* [GIT pull] x86 fixes for 4.4
@ 2015-12-13 9:23 Thomas Gleixner
2015-12-13 10:08 ` Thomas Gleixner
0 siblings, 1 reply; 4+ messages in thread
From: Thomas Gleixner @ 2015-12-13 9:23 UTC (permalink / raw)
To: Linus Torvalds; +Cc: LKML, Andrew Morton, Ingo Molnar, H. Peter Anvin
Linus,
please pull the latest x86-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus
A series of small fixes to plug a race condition in the x86 vector
management code related to irq affinity settings.
Thanks,
tglx
------------------>
Jiang Liu (4):
x86/irq: Do not reuse struct apic_chip_data.old_domain as temporary buffer
x86/irq: Enhance __assign_irq_vector() to rollback in case of failure
x86/irq: Fix a race window in x86_vector_free_irqs()
x86/irq: Fix a race condition between vector assigning and cleanup
arch/x86/kernel/apic/vector.c | 117 +++++++++++++++++++-----------------------
1 file changed, 53 insertions(+), 64 deletions(-)
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 861bc59c8f25..b63d6f84c0bb 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, used_cpumask;
static struct irq_chip lapic_controller;
#ifdef CONFIG_X86_IO_APIC
static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
@@ -117,13 +117,15 @@ 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;
+ unsigned int dest;
- if (d->move_in_progress)
+ if (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(used_cpumask);
cpu = cpumask_first_and(mask, cpu_online_mask);
while (cpu < nr_cpu_ids) {
int new_cpu, vector, offset;
@@ -139,11 +141,15 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d,
* the current in use mask. So cleanup the vector
* allocation for the members that are not used anymore.
*/
- 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);
+ cpumask_and(used_cpumask, d->domain, vector_cpumask);
+ err = apic->cpu_mask_to_apicid_and(mask, used_cpumask,
+ &dest);
+ if (!err) {
+ cpumask_andnot(d->old_domain, d->domain,
+ vector_cpumask);
+ cpumask_copy(d->domain, used_cpumask);
+ d->cfg.dest_apicid = dest;
+ }
break;
}
@@ -157,9 +163,8 @@ next:
}
if (unlikely(current_vector == vector)) {
- cpumask_or(d->old_domain, d->old_domain,
- vector_cpumask);
- cpumask_andnot(vector_cpumask, mask, d->old_domain);
+ cpumask_or(used_cpumask, used_cpumask, vector_cpumask);
+ cpumask_andnot(vector_cpumask, mask, used_cpumask);
cpu = cpumask_first_and(vector_cpumask,
cpu_online_mask);
continue;
@@ -167,22 +172,22 @@ next:
if (test_bit(vector, used_vectors))
goto next;
-
for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
goto next;
}
+ if (apic->cpu_mask_to_apicid_and(mask, vector_cpumask, &dest))
+ goto next;
+
/* Found one! */
current_vector = vector;
current_offset = offset;
- if (d->cfg.vector) {
+ if (d->cfg.vector)
cpumask_copy(d->old_domain, d->domain);
- d->move_in_progress =
- cpumask_intersects(d->old_domain, cpu_online_mask);
- }
+ d->cfg.vector = vector;
+ d->cfg.dest_apicid = dest;
for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
- d->cfg.vector = vector;
cpumask_copy(d->domain, vector_cpumask);
err = 0;
break;
@@ -190,8 +195,8 @@ next:
if (!err) {
/* cache destination APIC IDs into cfg->dest_apicid */
- err = apic->cpu_mask_to_apicid_and(mask, d->domain,
- &d->cfg.dest_apicid);
+ cpumask_and(d->old_domain, d->old_domain, cpu_online_mask);
+ d->move_in_progress = !cpumask_empty(d->old_domain);
}
return err;
@@ -223,26 +228,15 @@ 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;
+ struct irq_desc *desc = irq_to_desc(irq);
+ int cpu, vector = data->cfg.vector;
- raw_spin_lock_irqsave(&vector_lock, flags);
- BUG_ON(!data->cfg.vector);
-
- vector = data->cfg.vector;
+ BUG_ON(!vector);
for_each_cpu_and(cpu, data->domain, cpu_online_mask)
per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
-
data->cfg.vector = 0;
cpumask_clear(data->domain);
- if (likely(!data->move_in_progress)) {
- raw_spin_unlock_irqrestore(&vector_lock, flags);
- return;
- }
-
- desc = irq_to_desc(irq);
for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
@@ -253,7 +247,7 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
}
}
data->move_in_progress = 0;
- raw_spin_unlock_irqrestore(&vector_lock, flags);
+ cpumask_clear(data->old_domain);
}
void init_irq_alloc_info(struct irq_alloc_info *info,
@@ -275,18 +269,21 @@ static void x86_vector_free_irqs(struct irq_domain *domain,
unsigned int virq, unsigned int nr_irqs)
{
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);
+ irq_domain_reset_irq_data(irq_data);
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
#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 +401,7 @@ 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(&used_cpumask, GFP_KERNEL));
return arch_early_ioapic_init();
}
@@ -420,10 +418,13 @@ static void __setup_vector_irq(int cpu)
struct irq_data *idata = irq_desc_get_irq_data(desc);
data = apic_chip_data(idata);
- if (!data || !cpumask_test_cpu(cpu, data->domain))
- continue;
- vector = data->cfg.vector;
- per_cpu(vector_irq, cpu)[vector] = desc;
+ if (data) {
+ cpumask_clear_cpu(cpu, data->old_domain);
+ if (cpumask_test_cpu(cpu, data->domain)) {
+ vector = data->cfg.vector;
+ per_cpu(vector_irq, cpu)[vector] = desc;
+ }
+ }
}
/* Mark the free vectors */
for (vector = 0; vector < NR_VECTORS; ++vector) {
@@ -492,14 +493,8 @@ 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 +506,17 @@ 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;
+ unsigned long flags;
- 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_irqsave(&vector_lock, flags);
+ if (!data->move_in_progress)
+ goto out_unlock;
data->move_in_progress = 0;
+ cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
+ if (!cpumask_empty(data->old_domain))
+ apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR);
+out_unlock:
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
}
void send_cleanup_vector(struct irq_cfg *cfg)
@@ -568,14 +560,10 @@ 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 this cpu is not set
+ * in the old_domain mask.
*/
- if (data->move_in_progress)
- goto unlock;
-
- if (vector == data->cfg.vector &&
- cpumask_test_cpu(me, data->domain))
+ if (!cpumask_test_cpu(me, data->old_domain))
goto unlock;
irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
@@ -591,6 +579,7 @@ 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);
}
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [GIT pull] x86 fixes for 4.4
2015-12-13 9:23 [GIT pull] x86 fixes for 4.4 Thomas Gleixner
@ 2015-12-13 10:08 ` Thomas Gleixner
0 siblings, 0 replies; 4+ messages in thread
From: Thomas Gleixner @ 2015-12-13 10:08 UTC (permalink / raw)
To: Linus Torvalds; +Cc: LKML, Andrew Morton, Ingo Molnar, H. Peter Anvin
Linus
On Sun, 13 Dec 2015, Thomas Gleixner wrote:
> Linus,
>
> please pull the latest x86-urgent-for-linus git tree from:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus
>
> A series of small fixes to plug a race condition in the x86 vector
> management code related to irq affinity settings.
Please do not pull that lot. I just found a report against it, which I
need to verify first.
Thanks,
tglx
^ permalink raw reply [flat|nested] 4+ messages in thread
* [GIT pull] x86 fixes for 4.4
@ 2015-12-06 9:41 Thomas Gleixner
0 siblings, 0 replies; 4+ messages in thread
From: Thomas Gleixner @ 2015-12-06 9:41 UTC (permalink / raw)
To: Linus Torvalds; +Cc: LKML, Andrew Morton, Ingo Molnar, H. Peter Anvin
Linus,
please pull the latest x86-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus
Another round of fixes for x86:
- Move the initialization of the microcode driver to late_initcall to
make sure everything that init function needs is available.
- Make sure that lockdep knows about interrupts being off in the
entry code before calling into c-code.
- Undo the cpu hotplug init delay regression.
- Use the proper conditionals in the mpx instruction decoder.
- Fixup restart_syscall for x32 tasks.
- Fix the hugepage regression on PAE kernels which was introduced
with the latest PAT changes.
Thanks,
tglx
------------------>
Andy Lutomirski (1):
x86/entry/64: Fix irqflag tracing wrt context tracking
Borislav Petkov (1):
x86/microcode: Initialize the driver late when facilities are up
Dave Hansen (1):
x86/mpx: Fix instruction decoder condition
Dmitry V. Levin (1):
x86/signal: Fix restart_syscall number for x32 tasks
Kirill A. Shutemov (1):
x86/mm: Fix regression with huge pages on PAE
Len Brown (1):
x86 smpboot: Re-enable init_udelay=0 by default on modern CPUs
arch/x86/boot/boot.h | 1 -
arch/x86/boot/video-mode.c | 2 ++
arch/x86/boot/video.c | 2 ++
arch/x86/entry/entry_64.S | 19 ++++++++++++++++++-
arch/x86/include/asm/page_types.h | 16 +++++++++-------
arch/x86/include/asm/pgtable_types.h | 14 ++++----------
arch/x86/include/asm/x86_init.h | 1 -
arch/x86/kernel/cpu/microcode/core.c | 1 +
arch/x86/kernel/setup.c | 2 --
arch/x86/kernel/signal.c | 17 ++++++++++-------
arch/x86/kernel/smpboot.c | 9 +++++----
arch/x86/mm/mpx.c | 6 +++---
12 files changed, 54 insertions(+), 36 deletions(-)
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 0033e96c3f09..9011a88353de 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -23,7 +23,6 @@
#include <stdarg.h>
#include <linux/types.h>
#include <linux/edd.h>
-#include <asm/boot.h>
#include <asm/setup.h>
#include "bitops.h"
#include "ctype.h"
diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c
index aa8a96b052e3..95c7a818c0ed 100644
--- a/arch/x86/boot/video-mode.c
+++ b/arch/x86/boot/video-mode.c
@@ -19,6 +19,8 @@
#include "video.h"
#include "vesa.h"
+#include <uapi/asm/boot.h>
+
/*
* Common variables
*/
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index 05111bb8d018..77780e386e9b 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -13,6 +13,8 @@
* Select video mode
*/
+#include <uapi/asm/boot.h>
+
#include "boot.h"
#include "video.h"
#include "vesa.h"
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 53616ca03244..a55697d19824 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -509,6 +509,17 @@ END(irq_entries_start)
* tracking that we're in kernel mode.
*/
SWAPGS
+
+ /*
+ * We need to tell lockdep that IRQs are off. We can't do this until
+ * we fix gsbase, and we should do it before enter_from_user_mode
+ * (which can take locks). Since TRACE_IRQS_OFF idempotent,
+ * the simplest way to handle it is to just call it twice if
+ * we enter from user mode. There's no reason to optimize this since
+ * TRACE_IRQS_OFF is a no-op if lockdep is off.
+ */
+ TRACE_IRQS_OFF
+
#ifdef CONFIG_CONTEXT_TRACKING
call enter_from_user_mode
#endif
@@ -1049,12 +1060,18 @@ ENTRY(error_entry)
SWAPGS
.Lerror_entry_from_usermode_after_swapgs:
+ /*
+ * We need to tell lockdep that IRQs are off. We can't do this until
+ * we fix gsbase, and we should do it before enter_from_user_mode
+ * (which can take locks).
+ */
+ TRACE_IRQS_OFF
#ifdef CONFIG_CONTEXT_TRACKING
call enter_from_user_mode
#endif
+ ret
.Lerror_entry_done:
-
TRACE_IRQS_OFF
ret
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index c5b7fb2774d0..cc071c6f7d4d 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -9,19 +9,21 @@
#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT)
#define PAGE_MASK (~(PAGE_SIZE-1))
+#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT)
+#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1))
+
+#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
+
#define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
#define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1)
-/* Cast PAGE_MASK to a signed type so that it is sign-extended if
+/* Cast *PAGE_MASK to a signed type so that it is sign-extended if
virtual addresses are 32-bits but physical addresses are larger
(ie, 32-bit PAE). */
#define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-
-#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT)
-#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1))
-
-#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
+#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK)
#define HPAGE_SHIFT PMD_SHIFT
#define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index dd5b0aa9dd2f..a471cadb9630 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -279,17 +279,14 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
static inline pudval_t pud_pfn_mask(pud_t pud)
{
if (native_pud_val(pud) & _PAGE_PSE)
- return PUD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+ return PHYSICAL_PUD_PAGE_MASK;
else
return PTE_PFN_MASK;
}
static inline pudval_t pud_flags_mask(pud_t pud)
{
- if (native_pud_val(pud) & _PAGE_PSE)
- return ~(PUD_PAGE_MASK & (pudval_t)PHYSICAL_PAGE_MASK);
- else
- return ~PTE_PFN_MASK;
+ return ~pud_pfn_mask(pud);
}
static inline pudval_t pud_flags(pud_t pud)
@@ -300,17 +297,14 @@ static inline pudval_t pud_flags(pud_t pud)
static inline pmdval_t pmd_pfn_mask(pmd_t pmd)
{
if (native_pmd_val(pmd) & _PAGE_PSE)
- return PMD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+ return PHYSICAL_PMD_PAGE_MASK;
else
return PTE_PFN_MASK;
}
static inline pmdval_t pmd_flags_mask(pmd_t pmd)
{
- if (native_pmd_val(pmd) & _PAGE_PSE)
- return ~(PMD_PAGE_MASK & (pmdval_t)PHYSICAL_PAGE_MASK);
- else
- return ~PTE_PFN_MASK;
+ return ~pmd_pfn_mask(pmd);
}
static inline pmdval_t pmd_flags(pmd_t pmd)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 48d34d28f5a6..cd0fc0cc78bc 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -1,7 +1,6 @@
#ifndef _ASM_X86_PLATFORM_H
#define _ASM_X86_PLATFORM_H
-#include <asm/pgtable_types.h>
#include <asm/bootparam.h>
struct mpc_bus;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 7fc27f1cca58..b3e94ef461fd 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -698,3 +698,4 @@ int __init microcode_init(void)
return error;
}
+late_initcall(microcode_init);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 29db25f9a745..d2bbe343fda7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1250,8 +1250,6 @@ void __init setup_arch(char **cmdline_p)
if (efi_enabled(EFI_BOOT))
efi_apply_memmap_quirks();
#endif
-
- microcode_init();
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b7ffb7c00075..cb6282c3638f 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -690,12 +690,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
signal_setup_done(failed, ksig, stepping);
}
-#ifdef CONFIG_X86_32
-#define NR_restart_syscall __NR_restart_syscall
-#else /* !CONFIG_X86_32 */
-#define NR_restart_syscall \
- test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
-#endif /* CONFIG_X86_32 */
+static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
+{
+#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64)
+ return __NR_restart_syscall;
+#else /* !CONFIG_X86_32 && CONFIG_X86_64 */
+ return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall :
+ __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
+#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */
+}
/*
* Note that 'init' is a special process: it doesn't get signals it doesn't
@@ -724,7 +727,7 @@ void do_signal(struct pt_regs *regs)
break;
case -ERESTART_RESTARTBLOCK:
- regs->ax = NR_restart_syscall;
+ regs->ax = get_nr_restart_syscall(regs);
regs->ip -= 2;
break;
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 892ee2e5ecbc..fbabe4fcc7fb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -509,7 +509,7 @@ void __inquire_remote_apic(int apicid)
*/
#define UDELAY_10MS_DEFAULT 10000
-static unsigned int init_udelay = INT_MAX;
+static unsigned int init_udelay = UINT_MAX;
static int __init cpu_init_udelay(char *str)
{
@@ -522,14 +522,15 @@ early_param("cpu_init_udelay", cpu_init_udelay);
static void __init smp_quirk_init_udelay(void)
{
/* if cmdline changed it from default, leave it alone */
- if (init_udelay != INT_MAX)
+ if (init_udelay != UINT_MAX)
return;
/* if modern processor, use no delay */
if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
- ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+ ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
init_udelay = 0;
-
+ return;
+ }
/* else, use legacy delay */
init_udelay = UDELAY_10MS_DEFAULT;
}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 1202d5ca2fb5..b2fd67da1701 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -101,19 +101,19 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
switch (type) {
case REG_TYPE_RM:
regno = X86_MODRM_RM(insn->modrm.value);
- if (X86_REX_B(insn->rex_prefix.value) == 1)
+ if (X86_REX_B(insn->rex_prefix.value))
regno += 8;
break;
case REG_TYPE_INDEX:
regno = X86_SIB_INDEX(insn->sib.value);
- if (X86_REX_X(insn->rex_prefix.value) == 1)
+ if (X86_REX_X(insn->rex_prefix.value))
regno += 8;
break;
case REG_TYPE_BASE:
regno = X86_SIB_BASE(insn->sib.value);
- if (X86_REX_B(insn->rex_prefix.value) == 1)
+ if (X86_REX_B(insn->rex_prefix.value))
regno += 8;
break;
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [GIT pull] x86 fixes for 4.4
@ 2015-11-22 6:37 Thomas Gleixner
0 siblings, 0 replies; 4+ messages in thread
From: Thomas Gleixner @ 2015-11-22 6:37 UTC (permalink / raw)
To: Linus Torvalds; +Cc: LKML, Andrew Morton, Ingo Molnar, H. Peter Anvin
Linus,
please pull the latest x86-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus
This update contains:
- MPX updates for handling 32bit processes
- A fix for a long standing bug in 32bit signal frame handling
related to FPU/XSAVE state
- Handle get_xsave_addr() correctly in KVM
- Fix SMAP check under paravirtualization
- Add a comment to the static function trace entry to avoid further
confusion about the difference to dynamic tracing.
Thanks,
tglx
------------------>
Andrew Cooper (1):
x86/cpu: Fix SMAP check in PVOPS environments
Dave Hansen (3):
x86/mpx: Do proper get_user() when running 32-bit binaries on 64-bit kernels
x86/mpx: Fix 32-bit address space calculation
x86/fpu: Fix 32-bit signal frame handling
Huaitong Han (1):
x86/fpu: Fix get_xsave_addr() behavior under virtualization
Namhyung Kim (1):
x86/ftrace: Add comment on static function tracing
arch/x86/kernel/cpu/common.c | 3 +--
arch/x86/kernel/fpu/signal.c | 11 +++++------
arch/x86/kernel/fpu/xstate.c | 1 -
arch/x86/kernel/mcount_64.S | 6 ++++++
arch/x86/mm/mpx.c | 47 ++++++++++++++++++++++++++++++++++++++------
5 files changed, 53 insertions(+), 15 deletions(-)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4ddd780aeac9..c2b7522cbf35 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -273,10 +273,9 @@ __setup("nosmap", setup_disable_smap);
static __always_inline void setup_smap(struct cpuinfo_x86 *c)
{
- unsigned long eflags;
+ unsigned long eflags = native_save_fl();
/* This should have been cleared long ago */
- raw_local_save_flags(eflags);
BUG_ON(eflags & X86_EFLAGS_AC);
if (cpu_has(c, X86_FEATURE_SMAP)) {
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index ef29b742cea7..31c6a60505e6 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -385,20 +385,19 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
*/
void fpu__init_prepare_fx_sw_frame(void)
{
- int fsave_header_size = sizeof(struct fregs_state);
int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
- if (config_enabled(CONFIG_X86_32))
- size += fsave_header_size;
-
fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
fx_sw_reserved.extended_size = size;
fx_sw_reserved.xfeatures = xfeatures_mask;
fx_sw_reserved.xstate_size = xstate_size;
- if (config_enabled(CONFIG_IA32_EMULATION)) {
+ if (config_enabled(CONFIG_IA32_EMULATION) ||
+ config_enabled(CONFIG_X86_32)) {
+ int fsave_header_size = sizeof(struct fregs_state);
+
fx_sw_reserved_ia32 = fx_sw_reserved;
- fx_sw_reserved_ia32.extended_size += fsave_header_size;
+ fx_sw_reserved_ia32.extended_size = size + fsave_header_size;
}
}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 6454f2731b56..70fc312221fc 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -694,7 +694,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
if (!boot_cpu_has(X86_FEATURE_XSAVE))
return NULL;
- xsave = ¤t->thread.fpu.state.xsave;
/*
* We should not ever be requesting features that we
* have not enabled. Remember that pcntxt_mask is
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 94ea120fa21f..87e1762e2bca 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -278,6 +278,12 @@ trace:
/* save_mcount_regs fills in first two parameters */
save_mcount_regs
+ /*
+ * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not
+ * set (see include/asm/ftrace.h and include/linux/ftrace.h). Only the
+ * ip and parent ip are used and the list function is called when
+ * function tracing is enabled.
+ */
call *ftrace_trace_function
restore_mcount_regs
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index b0ae85f90f10..1202d5ca2fb5 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -586,6 +586,29 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
}
/*
+ * We only want to do a 4-byte get_user() on 32-bit. Otherwise,
+ * we might run off the end of the bounds table if we are on
+ * a 64-bit kernel and try to get 8 bytes.
+ */
+int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
+ long __user *bd_entry_ptr)
+{
+ u32 bd_entry_32;
+ int ret;
+
+ if (is_64bit_mm(mm))
+ return get_user(*bd_entry_ret, bd_entry_ptr);
+
+ /*
+ * Note that get_user() uses the type of the *pointer* to
+ * establish the size of the get, not the destination.
+ */
+ ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr);
+ *bd_entry_ret = bd_entry_32;
+ return ret;
+}
+
+/*
* Get the base of bounds tables pointed by specific bounds
* directory entry.
*/
@@ -605,7 +628,7 @@ static int get_bt_addr(struct mm_struct *mm,
int need_write = 0;
pagefault_disable();
- ret = get_user(bd_entry, bd_entry_ptr);
+ ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr);
pagefault_enable();
if (!ret)
break;
@@ -700,11 +723,23 @@ static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
*/
static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
{
- unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
- if (is_64bit_mm(mm))
- return virt_space / MPX_BD_NR_ENTRIES_64;
- else
- return virt_space / MPX_BD_NR_ENTRIES_32;
+ unsigned long long virt_space;
+ unsigned long long GB = (1ULL << 30);
+
+ /*
+ * This covers 32-bit emulation as well as 32-bit kernels
+ * running on 64-bit harware.
+ */
+ if (!is_64bit_mm(mm))
+ return (4ULL * GB) / MPX_BD_NR_ENTRIES_32;
+
+ /*
+ * 'x86_virt_bits' returns what the hardware is capable
+ * of, and returns the full >32-bit adddress space when
+ * running 32-bit kernels on 64-bit hardware.
+ */
+ virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+ return virt_space / MPX_BD_NR_ENTRIES_64;
}
/*
^ permalink raw reply related [flat|nested] 4+ messages in thread
end of thread, other threads:[~2015-12-13 10:09 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-12-13 9:23 [GIT pull] x86 fixes for 4.4 Thomas Gleixner
2015-12-13 10:08 ` Thomas Gleixner
-- strict thread matches above, loose matches on Subject: below --
2015-12-06 9:41 Thomas Gleixner
2015-11-22 6:37 Thomas Gleixner
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.