Re: Linux 2.6.29.2

From: Chris Wright
Date: Mon Apr 27 2009 - 14:42:18 EST


diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 5ede747..0876275 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -1242,7 +1242,7 @@ monitoring is enabled, and vice-versa.
To add ARP targets:
# echo +192.168.0.100 > /sys/class/net/bond0/bonding/arp_ip_target
# echo +192.168.0.101 > /sys/class/net/bond0/bonding/arp_ip_target
- NOTE: up to 10 target addresses may be specified.
+ NOTE: up to 16 target addresses may be specified.

To remove an ARP target:
# echo -192.168.0.100 > /sys/class/net/bond0/bonding/arp_ip_target
diff --git a/Makefile b/Makefile
index cdb1133..0380c7e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 29
-EXTRAVERSION = .1
+EXTRAVERSION = .2
NAME = Temporary Tasmanian Devil

# *DOCUMENTATION*
diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index f833a0b..0a2d6b8 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -4,6 +4,10 @@
config HAVE_KVM
bool

+config HAVE_KVM_IRQCHIP
+ bool
+ default y
+
menuconfig VIRTUALIZATION
bool "Virtualization"
depends on HAVE_KVM || IA64
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 1a86f84..5abcc7f 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -134,9 +134,9 @@ SYSCALL_DEFINE4(32_ftruncate64, unsigned long, fd, unsigned long, __dummy,
return sys_ftruncate(fd, merge_64(a2, a3));
}

-SYSCALL_DEFINE5(32_llseek, unsigned long, fd, unsigned long, offset_high,
- unsigned long, offset_low, loff_t __user *, result,
- unsigned long, origin)
+SYSCALL_DEFINE5(32_llseek, unsigned int, fd, unsigned int, offset_high,
+ unsigned int, offset_low, loff_t __user *, result,
+ unsigned int, origin)
{
return sys_llseek(fd, offset_high, offset_low, result, origin);
}
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index 6d406c5..9696cc3 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -27,7 +27,7 @@
PPC_LONG "1b,4b,2b,4b\n" \
".previous" \
: "=&r" (oldval), "=&r" (ret) \
- : "b" (uaddr), "i" (-EFAULT), "1" (oparg) \
+ : "b" (uaddr), "i" (-EFAULT), "r" (oparg) \
: "cr0", "memory")

static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
@@ -47,19 +47,19 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)

switch (op) {
case FUTEX_OP_SET:
- __futex_atomic_op("", ret, oldval, uaddr, oparg);
+ __futex_atomic_op("mr %1,%4\n", ret, oldval, uaddr, oparg);
break;
case FUTEX_OP_ADD:
- __futex_atomic_op("add %1,%0,%1\n", ret, oldval, uaddr, oparg);
+ __futex_atomic_op("add %1,%0,%4\n", ret, oldval, uaddr, oparg);
break;
case FUTEX_OP_OR:
- __futex_atomic_op("or %1,%0,%1\n", ret, oldval, uaddr, oparg);
+ __futex_atomic_op("or %1,%0,%4\n", ret, oldval, uaddr, oparg);
break;
case FUTEX_OP_ANDN:
- __futex_atomic_op("andc %1,%0,%1\n", ret, oldval, uaddr, oparg);
+ __futex_atomic_op("andc %1,%0,%4\n", ret, oldval, uaddr, oparg);
break;
case FUTEX_OP_XOR:
- __futex_atomic_op("xor %1,%0,%1\n", ret, oldval, uaddr, oparg);
+ __futex_atomic_op("xor %1,%0,%4\n", ret, oldval, uaddr, oparg);
break;
default:
ret = -ENOSYS;
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 6dbdc48..03becdf 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -2,6 +2,9 @@
# KVM configuration
#

+config HAVE_KVM_IRQCHIP
+ bool
+
menuconfig VIRTUALIZATION
bool "Virtualization"
---help---
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index e051cad..3e260b7 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -4,6 +4,9 @@
config HAVE_KVM
bool

+config HAVE_KVM_IRQCHIP
+ bool
+
menuconfig VIRTUALIZATION
bool "Virtualization"
default y
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index 0aaa086..ee38e73 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -57,9 +57,9 @@ static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm, unsigned i

static inline void tlb_flush_mmu(struct mmu_gather *mp)
{
+ if (!mp->fullmm)
+ flush_tlb_pending();
if (mp->need_flush) {
- if (!mp->fullmm)
- flush_tlb_pending();
free_pages_and_swap_cache(mp->pages, mp->pages_nr);
mp->pages_nr = 0;
mp->need_flush = 0;
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c98d52e..6ed3aca 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -523,6 +523,7 @@ config X86_PTRACE_BTS
bool "Branch Trace Store"
default y
depends on X86_DEBUGCTLMSR
+ depends on BROKEN
help
This adds a ptrace interface to the hardware's branch trace store.

diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index 8c3c25f..a99dbbe 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -27,13 +27,14 @@ static int detect_memory_e820(void)
do {
size = sizeof(struct e820entry);

- /* Important: %edx is clobbered by some BIOSes,
- so it must be either used for the error output
+ /* Important: %edx and %esi are clobbered by some BIOSes,
+ so they must be either used for the error output
or explicitly marked clobbered. */
asm("int $0x15; setc %0"
: "=d" (err), "+b" (next), "=a" (id), "+c" (size),
"=m" (*desc)
- : "D" (desc), "d" (SMAP), "a" (0xe820));
+ : "D" (desc), "d" (SMAP), "a" (0xe820)
+ : "esi");

/* BIOSes which terminate the chain with CF = 1 as opposed
to %ebx = 0 don't always report the SMAP signature on
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 4b1c319..89c676d 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -680,6 +680,18 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
perf->states[i].transition_latency * 1000;
}

+ /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
+ if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
+ policy->cpuinfo.transition_latency > 20 * 1000) {
+ static int print_once;
+ policy->cpuinfo.transition_latency = 20 * 1000;
+ if (!print_once) {
+ print_once = 1;
+ printk(KERN_INFO "Capping off P-state tranision latency"
+ " at 20 uS\n");
+ }
+ }
+
data->max_freq = perf->states[0].core_frequency * 1000;
/* table init */
for (i=0; i<perf->state_count; i++) {
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index bc7ac4d..7086b24 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -2475,6 +2475,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
me = smp_processor_id();
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
unsigned int irq;
+ unsigned int irr;
struct irq_desc *desc;
struct irq_cfg *cfg;
irq = __get_cpu_var(vector_irq)[vector];
@@ -2494,6 +2495,18 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
goto unlock;

+ irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
+ /*
+ * Check if the vector that needs to be cleanedup is
+ * registered at the cpu's IRR. If so, then this is not
+ * the best time to clean it up. Lets clean it up in the
+ * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR
+ * to myself.
+ */
+ if (irr & (1 << (vector % 32))) {
+ send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
+ goto unlock;
+ }
__get_cpu_var(vector_irq)[vector] = -1;
cfg->move_cleanup_count--;
unlock:
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b81125f..0a303c3 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -4,6 +4,10 @@
config HAVE_KVM
bool

+config HAVE_KVM_IRQCHIP
+ bool
+ default y
+
menuconfig VIRTUALIZATION
bool "Virtualization"
depends on HAVE_KVM || X86
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 72bd275..3dceaef 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -536,6 +536,16 @@ void kvm_pit_reset(struct kvm_pit *pit)
pit->pit_state.irq_ack = 1;
}

+static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
+{
+ struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
+
+ if (!mask) {
+ atomic_set(&pit->pit_state.pit_timer.pending, 0);
+ pit->pit_state.irq_ack = 1;
+ }
+}
+
struct kvm_pit *kvm_create_pit(struct kvm *kvm)
{
struct kvm_pit *pit;
@@ -584,6 +594,9 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)

kvm_pit_reset(pit);

+ pit->mask_notifier.func = pit_mask_notifer;
+ kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+
return pit;
}

@@ -592,6 +605,8 @@ void kvm_free_pit(struct kvm *kvm)
struct hrtimer *timer;

if (kvm->arch.vpit) {
+ kvm_unregister_irq_mask_notifier(kvm, 0,
+ &kvm->arch.vpit->mask_notifier);
mutex_lock(&kvm->arch.vpit->pit_state.lock);
timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
hrtimer_cancel(timer);
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 4178022..0dfb936 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -45,6 +45,7 @@ struct kvm_pit {
struct kvm *kvm;
struct kvm_kpit_state pit_state;
int irq_source_id;
+ struct kvm_irq_mask_notifier mask_notifier;
};

#define KVM_PIT_BASE_ADDRESS 0x40
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 258e5d5..eaab214 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -54,7 +54,7 @@ static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
static inline int is_long_mode(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
- return vcpu->arch.shadow_efer & EFER_LME;
+ return vcpu->arch.shadow_efer & EFER_LMA;
#else
return 0;
#endif
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index c95a67d..89addbd 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -476,16 +476,20 @@ static int FNAME(shadow_invlpg_entry)(struct kvm_shadow_walk *_sw,
if (level == PT_PAGE_TABLE_LEVEL ||
((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) {
struct kvm_mmu_page *sp = page_header(__pa(sptep));
+ int need_flush = 0;

sw->pte_gpa = (sp->gfn << PAGE_SHIFT);
sw->pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);

if (is_shadow_present_pte(*sptep)) {
+ need_flush = 1;
rmap_remove(vcpu->kvm, sptep);
if (is_large_pte(*sptep))
--vcpu->kvm->stat.lpages;
}
set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
+ if (need_flush)
+ kvm_flush_remote_tlbs(vcpu->kvm);
return 1;
}
if (!is_shadow_present_pte(*sptep))
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 90de444..898910c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1433,6 +1433,29 @@ continue_rmode:
init_rmode(vcpu->kvm);
}

+static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
+
+ vcpu->arch.shadow_efer = efer;
+ if (!msr)
+ return;
+ if (efer & EFER_LMA) {
+ vmcs_write32(VM_ENTRY_CONTROLS,
+ vmcs_read32(VM_ENTRY_CONTROLS) |
+ VM_ENTRY_IA32E_MODE);
+ msr->data = efer;
+ } else {
+ vmcs_write32(VM_ENTRY_CONTROLS,
+ vmcs_read32(VM_ENTRY_CONTROLS) &
+ ~VM_ENTRY_IA32E_MODE);
+
+ msr->data = efer & ~EFER_LME;
+ }
+ setup_msrs(vmx);
+}
+
#ifdef CONFIG_X86_64

static void enter_lmode(struct kvm_vcpu *vcpu)
@@ -1447,13 +1470,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
(guest_tr_ar & ~AR_TYPE_MASK)
| AR_TYPE_BUSY_64_TSS);
}
-
vcpu->arch.shadow_efer |= EFER_LMA;
-
- find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME;
- vmcs_write32(VM_ENTRY_CONTROLS,
- vmcs_read32(VM_ENTRY_CONTROLS)
- | VM_ENTRY_IA32E_MODE);
+ vmx_set_efer(vcpu, vcpu->arch.shadow_efer);
}

static void exit_lmode(struct kvm_vcpu *vcpu)
@@ -1612,30 +1630,6 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
vmcs_writel(GUEST_CR4, hw_cr4);
}

-static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
-
- vcpu->arch.shadow_efer = efer;
- if (!msr)
- return;
- if (efer & EFER_LMA) {
- vmcs_write32(VM_ENTRY_CONTROLS,
- vmcs_read32(VM_ENTRY_CONTROLS) |
- VM_ENTRY_IA32E_MODE);
- msr->data = efer;
-
- } else {
- vmcs_write32(VM_ENTRY_CONTROLS,
- vmcs_read32(VM_ENTRY_CONTROLS) &
- ~VM_ENTRY_IA32E_MODE);
-
- msr->data = efer & ~EFER_LME;
- }
- setup_msrs(vmx);
-}
-
static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 21bc1f7..441489c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -713,29 +713,28 @@ static void free_pfn_range(u64 paddr, unsigned long size)
*
* If the vma has a linear pfn mapping for the entire range, we get the prot
* from pte and reserve the entire vma range with single reserve_pfn_range call.
- * Otherwise, we reserve the entire vma range, my ging through the PTEs page
- * by page to get physical address and protection.
*/
int track_pfn_vma_copy(struct vm_area_struct *vma)
{
- int retval = 0;
- unsigned long i, j;
resource_size_t paddr;
unsigned long prot;
- unsigned long vma_start = vma->vm_start;
- unsigned long vma_end = vma->vm_end;
- unsigned long vma_size = vma_end - vma_start;
+ unsigned long vma_size = vma->vm_end - vma->vm_start;
pgprot_t pgprot;

if (!pat_enabled)
return 0;

+ /*
+ * For now, only handle remap_pfn_range() vmas where
+ * is_linear_pfn_mapping() == TRUE. Handling of
+ * vm_insert_pfn() is TBD.
+ */
if (is_linear_pfn_mapping(vma)) {
/*
* reserve the whole chunk covered by vma. We need the
* starting address and protection from pte.
*/
- if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+ if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
WARN_ON_ONCE(1);
return -EINVAL;
}
@@ -743,28 +742,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
}

- /* reserve entire vma page by page, using pfn and prot from pte */
- for (i = 0; i < vma_size; i += PAGE_SIZE) {
- if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
- continue;
-
- pgprot = __pgprot(prot);
- retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
- if (retval)
- goto cleanup_ret;
- }
return 0;
-
-cleanup_ret:
- /* Reserve error: Cleanup partial reservation and return error */
- for (j = 0; j < i; j += PAGE_SIZE) {
- if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
- continue;
-
- free_pfn_range(paddr, PAGE_SIZE);
- }
-
- return retval;
}

/*
@@ -774,50 +752,28 @@ cleanup_ret:
* prot is passed in as a parameter for the new mapping. If the vma has a
* linear pfn mapping for the entire range reserve the entire vma range with
* single reserve_pfn_range call.
- * Otherwise, we look t the pfn and size and reserve only the specified range
- * page by page.
- *
- * Note that this function can be called with caller trying to map only a
- * subrange/page inside the vma.
*/
int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long size)
{
- int retval = 0;
- unsigned long i, j;
- resource_size_t base_paddr;
resource_size_t paddr;
- unsigned long vma_start = vma->vm_start;
- unsigned long vma_end = vma->vm_end;
- unsigned long vma_size = vma_end - vma_start;
+ unsigned long vma_size = vma->vm_end - vma->vm_start;

if (!pat_enabled)
return 0;

+ /*
+ * For now, only handle remap_pfn_range() vmas where
+ * is_linear_pfn_mapping() == TRUE. Handling of
+ * vm_insert_pfn() is TBD.
+ */
if (is_linear_pfn_mapping(vma)) {
/* reserve the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
return reserve_pfn_range(paddr, vma_size, prot, 0);
}

- /* reserve page by page using pfn and size */
- base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
- for (i = 0; i < size; i += PAGE_SIZE) {
- paddr = base_paddr + i;
- retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0);
- if (retval)
- goto cleanup_ret;
- }
return 0;
-
-cleanup_ret:
- /* Reserve error: Cleanup partial reservation and return error */
- for (j = 0; j < i; j += PAGE_SIZE) {
- paddr = base_paddr + j;
- free_pfn_range(paddr, PAGE_SIZE);
- }
-
- return retval;
}

/*
@@ -828,39 +784,23 @@ cleanup_ret:
void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size)
{
- unsigned long i;
resource_size_t paddr;
- unsigned long prot;
- unsigned long vma_start = vma->vm_start;
- unsigned long vma_end = vma->vm_end;
- unsigned long vma_size = vma_end - vma_start;
+ unsigned long vma_size = vma->vm_end - vma->vm_start;

if (!pat_enabled)
return;

+ /*
+ * For now, only handle remap_pfn_range() vmas where
+ * is_linear_pfn_mapping() == TRUE. Handling of
+ * vm_insert_pfn() is TBD.
+ */
if (is_linear_pfn_mapping(vma)) {
/* free the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
free_pfn_range(paddr, vma_size);
return;
}
-
- if (size != 0 && size != vma_size) {
- /* free page by page, using pfn and size */
- paddr = (resource_size_t)pfn << PAGE_SHIFT;
- for (i = 0; i < size; i += PAGE_SIZE) {
- paddr = paddr + i;
- free_pfn_range(paddr, PAGE_SIZE);
- }
- } else {
- /* free entire vma, page by page, using the pfn from pte */
- for (i = 0; i < vma_size; i += PAGE_SIZE) {
- if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
- continue;
-
- free_pfn_range(paddr, PAGE_SIZE);
- }
- }
}

pgprot_t pgprot_writecombine(pgprot_t prot)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 7d388d5..096b0ed 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -495,26 +495,6 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015,
pci_siemens_interrupt_controller);

/*
- * Regular PCI devices have 256 bytes, but AMD Family 10h/11h CPUs have
- * 4096 bytes configuration space for each function of their processor
- * configuration space.
- */
-static void amd_cpu_pci_cfg_space_size(struct pci_dev *dev)
-{
- dev->cfg_size = pci_cfg_space_size_ext(dev);
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1300, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1301, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1302, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1303, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1304, amd_cpu_pci_cfg_space_size);
-
-/*
* SB600: Disable BAR1 on device 14.0 to avoid HPET resources from
* confusing the PCI engine:
*/
diff --git a/crypto/shash.c b/crypto/shash.c
index d5a2b61..6792a67 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -82,6 +82,9 @@ static int shash_update_unaligned(struct shash_desc *desc, const u8 *data,
u8 buf[shash_align_buffer_size(unaligned_len, alignmask)]
__attribute__ ((aligned));

+ if (unaligned_len > len)
+ unaligned_len = len;
+
memcpy(buf, data, unaligned_len);

return shash->update(desc, buf, unaligned_len) ?:
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 35094f2..8f62fa0 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -1146,9 +1146,10 @@ static int __init dock_init(void)
static void __exit dock_exit(void)
{
struct dock_station *dock_station;
+ struct dock_station *tmp;

unregister_acpi_bus_notifier(&dock_acpi_notifier);
- list_for_each_entry(dock_station, &dock_stations, sibiling)
+ list_for_each_entry_safe(dock_station, tmp, &dock_stations, sibiling)
dock_remove(dock_station);
}

diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c
index 4216399..233a5fd 100644
--- a/drivers/ata/pata_hpt37x.c
+++ b/drivers/ata/pata_hpt37x.c
@@ -8,7 +8,7 @@
* Copyright (C) 1999-2003 Andre Hedrick <andre@xxxxxxxxxxxxx>
* Portions Copyright (C) 2001 Sun Microsystems, Inc.
* Portions Copyright (C) 2003 Red Hat Inc
- * Portions Copyright (C) 2005-2007 MontaVista Software, Inc.
+ * Portions Copyright (C) 2005-2009 MontaVista Software, Inc.
*
* TODO
* Look into engine reset on timeout errors. Should not be required.
@@ -24,7 +24,7 @@
#include <linux/libata.h>

#define DRV_NAME "pata_hpt37x"
-#define DRV_VERSION "0.6.11"
+#define DRV_VERSION "0.6.12"

struct hpt_clock {
u8 xfer_speed;
@@ -445,23 +445,6 @@ static void hpt370_set_dmamode(struct ata_port *ap, struct ata_device *adev)
}

/**
- * hpt370_bmdma_start - DMA engine begin
- * @qc: ATA command
- *
- * The 370 and 370A want us to reset the DMA engine each time we
- * use it. The 372 and later are fine.
- */
-
-static void hpt370_bmdma_start(struct ata_queued_cmd *qc)
-{
- struct ata_port *ap = qc->ap;
- struct pci_dev *pdev = to_pci_dev(ap->host->dev);
- pci_write_config_byte(pdev, 0x50 + 4 * ap->port_no, 0x37);
- udelay(10);
- ata_bmdma_start(qc);
-}
-
-/**
* hpt370_bmdma_end - DMA engine stop
* @qc: ATA command
*
@@ -598,7 +581,6 @@ static struct scsi_host_template hpt37x_sht = {
static struct ata_port_operations hpt370_port_ops = {
.inherits = &ata_bmdma_port_ops,

- .bmdma_start = hpt370_bmdma_start,
.bmdma_stop = hpt370_bmdma_stop,

.mode_filter = hpt370_filter,
diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c
index 10d6cbd..2224b76 100644
--- a/drivers/char/agp/generic.c
+++ b/drivers/char/agp/generic.c
@@ -1226,7 +1226,7 @@ int agp_generic_alloc_pages(struct agp_bridge_data *bridge, struct agp_memory *m
int i, ret = -ENOMEM;

for (i = 0; i < num_pages; i++) {
- page = alloc_page(GFP_KERNEL | GFP_DMA32);
+ page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
/* agp_free_memory() needs gart address */
if (page == NULL)
goto out;
@@ -1257,7 +1257,7 @@ void *agp_generic_alloc_page(struct agp_bridge_data *bridge)
{
struct page * page;

- page = alloc_page(GFP_KERNEL | GFP_DMA32);
+ page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
if (page == NULL)
return NULL;

diff --git a/drivers/char/vt.c b/drivers/char/vt.c
index 7900bd6..60453ab 100644
--- a/drivers/char/vt.c
+++ b/drivers/char/vt.c
@@ -2271,7 +2271,7 @@ rescan_last_byte:
continue; /* nothing to display */
}
/* Glyph not found */
- if ((!(vc->vc_utf && !vc->vc_disp_ctrl) && c < 128) && !(c & ~charmask)) {
+ if ((!(vc->vc_utf && !vc->vc_disp_ctrl) || c < 128) && !(c & ~charmask)) {
/* In legacy mode use the glyph we get by a 1:1 mapping.
This would make absolutely no sense with Unicode in mind,
but do this for ASCII characters since a font may lack
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 88d3368..7ee1ce1 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -505,7 +505,6 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
struct drm_map *map = NULL;
struct drm_gem_object *obj;
struct drm_hash_item *hash;
- unsigned long prot;
int ret = 0;

mutex_lock(&dev->struct_mutex);
@@ -538,11 +537,7 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
vma->vm_ops = obj->dev->driver->gem_vm_ops;
vma->vm_private_data = map->handle;
/* FIXME: use pgprot_writecombine when available */
- prot = pgprot_val(vma->vm_page_prot);
-#ifdef CONFIG_X86
- prot |= _PAGE_CACHE_WC;
-#endif
- vma->vm_page_prot = __pgprot(prot);
+ vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);

/* Take a ref for this mapping of the object, so that the fault
* handler can dereference the mmap offset's pointer to the object.
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 6d21b9e..908d24e 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -41,7 +41,6 @@
int i915_wait_ring(struct drm_device * dev, int n, const char *caller)
{
drm_i915_private_t *dev_priv = dev->dev_private;
- struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
drm_i915_ring_buffer_t *ring = &(dev_priv->ring);
u32 acthd_reg = IS_I965G(dev) ? ACTHD_I965 : ACTHD;
u32 last_acthd = I915_READ(acthd_reg);
@@ -58,8 +57,12 @@ int i915_wait_ring(struct drm_device * dev, int n, const char *caller)
if (ring->space >= n)
return 0;

- if (master_priv->sarea_priv)
- master_priv->sarea_priv->perf_boxes |= I915_BOX_WAIT;
+ if (dev->primary->master) {
+ struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
+ if (master_priv->sarea_priv)
+ master_priv->sarea_priv->perf_boxes |= I915_BOX_WAIT;
+ }
+

if (ring->head != last_head)
i = 0;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 37427e4..fb6390a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -603,6 +603,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
case -EAGAIN:
return VM_FAULT_OOM;
case -EFAULT:
+ case -EINVAL:
return VM_FAULT_SIGBUS;
default:
return VM_FAULT_NOPAGE;
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 7fb4191..4cce1ae 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -96,16 +96,16 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
*/
swizzle_x = I915_BIT_6_SWIZZLE_NONE;
swizzle_y = I915_BIT_6_SWIZZLE_NONE;
- } else if ((!IS_I965G(dev) && !IS_G33(dev)) || IS_I965GM(dev) ||
- IS_GM45(dev)) {
+ } else if (IS_MOBILE(dev)) {
uint32_t dcc;

- /* On 915-945 and GM965, channel interleave by the CPU is
- * determined by DCC. The CPU will alternate based on bit 6
- * in interleaved mode, and the GPU will then also alternate
- * on bit 6, 9, and 10 for X, but the CPU may also optionally
- * alternate based on bit 17 (XOR not disabled and XOR
- * bit == 17).
+ /* On mobile 9xx chipsets, channel interleave by the CPU is
+ * determined by DCC. For single-channel, neither the CPU
+ * nor the GPU do swizzling. For dual channel interleaved,
+ * the GPU's interleave is bit 9 and 10 for X tiled, and bit
+ * 9 for Y tiled. The CPU's interleave is independent, and
+ * can be based on either bit 11 (haven't seen this yet) or
+ * bit 17 (common).
*/
dcc = I915_READ(DCC);
switch (dcc & DCC_ADDRESSING_MODE_MASK) {
@@ -115,19 +115,18 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
swizzle_y = I915_BIT_6_SWIZZLE_NONE;
break;
case DCC_ADDRESSING_MODE_DUAL_CHANNEL_INTERLEAVED:
- if (IS_I915G(dev) || IS_I915GM(dev) ||
- dcc & DCC_CHANNEL_XOR_DISABLE) {
+ if (dcc & DCC_CHANNEL_XOR_DISABLE) {
+ /* This is the base swizzling by the GPU for
+ * tiled buffers.
+ */
swizzle_x = I915_BIT_6_SWIZZLE_9_10;
swizzle_y = I915_BIT_6_SWIZZLE_9;
- } else if ((IS_I965GM(dev) || IS_GM45(dev)) &&
- (dcc & DCC_CHANNEL_XOR_BIT_17) == 0) {
- /* GM965/GM45 does either bit 11 or bit 17
- * swizzling.
- */
+ } else if ((dcc & DCC_CHANNEL_XOR_BIT_17) == 0) {
+ /* Bit 11 swizzling by the CPU in addition. */
swizzle_x = I915_BIT_6_SWIZZLE_9_10_11;
swizzle_y = I915_BIT_6_SWIZZLE_9_11;
} else {
- /* Bit 17 or perhaps other swizzling */
+ /* Bit 17 swizzling by the CPU in addition. */
swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
}
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 90600d8..cc2938d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -629,6 +629,22 @@
#define TV_HOTPLUG_INT_EN (1 << 18)
#define CRT_HOTPLUG_INT_EN (1 << 9)
#define CRT_HOTPLUG_FORCE_DETECT (1 << 3)
+#define CRT_HOTPLUG_ACTIVATION_PERIOD_32 (0 << 8)
+/* must use period 64 on GM45 according to docs */
+#define CRT_HOTPLUG_ACTIVATION_PERIOD_64 (1 << 8)
+#define CRT_HOTPLUG_DAC_ON_TIME_2M (0 << 7)
+#define CRT_HOTPLUG_DAC_ON_TIME_4M (1 << 7)
+#define CRT_HOTPLUG_VOLTAGE_COMPARE_40 (0 << 5)
+#define CRT_HOTPLUG_VOLTAGE_COMPARE_50 (1 << 5)
+#define CRT_HOTPLUG_VOLTAGE_COMPARE_60 (2 << 5)
+#define CRT_HOTPLUG_VOLTAGE_COMPARE_70 (3 << 5)
+#define CRT_HOTPLUG_VOLTAGE_COMPARE_MASK (3 << 5)
+#define CRT_HOTPLUG_DETECT_DELAY_1G (0 << 4)
+#define CRT_HOTPLUG_DETECT_DELAY_2G (1 << 4)
+#define CRT_HOTPLUG_DETECT_VOLTAGE_325MV (0 << 2)
+#define CRT_HOTPLUG_DETECT_VOLTAGE_475MV (1 << 2)
+#define CRT_HOTPLUG_MASK (0x3fc) /* Bits 9-2 */
+

#define PORT_HOTPLUG_STAT 0x61114
#define HDMIB_HOTPLUG_INT_STATUS (1 << 29)
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index dcaed34..61c108e 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -133,20 +133,39 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
{
struct drm_device *dev = connector->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 temp;
-
- unsigned long timeout = jiffies + msecs_to_jiffies(1000);
-
- temp = I915_READ(PORT_HOTPLUG_EN);
-
- I915_WRITE(PORT_HOTPLUG_EN,
- temp | CRT_HOTPLUG_FORCE_DETECT | (1 << 5));
+ u32 hotplug_en;
+ int i, tries = 0;
+ /*
+ * On 4 series desktop, CRT detect sequence need to be done twice
+ * to get a reliable result.
+ */

- do {
- if (!(I915_READ(PORT_HOTPLUG_EN) & CRT_HOTPLUG_FORCE_DETECT))
- break;
- msleep(1);
- } while (time_after(timeout, jiffies));
+ if (IS_G4X(dev) && !IS_GM45(dev))
+ tries = 2;
+ else
+ tries = 1;
+ hotplug_en = I915_READ(PORT_HOTPLUG_EN);
+ hotplug_en &= ~(CRT_HOTPLUG_MASK);
+ hotplug_en |= CRT_HOTPLUG_FORCE_DETECT;
+
+ if (IS_GM45(dev))
+ hotplug_en |= CRT_HOTPLUG_ACTIVATION_PERIOD_64;
+
+ hotplug_en |= CRT_HOTPLUG_VOLTAGE_COMPARE_50;
+
+ for (i = 0; i < tries ; i++) {
+ unsigned long timeout;
+ /* turn on the FORCE_DETECT */
+ I915_WRITE(PORT_HOTPLUG_EN, hotplug_en);
+ timeout = jiffies + msecs_to_jiffies(1000);
+ /* wait for FORCE_DETECT to go off */
+ do {
+ if (!(I915_READ(PORT_HOTPLUG_EN) &
+ CRT_HOTPLUG_FORCE_DETECT))
+ break;
+ msleep(1);
+ } while (time_after(timeout, jiffies));
+ }

if ((I915_READ(PORT_HOTPLUG_STAT) & CRT_HOTPLUG_MONITOR_MASK) ==
CRT_HOTPLUG_MONITOR_COLOR)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index a283427..601a76f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1474,13 +1474,21 @@ static void intel_setup_outputs(struct drm_device *dev)

if (IS_I9XX(dev)) {
int found;
+ u32 reg;

if (I915_READ(SDVOB) & SDVO_DETECTED) {
found = intel_sdvo_init(dev, SDVOB);
if (!found && SUPPORTS_INTEGRATED_HDMI(dev))
intel_hdmi_init(dev, SDVOB);
}
- if (!IS_G4X(dev) || (I915_READ(SDVOB) & SDVO_DETECTED)) {
+
+ /* Before G4X SDVOC doesn't have its own detect register */
+ if (IS_G4X(dev))
+ reg = SDVOC;
+ else
+ reg = SDVOB;
+
+ if (I915_READ(reg) & SDVO_DETECTED) {
found = intel_sdvo_init(dev, SDVOC);
if (!found && SUPPORTS_INTEGRATED_HDMI(dev))
intel_hdmi_init(dev, SDVOC);
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 56485d6..b05cb67 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1558,33 +1558,49 @@ intel_tv_set_property(struct drm_connector *connector, struct drm_property *prop
struct drm_device *dev = connector->dev;
struct intel_output *intel_output = to_intel_output(connector);
struct intel_tv_priv *tv_priv = intel_output->dev_priv;
+ struct drm_encoder *encoder = &intel_output->enc;
+ struct drm_crtc *crtc = encoder->crtc;
int ret = 0;
+ bool changed = false;

ret = drm_connector_property_set_value(connector, property, val);
if (ret < 0)
goto out;

- if (property == dev->mode_config.tv_left_margin_property)
+ if (property == dev->mode_config.tv_left_margin_property &&
+ tv_priv->margin[TV_MARGIN_LEFT] != val) {
tv_priv->margin[TV_MARGIN_LEFT] = val;
- else if (property == dev->mode_config.tv_right_margin_property)
+ changed = true;
+ } else if (property == dev->mode_config.tv_right_margin_property &&
+ tv_priv->margin[TV_MARGIN_RIGHT] != val) {
tv_priv->margin[TV_MARGIN_RIGHT] = val;
- else if (property == dev->mode_config.tv_top_margin_property)
+ changed = true;
+ } else if (property == dev->mode_config.tv_top_margin_property &&
+ tv_priv->margin[TV_MARGIN_TOP] != val) {
tv_priv->margin[TV_MARGIN_TOP] = val;
- else if (property == dev->mode_config.tv_bottom_margin_property)
+ changed = true;
+ } else if (property == dev->mode_config.tv_bottom_margin_property &&
+ tv_priv->margin[TV_MARGIN_BOTTOM] != val) {
tv_priv->margin[TV_MARGIN_BOTTOM] = val;
- else if (property == dev->mode_config.tv_mode_property) {
+ changed = true;
+ } else if (property == dev->mode_config.tv_mode_property) {
if (val >= NUM_TV_MODES) {
ret = -EINVAL;
goto out;
}
+ if (!strcmp(tv_priv->tv_format, tv_modes[val].name))
+ goto out;
+
tv_priv->tv_format = tv_modes[val].name;
- intel_tv_mode_set(&intel_output->enc, NULL, NULL);
+ changed = true;
} else {
ret = -EINVAL;
goto out;
}

- intel_tv_mode_set(&intel_output->enc, NULL, NULL);
+ if (changed && crtc)
+ drm_crtc_helper_set_mode(crtc, &crtc->mode, crtc->x,
+ crtc->y, crtc->fb);
out:
return ret;
}
diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c
index 3eb9b5c..5ff6962 100644
--- a/drivers/ide/hpt366.c
+++ b/drivers/ide/hpt366.c
@@ -114,6 +114,8 @@
* the register setting lists into the table indexed by the clock selected
* - set the correct hwif->ultra_mask for each individual chip
* - add Ultra and MW DMA mode filtering for the HPT37[24] based SATA cards
+ * - stop resetting HPT370's state machine before each DMA transfer as that has
+ * caused more harm than good
* Sergei Shtylyov, <sshtylyov@xxxxxxxxxxxxx> or <source@xxxxxxxxxx>
*/

@@ -133,7 +135,7 @@
#define DRV_NAME "hpt366"

/* various tuning parameters */
-#define HPT_RESET_STATE_ENGINE
+#undef HPT_RESET_STATE_ENGINE
#undef HPT_DELAY_INTERRUPT

static const char *quirk_drives[] = {
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index e9d042d..53a9e8d 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -6,6 +6,8 @@
#include <linux/cdrom.h>
#include <linux/delay.h>
#include <linux/ide.h>
+#include <linux/scatterlist.h>
+
#include <scsi/scsi.h>

#ifdef DEBUG
@@ -566,6 +568,10 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive)
: ide_pc_intr),
timeout, expiry);

+ /* Send the actual packet */
+ if ((drive->atapi_flags & IDE_AFLAG_ZIP_DRIVE) == 0)
+ hwif->tp_ops->output_data(drive, NULL, rq->cmd, cmd_len);
+
/* Begin DMA, if necessary */
if (dev_is_idecd(drive)) {
if (drive->dma)
@@ -577,10 +583,6 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive)
}
}

- /* Send the actual packet */
- if ((drive->atapi_flags & IDE_AFLAG_ZIP_DRIVE) == 0)
- hwif->tp_ops->output_data(drive, NULL, rq->cmd, cmd_len);
-
return ide_started;
}

diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index a9a6c20..af70777 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -736,11 +736,10 @@ repeat:
prev_port = hwif->host->cur_port;
hwif->rq = NULL;

- if (drive->dev_flags & IDE_DFLAG_SLEEPING) {
- if (time_before(drive->sleep, jiffies)) {
- ide_unlock_port(hwif);
- goto plug_device;
- }
+ if (drive->dev_flags & IDE_DFLAG_SLEEPING &&
+ time_after(drive->sleep, jiffies)) {
+ ide_unlock_port(hwif);
+ goto plug_device;
}

if ((hwif->host->host_flags & IDE_HFLAG_SERIALIZE) &&
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index ebf4be5..2d175b5 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -50,9 +50,8 @@ static LIST_HEAD(gameport_list);

static struct bus_type gameport_bus;

-static void gameport_add_driver(struct gameport_driver *drv);
static void gameport_add_port(struct gameport *gameport);
-static void gameport_destroy_port(struct gameport *gameport);
+static void gameport_attach_driver(struct gameport_driver *drv);
static void gameport_reconnect_port(struct gameport *gameport);
static void gameport_disconnect_port(struct gameport *gameport);

@@ -230,7 +229,6 @@ static void gameport_find_driver(struct gameport *gameport)

enum gameport_event_type {
GAMEPORT_REGISTER_PORT,
- GAMEPORT_REGISTER_DRIVER,
GAMEPORT_ATTACH_DRIVER,
};

@@ -374,8 +372,8 @@ static void gameport_handle_event(void)
gameport_add_port(event->object);
break;

- case GAMEPORT_REGISTER_DRIVER:
- gameport_add_driver(event->object);
+ case GAMEPORT_ATTACH_DRIVER:
+ gameport_attach_driver(event->object);
break;

default:
@@ -706,14 +704,14 @@ static int gameport_driver_remove(struct device *dev)
return 0;
}

-static void gameport_add_driver(struct gameport_driver *drv)
+static void gameport_attach_driver(struct gameport_driver *drv)
{
int error;

- error = driver_register(&drv->driver);
+ error = driver_attach(&drv->driver);
if (error)
printk(KERN_ERR
- "gameport: driver_register() failed for %s, error: %d\n",
+ "gameport: driver_attach() failed for %s, error: %d\n",
drv->driver.name, error);
}

diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h
index d3ec217..3a8cfa2 100644
--- a/drivers/md/dm-bio-record.h
+++ b/drivers/md/dm-bio-record.h
@@ -16,30 +16,56 @@
* functions in this file help the target record and restore the
* original bio state.
*/
+
+struct dm_bio_vec_details {
+#if PAGE_SIZE < 65536
+ __u16 bv_len;
+ __u16 bv_offset;
+#else
+ unsigned bv_len;
+ unsigned bv_offset;
+#endif
+};
+
struct dm_bio_details {
sector_t bi_sector;
struct block_device *bi_bdev;
unsigned int bi_size;
unsigned short bi_idx;
unsigned long bi_flags;
+ struct dm_bio_vec_details bi_io_vec[BIO_MAX_PAGES];
};

static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
{
+ unsigned i;
+
bd->bi_sector = bio->bi_sector;
bd->bi_bdev = bio->bi_bdev;
bd->bi_size = bio->bi_size;
bd->bi_idx = bio->bi_idx;
bd->bi_flags = bio->bi_flags;
+
+ for (i = 0; i < bio->bi_vcnt; i++) {
+ bd->bi_io_vec[i].bv_len = bio->bi_io_vec[i].bv_len;
+ bd->bi_io_vec[i].bv_offset = bio->bi_io_vec[i].bv_offset;
+ }
}

static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
{
+ unsigned i;
+
bio->bi_sector = bd->bi_sector;
bio->bi_bdev = bd->bi_bdev;
bio->bi_size = bd->bi_size;
bio->bi_idx = bd->bi_idx;
bio->bi_flags = bd->bi_flags;
+
+ for (i = 0; i < bio->bi_vcnt; i++) {
+ bio->bi_io_vec[i].bv_len = bd->bi_io_vec[i].bv_len;
+ bio->bi_io_vec[i].bv_offset = bd->bi_io_vec[i].bv_offset;
+ }
}

#endif
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 36e2b5e..e73aabd 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -370,16 +370,13 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
while (1) {
set_current_state(TASK_UNINTERRUPTIBLE);

- if (!atomic_read(&io.count) || signal_pending(current))
+ if (!atomic_read(&io.count))
break;

io_schedule();
}
set_current_state(TASK_RUNNING);

- if (atomic_read(&io.count))
- return -EINTR;
-
if (error_bits)
*error_bits = io.error_bits;

diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 0a225da..3e3fc06 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -297,7 +297,8 @@ static int run_complete_job(struct kcopyd_job *job)
dm_kcopyd_notify_fn fn = job->fn;
struct dm_kcopyd_client *kc = job->kc;

- kcopyd_put_pages(kc, job->pages);
+ if (job->pages)
+ kcopyd_put_pages(kc, job->pages);
mempool_free(job, kc->job_pool);
fn(read_err, write_err, context);

@@ -461,6 +462,7 @@ static void segment_complete(int read_err, unsigned long write_err,
sector_t progress = 0;
sector_t count = 0;
struct kcopyd_job *job = (struct kcopyd_job *) context;
+ struct dm_kcopyd_client *kc = job->kc;

mutex_lock(&job->lock);

@@ -490,7 +492,7 @@ static void segment_complete(int read_err, unsigned long write_err,

if (count) {
int i;
- struct kcopyd_job *sub_job = mempool_alloc(job->kc->job_pool,
+ struct kcopyd_job *sub_job = mempool_alloc(kc->job_pool,
GFP_NOIO);

*sub_job = *job;
@@ -509,13 +511,16 @@ static void segment_complete(int read_err, unsigned long write_err,
} else if (atomic_dec_and_test(&job->sub_jobs)) {

/*
- * To avoid a race we must keep the job around
- * until after the notify function has completed.
- * Otherwise the client may try and stop the job
- * after we've completed.
+ * Queue the completion callback to the kcopyd thread.
+ *
+ * Some callers assume that all the completions are called
+ * from a single thread and don't race with each other.
+ *
+ * We must not call the callback directly here because this
+ * code may not be executing in the thread.
*/
- job->fn(read_err, write_err, job->context);
- mempool_free(job, job->kc->job_pool);
+ push(&kc->complete_jobs, job);
+ wake(kc);
}
}

@@ -528,6 +533,8 @@ static void split_job(struct kcopyd_job *job)
{
int i;

+ atomic_inc(&job->kc->nr_jobs);
+
atomic_set(&job->sub_jobs, SPLIT_COUNT);
for (i = 0; i < SPLIT_COUNT; i++)
segment_complete(0, 0u, job);
diff --git a/drivers/md/dm-path-selector.c b/drivers/md/dm-path-selector.c
index 96ea226..42c04f0 100644
--- a/drivers/md/dm-path-selector.c
+++ b/drivers/md/dm-path-selector.c
@@ -17,9 +17,7 @@

struct ps_internal {
struct path_selector_type pst;
-
struct list_head list;
- long use;
};

#define pst_to_psi(__pst) container_of((__pst), struct ps_internal, pst)
@@ -45,12 +43,8 @@ static struct ps_internal *get_path_selector(const char *name)

down_read(&_ps_lock);
psi = __find_path_selector_type(name);
- if (psi) {
- if ((psi->use == 0) && !try_module_get(psi->pst.module))
- psi = NULL;
- else
- psi->use++;
- }
+ if (psi && !try_module_get(psi->pst.module))
+ psi = NULL;
up_read(&_ps_lock);

return psi;
@@ -84,11 +78,7 @@ void dm_put_path_selector(struct path_selector_type *pst)
if (!psi)
goto out;

- if (--psi->use == 0)
- module_put(psi->pst.module);
-
- BUG_ON(psi->use < 0);
-
+ module_put(psi->pst.module);
out:
up_read(&_ps_lock);
}
@@ -136,11 +126,6 @@ int dm_unregister_path_selector(struct path_selector_type *pst)
return -EINVAL;
}

- if (psi->use) {
- up_write(&_ps_lock);
- return -ETXTBSY;
- }
-
list_del(&psi->list);

up_write(&_ps_lock);
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 4d6bc10..62d5948 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -145,6 +145,8 @@ struct dm_raid1_read_record {
struct dm_bio_details details;
};

+static struct kmem_cache *_dm_raid1_read_record_cache;
+
/*
* Every mirror should look like this one.
*/
@@ -764,9 +766,9 @@ static struct mirror_set *alloc_context(unsigned int nr_mirrors,
atomic_set(&ms->suspend, 0);
atomic_set(&ms->default_mirror, DEFAULT_MIRROR);

- len = sizeof(struct dm_raid1_read_record);
- ms->read_record_pool = mempool_create_kmalloc_pool(MIN_READ_RECORDS,
- len);
+ ms->read_record_pool = mempool_create_slab_pool(MIN_READ_RECORDS,
+ _dm_raid1_read_record_cache);
+
if (!ms->read_record_pool) {
ti->error = "Error creating mirror read_record_pool";
kfree(ms);
@@ -1279,16 +1281,31 @@ static int __init dm_mirror_init(void)
{
int r;

+ _dm_raid1_read_record_cache = KMEM_CACHE(dm_raid1_read_record, 0);
+ if (!_dm_raid1_read_record_cache) {
+ DMERR("Can't allocate dm_raid1_read_record cache");
+ r = -ENOMEM;
+ goto bad_cache;
+ }
+
r = dm_register_target(&mirror_target);
- if (r < 0)
+ if (r < 0) {
DMERR("Failed to register mirror target");
+ goto bad_target;
+ }
+
+ return 0;

+bad_target:
+ kmem_cache_destroy(_dm_raid1_read_record_cache);
+bad_cache:
return r;
}

static void __exit dm_mirror_exit(void)
{
dm_unregister_target(&mirror_target);
+ kmem_cache_destroy(_dm_raid1_read_record_cache);
}

/* Module hooks */
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 65ff82f..462750c 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -972,6 +972,17 @@ static void start_copy(struct dm_snap_pending_exception *pe)
&src, 1, &dest, 0, copy_callback, pe);
}

+static struct dm_snap_pending_exception *
+__lookup_pending_exception(struct dm_snapshot *s, chunk_t chunk)
+{
+ struct dm_snap_exception *e = lookup_exception(&s->pending, chunk);
+
+ if (!e)
+ return NULL;
+
+ return container_of(e, struct dm_snap_pending_exception, e);
+}
+
/*
* Looks to see if this snapshot already has a pending exception
* for this chunk, otherwise it allocates a new one and inserts
@@ -981,40 +992,15 @@ static void start_copy(struct dm_snap_pending_exception *pe)
* this.
*/
static struct dm_snap_pending_exception *
-__find_pending_exception(struct dm_snapshot *s, struct bio *bio)
+__find_pending_exception(struct dm_snapshot *s,
+ struct dm_snap_pending_exception *pe, chunk_t chunk)
{
- struct dm_snap_exception *e;
- struct dm_snap_pending_exception *pe;
- chunk_t chunk = sector_to_chunk(s, bio->bi_sector);
-
- /*
- * Is there a pending exception for this already ?
- */
- e = lookup_exception(&s->pending, chunk);
- if (e) {
- /* cast the exception to a pending exception */
- pe = container_of(e, struct dm_snap_pending_exception, e);
- goto out;
- }
-
- /*
- * Create a new pending exception, we don't want
- * to hold the lock while we do this.
- */
- up_write(&s->lock);
- pe = alloc_pending_exception(s);
- down_write(&s->lock);
-
- if (!s->valid) {
- free_pending_exception(pe);
- return NULL;
- }
+ struct dm_snap_pending_exception *pe2;

- e = lookup_exception(&s->pending, chunk);
- if (e) {
+ pe2 = __lookup_pending_exception(s, chunk);
+ if (pe2) {
free_pending_exception(pe);
- pe = container_of(e, struct dm_snap_pending_exception, e);
- goto out;
+ return pe2;
}

pe->e.old_chunk = chunk;
@@ -1032,7 +1018,6 @@ __find_pending_exception(struct dm_snapshot *s, struct bio *bio)
get_pending_exception(pe);
insert_exception(&s->pending, &pe->e);

- out:
return pe;
}

@@ -1083,11 +1068,31 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio,
* writeable.
*/
if (bio_rw(bio) == WRITE) {
- pe = __find_pending_exception(s, bio);
+ pe = __lookup_pending_exception(s, chunk);
if (!pe) {
- __invalidate_snapshot(s, -ENOMEM);
- r = -EIO;
- goto out_unlock;
+ up_write(&s->lock);
+ pe = alloc_pending_exception(s);
+ down_write(&s->lock);
+
+ if (!s->valid) {
+ free_pending_exception(pe);
+ r = -EIO;
+ goto out_unlock;
+ }
+
+ e = lookup_exception(&s->complete, chunk);
+ if (e) {
+ free_pending_exception(pe);
+ remap_exception(s, e, bio, chunk);
+ goto out_unlock;
+ }
+
+ pe = __find_pending_exception(s, pe, chunk);
+ if (!pe) {
+ __invalidate_snapshot(s, -ENOMEM);
+ r = -EIO;
+ goto out_unlock;
+ }
}

remap_exception(s, &pe->e, bio, chunk);
@@ -1217,10 +1222,28 @@ static int __origin_write(struct list_head *snapshots, struct bio *bio)
if (e)
goto next_snapshot;

- pe = __find_pending_exception(snap, bio);
+ pe = __lookup_pending_exception(snap, chunk);
if (!pe) {
- __invalidate_snapshot(snap, -ENOMEM);
- goto next_snapshot;
+ up_write(&snap->lock);
+ pe = alloc_pending_exception(snap);
+ down_write(&snap->lock);
+
+ if (!snap->valid) {
+ free_pending_exception(pe);
+ goto next_snapshot;
+ }
+
+ e = lookup_exception(&snap->complete, chunk);
+ if (e) {
+ free_pending_exception(pe);
+ goto next_snapshot;
+ }
+
+ pe = __find_pending_exception(snap, pe, chunk);
+ if (!pe) {
+ __invalidate_snapshot(snap, -ENOMEM);
+ goto next_snapshot;
+ }
}

if (!primary_pe) {
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 2fd66c3..e8361b1 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -399,28 +399,30 @@ static int check_device_area(struct dm_dev_internal *dd, sector_t start,
}

/*
- * This upgrades the mode on an already open dm_dev. Being
+ * This upgrades the mode on an already open dm_dev, being
* careful to leave things as they were if we fail to reopen the
- * device.
+ * device and not to touch the existing bdev field in case
+ * it is accessed concurrently inside dm_table_any_congested().
*/
static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
struct mapped_device *md)
{
int r;
- struct dm_dev_internal dd_copy;
- dev_t dev = dd->dm_dev.bdev->bd_dev;
+ struct dm_dev_internal dd_new, dd_old;

- dd_copy = *dd;
+ dd_new = dd_old = *dd;
+
+ dd_new.dm_dev.mode |= new_mode;
+ dd_new.dm_dev.bdev = NULL;
+
+ r = open_dev(&dd_new, dd->dm_dev.bdev->bd_dev, md);
+ if (r)
+ return r;

dd->dm_dev.mode |= new_mode;
- dd->dm_dev.bdev = NULL;
- r = open_dev(dd, dev, md);
- if (!r)
- close_dev(&dd_copy, md);
- else
- *dd = dd_copy;
+ close_dev(&dd_old, md);

- return r;
+ return 0;
}

/*
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 7decf10..db72c94 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -18,7 +18,6 @@ struct tt_internal {
struct target_type tt;

struct list_head list;
- long use;
};

static LIST_HEAD(_targets);
@@ -44,12 +43,8 @@ static struct tt_internal *get_target_type(const char *name)
down_read(&_lock);

ti = __find_target_type(name);
- if (ti) {
- if ((ti->use == 0) && !try_module_get(ti->tt.module))
- ti = NULL;
- else
- ti->use++;
- }
+ if (ti && !try_module_get(ti->tt.module))
+ ti = NULL;

up_read(&_lock);
return ti;
@@ -77,10 +72,7 @@ void dm_put_target_type(struct target_type *t)
struct tt_internal *ti = (struct tt_internal *) t;

down_read(&_lock);
- if (--ti->use == 0)
- module_put(ti->tt.module);
-
- BUG_ON(ti->use < 0);
+ module_put(ti->tt.module);
up_read(&_lock);

return;
@@ -140,12 +132,6 @@ void dm_unregister_target(struct target_type *t)
BUG();
}

- if (ti->use) {
- DMCRIT("Attempt to unregister target still in use: %s",
- t->name);
- BUG();
- }
-
list_del(&ti->list);
kfree(ti);

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e246642..4a25fa9 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -120,6 +120,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
goto out_free_pages;

bio->bi_io_vec[i].bv_page = page;
+ bio->bi_vcnt = i+1;
}
}
/* If not user-requests, copy the page pointers to all bios */
@@ -135,9 +136,9 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
return r1_bio;

out_free_pages:
- for (i=0; i < RESYNC_PAGES ; i++)
- for (j=0 ; j < pi->raid_disks; j++)
- safe_put_page(r1_bio->bios[j]->bi_io_vec[i].bv_page);
+ for (j=0 ; j < pi->raid_disks; j++)
+ for (i=0; i < r1_bio->bios[j]->bi_vcnt ; i++)
+ put_page(r1_bio->bios[j]->bi_io_vec[i].bv_page);
j = -1;
out_free_bio:
while ( ++j < pi->raid_disks )
diff --git a/drivers/media/video/cx88/cx88-input.c b/drivers/media/video/cx88/cx88-input.c
index 8683d10..5b107fa 100644
--- a/drivers/media/video/cx88/cx88-input.c
+++ b/drivers/media/video/cx88/cx88-input.c
@@ -48,8 +48,7 @@ struct cx88_IR {

/* poll external decoder */
int polling;
- struct work_struct work;
- struct timer_list timer;
+ struct delayed_work work;
u32 gpio_addr;
u32 last_gpio;
u32 mask_keycode;
@@ -143,27 +142,19 @@ static void cx88_ir_handle_key(struct cx88_IR *ir)
}
}

-static void ir_timer(unsigned long data)
-{
- struct cx88_IR *ir = (struct cx88_IR *)data;
-
- schedule_work(&ir->work);
-}
-
static void cx88_ir_work(struct work_struct *work)
{
- struct cx88_IR *ir = container_of(work, struct cx88_IR, work);
+ struct cx88_IR *ir = container_of(work, struct cx88_IR, work.work);

cx88_ir_handle_key(ir);
- mod_timer(&ir->timer, jiffies + msecs_to_jiffies(ir->polling));
+ schedule_delayed_work(&ir->work, msecs_to_jiffies(ir->polling));
}

void cx88_ir_start(struct cx88_core *core, struct cx88_IR *ir)
{
if (ir->polling) {
- setup_timer(&ir->timer, ir_timer, (unsigned long)ir);
- INIT_WORK(&ir->work, cx88_ir_work);
- schedule_work(&ir->work);
+ INIT_DELAYED_WORK(&ir->work, cx88_ir_work);
+ schedule_delayed_work(&ir->work, 0);
}
if (ir->sampling) {
core->pci_irqmask |= PCI_INT_IR_SMPINT;
@@ -179,10 +170,8 @@ void cx88_ir_stop(struct cx88_core *core, struct cx88_IR *ir)
core->pci_irqmask &= ~PCI_INT_IR_SMPINT;
}

- if (ir->polling) {
- del_timer_sync(&ir->timer);
- flush_scheduled_work();
- }
+ if (ir->polling)
+ cancel_delayed_work_sync(&ir->work);
}

/* ---------------------------------------------------------------------- */
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index ea3aafb..6fc789e 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -5934,7 +5934,7 @@ mpt_config(MPT_ADAPTER *ioc, CONFIGPARMS *pCfg)

/* Initalize the timer
*/
- init_timer(&pCfg->timer);
+ init_timer_on_stack(&pCfg->timer);
pCfg->timer.data = (unsigned long) ioc;
pCfg->timer.function = mpt_timer_expired;
pCfg->wait_done = 0;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3d76686..87045f8 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2565,7 +2565,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)

for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
if (!targets[i])
- continue;
+ break;
pr_debug("basa: target %x\n", targets[i]);
if (list_empty(&bond->vlan_list)) {
pr_debug("basa: empty vlan: arp_send\n");
@@ -2672,7 +2672,6 @@ static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32
int i;
__be32 *targets = bond->params.arp_targets;

- targets = bond->params.arp_targets;
for (i = 0; (i < BOND_MAX_ARP_TARGETS) && targets[i]; i++) {
pr_debug("bva: sip %pI4 tip %pI4 t[%d] %pI4 bhti(tip) %d\n",
&sip, &tip, i, &targets[i], bond_has_this_ip(bond, tip));
@@ -3294,7 +3293,7 @@ static void bond_info_show_master(struct seq_file *seq)

for(i = 0; (i < BOND_MAX_ARP_TARGETS) ;i++) {
if (!bond->params.arp_targets[i])
- continue;
+ break;
if (printed)
seq_printf(seq, ",");
seq_printf(seq, " %pI4", &bond->params.arp_targets[i]);
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 18cf478..d287315 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -684,17 +684,15 @@ static ssize_t bonding_store_arp_targets(struct device *d,
goto out;
}
/* look for an empty slot to put the target in, and check for dupes */
- for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
+ for (i = 0; (i < BOND_MAX_ARP_TARGETS) && !done; i++) {
if (targets[i] == newtarget) { /* duplicate */
printk(KERN_ERR DRV_NAME
": %s: ARP target %pI4 is already present\n",
bond->dev->name, &newtarget);
- if (done)
- targets[i] = 0;
ret = -EINVAL;
goto out;
}
- if (targets[i] == 0 && !done) {
+ if (targets[i] == 0) {
printk(KERN_INFO DRV_NAME
": %s: adding ARP target %pI4.\n",
bond->dev->name, &newtarget);
@@ -720,12 +718,16 @@ static ssize_t bonding_store_arp_targets(struct device *d,
goto out;
}

- for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
+ for (i = 0; (i < BOND_MAX_ARP_TARGETS) && !done; i++) {
if (targets[i] == newtarget) {
+ int j;
printk(KERN_INFO DRV_NAME
": %s: removing ARP target %pI4.\n",
bond->dev->name, &newtarget);
- targets[i] = 0;
+ for (j = i; (j < (BOND_MAX_ARP_TARGETS-1)) && targets[j+1]; j++)
+ targets[j] = targets[j+1];
+
+ targets[j] = 0;
done = 1;
}
}
diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c
index 67f87a7..090ada6 100644
--- a/drivers/net/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ixgbe/ixgbe_ethtool.c
@@ -691,9 +691,10 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
struct ethtool_ringparam *ring)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- struct ixgbe_ring *temp_ring;
+ struct ixgbe_ring *temp_tx_ring, *temp_rx_ring;
int i, err;
u32 new_rx_count, new_tx_count;
+ bool need_update = false;

if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
return -EINVAL;
@@ -712,80 +713,94 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
return 0;
}

- temp_ring = kcalloc(adapter->num_tx_queues,
- sizeof(struct ixgbe_ring), GFP_KERNEL);
- if (!temp_ring)
- return -ENOMEM;
-
while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
msleep(1);

- if (new_tx_count != adapter->tx_ring->count) {
+ temp_tx_ring = kcalloc(adapter->num_tx_queues,
+ sizeof(struct ixgbe_ring), GFP_KERNEL);
+ if (!temp_tx_ring) {
+ err = -ENOMEM;
+ goto err_setup;
+ }
+
+ if (new_tx_count != adapter->tx_ring_count) {
+ memcpy(temp_tx_ring, adapter->tx_ring,
+ adapter->num_tx_queues * sizeof(struct ixgbe_ring));
for (i = 0; i < adapter->num_tx_queues; i++) {
- temp_ring[i].count = new_tx_count;
- err = ixgbe_setup_tx_resources(adapter, &temp_ring[i]);
+ temp_tx_ring[i].count = new_tx_count;
+ err = ixgbe_setup_tx_resources(adapter,
+ &temp_tx_ring[i]);
if (err) {
while (i) {
i--;
ixgbe_free_tx_resources(adapter,
- &temp_ring[i]);
+ &temp_tx_ring[i]);
}
goto err_setup;
}
- temp_ring[i].v_idx = adapter->tx_ring[i].v_idx;
+ temp_tx_ring[i].v_idx = adapter->tx_ring[i].v_idx;
}
- if (netif_running(netdev))
- netdev->netdev_ops->ndo_stop(netdev);
- ixgbe_reset_interrupt_capability(adapter);
- ixgbe_napi_del_all(adapter);
- INIT_LIST_HEAD(&netdev->napi_list);
- kfree(adapter->tx_ring);
- adapter->tx_ring = temp_ring;
- temp_ring = NULL;
- adapter->tx_ring_count = new_tx_count;
+ need_update = true;
}

- temp_ring = kcalloc(adapter->num_rx_queues,
- sizeof(struct ixgbe_ring), GFP_KERNEL);
- if (!temp_ring) {
- if (netif_running(netdev))
- netdev->netdev_ops->ndo_open(netdev);
- return -ENOMEM;
+ temp_rx_ring = kcalloc(adapter->num_rx_queues,
+ sizeof(struct ixgbe_ring), GFP_KERNEL);
+ if ((!temp_rx_ring) && (need_update)) {
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ ixgbe_free_tx_resources(adapter, &temp_tx_ring[i]);
+ kfree(temp_tx_ring);
+ err = -ENOMEM;
+ goto err_setup;
}

- if (new_rx_count != adapter->rx_ring->count) {
+ if (new_rx_count != adapter->rx_ring_count) {
+ memcpy(temp_rx_ring, adapter->rx_ring,
+ adapter->num_rx_queues * sizeof(struct ixgbe_ring));
for (i = 0; i < adapter->num_rx_queues; i++) {
- temp_ring[i].count = new_rx_count;
- err = ixgbe_setup_rx_resources(adapter, &temp_ring[i]);
+ temp_rx_ring[i].count = new_rx_count;
+ err = ixgbe_setup_rx_resources(adapter,
+ &temp_rx_ring[i]);
if (err) {
while (i) {
i--;
ixgbe_free_rx_resources(adapter,
- &temp_ring[i]);
+ &temp_rx_ring[i]);
}
goto err_setup;
}
- temp_ring[i].v_idx = adapter->rx_ring[i].v_idx;
+ temp_rx_ring[i].v_idx = adapter->rx_ring[i].v_idx;
}
+ need_update = true;
+ }
+
+ /* if rings need to be updated, here's the place to do it in one shot */
+ if (need_update) {
if (netif_running(netdev))
- netdev->netdev_ops->ndo_stop(netdev);
- ixgbe_reset_interrupt_capability(adapter);
- ixgbe_napi_del_all(adapter);
- INIT_LIST_HEAD(&netdev->napi_list);
- kfree(adapter->rx_ring);
- adapter->rx_ring = temp_ring;
- temp_ring = NULL;
-
- adapter->rx_ring_count = new_rx_count;
+ ixgbe_down(adapter);
+
+ /* tx */
+ if (new_tx_count != adapter->tx_ring_count) {
+ kfree(adapter->tx_ring);
+ adapter->tx_ring = temp_tx_ring;
+ temp_tx_ring = NULL;
+ adapter->tx_ring_count = new_tx_count;
+ }
+
+ /* rx */
+ if (new_rx_count != adapter->rx_ring_count) {
+ kfree(adapter->rx_ring);
+ adapter->rx_ring = temp_rx_ring;
+ temp_rx_ring = NULL;
+ adapter->rx_ring_count = new_rx_count;
+ }
}

/* success! */
err = 0;
-err_setup:
- ixgbe_init_interrupt_scheme(adapter);
if (netif_running(netdev))
- netdev->netdev_ops->ndo_open(netdev);
+ ixgbe_up(adapter);

+err_setup:
clear_bit(__IXGBE_RESETTING, &adapter->state);
return err;
}
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 43fedb9..9201e5a 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -2075,8 +2075,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (!tp->pcie_cap && netif_msg_probe(tp))
dev_info(&pdev->dev, "no PCI Express capability\n");

- /* Unneeded ? Don't mess with Mrs. Murphy. */
- rtl8169_irq_mask_and_ack(ioaddr);
+ RTL_W16(IntrMask, 0x0000);

/* Soft reset the chip. */
RTL_W8(ChipCmd, CmdReset);
@@ -2088,6 +2087,8 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
msleep_interruptible(1);
}

+ RTL_W16(IntrStatus, 0xffff);
+
/* Identify chip attached to board */
rtl8169_get_mac_version(tp, ioaddr);

diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index ab0e09b..655e9b2 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -424,10 +424,6 @@ static void efx_start_channel(struct efx_channel *channel)

EFX_LOG(channel->efx, "starting chan %d\n", channel->channel);

- if (!(channel->efx->net_dev->flags & IFF_UP))
- netif_napi_add(channel->napi_dev, &channel->napi_str,
- efx_poll, napi_weight);
-
/* The interrupt handler for this channel may set work_pending
* as soon as we enable it. Make sure it's cleared before
* then. Similarly, make sure it sees the enabled flag set. */
@@ -1273,6 +1269,8 @@ static int efx_init_napi(struct efx_nic *efx)

efx_for_each_channel(channel, efx) {
channel->napi_dev = efx->net_dev;
+ netif_napi_add(channel->napi_dev, &channel->napi_str,
+ efx_poll, napi_weight);
rc = efx_lro_init(&channel->lro_mgr, efx);
if (rc)
goto err;
@@ -1289,6 +1287,8 @@ static void efx_fini_napi(struct efx_nic *efx)

efx_for_each_channel(channel, efx) {
efx_lro_fini(&channel->lro_mgr);
+ if (channel->napi_dev)
+ netif_napi_del(&channel->napi_str);
channel->napi_dev = NULL;
}
}
diff --git a/drivers/net/skge.c b/drivers/net/skge.c
index c9dbb06..2bbb44b 100644
--- a/drivers/net/skge.c
+++ b/drivers/net/skge.c
@@ -2674,7 +2674,7 @@ static int skge_down(struct net_device *dev)
if (netif_msg_ifdown(skge))
printk(KERN_INFO PFX "%s: disabling interface\n", dev->name);

- netif_stop_queue(dev);
+ netif_tx_disable(dev);

if (hw->chip_id == CHIP_ID_GENESIS && hw->phy_type == SK_PHY_XMAC)
del_timer_sync(&skge->link_timer);
@@ -2881,7 +2881,6 @@ static void skge_tx_clean(struct net_device *dev)
}

skge->tx_ring.to_clean = e;
- netif_wake_queue(dev);
}

static void skge_tx_timeout(struct net_device *dev)
@@ -2893,6 +2892,7 @@ static void skge_tx_timeout(struct net_device *dev)

skge_write8(skge->hw, Q_ADDR(txqaddr[skge->port], Q_CSR), CSR_STOP);
skge_tx_clean(dev);
+ netif_wake_queue(dev);
}

static int skge_change_mtu(struct net_device *dev, int new_mtu)
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index 39ecf3b..820fdb2 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -687,8 +687,7 @@ struct rt2x00_dev {
*/
#ifdef CONFIG_RT2X00_LIB_RFKILL
unsigned long rfkill_state;
-#define RFKILL_STATE_ALLOCATED 1
-#define RFKILL_STATE_REGISTERED 2
+#define RFKILL_STATE_REGISTERED 1
struct rfkill *rfkill;
struct delayed_work rfkill_work;
#endif /* CONFIG_RT2X00_LIB_RFKILL */
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 87c0f2c..e694bb7 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -1105,7 +1105,6 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
* Register extra components.
*/
rt2x00leds_register(rt2x00dev);
- rt2x00rfkill_allocate(rt2x00dev);
rt2x00debug_register(rt2x00dev);

set_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags);
@@ -1137,7 +1136,6 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev)
* Free extra components
*/
rt2x00debug_deregister(rt2x00dev);
- rt2x00rfkill_free(rt2x00dev);
rt2x00leds_unregister(rt2x00dev);

/*
diff --git a/drivers/net/wireless/rt2x00/rt2x00lib.h b/drivers/net/wireless/rt2x00/rt2x00lib.h
index 86cd26f..49309d4 100644
--- a/drivers/net/wireless/rt2x00/rt2x00lib.h
+++ b/drivers/net/wireless/rt2x00/rt2x00lib.h
@@ -260,8 +260,6 @@ static inline void rt2x00crypto_rx_insert_iv(struct sk_buff *skb,
#ifdef CONFIG_RT2X00_LIB_RFKILL
void rt2x00rfkill_register(struct rt2x00_dev *rt2x00dev);
void rt2x00rfkill_unregister(struct rt2x00_dev *rt2x00dev);
-void rt2x00rfkill_allocate(struct rt2x00_dev *rt2x00dev);
-void rt2x00rfkill_free(struct rt2x00_dev *rt2x00dev);
#else
static inline void rt2x00rfkill_register(struct rt2x00_dev *rt2x00dev)
{
@@ -270,14 +268,6 @@ static inline void rt2x00rfkill_register(struct rt2x00_dev *rt2x00dev)
static inline void rt2x00rfkill_unregister(struct rt2x00_dev *rt2x00dev)
{
}
-
-static inline void rt2x00rfkill_allocate(struct rt2x00_dev *rt2x00dev)
-{
-}
-
-static inline void rt2x00rfkill_free(struct rt2x00_dev *rt2x00dev)
-{
-}
#endif /* CONFIG_RT2X00_LIB_RFKILL */

/*
diff --git a/drivers/net/wireless/rt2x00/rt2x00rfkill.c b/drivers/net/wireless/rt2x00/rt2x00rfkill.c
index 3298cae..08ffc6d 100644
--- a/drivers/net/wireless/rt2x00/rt2x00rfkill.c
+++ b/drivers/net/wireless/rt2x00/rt2x00rfkill.c
@@ -94,14 +94,50 @@ static void rt2x00rfkill_poll(struct work_struct *work)
&rt2x00dev->rfkill_work, RFKILL_POLL_INTERVAL);
}

+static int rt2x00rfkill_allocate(struct rt2x00_dev *rt2x00dev)
+{
+ struct device *dev = wiphy_dev(rt2x00dev->hw->wiphy);
+
+ rt2x00dev->rfkill = rfkill_allocate(dev, RFKILL_TYPE_WLAN);
+ if (!rt2x00dev->rfkill)
+ return -ENOMEM;
+
+ rt2x00dev->rfkill->name = rt2x00dev->ops->name;
+ rt2x00dev->rfkill->data = rt2x00dev;
+ rt2x00dev->rfkill->toggle_radio = rt2x00rfkill_toggle_radio;
+ if (test_bit(CONFIG_SUPPORT_HW_BUTTON, &rt2x00dev->flags)) {
+ rt2x00dev->rfkill->get_state = rt2x00rfkill_get_state;
+ rt2x00dev->rfkill->state =
+ rt2x00dev->ops->lib->rfkill_poll(rt2x00dev) ?
+ RFKILL_STATE_SOFT_BLOCKED : RFKILL_STATE_UNBLOCKED;
+ } else {
+ rt2x00dev->rfkill->state = RFKILL_STATE_UNBLOCKED;
+ }
+
+ INIT_DELAYED_WORK(&rt2x00dev->rfkill_work, rt2x00rfkill_poll);
+
+ return 0;
+}
+
+static void rt2x00rfkill_free(struct rt2x00_dev *rt2x00dev)
+{
+ rfkill_free(rt2x00dev->rfkill);
+ rt2x00dev->rfkill = NULL;
+}
+
void rt2x00rfkill_register(struct rt2x00_dev *rt2x00dev)
{
- if (!test_bit(RFKILL_STATE_ALLOCATED, &rt2x00dev->rfkill_state) ||
- test_bit(RFKILL_STATE_REGISTERED, &rt2x00dev->rfkill_state))
+ if (test_bit(RFKILL_STATE_REGISTERED, &rt2x00dev->rfkill_state))
+ return;
+
+ if (rt2x00rfkill_allocate(rt2x00dev)) {
+ ERROR(rt2x00dev, "Failed to allocate rfkill handler.\n");
return;
+ }

if (rfkill_register(rt2x00dev->rfkill)) {
ERROR(rt2x00dev, "Failed to register rfkill handler.\n");
+ rt2x00rfkill_free(rt2x00dev);
return;
}

@@ -117,8 +153,7 @@ void rt2x00rfkill_register(struct rt2x00_dev *rt2x00dev)

void rt2x00rfkill_unregister(struct rt2x00_dev *rt2x00dev)
{
- if (!test_bit(RFKILL_STATE_ALLOCATED, &rt2x00dev->rfkill_state) ||
- !test_bit(RFKILL_STATE_REGISTERED, &rt2x00dev->rfkill_state))
+ if (!test_bit(RFKILL_STATE_REGISTERED, &rt2x00dev->rfkill_state))
return;

cancel_delayed_work_sync(&rt2x00dev->rfkill_work);
@@ -127,46 +162,3 @@ void rt2x00rfkill_unregister(struct rt2x00_dev *rt2x00dev)

__clear_bit(RFKILL_STATE_REGISTERED, &rt2x00dev->rfkill_state);
}
-
-void rt2x00rfkill_allocate(struct rt2x00_dev *rt2x00dev)
-{
- struct device *dev = wiphy_dev(rt2x00dev->hw->wiphy);
-
- if (test_bit(RFKILL_STATE_ALLOCATED, &rt2x00dev->rfkill_state))
- return;
-
- rt2x00dev->rfkill = rfkill_allocate(dev, RFKILL_TYPE_WLAN);
- if (!rt2x00dev->rfkill) {
- ERROR(rt2x00dev, "Failed to allocate rfkill handler.\n");
- return;
- }
-
- __set_bit(RFKILL_STATE_ALLOCATED, &rt2x00dev->rfkill_state);
-
- rt2x00dev->rfkill->name = rt2x00dev->ops->name;
- rt2x00dev->rfkill->data = rt2x00dev;
- rt2x00dev->rfkill->toggle_radio = rt2x00rfkill_toggle_radio;
- if (test_bit(CONFIG_SUPPORT_HW_BUTTON, &rt2x00dev->flags)) {
- rt2x00dev->rfkill->get_state = rt2x00rfkill_get_state;
- rt2x00dev->rfkill->state =
- rt2x00dev->ops->lib->rfkill_poll(rt2x00dev) ?
- RFKILL_STATE_SOFT_BLOCKED : RFKILL_STATE_UNBLOCKED;
- } else {
- rt2x00dev->rfkill->state = RFKILL_STATE_UNBLOCKED;
- }
-
- INIT_DELAYED_WORK(&rt2x00dev->rfkill_work, rt2x00rfkill_poll);
-
- return;
-}
-
-void rt2x00rfkill_free(struct rt2x00_dev *rt2x00dev)
-{
- if (!test_bit(RFKILL_STATE_ALLOCATED, &rt2x00dev->rfkill_state))
- return;
-
- cancel_delayed_work_sync(&rt2x00dev->rfkill_work);
-
- rfkill_free(rt2x00dev->rfkill);
- rt2x00dev->rfkill = NULL;
-}
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 55ec44a..31cfd86 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -847,6 +847,11 @@ int pci_cfg_space_size(struct pci_dev *dev)
{
int pos;
u32 status;
+ u16 class;
+
+ class = dev->class >> 8;
+ if (class == PCI_CLASS_BRIDGE_HOST)
+ return pci_cfg_space_size_ext(dev);

pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
if (!pos) {
@@ -936,7 +941,6 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
dev->multifunction = !!(hdr_type & 0x80);
dev->vendor = l & 0xffff;
dev->device = (l >> 16) & 0xffff;
- dev->cfg_size = pci_cfg_space_size(dev);
dev->error_state = pci_channel_io_normal;
set_pcie_port_type(dev);

@@ -952,6 +956,9 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
return NULL;
}

+ /* need to have dev->class ready */
+ dev->cfg_size = pci_cfg_space_size(dev);
+
return dev;
}

diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index a6a42e8..60fbef2 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -225,6 +225,25 @@ static struct quirk_entry quirk_fujitsu_amilo_li_1718 = {
.wireless = 2,
};

+/* The Aspire One has a dummy ACPI-WMI interface - disable it */
+static struct dmi_system_id __devinitdata acer_blacklist[] = {
+ {
+ .ident = "Acer Aspire One (SSD)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
+ },
+ },
+ {
+ .ident = "Acer Aspire One (HDD)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"),
+ },
+ },
+ {}
+};
+
static struct dmi_system_id acer_quirks[] = {
{
.callback = dmi_matched,
@@ -1254,6 +1273,12 @@ static int __init acer_wmi_init(void)

printk(ACER_INFO "Acer Laptop ACPI-WMI Extras\n");

+ if (dmi_check_system(acer_blacklist)) {
+ printk(ACER_INFO "Blacklisted hardware detected - "
+ "not loading\n");
+ return -ENODEV;
+ }
+
find_quirks();

/*
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 809d32d..ca4467c 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1944,12 +1944,14 @@ iscsi_pool_init(struct iscsi_pool *q, int max, void ***items, int item_size)
num_arrays++;
q->pool = kzalloc(num_arrays * max * sizeof(void*), GFP_KERNEL);
if (q->pool == NULL)
- goto enomem;
+ return -ENOMEM;

q->queue = kfifo_init((void*)q->pool, max * sizeof(void*),
GFP_KERNEL, NULL);
- if (q->queue == ERR_PTR(-ENOMEM))
+ if (IS_ERR(q->queue)) {
+ q->queue = NULL;
goto enomem;
+ }

for (i = 0; i < max; i++) {
q->pool[i] = kzalloc(item_size, GFP_KERNEL);
@@ -1979,8 +1981,7 @@ void iscsi_pool_free(struct iscsi_pool *q)

for (i = 0; i < q->max; i++)
kfree(q->pool[i]);
- if (q->pool)
- kfree(q->pool);
+ kfree(q->pool);
kfree(q->queue);
}
EXPORT_SYMBOL_GPL(iscsi_pool_free);
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 516925d..5e390d2 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -101,6 +101,7 @@ static int scatter_elem_sz_prev = SG_SCATTER_SZ;
#define SG_SECTOR_MSK (SG_SECTOR_SZ - 1)

static int sg_add(struct device *, struct class_interface *);
+static void sg_device_destroy(struct kref *kref);
static void sg_remove(struct device *, struct class_interface *);

static DEFINE_IDR(sg_index_idr);
@@ -137,6 +138,7 @@ typedef struct sg_request { /* SG_MAX_QUEUE requests outstanding per file */
volatile char done; /* 0->before bh, 1->before read, 2->read */
struct request *rq;
struct bio *bio;
+ struct execute_work ew;
} Sg_request;

typedef struct sg_fd { /* holds the state of a file descriptor */
@@ -158,6 +160,8 @@ typedef struct sg_fd { /* holds the state of a file descriptor */
char next_cmd_len; /* 0 -> automatic (def), >0 -> use on next write() */
char keep_orphan; /* 0 -> drop orphan (def), 1 -> keep for read() */
char mmap_called; /* 0 -> mmap() never called on this fd */
+ struct kref f_ref;
+ struct execute_work ew;
} Sg_fd;

typedef struct sg_device { /* holds the state of each scsi generic device */
@@ -171,6 +175,7 @@ typedef struct sg_device { /* holds the state of each scsi generic device */
char sgdebug; /* 0->off, 1->sense, 9->dump dev, 10-> all devs */
struct gendisk *disk;
struct cdev * cdev; /* char_dev [sysfs: /sys/cdev/major/sg<n>] */
+ struct kref d_ref;
} Sg_device;

static int sg_fasync(int fd, struct file *filp, int mode);
@@ -185,7 +190,7 @@ static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count,
Sg_request * srp);
static ssize_t sg_new_write(Sg_fd *sfp, struct file *file,
const char __user *buf, size_t count, int blocking,
- int read_only, Sg_request **o_srp);
+ int read_only, int sg_io_owned, Sg_request **o_srp);
static int sg_common_write(Sg_fd * sfp, Sg_request * srp,
unsigned char *cmnd, int timeout, int blocking);
static int sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer);
@@ -194,13 +199,14 @@ static void sg_build_reserve(Sg_fd * sfp, int req_size);
static void sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size);
static void sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp);
static Sg_fd *sg_add_sfp(Sg_device * sdp, int dev);
-static int sg_remove_sfp(Sg_device * sdp, Sg_fd * sfp);
-static void __sg_remove_sfp(Sg_device * sdp, Sg_fd * sfp);
+static void sg_remove_sfp(struct kref *);
static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id);
static Sg_request *sg_add_request(Sg_fd * sfp);
static int sg_remove_request(Sg_fd * sfp, Sg_request * srp);
static int sg_res_in_use(Sg_fd * sfp);
+static Sg_device *sg_lookup_dev(int dev);
static Sg_device *sg_get_dev(int dev);
+static void sg_put_dev(Sg_device *sdp);
#ifdef CONFIG_SCSI_PROC_FS
static int sg_last_dev(void);
#endif
@@ -237,22 +243,17 @@ sg_open(struct inode *inode, struct file *filp)
nonseekable_open(inode, filp);
SCSI_LOG_TIMEOUT(3, printk("sg_open: dev=%d, flags=0x%x\n", dev, flags));
sdp = sg_get_dev(dev);
- if ((!sdp) || (!sdp->device)) {
- unlock_kernel();
- return -ENXIO;
- }
- if (sdp->detached) {
- unlock_kernel();
- return -ENODEV;
+ if (IS_ERR(sdp)) {
+ retval = PTR_ERR(sdp);
+ sdp = NULL;
+ goto sg_put;
}

/* This driver's module count bumped by fops_get in <linux/fs.h> */
/* Prevent the device driver from vanishing while we sleep */
retval = scsi_device_get(sdp->device);
- if (retval) {
- unlock_kernel();
- return retval;
- }
+ if (retval)
+ goto sg_put;

if (!((flags & O_NONBLOCK) ||
scsi_block_when_processing_errors(sdp->device))) {
@@ -303,16 +304,20 @@ sg_open(struct inode *inode, struct file *filp)
if ((sfp = sg_add_sfp(sdp, dev)))
filp->private_data = sfp;
else {
- if (flags & O_EXCL)
+ if (flags & O_EXCL) {
sdp->exclude = 0; /* undo if error */
+ wake_up_interruptible(&sdp->o_excl_wait);
+ }
retval = -ENOMEM;
goto error_out;
}
- unlock_kernel();
- return 0;
-
- error_out:
- scsi_device_put(sdp->device);
+ retval = 0;
+error_out:
+ if (retval)
+ scsi_device_put(sdp->device);
+sg_put:
+ if (sdp)
+ sg_put_dev(sdp);
unlock_kernel();
return retval;
}
@@ -327,13 +332,13 @@ sg_release(struct inode *inode, struct file *filp)
if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
return -ENXIO;
SCSI_LOG_TIMEOUT(3, printk("sg_release: %s\n", sdp->disk->disk_name));
- if (0 == sg_remove_sfp(sdp, sfp)) { /* Returns 1 when sdp gone */
- if (!sdp->detached) {
- scsi_device_put(sdp->device);
- }
- sdp->exclude = 0;
- wake_up_interruptible(&sdp->o_excl_wait);
- }
+
+ sfp->closed = 1;
+
+ sdp->exclude = 0;
+ wake_up_interruptible(&sdp->o_excl_wait);
+
+ kref_put(&sfp->f_ref, sg_remove_sfp);
return 0;
}

@@ -557,7 +562,8 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
return -EFAULT;
blocking = !(filp->f_flags & O_NONBLOCK);
if (old_hdr.reply_len < 0)
- return sg_new_write(sfp, filp, buf, count, blocking, 0, NULL);
+ return sg_new_write(sfp, filp, buf, count,
+ blocking, 0, 0, NULL);
if (count < (SZ_SG_HEADER + 6))
return -EIO; /* The minimum scsi command length is 6 bytes. */

@@ -638,7 +644,7 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)

static ssize_t
sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf,
- size_t count, int blocking, int read_only,
+ size_t count, int blocking, int read_only, int sg_io_owned,
Sg_request **o_srp)
{
int k;
@@ -658,6 +664,7 @@ sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf,
SCSI_LOG_TIMEOUT(1, printk("sg_new_write: queue full\n"));
return -EDOM;
}
+ srp->sg_io_owned = sg_io_owned;
hp = &srp->header;
if (__copy_from_user(hp, buf, SZ_SG_IO_HDR)) {
sg_remove_request(sfp, srp);
@@ -755,24 +762,13 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
hp->duration = jiffies_to_msecs(jiffies);

srp->rq->timeout = timeout;
+ kref_get(&sfp->f_ref); /* sg_rq_end_io() does kref_put(). */
blk_execute_rq_nowait(sdp->device->request_queue, sdp->disk,
srp->rq, 1, sg_rq_end_io);
return 0;
}

static int
-sg_srp_done(Sg_request *srp, Sg_fd *sfp)
-{
- unsigned long iflags;
- int done;
-
- read_lock_irqsave(&sfp->rq_list_lock, iflags);
- done = srp->done;
- read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
- return done;
-}
-
-static int
sg_ioctl(struct inode *inode, struct file *filp,
unsigned int cmd_in, unsigned long arg)
{
@@ -804,27 +800,26 @@ sg_ioctl(struct inode *inode, struct file *filp,
return -EFAULT;
result =
sg_new_write(sfp, filp, p, SZ_SG_IO_HDR,
- blocking, read_only, &srp);
+ blocking, read_only, 1, &srp);
if (result < 0)
return result;
- srp->sg_io_owned = 1;
while (1) {
result = 0; /* following macro to beat race condition */
__wait_event_interruptible(sfp->read_wait,
- (sdp->detached || sfp->closed || sg_srp_done(srp, sfp)),
- result);
+ (srp->done || sdp->detached),
+ result);
if (sdp->detached)
return -ENODEV;
- if (sfp->closed)
- return 0; /* request packet dropped already */
- if (0 == result)
+ write_lock_irq(&sfp->rq_list_lock);
+ if (srp->done) {
+ srp->done = 2;
+ write_unlock_irq(&sfp->rq_list_lock);
break;
+ }
srp->orphan = 1;
+ write_unlock_irq(&sfp->rq_list_lock);
return result; /* -ERESTARTSYS because signal hit process */
}
- write_lock_irqsave(&sfp->rq_list_lock, iflags);
- srp->done = 2;
- write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
result = sg_new_read(sfp, p, SZ_SG_IO_HDR, srp);
return (result < 0) ? result : 0;
}
@@ -1240,6 +1235,15 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
return 0;
}

+static void sg_rq_end_io_usercontext(struct work_struct *work)
+{
+ struct sg_request *srp = container_of(work, struct sg_request, ew.work);
+ struct sg_fd *sfp = srp->parentfp;
+
+ sg_finish_rem_req(srp);
+ kref_put(&sfp->f_ref, sg_remove_sfp);
+}
+
/*
* This function is a "bottom half" handler that is called by the mid
* level when a command is completed (or has failed).
@@ -1247,24 +1251,23 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
static void sg_rq_end_io(struct request *rq, int uptodate)
{
struct sg_request *srp = rq->end_io_data;
- Sg_device *sdp = NULL;
+ Sg_device *sdp;
Sg_fd *sfp;
unsigned long iflags;
unsigned int ms;
char *sense;
- int result, resid;
+ int result, resid, done = 1;

- if (NULL == srp) {
- printk(KERN_ERR "sg_cmd_done: NULL request\n");
+ if (WARN_ON(srp->done != 0))
return;
- }
+
sfp = srp->parentfp;
- if (sfp)
- sdp = sfp->parentdp;
- if ((NULL == sdp) || sdp->detached) {
- printk(KERN_INFO "sg_cmd_done: device detached\n");
+ if (WARN_ON(sfp == NULL))
return;
- }
+
+ sdp = sfp->parentdp;
+ if (unlikely(sdp->detached))
+ printk(KERN_INFO "sg_rq_end_io: device detached\n");

sense = rq->sense;
result = rq->errors;
@@ -1303,32 +1306,26 @@ static void sg_rq_end_io(struct request *rq, int uptodate)
}
/* Rely on write phase to clean out srp status values, so no "else" */

- if (sfp->closed) { /* whoops this fd already released, cleanup */
- SCSI_LOG_TIMEOUT(1, printk("sg_cmd_done: already closed, freeing ...\n"));
- sg_finish_rem_req(srp);
- srp = NULL;
- if (NULL == sfp->headrp) {
- SCSI_LOG_TIMEOUT(1, printk("sg_cmd_done: already closed, final cleanup\n"));
- if (0 == sg_remove_sfp(sdp, sfp)) { /* device still present */
- scsi_device_put(sdp->device);
- }
- sfp = NULL;
- }
- } else if (srp && srp->orphan) {
+ write_lock_irqsave(&sfp->rq_list_lock, iflags);
+ if (unlikely(srp->orphan)) {
if (sfp->keep_orphan)
srp->sg_io_owned = 0;
- else {
- sg_finish_rem_req(srp);
- srp = NULL;
- }
+ else
+ done = 0;
}
- if (sfp && srp) {
- /* Now wake up any sg_read() that is waiting for this packet. */
- kill_fasync(&sfp->async_qp, SIGPOLL, POLL_IN);
- write_lock_irqsave(&sfp->rq_list_lock, iflags);
- srp->done = 1;
+ srp->done = done;
+ write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+
+ if (likely(done)) {
+ /* Now wake up any sg_read() that is waiting for this
+ * packet.
+ */
wake_up_interruptible(&sfp->read_wait);
- write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+ kill_fasync(&sfp->async_qp, SIGPOLL, POLL_IN);
+ kref_put(&sfp->f_ref, sg_remove_sfp);
+ } else {
+ INIT_WORK(&srp->ew.work, sg_rq_end_io_usercontext);
+ schedule_work(&srp->ew.work);
}
}

@@ -1364,17 +1361,18 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp)
printk(KERN_WARNING "kmalloc Sg_device failure\n");
return ERR_PTR(-ENOMEM);
}
- error = -ENOMEM;
+
if (!idr_pre_get(&sg_index_idr, GFP_KERNEL)) {
printk(KERN_WARNING "idr expansion Sg_device failure\n");
+ error = -ENOMEM;
goto out;
}

write_lock_irqsave(&sg_index_lock, iflags);
- error = idr_get_new(&sg_index_idr, sdp, &k);
- write_unlock_irqrestore(&sg_index_lock, iflags);

+ error = idr_get_new(&sg_index_idr, sdp, &k);
if (error) {
+ write_unlock_irqrestore(&sg_index_lock, iflags);
printk(KERN_WARNING "idr allocation Sg_device failure: %d\n",
error);
goto out;
@@ -1391,6 +1389,9 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp)
init_waitqueue_head(&sdp->o_excl_wait);
sdp->sg_tablesize = min(q->max_hw_segments, q->max_phys_segments);
sdp->index = k;
+ kref_init(&sdp->d_ref);
+
+ write_unlock_irqrestore(&sg_index_lock, iflags);

error = 0;
out:
@@ -1401,6 +1402,8 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp)
return sdp;

overflow:
+ idr_remove(&sg_index_idr, k);
+ write_unlock_irqrestore(&sg_index_lock, iflags);
sdev_printk(KERN_WARNING, scsidp,
"Unable to attach sg device type=%d, minor "
"number exceeds %d\n", scsidp->type, SG_MAX_DEVS - 1);
@@ -1488,49 +1491,46 @@ out:
return error;
}

-static void
-sg_remove(struct device *cl_dev, struct class_interface *cl_intf)
+static void sg_device_destroy(struct kref *kref)
+{
+ struct sg_device *sdp = container_of(kref, struct sg_device, d_ref);
+ unsigned long flags;
+
+ /* CAUTION! Note that the device can still be found via idr_find()
+ * even though the refcount is 0. Therefore, do idr_remove() BEFORE
+ * any other cleanup.
+ */
+
+ write_lock_irqsave(&sg_index_lock, flags);
+ idr_remove(&sg_index_idr, sdp->index);
+ write_unlock_irqrestore(&sg_index_lock, flags);
+
+ SCSI_LOG_TIMEOUT(3,
+ printk("sg_device_destroy: %s\n",
+ sdp->disk->disk_name));
+
+ put_disk(sdp->disk);
+ kfree(sdp);
+}
+
+static void sg_remove(struct device *cl_dev, struct class_interface *cl_intf)
{
struct scsi_device *scsidp = to_scsi_device(cl_dev->parent);
Sg_device *sdp = dev_get_drvdata(cl_dev);
unsigned long iflags;
Sg_fd *sfp;
- Sg_fd *tsfp;
- Sg_request *srp;
- Sg_request *tsrp;
- int delay;

- if (!sdp)
+ if (!sdp || sdp->detached)
return;

- delay = 0;
+ SCSI_LOG_TIMEOUT(3, printk("sg_remove: %s\n", sdp->disk->disk_name));
+
+ /* Need a write lock to set sdp->detached. */
write_lock_irqsave(&sg_index_lock, iflags);
- if (sdp->headfp) {
- sdp->detached = 1;
- for (sfp = sdp->headfp; sfp; sfp = tsfp) {
- tsfp = sfp->nextfp;
- for (srp = sfp->headrp; srp; srp = tsrp) {
- tsrp = srp->nextrp;
- if (sfp->closed || (0 == sg_srp_done(srp, sfp)))
- sg_finish_rem_req(srp);
- }
- if (sfp->closed) {
- scsi_device_put(sdp->device);
- __sg_remove_sfp(sdp, sfp);
- } else {
- delay = 1;
- wake_up_interruptible(&sfp->read_wait);
- kill_fasync(&sfp->async_qp, SIGPOLL,
- POLL_HUP);
- }
- }
- SCSI_LOG_TIMEOUT(3, printk("sg_remove: dev=%d, dirty\n", sdp->index));
- if (NULL == sdp->headfp) {
- idr_remove(&sg_index_idr, sdp->index);
- }
- } else { /* nothing active, simple case */
- SCSI_LOG_TIMEOUT(3, printk("sg_remove: dev=%d\n", sdp->index));
- idr_remove(&sg_index_idr, sdp->index);
+ sdp->detached = 1;
+ for (sfp = sdp->headfp; sfp; sfp = sfp->nextfp) {
+ wake_up_interruptible(&sfp->read_wait);
+ kill_fasync(&sfp->async_qp, SIGPOLL, POLL_HUP);
}
write_unlock_irqrestore(&sg_index_lock, iflags);

@@ -1538,13 +1538,8 @@ sg_remove(struct device *cl_dev, struct class_interface *cl_intf)
device_destroy(sg_sysfs_class, MKDEV(SCSI_GENERIC_MAJOR, sdp->index));
cdev_del(sdp->cdev);
sdp->cdev = NULL;
- put_disk(sdp->disk);
- sdp->disk = NULL;
- if (NULL == sdp->headfp)
- kfree(sdp);

- if (delay)
- msleep(10); /* dirty detach so delay device destruction */
+ sg_put_dev(sdp);
}

module_param_named(scatter_elem_sz, scatter_elem_sz, int, S_IRUGO | S_IWUSR);
@@ -1673,10 +1668,30 @@ static int sg_start_req(Sg_request *srp, unsigned char *cmd)
md->null_mapped = hp->dxferp ? 0 : 1;
}

- if (iov_count)
- res = blk_rq_map_user_iov(q, rq, md, hp->dxferp, iov_count,
- hp->dxfer_len, GFP_ATOMIC);
- else
+ if (iov_count) {
+ int len, size = sizeof(struct sg_iovec) * iov_count;
+ struct iovec *iov;
+
+ iov = kmalloc(size, GFP_ATOMIC);
+ if (!iov)
+ return -ENOMEM;
+
+ if (copy_from_user(iov, hp->dxferp, size)) {
+ kfree(iov);
+ return -EFAULT;
+ }
+
+ len = iov_length(iov, iov_count);
+ if (hp->dxfer_len < len) {
+ iov_count = iov_shorten(iov, iov_count, hp->dxfer_len);
+ len = hp->dxfer_len;
+ }
+
+ res = blk_rq_map_user_iov(q, rq, md, (struct sg_iovec *)iov,
+ iov_count,
+ len, GFP_ATOMIC);
+ kfree(iov);
+ } else
res = blk_rq_map_user(q, rq, md, hp->dxferp,
hp->dxfer_len, GFP_ATOMIC);

@@ -1941,22 +1956,6 @@ sg_get_rq_mark(Sg_fd * sfp, int pack_id)
return resp;
}

-#ifdef CONFIG_SCSI_PROC_FS
-static Sg_request *
-sg_get_nth_request(Sg_fd * sfp, int nth)
-{
- Sg_request *resp;
- unsigned long iflags;
- int k;
-
- read_lock_irqsave(&sfp->rq_list_lock, iflags);
- for (k = 0, resp = sfp->headrp; resp && (k < nth);
- ++k, resp = resp->nextrp) ;
- read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
- return resp;
-}
-#endif
-
/* always adds to end of list */
static Sg_request *
sg_add_request(Sg_fd * sfp)
@@ -2032,22 +2031,6 @@ sg_remove_request(Sg_fd * sfp, Sg_request * srp)
return res;
}

-#ifdef CONFIG_SCSI_PROC_FS
-static Sg_fd *
-sg_get_nth_sfp(Sg_device * sdp, int nth)
-{
- Sg_fd *resp;
- unsigned long iflags;
- int k;
-
- read_lock_irqsave(&sg_index_lock, iflags);
- for (k = 0, resp = sdp->headfp; resp && (k < nth);
- ++k, resp = resp->nextfp) ;
- read_unlock_irqrestore(&sg_index_lock, iflags);
- return resp;
-}
-#endif
-
static Sg_fd *
sg_add_sfp(Sg_device * sdp, int dev)
{
@@ -2062,6 +2045,7 @@ sg_add_sfp(Sg_device * sdp, int dev)
init_waitqueue_head(&sfp->read_wait);
rwlock_init(&sfp->rq_list_lock);

+ kref_init(&sfp->f_ref);
sfp->timeout = SG_DEFAULT_TIMEOUT;
sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER;
sfp->force_packid = SG_DEF_FORCE_PACK_ID;
@@ -2089,15 +2073,54 @@ sg_add_sfp(Sg_device * sdp, int dev)
sg_build_reserve(sfp, bufflen);
SCSI_LOG_TIMEOUT(3, printk("sg_add_sfp: bufflen=%d, k_use_sg=%d\n",
sfp->reserve.bufflen, sfp->reserve.k_use_sg));
+
+ kref_get(&sdp->d_ref);
+ __module_get(THIS_MODULE);
return sfp;
}

-static void
-__sg_remove_sfp(Sg_device * sdp, Sg_fd * sfp)
+static void sg_remove_sfp_usercontext(struct work_struct *work)
+{
+ struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work);
+ struct sg_device *sdp = sfp->parentdp;
+
+ /* Cleanup any responses which were never read(). */
+ while (sfp->headrp)
+ sg_finish_rem_req(sfp->headrp);
+
+ if (sfp->reserve.bufflen > 0) {
+ SCSI_LOG_TIMEOUT(6,
+ printk("sg_remove_sfp: bufflen=%d, k_use_sg=%d\n",
+ (int) sfp->reserve.bufflen,
+ (int) sfp->reserve.k_use_sg));
+ sg_remove_scat(&sfp->reserve);
+ }
+
+ SCSI_LOG_TIMEOUT(6,
+ printk("sg_remove_sfp: %s, sfp=0x%p\n",
+ sdp->disk->disk_name,
+ sfp));
+ kfree(sfp);
+
+ scsi_device_put(sdp->device);
+ sg_put_dev(sdp);
+ module_put(THIS_MODULE);
+}
+
+static void sg_remove_sfp(struct kref *kref)
{
+ struct sg_fd *sfp = container_of(kref, struct sg_fd, f_ref);
+ struct sg_device *sdp = sfp->parentdp;
Sg_fd *fp;
Sg_fd *prev_fp;
+ unsigned long iflags;

+ /* CAUTION! Note that sfp can still be found by walking sdp->headfp
+ * even though the refcount is now 0. Therefore, unlink sfp from
+ * sdp->headfp BEFORE doing any other cleanup.
+ */
+
+ write_lock_irqsave(&sg_index_lock, iflags);
prev_fp = sdp->headfp;
if (sfp == prev_fp)
sdp->headfp = prev_fp->nextfp;
@@ -2110,54 +2133,11 @@ __sg_remove_sfp(Sg_device * sdp, Sg_fd * sfp)
prev_fp = fp;
}
}
- if (sfp->reserve.bufflen > 0) {
- SCSI_LOG_TIMEOUT(6,
- printk("__sg_remove_sfp: bufflen=%d, k_use_sg=%d\n",
- (int) sfp->reserve.bufflen, (int) sfp->reserve.k_use_sg));
- sg_remove_scat(&sfp->reserve);
- }
- sfp->parentdp = NULL;
- SCSI_LOG_TIMEOUT(6, printk("__sg_remove_sfp: sfp=0x%p\n", sfp));
- kfree(sfp);
-}
-
-/* Returns 0 in normal case, 1 when detached and sdp object removed */
-static int
-sg_remove_sfp(Sg_device * sdp, Sg_fd * sfp)
-{
- Sg_request *srp;
- Sg_request *tsrp;
- int dirty = 0;
- int res = 0;
-
- for (srp = sfp->headrp; srp; srp = tsrp) {
- tsrp = srp->nextrp;
- if (sg_srp_done(srp, sfp))
- sg_finish_rem_req(srp);
- else
- ++dirty;
- }
- if (0 == dirty) {
- unsigned long iflags;
+ write_unlock_irqrestore(&sg_index_lock, iflags);
+ wake_up_interruptible(&sdp->o_excl_wait);

- write_lock_irqsave(&sg_index_lock, iflags);
- __sg_remove_sfp(sdp, sfp);
- if (sdp->detached && (NULL == sdp->headfp)) {
- idr_remove(&sg_index_idr, sdp->index);
- kfree(sdp);
- res = 1;
- }
- write_unlock_irqrestore(&sg_index_lock, iflags);
- } else {
- /* MOD_INC's to inhibit unloading sg and associated adapter driver */
- /* only bump the access_count if we actually succeeded in
- * throwing another counter on the host module */
- scsi_device_get(sdp->device); /* XXX: retval ignored? */
- sfp->closed = 1; /* flag dirty state on this fd */
- SCSI_LOG_TIMEOUT(1, printk("sg_remove_sfp: worrisome, %d writes pending\n",
- dirty));
- }
- return res;
+ INIT_WORK(&sfp->ew.work, sg_remove_sfp_usercontext);
+ schedule_work(&sfp->ew.work);
}

static int
@@ -2199,19 +2179,38 @@ sg_last_dev(void)
}
#endif

-static Sg_device *
-sg_get_dev(int dev)
+/* must be called with sg_index_lock held */
+static Sg_device *sg_lookup_dev(int dev)
{
- Sg_device *sdp;
- unsigned long iflags;
+ return idr_find(&sg_index_idr, dev);
+}

- read_lock_irqsave(&sg_index_lock, iflags);
- sdp = idr_find(&sg_index_idr, dev);
- read_unlock_irqrestore(&sg_index_lock, iflags);
+static Sg_device *sg_get_dev(int dev)
+{
+ struct sg_device *sdp;
+ unsigned long flags;
+
+ read_lock_irqsave(&sg_index_lock, flags);
+ sdp = sg_lookup_dev(dev);
+ if (!sdp)
+ sdp = ERR_PTR(-ENXIO);
+ else if (sdp->detached) {
+ /* If sdp->detached, then the refcount may already be 0, in
+ * which case it would be a bug to do kref_get().
+ */
+ sdp = ERR_PTR(-ENODEV);
+ } else
+ kref_get(&sdp->d_ref);
+ read_unlock_irqrestore(&sg_index_lock, flags);

return sdp;
}

+static void sg_put_dev(struct sg_device *sdp)
+{
+ kref_put(&sdp->d_ref, sg_device_destroy);
+}
+
#ifdef CONFIG_SCSI_PROC_FS

static struct proc_dir_entry *sg_proc_sgp = NULL;
@@ -2468,8 +2467,10 @@ static int sg_proc_seq_show_dev(struct seq_file *s, void *v)
struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
Sg_device *sdp;
struct scsi_device *scsidp;
+ unsigned long iflags;

- sdp = it ? sg_get_dev(it->index) : NULL;
+ read_lock_irqsave(&sg_index_lock, iflags);
+ sdp = it ? sg_lookup_dev(it->index) : NULL;
if (sdp && (scsidp = sdp->device) && (!sdp->detached))
seq_printf(s, "%d\t%d\t%d\t%d\t%d\t%d\t%d\t%d\t%d\n",
scsidp->host->host_no, scsidp->channel,
@@ -2480,6 +2481,7 @@ static int sg_proc_seq_show_dev(struct seq_file *s, void *v)
(int) scsi_device_online(scsidp));
else
seq_printf(s, "-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n");
+ read_unlock_irqrestore(&sg_index_lock, iflags);
return 0;
}

@@ -2493,16 +2495,20 @@ static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v)
struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
Sg_device *sdp;
struct scsi_device *scsidp;
+ unsigned long iflags;

- sdp = it ? sg_get_dev(it->index) : NULL;
+ read_lock_irqsave(&sg_index_lock, iflags);
+ sdp = it ? sg_lookup_dev(it->index) : NULL;
if (sdp && (scsidp = sdp->device) && (!sdp->detached))
seq_printf(s, "%8.8s\t%16.16s\t%4.4s\n",
scsidp->vendor, scsidp->model, scsidp->rev);
else
seq_printf(s, "<no active device>\n");
+ read_unlock_irqrestore(&sg_index_lock, iflags);
return 0;
}

+/* must be called while holding sg_index_lock */
static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
{
int k, m, new_interface, blen, usg;
@@ -2512,7 +2518,8 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
const char * cp;
unsigned int ms;

- for (k = 0; (fp = sg_get_nth_sfp(sdp, k)); ++k) {
+ for (k = 0, fp = sdp->headfp; fp != NULL; ++k, fp = fp->nextfp) {
+ read_lock(&fp->rq_list_lock); /* irqs already disabled */
seq_printf(s, " FD(%d): timeout=%dms bufflen=%d "
"(res)sgat=%d low_dma=%d\n", k + 1,
jiffies_to_msecs(fp->timeout),
@@ -2522,7 +2529,9 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
seq_printf(s, " cmd_q=%d f_packid=%d k_orphan=%d closed=%d\n",
(int) fp->cmd_q, (int) fp->force_packid,
(int) fp->keep_orphan, (int) fp->closed);
- for (m = 0; (srp = sg_get_nth_request(fp, m)); ++m) {
+ for (m = 0, srp = fp->headrp;
+ srp != NULL;
+ ++m, srp = srp->nextrp) {
hp = &srp->header;
new_interface = (hp->interface_id == '\0') ? 0 : 1;
if (srp->res_used) {
@@ -2559,6 +2568,7 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
}
if (0 == m)
seq_printf(s, " No requests active\n");
+ read_unlock(&fp->rq_list_lock);
}
}

@@ -2571,39 +2581,34 @@ static int sg_proc_seq_show_debug(struct seq_file *s, void *v)
{
struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
Sg_device *sdp;
+ unsigned long iflags;

if (it && (0 == it->index)) {
seq_printf(s, "max_active_device=%d(origin 1)\n",
(int)it->max);
seq_printf(s, " def_reserved_size=%d\n", sg_big_buff);
}
- sdp = it ? sg_get_dev(it->index) : NULL;
- if (sdp) {
- struct scsi_device *scsidp = sdp->device;

- if (NULL == scsidp) {
- seq_printf(s, "device %d detached ??\n",
- (int)it->index);
- return 0;
- }
+ read_lock_irqsave(&sg_index_lock, iflags);
+ sdp = it ? sg_lookup_dev(it->index) : NULL;
+ if (sdp && sdp->headfp) {
+ struct scsi_device *scsidp = sdp->device;

- if (sg_get_nth_sfp(sdp, 0)) {
- seq_printf(s, " >>> device=%s ",
- sdp->disk->disk_name);
- if (sdp->detached)
- seq_printf(s, "detached pending close ");
- else
- seq_printf
- (s, "scsi%d chan=%d id=%d lun=%d em=%d",
- scsidp->host->host_no,
- scsidp->channel, scsidp->id,
- scsidp->lun,
- scsidp->host->hostt->emulated);
- seq_printf(s, " sg_tablesize=%d excl=%d\n",
- sdp->sg_tablesize, sdp->exclude);
- }
+ seq_printf(s, " >>> device=%s ", sdp->disk->disk_name);
+ if (sdp->detached)
+ seq_printf(s, "detached pending close ");
+ else
+ seq_printf
+ (s, "scsi%d chan=%d id=%d lun=%d em=%d",
+ scsidp->host->host_no,
+ scsidp->channel, scsidp->id,
+ scsidp->lun,
+ scsidp->host->hostt->emulated);
+ seq_printf(s, " sg_tablesize=%d excl=%d\n",
+ sdp->sg_tablesize, sdp->exclude);
sg_proc_debug_helper(s, sdp);
}
+ read_unlock_irqrestore(&sg_index_lock, iflags);
return 0;
}

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 643908b..8eba98c 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -658,7 +658,7 @@ int spi_write_then_read(struct spi_device *spi,

int status;
struct spi_message message;
- struct spi_transfer x;
+ struct spi_transfer x[2];
u8 *local_buf;

/* Use preallocated DMA-safe buffer. We can't avoid copying here,
@@ -669,9 +669,15 @@ int spi_write_then_read(struct spi_device *spi,
return -EINVAL;

spi_message_init(&message);
- memset(&x, 0, sizeof x);
- x.len = n_tx + n_rx;
- spi_message_add_tail(&x, &message);
+ memset(x, 0, sizeof x);
+ if (n_tx) {
+ x[0].len = n_tx;
+ spi_message_add_tail(&x[0], &message);
+ }
+ if (n_rx) {
+ x[1].len = n_rx;
+ spi_message_add_tail(&x[1], &message);
+ }

/* ... unless someone else is using the pre-allocated buffer */
if (!mutex_trylock(&lock)) {
@@ -682,15 +688,15 @@ int spi_write_then_read(struct spi_device *spi,
local_buf = buf;

memcpy(local_buf, txbuf, n_tx);
- x.tx_buf = local_buf;
- x.rx_buf = local_buf;
+ x[0].tx_buf = local_buf;
+ x[1].rx_buf = local_buf + n_tx;

/* do the i/o */
status = spi_sync(spi, &message);
if (status == 0)
- memcpy(rxbuf, x.rx_buf + n_tx, n_rx);
+ memcpy(rxbuf, x[1].rx_buf, n_rx);

- if (x.tx_buf == buf)
+ if (x[0].tx_buf == buf)
mutex_unlock(&lock);
else
kfree(local_buf);
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 3771d6e..34e6108 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -652,7 +652,7 @@ next_desc:

iface = &intf->altsetting[0];
ep = &iface->endpoint[0].desc;
- if (!usb_endpoint_is_int_in(ep)) {
+ if (!ep || !usb_endpoint_is_int_in(ep)) {
rv = -EINVAL;
goto err;
}
diff --git a/drivers/usb/gadget/u_ether.c b/drivers/usb/gadget/u_ether.c
index 96d65ca..4007770 100644
--- a/drivers/usb/gadget/u_ether.c
+++ b/drivers/usb/gadget/u_ether.c
@@ -175,12 +175,6 @@ static void eth_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *p)
strlcpy(p->bus_info, dev_name(&dev->gadget->dev), sizeof p->bus_info);
}

-static u32 eth_get_link(struct net_device *net)
-{
- struct eth_dev *dev = netdev_priv(net);
- return dev->gadget->speed != USB_SPEED_UNKNOWN;
-}
-
/* REVISIT can also support:
* - WOL (by tracking suspends and issuing remote wakeup)
* - msglevel (implies updated messaging)
@@ -189,7 +183,7 @@ static u32 eth_get_link(struct net_device *net)

static struct ethtool_ops ops = {
.get_drvinfo = eth_get_drvinfo,
- .get_link = eth_get_link
+ .get_link = ethtool_op_get_link,
};

static void defer_kevent(struct eth_dev *dev, int flag)
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index ae84c32..bb3143e 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -668,6 +668,7 @@ static struct usb_device_id id_table_combined [] = {
{ USB_DEVICE(DE_VID, WHT_PID) },
{ USB_DEVICE(ADI_VID, ADI_GNICE_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE(JETI_VID, JETI_SPC1201_PID) },
{ }, /* Optional parameter entry */
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/ftdi_sio.h b/drivers/usb/serial/ftdi_sio.h
index daaf63d..c09f658 100644
--- a/drivers/usb/serial/ftdi_sio.h
+++ b/drivers/usb/serial/ftdi_sio.h
@@ -913,6 +913,13 @@
#define ADI_GNICE_PID 0xF000

/*
+ * JETI SPECTROMETER SPECBOS 1201
+ * http://www.jeti.com/products/sys/scb/scb1201.php
+ */
+#define JETI_VID 0x0c6c
+#define JETI_SPC1201_PID 0x04b2
+
+/*
* BmRequestType: 1100 0000b
* bRequest: FTDI_E2_READ
* wValue: 0
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index 2620bf6..9c4c700 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -1215,20 +1215,22 @@ static void ti_bulk_in_callback(struct urb *urb)
}

tty = tty_port_tty_get(&port->port);
- if (tty && urb->actual_length) {
- usb_serial_debug_data(debug, dev, __func__,
- urb->actual_length, urb->transfer_buffer);
-
- if (!tport->tp_is_open)
- dbg("%s - port closed, dropping data", __func__);
- else
- ti_recv(&urb->dev->dev, tty,
+ if (tty) {
+ if (urb->actual_length) {
+ usb_serial_debug_data(debug, dev, __func__,
+ urb->actual_length, urb->transfer_buffer);
+
+ if (!tport->tp_is_open)
+ dbg("%s - port closed, dropping data",
+ __func__);
+ else
+ ti_recv(&urb->dev->dev, tty,
urb->transfer_buffer,
urb->actual_length);
-
- spin_lock(&tport->tp_lock);
- tport->tp_icount.rx += urb->actual_length;
- spin_unlock(&tport->tp_lock);
+ spin_lock(&tport->tp_lock);
+ tport->tp_icount.rx += urb->actual_length;
+ spin_unlock(&tport->tp_lock);
+ }
tty_kref_put(tty);
}

diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index cfde74a..0f54399 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1218,12 +1218,14 @@ UNUSUAL_DEV( 0x07c4, 0xa400, 0x0000, 0xffff,
US_SC_DEVICE, US_PR_DEVICE, NULL,
US_FL_FIX_INQUIRY | US_FL_FIX_CAPACITY ),

-/* Reported by Rauch Wolke <rauchwolke@xxxxxxx> */
+/* Reported by Rauch Wolke <rauchwolke@xxxxxxx>
+ * and augmented by binbin <binbinsh@xxxxxxxxx> (Bugzilla #12882)
+ */
UNUSUAL_DEV( 0x07c4, 0xa4a5, 0x0000, 0xffff,
"Simple Tech/Datafab",
"CF+SM Reader",
US_SC_DEVICE, US_PR_DEVICE, NULL,
- US_FL_IGNORE_RESIDUE ),
+ US_FL_IGNORE_RESIDUE | US_FL_MAX_SECTORS_64 ),

/* Casio QV 2x00/3x00/4000/8000 digital still cameras are not conformant
* to the USB storage specification in two ways:
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index 1657b96..471a9a6 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -2263,9 +2263,12 @@ static void fbcon_generic_blank(struct vc_data *vc, struct fb_info *info,
}


+ if (!lock_fb_info(info))
+ return;
event.info = info;
event.data = &blank;
fb_notifier_call_chain(FB_EVENT_CONBLANK, &event);
+ unlock_fb_info(info);
}

static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch)
@@ -2954,8 +2957,9 @@ static int fbcon_fb_unbind(int idx)

static int fbcon_fb_unregistered(struct fb_info *info)
{
- int i, idx = info->node;
+ int i, idx;

+ idx = info->node;
for (i = first_fb_vc; i <= last_fb_vc; i++) {
if (con2fb_map[i] == idx)
con2fb_map[i] = -1;
@@ -2979,13 +2983,12 @@ static int fbcon_fb_unregistered(struct fb_info *info)
}
}

- if (!num_registered_fb)
- unregister_con_driver(&fb_con);
-
-
if (primary_device == idx)
primary_device = -1;

+ if (!num_registered_fb)
+ unregister_con_driver(&fb_con);
+
return 0;
}

@@ -3021,8 +3024,9 @@ static inline void fbcon_select_primary(struct fb_info *info)

static int fbcon_fb_registered(struct fb_info *info)
{
- int ret = 0, i, idx = info->node;
+ int ret = 0, i, idx;

+ idx = info->node;
fbcon_select_primary(info);

if (info_idx == -1) {
@@ -3124,7 +3128,7 @@ static void fbcon_get_requirement(struct fb_info *info,
}
}

-static int fbcon_event_notify(struct notifier_block *self,
+static int fbcon_event_notify(struct notifier_block *self,
unsigned long action, void *data)
{
struct fb_event *event = data;
@@ -3132,7 +3136,7 @@ static int fbcon_event_notify(struct notifier_block *self,
struct fb_videomode *mode;
struct fb_con2fbmap *con2fb;
struct fb_blit_caps *caps;
- int ret = 0;
+ int idx, ret = 0;

/*
* ignore all events except driver registration and deregistration
@@ -3160,7 +3164,8 @@ static int fbcon_event_notify(struct notifier_block *self,
ret = fbcon_mode_deleted(info, mode);
break;
case FB_EVENT_FB_UNBIND:
- ret = fbcon_fb_unbind(info->node);
+ idx = info->node;
+ ret = fbcon_fb_unbind(idx);
break;
case FB_EVENT_FB_REGISTERED:
ret = fbcon_fb_registered(info);
@@ -3188,7 +3193,6 @@ static int fbcon_event_notify(struct notifier_block *self,
fbcon_get_requirement(info, caps);
break;
}
-
done:
return ret;
}
diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
index cfd9dce..1d6fb41 100644
--- a/drivers/video/fbmem.c
+++ b/drivers/video/fbmem.c
@@ -1086,13 +1086,11 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd,
return -EINVAL;
con2fb.framebuffer = -1;
event.data = &con2fb;
-
if (!lock_fb_info(info))
return -ENODEV;
event.info = info;
fb_notifier_call_chain(FB_EVENT_GET_CONSOLE_MAP, &event);
unlock_fb_info(info);
-
ret = copy_to_user(argp, &con2fb, sizeof(con2fb)) ? -EFAULT : 0;
break;
case FBIOPUT_CON2FBMAP:
@@ -1112,8 +1110,7 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd,
if (!lock_fb_info(info))
return -ENODEV;
event.info = info;
- ret = fb_notifier_call_chain(FB_EVENT_SET_CONSOLE_MAP,
- &event);
+ ret = fb_notifier_call_chain(FB_EVENT_SET_CONSOLE_MAP, &event);
unlock_fb_info(info);
break;
case FBIOBLANK:
@@ -1519,7 +1516,10 @@ register_framebuffer(struct fb_info *fb_info)
registered_fb[i] = fb_info;

event.info = fb_info;
+ if (!lock_fb_info(fb_info))
+ return -ENODEV;
fb_notifier_call_chain(FB_EVENT_FB_REGISTERED, &event);
+ unlock_fb_info(fb_info);
return 0;
}

@@ -1553,8 +1553,12 @@ unregister_framebuffer(struct fb_info *fb_info)
goto done;
}

+
+ if (!lock_fb_info(fb_info))
+ return -ENODEV;
event.info = fb_info;
ret = fb_notifier_call_chain(FB_EVENT_FB_UNBIND, &event);
+ unlock_fb_info(fb_info);

if (ret) {
ret = -EINVAL;
@@ -1588,6 +1592,8 @@ void fb_set_suspend(struct fb_info *info, int state)
{
struct fb_event event;

+ if (!lock_fb_info(info))
+ return;
event.info = info;
if (state) {
fb_notifier_call_chain(FB_EVENT_SUSPEND, &event);
@@ -1596,6 +1602,7 @@ void fb_set_suspend(struct fb_info *info, int state)
info->state = FBINFO_STATE_RUNNING;
fb_notifier_call_chain(FB_EVENT_RESUME, &event);
}
+ unlock_fb_info(info);
}

/**
@@ -1665,8 +1672,11 @@ int fb_new_modelist(struct fb_info *info)
err = 1;

if (!list_empty(&info->modelist)) {
+ if (!lock_fb_info(info))
+ return -ENODEV;
event.info = info;
err = fb_notifier_call_chain(FB_EVENT_NEW_MODELIST, &event);
+ unlock_fb_info(info);
}

return err;
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 5926826..9c76a06 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -190,7 +190,8 @@ static int balloon(void *_vballoon)
try_to_freeze();
wait_event_interruptible(vb->config_change,
(diff = towards_target(vb)) != 0
- || kthread_should_stop());
+ || kthread_should_stop()
+ || freezing(current));
if (diff > 0)
fill_balloon(vb, diff);
else if (diff < 0)
diff --git a/fs/dquot.c b/fs/dquot.c
index bca3cac..5a0059d 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -793,7 +793,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
continue;
if (!dqinit_needed(inode, type))
continue;
- if (inode->i_state & (I_FREEING|I_WILL_FREE))
+ if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
continue;

__iget(inode);
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 3e5637f..f7e66c0 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct super_block *sb)

spin_lock(&inode_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
- if (inode->i_state & (I_FREEING|I_WILL_FREE))
+ if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
continue;
if (inode->i_mapping->nrpages == 0)
continue;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 9f61e62..27b3741 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2693,7 +2693,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
i = (sb->s_blocksize_bits + 2) * sizeof(unsigned int);
sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
if (sbi->s_mb_maxs == NULL) {
- kfree(sbi->s_mb_maxs);
+ kfree(sbi->s_mb_offsets);
return -ENOMEM;
}

@@ -4439,7 +4439,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
pa_inode_list) {
spin_lock(&tmp_pa->pa_lock);
if (tmp_pa->pa_deleted) {
- spin_unlock(&pa->pa_lock);
+ spin_unlock(&tmp_pa->pa_lock);
continue;
}
if (!added && pa->pa_free < tmp_pa->pa_free) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e3fe991..f81f9e7 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -538,7 +538,8 @@ void generic_sync_sb_inodes(struct super_block *sb,
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
struct address_space *mapping;

- if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
+ if (inode->i_state &
+ (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue;
mapping = inode->i_mapping;
if (mapping->nrpages == 0)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 9b800d9..c91a818 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -26,7 +26,6 @@
#include <linux/pagevec.h>
#include <linux/parser.h>
#include <linux/mman.h>
-#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
#include <linux/statfs.h>
@@ -842,7 +841,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
bad_val:
printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n",
args[0].from, p);
- return 1;
+ return -EINVAL;
}

static int
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 6cdeacf..4bd49c1 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -716,7 +716,8 @@ nfs3_xdr_setaclargs(struct rpc_rqst *req, __be32 *p,
if (args->npages != 0)
xdr_encode_pages(buf, args->pages, 0, args->len);
else
- req->rq_slen += args->len;
+ req->rq_slen = xdr_adjust_iovec(req->rq_svec,
+ p + XDR_QUADLEN(args->len));

err = nfsacl_encode(buf, base, args->inode,
(args->mask & NFS_ACL) ?
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index a5887df..8672b95 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1926,7 +1926,7 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
out->f_path.dentry->d_name.len,
out->f_path.dentry->d_name.name);

- inode_double_lock(inode, pipe->inode);
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);

ret = ocfs2_rw_lock(inode, 1);
if (ret < 0) {
@@ -1941,12 +1941,16 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
goto out_unlock;
}

+ if (pipe->inode)
+ mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_CHILD);
ret = generic_file_splice_write_nolock(pipe, out, ppos, len, flags);
+ if (pipe->inode)
+ mutex_unlock(&pipe->inode->i_mutex);

out_unlock:
ocfs2_rw_unlock(inode, 1);
out:
- inode_double_unlock(inode, pipe->inode);
+ mutex_unlock(&inode->i_mutex);

mlog_exit(ret);
return ret;
diff --git a/fs/splice.c b/fs/splice.c
index 4ed0ba4..4c1029a 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -736,10 +736,19 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
* ->write_end. Most of the time, these expect i_mutex to
* be held. Since this may result in an ABBA deadlock with
* pipe->inode, we have to order lock acquiry here.
+ *
+ * Outer lock must be inode->i_mutex, as pipe_wait() will
+ * release and reacquire pipe->inode->i_mutex, AND inode must
+ * never be a pipe.
*/
- inode_double_lock(inode, pipe->inode);
+ WARN_ON(S_ISFIFO(inode->i_mode));
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
+ if (pipe->inode)
+ mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_CHILD);
ret = __splice_from_pipe(pipe, &sd, actor);
- inode_double_unlock(inode, pipe->inode);
+ if (pipe->inode)
+ mutex_unlock(&pipe->inode->i_mutex);
+ mutex_unlock(&inode->i_mutex);

return ret;
}
@@ -830,11 +839,17 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
};
ssize_t ret;

- inode_double_lock(inode, pipe->inode);
+ WARN_ON(S_ISFIFO(inode->i_mode));
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
ret = file_remove_suid(out);
- if (likely(!ret))
+ if (likely(!ret)) {
+ if (pipe->inode)
+ mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_CHILD);
ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
- inode_double_unlock(inode, pipe->inode);
+ if (pipe->inode)
+ mutex_unlock(&pipe->inode->i_mutex);
+ }
+ mutex_unlock(&inode->i_mutex);
if (ret > 0) {
unsigned long nr_pages;

diff --git a/include/linux/capability.h b/include/linux/capability.h
index 4864a43..c302110 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -377,7 +377,21 @@ struct cpu_vfs_cap_data {
#define CAP_FOR_EACH_U32(__capi) \
for (__capi = 0; __capi < _KERNEL_CAPABILITY_U32S; ++__capi)

+/*
+ * CAP_FS_MASK and CAP_NFSD_MASKS:
+ *
+ * The fs mask is all the privileges that fsuid==0 historically meant.
+ * At one time in the past, that included CAP_MKNOD and CAP_LINUX_IMMUTABLE.
+ *
+ * It has never meant setting security.* and trusted.* xattrs.
+ *
+ * We could also define fsmask as follows:
+ * 1. CAP_FS_MASK is the privilege to bypass all fs-related DAC permissions
+ * 2. The security.* and trusted.* xattrs are fs-related MAC permissions
+ */
+
# define CAP_FS_MASK_B0 (CAP_TO_MASK(CAP_CHOWN) \
+ | CAP_TO_MASK(CAP_MKNOD) \
| CAP_TO_MASK(CAP_DAC_OVERRIDE) \
| CAP_TO_MASK(CAP_DAC_READ_SEARCH) \
| CAP_TO_MASK(CAP_FOWNER) \
@@ -392,11 +406,12 @@ struct cpu_vfs_cap_data {
# define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }})
# define CAP_FULL_SET ((kernel_cap_t){{ ~0, ~0 }})
# define CAP_INIT_EFF_SET ((kernel_cap_t){{ ~CAP_TO_MASK(CAP_SETPCAP), ~0 }})
-# define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0, CAP_FS_MASK_B1 } })
+# define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \
+ | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \
+ CAP_FS_MASK_B1 } })
# define CAP_NFSD_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \
- | CAP_TO_MASK(CAP_SYS_RESOURCE) \
- | CAP_TO_MASK(CAP_MKNOD), \
- CAP_FS_MASK_B1 } })
+ | CAP_TO_MASK(CAP_SYS_RESOURCE), \
+ CAP_FS_MASK_B1 } })

#endif /* _KERNEL_CAPABILITY_U32S != 2 */

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index bd37078..0d2f7c8 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -336,6 +336,11 @@ extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
const enum hrtimer_mode mode);
extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
unsigned long range_ns, const enum hrtimer_mode mode);
+extern int
+__hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns,
+ const enum hrtimer_mode mode, int wakeup);
+
extern int hrtimer_cancel(struct hrtimer *timer);
extern int hrtimer_try_to_cancel(struct hrtimer *timer);

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 9127f6b..564d1c0 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -274,6 +274,7 @@ extern void softirq_init(void);
#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
extern void raise_softirq_irqoff(unsigned int nr);
extern void raise_softirq(unsigned int nr);
+extern void wakeup_softirqd(void);

/* This is the worklist that queues up per-cpu softirq work.
*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bf6f703..552ef4f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -127,6 +127,10 @@ struct kvm {
struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
#endif

+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+ struct hlist_head mask_notifier_list;
+#endif
+
#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
struct mmu_notifier mmu_notifier;
unsigned long mmu_notifier_seq;
@@ -321,6 +325,19 @@ struct kvm_assigned_dev_kernel {
struct pci_dev *dev;
struct kvm *kvm;
};
+
+struct kvm_irq_mask_notifier {
+ void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
+ int irq;
+ struct hlist_node link;
+};
+
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn);
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn);
+void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask);
+
void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level);
void kvm_notify_acked_irq(struct kvm *kvm, unsigned gsi);
void kvm_register_irq_ack_notifier(struct kvm *kvm,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 01ca085..076a7dc 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -18,9 +18,14 @@
* Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page
* allocation mode flags.
*/
-#define AS_EIO (__GFP_BITS_SHIFT + 0) /* IO error on async write */
-#define AS_ENOSPC (__GFP_BITS_SHIFT + 1) /* ENOSPC on async write */
-#define AS_MM_ALL_LOCKS (__GFP_BITS_SHIFT + 2) /* under mm_take_all_locks() */
+enum mapping_flags {
+ AS_EIO = __GFP_BITS_SHIFT + 0, /* IO error on async write */
+ AS_ENOSPC = __GFP_BITS_SHIFT + 1, /* ENOSPC on async write */
+ AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */
+#ifdef CONFIG_UNEVICTABLE_LRU
+ AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */
+#endif
+};

static inline void mapping_set_error(struct address_space *mapping, int error)
{
@@ -33,7 +38,6 @@ static inline void mapping_set_error(struct address_space *mapping, int error)
}

#ifdef CONFIG_UNEVICTABLE_LRU
-#define AS_UNEVICTABLE (__GFP_BITS_SHIFT + 2) /* e.g., ramdisk, SHM_LOCK */

static inline void mapping_set_unevictable(struct address_space *mapping)
{
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 011db2f..f8af167 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -202,7 +202,8 @@ extern unsigned long long time_sync_thresh;
#define task_is_stopped_or_traced(task) \
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
- ((task->state & TASK_UNINTERRUPTIBLE) != 0)
+ ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
+ (task->flags & PF_FROZEN) == 0)

#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
diff --git a/kernel/fork.c b/kernel/fork.c
index 4854c2c..9b51a1b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -808,6 +808,12 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
sig->cputime_expires.virt_exp = cputime_zero;
sig->cputime_expires.sched_exp = 0;

+ if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
+ sig->cputime_expires.prof_exp =
+ secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+ sig->cputimer.running = 1;
+ }
+
/* The timer lists. */
INIT_LIST_HEAD(&sig->cpu_timers[0]);
INIT_LIST_HEAD(&sig->cpu_timers[1]);
@@ -823,11 +829,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
atomic_inc(&current->signal->live);
return 0;
}
- sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
-
- if (sig)
- posix_cpu_timers_init_group(sig);

+ sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
tsk->signal = sig;
if (!sig)
return -ENOMEM;
@@ -865,6 +868,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
task_unlock(current->group_leader);

+ posix_cpu_timers_init_group(sig);
+
acct_init_pacct(&sig->pacct);

tty_audit_fork(sig);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f394d2a..cb8a15c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -651,14 +651,20 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
* and expiry check is done in the hrtimer_interrupt or in the softirq.
*/
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ int wakeup)
{
if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
- spin_unlock(&base->cpu_base->lock);
- raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- spin_lock(&base->cpu_base->lock);
+ if (wakeup) {
+ spin_unlock(&base->cpu_base->lock);
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+ spin_lock(&base->cpu_base->lock);
+ } else
+ __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+
return 1;
}
+
return 0;
}

@@ -703,7 +709,8 @@ static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline int hrtimer_switch_to_hres(void) { return 0; }
static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ int wakeup)
{
return 0;
}
@@ -886,20 +893,9 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
return 0;
}

-/**
- * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
- * @timer: the timer to be added
- * @tim: expiry time
- * @delta_ns: "slack" range for the timer
- * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
- *
- * Returns:
- * 0 on success
- * 1 when the timer was active
- */
-int
-hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns,
- const enum hrtimer_mode mode)
+int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns, const enum hrtimer_mode mode,
+ int wakeup)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
@@ -940,12 +936,29 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n
* XXX send_remote_softirq() ?
*/
if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
- hrtimer_enqueue_reprogram(timer, new_base);
+ hrtimer_enqueue_reprogram(timer, new_base, wakeup);

unlock_hrtimer_base(timer, &flags);

return ret;
}
+
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer: the timer to be added
+ * @tim: expiry time
+ * @delta_ns: "slack" range for the timer
+ * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ *
+ * Returns:
+ * 0 on success
+ * 1 when the timer was active
+ */
+int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns, const enum hrtimer_mode mode)
+{
+ return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
+}
EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);

/**
@@ -961,7 +974,7 @@ EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
int
hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
{
- return hrtimer_start_range_ns(timer, tim, 0, mode);
+ return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
}
EXPORT_SYMBOL_GPL(hrtimer_start);

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 7ba8cd9..6589776 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -912,10 +912,8 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
ri->rp = rp;
ri->task = current;

- if (rp->entry_handler && rp->entry_handler(ri, regs)) {
- spin_unlock_irqrestore(&rp->lock, flags);
+ if (rp->entry_handler && rp->entry_handler(ri, regs))
return 0;
- }

arch_prepare_kretprobe(ri, regs);

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e976e50..68647c1 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -18,7 +18,7 @@ void update_rlimit_cpu(unsigned long rlim_new)

cputime = secs_to_cputime(rlim_new);
if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
- cputime_lt(current->signal->it_prof_expires, cputime)) {
+ cputime_gt(current->signal->it_prof_expires, cputime)) {
spin_lock_irq(&current->sighand->siglock);
set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
spin_unlock_irq(&current->sighand->siglock);
@@ -224,7 +224,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
cpu->cpu = virt_ticks(p);
break;
case CPUCLOCK_SCHED:
- cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p);
+ cpu->sched = task_sched_runtime(p);
break;
}
return 0;
@@ -305,18 +305,19 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
{
struct task_cputime cputime;

- thread_group_cputime(p, &cputime);
switch (CPUCLOCK_WHICH(which_clock)) {
default:
return -EINVAL;
case CPUCLOCK_PROF:
+ thread_group_cputime(p, &cputime);
cpu->cpu = cputime_add(cputime.utime, cputime.stime);
break;
case CPUCLOCK_VIRT:
+ thread_group_cputime(p, &cputime);
cpu->cpu = cputime.utime;
break;
case CPUCLOCK_SCHED:
- cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+ cpu->sched = thread_group_sched_runtime(p);
break;
}
return 0;
diff --git a/kernel/sched.c b/kernel/sched.c
index 8e2558c..5e80629 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -231,13 +231,20 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)

spin_lock(&rt_b->rt_runtime_lock);
for (;;) {
+ unsigned long delta;
+ ktime_t soft, hard;
+
if (hrtimer_active(&rt_b->rt_period_timer))
break;

now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
- hrtimer_start_expires(&rt_b->rt_period_timer,
- HRTIMER_MODE_ABS);
+
+ soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
+ hard = hrtimer_get_expires(&rt_b->rt_period_timer);
+ delta = ktime_to_ns(ktime_sub(hard, soft));
+ __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
+ HRTIMER_MODE_ABS, 0);
}
spin_unlock(&rt_b->rt_runtime_lock);
}
@@ -1129,7 +1136,8 @@ static __init void init_hrtick(void)
*/
static void hrtick_start(struct rq *rq, u64 delay)
{
- hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+ __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
+ HRTIMER_MODE_REL, 0);
}

static inline void init_hrtick(void)
@@ -4134,9 +4142,25 @@ DEFINE_PER_CPU(struct kernel_stat, kstat);
EXPORT_PER_CPU_SYMBOL(kstat);

/*
- * Return any ns on the sched_clock that have not yet been banked in
+ * Return any ns on the sched_clock that have not yet been accounted in
* @p in case that task is currently running.
+ *
+ * Called with task_rq_lock() held on @rq.
*/
+static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
+{
+ u64 ns = 0;
+
+ if (task_current(rq, p)) {
+ update_rq_clock(rq);
+ ns = rq->clock - p->se.exec_start;
+ if ((s64)ns < 0)
+ ns = 0;
+ }
+
+ return ns;
+}
+
unsigned long long task_delta_exec(struct task_struct *p)
{
unsigned long flags;
@@ -4144,16 +4168,49 @@ unsigned long long task_delta_exec(struct task_struct *p)
u64 ns = 0;

rq = task_rq_lock(p, &flags);
+ ns = do_task_delta_exec(p, rq);
+ task_rq_unlock(rq, &flags);

- if (task_current(rq, p)) {
- u64 delta_exec;
+ return ns;
+}

- update_rq_clock(rq);
- delta_exec = rq->clock - p->se.exec_start;
- if ((s64)delta_exec > 0)
- ns = delta_exec;
- }
+/*
+ * Return accounted runtime for the task.
+ * In case the task is currently running, return the runtime plus current's
+ * pending runtime that have not been accounted yet.
+ */
+unsigned long long task_sched_runtime(struct task_struct *p)
+{
+ unsigned long flags;
+ struct rq *rq;
+ u64 ns = 0;

+ rq = task_rq_lock(p, &flags);
+ ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
+ task_rq_unlock(rq, &flags);
+
+ return ns;
+}
+
+/*
+ * Return sum_exec_runtime for the thread group.
+ * In case the task is currently running, return the sum plus current's
+ * pending runtime that have not been accounted yet.
+ *
+ * Note that the thread group might have other running tasks as well,
+ * so the return value not includes other pending runtime that other
+ * running tasks might have.
+ */
+unsigned long long thread_group_sched_runtime(struct task_struct *p)
+{
+ struct task_cputime totals;
+ unsigned long flags;
+ struct rq *rq;
+ u64 ns;
+
+ rq = task_rq_lock(p, &flags);
+ thread_group_cputime(p, &totals);
+ ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
task_rq_unlock(rq, &flags);

return ns;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 9041ea7..d2b183e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
* to the pending events, so lets the scheduler to balance
* the softirq load for us.
*/
-static inline void wakeup_softirqd(void)
+void wakeup_softirqd(void)
{
/* Interrupts are disabled: no need to stop preemption */
struct task_struct *tsk = __get_cpu_var(ksoftirqd);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c5ef44f..7755ae7 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -95,12 +95,9 @@ static int sixty = 60;
static int neg_one = -1;
#endif

-#if defined(CONFIG_MMU) && defined(CONFIG_FILE_LOCKING)
-static int two = 2;
-#endif
-
static int zero;
static int one = 1;
+static int two = 2;
static unsigned long one_ul = 1;
static int one_hundred = 100;

@@ -1373,10 +1370,7 @@ static struct ctl_table fs_table[] = {
.data = &lease_break_time,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
- .extra1 = &zero,
- .extra2 = &two,
+ .proc_handler = &proc_dointvec,
},
#endif
#ifdef CONFIG_AIO
@@ -1417,7 +1411,10 @@ static struct ctl_table fs_table[] = {
.data = &suid_dumpable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &two,
},
#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
{
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 17bb88d..b2387c0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3886,7 +3886,8 @@ __init static int tracer_alloc_buffers(void)
&trace_panic_notifier);

register_die_notifier(&trace_die_notifier);
- ret = 0;
+
+ return 0;

out_free_cpumask:
free_cpumask_var(tracing_cpumask);
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 3389e24..1f71b97 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -109,10 +109,10 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
#endif
/* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */
if (*mask) {
+ unsigned char *ptr = (unsigned char *)cpumask_bits(*mask);
unsigned int tail;
tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long);
- memset(cpumask_bits(*mask) + cpumask_size() - tail,
- 0, tail);
+ memset(ptr + cpumask_size() - tail, 0, tail);
}

return *mask != NULL;
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 0c04615..427dfe3 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -89,8 +89,8 @@ do_xip_mapping_read(struct address_space *mapping,
}
}
nr = nr - offset;
- if (nr > len)
- nr = len;
+ if (nr > len - copied)
+ nr = len - copied;

error = mapping->a_ops->get_xip_mem(mapping, index, 0,
&xip_mem, &xip_pfn);
diff --git a/mm/mmap.c b/mm/mmap.c
index 00ced3e..f1aa6f9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1571,7 +1571,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
* Overcommit.. This must be the final test, as it will
* update security statistics.
*/
- if (security_vm_enough_memory(grow))
+ if (security_vm_enough_memory_mm(mm, grow))
return -ENOMEM;

/* Ok, everything looks good - let it rip */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c6a6b16..eae6954 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2496,7 +2496,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
skb_network_header_len(skb));
skb_copy_from_linear_data(skb, nskb->data, doffset);

- if (pos >= offset + len)
+ if (fskb != skb_shinfo(skb)->frag_list)
continue;

if (!sg) {
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 7ea88b6..39879ae 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -374,7 +374,9 @@ static int mark_source_chains(struct xt_table_info *newinfo,
&& unconditional(&e->arp)) || visited) {
unsigned int oldpos, size;

- if (t->verdict < -NF_MAX_VERDICT - 1) {
+ if ((strcmp(t->target.u.user.name,
+ ARPT_STANDARD_TARGET) == 0) &&
+ t->verdict < -NF_MAX_VERDICT - 1) {
duprintf("mark_source_chains: bad "
"negative verdict (%i)\n",
t->verdict);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index ef8b6ca..ec362a3 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -496,7 +496,9 @@ mark_source_chains(struct xt_table_info *newinfo,
&& unconditional(&e->ip)) || visited) {
unsigned int oldpos, size;

- if (t->verdict < -NF_MAX_VERDICT - 1) {
+ if ((strcmp(t->target.u.user.name,
+ IPT_STANDARD_TARGET) == 0) &&
+ t->verdict < -NF_MAX_VERDICT - 1) {
duprintf("mark_source_chains: bad "
"negative verdict (%i)\n",
t->verdict);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index a33485d..def375b 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -525,7 +525,9 @@ mark_source_chains(struct xt_table_info *newinfo,
&& unconditional(&e->ipv6)) || visited) {
unsigned int oldpos, size;

- if (t->verdict < -NF_MAX_VERDICT - 1) {
+ if ((strcmp(t->target.u.user.name,
+ IP6T_STANDARD_TARGET) == 0) &&
+ t->verdict < -NF_MAX_VERDICT - 1) {
duprintf("mark_source_chains: bad "
"negative verdict (%i)\n",
t->verdict);
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index e9c05b8..dcce778 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1082,7 +1082,13 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock,

SOCK_DEBUG(sk, "NET/ROM: sendto: Addresses built.\n");

- /* Build a packet */
+ /* Build a packet - the conventional user limit is 236 bytes. We can
+ do ludicrously large NetROM frames but must not overflow */
+ if (len > 65536) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
SOCK_DEBUG(sk, "NET/ROM: sendto: building packet.\n");
size = len + NR_NETWORK_LEN + NR_TRANSPORT_LEN;

diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 0139264..5e75bbf 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1124,6 +1124,10 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock,

/* Build a packet */
SOCK_DEBUG(sk, "ROSE: sendto: building packet.\n");
+ /* Sanity check the packet size */
+ if (len > 65535)
+ return -EMSGSIZE;
+
size = len + AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN;

if ((skb = sock_alloc_send_skb(sk, size, msg->msg_flags & MSG_DONTWAIT, &err)) == NULL)
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 9fc5b02..88d80f5 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1037,6 +1037,12 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock,
sx25.sx25_addr = x25->dest_addr;
}

+ /* Sanity check the packet size */
+ if (len > 65535) {
+ rc = -EMSGSIZE;
+ goto out;
+ }
+
SOCK_DEBUG(sk, "x25_sendmsg: sendto: Addresses built.\n");

/* Build a packet */
diff --git a/security/commoncap.c b/security/commoncap.c
index 7cd61a5..beac025 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -916,7 +916,6 @@ changed:
return commit_creds(new);

no_change:
- error = 0;
error:
abort_creds(new);
return error;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index e7ded13..c1c5f36 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -607,6 +607,8 @@ static int smack_inode_setxattr(struct dentry *dentry, const char *name,
strcmp(name, XATTR_NAME_SMACKIPOUT) == 0) {
if (!capable(CAP_MAC_ADMIN))
rc = -EPERM;
+ if (size == 0)
+ rc = -EINVAL;
} else
rc = cap_inode_setxattr(dentry, name, value, size, flags);

@@ -1430,7 +1432,7 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name,
struct socket *sock;
int rc = 0;

- if (value == NULL || size > SMK_LABELLEN)
+ if (value == NULL || size > SMK_LABELLEN || size == 0)
return -EACCES;

sp = smk_import(value, size);
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index d03f992..cef1ce0 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -2003,7 +2003,11 @@ int snd_hda_codec_write_cache(struct hda_codec *codec, hda_nid_t nid,
err = bus->ops.command(bus, res);
if (!err) {
struct hda_cache_head *c;
- u32 key = build_cmd_cache_key(nid, verb);
+ u32 key;
+ /* parm may contain the verb stuff for get/set amp */
+ verb = verb | (parm >> 8);
+ parm &= 0xff;
+ key = build_cmd_cache_key(nid, verb);
c = get_alloc_hash(&codec->cmd_cache, key);
if (c)
c->val = parm;
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index e486123..5a6d6d8 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -3239,7 +3239,7 @@ static const char *ad1884_slave_vols[] = {
"Mic Playback Volume",
"CD Playback Volume",
"Internal Mic Playback Volume",
- "Docking Mic Playback Volume"
+ "Docking Mic Playback Volume",
"Beep Playback Volume",
"IEC958 Playback Volume",
NULL
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 23b81cf..e85a2bc 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -101,6 +101,7 @@ static void ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
{
unsigned index;
+ bool mask_before, mask_after;

switch (ioapic->ioregsel) {
case IOAPIC_REG_VERSION:
@@ -120,6 +121,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
ioapic_debug("change redir index %x val %x\n", index, val);
if (index >= IOAPIC_NUM_PINS)
return;
+ mask_before = ioapic->redirtbl[index].fields.mask;
if (ioapic->ioregsel & 1) {
ioapic->redirtbl[index].bits &= 0xffffffff;
ioapic->redirtbl[index].bits |= (u64) val << 32;
@@ -128,6 +130,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
ioapic->redirtbl[index].bits |= (u32) val;
ioapic->redirtbl[index].fields.remote_irr = 0;
}
+ mask_after = ioapic->redirtbl[index].fields.mask;
+ if (mask_before != mask_after)
+ kvm_fire_mask_notifiers(ioapic->kvm, index, mask_after);
if (ioapic->irr & (1 << index))
ioapic_service(ioapic, index);
break;
@@ -426,3 +431,4 @@ int kvm_ioapic_init(struct kvm *kvm)
kvm_io_bus_register_dev(&kvm->mmio_bus, &ioapic->dev);
return 0;
}
+
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index aa5d1e5..5162a41 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -99,3 +99,27 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
clear_bit(irq_source_id, &kvm->arch.irq_states[i]);
clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
}
+
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn)
+{
+ kimn->irq = irq;
+ hlist_add_head(&kimn->link, &kvm->mask_notifier_list);
+}
+
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn)
+{
+ hlist_del(&kimn->link);
+}
+
+void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
+{
+ struct kvm_irq_mask_notifier *kimn;
+ struct hlist_node *n;
+
+ hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link)
+ if (kimn->irq == irq)
+ kimn->func(kimn, mask);
+}
+
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 29a667c..6723411 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -563,7 +563,7 @@ static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
goto out;
}

- if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
+ if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
kvm_deassign_device(kvm, match);

kvm_free_assigned_device(kvm, match);
@@ -581,8 +581,10 @@ static inline int valid_vcpu(int n)

inline int kvm_is_mmio_pfn(pfn_t pfn)
{
- if (pfn_valid(pfn))
- return PageReserved(pfn_to_page(pfn));
+ if (pfn_valid(pfn)) {
+ struct page *page = compound_head(pfn_to_page(pfn));
+ return PageReserved(page);
+ }

return true;
}
@@ -828,6 +830,9 @@ static struct kvm *kvm_create_vm(void)

if (IS_ERR(kvm))
goto out;
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+ INIT_HLIST_HEAD(&kvm->mask_notifier_list);
+#endif

#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/