x86/kernel/test_rodata.c
+++ b/arch/x86/kernel/test_rodata.c
@@ -76,5 +76,5 @@ int rodata_test(void)
}
MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Testcase for the DEBUG_RODATA infrastructure");
+MODULE_DESCRIPTION("Testcase for marking rodata as read-only");
MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 74e4bf11f562..fe133b710bef 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -41,29 +41,28 @@ ENTRY(phys_startup_64)
jiffies_64 = jiffies;
#endif
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
/*
- * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA
- * we retain large page mappings for boundaries spanning kernel text, rodata
- * and data sections.
+ * On 64-bit, align RODATA to 2MB so we retain large page mappings for
+ * boundaries spanning kernel text, rodata and data sections.
*
* However, kernel identity mappings will have different RWX permissions
* to the pages mapping to text and to the pages padding (which are freed) the
* text section. Hence kernel identity mappings will be broken to smaller
* pages. For 64-bit, kernel text and kernel identity mappings are different,
- * so we can enable protection checks that come with CONFIG_DEBUG_RODATA,
- * as well as retain 2MB large page mappings for kernel text.
+ * so we can enable protection checks as well as retain 2MB large page
+ * mappings for kernel text.
*/
-#define X64_ALIGN_DEBUG_RODATA_BEGIN . = ALIGN(HPAGE_SIZE);
+#define X64_ALIGN_RODATA_BEGIN . = ALIGN(HPAGE_SIZE);
-#define X64_ALIGN_DEBUG_RODATA_END \
+#define X64_ALIGN_RODATA_END \
. = ALIGN(HPAGE_SIZE); \
__end_rodata_hpage_align = .;
#else
-#define X64_ALIGN_DEBUG_RODATA_BEGIN
-#define X64_ALIGN_DEBUG_RODATA_END
+#define X64_ALIGN_RODATA_BEGIN
+#define X64_ALIGN_RODATA_END
#endif
@@ -112,13 +111,11 @@ SECTIONS
EXCEPTION_TABLE(16) :text = 0x9090
-#if defined(CONFIG_DEBUG_RODATA)
/* .text should occupy whole number of pages */
. = ALIGN(PAGE_SIZE);
-#endif
- X64_ALIGN_DEBUG_RODATA_BEGIN
+ X64_ALIGN_RODATA_BEGIN
RO_DATA(PAGE_SIZE)
- X64_ALIGN_DEBUG_RODATA_END
+ X64_ALIGN_RODATA_END
/* Data */
.data : AT(ADDR(.data) - LOAD_OFFSET) {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1505587d06e9..b9b09fec173b 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/mmu.c b/arch/x86/kvm/mmu.c
index e7c2c1428a69..8eb8a934b531 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3754,13 +3754,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
+ bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+
/*
* Passing "true" to the last argument is okay; it adds a check
* on bit 8 of the SPTEs which KVM doesn't use anyway.
*/
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
- context->shadow_root_level, context->nx,
+ context->shadow_root_level, uses_nx,
guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
true);
}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 3058a22a658d..7be8a251363e 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/vmx.c b/arch/x86/kvm/vmx.c
index 10e7693b3540..0958fa2b7cb7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -595,6 +595,8 @@ struct vcpu_vmx {
/* Support for PML */
#define PML_ENTITY_NUM 512
struct page *pml_pg;
+
+ u64 current_tsc_ratio;
};
enum segment_cache_field {
@@ -1746,6 +1748,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
return;
}
break;
+ case MSR_IA32_PEBS_ENABLE:
+ /* PEBS needs a quiescent period after being disabled (to write
+ * a record). Disabling PEBS through VMX MSR swapping doesn't
+ * provide that period, so a CPU could write host's record into
+ * guest's memory.
+ */
+ wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}
for (i = 0; i < m->nr; ++i)
@@ -1783,26 +1792,31 @@ static void reload_tss(void)
static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
{
- u64 guest_efer;
- u64 ignore_bits;
+ u64 guest_efer = vmx->vcpu.arch.efer;
+ u64 ignore_bits = 0;
- guest_efer = vmx->vcpu.arch.efer;
+ if (!enable_ept) {
+ /*
+ * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing
+ * host CPUID is more efficient than testing guest CPUID
+ * or CR4. Host SMEP is anyway a requirement for guest SMEP.
+ */
+ if (boot_cpu_has(X86_FEATURE_SMEP))
+ guest_efer |= EFER_NX;
+ else if (!(guest_efer & EFER_NX))
+ ignore_bits |= EFER_NX;
+ }
/*
- * NX is emulated; LMA and LME handled by hardware; SCE meaningless
- * outside long mode
+ * LMA and LME handled by hardware; SCE meaningless outside long mode.
*/
- ignore_bits = EFER_NX | EFER_SCE;
+ ignore_bits |= EFER_SCE;
#ifdef CONFIG_X86_64
ignore_bits |= EFER_LMA | EFER_LME;
/* SCE is meaningful only in long mode on Intel */
if (guest_efer & EFER_LMA)
ignore_bits &= ~(u64)EFER_SCE;
#endif
- guest_efer &= ~ignore_bits;
- guest_efer |= host_efer & ignore_bits;
- vmx->guest_msrs[efer_offset].data = guest_efer;
- vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
clear_atomic_switch_msr(vmx, MSR_EFER);
@@ -1813,16 +1827,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
*/
if (cpu_has_load_ia32_efer ||
(enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
- guest_efer = vmx->vcpu.arch.efer;
if (!(guest_efer & EFER_LMA))
guest_efer &= ~EFER_LME;
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
guest_efer, host_efer);
return false;
- }
+ } else {
+ guest_efer &= ~ignore_bits;
+ guest_efer |= host_efer & ignore_bits;
- return true;
+ vmx->guest_msrs[efer_offset].data = guest_efer;
+ vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+ return true;
+ }
}
static unsigned long segment_base(u16 selector)
@@ -2062,14 +2081,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
- /* Setup TSC multiplier */
- if (cpu_has_vmx_tsc_scaling())
- vmcs_write64(TSC_MULTIPLIER,
- vcpu->arch.tsc_scaling_ratio);
-
vmx->loaded_vmcs->cpu = cpu;
}
+ /* Setup TSC multiplier */
+ if (kvm_has_tsc_control &&
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
+ vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+ }
+
vmx_vcpu_pi_load(vcpu, cpu);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a2ed8904513..d2945024ed33 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6544,12 +6544,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
* KVM_DEBUGREG_WONT_EXIT again.
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
- int i;
-
WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
kvm_x86_ops->sync_dirty_debug_regs(vcpu);
- for (i = 0; i < KVM_NR_DB_REGS; i++)
- vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+ kvm_update_dr0123(vcpu);
+ kvm_update_dr6(vcpu);
+ kvm_update_dr7(vcpu);
+ vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
}
/*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index cb4ef3de61f9..2ebfbaf61142 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -871,7 +871,6 @@ static noinline int do_test_wp_bit(void)
return flag;
}
-#ifdef CONFIG_DEBUG_RODATA
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);
@@ -960,5 +959,3 @@ void mark_rodata_ro(void)
if (__supported_pte_mask & _PAGE_NX)
debug_checkwx();
}
-#endif
-
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ec081fe0ce2c..e08d141844ee 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1062,7 +1062,6 @@ void __init mem_init(void)
mem_init_print_info(NULL);
}
-#ifdef CONFIG_DEBUG_RODATA
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);
@@ -1154,8 +1153,6 @@ void mark_rodata_ro(void)
debug_checkwx();
}
-#endif
-
int kern_addr_valid(unsigned long addr)
{
unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index b2fd67da1701..ef05755a1900 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;
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index db20ee9a413a..4540e8880cd9 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -278,7 +278,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
__pa_symbol(__end_rodata) >> PAGE_SHIFT))
pgprot_val(forbidden) |= _PAGE_RW;
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
/*
* Once the kernel maps the text as RO (kernel_set_to_readonly is set),
* kernel text mappings for the large page aligned text, rodata sections
@@ -414,24 +414,30 @@ pmd_t *lookup_pmd_address(unsigned long address)
phys_addr_t slow_virt_to_phys(void *__virt_addr)
{
unsigned long virt_addr = (unsigned long)__virt_addr;
- unsigned long phys_addr, offset;
+ phys_addr_t phys_addr;
+ unsigned long offset;
enum pg_level level;
pte_t *pte;
pte = lookup_address(virt_addr, &level);
BUG_ON(!pte);
+ /*
+ * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t
+ * before being left-shifted PAGE_SHIFT bits -- this trick is to
+ * make 32-PAE kernel work correctly.
+ */
switch (level) {
case PG_LEVEL_1G:
- phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
+ phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
offset = virt_addr & ~PUD_PAGE_MASK;
break;
case PG_LEVEL_2M:
- phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
+ phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
offset = virt_addr & ~PMD_PAGE_MASK;
break;
default:
- phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+ phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
offset = virt_addr & ~PAGE_MASK;
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-25 13:58:21 +0000