Re: Linux 2.6.32.17

From: Greg KH
Date: Mon Aug 02 2010 - 15:03:36 EST

Next message: Greg KH: "Re: Linux 2.6.27.49"
Previous message: Greg KH: "Linux 2.6.32.17"
In reply to: Greg KH: "Linux 2.6.32.17"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

diff --git a/Makefile b/Makefile
index 9797439..2e357ce 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 32
-EXTRAVERSION = .16
+EXTRAVERSION = .17
NAME = Man-Eating Seals of Antiquity

# *DOCUMENTATION*
diff --git a/arch/arm/kernel/kprobes-decode.c b/arch/arm/kernel/kprobes-decode.c
index da1f949..8bccbfa 100644
--- a/arch/arm/kernel/kprobes-decode.c
+++ b/arch/arm/kernel/kprobes-decode.c
@@ -583,13 +583,14 @@ static void __kprobes emulate_ldr(struct kprobe *p, struct pt_regs *regs)
{
insn_llret_3arg_fn_t *i_fn = (insn_llret_3arg_fn_t *)&p->ainsn.insn[0];
kprobe_opcode_t insn = p->opcode;
+ long ppc = (long)p->addr + 8;
union reg_pair fnr;
int rd = (insn >> 12) & 0xf;
int rn = (insn >> 16) & 0xf;
int rm = insn & 0xf;
long rdv;
- long rnv = regs->uregs[rn];
- long rmv = regs->uregs[rm]; /* rm/rmv may be invalid, don't care. */
+ long rnv = (rn == 15) ? ppc : regs->uregs[rn];
+ long rmv = (rm == 15) ? ppc : regs->uregs[rm];
long cpsr = regs->ARM_cpsr;

fnr.dr = insnslot_llret_3arg_rflags(rnv, 0, rmv, cpsr, i_fn);
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index e34d96a..6879cfe 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -37,6 +37,10 @@
#define SYSTEM_REV_S_USES_VAUX3 0x8

static int board_keymap[] = {
+ /*
+ * Note that KEY(x, 8, KEY_XXX) entries represent "entrire row
+ * connected to the ground" matrix state.
+ */
KEY(0, 0, KEY_Q),
KEY(0, 1, KEY_O),
KEY(0, 2, KEY_P),
@@ -44,6 +48,7 @@ static int board_keymap[] = {
KEY(0, 4, KEY_BACKSPACE),
KEY(0, 6, KEY_A),
KEY(0, 7, KEY_S),
+
KEY(1, 0, KEY_W),
KEY(1, 1, KEY_D),
KEY(1, 2, KEY_F),
@@ -52,6 +57,7 @@ static int board_keymap[] = {
KEY(1, 5, KEY_J),
KEY(1, 6, KEY_K),
KEY(1, 7, KEY_L),
+
KEY(2, 0, KEY_E),
KEY(2, 1, KEY_DOT),
KEY(2, 2, KEY_UP),
@@ -59,6 +65,8 @@ static int board_keymap[] = {
KEY(2, 5, KEY_Z),
KEY(2, 6, KEY_X),
KEY(2, 7, KEY_C),
+ KEY(2, 8, KEY_F9),
+
KEY(3, 0, KEY_R),
KEY(3, 1, KEY_V),
KEY(3, 2, KEY_B),
@@ -67,20 +75,23 @@ static int board_keymap[] = {
KEY(3, 5, KEY_SPACE),
KEY(3, 6, KEY_SPACE),
KEY(3, 7, KEY_LEFT),
+
KEY(4, 0, KEY_T),
KEY(4, 1, KEY_DOWN),
KEY(4, 2, KEY_RIGHT),
KEY(4, 4, KEY_LEFTCTRL),
KEY(4, 5, KEY_RIGHTALT),
KEY(4, 6, KEY_LEFTSHIFT),
+ KEY(4, 8, KEY_F10),
+
KEY(5, 0, KEY_Y),
+ KEY(5, 8, KEY_F11),
+
KEY(6, 0, KEY_U),
+
KEY(7, 0, KEY_I),
KEY(7, 1, KEY_F7),
KEY(7, 2, KEY_F8),
- KEY(0xff, 2, KEY_F9),
- KEY(0xff, 4, KEY_F10),
- KEY(0xff, 5, KEY_F11),
};

static struct matrix_keymap_data board_map_data = {
diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig
index c48e1f2..6727c78 100644
--- a/arch/arm/mach-realview/Kconfig
+++ b/arch/arm/mach-realview/Kconfig
@@ -18,6 +18,7 @@ config REALVIEW_EB_ARM11MP
bool "Support ARM11MPCore tile"
depends on MACH_REALVIEW_EB
select CPU_V6
+ select ARCH_HAS_BARRIERS if SMP
help
Enable support for the ARM11MPCore tile on the Realview platform.

@@ -35,6 +36,7 @@ config MACH_REALVIEW_PB11MP
select CPU_V6
select ARM_GIC
select HAVE_PATA_PLATFORM
+ select ARCH_HAS_BARRIERS if SMP
help
Include support for the ARM(R) RealView MPCore Platform Baseboard.
PB11MPCore is a platform with an on-board ARM11MPCore and has
diff --git a/arch/arm/mach-realview/include/mach/barriers.h b/arch/arm/mach-realview/include/mach/barriers.h
new file mode 100644
index 0000000..0c5d749
--- /dev/null
+++ b/arch/arm/mach-realview/include/mach/barriers.h
@@ -0,0 +1,8 @@
+/*
+ * Barriers redefined for RealView ARM11MPCore platforms with L220 cache
+ * controller to work around hardware errata causing the outer_sync()
+ * operation to deadlock the system.
+ */
+#define mb() dsb()
+#define rmb() dmb()
+#define wmb() mb()
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index ee09d26..e2cde52 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -120,7 +120,7 @@ static inline void down_spin(struct spinaphore *ss)
ia64_invala();

for (;;) {
- asm volatile ("ld4.c.nc %0=[%1]" : "=r"(serve) : "r"(&ss->serve) : "memory");
+ asm volatile ("ld8.c.nc %0=[%1]" : "=r"(serve) : "r"(&ss->serve) : "memory");
if (time_before(t, serve))
return;
cpu_relax();
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index a581d60..608dc97 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -135,6 +135,12 @@
#define FPU_CSR_COND7 0x80000000 /* $fcc7 */

/*
+ * Bits 18 - 20 of the FPU Status Register will be read as 0,
+ * and should be written as zero.
+ */
+#define FPU_CSR_RSVD 0x001c0000
+
+/*
* X the exception cause indicator
* E the exception enable
* S the sticky/flag bit
@@ -161,7 +167,8 @@
#define FPU_CSR_UDF_S 0x00000008
#define FPU_CSR_INE_S 0x00000004

-/* rounding mode */
+/* Bits 0 and 1 of FPU Status Register specify the rounding mode */
+#define FPU_CSR_RM 0x00000003
#define FPU_CSR_RN 0x0 /* nearest */
#define FPU_CSR_RZ 0x1 /* towards zero */
#define FPU_CSR_RU 0x2 /* towards +Infinity */
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 454b539..c15d94b 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -75,6 +75,9 @@ struct mips_fpu_emulator_stats fpuemustats;
#define FPCREG_RID 0 /* $0 = revision id */
#define FPCREG_CSR 31 /* $31 = csr */

+/* Determine rounding mode from the RM bits of the FCSR */
+#define modeindex(v) ((v) & FPU_CSR_RM)
+
/* Convert Mips rounding mode (0..3) to IEEE library modes. */
static const unsigned char ieee_rm[4] = {
[FPU_CSR_RN] = IEEE754_RN,
@@ -381,10 +384,14 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
(void *) (xcp->cp0_epc),
MIPSInst_RT(ir), value);
#endif
- value &= (FPU_CSR_FLUSH | FPU_CSR_ALL_E | FPU_CSR_ALL_S | 0x03);
- ctx->fcr31 &= ~(FPU_CSR_FLUSH | FPU_CSR_ALL_E | FPU_CSR_ALL_S | 0x03);
- /* convert to ieee library modes */
- ctx->fcr31 |= (value & ~0x3) | ieee_rm[value & 0x3];
+
+ /*
+ * Don't write reserved bits,
+ * and convert to ieee library modes
+ */
+ ctx->fcr31 = (value &
+ ~(FPU_CSR_RSVD | FPU_CSR_RM)) |
+ ieee_rm[modeindex(value)];
}
if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) {
return SIGFPE;
diff --git a/arch/sparc/include/asm/stat.h b/arch/sparc/include/asm/stat.h
index 39327d6..a232e9e 100644
--- a/arch/sparc/include/asm/stat.h
+++ b/arch/sparc/include/asm/stat.h
@@ -53,8 +53,8 @@ struct stat {
ino_t st_ino;
mode_t st_mode;
short st_nlink;
- uid16_t st_uid;
- gid16_t st_gid;
+ unsigned short st_uid;
+ unsigned short st_gid;
unsigned short st_rdev;
off_t st_size;
time_t st_atime;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a7881c7..a7e502f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -106,6 +106,7 @@
#define MSR_AMD64_PATCH_LOADER 0xc0010020
#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
#define MSR_AMD64_OSVW_STATUS 0xc0010141
+#define MSR_AMD64_DC_CFG 0xc0011022
#define MSR_AMD64_IBSFETCHCTL 0xc0011030
#define MSR_AMD64_IBSFETCHLINAD 0xc0011031
#define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 48dcfa6..fd921c3 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -15,6 +15,8 @@ static inline int arch_prepare_suspend(void) { return 0; }
struct saved_context {
u16 es, fs, gs, ss;
unsigned long cr0, cr2, cr3, cr4;
+ u64 misc_enable;
+ bool misc_enable_saved;
struct desc_ptr gdt;
struct desc_ptr idt;
u16 ldt;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 06284f4..8d942af 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -27,6 +27,8 @@ struct saved_context {
u16 ds, es, fs, gs, ss;
unsigned long gs_base, gs_kernel_base, fs_base;
unsigned long cr0, cr2, cr3, cr4, cr8;
+ u64 misc_enable;
+ bool misc_enable_saved;
unsigned long efer;
u16 gdt_pad;
u16 gdt_limit;
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index f08f973..e0fbf29 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -449,7 +449,7 @@ void stop_this_cpu(void *dummy);
*
* (Could use an alternative three way for this if there was one.)
*/
-static inline void rdtsc_barrier(void)
+static __always_inline void rdtsc_barrier(void)
{
alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 2e837f5..fb7a5f0 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -145,6 +145,15 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
percpu_entry->states[cx->index].eax = cx->address;
percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK;
}
+
+ /*
+ * For _CST FFH on Intel, if GAS.access_size bit 1 is cleared,
+ * then we should skip checking BM_STS for this C-state.
+ * ref: "Intel Processor Vendor-Specific ACPI Interface Specification"
+ */
+ if ((c->x86_vendor == X86_VENDOR_INTEL) && !(reg->access_size & 0x2))
+ cx->bm_sts_skip = 1;
+
return retval;
}
EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 8b85734..ca93638 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -162,8 +162,6 @@ static int __init acpi_sleep_setup(char *str)
#endif
if (strncmp(str, "old_ordering", 12) == 0)
acpi_old_suspend_ordering();
- if (strncmp(str, "sci_force_enable", 16) == 0)
- acpi_set_sci_en_on_resume();
str = strchr(str, ',');
if (str != NULL)
str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 168e172..bc9cd5a 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -941,7 +941,7 @@ void disable_local_APIC(void)
unsigned int value;

/* APIC hasn't been mapped yet */
- if (!apic_phys)
+ if (!x2apic_mode && !apic_phys)
return;

clear_local_APIC();
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 74f5a3f..19528ef 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -949,7 +949,7 @@ fs_initcall(hpet_late_init);

void hpet_disable(void)
{
- if (is_hpet_capable()) {
+ if (is_hpet_capable() && hpet_virt_address) {
unsigned long cfg = hpet_readl(HPET_CFG);

if (hpet_legacy_int_enabled) {
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index e6ec8a2..1a2d4b1 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -102,11 +102,16 @@ int use_calgary __read_mostly = 0;
#define PMR_SOFTSTOPFAULT 0x40000000
#define PMR_HARDSTOP 0x20000000

-#define MAX_NUM_OF_PHBS 8 /* how many PHBs in total? */
-#define MAX_NUM_CHASSIS 8 /* max number of chassis */
-/* MAX_PHB_BUS_NUM is the maximal possible dev->bus->number */
-#define MAX_PHB_BUS_NUM (MAX_NUM_OF_PHBS * MAX_NUM_CHASSIS * 2)
-#define PHBS_PER_CALGARY 4
+/*
+ * The maximum PHB bus number.
+ * x3950M2 (rare): 8 chassis, 48 PHBs per chassis = 384
+ * x3950M2: 4 chassis, 48 PHBs per chassis = 192
+ * x3950 (PCIE): 8 chassis, 32 PHBs per chassis = 256
+ * x3950 (PCIX): 8 chassis, 16 PHBs per chassis = 128
+ */
+#define MAX_PHB_BUS_NUM 256
+
+#define PHBS_PER_CALGARY 4

/* register offsets in Calgary's internal register space */
static const unsigned long tar_offsets[] = {
@@ -1053,8 +1058,6 @@ static int __init calgary_init_one(struct pci_dev *dev)
struct iommu_table *tbl;
int ret;

- BUG_ON(dev->bus->number >= MAX_PHB_BUS_NUM);
-
bbar = busno_to_bbar(dev->bus->number);
ret = calgary_setup_tar(dev, bbar);
if (ret)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index a265626..fdf2e28 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1843,6 +1843,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,

spte |= PT_WRITABLE_MASK;

+ if (!tdp_enabled && !(pte_access & ACC_WRITE_MASK))
+ spte &= ~PT_USER_MASK;
+
/*
* Optimization: for pte sync, if spte was writable the hash
* lookup is unnecessary (and expensive). Write protection
@@ -1898,6 +1901,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,

child = page_header(pte & PT64_BASE_ADDR_MASK);
mmu_page_remove_parent_pte(child, sptep);
+ __set_spte(sptep, shadow_trap_nonpresent_pte);
+ kvm_flush_remote_tlbs(vcpu->kvm);
} else if (pfn != spte_to_pfn(*sptep)) {
pgprintk("hfn old %lx new %lx\n",
spte_to_pfn(*sptep), pfn);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 8e65552..61ba669 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -27,6 +27,7 @@
#include <linux/sched.h>
#include <linux/ftrace_event.h>

+#include <asm/tlbflush.h>
#include <asm/desc.h>

#include <asm/virtext.h>
@@ -62,6 +63,8 @@ MODULE_LICENSE("GPL");
#define nsvm_printk(fmt, args...) do {} while(0)
#endif

+static bool erratum_383_found __read_mostly;
+
static const u32 host_save_user_msrs[] = {
#ifdef CONFIG_X86_64
MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
@@ -299,6 +302,31 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
svm_set_interrupt_shadow(vcpu, 0);
}

+static void svm_init_erratum_383(void)
+{
+ u32 low, high;
+ int err;
+ u64 val;
+
+ /* Only Fam10h is affected */
+ if (boot_cpu_data.x86 != 0x10)
+ return;
+
+ /* Use _safe variants to not break nested virtualization */
+ val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
+ if (err)
+ return;
+
+ val |= (1ULL << 47);
+
+ low = lower_32_bits(val);
+ high = upper_32_bits(val);
+
+ native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
+
+ erratum_383_found = true;
+}
+
static int has_svm(void)
{
const char *msg;
@@ -318,7 +346,6 @@ static void svm_hardware_disable(void *garbage)

static void svm_hardware_enable(void *garbage)
{
-
struct svm_cpu_data *svm_data;
uint64_t efer;
struct descriptor_table gdt_descr;
@@ -350,6 +377,10 @@ static void svm_hardware_enable(void *garbage)

wrmsrl(MSR_VM_HSAVE_PA,
page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
+
+ svm_init_erratum_383();
+
+ return;
}

static void svm_cpu_uninit(int cpu)
@@ -1257,8 +1288,59 @@ static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
return 1;
}

-static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static bool is_erratum_383(void)
{
+ int err, i;
+ u64 value;
+
+ if (!erratum_383_found)
+ return false;
+
+ value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
+ if (err)
+ return false;
+
+ /* Bit 62 may or may not be set for this mce */
+ value &= ~(1ULL << 62);
+
+ if (value != 0xb600000000010015ULL)
+ return false;
+
+ /* Clear MCi_STATUS registers */
+ for (i = 0; i < 6; ++i)
+ native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
+
+ value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
+ if (!err) {
+ u32 low, high;
+
+ value &= ~(1ULL << 2);
+ low = lower_32_bits(value);
+ high = upper_32_bits(value);
+
+ native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
+ }
+
+ /* Flush tlb to evict multi-match entries */
+ __flush_tlb_all();
+
+ return true;
+}
+
+static void svm_handle_mce(struct vcpu_svm *svm)
+{
+ if (is_erratum_383()) {
+ /*
+ * Erratum 383 triggered. Guest state is corrupt so kill the
+ * guest.
+ */
+ pr_err("KVM: Guest triggered AMD Erratum 383\n");
+
+ set_bit(KVM_REQ_TRIPLE_FAULT, &svm->vcpu.requests);
+
+ return;
+ }
+
/*
* On an #MC intercept the MCE handler is not called automatically in
* the host. So do it by hand here.
@@ -1267,6 +1349,11 @@ static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
"int $0x12\n");
/* not sure if we ever come back to this point */

+ return;
+}
+
+static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
return 1;
}

@@ -2717,6 +2804,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);
vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR);
}
+
+ /*
+ * We need to handle MC intercepts here before the vcpu has a chance to
+ * change the physical cpu
+ */
+ if (unlikely(svm->vmcb->control.exit_code ==
+ SVM_EXIT_EXCP_BASE + MC_VECTOR))
+ svm_handle_mce(svm);
}

#undef R
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 8aa85f1..eeeb522 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -104,6 +104,8 @@ static void __save_processor_state(struct saved_context *ctxt)
ctxt->cr4 = read_cr4();
ctxt->cr8 = read_cr8();
#endif
+ ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
+ &ctxt->misc_enable);
}

/* Needed by apm.c */
@@ -176,6 +178,8 @@ static void fix_processor_context(void)
*/
static void __restore_processor_state(struct saved_context *ctxt)
{
+ if (ctxt->misc_enable_saved)
+ wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
/*
* control registers
*/
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index c8f0797..a6ad608 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -962,7 +962,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
if (acpi_idle_suspend)
return(acpi_idle_enter_c1(dev, state));

- if (acpi_idle_bm_check()) {
+ if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
if (dev->safe_state) {
dev->last_state = dev->safe_state;
return dev->safe_state->enter(dev, dev->safe_state);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 9ed9292..0458094 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -80,22 +80,6 @@ static int acpi_sleep_prepare(u32 acpi_state)

#ifdef CONFIG_ACPI_SLEEP
static u32 acpi_target_sleep_state = ACPI_STATE_S0;
-/*
- * According to the ACPI specification the BIOS should make sure that ACPI is
- * enabled and SCI_EN bit is set on wake-up from S1 - S3 sleep states. Still,
- * some BIOSes don't do that and therefore we use acpi_enable() to enable ACPI
- * on such systems during resume. Unfortunately that doesn't help in
- * particularly pathological cases in which SCI_EN has to be set directly on
- * resume, although the specification states very clearly that this flag is
- * owned by the hardware. The set_sci_en_on_resume variable will be set in such
- * cases.
- */
-static bool set_sci_en_on_resume;
-
-void __init acpi_set_sci_en_on_resume(void)
-{
- set_sci_en_on_resume = true;
-}

/*
* ACPI 1.0 wants us to execute _PTS before suspending devices, so we allow the
@@ -253,11 +237,8 @@ static int acpi_suspend_enter(suspend_state_t pm_state)
break;
}

- /* If ACPI is not enabled by the BIOS, we need to enable it here. */
- if (set_sci_en_on_resume)
- acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1);
- else
- acpi_enable();
+ /* This violates the spec but is required for bug compatibility. */
+ acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1);

/* Reprogram control registers and execute _BFS */
acpi_leave_sleep_state_prep(acpi_state);
@@ -346,12 +327,6 @@ static int __init init_old_suspend_ordering(const struct dmi_system_id *d)
return 0;
}

-static int __init init_set_sci_en_on_resume(const struct dmi_system_id *d)
-{
- set_sci_en_on_resume = true;
- return 0;
-}
-
static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
{
.callback = init_old_suspend_ordering,
@@ -370,22 +345,6 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
},
},
{
- .callback = init_set_sci_en_on_resume,
- .ident = "Apple MacBook 1,1",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Apple Computer, Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "MacBook1,1"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Apple MacMini 1,1",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Apple Computer, Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Macmini1,1"),
- },
- },
- {
.callback = init_old_suspend_ordering,
.ident = "Asus Pundit P1-AH2 (M2N8L motherboard)",
.matches = {
@@ -394,94 +353,6 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
},
},
{
- .callback = init_set_sci_en_on_resume,
- .ident = "Toshiba Satellite L300",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Satellite L300"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Hewlett-Packard HP G7000 Notebook PC",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP G7000 Notebook PC"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Hewlett-Packard HP Pavilion dv3 Notebook PC",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv3 Notebook PC"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Hewlett-Packard Pavilion dv4",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Hewlett-Packard Pavilion dv7",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv7"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Hewlett-Packard Compaq Presario C700 Notebook PC",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Compaq Presario C700 Notebook PC"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Hewlett-Packard Compaq Presario CQ40 Notebook PC",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Compaq Presario CQ40 Notebook PC"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Lenovo ThinkPad T410",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T410"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Lenovo ThinkPad T510",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T510"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Lenovo ThinkPad W510",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W510"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Lenovo ThinkPad X201[s]",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201"),
- },
- },
- {
.callback = init_old_suspend_ordering,
.ident = "Panasonic CF51-2L",
.matches = {
@@ -490,30 +361,6 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "CF51-2L"),
},
},
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Dell Studio 1558",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1558"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Dell Studio 1557",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1557"),
- },
- },
- {
- .callback = init_set_sci_en_on_resume,
- .ident = "Dell Studio 1555",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1555"),
- },
- },
{},
};
#endif /* CONFIG_SUSPEND */
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 7376367..e0e6570 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -125,6 +125,17 @@ static ssize_t firmware_loading_show(struct device *dev,
return sprintf(buf, "%d\n", loading);
}

+static void firmware_free_data(const struct firmware *fw)
+{
+ int i;
+ vunmap(fw->data);
+ if (fw->pages) {
+ for (i = 0; i < PFN_UP(fw->size); i++)
+ __free_page(fw->pages[i]);
+ kfree(fw->pages);
+ }
+}
+
/* Some architectures don't have PAGE_KERNEL_RO */
#ifndef PAGE_KERNEL_RO
#define PAGE_KERNEL_RO PAGE_KERNEL
@@ -157,21 +168,21 @@ static ssize_t firmware_loading_store(struct device *dev,
mutex_unlock(&fw_lock);
break;
}
- vfree(fw_priv->fw->data);
- fw_priv->fw->data = NULL;
+ firmware_free_data(fw_priv->fw);
+ memset(fw_priv->fw, 0, sizeof(struct firmware));
+ /* If the pages are not owned by 'struct firmware' */
for (i = 0; i < fw_priv->nr_pages; i++)
__free_page(fw_priv->pages[i]);
kfree(fw_priv->pages);
fw_priv->pages = NULL;
fw_priv->page_array_size = 0;
fw_priv->nr_pages = 0;
- fw_priv->fw->size = 0;
set_bit(FW_STATUS_LOADING, &fw_priv->status);
mutex_unlock(&fw_lock);
break;
case 0:
if (test_bit(FW_STATUS_LOADING, &fw_priv->status)) {
- vfree(fw_priv->fw->data);
+ vunmap(fw_priv->fw->data);
fw_priv->fw->data = vmap(fw_priv->pages,
fw_priv->nr_pages,
0, PAGE_KERNEL_RO);
@@ -179,7 +190,10 @@ static ssize_t firmware_loading_store(struct device *dev,
dev_err(dev, "%s: vmap() failed\n", __func__);
goto err;
}
- /* Pages will be freed by vfree() */
+ /* Pages are now owned by 'struct firmware' */
+ fw_priv->fw->pages = fw_priv->pages;
+ fw_priv->pages = NULL;
+
fw_priv->page_array_size = 0;
fw_priv->nr_pages = 0;
complete(&fw_priv->completion);
@@ -572,7 +586,7 @@ release_firmware(const struct firmware *fw)
if (fw->data == builtin->data)
goto free_fw;
}
- vfree(fw->data);
+ firmware_free_data(fw);
free_fw:
kfree(fw);
}
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index 2fb2e6c..c496c8a 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -499,6 +499,10 @@ static int __devinit agp_amd64_probe(struct pci_dev *pdev,
u8 cap_ptr;
int err;

+ /* The Highlander principle */
+ if (agp_bridges_found)
+ return -ENODEV;
+
cap_ptr = pci_find_capability(pdev, PCI_CAP_ID_AGP);
if (!cap_ptr)
return -ENODEV;
@@ -562,6 +566,8 @@ static void __devexit agp_amd64_remove(struct pci_dev *pdev)
amd64_aperture_sizes[bridge->aperture_size_idx].size);
agp_remove_bridge(bridge);
agp_put_bridge(bridge);
+
+ agp_bridges_found--;
}

#ifdef CONFIG_PM
@@ -709,6 +715,11 @@ static struct pci_device_id agp_amd64_pci_table[] = {

MODULE_DEVICE_TABLE(pci, agp_amd64_pci_table);

+static DEFINE_PCI_DEVICE_TABLE(agp_amd64_pci_promisc_table) = {
+ { PCI_DEVICE_CLASS(0, 0) },
+ { }
+};
+
static struct pci_driver agp_amd64_pci_driver = {
.name = "agpgart-amd64",
.id_table = agp_amd64_pci_table,
@@ -733,7 +744,6 @@ int __init agp_amd64_init(void)
return err;

if (agp_bridges_found == 0) {
- struct pci_dev *dev;
if (!agp_try_unsupported && !agp_try_unsupported_boot) {
printk(KERN_INFO PFX "No supported AGP bridge found.\n");
#ifdef MODULE
@@ -749,17 +759,10 @@ int __init agp_amd64_init(void)
return -ENODEV;

/* Look for any AGP bridge */
- dev = NULL;
- err = -ENODEV;
- for_each_pci_dev(dev) {
- if (!pci_find_capability(dev, PCI_CAP_ID_AGP))
- continue;
- /* Only one bridge supported right now */
- if (agp_amd64_probe(dev, NULL) == 0) {
- err = 0;
- break;
- }
- }
+ agp_amd64_pci_driver.id_table = agp_amd64_pci_promisc_table;
+ err = driver_attach(&agp_amd64_pci_driver.driver);
+ if (err == 0 && agp_bridges_found == 0)
+ err = -ENODEV;
}
return err;
}
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 8e00b4d..792868d 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -224,6 +224,7 @@ struct tpm_readpubek_params_out {
u8 algorithm[4];
u8 encscheme[2];
u8 sigscheme[2];
+ __be32 paramsize;
u8 parameters[12]; /*assuming RSA*/
__be32 keysize;
u8 modulus[256];
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 2405f17..ca15c04 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -622,7 +622,14 @@ static int tpm_tis_pnp_suspend(struct pnp_dev *dev, pm_message_t msg)

static int tpm_tis_pnp_resume(struct pnp_dev *dev)
{
- return tpm_pm_resume(&dev->dev);
+ struct tpm_chip *chip = pnp_get_drvdata(dev);
+ int ret;
+
+ ret = tpm_pm_resume(&dev->dev);
+ if (!ret)
+ tpm_continue_selftest(chip);
+
+ return ret;
}

static struct pnp_device_id tpm_pnp_tbl[] __devinitdata = {
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index ff57c40..c18e65e 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1741,17 +1741,8 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
dprintk("governor switch\n");

/* end old governor */
- if (data->governor) {
- /*
- * Need to release the rwsem around governor
- * stop due to lock dependency between
- * cancel_delayed_work_sync and the read lock
- * taken in the delayed work handler.
- */
- unlock_policy_rwsem_write(data->cpu);
+ if (data->governor)
__cpufreq_governor(data, CPUFREQ_GOV_STOP);
- lock_policy_rwsem_write(data->cpu);
- }

/* start new governor */
data->governor = policy->governor;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 7f436ec..5449239 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -192,6 +192,7 @@ int i965_reset(struct drm_device *dev, u8 flags)
}
} else {
DRM_ERROR("Error occurred. Don't know how to reset this chip.\n");
+ mutex_unlock(&dev->struct_mutex);
return -ENODEV;
}

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index df6f7c9..952c844 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4697,6 +4697,16 @@ i915_gem_load(struct drm_device *dev)
list_add(&dev_priv->mm.shrink_list, &shrink_list);
spin_unlock(&shrink_list_lock);

+ /* On GEN3 we really need to make sure the ARB C3 LP bit is set */
+ if (IS_I915G(dev) || IS_I915GM(dev) || IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) {
+ u32 tmp = I915_READ(MI_ARB_STATE);
+ if (!(tmp & MI_ARB_C3_LP_WRITE_ENABLE)) {
+ /* arb state is a masked write, so set bit + bit in mask */
+ tmp = MI_ARB_C3_LP_WRITE_ENABLE | (MI_ARB_C3_LP_WRITE_ENABLE << MI_ARB_MASK_SHIFT);
+ I915_WRITE(MI_ARB_STATE, tmp);
+ }
+ }
+
/* Old X drivers will take 0-2 for front, back, depth buffers */
dev_priv->fence_reg_start = 3;

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 73e7ec0..7214c85 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -307,6 +307,70 @@
#define LM_BURST_LENGTH 0x00000700
#define LM_FIFO_WATERMARK 0x0000001F
#define MI_ARB_STATE 0x020e4 /* 915+ only */
+#define MI_ARB_MASK_SHIFT 16 /* shift for enable bits */
+
+/* Make render/texture TLB fetches lower priorty than associated data
+ * fetches. This is not turned on by default
+ */
+#define MI_ARB_RENDER_TLB_LOW_PRIORITY (1 << 15)
+
+/* Isoch request wait on GTT enable (Display A/B/C streams).
+ * Make isoch requests stall on the TLB update. May cause
+ * display underruns (test mode only)
+ */
+#define MI_ARB_ISOCH_WAIT_GTT (1 << 14)
+
+/* Block grant count for isoch requests when block count is
+ * set to a finite value.
+ */
+#define MI_ARB_BLOCK_GRANT_MASK (3 << 12)
+#define MI_ARB_BLOCK_GRANT_8 (0 << 12) /* for 3 display planes */
+#define MI_ARB_BLOCK_GRANT_4 (1 << 12) /* for 2 display planes */
+#define MI_ARB_BLOCK_GRANT_2 (2 << 12) /* for 1 display plane */
+#define MI_ARB_BLOCK_GRANT_0 (3 << 12) /* don't use */
+
+/* Enable render writes to complete in C2/C3/C4 power states.
+ * If this isn't enabled, render writes are prevented in low
+ * power states. That seems bad to me.
+ */
+#define MI_ARB_C3_LP_WRITE_ENABLE (1 << 11)
+
+/* This acknowledges an async flip immediately instead
+ * of waiting for 2TLB fetches.
+ */
+#define MI_ARB_ASYNC_FLIP_ACK_IMMEDIATE (1 << 10)
+
+/* Enables non-sequential data reads through arbiter
+ */
+#define MI_ARB_DUAL_DATA_PHASE_DISABLE (1 << 9)
+
+/* Disable FSB snooping of cacheable write cycles from binner/render
+ * command stream
+ */
+#define MI_ARB_CACHE_SNOOP_DISABLE (1 << 8)
+
+/* Arbiter time slice for non-isoch streams */
+#define MI_ARB_TIME_SLICE_MASK (7 << 5)
+#define MI_ARB_TIME_SLICE_1 (0 << 5)
+#define MI_ARB_TIME_SLICE_2 (1 << 5)
+#define MI_ARB_TIME_SLICE_4 (2 << 5)
+#define MI_ARB_TIME_SLICE_6 (3 << 5)
+#define MI_ARB_TIME_SLICE_8 (4 << 5)
+#define MI_ARB_TIME_SLICE_10 (5 << 5)
+#define MI_ARB_TIME_SLICE_14 (6 << 5)
+#define MI_ARB_TIME_SLICE_16 (7 << 5)
+
+/* Low priority grace period page size */
+#define MI_ARB_LOW_PRIORITY_GRACE_4KB (0 << 4) /* default */
+#define MI_ARB_LOW_PRIORITY_GRACE_8KB (1 << 4)
+
+/* Disable display A/B trickle feed */
+#define MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE (1 << 2)
+
+/* Set display plane priority */
+#define MI_ARB_DISPLAY_PRIORITY_A_B (0 << 0) /* display A > display B */
+#define MI_ARB_DISPLAY_PRIORITY_B_A (1 << 0) /* display B > display A */
+
#define CACHE_MODE_0 0x02120 /* 915+ only */
#define CM0_MASK_SHIFT 16
#define CM0_IZ_OPT_DISABLE (1<<6)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index cce453e..88d5e3a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -785,8 +785,8 @@ intel_g4x_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc,
intel_clock_t clock;
int max_n;
bool found;
- /* approximately equals target * 0.00488 */
- int err_most = (target >> 8) + (target >> 10);
+ /* approximately equals target * 0.00585 */
+ int err_most = (target >> 8) + (target >> 9);
found = false;

if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) {
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index eb740fc..ccf42c3 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -368,6 +368,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
/* 2D, 3D, CUBE */
switch (tmp) {
case 0:
+ case 3:
+ case 4:
case 5:
case 6:
case 7:
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index a4813c6..e5e22b1 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -161,6 +161,15 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev,
}
}

+ /* ASUS HD 3600 board lists the DVI port as HDMI */
+ if ((dev->pdev->device == 0x9598) &&
+ (dev->pdev->subsystem_vendor == 0x1043) &&
+ (dev->pdev->subsystem_device == 0x01e4)) {
+ if (*connector_type == DRM_MODE_CONNECTOR_HDMIA) {
+ *connector_type = DRM_MODE_CONNECTOR_DVII;
+ }
+ }
+
/* ASUS HD 3450 board lists the DVI port as HDMI */
if ((dev->pdev->device == 0x95C5) &&
(dev->pdev->subsystem_vendor == 0x1043) &&
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index 0038212..183bef8 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -89,6 +89,7 @@ static void radeon_legacy_lvds_dpms(struct drm_encoder *encoder, int mode)
udelay(panel_pwr_delay * 1000);
WREG32(RADEON_LVDS_GEN_CNTL, lvds_gen_cntl);
WREG32_PLL(RADEON_PIXCLKS_CNTL, pixclks_cntl);
+ udelay(panel_pwr_delay * 1000);
break;
}

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index cb4290a..5852191 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -53,6 +53,7 @@ struct coretemp_data {
struct mutex update_lock;
const char *name;
u32 id;
+ u16 core_id;
char valid; /* zero until following fields are valid */
unsigned long last_updated; /* in jiffies */
int temp;
@@ -75,7 +76,7 @@ static ssize_t show_name(struct device *dev, struct device_attribute
if (attr->index == SHOW_NAME)
ret = sprintf(buf, "%s\n", data->name);
else /* show label */
- ret = sprintf(buf, "Core %d\n", data->id);
+ ret = sprintf(buf, "Core %d\n", data->core_id);
return ret;
}

@@ -255,6 +256,9 @@ static int __devinit coretemp_probe(struct platform_device *pdev)
}

data->id = pdev->id;
+#ifdef CONFIG_SMP
+ data->core_id = c->cpu_core_id;
+#endif
data->name = "coretemp";
mutex_init(&data->update_lock);

@@ -352,6 +356,10 @@ struct pdev_entry {
struct list_head list;
struct platform_device *pdev;
unsigned int cpu;
+#ifdef CONFIG_SMP
+ u16 phys_proc_id;
+ u16 cpu_core_id;
+#endif
};

static LIST_HEAD(pdev_list);
@@ -362,6 +370,22 @@ static int __cpuinit coretemp_device_add(unsigned int cpu)
int err;
struct platform_device *pdev;
struct pdev_entry *pdev_entry;
+#ifdef CONFIG_SMP
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+#endif
+
+ mutex_lock(&pdev_list_mutex);
+
+#ifdef CONFIG_SMP
+ /* Skip second HT entry of each core */
+ list_for_each_entry(pdev_entry, &pdev_list, list) {
+ if (c->phys_proc_id == pdev_entry->phys_proc_id &&
+ c->cpu_core_id == pdev_entry->cpu_core_id) {
+ err = 0; /* Not an error */
+ goto exit;
+ }
+ }
+#endif

pdev = platform_device_alloc(DRVNAME, cpu);
if (!pdev) {
@@ -385,7 +409,10 @@ static int __cpuinit coretemp_device_add(unsigned int cpu)

pdev_entry->pdev = pdev;
pdev_entry->cpu = cpu;
- mutex_lock(&pdev_list_mutex);
+#ifdef CONFIG_SMP
+ pdev_entry->phys_proc_id = c->phys_proc_id;
+ pdev_entry->cpu_core_id = c->cpu_core_id;
+#endif
list_add_tail(&pdev_entry->list, &pdev_list);
mutex_unlock(&pdev_list_mutex);

@@ -396,6 +423,7 @@ exit_device_free:
exit_device_put:
platform_device_put(pdev);
exit:
+ mutex_unlock(&pdev_list_mutex);
return err;
}

diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index a3749cb..497476f 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -80,6 +80,13 @@ superio_inb(int reg)
return inb(VAL);
}

+static inline void
+superio_outb(int reg, int val)
+{
+ outb(reg, REG);
+ outb(val, VAL);
+}
+
static int superio_inw(int reg)
{
int val;
@@ -1036,6 +1043,21 @@ static int __init it87_find(unsigned short *address,
sio_data->vid_value = superio_inb(IT87_SIO_VID_REG);

reg = superio_inb(IT87_SIO_PINX2_REG);
+ /*
+ * The IT8720F has no VIN7 pin, so VCCH should always be
+ * routed internally to VIN7 with an internal divider.
+ * Curiously, there still is a configuration bit to control
+ * this, which means it can be set incorrectly. And even
+ * more curiously, many boards out there are improperly
+ * configured, even though the IT8720F datasheet claims
+ * that the internal routing of VCCH to VIN7 is the default
+ * setting. So we force the internal routing in this case.
+ */
+ if (sio_data->type == it8720 && !(reg & (1 << 1))) {
+ reg |= (1 << 1);
+ superio_outb(IT87_SIO_PINX2_REG, reg);
+ pr_notice("it87: Routing internal VCCH to in7\n");
+ }
if (reg & (1 << 0))
pr_info("it87: in3 is VCC (+5V)\n");
if (reg & (1 << 1))
diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c
index 1fe9951..f808d18 100644
--- a/drivers/hwmon/k8temp.c
+++ b/drivers/hwmon/k8temp.c
@@ -120,7 +120,7 @@ static ssize_t show_temp(struct device *dev,
int temp;
struct k8temp_data *data = k8temp_update_device(dev);

- if (data->swap_core_select)
+ if (data->swap_core_select && (data->sensorsp & SEL_CORE))
core = core ? 0 : 1;

temp = TEMP_FROM_REG(data->temp[core][place]) + data->temp_offset;
@@ -180,11 +180,13 @@ static int __devinit k8temp_probe(struct pci_dev *pdev,
}

if ((model >= 0x69) &&
- !(model == 0xc1 || model == 0x6c || model == 0x7c)) {
+ !(model == 0xc1 || model == 0x6c || model == 0x7c ||
+ model == 0x6b || model == 0x6f || model == 0x7f)) {
/*
- * RevG desktop CPUs (i.e. no socket S1G1 parts)
- * need additional offset, otherwise reported
- * temperature is below ambient temperature
+ * RevG desktop CPUs (i.e. no socket S1G1 or
+ * ASB1 parts) need additional offset,
+ * otherwise reported temperature is below
+ * ambient temperature
*/
data->temp_offset = 21000;
}
diff --git a/drivers/ide/cmd640.c b/drivers/ide/cmd640.c
index 1a32d62..a9c3313 100644
--- a/drivers/ide/cmd640.c
+++ b/drivers/ide/cmd640.c
@@ -632,12 +632,10 @@ static void cmd640_init_dev(ide_drive_t *drive)

static int cmd640_test_irq(ide_hwif_t *hwif)
{
- struct pci_dev *dev = to_pci_dev(hwif->dev);
int irq_reg = hwif->channel ? ARTTIM23 : CFR;
- u8 irq_stat, irq_mask = hwif->channel ? ARTTIM23_IDE23INTR :
+ u8 irq_mask = hwif->channel ? ARTTIM23_IDE23INTR :
CFR_IDE01INTR;
-
- pci_read_config_byte(dev, irq_reg, &irq_stat);
+ u8 irq_stat = get_cmd640_reg(irq_reg);

return (irq_stat & irq_mask) ? 1 : 0;
}
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index cc8633c..67fb735 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -428,13 +428,11 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
{
struct request *rq;
int error;
+ int rw = !(cmd->tf_flags & IDE_TFLAG_WRITE) ? READ : WRITE;

- rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+ rq = blk_get_request(drive->queue, rw, __GFP_WAIT);
rq->cmd_type = REQ_TYPE_ATA_TASKFILE;

- if (cmd->tf_flags & IDE_TFLAG_WRITE)
- rq->cmd_flags |= REQ_RW;
-
/*
* (ks) We transfer currently only whole sectors.
* This is suffient for now. But, it would be great,
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index df3eb8c..b4b2257 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1163,7 +1163,7 @@ static ssize_t create_child(struct device *dev,

return ret ? ret : count;
}
-static DEVICE_ATTR(create_child, S_IWUGO, NULL, create_child);
+static DEVICE_ATTR(create_child, S_IWUSR, NULL, create_child);

static ssize_t delete_child(struct device *dev,
struct device_attribute *attr,
@@ -1183,7 +1183,7 @@ static ssize_t delete_child(struct device *dev,
return ret ? ret : count;

}
-static DEVICE_ATTR(delete_child, S_IWUGO, NULL, delete_child);
+static DEVICE_ATTR(delete_child, S_IWUSR, NULL, delete_child);

int ipoib_add_pkey_attr(struct net_device *dev)
{
diff --git a/drivers/input/keyboard/twl4030_keypad.c b/drivers/input/keyboard/twl4030_keypad.c
index 9a2977c..2cfbc17 100644
--- a/drivers/input/keyboard/twl4030_keypad.c
+++ b/drivers/input/keyboard/twl4030_keypad.c
@@ -50,8 +50,12 @@
*/
#define TWL4030_MAX_ROWS 8 /* TWL4030 hard limit */
#define TWL4030_MAX_COLS 8
-#define TWL4030_ROW_SHIFT 3
-#define TWL4030_KEYMAP_SIZE (TWL4030_MAX_ROWS * TWL4030_MAX_COLS)
+/*
+ * Note that we add space for an extra column so that we can handle
+ * row lines connected to the gnd (see twl4030_col_xlate()).
+ */
+#define TWL4030_ROW_SHIFT 4
+#define TWL4030_KEYMAP_SIZE (TWL4030_MAX_ROWS << TWL4030_ROW_SHIFT)

struct twl4030_keypad {
unsigned short keymap[TWL4030_KEYMAP_SIZE];
@@ -181,7 +185,7 @@ static int twl4030_read_kp_matrix_state(struct twl4030_keypad *kp, u16 *state)
return ret;
}

-static int twl4030_is_in_ghost_state(struct twl4030_keypad *kp, u16 *key_state)
+static bool twl4030_is_in_ghost_state(struct twl4030_keypad *kp, u16 *key_state)
{
int i;
u16 check = 0;
@@ -190,12 +194,12 @@ static int twl4030_is_in_ghost_state(struct twl4030_keypad *kp, u16 *key_state)
u16 col = key_state[i];

if ((col & check) && hweight16(col) > 1)
- return 1;
+ return true;

check |= col;
}

- return 0;
+ return false;
}

static void twl4030_kp_scan(struct twl4030_keypad *kp, bool release_all)
@@ -224,7 +228,8 @@ static void twl4030_kp_scan(struct twl4030_keypad *kp, bool release_all)
if (!changed)
continue;

- for (col = 0; col < kp->n_cols; col++) {
+ /* Extra column handles "all gnd" rows */
+ for (col = 0; col < kp->n_cols + 1; col++) {
int code;

if (!(changed & (1 << col)))
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 525b9b9..ba09e4d 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -166,6 +166,13 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
},
},
{
+ /* Gigabyte Spring Peak - defines wrong chassis type */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Spring Peak"),
+ },
+ },
+ {
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv9700"),
diff --git a/drivers/media/dvb/dvb-core/dvb_net.c b/drivers/media/dvb/dvb-core/dvb_net.c
index dddfc46..55e591d 100644
--- a/drivers/media/dvb/dvb-core/dvb_net.c
+++ b/drivers/media/dvb/dvb-core/dvb_net.c
@@ -350,6 +350,7 @@ static void dvb_net_ule( struct net_device *dev, const u8 *buf, size_t buf_len )
const u8 *ts, *ts_end, *from_where = NULL;
u8 ts_remain = 0, how_much = 0, new_ts = 1;
struct ethhdr *ethh = NULL;
+ bool error = false;

#ifdef ULE_DEBUG
/* The code inside ULE_DEBUG keeps a history of the last 100 TS cells processed. */
@@ -459,10 +460,16 @@ static void dvb_net_ule( struct net_device *dev, const u8 *buf, size_t buf_len )

/* Drop partly decoded SNDU, reset state, resync on PUSI. */
if (priv->ule_skb) {
- dev_kfree_skb( priv->ule_skb );
+ error = true;
+ dev_kfree_skb(priv->ule_skb);
+ }
+
+ if (error || priv->ule_sndu_remain) {
dev->stats.rx_errors++;
dev->stats.rx_frame_errors++;
+ error = false;
}
+
reset_ule(priv);
priv->need_pusi = 1;
continue;
@@ -534,6 +541,7 @@ static void dvb_net_ule( struct net_device *dev, const u8 *buf, size_t buf_len )
from_where += 2;
}

+ priv->ule_sndu_remain = priv->ule_sndu_len + 2;
/*
* State of current TS:
* ts_remain (remaining bytes in the current TS cell)
@@ -543,6 +551,7 @@ static void dvb_net_ule( struct net_device *dev, const u8 *buf, size_t buf_len )
*/
switch (ts_remain) {
case 1:
+ priv->ule_sndu_remain--;
priv->ule_sndu_type = from_where[0] << 8;
priv->ule_sndu_type_1 = 1; /* first byte of ule_type is set. */
ts_remain -= 1; from_where += 1;
@@ -556,6 +565,7 @@ static void dvb_net_ule( struct net_device *dev, const u8 *buf, size_t buf_len )
default: /* complete ULE header is present in current TS. */
/* Extract ULE type field. */
if (priv->ule_sndu_type_1) {
+ priv->ule_sndu_type_1 = 0;
priv->ule_sndu_type |= from_where[0];
from_where += 1; /* points to payload start. */
ts_remain -= 1;
diff --git a/drivers/media/dvb/ttpci/Kconfig b/drivers/media/dvb/ttpci/Kconfig
index d8d4214..32a7ec6 100644
--- a/drivers/media/dvb/ttpci/Kconfig
+++ b/drivers/media/dvb/ttpci/Kconfig
@@ -68,13 +68,14 @@ config DVB_BUDGET
select DVB_VES1820 if !DVB_FE_CUSTOMISE
select DVB_L64781 if !DVB_FE_CUSTOMISE
select DVB_TDA8083 if !DVB_FE_CUSTOMISE
- select DVB_TDA10021 if !DVB_FE_CUSTOMISE
- select DVB_TDA10023 if !DVB_FE_CUSTOMISE
select DVB_S5H1420 if !DVB_FE_CUSTOMISE
select DVB_TDA10086 if !DVB_FE_CUSTOMISE
select DVB_TDA826X if !DVB_FE_CUSTOMISE
select DVB_LNBP21 if !DVB_FE_CUSTOMISE
select DVB_TDA1004X if !DVB_FE_CUSTOMISE
+ select DVB_ISL6423 if !DVB_FE_CUSTOMISE
+ select DVB_STV090x if !DVB_FE_CUSTOMISE
+ select DVB_STV6110x if !DVB_FE_CUSTOMISE
help
Support for simple SAA7146 based DVB cards (so called Budget-
or Nova-PCI cards) without onboard MPEG2 decoder, and without
diff --git a/drivers/media/video/cx23885/cx23885-i2c.c b/drivers/media/video/cx23885/cx23885-i2c.c
index 4172cb3..d4746e0 100644
--- a/drivers/media/video/cx23885/cx23885-i2c.c
+++ b/drivers/media/video/cx23885/cx23885-i2c.c
@@ -365,7 +365,17 @@ int cx23885_i2c_register(struct cx23885_i2c *bus)

memset(&info, 0, sizeof(struct i2c_board_info));
strlcpy(info.type, "ir_video", I2C_NAME_SIZE);
- i2c_new_probed_device(&bus->i2c_adap, &info, addr_list);
+ /*
+ * We can't call i2c_new_probed_device() because it uses
+ * quick writes for probing and the IR receiver device only
+ * replies to reads.
+ */
+ if (i2c_smbus_xfer(&bus->i2c_adap, addr_list[0], 0,
+ I2C_SMBUS_READ, 0, I2C_SMBUS_QUICK,
+ NULL) >= 0) {
+ info.addr = addr_list[0];
+ i2c_new_device(&bus->i2c_adap, &info);
+ }
}

return bus->i2c_rc;
diff --git a/drivers/media/video/cx88/cx88-i2c.c b/drivers/media/video/cx88/cx88-i2c.c
index ee1ca39..fb39f11 100644
--- a/drivers/media/video/cx88/cx88-i2c.c
+++ b/drivers/media/video/cx88/cx88-i2c.c
@@ -188,10 +188,24 @@ int cx88_i2c_init(struct cx88_core *core, struct pci_dev *pci)
0x18, 0x6b, 0x71,
I2C_CLIENT_END
};
+ const unsigned short *addrp;

memset(&info, 0, sizeof(struct i2c_board_info));
strlcpy(info.type, "ir_video", I2C_NAME_SIZE);
- i2c_new_probed_device(&core->i2c_adap, &info, addr_list);
+ /*
+ * We can't call i2c_new_probed_device() because it uses
+ * quick writes for probing and at least some R receiver
+ * devices only reply to reads.
+ */
+ for (addrp = addr_list; *addrp != I2C_CLIENT_END; addrp++) {
+ if (i2c_smbus_xfer(&core->i2c_adap, *addrp, 0,
+ I2C_SMBUS_READ, 0,
+ I2C_SMBUS_QUICK, NULL) >= 0) {
+ info.addr = *addrp;
+ i2c_new_device(&core->i2c_adap, &info);
+ break;
+ }
+ }
}
return core->i2c_rc;
}
diff --git a/drivers/media/video/uvc/uvc_driver.c b/drivers/media/video/uvc/uvc_driver.c
index 8756be5..450ac70 100644
--- a/drivers/media/video/uvc/uvc_driver.c
+++ b/drivers/media/video/uvc/uvc_driver.c
@@ -58,6 +58,11 @@ static struct uvc_format_desc uvc_fmts[] = {
.fcc = V4L2_PIX_FMT_YUYV,
},
{
+ .name = "YUV 4:2:2 (YUYV)",
+ .guid = UVC_GUID_FORMAT_YUY2_ISIGHT,
+ .fcc = V4L2_PIX_FMT_YUYV,
+ },
+ {
.name = "YUV 4:2:0 (NV12)",
.guid = UVC_GUID_FORMAT_NV12,
.fcc = V4L2_PIX_FMT_NV12,
@@ -83,11 +88,16 @@ static struct uvc_format_desc uvc_fmts[] = {
.fcc = V4L2_PIX_FMT_UYVY,
},
{
- .name = "Greyscale",
+ .name = "Greyscale (8-bit)",
.guid = UVC_GUID_FORMAT_Y800,
.fcc = V4L2_PIX_FMT_GREY,
},
{
+ .name = "Greyscale (16-bit)",
+ .guid = UVC_GUID_FORMAT_Y16,
+ .fcc = V4L2_PIX_FMT_Y16,
+ },
+ {
.name = "RGB Bayer",
.guid = UVC_GUID_FORMAT_BY8,
.fcc = V4L2_PIX_FMT_SBGGR8,
@@ -2048,6 +2058,15 @@ static struct usb_device_id uvc_ids[] = {
.bInterfaceSubClass = 1,
.bInterfaceProtocol = 0,
.driver_info = UVC_QUIRK_STREAM_NO_FID },
+ /* Syntek (Packard Bell EasyNote MX52 */
+ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE
+ | USB_DEVICE_ID_MATCH_INT_INFO,
+ .idVendor = 0x174f,
+ .idProduct = 0x8a12,
+ .bInterfaceClass = USB_CLASS_VIDEO,
+ .bInterfaceSubClass = 1,
+ .bInterfaceProtocol = 0,
+ .driver_info = UVC_QUIRK_STREAM_NO_FID },
/* Syntek (Asus F9SG) */
{ .match_flags = USB_DEVICE_ID_MATCH_DEVICE
| USB_DEVICE_ID_MATCH_INT_INFO,
@@ -2112,6 +2131,15 @@ static struct usb_device_id uvc_ids[] = {
.bInterfaceSubClass = 1,
.bInterfaceProtocol = 0,
.driver_info = UVC_QUIRK_PROBE_MINMAX },
+ /* Arkmicro unbranded */
+ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE
+ | USB_DEVICE_ID_MATCH_INT_INFO,
+ .idVendor = 0x18ec,
+ .idProduct = 0x3290,
+ .bInterfaceClass = USB_CLASS_VIDEO,
+ .bInterfaceSubClass = 1,
+ .bInterfaceProtocol = 0,
+ .driver_info = UVC_QUIRK_PROBE_DEF },
/* Bodelin ProScopeHR */
{ .match_flags = USB_DEVICE_ID_MATCH_DEVICE
| USB_DEVICE_ID_MATCH_DEV_HI
diff --git a/drivers/media/video/uvc/uvcvideo.h b/drivers/media/video/uvc/uvcvideo.h
index e7958aa..64007b9 100644
--- a/drivers/media/video/uvc/uvcvideo.h
+++ b/drivers/media/video/uvc/uvcvideo.h
@@ -112,6 +112,9 @@ struct uvc_xu_control {
#define UVC_GUID_FORMAT_YUY2 \
{ 'Y', 'U', 'Y', '2', 0x00, 0x00, 0x10, 0x00, \
0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_YUY2_ISIGHT \
+ { 'Y', 'U', 'Y', '2', 0x00, 0x00, 0x10, 0x00, \
+ 0x80, 0x00, 0x00, 0x00, 0x00, 0x38, 0x9b, 0x71}
#define UVC_GUID_FORMAT_NV12 \
{ 'N', 'V', '1', '2', 0x00, 0x00, 0x10, 0x00, \
0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
@@ -127,11 +130,13 @@ struct uvc_xu_control {
#define UVC_GUID_FORMAT_Y800 \
{ 'Y', '8', '0', '0', 0x00, 0x00, 0x10, 0x00, \
0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Y16 \
+ { 'Y', '1', '6', ' ', 0x00, 0x00, 0x10, 0x00, \
+ 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
#define UVC_GUID_FORMAT_BY8 \
{ 'B', 'Y', '8', ' ', 0x00, 0x00, 0x10, 0x00, \
0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}

-
/* ------------------------------------------------------------------------
* Driver specific constants.
*/
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index 50997d2..676cd0c 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -372,6 +372,26 @@ static int __devinit sdhci_s3c_probe(struct platform_device *pdev)

static int __devexit sdhci_s3c_remove(struct platform_device *pdev)
{
+ struct sdhci_host *host = platform_get_drvdata(pdev);
+ struct sdhci_s3c *sc = sdhci_priv(host);
+ int ptr;
+
+ sdhci_remove_host(host, 1);
+
+ for (ptr = 0; ptr < 3; ptr++) {
+ clk_disable(sc->clk_bus[ptr]);
+ clk_put(sc->clk_bus[ptr]);
+ }
+ clk_disable(sc->clk_io);
+ clk_put(sc->clk_io);
+
+ iounmap(host->ioaddr);
+ release_resource(sc->ioarea);
+ kfree(sc->ioarea);
+
+ sdhci_free_host(host);
+ platform_set_drvdata(pdev, NULL);
+
return 0;
}

diff --git a/drivers/net/cpmac.c b/drivers/net/cpmac.c
index 61f9da2..1cace00 100644
--- a/drivers/net/cpmac.c
+++ b/drivers/net/cpmac.c
@@ -1176,7 +1176,8 @@ static int __devinit cpmac_probe(struct platform_device *pdev)
if (netif_msg_drv(priv))
printk(KERN_ERR "%s: Could not attach to PHY\n",
dev->name);
- return PTR_ERR(priv->phy);
+ rc = PTR_ERR(priv->phy);
+ goto fail;
}

if ((rc = register_netdev(dev))) {
diff --git a/drivers/net/cxgb3/ael1002.c b/drivers/net/cxgb3/ael1002.c
index 5248f9e..35cd367 100644
--- a/drivers/net/cxgb3/ael1002.c
+++ b/drivers/net/cxgb3/ael1002.c
@@ -934,7 +934,7 @@ static struct cphy_ops xaui_direct_ops = {
int t3_xaui_direct_phy_prep(struct cphy *phy, struct adapter *adapter,
int phy_addr, const struct mdio_ops *mdio_ops)
{
- cphy_init(phy, adapter, MDIO_PRTAD_NONE, &xaui_direct_ops, mdio_ops,
+ cphy_init(phy, adapter, phy_addr, &xaui_direct_ops, mdio_ops,
SUPPORTED_10000baseT_Full | SUPPORTED_AUI | SUPPORTED_TP,
"10GBASE-CX4");
return 0;
diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c
index 31b8bef..3f5eb81 100644
--- a/drivers/net/dm9000.c
+++ b/drivers/net/dm9000.c
@@ -471,17 +471,13 @@ static uint32_t dm9000_get_rx_csum(struct net_device *dev)
return dm->rx_csum;
}

-static int dm9000_set_rx_csum(struct net_device *dev, uint32_t data)
+static int dm9000_set_rx_csum_unlocked(struct net_device *dev, uint32_t data)
{
board_info_t *dm = to_dm9000_board(dev);
- unsigned long flags;

if (dm->can_csum) {
dm->rx_csum = data;
-
- spin_lock_irqsave(&dm->lock, flags);
iow(dm, DM9000_RCSR, dm->rx_csum ? RCSR_CSUM : 0);
- spin_unlock_irqrestore(&dm->lock, flags);

return 0;
}
@@ -489,6 +485,19 @@ static int dm9000_set_rx_csum(struct net_device *dev, uint32_t data)
return -EOPNOTSUPP;
}

+static int dm9000_set_rx_csum(struct net_device *dev, uint32_t data)
+{
+ board_info_t *dm = to_dm9000_board(dev);
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&dm->lock, flags);
+ ret = dm9000_set_rx_csum_unlocked(dev, data);
+ spin_unlock_irqrestore(&dm->lock, flags);
+
+ return ret;
+}
+
static int dm9000_set_tx_csum(struct net_device *dev, uint32_t data)
{
board_info_t *dm = to_dm9000_board(dev);
@@ -667,7 +676,7 @@ static unsigned char dm9000_type_to_char(enum dm9000_type type)
* Set DM9000 multicast address
*/
static void
-dm9000_hash_table(struct net_device *dev)
+dm9000_hash_table_unlocked(struct net_device *dev)
{
board_info_t *db = netdev_priv(dev);
struct dev_mc_list *mcptr = dev->mc_list;
@@ -676,12 +685,9 @@ dm9000_hash_table(struct net_device *dev)
u32 hash_val;
u16 hash_table[4];
u8 rcr = RCR_DIS_LONG | RCR_DIS_CRC | RCR_RXEN;
- unsigned long flags;

dm9000_dbg(db, 1, "entering %s\n", __func__);

- spin_lock_irqsave(&db->lock, flags);
-
for (i = 0, oft = DM9000_PAR; i < 6; i++, oft++)
iow(db, oft, dev->dev_addr[i]);

@@ -711,6 +717,16 @@ dm9000_hash_table(struct net_device *dev)
}

iow(db, DM9000_RCR, rcr);
+}
+
+static void
+dm9000_hash_table(struct net_device *dev)
+{
+ board_info_t *db = netdev_priv(dev);
+ unsigned long flags;
+
+ spin_lock_irqsave(&db->lock, flags);
+ dm9000_hash_table_unlocked(dev);
spin_unlock_irqrestore(&db->lock, flags);
}

@@ -729,7 +745,7 @@ dm9000_init_dm9000(struct net_device *dev)
db->io_mode = ior(db, DM9000_ISR) >> 6; /* ISR bit7:6 keeps I/O mode */

/* Checksum mode */
- dm9000_set_rx_csum(dev, db->rx_csum);
+ dm9000_set_rx_csum_unlocked(dev, db->rx_csum);

/* GPIO0 on pre-activate PHY */
iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */
@@ -749,7 +765,7 @@ dm9000_init_dm9000(struct net_device *dev)
iow(db, DM9000_ISR, ISR_CLR_STATUS); /* Clear interrupt status */

/* Set address filter table */
- dm9000_hash_table(dev);
+ dm9000_hash_table_unlocked(dev);

imr = IMR_PAR | IMR_PTM | IMR_PRM;
if (db->type != TYPE_DM9000E)
diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c
index 3116601..7cd446d 100644
--- a/drivers/net/forcedeth.c
+++ b/drivers/net/forcedeth.c
@@ -5900,7 +5900,7 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i
/* Limit the number of tx's outstanding for hw bug */
if (id->driver_data & DEV_NEED_TX_LIMIT) {
np->tx_limit = 1;
- if ((id->driver_data & DEV_NEED_TX_LIMIT2) &&
+ if (((id->driver_data & DEV_NEED_TX_LIMIT2) == DEV_NEED_TX_LIMIT2) &&
pci_dev->revision >= 0xA2)
np->tx_limit = 0;
}
diff --git a/drivers/net/igb/e1000_82575.c b/drivers/net/igb/e1000_82575.c
index c6d97eb..33352ff 100644
--- a/drivers/net/igb/e1000_82575.c
+++ b/drivers/net/igb/e1000_82575.c
@@ -1168,9 +1168,18 @@ static s32 igb_read_mac_addr_82575(struct e1000_hw *hw)
{
s32 ret_val = 0;

- if (igb_check_alt_mac_addr(hw))
- ret_val = igb_read_mac_addr(hw);
+ /*
+ * If there's an alternate MAC address place it in RAR0
+ * so that it will override the Si installed default perm
+ * address.
+ */
+ ret_val = igb_check_alt_mac_addr(hw);
+ if (ret_val)
+ goto out;
+
+ ret_val = igb_read_mac_addr(hw);

+out:
return ret_val;
}

diff --git a/drivers/net/igb/e1000_hw.h b/drivers/net/igb/e1000_hw.h
index 1a23aeb..72081df 100644
--- a/drivers/net/igb/e1000_hw.h
+++ b/drivers/net/igb/e1000_hw.h
@@ -53,6 +53,8 @@ struct e1000_hw;

#define E1000_FUNC_1 1

+#define E1000_ALT_MAC_ADDRESS_OFFSET_LAN1 3
+
enum e1000_mac_type {
e1000_undefined = 0,
e1000_82575,
diff --git a/drivers/net/igb/e1000_mac.c b/drivers/net/igb/e1000_mac.c
index 7d76bb0..d4fa82c 100644
--- a/drivers/net/igb/e1000_mac.c
+++ b/drivers/net/igb/e1000_mac.c
@@ -185,13 +185,12 @@ s32 igb_check_alt_mac_addr(struct e1000_hw *hw)
}

if (nvm_alt_mac_addr_offset == 0xFFFF) {
- ret_val = -(E1000_NOT_IMPLEMENTED);
+ /* There is no Alternate MAC Address */
goto out;
}

if (hw->bus.func == E1000_FUNC_1)
- nvm_alt_mac_addr_offset += ETH_ALEN/sizeof(u16);
-
+ nvm_alt_mac_addr_offset += E1000_ALT_MAC_ADDRESS_OFFSET_LAN1;
for (i = 0; i < ETH_ALEN; i += 2) {
offset = nvm_alt_mac_addr_offset + (i >> 1);
ret_val = hw->nvm.ops.read(hw, offset, 1, &nvm_data);
@@ -206,14 +205,16 @@ s32 igb_check_alt_mac_addr(struct e1000_hw *hw)

/* if multicast bit is set, the alternate address will not be used */
if (alt_mac_addr[0] & 0x01) {
- ret_val = -(E1000_NOT_IMPLEMENTED);
+ hw_dbg("Ignoring Alternate Mac Address with MC bit set\n");
goto out;
}

- for (i = 0; i < ETH_ALEN; i++)
- hw->mac.addr[i] = hw->mac.perm_addr[i] = alt_mac_addr[i];
-
- hw->mac.ops.rar_set(hw, hw->mac.perm_addr, 0);
+ /*
+ * We have a valid alternate MAC address, and we want to treat it the
+ * same as the normal permanent MAC address stored by the HW into the
+ * RAR. Do this by mapping this address into RAR0.
+ */
+ hw->mac.ops.rar_set(hw, alt_mac_addr, 0);

out:
return ret_val;
diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c
index 77125b5..a17aaee 100644
--- a/drivers/net/sky2.c
+++ b/drivers/net/sky2.c
@@ -704,11 +704,24 @@ static void sky2_phy_power_down(struct sky2_hw *hw, unsigned port)
sky2_write8(hw, B2_TST_CTRL1, TST_CFG_WRITE_OFF);
}

+/* Enable Rx/Tx */
+static void sky2_enable_rx_tx(struct sky2_port *sky2)
+{
+ struct sky2_hw *hw = sky2->hw;
+ unsigned port = sky2->port;
+ u16 reg;
+
+ reg = gma_read16(hw, port, GM_GP_CTRL);
+ reg |= GM_GPCR_RX_ENA | GM_GPCR_TX_ENA;
+ gma_write16(hw, port, GM_GP_CTRL, reg);
+}
+
/* Force a renegotiation */
static void sky2_phy_reinit(struct sky2_port *sky2)
{
spin_lock_bh(&sky2->phy_lock);
sky2_phy_init(sky2->hw, sky2->port);
+ sky2_enable_rx_tx(sky2);
spin_unlock_bh(&sky2->phy_lock);
}

@@ -1929,7 +1942,6 @@ static void sky2_link_up(struct sky2_port *sky2)
{
struct sky2_hw *hw = sky2->hw;
unsigned port = sky2->port;
- u16 reg;
static const char *fc_name[] = {
[FC_NONE] = "none",
[FC_TX] = "tx",
@@ -1937,10 +1949,7 @@ static void sky2_link_up(struct sky2_port *sky2)
[FC_BOTH] = "both",
};

- /* enable Rx/Tx */
- reg = gma_read16(hw, port, GM_GP_CTRL);
- reg |= GM_GPCR_RX_ENA | GM_GPCR_TX_ENA;
- gma_write16(hw, port, GM_GP_CTRL, reg);
+ sky2_enable_rx_tx(sky2);

gm_phy_write(hw, port, PHY_MARV_INT_MASK, PHY_M_DEF_MSK);

diff --git a/drivers/net/wireless/ath/ath5k/attach.c b/drivers/net/wireless/ath/ath5k/attach.c
index 71a1bd25..88663df 100644
--- a/drivers/net/wireless/ath/ath5k/attach.c
+++ b/drivers/net/wireless/ath/ath5k/attach.c
@@ -133,6 +133,7 @@ struct ath5k_hw *ath5k_hw_attach(struct ath5k_softc *sc)
ah->ah_cw_min = AR5K_TUNE_CWMIN;
ah->ah_limit_tx_retries = AR5K_INIT_TX_RETRY;
ah->ah_software_retry = false;
+ ah->ah_current_channel = &sc->channels[0];

/*
* Find the mac version
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index cefbfb9..7ee61d4 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -1818,11 +1818,6 @@ ath5k_tasklet_rx(unsigned long data)
return;
}

- if (unlikely(rs.rs_more)) {
- ATH5K_WARN(sc, "unsupported jumbo\n");
- goto next;
- }
-
if (unlikely(rs.rs_status)) {
if (rs.rs_status & AR5K_RXERR_PHY)
goto next;
@@ -1852,6 +1847,8 @@ ath5k_tasklet_rx(unsigned long data)
sc->opmode != NL80211_IFTYPE_MONITOR)
goto next;
}
+ if (unlikely(rs.rs_more))
+ goto next;
accept:
next_skb = ath5k_rx_skb_alloc(sc, &next_skb_addr);

diff --git a/drivers/net/wireless/ath/ath9k/initvals.h b/drivers/net/wireless/ath/ath9k/initvals.h
index 8622265..a21c214 100644
--- a/drivers/net/wireless/ath/ath9k/initvals.h
+++ b/drivers/net/wireless/ath/ath9k/initvals.h
@@ -2762,7 +2762,7 @@ static const u32 ar9280Common_9280_2[][2] = {
{ 0x00008258, 0x00000000 },
{ 0x0000825c, 0x400000ff },
{ 0x00008260, 0x00080922 },
- { 0x00008264, 0xa8a00010 },
+ { 0x00008264, 0x88a00010 },
{ 0x00008270, 0x00000000 },
{ 0x00008274, 0x40000000 },
{ 0x00008278, 0x003e4180 },
@@ -3935,7 +3935,7 @@ static const u_int32_t ar9285Common_9285[][2] = {
{ 0x00008258, 0x00000000 },
{ 0x0000825c, 0x400000ff },
{ 0x00008260, 0x00080922 },
- { 0x00008264, 0xa8a00010 },
+ { 0x00008264, 0x88a00010 },
{ 0x00008270, 0x00000000 },
{ 0x00008274, 0x40000000 },
{ 0x00008278, 0x003e4180 },
@@ -5072,7 +5072,7 @@ static const u_int32_t ar9287Common_9287_1_0[][2] = {
{ 0x00008258, 0x00000000 },
{ 0x0000825c, 0x400000ff },
{ 0x00008260, 0x00080922 },
- { 0x00008264, 0xa8a00010 },
+ { 0x00008264, 0x88a00010 },
{ 0x00008270, 0x00000000 },
{ 0x00008274, 0x40000000 },
{ 0x00008278, 0x003e4180 },
@@ -6864,7 +6864,7 @@ static const u_int32_t ar9271Common_9271_1_0[][2] = {
{ 0x00008258, 0x00000000 },
{ 0x0000825c, 0x400000ff },
{ 0x00008260, 0x00080922 },
- { 0x00008264, 0xa8a00010 },
+ { 0x00008264, 0x88a00010 },
{ 0x00008270, 0x00000000 },
{ 0x00008274, 0x40000000 },
{ 0x00008278, 0x003e4180 },
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 087b7e5..0c349ce 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1538,6 +1538,8 @@ bad_no_ah:

void ath_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw)
{
+ struct ath_hw *ah = sc->sc_ah;
+
hw->flags = IEEE80211_HW_RX_INCLUDES_FCS |
IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING |
IEEE80211_HW_SIGNAL_DBM |
@@ -1558,7 +1560,10 @@ void ath_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw)
BIT(NL80211_IFTYPE_ADHOC) |
BIT(NL80211_IFTYPE_MESH_POINT);

- hw->wiphy->ps_default = false;
+ if (AR_SREV_5416(ah))
+ hw->wiphy->ps_default = false;
+ else
+ hw->wiphy->ps_default = true;

hw->queues = 4;
hw->max_rates = 4;
diff --git a/drivers/net/wireless/hostap/hostap_cs.c b/drivers/net/wireless/hostap/hostap_cs.c
index ad8eab4..b4ff1dc 100644
--- a/drivers/net/wireless/hostap/hostap_cs.c
+++ b/drivers/net/wireless/hostap/hostap_cs.c
@@ -626,6 +626,7 @@ static int prism2_config(struct pcmcia_device *link)
int ret = 1;
int last_fn, last_ret;
struct hostap_cs_priv *hw_priv;
+ unsigned long flags;

PDEBUG(DEBUG_FLOW, "prism2_config()\n");

@@ -661,6 +662,12 @@ static int prism2_config(struct pcmcia_device *link)
link->dev_node = &hw_priv->node;

/*
+ * Make sure the IRQ handler cannot proceed until at least
+ * dev->base_addr is initialized.
+ */
+ spin_lock_irqsave(&local->irq_init_lock, flags);
+
+ /*
* Allocate an interrupt line. Note that this does not assign a
* handler to the interrupt, unless the 'Handler' member of the
* irq structure is initialized.
@@ -686,6 +693,8 @@ static int prism2_config(struct pcmcia_device *link)
dev->irq = link->irq.AssignedIRQ;
dev->base_addr = link->io.BasePort1;

+ spin_unlock_irqrestore(&local->irq_init_lock, flags);
+
/* Finally, report what we've done */
printk(KERN_INFO "%s: index 0x%02x: ",
dev_info, link->conf.ConfigIndex);
@@ -715,6 +724,7 @@ static int prism2_config(struct pcmcia_device *link)
return ret;

cs_failed:
+ spin_unlock_irqrestore(&local->irq_init_lock, flags);
cs_error(link, last_fn, last_ret);

failed:
diff --git a/drivers/net/wireless/hostap/hostap_hw.c b/drivers/net/wireless/hostap/hostap_hw.c
index ff9b5c8..2f999fc 100644
--- a/drivers/net/wireless/hostap/hostap_hw.c
+++ b/drivers/net/wireless/hostap/hostap_hw.c
@@ -2621,6 +2621,18 @@ static irqreturn_t prism2_interrupt(int irq, void *dev_id)
iface = netdev_priv(dev);
local = iface->local;

+ /* Detect early interrupt before driver is fully configued */
+ spin_lock(&local->irq_init_lock);
+ if (!dev->base_addr) {
+ if (net_ratelimit()) {
+ printk(KERN_DEBUG "%s: Interrupt, but dev not configured\n",
+ dev->name);
+ }
+ spin_unlock(&local->irq_init_lock);
+ return IRQ_HANDLED;
+ }
+ spin_unlock(&local->irq_init_lock);
+
prism2_io_debug_add(dev, PRISM2_IO_DEBUG_CMD_INTERRUPT, 0, 0);

if (local->func->card_present && !local->func->card_present(local)) {
@@ -3138,6 +3150,7 @@ prism2_init_local_data(struct prism2_helper_functions *funcs, int card_idx,
spin_lock_init(&local->cmdlock);
spin_lock_init(&local->baplock);
spin_lock_init(&local->lock);
+ spin_lock_init(&local->irq_init_lock);
mutex_init(&local->rid_bap_mtx);

if (card_idx < 0 || card_idx >= MAX_PARM_DEVICES)
diff --git a/drivers/net/wireless/hostap/hostap_wlan.h b/drivers/net/wireless/hostap/hostap_wlan.h
index 3d23891..1ba33be 100644
--- a/drivers/net/wireless/hostap/hostap_wlan.h
+++ b/drivers/net/wireless/hostap/hostap_wlan.h
@@ -654,7 +654,7 @@ struct local_info {
rwlock_t iface_lock; /* hostap_interfaces read lock; use write lock
* when removing entries from the list.
* TX and RX paths can use read lock. */
- spinlock_t cmdlock, baplock, lock;
+ spinlock_t cmdlock, baplock, lock, irq_init_lock;
struct mutex rid_bap_mtx;
u16 infofid; /* MAC buffer id for info frame */
/* txfid, intransmitfid, next_txtid, and next_alloc are protected by
diff --git a/drivers/net/wireless/iwlwifi/iwl-scan.c b/drivers/net/wireless/iwlwifi/iwl-scan.c
index 71c0ad4..db2946e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-scan.c
+++ b/drivers/net/wireless/iwlwifi/iwl-scan.c
@@ -799,6 +799,7 @@ void iwl_bg_abort_scan(struct work_struct *work)

mutex_lock(&priv->mutex);

+ cancel_delayed_work_sync(&priv->scan_check);
set_bit(STATUS_SCAN_ABORTING, &priv->status);
iwl_send_scan_abort(priv);

diff --git a/drivers/net/wireless/iwlwifi/iwl-tx.c b/drivers/net/wireless/iwlwifi/iwl-tx.c
index 7f15b7e..d21c06e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-tx.c
+++ b/drivers/net/wireless/iwlwifi/iwl-tx.c
@@ -1479,6 +1479,11 @@ void iwl_rx_reply_compressed_ba(struct iwl_priv *priv,
sta_id = ba_resp->sta_id;
tid = ba_resp->tid;
agg = &priv->stations[sta_id].tid[tid].agg;
+ if (unlikely(agg->txq_id != scd_flow)) {
+ IWL_ERR(priv, "BA scd_flow %d does not match txq_id %d\n",
+ scd_flow, agg->txq_id);
+ return;
+ }

/* Find index just before block-ack window */
index = iwl_queue_dec_wrap(ba_resp_scd_ssn & 0xff, txq->q.n_bd);
diff --git a/drivers/net/wireless/libertas/if_sdio.c b/drivers/net/wireless/libertas/if_sdio.c
index 485a8d4..f876d02 100644
--- a/drivers/net/wireless/libertas/if_sdio.c
+++ b/drivers/net/wireless/libertas/if_sdio.c
@@ -34,6 +34,8 @@
#include <linux/mmc/card.h>
#include <linux/mmc/sdio_func.h>
#include <linux/mmc/sdio_ids.h>
+#include <linux/mmc/sdio.h>
+#include <linux/mmc/host.h>

#include "host.h"
#include "decl.h"
@@ -883,6 +885,7 @@ static int if_sdio_probe(struct sdio_func *func,
int ret, i;
unsigned int model;
struct if_sdio_packet *packet;
+ struct mmc_host *host = func->card->host;

lbs_deb_enter(LBS_DEB_SDIO);

@@ -963,6 +966,25 @@ static int if_sdio_probe(struct sdio_func *func,
if (ret)
goto disable;

+ /* For 1-bit transfers to the 8686 model, we need to enable the
+ * interrupt flag in the CCCR register. Set the MMC_QUIRK_LENIENT_FN0
+ * bit to allow access to non-vendor registers. */
+ if ((card->model == IF_SDIO_MODEL_8686) &&
+ (host->caps & MMC_CAP_SDIO_IRQ) &&
+ (host->ios.bus_width == MMC_BUS_WIDTH_1)) {
+ u8 reg;
+
+ func->card->quirks |= MMC_QUIRK_LENIENT_FN0;
+ reg = sdio_f0_readb(func, SDIO_CCCR_IF, &ret);
+ if (ret)
+ goto release_int;
+
+ reg |= SDIO_BUS_ECSI;
+ sdio_f0_writeb(func, reg, SDIO_CCCR_IF, &ret);
+ if (ret)
+ goto release_int;
+ }
+
card->ioport = sdio_readb(func, IF_SDIO_IOPORT, &ret);
if (ret)
goto release_int;
diff --git a/drivers/net/wireless/p54/p54pci.c b/drivers/net/wireless/p54/p54pci.c
index 7bafa83..3df13f5 100644
--- a/drivers/net/wireless/p54/p54pci.c
+++ b/drivers/net/wireless/p54/p54pci.c
@@ -40,6 +40,8 @@ static struct pci_device_id p54p_table[] __devinitdata = {
{ PCI_DEVICE(0x1260, 0x3877) },
/* Intersil PRISM Javelin/Xbow Wireless LAN adapter */
{ PCI_DEVICE(0x1260, 0x3886) },
+ /* Intersil PRISM Xbow Wireless LAN adapter (Symbol AP-300) */
+ { PCI_DEVICE(0x1260, 0xffff) },
{ },
};

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 595d03a..812d4ac 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2046,6 +2046,7 @@ void pci_msi_off(struct pci_dev *dev)
pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
}
}
+EXPORT_SYMBOL_GPL(pci_msi_off);

#ifndef HAVE_ARCH_PCI_SET_DMA_MASK
/*
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index 329093e..c533b1c 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -752,6 +752,8 @@ static void eeepc_rfkill_hotplug(void)
struct pci_dev *dev;
struct pci_bus *bus;
bool blocked = eeepc_wlan_rfkill_blocked();
+ bool absent;
+ u32 l;

if (ehotk->wlan_rfkill)
rfkill_set_sw_state(ehotk->wlan_rfkill, blocked);
@@ -765,6 +767,22 @@ static void eeepc_rfkill_hotplug(void)
goto out_unlock;
}

+ if (pci_bus_read_config_dword(bus, 0, PCI_VENDOR_ID, &l)) {
+ pr_err("Unable to read PCI config space?\n");
+ goto out_unlock;
+ }
+ absent = (l == 0xffffffff);
+
+ if (blocked != absent) {
+ pr_warning("BIOS says wireless lan is %s, "
+ "but the pci device is %s\n",
+ blocked ? "blocked" : "unblocked",
+ absent ? "absent" : "present");
+ pr_warning("skipped wireless hotplug as probably "
+ "inappropriate for this model\n");
+ goto out_unlock;
+ }
+
if (!blocked) {
dev = pci_get_slot(bus, 0);
if (dev) {
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index eb99ee4..861d91d 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -775,7 +775,7 @@ static int __devinit ds1307_probe(struct i2c_client *client,

read_rtc:
/* read RTC registers */
- tmp = ds1307->read_block_data(ds1307->client, 0, 8, buf);
+ tmp = ds1307->read_block_data(ds1307->client, ds1307->offset, 8, buf);
if (tmp != 8) {
pr_debug("read error %d\n", tmp);
err = -EIO;
@@ -860,7 +860,7 @@ read_rtc:
if (ds1307->regs[DS1307_REG_HOUR] & DS1307_BIT_PM)
tmp += 12;
i2c_smbus_write_byte_data(client,
- DS1307_REG_HOUR,
+ ds1307->offset + DS1307_REG_HOUR,
bin2bcd(tmp));
}

diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index 0391d75..a5b8e7b 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -655,9 +655,9 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
/* Does this really need to be GFP_DMA? */
p = kmalloc(usg->sg[i].count,GFP_KERNEL|__GFP_DMA);
if(!p) {
- kfree (usg);
- dprintk((KERN_DEBUG"aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
+ dprintk((KERN_DEBUG "aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
usg->sg[i].count,i,usg->count));
+ kfree(usg);
rcode = -ENOMEM;
goto cleanup;
}
diff --git a/drivers/serial/cpm_uart/cpm_uart_core.c b/drivers/serial/cpm_uart/cpm_uart_core.c
index 300cea7..7feb902 100644
--- a/drivers/serial/cpm_uart/cpm_uart_core.c
+++ b/drivers/serial/cpm_uart/cpm_uart_core.c
@@ -930,6 +930,83 @@ static void cpm_uart_config_port(struct uart_port *port, int flags)
}
}

+#if defined(CONFIG_CONSOLE_POLL) || defined(CONFIG_SERIAL_CPM_CONSOLE)
+/*
+ * Write a string to the serial port
+ * Note that this is called with interrupts already disabled
+ */
+static void cpm_uart_early_write(struct uart_cpm_port *pinfo,
+ const char *string, u_int count)
+{
+ unsigned int i;
+ cbd_t __iomem *bdp, *bdbase;
+ unsigned char *cpm_outp_addr;
+
+ /* Get the address of the host memory buffer.
+ */
+ bdp = pinfo->tx_cur;
+ bdbase = pinfo->tx_bd_base;
+
+ /*
+ * Now, do each character. This is not as bad as it looks
+ * since this is a holding FIFO and not a transmitting FIFO.
+ * We could add the complexity of filling the entire transmit
+ * buffer, but we would just wait longer between accesses......
+ */
+ for (i = 0; i < count; i++, string++) {
+ /* Wait for transmitter fifo to empty.
+ * Ready indicates output is ready, and xmt is doing
+ * that, not that it is ready for us to send.
+ */
+ while ((in_be16(&bdp->cbd_sc) & BD_SC_READY) != 0)
+ ;
+
+ /* Send the character out.
+ * If the buffer address is in the CPM DPRAM, don't
+ * convert it.
+ */
+ cpm_outp_addr = cpm2cpu_addr(in_be32(&bdp->cbd_bufaddr),
+ pinfo);
+ *cpm_outp_addr = *string;
+
+ out_be16(&bdp->cbd_datlen, 1);
+ setbits16(&bdp->cbd_sc, BD_SC_READY);
+
+ if (in_be16(&bdp->cbd_sc) & BD_SC_WRAP)
+ bdp = bdbase;
+ else
+ bdp++;
+
+ /* if a LF, also do CR... */
+ if (*string == 10) {
+ while ((in_be16(&bdp->cbd_sc) & BD_SC_READY) != 0)
+ ;
+
+ cpm_outp_addr = cpm2cpu_addr(in_be32(&bdp->cbd_bufaddr),
+ pinfo);
+ *cpm_outp_addr = 13;
+
+ out_be16(&bdp->cbd_datlen, 1);
+ setbits16(&bdp->cbd_sc, BD_SC_READY);
+
+ if (in_be16(&bdp->cbd_sc) & BD_SC_WRAP)
+ bdp = bdbase;
+ else
+ bdp++;
+ }
+ }
+
+ /*
+ * Finally, Wait for transmitter & holding register to empty
+ * and restore the IER
+ */
+ while ((in_be16(&bdp->cbd_sc) & BD_SC_READY) != 0)
+ ;
+
+ pinfo->tx_cur = bdp;
+}
+#endif
+
#ifdef CONFIG_CONSOLE_POLL
/* Serial polling routines for writing and reading from the uart while
* in an interrupt or debug context.
@@ -999,7 +1076,7 @@ static void cpm_put_poll_char(struct uart_port *port,
static char ch[2];

ch[0] = (char)c;
- cpm_uart_early_write(pinfo->port.line, ch, 1);
+ cpm_uart_early_write(pinfo, ch, 1);
}
#endif /* CONFIG_CONSOLE_POLL */

@@ -1130,9 +1207,6 @@ static void cpm_uart_console_write(struct console *co, const char *s,
u_int count)
{
struct uart_cpm_port *pinfo = &cpm_uart_ports[co->index];
- unsigned int i;
- cbd_t __iomem *bdp, *bdbase;
- unsigned char *cp;
unsigned long flags;
int nolock = oops_in_progress;

@@ -1142,66 +1216,7 @@ static void cpm_uart_console_write(struct console *co, const char *s,
spin_lock_irqsave(&pinfo->port.lock, flags);
}

- /* Get the address of the host memory buffer.
- */
- bdp = pinfo->tx_cur;
- bdbase = pinfo->tx_bd_base;
-
- /*
- * Now, do each character. This is not as bad as it looks
- * since this is a holding FIFO and not a transmitting FIFO.
- * We could add the complexity of filling the entire transmit
- * buffer, but we would just wait longer between accesses......
- */
- for (i = 0; i < count; i++, s++) {
- /* Wait for transmitter fifo to empty.
- * Ready indicates output is ready, and xmt is doing
- * that, not that it is ready for us to send.
- */
- while ((in_be16(&bdp->cbd_sc) & BD_SC_READY) != 0)
- ;
-
- /* Send the character out.
- * If the buffer address is in the CPM DPRAM, don't
- * convert it.
- */
- cp = cpm2cpu_addr(in_be32(&bdp->cbd_bufaddr), pinfo);
- *cp = *s;
-
- out_be16(&bdp->cbd_datlen, 1);
- setbits16(&bdp->cbd_sc, BD_SC_READY);
-
- if (in_be16(&bdp->cbd_sc) & BD_SC_WRAP)
- bdp = bdbase;
- else
- bdp++;
-
- /* if a LF, also do CR... */
- if (*s == 10) {
- while ((in_be16(&bdp->cbd_sc) & BD_SC_READY) != 0)
- ;
-
- cp = cpm2cpu_addr(in_be32(&bdp->cbd_bufaddr), pinfo);
- *cp = 13;
-
- out_be16(&bdp->cbd_datlen, 1);
- setbits16(&bdp->cbd_sc, BD_SC_READY);
-
- if (in_be16(&bdp->cbd_sc) & BD_SC_WRAP)
- bdp = bdbase;
- else
- bdp++;
- }
- }
-
- /*
- * Finally, Wait for transmitter & holding register to empty
- * and restore the IER
- */
- while ((in_be16(&bdp->cbd_sc) & BD_SC_READY) != 0)
- ;
-
- pinfo->tx_cur = bdp;
+ cpm_uart_early_write(pinfo, s, count);

if (unlikely(nolock)) {
local_irq_restore(flags);
diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c
index 9681536..bbf1cb2 100644
--- a/drivers/ssb/driver_chipcommon.c
+++ b/drivers/ssb/driver_chipcommon.c
@@ -233,6 +233,9 @@ void ssb_chipcommon_init(struct ssb_chipcommon *cc)
{
if (!cc->dev)
return; /* We don't have a ChipCommon */
+ if (cc->dev->id.revision >= 11)
+ cc->status = chipco_read32(cc, SSB_CHIPCO_CHIPSTAT);
+ ssb_dprintk(KERN_INFO PFX "chipcommon status is 0x%x\n", cc->status);
ssb_pmu_init(cc);
chipco_powercontrol_init(cc);
ssb_chipco_set_clockmode(cc, SSB_CLKMODE_FAST);
diff --git a/drivers/ssb/driver_chipcommon_pmu.c b/drivers/ssb/driver_chipcommon_pmu.c
index 64abd11..8e194d5 100644
--- a/drivers/ssb/driver_chipcommon_pmu.c
+++ b/drivers/ssb/driver_chipcommon_pmu.c
@@ -495,9 +495,9 @@ static void ssb_pmu_resources_init(struct ssb_chipcommon *cc)
chipco_write32(cc, SSB_CHIPCO_PMU_MAXRES_MSK, max_msk);
}

+/* http://bcm-v4.sipsolutions.net/802.11/SSB/PmuInit */
void ssb_pmu_init(struct ssb_chipcommon *cc)
{
- struct ssb_bus *bus = cc->dev->bus;
u32 pmucap;

if (!(cc->capabilities & SSB_CHIPCO_CAP_PMU))
@@ -509,15 +509,12 @@ void ssb_pmu_init(struct ssb_chipcommon *cc)
ssb_dprintk(KERN_DEBUG PFX "Found rev %u PMU (capabilities 0x%08X)\n",
cc->pmu.rev, pmucap);

- if (cc->pmu.rev >= 1) {
- if ((bus->chip_id == 0x4325) && (bus->chip_rev < 2)) {
- chipco_mask32(cc, SSB_CHIPCO_PMU_CTL,
- ~SSB_CHIPCO_PMU_CTL_NOILPONW);
- } else {
- chipco_set32(cc, SSB_CHIPCO_PMU_CTL,
- SSB_CHIPCO_PMU_CTL_NOILPONW);
- }
- }
+ if (cc->pmu.rev == 1)
+ chipco_mask32(cc, SSB_CHIPCO_PMU_CTL,
+ ~SSB_CHIPCO_PMU_CTL_NOILPONW);
+ else
+ chipco_set32(cc, SSB_CHIPCO_PMU_CTL,
+ SSB_CHIPCO_PMU_CTL_NOILPONW);
ssb_pmu_pll_init(cc);
ssb_pmu_resources_init(cc);
}
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 9e50896..17a1781 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -22,6 +22,7 @@

#include "ssb_private.h"

+bool ssb_is_sprom_available(struct ssb_bus *bus);

/* Define the following to 1 to enable a printk on each coreswitch. */
#define SSB_VERBOSE_PCICORESWITCH_DEBUG 0
@@ -167,7 +168,7 @@ err_pci:
}

/* Get the word-offset for a SSB_SPROM_XXX define. */
-#define SPOFF(offset) (((offset) - SSB_SPROM_BASE) / sizeof(u16))
+#define SPOFF(offset) ((offset) / sizeof(u16))
/* Helper to extract some _offset, which is one of the SSB_SPROM_XXX defines. */
#define SPEX16(_outvar, _offset, _mask, _shift) \
out->_outvar = ((in[SPOFF(_offset)] & (_mask)) >> (_shift))
@@ -252,8 +253,13 @@ static int sprom_do_read(struct ssb_bus *bus, u16 *sprom)
{
int i;

+ /* Check if SPROM can be read */
+ if (ioread16(bus->mmio + bus->sprom_offset) == 0xFFFF) {
+ ssb_printk(KERN_ERR PFX "Unable to read SPROM\n");
+ return -ENODEV;
+ }
for (i = 0; i < bus->sprom_size; i++)
- sprom[i] = ioread16(bus->mmio + SSB_SPROM_BASE + (i * 2));
+ sprom[i] = ioread16(bus->mmio + bus->sprom_offset + (i * 2));

return 0;
}
@@ -284,7 +290,7 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
ssb_printk("75%%");
else if (i % 2)
ssb_printk(".");
- writew(sprom[i], bus->mmio + SSB_SPROM_BASE + (i * 2));
+ writew(sprom[i], bus->mmio + bus->sprom_offset + (i * 2));
mmiowb();
msleep(20);
}
@@ -620,21 +626,49 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
int err = -ENOMEM;
u16 *buf;

+ if (!ssb_is_sprom_available(bus)) {
+ ssb_printk(KERN_ERR PFX "No SPROM available!\n");
+ return -ENODEV;
+ }
+ if (bus->chipco.dev) { /* can be unavailible! */
+ /*
+ * get SPROM offset: SSB_SPROM_BASE1 except for
+ * chipcommon rev >= 31 or chip ID is 0x4312 and
+ * chipcommon status & 3 == 2
+ */
+ if (bus->chipco.dev->id.revision >= 31)
+ bus->sprom_offset = SSB_SPROM_BASE31;
+ else if (bus->chip_id == 0x4312 &&
+ (bus->chipco.status & 0x03) == 2)
+ bus->sprom_offset = SSB_SPROM_BASE31;
+ else
+ bus->sprom_offset = SSB_SPROM_BASE1;
+ } else {
+ bus->sprom_offset = SSB_SPROM_BASE1;
+ }
+ ssb_dprintk(KERN_INFO PFX "SPROM offset is 0x%x\n", bus->sprom_offset);
+
buf = kcalloc(SSB_SPROMSIZE_WORDS_R123, sizeof(u16), GFP_KERNEL);
if (!buf)
goto out;
bus->sprom_size = SSB_SPROMSIZE_WORDS_R123;
- sprom_do_read(bus, buf);
+ err = sprom_do_read(bus, buf);
+ if (err)
+ goto out_free;
err = sprom_check_crc(buf, bus->sprom_size);
if (err) {
/* try for a 440 byte SPROM - revision 4 and higher */
kfree(buf);
buf = kcalloc(SSB_SPROMSIZE_WORDS_R4, sizeof(u16),
GFP_KERNEL);
- if (!buf)
+ if (!buf) {
+ err = -ENOMEM;
goto out;
+ }
bus->sprom_size = SSB_SPROMSIZE_WORDS_R4;
- sprom_do_read(bus, buf);
+ err = sprom_do_read(bus, buf);
+ if (err)
+ goto out_free;
err = sprom_check_crc(buf, bus->sprom_size);
if (err) {
/* All CRC attempts failed.
diff --git a/drivers/ssb/sprom.c b/drivers/ssb/sprom.c
index eb70843..5f7154d 100644
--- a/drivers/ssb/sprom.c
+++ b/drivers/ssb/sprom.c
@@ -179,3 +179,18 @@ const struct ssb_sprom *ssb_get_fallback_sprom(void)
{
return fallback_sprom;
}
+
+/* http://bcm-v4.sipsolutions.net/802.11/IsSpromAvailable */
+bool ssb_is_sprom_available(struct ssb_bus *bus)
+{
+ /* status register only exists on chipcomon rev >= 11 and we need check
+ for >= 31 only */
+ /* this routine differs from specs as we do not access SPROM directly
+ on PCMCIA */
+ if (bus->bustype == SSB_BUSTYPE_PCI &&
+ bus->chipco.dev && /* can be unavailible! */
+ bus->chipco.dev->id.revision >= 31)
+ return bus->chipco.capabilities & SSB_CHIPCO_CAP_SPROM;
+
+ return true;
+}
diff --git a/drivers/staging/rtl8192su/r8192U_core.c b/drivers/staging/rtl8192su/r8192U_core.c
index 88644ef..6d52d6a 100644
--- a/drivers/staging/rtl8192su/r8192U_core.c
+++ b/drivers/staging/rtl8192su/r8192U_core.c
@@ -112,12 +112,14 @@ u32 rt_global_debug_component = \

static struct usb_device_id rtl8192_usb_id_tbl[] = {
/* Realtek */
+ {USB_DEVICE(0x0bda, 0x8171)},
{USB_DEVICE(0x0bda, 0x8192)},
{USB_DEVICE(0x0bda, 0x8709)},
/* Corega */
{USB_DEVICE(0x07aa, 0x0043)},
/* Belkin */
{USB_DEVICE(0x050d, 0x805E)},
+ {USB_DEVICE(0x050d, 0x815F)}, /* Belkin F5D8053 v6 */
/* Sitecom */
{USB_DEVICE(0x0df6, 0x0031)},
{USB_DEVICE(0x0df6, 0x004b)}, /* WL-349 */
@@ -127,6 +129,8 @@ static struct usb_device_id rtl8192_usb_id_tbl[] = {
{USB_DEVICE(0x2001, 0x3301)},
/* Zinwell */
{USB_DEVICE(0x5a57, 0x0290)},
+ /* Guillemot */
+ {USB_DEVICE(0x06f8, 0xe031)},
//92SU
{USB_DEVICE(0x0bda, 0x8172)},
{}
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 34fc7bb..d784a8b 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1743,9 +1743,6 @@ int usb_external_resume_device(struct usb_device *udev, pm_message_t msg)

static void choose_wakeup(struct usb_device *udev, pm_message_t msg)
{
- int w, i;
- struct usb_interface *intf;
-
/* Remote wakeup is needed only when we actually go to sleep.
* For things like FREEZE and QUIESCE, if the device is already
* autosuspended then its current wakeup setting is okay.
@@ -1755,18 +1752,10 @@ static void choose_wakeup(struct usb_device *udev, pm_message_t msg)
return;
}

- /* If remote wakeup is permitted, see whether any interface drivers
+ /* Allow remote wakeup if it is enabled, even if no interface drivers
* actually want it.
*/
- w = 0;
- if (device_may_wakeup(&udev->dev) && udev->actconfig) {
- for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) {
- intf = udev->actconfig->interface[i];
- w |= intf->needs_remote_wakeup;
- }
- }
-
- udev->do_remote_wakeup = w;
+ udev->do_remote_wakeup = device_may_wakeup(&udev->dev);
}

int usb_suspend(struct device *dev, pm_message_t msg)
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index ab93918..a61f160 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -41,6 +41,10 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Philips PSC805 audio device */
{ USB_DEVICE(0x0471, 0x0155), .driver_info = USB_QUIRK_RESET_RESUME },

+ /* Artisman Watchdog Dongle */
+ { USB_DEVICE(0x04b4, 0x0526), .driver_info =
+ USB_QUIRK_CONFIG_INTF_STRINGS },
+
/* Roland SC-8820 */
{ USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME },

@@ -64,6 +68,9 @@ static const struct usb_device_id usb_quirk_list[] = {
/* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */
{ USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF },

+ /* Broadcom BCM92035DGROM BT dongle */
+ { USB_DEVICE(0x0a5c, 0x2021), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Action Semiconductor flash disk */
{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
USB_QUIRK_STRING_FETCH_255 },
diff --git a/drivers/usb/gadget/u_serial.c b/drivers/usb/gadget/u_serial.c
index adf8260..9e5f9f1 100644
--- a/drivers/usb/gadget/u_serial.c
+++ b/drivers/usb/gadget/u_serial.c
@@ -535,17 +535,11 @@ recycle:
list_move(&req->list, &port->read_pool);
}

- /* Push from tty to ldisc; this is immediate with low_latency, and
- * may trigger callbacks to this driver ... so drop the spinlock.
+ /* Push from tty to ldisc; without low_latency set this is handled by
+ * a workqueue, so we won't get callbacks and can hold port_lock
*/
if (tty && do_push) {
- spin_unlock_irq(&port->port_lock);
tty_flip_buffer_push(tty);
- wake_up_interruptible(&tty->read_wait);
- spin_lock_irq(&port->port_lock);
-
- /* tty may have been closed */
- tty = port->port_tty;
}

@@ -783,11 +777,6 @@ static int gs_open(struct tty_struct *tty, struct file *file)
port->open_count = 1;
port->openclose = false;

- /* low_latency means ldiscs work in tasklet context, without
- * needing a workqueue schedule ... easier to keep up.
- */
- tty->low_latency = 1;
-
/* if connected, start the I/O stream */
if (port->port_usb) {
struct gserial *gser = port->port_usb;
@@ -1194,6 +1183,7 @@ void gserial_cleanup(void)
n_ports = 0;

tty_unregister_driver(gs_tty_driver);
+ put_tty_driver(gs_tty_driver);
gs_tty_driver = NULL;

pr_debug("%s: cleaned up ttyGS* support\n", __func__);
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index 8b37a4b..be41ec3 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -2435,7 +2435,8 @@ sisusb_open(struct inode *inode, struct file *file)
}

if (!sisusb->devinit) {
- if (sisusb->sisusb_dev->speed == USB_SPEED_HIGH) {
+ if (sisusb->sisusb_dev->speed == USB_SPEED_HIGH ||
+ sisusb->sisusb_dev->speed == USB_SPEED_SUPER) {
if (sisusb_init_gfxdevice(sisusb, 0)) {
mutex_unlock(&sisusb->lock);
dev_err(&sisusb->sisusb_dev->dev, "Failed to initialize device\n");
@@ -3167,7 +3168,7 @@ static int sisusb_probe(struct usb_interface *intf,

sisusb->present = 1;

- if (dev->speed == USB_SPEED_HIGH) {
+ if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER) {
int initscreen = 1;
#ifdef INCL_SISUSB_CON
if (sisusb_first_vc > 0 &&
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index bf56be1..8de8572 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -697,6 +697,7 @@ static struct usb_device_id id_table_combined [] = {
{ USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID),
.driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk },
{ USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_SERIAL_VX7_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_MAXSTREAM_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_PHI_FISCO_PID) },
{ USB_DEVICE(TML_VID, TML_USB_SERIAL_PID) },
@@ -743,6 +744,14 @@ static struct usb_device_id id_table_combined [] = {
{ USB_DEVICE(FTDI_VID, MJSG_SR_RADIO_PID) },
{ USB_DEVICE(FTDI_VID, MJSG_HD_RADIO_PID) },
{ USB_DEVICE(FTDI_VID, MJSG_XM_RADIO_PID) },
+ { USB_DEVICE(FTDI_VID, XVERVE_SIGNALYZER_ST_PID),
+ .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE(FTDI_VID, XVERVE_SIGNALYZER_SLITE_PID),
+ .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE(FTDI_VID, XVERVE_SIGNALYZER_SH2_PID),
+ .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE(FTDI_VID, XVERVE_SIGNALYZER_SH4_PID),
+ .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ }, /* Optional parameter entry */
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 8f9e805..ffdcec7 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -703,6 +703,12 @@
#define TELLDUS_TELLSTICK_PID 0x0C30 /* RF control dongle 433 MHz using FT232RL */

/*
+ * RT Systems programming cables for various ham radios
+ */
+#define RTSYSTEMS_VID 0x2100 /* Vendor ID */
+#define RTSYSTEMS_SERIAL_VX7_PID 0x9e52 /* Serial converter for VX-7 Radios using FT232RL */
+
+/*
* Bayer Ascensia Contour blood glucose meter USB-converter cable.
* http://winglucofacts.com/cables/
*/
@@ -1024,3 +1030,12 @@
#define MJSG_SR_RADIO_PID 0x9379
#define MJSG_XM_RADIO_PID 0x937A
#define MJSG_HD_RADIO_PID 0x937C
+
+/*
+ * Xverve Signalyzer tools (http://www.signalyzer.com/)
+ */
+#define XVERVE_SIGNALYZER_ST_PID 0xBCA0
+#define XVERVE_SIGNALYZER_SLITE_PID 0xBCA1
+#define XVERVE_SIGNALYZER_SH2_PID 0xBCA2
+#define XVERVE_SIGNALYZER_SH4_PID 0xBCA4
+
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index fac0732..2586023 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -226,6 +226,7 @@ static int option_resume(struct usb_serial *serial);
#define AMOI_PRODUCT_H01 0x0800
#define AMOI_PRODUCT_H01A 0x7002
#define AMOI_PRODUCT_H02 0x0802
+#define AMOI_PRODUCT_SKYPEPHONE_S2 0x0407

#define DELL_VENDOR_ID 0x413C

@@ -316,6 +317,7 @@ static int option_resume(struct usb_serial *serial);
#define QISDA_PRODUCT_H21_4512 0x4512
#define QISDA_PRODUCT_H21_4523 0x4523
#define QISDA_PRODUCT_H20_4515 0x4515
+#define QISDA_PRODUCT_H20_4518 0x4518
#define QISDA_PRODUCT_H20_4519 0x4519

/* TLAYTECH PRODUCTS */
@@ -503,6 +505,7 @@ static struct usb_device_id option_ids[] = {
{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01) },
{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01A) },
{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H02) },
+ { USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_SKYPEPHONE_S2) },

{ USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5700_MINICARD) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO Mini-Card == Novatel Expedite EV620 CDMA/EV-DO */
{ USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5500_MINICARD) }, /* Dell Wireless 5500 Mobile Broadband HSDPA Mini-Card == Novatel Expedite EU740 HSDPA/3G */
@@ -836,6 +839,7 @@ static struct usb_device_id option_ids[] = {
{ USB_DEVICE(QISDA_VENDOR_ID, QISDA_PRODUCT_H21_4512) },
{ USB_DEVICE(QISDA_VENDOR_ID, QISDA_PRODUCT_H21_4523) },
{ USB_DEVICE(QISDA_VENDOR_ID, QISDA_PRODUCT_H20_4515) },
+ { USB_DEVICE(QISDA_VENDOR_ID, QISDA_PRODUCT_H20_4518) },
{ USB_DEVICE(QISDA_VENDOR_ID, QISDA_PRODUCT_H20_4519) },
{ USB_DEVICE(TOSHIBA_VENDOR_ID, TOSHIBA_PRODUCT_G450) },
{ USB_DEVICE(TOSHIBA_VENDOR_ID, TOSHIBA_PRODUCT_HSDPA_MINICARD ) }, /* Toshiba 3G HSDPA == Novatel Expedite EU870D MiniCard */
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index 54f8494..328578b 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -210,6 +210,7 @@ static struct usb_device_id id_table [] = {
{ USB_DEVICE(0x1199, 0x0021) }, /* Sierra Wireless AirCard 597E */
{ USB_DEVICE(0x1199, 0x0112) }, /* Sierra Wireless AirCard 580 */
{ USB_DEVICE(0x1199, 0x0120) }, /* Sierra Wireless USB Dongle 595U */
+ { USB_DEVICE(0x1199, 0x0301) }, /* Sierra Wireless USB Dongle 250U */
/* Sierra Wireless C597 */
{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x0023, 0xFF, 0xFF, 0xFF) },
/* Sierra Wireless T598 */
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 7127bfe..d43859f 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -635,6 +635,9 @@ static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
INIT_LIST_HEAD(&vp_dev->virtqueues);
spin_lock_init(&vp_dev->lock);

+ /* Disable MSI/MSIX to bring device to a known good state. */
+ pci_msi_off(pci_dev);
+
/* enable the device */
err = pci_enable_device(pci_dev);
if (err)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 64f6b2f..b9840fa 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -947,7 +947,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
*/

/* the destination must be opened for writing */
- if (!(file->f_mode & FMODE_WRITE))
+ if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
return -EINVAL;

ret = mnt_want_write(file->f_path.mnt);
@@ -1000,7 +1000,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,

/* determine range to clone */
ret = -EINVAL;
- if (off >= src->i_size || off + len > src->i_size)
+ if (off + len > src->i_size || off + len < off)
goto out_unlock;
if (len == 0)
olen = len = src->i_size - off;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 29f1da7..1445407 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1033,7 +1033,7 @@ init_cifs(void)
goto out_unregister_filesystem;
#endif
#ifdef CONFIG_CIFS_DFS_UPCALL
- rc = register_key_type(&key_type_dns_resolver);
+ rc = cifs_init_dns_resolver();
if (rc)
goto out_unregister_key_type;
#endif
@@ -1045,7 +1045,7 @@ init_cifs(void)

out_unregister_resolver_key:
#ifdef CONFIG_CIFS_DFS_UPCALL
- unregister_key_type(&key_type_dns_resolver);
+ cifs_exit_dns_resolver();
out_unregister_key_type:
#endif
#ifdef CONFIG_CIFS_UPCALL
@@ -1071,7 +1071,7 @@ exit_cifs(void)
cifs_proc_clean();
#ifdef CONFIG_CIFS_DFS_UPCALL
cifs_dfs_release_automount_timer();
- unregister_key_type(&key_type_dns_resolver);
+ cifs_exit_dns_resolver();
#endif
#ifdef CONFIG_CIFS_UPCALL
unregister_key_type(&cifs_spnego_key_type);
diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c
index 8794814..16f31c1 100644
--- a/fs/cifs/dns_resolve.c
+++ b/fs/cifs/dns_resolve.c
@@ -23,12 +23,16 @@
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/

+#include <linux/keyctl.h>
+#include <linux/key-type.h>
#include <keys/user-type.h>
#include "dns_resolve.h"
#include "cifsglob.h"
#include "cifsproto.h"
#include "cifs_debug.h"

+static const struct cred *dns_resolver_cache;
+
/* Checks if supplied name is IP address
* returns:
* 1 - name is IP
@@ -93,6 +97,7 @@ struct key_type key_type_dns_resolver = {
int
dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
{
+ const struct cred *saved_cred;
int rc = -EAGAIN;
struct key *rkey = ERR_PTR(-EAGAIN);
char *name;
@@ -132,8 +137,15 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
goto skip_upcall;
}

+ saved_cred = override_creds(dns_resolver_cache);
rkey = request_key(&key_type_dns_resolver, name, "");
+ revert_creds(saved_cred);
if (!IS_ERR(rkey)) {
+ if (!(rkey->perm & KEY_USR_VIEW)) {
+ down_read(&rkey->sem);
+ rkey->perm |= KEY_USR_VIEW;
+ up_read(&rkey->sem);
+ }
len = rkey->type_data.x[0];
data = rkey->payload.data;
} else {
@@ -164,4 +176,61 @@ out:
return rc;
}

+int __init cifs_init_dns_resolver(void)
+{
+ struct cred *cred;
+ struct key *keyring;
+ int ret;
+
+ printk(KERN_NOTICE "Registering the %s key type\n",
+ key_type_dns_resolver.name);
+
+ /* create an override credential set with a special thread keyring in
+ * which DNS requests are cached
+ *
+ * this is used to prevent malicious redirections from being installed
+ * with add_key().
+ */
+ cred = prepare_kernel_cred(NULL);
+ if (!cred)
+ return -ENOMEM;
+
+ keyring = key_alloc(&key_type_keyring, ".dns_resolver", 0, 0, cred,
+ (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ,
+ KEY_ALLOC_NOT_IN_QUOTA);
+ if (IS_ERR(keyring)) {
+ ret = PTR_ERR(keyring);
+ goto failed_put_cred;
+ }
+
+ ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL);
+ if (ret < 0)
+ goto failed_put_key;
+
+ ret = register_key_type(&key_type_dns_resolver);
+ if (ret < 0)
+ goto failed_put_key;
+
+ /* instruct request_key() to use this special keyring as a cache for
+ * the results it looks up */
+ cred->thread_keyring = keyring;
+ cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
+ dns_resolver_cache = cred;
+ return 0;
+
+failed_put_key:
+ key_put(keyring);
+failed_put_cred:
+ put_cred(cred);
+ return ret;
+}

+void __exit cifs_exit_dns_resolver(void)
+{
+ key_revoke(dns_resolver_cache->thread_keyring);
+ unregister_key_type(&key_type_dns_resolver);
+ put_cred(dns_resolver_cache);
+ printk(KERN_NOTICE "Unregistered %s key type\n",
+ key_type_dns_resolver.name);
+}
diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h
index 966e928..26b9eaa 100644
--- a/fs/cifs/dns_resolve.h
+++ b/fs/cifs/dns_resolve.h
@@ -24,8 +24,8 @@
#define _DNS_RESOLVE_H

#ifdef __KERNEL__
-#include <linux/key-type.h>
-extern struct key_type key_type_dns_resolver;
+extern int __init cifs_init_dns_resolver(void);
+extern void __exit cifs_exit_dns_resolver(void);
extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr);
#endif /* KERNEL */

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a104ca3..303fd7f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1284,6 +1284,10 @@ cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath,
if (rc == 0 || rc != -ETXTBSY)
return rc;

+ /* open-file renames don't work across directories */
+ if (to_dentry->d_parent != from_dentry->d_parent)
+ return rc;
+
/* open the file to be renamed -- we need DELETE perms */
rc = CIFSSMBOpen(xid, pTcon, fromPath, FILE_OPEN, DELETE,
CREATE_NOT_DIR, &srcfid, &oplock, NULL,
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 7085a62..6d6ff4f 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -723,15 +723,7 @@ ssetup_ntlmssp_authenticate:

/* calculate session key */
setup_ntlmv2_rsp(ses, v2_sess_key, nls_cp);
- if (first_time) /* should this be moved into common code
- with similar ntlmv2 path? */
- /* cifs_calculate_ntlmv2_mac_key(ses->server->mac_signing_key,
- response BB FIXME, v2_sess_key); */
-
- /* copy session key */
-
- /* memcpy(bcc_ptr, (char *)ntlm_session_key,LM2_SESS_KEY_SIZE);
- bcc_ptr += LM2_SESS_KEY_SIZE; */
+ /* FIXME: calculate MAC key */
memcpy(bcc_ptr, (char *)v2_sess_key,
sizeof(struct ntlmv2_resp));
bcc_ptr += sizeof(struct ntlmv2_resp);
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index f1c17e8..3dfe7ce 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -30,9 +30,9 @@ static struct mutex ecryptfs_msg_ctx_lists_mux;

static struct hlist_head *ecryptfs_daemon_hash;
struct mutex ecryptfs_daemon_hash_mux;
-static int ecryptfs_hash_buckets;
+static int ecryptfs_hash_bits;
#define ecryptfs_uid_hash(uid) \
- hash_long((unsigned long)uid, ecryptfs_hash_buckets)
+ hash_long((unsigned long)uid, ecryptfs_hash_bits)

static u32 ecryptfs_msg_counter;
static struct ecryptfs_msg_ctx *ecryptfs_msg_ctx_arr;
@@ -485,18 +485,19 @@ int ecryptfs_init_messaging(void)
}
mutex_init(&ecryptfs_daemon_hash_mux);
mutex_lock(&ecryptfs_daemon_hash_mux);
- ecryptfs_hash_buckets = 1;
- while (ecryptfs_number_of_users >> ecryptfs_hash_buckets)
- ecryptfs_hash_buckets++;
+ ecryptfs_hash_bits = 1;
+ while (ecryptfs_number_of_users >> ecryptfs_hash_bits)
+ ecryptfs_hash_bits++;
ecryptfs_daemon_hash = kmalloc((sizeof(struct hlist_head)
- * ecryptfs_hash_buckets), GFP_KERNEL);
+ * (1 << ecryptfs_hash_bits)),
+ GFP_KERNEL);
if (!ecryptfs_daemon_hash) {
rc = -ENOMEM;
printk(KERN_ERR "%s: Failed to allocate memory\n", __func__);
mutex_unlock(&ecryptfs_daemon_hash_mux);
goto out;
}
- for (i = 0; i < ecryptfs_hash_buckets; i++)
+ for (i = 0; i < (1 << ecryptfs_hash_bits); i++)
INIT_HLIST_HEAD(&ecryptfs_daemon_hash[i]);
mutex_unlock(&ecryptfs_daemon_hash_mux);
ecryptfs_msg_ctx_arr = kmalloc((sizeof(struct ecryptfs_msg_ctx)
@@ -553,7 +554,7 @@ void ecryptfs_release_messaging(void)
int i;

mutex_lock(&ecryptfs_daemon_hash_mux);
- for (i = 0; i < ecryptfs_hash_buckets; i++) {
+ for (i = 0; i < (1 << ecryptfs_hash_bits); i++) {
int rc;

hlist_for_each_entry(daemon, elem,
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 9dc93168..aa6fb6b 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -84,9 +84,11 @@ int ext4_check_dir_entry(const char *function, struct inode *dir,

if (error_msg != NULL)
ext4_error(dir->i_sb, function,
- "bad entry in directory #%lu: %s - "
- "offset=%u, inode=%u, rec_len=%d, name_len=%d",
- dir->i_ino, error_msg, offset,
+ "bad entry in directory #%lu: %s - block=%llu"
+ "offset=%u(%u), inode=%u, rec_len=%d, name_len=%d",
+ dir->i_ino, error_msg,
+ (unsigned long long) bh->b_blocknr,
+ (unsigned) (offset%bh->b_size), offset,
le32_to_cpu(de->inode),
rlen, de->name_len);
return error_msg == NULL ? 1 : 0;
@@ -109,7 +111,7 @@ static int ext4_readdir(struct file *filp,

if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_COMPAT_DIR_INDEX) &&
- ((EXT4_I(inode)->i_flags & EXT4_INDEX_FL) ||
+ ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
((inode->i_size >> sb->s_blocksize_bits) == 1))) {
err = ext4_dx_readdir(filp, dirent, filldir);
if (err != ERR_BAD_DX_DIR) {
@@ -120,7 +122,7 @@ static int ext4_readdir(struct file *filp,
* We don't set the inode dirty flag since it's not
* critical that it get flushed back to the disk.
*/
- EXT4_I(filp->f_path.dentry->d_inode)->i_flags &= ~EXT4_INDEX_FL;
+ ext4_clear_inode_flag(filp->f_path.dentry->d_inode, EXT4_INODE_INDEX);
}
stored = 0;
offset = filp->f_pos & (sb->s_blocksize - 1);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4a825c1..fa6b79f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -29,6 +29,9 @@
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
+#ifdef __KERNEL__
+#include <linux/compat.h>
+#endif

/*
* The fourth extended filesystem constants/structures
@@ -284,10 +287,12 @@ struct flex_groups {
#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
+#define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
+#define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */

-#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE 0x000B80FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE 0x004B80FF /* User modifiable flags */

/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
@@ -314,15 +319,81 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
}

/*
- * Inode dynamic state flags
+ * Inode flags used for atomic set/get
+ */
+enum {
+ EXT4_INODE_SECRM = 0, /* Secure deletion */
+ EXT4_INODE_UNRM = 1, /* Undelete */
+ EXT4_INODE_COMPR = 2, /* Compress file */
+ EXT4_INODE_SYNC = 3, /* Synchronous updates */
+ EXT4_INODE_IMMUTABLE = 4, /* Immutable file */
+ EXT4_INODE_APPEND = 5, /* writes to file may only append */
+ EXT4_INODE_NODUMP = 6, /* do not dump file */
+ EXT4_INODE_NOATIME = 7, /* do not update atime */
+/* Reserved for compression usage... */
+ EXT4_INODE_DIRTY = 8,
+ EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */
+ EXT4_INODE_NOCOMPR = 10, /* Don't compress */
+ EXT4_INODE_ECOMPR = 11, /* Compression error */
+/* End compression flags --- maybe not all used */
+ EXT4_INODE_INDEX = 12, /* hash-indexed directory */
+ EXT4_INODE_IMAGIC = 13, /* AFS directory */
+ EXT4_INODE_JOURNAL_DATA = 14, /* file data should be journaled */
+ EXT4_INODE_NOTAIL = 15, /* file tail should not be merged */
+ EXT4_INODE_DIRSYNC = 16, /* dirsync behaviour (directories only) */
+ EXT4_INODE_TOPDIR = 17, /* Top of directory hierarchies*/
+ EXT4_INODE_HUGE_FILE = 18, /* Set to each huge file */
+ EXT4_INODE_EXTENTS = 19, /* Inode uses extents */
+ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */
+ EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */
+ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */
+};
+
+#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
+#define CHECK_FLAG_VALUE(FLAG) if (!TEST_FLAG_VALUE(FLAG)) { \
+ printk(KERN_EMERG "EXT4 flag fail: " #FLAG ": %d %d\n", \
+ EXT4_##FLAG##_FL, EXT4_INODE_##FLAG); BUG_ON(1); }
+
+/*
+ * Since it's pretty easy to mix up bit numbers and hex values, and we
+ * can't do a compile-time test for ENUM values, we use a run-time
+ * test to make sure that EXT4_XXX_FL is consistent with respect to
+ * EXT4_INODE_XXX. If all is well the printk and BUG_ON will all drop
+ * out so it won't cost any extra space in the compiled kernel image.
+ * But it's important that these values are the same, since we are
+ * using EXT4_INODE_XXX to test for the flag values, but EXT4_XX_FL
+ * must be consistent with the values of FS_XXX_FL defined in
+ * include/linux/fs.h and the on-disk values found in ext2, ext3, and
+ * ext4 filesystems, and of course the values defined in e2fsprogs.
+ *
+ * It's not paranoia if the Murphy's Law really *is* out to get you. :-)
*/
-#define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */
-#define EXT4_STATE_NEW 0x00000002 /* inode is newly created */
-#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */
-#define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */
-#define EXT4_STATE_DA_ALLOC_CLOSE 0x00000010 /* Alloc DA blks on close */
-#define EXT4_STATE_EXT_MIGRATE 0x00000020 /* Inode is migrating */
-#define EXT4_STATE_DIO_UNWRITTEN 0x00000040 /* need convert on dio done*/
+static inline void ext4_check_flag_values(void)
+{
+ CHECK_FLAG_VALUE(SECRM);
+ CHECK_FLAG_VALUE(UNRM);
+ CHECK_FLAG_VALUE(COMPR);
+ CHECK_FLAG_VALUE(SYNC);
+ CHECK_FLAG_VALUE(IMMUTABLE);
+ CHECK_FLAG_VALUE(APPEND);
+ CHECK_FLAG_VALUE(NODUMP);
+ CHECK_FLAG_VALUE(NOATIME);
+ CHECK_FLAG_VALUE(DIRTY);
+ CHECK_FLAG_VALUE(COMPRBLK);
+ CHECK_FLAG_VALUE(NOCOMPR);
+ CHECK_FLAG_VALUE(ECOMPR);
+ CHECK_FLAG_VALUE(INDEX);
+ CHECK_FLAG_VALUE(IMAGIC);
+ CHECK_FLAG_VALUE(JOURNAL_DATA);
+ CHECK_FLAG_VALUE(NOTAIL);
+ CHECK_FLAG_VALUE(DIRSYNC);
+ CHECK_FLAG_VALUE(TOPDIR);
+ CHECK_FLAG_VALUE(HUGE_FILE);
+ CHECK_FLAG_VALUE(EXTENTS);
+ CHECK_FLAG_VALUE(EA_INODE);
+ CHECK_FLAG_VALUE(EOFBLOCKS);
+ CHECK_FLAG_VALUE(RESERVED);
+}

/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
@@ -335,6 +406,18 @@ struct ext4_new_group_input {
__u16 unused;
};

+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+struct compat_ext4_new_group_input {
+ u32 group;
+ compat_u64 block_bitmap;
+ compat_u64 inode_bitmap;
+ compat_u64 inode_table;
+ u32 blocks_count;
+ u16 reserved_blocks;
+ u16 unused;
+};
+#endif
+
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
__u32 group;
@@ -361,14 +444,11 @@ struct ext4_new_group_data {
so set the magic i_delalloc_reserve_flag after taking the
inode allocation semaphore for */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
- /* Call ext4_da_update_reserve_space() after successfully
- allocating the blocks */
-#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0008
/* caller is from the direct IO path, request to creation of an
unitialized extents if not allocated, split the uninitialized
extent if blocks has been preallocated already*/
-#define EXT4_GET_BLOCKS_DIO 0x0010
-#define EXT4_GET_BLOCKS_CONVERT 0x0020
+#define EXT4_GET_BLOCKS_DIO 0x0008
+#define EXT4_GET_BLOCKS_CONVERT 0x0010
#define EXT4_GET_BLOCKS_DIO_CREATE_EXT (EXT4_GET_BLOCKS_DIO|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
/* Convert extent to initialized after direct IO complete */
@@ -397,6 +477,7 @@ struct ext4_new_group_data {
#define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12)
#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent)

+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
*/
@@ -407,11 +488,13 @@ struct ext4_new_group_data {
#define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int)
#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
+#define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input)
#ifdef CONFIG_JBD2_DEBUG
#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int)
#endif
#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
+#endif

/*
@@ -615,9 +698,8 @@ struct ext4_ext_cache {
*/
struct ext4_inode_info {
__le32 i_data[15]; /* unconverted */
- __u32 i_flags;
- ext4_fsblk_t i_file_acl;
__u32 i_dtime;
+ ext4_fsblk_t i_file_acl;

/*
* i_block_group is the number of the block group which contains
@@ -627,7 +709,8 @@ struct ext4_inode_info {
* near to their parent directory's inode.
*/
ext4_group_t i_block_group;
- __u32 i_state; /* Dynamic state flags for ext4 */
+ unsigned long i_state_flags; /* Dynamic state flags */
+ unsigned long i_flags;

ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
@@ -693,6 +776,8 @@ struct ext4_inode_info {
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
unsigned short i_delalloc_reserved_flag;
+ sector_t i_da_metadata_calc_last_lblock;
+ int i_da_metadata_calc_len;

/* on-disk additional length */
__u16 i_extra_isize;
@@ -1045,6 +1130,37 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
(ino >= EXT4_FIRST_INO(sb) &&
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
+
+/*
+ * Inode dynamic state flags
+ */
+enum {
+ EXT4_STATE_JDATA, /* journaled data exists */
+ EXT4_STATE_NEW, /* inode is newly created */
+ EXT4_STATE_XATTR, /* has in-inode xattrs */
+ EXT4_STATE_NO_EXPAND, /* No space for expansion */
+ EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */
+ EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */
+ EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/
+ EXT4_STATE_NEWENTRY, /* File just added to dir */
+};
+
+#define EXT4_INODE_BIT_FNS(name, field) \
+static inline int ext4_test_inode_##name(struct inode *inode, int bit) \
+{ \
+ return test_bit(bit, &EXT4_I(inode)->i_##field); \
+} \
+static inline void ext4_set_inode_##name(struct inode *inode, int bit) \
+{ \
+ set_bit(bit, &EXT4_I(inode)->i_##field); \
+} \
+static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
+{ \
+ clear_bit(bit, &EXT4_I(inode)->i_##field); \
+}
+
+EXT4_INODE_BIT_FNS(flag, flags)
+EXT4_INODE_BIT_FNS(state, state_flags)
#else
/* Assume that user mode programs are passing in an ext4fs superblock, not
* a kernel struct super_block. This will allow us to call the feature-test
@@ -1229,7 +1345,7 @@ struct ext4_dir_entry_2 {

#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
EXT4_FEATURE_COMPAT_DIR_INDEX) && \
- (EXT4_I(dir)->i_flags & EXT4_INDEX_FL))
+ ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)

@@ -1438,6 +1554,8 @@ extern int ext4_block_truncate_page(handle_t *handle,
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern int flush_aio_dio_completed_IO(struct inode *inode);
+extern void ext4_da_update_reserve_space(struct inode *inode,
+ int used, int quota_claim);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
@@ -1637,6 +1755,7 @@ struct ext4_group_info {
ext4_grpblk_t bb_first_free; /* first free block */
ext4_grpblk_t bb_free; /* total free blocks */
ext4_grpblk_t bb_fragments; /* nr of freespace fragments */
+ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */
struct list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
void *bb_bitmap;
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 2ca6864..bdb6ce7 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -225,7 +225,8 @@ static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
}

-extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
+extern int ext4_ext_calc_metadata_amount(struct inode *inode,
+ sector_t lblocks);
extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex);
extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 6a94099..496249a 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -89,7 +89,7 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
ext4_journal_abort_handle(where, __func__, bh,
handle, err);
} else {
- if (inode && bh)
+ if (inode)
mark_buffer_dirty_inode(bh, inode);
else
mark_buffer_dirty(bh);
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 1892a77..386095d 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -282,7 +282,7 @@ static inline int ext4_should_journal_data(struct inode *inode)
return 1;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
return 1;
- if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 1;
return 0;
}
@@ -293,7 +293,7 @@ static inline int ext4_should_order_data(struct inode *inode)
return 0;
if (!S_ISREG(inode->i_mode))
return 0;
- if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 0;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
return 1;
@@ -306,7 +306,7 @@ static inline int ext4_should_writeback_data(struct inode *inode)
return 0;
if (EXT4_JOURNAL(inode) == NULL)
return 1;
- if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 0;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
return 1;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 9e21653..99482ea 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -107,11 +107,8 @@ static int ext4_ext_truncate_extend_restart(handle_t *handle,
if (err <= 0)
return err;
err = ext4_truncate_restart_trans(handle, inode, needed);
- /*
- * We have dropped i_data_sem so someone might have cached again
- * an extent we are going to truncate.
- */
- ext4_ext_invalidate_cache(inode);
+ if (err == 0)
+ err = -EAGAIN;

return err;
}
@@ -296,29 +293,44 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
* to allocate @blocks
* Worse case is one block per extent
*/
-int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks)
+int ext4_ext_calc_metadata_amount(struct inode *inode, sector_t lblock)
{
- int lcap, icap, rcap, leafs, idxs, num;
- int newextents = blocks;
-
- rcap = ext4_ext_space_root_idx(inode, 0);
- lcap = ext4_ext_space_block(inode, 0);
- icap = ext4_ext_space_block_idx(inode, 0);
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int idxs, num = 0;

- /* number of new leaf blocks needed */
- num = leafs = (newextents + lcap - 1) / lcap;
+ idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+ / sizeof(struct ext4_extent_idx));

/*
- * Worse case, we need separate index block(s)
- * to link all new leaf blocks
+ * If the new delayed allocation block is contiguous with the
+ * previous da block, it can share index blocks with the
+ * previous block, so we only need to allocate a new index
+ * block every idxs leaf blocks. At ldxs**2 blocks, we need
+ * an additional index block, and at ldxs**3 blocks, yet
+ * another index blocks.
*/
- idxs = (leafs + icap - 1) / icap;
- do {
- num += idxs;
- idxs = (idxs + icap - 1) / icap;
- } while (idxs > rcap);
+ if (ei->i_da_metadata_calc_len &&
+ ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+ if ((ei->i_da_metadata_calc_len % idxs) == 0)
+ num++;
+ if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
+ num++;
+ if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) {
+ num++;
+ ei->i_da_metadata_calc_len = 0;
+ } else
+ ei->i_da_metadata_calc_len++;
+ ei->i_da_metadata_calc_last_lblock++;
+ return num;
+ }

- return num;
+ /*
+ * In the worst case we need a new set of index blocks at
+ * every level of the inode's extent tree.
+ */
+ ei->i_da_metadata_calc_len = 1;
+ ei->i_da_metadata_calc_last_lblock = lblock;
+ return ext_depth(inode) + 1;
}

static int
@@ -2248,7 +2260,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
int depth = ext_depth(inode);
struct ext4_ext_path *path;
handle_t *handle;
- int i = 0, err = 0;
+ int i, err;

ext_debug("truncate since %u\n", start);

@@ -2257,23 +2269,26 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
if (IS_ERR(handle))
return PTR_ERR(handle);

+again:
ext4_ext_invalidate_cache(inode);

/*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
+ depth = ext_depth(inode);
path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
if (path == NULL) {
ext4_journal_stop(handle);
return -ENOMEM;
}
+ path[0].p_depth = depth;
path[0].p_hdr = ext_inode_hdr(inode);
if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
err = -EIO;
goto out;
}
- path[0].p_depth = depth;
+ i = err = 0;

while (i >= 0 && err == 0) {
if (i == depth) {
@@ -2367,6 +2382,8 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
out:
ext4_ext_drop_refs(path);
kfree(path);
+ if (err == -EAGAIN)
+ goto again;
ext4_journal_stop(handle);

return err;
@@ -2431,7 +2448,7 @@ static void bi_complete(struct bio *bio, int error)
/* FIXME!! we need to try to merge to left or right after zero-out */
static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
{
- int ret = -EIO;
+ int ret;
struct bio *bio;
int blkbits, blocksize;
sector_t ee_pblock;
@@ -2455,6 +2472,9 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
len = ee_len;

bio = bio_alloc(GFP_NOIO, len);
+ if (!bio)
+ return -ENOMEM;
+
bio->bi_sector = ee_pblock;
bio->bi_bdev = inode->i_sb->s_bdev;

@@ -2482,17 +2502,15 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
submit_bio(WRITE, bio);
wait_for_completion(&event);

- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
- ret = 0;
- else {
- ret = -EIO;
- break;
+ if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+ bio_put(bio);
+ return -EIO;
}
bio_put(bio);
ee_len -= done;
ee_pblock += done << (blkbits - 9);
}
- return ret;
+ return 0;
}

#define EXT4_EXT_ZERO_LEN 7
@@ -2517,11 +2535,21 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
struct ext4_extent *ex2 = NULL;
struct ext4_extent *ex3 = NULL;
struct ext4_extent_header *eh;
- ext4_lblk_t ee_block;
+ ext4_lblk_t ee_block, eof_block;
unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0;
int ret = 0;
+ int may_zeroout;
+
+ ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
+ "block %llu, max_blocks %u\n", inode->i_ino,
+ (unsigned long long)iblock, max_blocks);
+
+ eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+ inode->i_sb->s_blocksize_bits;
+ if (eof_block < iblock + max_blocks)
+ eof_block = iblock + max_blocks;

depth = ext_depth(inode);
eh = path[depth].p_hdr;
@@ -2530,16 +2558,23 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (iblock - ee_block);
newblock = iblock - ee_block + ext_pblock(ex);
+
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));

+ /*
+ * It is safe to convert extent to initialized via explicit
+ * zeroout only if extent is fully insde i_size or new_size.
+ */
+ may_zeroout = ee_block + ee_len <= eof_block;
+
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
/* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
- if (ee_len <= 2*EXT4_EXT_ZERO_LEN) {
+ if (ee_len <= 2*EXT4_EXT_ZERO_LEN && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2570,7 +2605,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
if (allocated > max_blocks) {
unsigned int newdepth;
/* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
- if (allocated <= EXT4_EXT_ZERO_LEN) {
+ if (allocated <= EXT4_EXT_ZERO_LEN && may_zeroout) {
/*
* iblock == ee_block is handled by the zerouout
* at the beginning.
@@ -2646,7 +2681,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ex3->ee_len = cpu_to_le16(allocated - max_blocks);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3, 0);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2670,8 +2705,10 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* update the extent length after successful insert of the
* split extent
*/
- orig_ex.ee_len = cpu_to_le16(ee_len -
- ext4_ext_get_actual_len(ex3));
+ ee_len -= ext4_ext_get_actual_len(ex3);
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ may_zeroout = ee_block + ee_len <= eof_block;
+
depth = newdepth;
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode, iblock, path);
@@ -2695,7 +2732,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* otherwise give the extent a chance to merge to left
*/
if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
- iblock != ee_block) {
+ iblock != ee_block && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2764,7 +2801,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex, 0);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2824,14 +2861,21 @@ static int ext4_split_unwritten_extents(handle_t *handle,
struct ext4_extent *ex2 = NULL;
struct ext4_extent *ex3 = NULL;
struct ext4_extent_header *eh;
- ext4_lblk_t ee_block;
+ ext4_lblk_t ee_block, eof_block;
unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0;
+ int may_zeroout;
+
+ ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
+ "block %llu, max_blocks %u\n", inode->i_ino,
+ (unsigned long long)iblock, max_blocks);
+
+ eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+ inode->i_sb->s_blocksize_bits;
+ if (eof_block < iblock + max_blocks)
+ eof_block = iblock + max_blocks;

- ext_debug("ext4_split_unwritten_extents: inode %lu,"
- "iblock %llu, max_blocks %u\n", inode->i_ino,
- (unsigned long long)iblock, max_blocks);
depth = ext_depth(inode);
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
@@ -2839,12 +2883,19 @@ static int ext4_split_unwritten_extents(handle_t *handle,
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (iblock - ee_block);
newblock = iblock - ee_block + ext_pblock(ex);
+
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));

/*
+ * It is safe to convert extent to initialized via explicit
+ * zeroout only if extent is fully insde i_size or new_size.
+ */
+ may_zeroout = ee_block + ee_len <= eof_block;
+
+ /*
* If the uninitialized extent begins at the same logical
* block where the write begins, and the write completely
* covers the extent, then we don't need to split it.
@@ -2878,7 +2929,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
ex3->ee_len = cpu_to_le16(allocated - max_blocks);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3, flags);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2902,8 +2953,10 @@ static int ext4_split_unwritten_extents(handle_t *handle,
* update the extent length after successful insert of the
* split extent
*/
- orig_ex.ee_len = cpu_to_le16(ee_len -
- ext4_ext_get_actual_len(ex3));
+ ee_len -= ext4_ext_get_actual_len(ex3);
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ may_zeroout = ee_block + ee_len <= eof_block;
+
depth = newdepth;
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode, iblock, path);
@@ -2949,7 +3002,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -3029,6 +3082,14 @@ out:
return err;
}

+static void unmap_underlying_metadata_blocks(struct block_device *bdev,
+ sector_t block, int count)
+{
+ int i;
+ for (i = 0; i < count; i++)
+ unmap_underlying_metadata(bdev, block + i);
+}
+
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, unsigned int max_blocks,
@@ -3059,7 +3120,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
if (io)
io->flag = DIO_AIO_UNWRITTEN;
else
- EXT4_I(inode)->i_state |= EXT4_STATE_DIO_UNWRITTEN;
+ ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
goto out;
}
/* async DIO end_io complete, convert the filled extent to written */
@@ -3104,6 +3165,30 @@ out:
} else
allocated = ret;
set_buffer_new(bh_result);
+ /*
+ * if we allocated more blocks than requested
+ * we need to make sure we unmap the extra block
+ * allocated. The actual needed block will get
+ * unmapped later when we find the buffer_head marked
+ * new.
+ */
+ if (allocated > max_blocks) {
+ unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
+ newblock + max_blocks,
+ allocated - max_blocks);
+ allocated = max_blocks;
+ }
+
+ /*
+ * If we have done fallocate with the offset that is already
+ * delayed allocated, we would have block reservation
+ * and quota reservation done in the delayed write path.
+ * But fallocate would have already updated quota and block
+ * count for this offset. So cancel these reservation
+ */
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ ext4_da_update_reserve_space(inode, allocated, 0);
+
map_out:
set_buffer_mapped(bh_result);
out1:
@@ -3144,9 +3229,9 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
{
struct ext4_ext_path *path = NULL;
struct ext4_extent_header *eh;
- struct ext4_extent newex, *ex;
+ struct ext4_extent newex, *ex, *last_ex;
ext4_fsblk_t newblock;
- int err = 0, depth, ret, cache_type;
+ int i, err = 0, depth, ret, cache_type;
unsigned int allocated = 0;
struct ext4_allocation_request ar;
ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
@@ -3196,7 +3281,13 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
* this situation is possible, though, _during_ tree modification;
* this is why assert can't be put in ext4_ext_find_extent()
*/
- BUG_ON(path[depth].p_ext == NULL && depth != 0);
+ if (path[depth].p_ext == NULL && depth != 0) {
+ ext4_error(inode->i_sb, __func__, "bad extent address "
+ "inode: %lu, iblock: %lu, depth: %d",
+ inode->i_ino, (unsigned long) iblock, depth);
+ err = -EIO;
+ goto out2;
+ }
eh = path[depth].p_hdr;

ex = path[depth].p_ext;
@@ -3315,10 +3406,36 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
if (io)
io->flag = DIO_AIO_UNWRITTEN;
else
- EXT4_I(inode)->i_state |=
- EXT4_STATE_DIO_UNWRITTEN;;
+ ext4_set_inode_state(inode,
+ EXT4_STATE_DIO_UNWRITTEN);
}
}
+
+ if (unlikely(ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))) {
+ if (unlikely(!eh->eh_entries)) {
+ ext4_error(inode->i_sb, __func__,
+ "inode#%lu, eh->eh_entries = 0 and "
+ "EOFBLOCKS_FL set", inode->i_ino);
+ err = -EIO;
+ goto out2;
+ }
+ last_ex = EXT_LAST_EXTENT(eh);
+ /*
+ * If the current leaf block was reached by looking at
+ * the last index block all the way down the tree, and
+ * we are extending the inode beyond the last extent
+ * in the current leaf block, then clear the
+ * EOFBLOCKS_FL flag.
+ */
+ for (i = depth-1; i >= 0; i--) {
+ if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
+ break;
+ }
+ if ((i < 0) &&
+ (iblock + ar.len > le32_to_cpu(last_ex->ee_block) +
+ ext4_ext_get_actual_len(last_ex)))
+ ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+ }
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err) {
/* free data blocks we just allocated */
@@ -3333,9 +3450,18 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* previous routine could use block we allocated */
newblock = ext_pblock(&newex);
allocated = ext4_ext_get_actual_len(&newex);
+ if (allocated > max_blocks)
+ allocated = max_blocks;
set_buffer_new(bh_result);

/*
+ * Update reserved blocks/metadata blocks after successful
+ * block allocation which had been deferred till now.
+ */
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ ext4_da_update_reserve_space(inode, allocated, 1);
+
+ /*
* Cache the extent and update transaction to commit on fdatasync only
* when it is _not_ an uninitialized extent.
*/
@@ -3443,6 +3569,13 @@ static void ext4_falloc_update_inode(struct inode *inode,
i_size_write(inode, new_size);
if (new_size > EXT4_I(inode)->i_disksize)
ext4_update_i_disksize(inode, new_size);
+ } else {
+ /*
+ * Mark that we allocate beyond EOF so the subsequent truncate
+ * can proceed even if the new size is the same as i_size.
+ */
+ if (new_size > i_size_read(inode))
+ ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
}

}
@@ -3470,7 +3603,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
* currently supporting (pre)allocate mode for extent-based
* files _only_
*/
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EOPNOTSUPP;

/* preallocation to directories is currently not supported */
@@ -3489,6 +3622,11 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
*/
credits = ext4_chunk_trans_blocks(inode, max_blocks);
mutex_lock(&inode->i_mutex);
+ ret = inode_newsize_ok(inode, (len + offset));
+ if (ret) {
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+ }
retry:
while (ret >= 0 && ret < max_blocks) {
block = block + ret;
@@ -3683,7 +3821,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
int error = 0;

/* in-inode? */
- if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
struct ext4_iloc iloc;
int offset; /* offset of xattr in inode */

@@ -3696,6 +3834,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
physical += offset;
length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
flags |= FIEMAP_EXTENT_DATA_INLINE;
+ brelse(iloc.bh);
} else { /* external block */
physical = EXT4_I(inode)->i_file_acl << blockbits;
length = inode->i_sb->s_blocksize;
@@ -3714,7 +3853,7 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
int error = 0;

/* fallback to generic here if not in extents fmt */
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return generic_block_fiemap(inode, fieinfo, start, len,
ext4_get_block);

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 9630583..2a60541 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -35,9 +35,9 @@
*/
static int ext4_release_file(struct inode *inode, struct file *filp)
{
- if (EXT4_I(inode)->i_state & EXT4_STATE_DA_ALLOC_CLOSE) {
+ if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
ext4_alloc_da_blocks(inode);
- EXT4_I(inode)->i_state &= ~EXT4_STATE_DA_ALLOC_CLOSE;
+ ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
}
/* if we are the last writer on the inode, drop the block reservation */
if ((filp->f_mode & FMODE_WRITE) &&
@@ -65,7 +65,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
* is smaller than s_maxbytes, which is for extent-mapped files.
*/

- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index d6049e4..c3660a6 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -35,6 +35,29 @@
#include <trace/events/ext4.h>

/*
+ * If we're not journaling and this is a just-created file, we have to
+ * sync our parent directory (if it was freshly created) since
+ * otherwise it will only be written by writeback, leaving a huge
+ * window during which a crash may lose the file. This may apply for
+ * the parent directory's parent as well, and so on recursively, if
+ * they are also freshly created.
+ */
+static void ext4_sync_parent(struct inode *inode)
+{
+ struct dentry *dentry = NULL;
+
+ while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+ ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
+ dentry = list_entry(inode->i_dentry.next,
+ struct dentry, d_alias);
+ if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
+ break;
+ inode = dentry->d_parent->d_inode;
+ sync_mapping_buffers(inode->i_mapping);
+ }
+}
+
+/*
* akpm: A new design for ext4_sync_file().
*
* This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
@@ -67,8 +90,12 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
if (ret < 0)
return ret;

- if (!journal)
- return simple_fsync(file, dentry, datasync);
+ if (!journal) {
+ ret = simple_fsync(file, dentry, datasync);
+ if (!ret && !list_empty(&inode->i_dentry))
+ ext4_sync_parent(inode);
+ return ret;
+ }

/*
* data=writeback,ordered:
@@ -88,9 +115,21 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
return ext4_force_commit(inode->i_sb);

commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
- if (jbd2_log_start_commit(journal, commit_tid))
- jbd2_log_wait_commit(journal, commit_tid);
- else if (journal->j_flags & JBD2_BARRIER)
+ if (jbd2_log_start_commit(journal, commit_tid)) {
+ /*
+ * When the journal is on a different device than the
+ * fs data disk, we need to issue the barrier in
+ * writeback mode. (In ordered mode, the jbd2 layer
+ * will take care of issuing the barrier. In
+ * data=journal, all of the data blocks are written to
+ * the journal device.)
+ */
+ if (ext4_should_writeback_data(inode) &&
+ (journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
+ ret = jbd2_log_wait_commit(journal, commit_tid);
+ } else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f3624ea..55a93f5 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -244,57 +244,50 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
if (fatal)
goto error_return;

- /* Ok, now we can actually update the inode bitmaps.. */
- cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
- bit, bitmap_bh->b_data);
- if (!cleared)
- ext4_error(sb, "ext4_free_inode",
- "bit already cleared for inode %lu", ino);
- else {
- gdp = ext4_get_group_desc(sb, block_group, &bh2);
-
+ fatal = -ESRCH;
+ gdp = ext4_get_group_desc(sb, block_group, &bh2);
+ if (gdp) {
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bh2);
- if (fatal) goto error_return;
-
- if (gdp) {
- ext4_lock_group(sb, block_group);
- count = ext4_free_inodes_count(sb, gdp) + 1;
- ext4_free_inodes_set(sb, gdp, count);
- if (is_directory) {
- count = ext4_used_dirs_count(sb, gdp) - 1;
- ext4_used_dirs_set(sb, gdp, count);
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t f;
-
- f = ext4_flex_group(sbi, block_group);
- atomic_dec(&sbi->s_flex_groups[f].free_inodes);
- }
+ }
+ ext4_lock_group(sb, block_group);
+ cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
+ if (fatal || !cleared) {
+ ext4_unlock_group(sb, block_group);
+ goto out;
+ }

- }
- gdp->bg_checksum = ext4_group_desc_csum(sbi,
- block_group, gdp);
- ext4_unlock_group(sb, block_group);
- percpu_counter_inc(&sbi->s_freeinodes_counter);
- if (is_directory)
- percpu_counter_dec(&sbi->s_dirs_counter);
-
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t f;
-
- f = ext4_flex_group(sbi, block_group);
- atomic_inc(&sbi->s_flex_groups[f].free_inodes);
- }
- }
- BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, NULL, bh2);
- if (!fatal) fatal = err;
+ count = ext4_free_inodes_count(sb, gdp) + 1;
+ ext4_free_inodes_set(sb, gdp, count);
+ if (is_directory) {
+ count = ext4_used_dirs_count(sb, gdp) - 1;
+ ext4_used_dirs_set(sb, gdp, count);
+ percpu_counter_dec(&sbi->s_dirs_counter);
}
- BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
- if (!fatal)
- fatal = err;
- sb->s_dirt = 1;
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
+ ext4_unlock_group(sb, block_group);
+
+ percpu_counter_inc(&sbi->s_freeinodes_counter);
+ if (sbi->s_log_groups_per_flex) {
+ ext4_group_t f = ext4_flex_group(sbi, block_group);
+
+ atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+ if (is_directory)
+ atomic_dec(&sbi->s_flex_groups[f].used_dirs);
+ }
+ BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+ fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
+out:
+ if (cleared) {
+ BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+ if (!fatal)
+ fatal = err;
+ sb->s_dirt = 1;
+ } else
+ ext4_error(sb, "ext4_free_inode",
+ "bit already cleared for inode %lu", ino);
+
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, fatal);
@@ -504,7 +497,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,

if (S_ISDIR(mode) &&
((parent == sb->s_root->d_inode) ||
- (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL))) {
+ (ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) {
int best_ndir = inodes_per_group;
int ret = -1;

@@ -779,7 +772,7 @@ static int ext4_claim_inode(struct super_block *sb,
if (sbi->s_log_groups_per_flex) {
ext4_group_t f = ext4_flex_group(sbi, group);

- atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+ atomic_inc(&sbi->s_flex_groups[f].used_dirs);
}
}
gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
@@ -904,7 +897,7 @@ repeat_in_this_group:
BUFFER_TRACE(inode_bitmap_bh,
"call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle,
- inode,
+ NULL,
inode_bitmap_bh);
if (err)
goto fail;
@@ -1029,7 +1022,8 @@ got:
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);

- ei->i_state = EXT4_STATE_NEW;
+ ei->i_state_flags = 0;
+ ext4_set_inode_state(inode, EXT4_STATE_NEW);

ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;

@@ -1050,7 +1044,7 @@ got:
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
/* set extent flag only for directory, file and normal symlink*/
if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) {
- EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
+ ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode);
}
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 16efcee..99596fc 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -957,7 +957,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
int count = 0;
ext4_fsblk_t first_block = 0;

- J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
+ J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
depth = ext4_block_to_path(inode, iblock, offsets,
&blocks_to_boundary);
@@ -1051,81 +1051,115 @@ qsize_t *ext4_get_reserved_space(struct inode *inode)
return &EXT4_I(inode)->i_reserved_quota;
}
#endif
+
/*
* Calculate the number of metadata blocks need to reserve
- * to allocate @blocks for non extent file based file
+ * to allocate a new block at @lblocks for non extent file based file
*/
-static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
+static int ext4_indirect_calc_metadata_amount(struct inode *inode,
+ sector_t lblock)
{
- int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- int ind_blks, dind_blks, tind_blks;
-
- /* number of new indirect blocks needed */
- ind_blks = (blocks + icap - 1) / icap;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
+ int blk_bits;

- dind_blks = (ind_blks + icap - 1) / icap;
+ if (lblock < EXT4_NDIR_BLOCKS)
+ return 0;

- tind_blks = 1;
+ lblock -= EXT4_NDIR_BLOCKS;

- return ind_blks + dind_blks + tind_blks;
+ if (ei->i_da_metadata_calc_len &&
+ (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
+ ei->i_da_metadata_calc_len++;
+ return 0;
+ }
+ ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
+ ei->i_da_metadata_calc_len = 1;
+ blk_bits = order_base_2(lblock);
+ return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
}

/*
* Calculate the number of metadata blocks need to reserve
- * to allocate given number of blocks
+ * to allocate a block located at @lblock
*/
-static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
+static int ext4_calc_metadata_amount(struct inode *inode, sector_t lblock)
{
- if (!blocks)
- return 0;
-
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
- return ext4_ext_calc_metadata_amount(inode, blocks);
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ return ext4_ext_calc_metadata_amount(inode, lblock);

- return ext4_indirect_calc_metadata_amount(inode, blocks);
+ return ext4_indirect_calc_metadata_amount(inode, lblock);
}

-static void ext4_da_update_reserve_space(struct inode *inode, int used)
+/*
+ * Called with i_data_sem down, which is important since we can call
+ * ext4_discard_preallocations() from here.
+ */
+void ext4_da_update_reserve_space(struct inode *inode,
+ int used, int quota_claim)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- int total, mdb, mdb_free;
-
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- /* recalculate the number of metablocks still need to be reserved */
- total = EXT4_I(inode)->i_reserved_data_blocks - used;
- mdb = ext4_calc_metadata_amount(inode, total);
-
- /* figure out how many metablocks to release */
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
- if (mdb_free) {
- /* Account for allocated meta_blocks */
- mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
-
- /* update fs dirty blocks counter */
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int mdb_free = 0, allocated_meta_blocks = 0;
+
+ spin_lock(&ei->i_block_reservation_lock);
+ if (unlikely(used > ei->i_reserved_data_blocks)) {
+ ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
+ "with only %d reserved data blocks\n",
+ __func__, inode->i_ino, used,
+ ei->i_reserved_data_blocks);
+ WARN_ON(1);
+ used = ei->i_reserved_data_blocks;
+ }
+
+ /* Update per-inode reservations */
+ ei->i_reserved_data_blocks -= used;
+ used += ei->i_allocated_meta_blocks;
+ ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
+ allocated_meta_blocks = ei->i_allocated_meta_blocks;
+ ei->i_allocated_meta_blocks = 0;
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, used);
+
+ if (ei->i_reserved_data_blocks == 0) {
+ /*
+ * We can release all of the reserved metadata blocks
+ * only when we have written all of the delayed
+ * allocation blocks.
+ */
+ mdb_free = ei->i_reserved_meta_blocks;
+ ei->i_reserved_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
- EXT4_I(inode)->i_allocated_meta_blocks = 0;
- EXT4_I(inode)->i_reserved_meta_blocks = mdb;
}
-
- /* update per-inode reservations */
- BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks);
- EXT4_I(inode)->i_reserved_data_blocks -= used;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);

- /*
- * free those over-booking quota for metadata blocks
- */
- if (mdb_free)
- vfs_dq_release_reservation_block(inode, mdb_free);
+ /* Update quota subsystem */
+ if (quota_claim) {
+ vfs_dq_claim_block(inode, used);
+ if (mdb_free)
+ vfs_dq_release_reservation_block(inode, mdb_free);
+ } else {
+ /*
+ * We did fallocate with an offset that is already delayed
+ * allocated. So on delayed allocated writeback we should
+ * not update the quota for allocated blocks. But then
+ * converting an fallocate region to initialized region would
+ * have caused a metadata allocation. So claim quota for
+ * that
+ */
+ if (allocated_meta_blocks)
+ vfs_dq_claim_block(inode, allocated_meta_blocks);
+ vfs_dq_release_reservation_block(inode, mdb_free + used -
+ allocated_meta_blocks);
+ }

/*
* If we have done all the pending block allocations and if
* there aren't any writers on the inode, we can discard the
* inode's preallocations.
*/
- if (!total && (atomic_read(&inode->i_writecount) == 0))
+ if ((ei->i_reserved_data_blocks == 0) &&
+ (atomic_read(&inode->i_writecount) == 0))
ext4_discard_preallocations(inode);
}

@@ -1240,7 +1274,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
* file system block.
*/
down_read((&EXT4_I(inode)->i_data_sem));
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
bh, 0);
} else {
@@ -1302,7 +1336,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
*/
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
bh, flags);
} else {
@@ -1315,20 +1349,22 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
* i_data's format changing. Force the migrate
* to fail by clearing migrate flags
*/
- EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
+ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
}
- }

+ /*
+ * Update reserved blocks/metadata blocks after successful
+ * block allocation which had been deferred till now. We don't
+ * support fallocate for non extent files. So we can update
+ * reserve space here.
+ */
+ if ((retval > 0) &&
+ (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
+ ext4_da_update_reserve_space(inode, retval, 1);
+ }
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
EXT4_I(inode)->i_delalloc_reserved_flag = 0;

- /*
- * Update reserved blocks/metadata blocks after successful
- * block allocation which had been deferred till now.
- */
- if ((retval > 0) && (flags & EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE))
- ext4_da_update_reserve_space(inode, retval);
-
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && buffer_mapped(bh)) {
int ret = check_block_validity(inode, "file system "
@@ -1800,7 +1836,7 @@ static int ext4_journalled_write_end(struct file *file,
new_i_size = pos + copied;
if (new_i_size > inode->i_size)
i_size_write(inode, pos+copied);
- EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
+ ext4_set_inode_state(inode, EXT4_STATE_JDATA);
if (new_i_size > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, new_i_size);
ret2 = ext4_mark_inode_dirty(handle, inode);
@@ -1834,11 +1870,15 @@ static int ext4_journalled_write_end(struct file *file,
return ret ? ret : copied;
}

-static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
+/*
+ * Reserve a single block located at lblock
+ */
+static int ext4_da_reserve_space(struct inode *inode, sector_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned long md_needed, mdblocks, total = 0;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned long md_needed, md_reserved;

/*
* recalculate the amount of metadata blocks to reserve
@@ -1846,35 +1886,31 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
* worse case is one extent per block
*/
repeat:
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
- mdblocks = ext4_calc_metadata_amount(inode, total);
- BUG_ON(mdblocks < EXT4_I(inode)->i_reserved_meta_blocks);
-
- md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
- total = md_needed + nrblocks;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ spin_lock(&ei->i_block_reservation_lock);
+ md_reserved = ei->i_reserved_meta_blocks;
+ md_needed = ext4_calc_metadata_amount(inode, lblock);
+ spin_unlock(&ei->i_block_reservation_lock);

/*
* Make quota reservation here to prevent quota overflow
* later. Real quota accounting is done at pages writeout
* time.
*/
- if (vfs_dq_reserve_block(inode, total))
+ if (vfs_dq_reserve_block(inode, md_needed + 1))
return -EDQUOT;

- if (ext4_claim_free_blocks(sbi, total)) {
- vfs_dq_release_reservation_block(inode, total);
+ if (ext4_claim_free_blocks(sbi, md_needed + 1)) {
+ vfs_dq_release_reservation_block(inode, md_needed + 1);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
}
return -ENOSPC;
}
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
- EXT4_I(inode)->i_reserved_meta_blocks += md_needed;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ spin_lock(&ei->i_block_reservation_lock);
+ ei->i_reserved_data_blocks++;
+ ei->i_reserved_meta_blocks += md_needed;
+ spin_unlock(&ei->i_block_reservation_lock);

return 0; /* success */
}
@@ -1882,49 +1918,46 @@ repeat:
static void ext4_da_release_space(struct inode *inode, int to_free)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- int total, mdb, mdb_free, release;
+ struct ext4_inode_info *ei = EXT4_I(inode);

if (!to_free)
return; /* Nothing to release, exit */

spin_lock(&EXT4_I(inode)->i_block_reservation_lock);

- if (!EXT4_I(inode)->i_reserved_data_blocks) {
+ if (unlikely(to_free > ei->i_reserved_data_blocks)) {
/*
- * if there is no reserved blocks, but we try to free some
- * then the counter is messed up somewhere.
- * but since this function is called from invalidate
- * page, it's harmless to return without any action
+ * if there aren't enough reserved blocks, then the
+ * counter is messed up somewhere. Since this
+ * function is called from invalidate page, it's
+ * harmless to return without any action.
*/
- printk(KERN_INFO "ext4 delalloc try to release %d reserved "
- "blocks for inode %lu, but there is no reserved "
- "data blocks\n", to_free, inode->i_ino);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- return;
+ ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
+ "ino %lu, to_free %d with only %d reserved "
+ "data blocks\n", inode->i_ino, to_free,
+ ei->i_reserved_data_blocks);
+ WARN_ON(1);
+ to_free = ei->i_reserved_data_blocks;
}
+ ei->i_reserved_data_blocks -= to_free;

- /* recalculate the number of metablocks still need to be reserved */
- total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
- mdb = ext4_calc_metadata_amount(inode, total);
-
- /* figure out how many metablocks to release */
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
- release = to_free + mdb_free;
-
- /* update fs dirty blocks counter for truncate case */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
+ if (ei->i_reserved_data_blocks == 0) {
+ /*
+ * We can release all of the reserved metadata blocks
+ * only when we have written all of the delayed
+ * allocation blocks.
+ */
+ to_free += ei->i_reserved_meta_blocks;
+ ei->i_reserved_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
+ }

- /* update per-inode reservations */
- BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
- EXT4_I(inode)->i_reserved_data_blocks -= to_free;
+ /* update fs dirty blocks counter */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);

- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- EXT4_I(inode)->i_reserved_meta_blocks = mdb;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);

- vfs_dq_release_reservation_block(inode, release);
+ vfs_dq_release_reservation_block(inode, to_free);
}

static void ext4_da_page_release_reservation(struct page *page,
@@ -2229,10 +2262,10 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
* variables are updated after the blocks have been allocated.
*/
new.b_state = 0;
- get_blocks_flags = (EXT4_GET_BLOCKS_CREATE |
- EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+ get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
if (mpd->b_state & (1 << BH_Delay))
- get_blocks_flags |= EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE;
+ get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
+
blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks,
&new, get_blocks_flags);
if (blks < 0) {
@@ -2261,7 +2294,7 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
ext4_msg(mpd->inode->i_sb, KERN_CRIT,
"delayed block allocation failed for inode %lu at "
"logical offset %llu with max blocks %zd with "
- "error %d\n", mpd->inode->i_ino,
+ "error %d", mpd->inode->i_ino,
(unsigned long long) next,
mpd->b_size >> mpd->inode->i_blkbits, err);
printk(KERN_CRIT "This should not happen!! "
@@ -2328,8 +2361,17 @@ static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
sector_t next;
int nrblocks = mpd->b_size >> mpd->inode->i_blkbits;

+ /*
+ * XXX Don't go larger than mballoc is willing to allocate
+ * This is a stopgap solution. We eventually need to fold
+ * mpage_da_submit_io() into this function and then call
+ * ext4_get_blocks() multiple times in a loop
+ */
+ if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize)
+ goto flush_it;
+
/* check if thereserved journal credits might overflow */
- if (!(EXT4_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS))) {
if (nrblocks >= EXT4_MAX_TRANS_DATA) {
/*
* With non-extent format we are limited by the journal
@@ -2530,7 +2572,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
*/
- ret = ext4_da_reserve_space(inode, 1);
+ ret = ext4_da_reserve_space(inode, iblock);
if (ret)
/* not enough space to reserve */
return ret;
@@ -2641,7 +2683,7 @@ static int __ext4_journalled_writepage(struct page *page,
ret = err;

walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
- EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
+ ext4_set_inode_state(inode, EXT4_STATE_JDATA);
out:
return ret;
}
@@ -2794,7 +2836,7 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
* number of contiguous block. So we will limit
* number of contiguous block to a sane value
*/
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) &&
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
(max_blocks > EXT4_MAX_TRANS_DATA))
max_blocks = EXT4_MAX_TRANS_DATA;

@@ -2914,7 +2956,7 @@ retry:
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
- "%ld pages, ino %lu; err %d\n", __func__,
+ "%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
goto out_writepages;
}
@@ -2989,7 +3031,7 @@ retry:
if (pages_skipped != wbc->pages_skipped)
ext4_msg(inode->i_sb, KERN_CRIT,
"This should not happen leaving %s "
- "with nr_to_write = %ld ret = %d\n",
+ "with nr_to_write = %ld ret = %d",
__func__, wbc->nr_to_write, ret);

/* Update index */
@@ -3005,8 +3047,7 @@ retry:
out_writepages:
if (!no_nrwrite_index_update)
wbc->no_nrwrite_index_update = 0;
- if (wbc->nr_to_write > nr_to_writebump)
- wbc->nr_to_write -= nr_to_writebump;
+ wbc->nr_to_write -= nr_to_writebump;
wbc->range_start = range_start;
trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
return ret;
@@ -3050,7 +3091,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
- int ret, retries = 0;
+ int ret, retries = 0, quota_retries = 0;
struct page *page;
pgoff_t index;
unsigned from, to;
@@ -3109,6 +3150,22 @@ retry:

if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
+
+ if ((ret == -EDQUOT) &&
+ EXT4_I(inode)->i_reserved_meta_blocks &&
+ (quota_retries++ < 3)) {
+ /*
+ * Since we often over-estimate the number of meta
+ * data blocks required, we may sometimes get a
+ * spurios out of quota error even though there would
+ * be enough space once we write the data blocks and
+ * find out how many meta data blocks were _really_
+ * required. So try forcing the inode write to see if
+ * that helps.
+ */
+ write_inode_now(inode, (quota_retries == 3));
+ goto retry;
+ }
out:
return ret;
}
@@ -3297,7 +3354,8 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
filemap_write_and_wait(mapping);
}

- if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
+ if (EXT4_JOURNAL(inode) &&
+ ext4_test_inode_state(inode, EXT4_STATE_JDATA)) {
/*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
@@ -3316,7 +3374,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
* everything they get.
*/

- EXT4_I(inode)->i_state &= ~EXT4_STATE_JDATA;
+ ext4_clear_inode_state(inode, EXT4_STATE_JDATA);
journal = EXT4_JOURNAL(inode);
jbd2_journal_lock_updates(journal);
err = jbd2_journal_flush(journal);
@@ -3432,6 +3490,9 @@ retry:
* but cannot extend i_size. Bail out and pretend
* the write failed... */
ret = PTR_ERR(handle);
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+
goto out;
}
if (inode->i_nlink)
@@ -3784,8 +3845,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
ext4_free_io_end(iocb->private);
iocb->private = NULL;
- } else if (ret > 0 && (EXT4_I(inode)->i_state &
- EXT4_STATE_DIO_UNWRITTEN)) {
+ } else if (ret > 0 && ext4_test_inode_state(inode,
+ EXT4_STATE_DIO_UNWRITTEN)) {
int err;
/*
* for non AIO case, since the IO is already
@@ -3795,7 +3856,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
offset, ret);
if (err < 0)
ret = err;
- EXT4_I(inode)->i_state &= ~EXT4_STATE_DIO_UNWRITTEN;
+ ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
}
return ret;
}
@@ -3811,7 +3872,7 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;

- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);

return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
@@ -4442,10 +4503,12 @@ void ext4_truncate(struct inode *inode)
if (!ext4_can_truncate(inode))
return;

+ ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
- ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;
+ ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);

- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
ext4_ext_truncate(inode);
return;
}
@@ -4729,7 +4792,7 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
{
/* We have all inode data except xattrs in memory here. */
return __ext4_get_inode_loc(inode, iloc,
- !(EXT4_I(inode)->i_state & EXT4_STATE_XATTR));
+ !ext4_test_inode_state(inode, EXT4_STATE_XATTR));
}

void ext4_set_inode_flags(struct inode *inode)
@@ -4823,7 +4886,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);

- ei->i_state = 0;
+ ei->i_state_flags = 0;
ei->i_dir_start_lookup = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
@@ -4906,7 +4969,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
EXT4_GOOD_OLD_INODE_SIZE +
ei->i_extra_isize;
if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC))
- ei->i_state |= EXT4_STATE_XATTR;
+ ext4_set_inode_state(inode, EXT4_STATE_XATTR);
}
} else
ei->i_extra_isize = 0;
@@ -5046,7 +5109,7 @@ static int ext4_do_update_inode(handle_t *handle,

/* For fields not not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
- if (ei->i_state & EXT4_STATE_NEW)
+ if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);

ext4_get_inode_flags(ei);
@@ -5110,7 +5173,7 @@ static int ext4_do_update_inode(handle_t *handle,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
sb->s_dirt = 1;
ext4_handle_sync(handle);
- err = ext4_handle_dirty_metadata(handle, inode,
+ err = ext4_handle_dirty_metadata(handle, NULL,
EXT4_SB(sb)->s_sbh);
}
}
@@ -5139,10 +5202,10 @@ static int ext4_do_update_inode(handle_t *handle,
}

BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- rc = ext4_handle_dirty_metadata(handle, inode, bh);
+ rc = ext4_handle_dirty_metadata(handle, NULL, bh);
if (!err)
err = rc;
- ei->i_state &= ~EXT4_STATE_NEW;
+ ext4_clear_inode_state(inode, EXT4_STATE_NEW);

ext4_update_inode_fsync_trans(handle, inode, 0);
out_brelse:
@@ -5207,7 +5270,7 @@ int ext4_write_inode(struct inode *inode, int wait)
} else {
struct ext4_iloc iloc;

- err = ext4_get_inode_loc(inode, &iloc);
+ err = __ext4_get_inode_loc(inode, &iloc, 0);
if (err)
return err;
if (wait)
@@ -5220,6 +5283,7 @@ int ext4_write_inode(struct inode *inode, int wait)
(unsigned long long)iloc.bh->b_blocknr);
err = -EIO;
}
+ brelse(iloc.bh);
}
return err;
}
@@ -5286,7 +5350,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
}

if (attr->ia_valid & ATTR_SIZE) {
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);

if (attr->ia_size > sbi->s_bitmap_maxbytes) {
@@ -5297,7 +5361,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
}

if (S_ISREG(inode->i_mode) &&
- attr->ia_valid & ATTR_SIZE && attr->ia_size < inode->i_size) {
+ attr->ia_valid & ATTR_SIZE &&
+ (attr->ia_size < inode->i_size ||
+ (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))) {
handle_t *handle;

handle = ext4_journal_start(inode, 3);
@@ -5328,6 +5394,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
goto err_out;
}
}
+ /* ext4_truncate will clear the flag */
+ if ((ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))
+ ext4_truncate(inode);
}

rc = inode_setattr(inode, attr);
@@ -5402,7 +5471,7 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,

static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
}
@@ -5566,8 +5635,8 @@ static int ext4_expand_extra_isize(struct inode *inode,
entry = IFIRST(header);

/* No extended attributes present */
- if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR) ||
- header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
+ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
+ header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
new_extra_isize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
@@ -5611,7 +5680,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (ext4_handle_valid(handle) &&
EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
- !(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
+ !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
/*
* We need extra buffer credits since we may write into EA block
* with this same handle. If journal_extend fails, then it will
@@ -5625,7 +5694,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+ ext4_set_inode_state(inode,
+ EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb, __func__,
@@ -5692,7 +5762,7 @@ static int ext4_pin_inode(handle_t *handle, struct inode *inode)
err = jbd2_journal_get_write_access(handle, iloc.bh);
if (!err)
err = ext4_handle_dirty_metadata(handle,
- inode,
+ NULL,
iloc.bh);
brelse(iloc.bh);
}
@@ -5736,9 +5806,9 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
*/

if (val)
- EXT4_I(inode)->i_flags |= EXT4_JOURNAL_DATA_FL;
+ ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
else
- EXT4_I(inode)->i_flags &= ~EXT4_JOURNAL_DATA_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
ext4_set_aops(inode);

jbd2_journal_unlock_updates(journal);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index b63d193..bf5ae88 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -92,6 +92,15 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
flags &= ~EXT4_EXTENTS_FL;
}

+ if (flags & EXT4_EOFBLOCKS_FL) {
+ /* we don't support adding EOFBLOCKS flag */
+ if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
+ err = -EOPNOTSUPP;
+ goto flags_out;
+ }
+ } else if (oldflags & EXT4_EOFBLOCKS_FL)
+ ext4_truncate(inode);
+
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
@@ -249,7 +258,8 @@ setversion_out:
if (me.moved_len > 0)
file_remove_suid(donor_filp);

- if (copy_to_user((struct move_extent *)arg, &me, sizeof(me)))
+ if (copy_to_user((struct move_extent __user *)arg,
+ &me, sizeof(me)))
err = -EFAULT;
mext_out:
fput(donor_filp);
@@ -363,7 +373,30 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC32_SETRSVSZ:
cmd = EXT4_IOC_SETRSVSZ;
break;
- case EXT4_IOC_GROUP_ADD:
+ case EXT4_IOC32_GROUP_ADD: {
+ struct compat_ext4_new_group_input __user *uinput;
+ struct ext4_new_group_input input;
+ mm_segment_t old_fs;
+ int err;
+
+ uinput = compat_ptr(arg);
+ err = get_user(input.group, &uinput->group);
+ err |= get_user(input.block_bitmap, &uinput->block_bitmap);
+ err |= get_user(input.inode_bitmap, &uinput->inode_bitmap);
+ err |= get_user(input.inode_table, &uinput->inode_table);
+ err |= get_user(input.blocks_count, &uinput->blocks_count);
+ err |= get_user(input.reserved_blocks,
+ &uinput->reserved_blocks);
+ if (err)
+ return -EFAULT;
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ err = ext4_ioctl(file, EXT4_IOC_GROUP_ADD,
+ (unsigned long) &input);
+ set_fs(old_fs);
+ return err;
+ }
+ case EXT4_IOC_MOVE_EXT:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7d71148..04e07e2 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -658,6 +658,27 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
}
}

+/*
+ * Cache the order of the largest free extent we have available in this block
+ * group.
+ */
+static void
+mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
+{
+ int i;
+ int bits;
+
+ grp->bb_largest_free_order = -1; /* uninit */
+
+ bits = sb->s_blocksize_bits + 1;
+ for (i = bits; i >= 0; i--) {
+ if (grp->bb_counters[i] > 0) {
+ grp->bb_largest_free_order = i;
+ break;
+ }
+ }
+}
+
static noinline_for_stack
void ext4_mb_generate_buddy(struct super_block *sb,
void *buddy, void *bitmap, ext4_group_t group)
@@ -700,6 +721,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
*/
grp->bb_free = free;
}
+ mb_set_largest_free_order(sb, grp);

clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));

@@ -725,6 +747,9 @@ void ext4_mb_generate_buddy(struct super_block *sb,
* contain blocks_per_page (PAGE_CACHE_SIZE / blocksize) blocks.
* So it can have information regarding groups_per_page which
* is blocks_per_page/2
+ *
+ * Locking note: This routine takes the block group lock of all groups
+ * for this page; do not hold this lock when calling this routine!
*/

static int ext4_mb_init_cache(struct page *page, char *incore)
@@ -910,6 +935,11 @@ out:
return err;
}

+/*
+ * Locking note: This routine calls ext4_mb_init_cache(), which takes the
+ * block group lock of all groups for this page; do not hold the BG lock when
+ * calling this routine!
+ */
static noinline_for_stack
int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
{
@@ -1004,6 +1034,11 @@ err:
return ret;
}

+/*
+ * Locking note: This routine calls ext4_mb_init_cache(), which takes the
+ * block group lock of all groups for this page; do not hold the BG lock when
+ * calling this routine!
+ */
static noinline_for_stack int
ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
struct ext4_buddy *e4b)
@@ -1150,7 +1185,7 @@ err:
return ret;
}

-static void ext4_mb_release_desc(struct ext4_buddy *e4b)
+static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
{
if (e4b->bd_bitmap_page)
page_cache_release(e4b->bd_bitmap_page);
@@ -1300,6 +1335,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
buddy = buddy2;
} while (1);
}
+ mb_set_largest_free_order(sb, e4b->bd_info);
mb_check_buddy(e4b);
}

@@ -1428,6 +1464,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
e4b->bd_info->bb_counters[ord]++;
e4b->bd_info->bb_counters[ord]++;
}
+ mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);

mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
mb_check_buddy(e4b);
@@ -1618,7 +1655,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
}

ext4_unlock_group(ac->ac_sb, group);
- ext4_mb_release_desc(e4b);
+ ext4_mb_unload_buddy(e4b);

return 0;
}
@@ -1674,7 +1711,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
ext4_mb_use_best_found(ac, e4b);
}
ext4_unlock_group(ac->ac_sb, group);
- ext4_mb_release_desc(e4b);
+ ext4_mb_unload_buddy(e4b);

return 0;
}
@@ -1823,16 +1860,22 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
}
}

+/* This is now called BEFORE we load the buddy bitmap. */
static int ext4_mb_good_group(struct ext4_allocation_context *ac,
ext4_group_t group, int cr)
{
unsigned free, fragments;
- unsigned i, bits;
int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb));
struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);

BUG_ON(cr < 0 || cr >= 4);
- BUG_ON(EXT4_MB_GRP_NEED_INIT(grp));
+
+ /* We only do this if the grp has never been initialized */
+ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+ int ret = ext4_mb_init_group(ac->ac_sb, group);
+ if (ret)
+ return 0;
+ }

free = grp->bb_free;
fragments = grp->bb_fragments;
@@ -1845,17 +1888,16 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
case 0:
BUG_ON(ac->ac_2order == 0);

+ if (grp->bb_largest_free_order < ac->ac_2order)
+ return 0;
+
/* Avoid using the first bg of a flexgroup for data files */
if ((ac->ac_flags & EXT4_MB_HINT_DATA) &&
(flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) &&
((group % flex_size) == 0))
return 0;

- bits = ac->ac_sb->s_blocksize_bits + 1;
- for (i = ac->ac_2order; i <= bits; i++)
- if (grp->bb_counters[i] > 0)
- return 1;
- break;
+ return 1;
case 1:
if ((free / fragments) >= ac->ac_g_ex.fe_len)
return 1;
@@ -1966,7 +2008,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
sbi = EXT4_SB(sb);
ngroups = ext4_get_groups_count(sb);
/* non-extent files are limited to low blocks/groups */
- if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)))
ngroups = sbi->s_blockfile_groups;

BUG_ON(ac->ac_status == AC_STATUS_FOUND);
@@ -2026,15 +2068,11 @@ repeat:
group = ac->ac_g_ex.fe_group;

for (i = 0; i < ngroups; group++, i++) {
- struct ext4_group_info *grp;
- struct ext4_group_desc *desc;
-
if (group == ngroups)
group = 0;

- /* quick check to skip empty groups */
- grp = ext4_get_group_info(sb, group);
- if (grp->bb_free == 0)
+ /* This now checks without needing the buddy page */
+ if (!ext4_mb_good_group(ac, group, cr))
continue;

err = ext4_mb_load_buddy(sb, group, &e4b);
@@ -2042,15 +2080,18 @@ repeat:
goto out;

ext4_lock_group(sb, group);
+
+ /*
+ * We need to check again after locking the
+ * block group
+ */
if (!ext4_mb_good_group(ac, group, cr)) {
- /* someone did allocation from this group */
ext4_unlock_group(sb, group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
continue;
}

ac->ac_groups_scanned++;
- desc = ext4_get_group_desc(sb, group, NULL);
if (cr == 0)
ext4_mb_simple_scan_group(ac, &e4b);
else if (cr == 1 &&
@@ -2060,7 +2101,7 @@ repeat:
ext4_mb_complex_scan_group(ac, &e4b);

ext4_unlock_group(sb, group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);

if (ac->ac_status != AC_STATUS_CONTINUE)
break;
@@ -2150,7 +2191,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
ext4_lock_group(sb, group);
memcpy(&sg, ext4_get_group_info(sb, group), i);
ext4_unlock_group(sb, group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);

seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
sg.info.bb_fragments, sg.info.bb_first_free);
@@ -2257,6 +2298,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
init_rwsem(&meta_group_info[i]->alloc_sem);
meta_group_info[i]->bb_free_root.rb_node = NULL;
+ meta_group_info[i]->bb_largest_free_order = -1; /* uninit */

#ifdef DOUBLE_CHECK
{
@@ -2537,6 +2579,23 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
entry->count, entry->group, entry);

+ if (test_opt(sb, DISCARD)) {
+ int ret;
+ ext4_fsblk_t discard_block;
+
+ discard_block = entry->start_blk +
+ ext4_group_first_block_no(sb, entry->group);
+ trace_ext4_discard_blocks(sb,
+ (unsigned long long)discard_block,
+ entry->count);
+ ret = sb_issue_discard(sb, discard_block, entry->count);
+ if (ret == EOPNOTSUPP) {
+ ext4_warning(sb, __func__,
+ "discard not supported, disabling");
+ clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);
+ }
+ }
+
err = ext4_mb_load_buddy(sb, entry->group, &e4b);
/* we expect to find existing buddy because it's pinned */
BUG_ON(err != 0);
@@ -2558,21 +2617,8 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
page_cache_release(e4b.bd_bitmap_page);
}
ext4_unlock_group(sb, entry->group);
- if (test_opt(sb, DISCARD)) {
- ext4_fsblk_t discard_block;
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
-
- discard_block = (ext4_fsblk_t)entry->group *
- EXT4_BLOCKS_PER_GROUP(sb)
- + entry->start_blk
- + le32_to_cpu(es->s_first_data_block);
- trace_ext4_discard_blocks(sb,
- (unsigned long long)discard_block,
- entry->count);
- sb_issue_discard(sb, discard_block, entry->count);
- }
kmem_cache_free(ext4_free_ext_cachep, entry);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
}

mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
@@ -2755,12 +2801,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
/* release all the reserved blocks if non delalloc */
percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
- else {
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
- ac->ac_b_ex.fe_len);
- /* convert reserved quota blocks to real quota blocks */
- vfs_dq_claim_block(ac->ac_inode, ac->ac_b_ex.fe_len);
- }

if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
@@ -3136,7 +3176,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
continue;

/* non-extent files can't have physical blocks past 2^32 */
- if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL) &&
+ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
continue;

@@ -3715,7 +3755,7 @@ out:
ext4_unlock_group(sb, group);
if (ac)
kmem_cache_free(ext4_ac_cachep, ac);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
put_bh(bitmap_bh);
return free;
}
@@ -3819,7 +3859,7 @@ repeat:
if (bitmap_bh == NULL) {
ext4_error(sb, __func__, "Error in reading block "
"bitmap for %u", group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
continue;
}

@@ -3828,7 +3868,7 @@ repeat:
ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa, ac);
ext4_unlock_group(sb, group);

- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
put_bh(bitmap_bh);

list_del(&pa->u.pa_tmp_list);
@@ -3944,7 +3984,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)

/* don't use group allocation for large files */
size = max(size, isize);
- if (size >= sbi->s_mb_stream_request) {
+ if (size > sbi->s_mb_stream_request) {
ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
return;
}
@@ -4092,7 +4132,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
ext4_mb_release_group_pa(&e4b, pa, ac);
ext4_unlock_group(sb, group);

- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
list_del(&pa->u.pa_tmp_list);
call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
}
@@ -4594,7 +4634,7 @@ do_more:
atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
}

- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);

*freed += count;

diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 8646149..7901f13 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -357,12 +357,12 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
* happened after we started the migrate. We need to
* fail the migrate
*/
- if (!(EXT4_I(inode)->i_state & EXT4_STATE_EXT_MIGRATE)) {
+ if (!ext4_test_inode_state(inode, EXT4_STATE_EXT_MIGRATE)) {
retval = -EAGAIN;
up_write(&EXT4_I(inode)->i_data_sem);
goto err_out;
} else
- EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
+ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
/*
* We have the extent map build with the tmp inode.
* Now copy the i_data across
@@ -465,7 +465,7 @@ int ext4_ext_migrate(struct inode *inode)
*/
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
- (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;

if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
@@ -494,14 +494,10 @@ int ext4_ext_migrate(struct inode *inode)
}
i_size_write(tmp_inode, i_size_read(inode));
/*
- * We don't want the inode to be reclaimed
- * if we got interrupted in between. We have
- * this tmp inode carrying reference to the
- * data blocks of the original file. We set
- * the i_nlink to zero at the last stage after
- * switching the original file to extent format
+ * Set the i_nlink to zero so it will be deleted later
+ * when we drop inode reference.
*/
- tmp_inode->i_nlink = 1;
+ tmp_inode->i_nlink = 0;

ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
@@ -524,10 +520,20 @@ int ext4_ext_migrate(struct inode *inode)
* allocation.
*/
down_read((&EXT4_I(inode)->i_data_sem));
- EXT4_I(inode)->i_state |= EXT4_STATE_EXT_MIGRATE;
+ ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));

handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle)) {
+ /*
+ * It is impossible to update on-disk structures without
+ * a handle, so just rollback in-core changes and live other
+ * work to orphan_list_cleanup()
+ */
+ ext4_orphan_del(NULL, tmp_inode);
+ retval = PTR_ERR(handle);
+ goto out;
+ }

ei = EXT4_I(inode);
i_data = ei->i_data;
@@ -609,15 +615,8 @@ err_out:

/* Reset the extent details */
ext4_ext_tree_init(handle, tmp_inode);
-
- /*
- * Set the i_nlink to zero so that
- * generic_drop_inode really deletes the
- * inode
- */
- tmp_inode->i_nlink = 0;
-
ext4_journal_stop(handle);
+out:
unlock_new_inode(tmp_inode);
iput(tmp_inode);

diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index f5b03a1..5b14d11 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -252,6 +252,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
}

o_start->ee_len = start_ext->ee_len;
+ eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;

} else if (start_ext->ee_len && new_ext->ee_len &&
@@ -262,6 +263,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
* orig |------------------------------|
*/
o_start->ee_len = start_ext->ee_len;
+ eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;

} else if (!start_ext->ee_len && new_ext->ee_len &&
@@ -475,7 +477,6 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
struct ext4_extent new_ext, start_ext, end_ext;
ext4_lblk_t new_ext_end;
- ext4_fsblk_t new_phys_end;
int oext_alen, new_ext_alen, end_ext_alen;
int depth = ext_depth(orig_inode);
int ret;
@@ -489,7 +490,6 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
new_ext.ee_len = dext->ee_len;
new_ext_alen = ext4_ext_get_actual_len(&new_ext);
new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
- new_phys_end = ext_pblock(&new_ext) + new_ext_alen - 1;

/*
* Case: original extent is first
@@ -502,6 +502,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
le32_to_cpu(oext->ee_block) + oext_alen) {
start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
le32_to_cpu(oext->ee_block));
+ start_ext.ee_block = oext->ee_block;
copy_extent_status(oext, &start_ext);
} else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
prev_ext = oext - 1;
@@ -515,6 +516,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
start_ext.ee_len = cpu_to_le16(
ext4_ext_get_actual_len(prev_ext) +
new_ext_alen);
+ start_ext.ee_block = oext->ee_block;
copy_extent_status(prev_ext, &start_ext);
new_ext.ee_len = 0;
}
@@ -928,7 +930,7 @@ out2:
}

/**
- * mext_check_argumants - Check whether move extent can be done
+ * mext_check_arguments - Check whether move extent can be done
*
* @orig_inode: original inode
* @donor_inode: donor inode
@@ -949,14 +951,6 @@ mext_check_arguments(struct inode *orig_inode,
unsigned int blkbits = orig_inode->i_blkbits;
unsigned int blocksize = 1 << blkbits;

- /* Regular file check */
- if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
- ext4_debug("ext4 move extent: The argument files should be "
- "regular file [ino:orig %lu, donor %lu]\n",
- orig_inode->i_ino, donor_inode->i_ino);
- return -EINVAL;
- }
-
if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
ext4_debug("ext4 move extent: suid or sgid is set"
" to donor file [ino:orig %lu, donor %lu]\n",
@@ -981,11 +975,11 @@ mext_check_arguments(struct inode *orig_inode,
}

/* Ext4 move extent supports only extent based file */
- if (!(EXT4_I(orig_inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: orig file is not extents "
"based file [ino:orig %lu]\n", orig_inode->i_ino);
return -EOPNOTSUPP;
- } else if (!(EXT4_I(donor_inode)->i_flags & EXT4_EXTENTS_FL)) {
+ } else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: donor file is not extents "
"based file [ino:donor %lu]\n", donor_inode->i_ino);
return -EOPNOTSUPP;
@@ -1204,6 +1198,14 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
return -EINVAL;
}

+ /* Regular file check */
+ if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
+ ext4_debug("ext4 move extent: The argument files should be "
+ "regular file [ino:orig %lu, donor %lu]\n",
+ orig_inode->i_ino, donor_inode->i_ino);
+ return -EINVAL;
+ }
+
/* Protect orig and donor inodes against a truncate */
ret1 = mext_inode_double_lock(orig_inode, donor_inode);
if (ret1 < 0)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 17a17e1..c3b6ad0 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -660,7 +660,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
start_hash, start_minor_hash));
dir = dir_file->f_path.dentry->d_inode;
- if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
+ if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) {
hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
if (hinfo.hash_version <= DX_HASH_TEA)
hinfo.hash_version +=
@@ -805,7 +805,7 @@ static void ext4_update_dx_flag(struct inode *inode)
{
if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_COMPAT_DIR_INDEX))
- EXT4_I(inode)->i_flags &= ~EXT4_INDEX_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
}

/*
@@ -1424,7 +1424,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
brelse(bh);
return retval;
}
- EXT4_I(dir)->i_flags |= EXT4_INDEX_FL;
+ ext4_set_inode_flag(dir, EXT4_INODE_INDEX);
data1 = bh2->b_data;

memcpy (data1, de, len);
@@ -1497,7 +1497,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
retval = ext4_dx_add_entry(handle, dentry, inode);
if (!retval || (retval != ERR_BAD_DX_DIR))
return retval;
- EXT4_I(dir)->i_flags &= ~EXT4_INDEX_FL;
+ ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
dx_fallback++;
ext4_mark_inode_dirty(handle, dir);
}
@@ -1525,6 +1525,8 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
brelse(bh);
+ if (retval == 0)
+ ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY);
return retval;
}

@@ -2020,11 +2022,18 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out_unlock;
+ /*
+ * Due to previous errors inode may be already a part of on-disk
+ * orphan list. If so skip on-disk list modification.
+ */
+ if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)))
+ goto mem_insert;

/* Insert this inode at the head of the on-disk orphan list... */
NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
- err = ext4_handle_dirty_metadata(handle, inode, EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
@@ -2037,6 +2046,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
*
* This is safe: on error we're going to ignore the orphan list
* anyway on the next recovery. */
+mem_insert:
if (!err)
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);

@@ -2096,7 +2106,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
if (err)
goto out_brelse;
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
- err = ext4_handle_dirty_metadata(handle, inode, sbi->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
@@ -2284,7 +2294,7 @@ retry:
}
} else {
/* clear the extent format for fast symlink */
- EXT4_I(inode)->i_flags &= ~EXT4_EXTENTS_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
inode->i_op = &ext4_fast_symlink_inode_operations;
memcpy((char *)&EXT4_I(inode)->i_data, symname, l);
inode->i_size = l-1;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 3b2c554..433ea27 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -930,7 +930,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
percpu_counter_add(&sbi->s_freeinodes_counter,
EXT4_INODES_PER_GROUP(sb));

- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
+ sbi->s_log_groups_per_flex) {
ext4_group_t flex_group;
flex_group = ext4_flex_group(sbi, input->group);
atomic_add(input->free_blocks_count,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 92943f2..54a05cc 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -227,6 +227,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);

+ vfs_check_frozen(sb, SB_FREEZE_WRITE);
/* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly. */
@@ -702,6 +703,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
ei->i_delalloc_reserved_flag = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
@@ -875,6 +877,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
seq_puts(seq, ",journal_async_commit");
+ else if (test_opt(sb, JOURNAL_CHECKSUM))
+ seq_puts(seq, ",journal_checksum");
if (test_opt(sb, NOBH))
seq_puts(seq, ",nobh");
if (test_opt(sb, I_VERSION))
@@ -2693,24 +2697,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);

- err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
- if (!err) {
- err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext4_count_free_inodes(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
- }
- if (err) {
- ext4_msg(sb, KERN_ERR, "insufficient memory");
- goto failed_mount3;
- }
-
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_max_writeback_mb_bump = 128;

@@ -2830,7 +2816,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);

no_journal:
-
+ err = percpu_counter_init(&sbi->s_freeblocks_counter,
+ ext4_count_free_blocks(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_freeinodes_counter,
+ ext4_count_free_inodes(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "insufficient memory");
+ goto failed_mount_wq;
+ }
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
@@ -2905,7 +2904,7 @@ no_journal:
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
- "zone (%d)\n", err);
+ "zone (%d)", err);
goto failed_mount4;
}

@@ -2963,6 +2962,10 @@ failed_mount_wq:
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
+ percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount3:
if (sbi->s_flex_groups) {
if (is_vmalloc_addr(sbi->s_flex_groups))
@@ -2970,10 +2973,6 @@ failed_mount3:
else
kfree(sbi->s_flex_groups);
}
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
- percpu_counter_destroy(&sbi->s_freeinodes_counter);
- percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
@@ -3390,8 +3389,10 @@ int ext4_force_commit(struct super_block *sb)
return 0;

journal = EXT4_SB(sb)->s_journal;
- if (journal)
+ if (journal) {
+ vfs_check_frozen(sb, SB_FREEZE_WRITE);
ret = ext4_journal_force_commit(journal);
+ }

return ret;
}
@@ -3440,18 +3441,16 @@ static int ext4_freeze(struct super_block *sb)
* the journal.
*/
error = jbd2_journal_flush(journal);
- if (error < 0) {
- out:
- jbd2_journal_unlock_updates(journal);
- return error;
- }
+ if (error < 0)
+ goto out;

/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
error = ext4_commit_super(sb, 1);
- if (error)
- goto out;
- return 0;
+out:
+ /* we rely on s_frozen to stop further updates */
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+ return error;
}

/*
@@ -3468,7 +3467,6 @@ static int ext4_unfreeze(struct super_block *sb)
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
unlock_super(sb);
- jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
return 0;
}

@@ -4001,6 +3999,7 @@ static int __init init_ext4_fs(void)
{
int err;

+ ext4_check_flag_values();
err = init_ext4_system_zone();
if (err)
return err;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 0257019..4de7d0a 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -267,7 +267,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
void *end;
int error;

- if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
+ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return -ENODATA;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
@@ -393,7 +393,7 @@ ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
void *end;
int error;

- if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
+ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return 0;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
@@ -816,7 +816,7 @@ inserted:
EXT4_I(inode)->i_block_group);

/* non-extent files can't have physical blocks past 2^32 */
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;

block = ext4_new_meta_blocks(handle, inode,
@@ -824,7 +824,7 @@ inserted:
if (error)
goto cleanup;

- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);

ea_idebug(inode, "creating block %d", block);
@@ -903,7 +903,7 @@ ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
is->s.base = is->s.first = IFIRST(header);
is->s.here = is->s.first;
is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
- if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
error = ext4_xattr_check_names(IFIRST(header), is->s.end);
if (error)
return error;
@@ -935,10 +935,10 @@ ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
header = IHDR(inode, ext4_raw_inode(&is->iloc));
if (!IS_LAST_ENTRY(s->first)) {
header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
- EXT4_I(inode)->i_state |= EXT4_STATE_XATTR;
+ ext4_set_inode_state(inode, EXT4_STATE_XATTR);
} else {
header->h_magic = cpu_to_le32(0);
- EXT4_I(inode)->i_state &= ~EXT4_STATE_XATTR;
+ ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
}
return 0;
}
@@ -981,8 +981,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
if (strlen(name) > 255)
return -ERANGE;
down_write(&EXT4_I(inode)->xattr_sem);
- no_expand = EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND;
- EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+ no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);

error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
@@ -992,10 +992,10 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
if (error)
goto cleanup;

- if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) {
+ if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) {
struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
- EXT4_I(inode)->i_state &= ~EXT4_STATE_NEW;
+ ext4_clear_inode_state(inode, EXT4_STATE_NEW);
}

error = ext4_xattr_ibody_find(inode, &i, &is);
@@ -1047,7 +1047,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
ext4_xattr_update_super_block(handle, inode->i_sb);
inode->i_ctime = ext4_current_time(inode);
if (!value)
- EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
/*
* The bh is consumed by ext4_mark_iloc_dirty, even with
@@ -1062,7 +1062,7 @@ cleanup:
brelse(is.iloc.bh);
brelse(bs.bh);
if (no_expand == 0)
- EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
up_write(&EXT4_I(inode)->xattr_sem);
return error;
}
@@ -1327,6 +1327,8 @@ retry:
goto cleanup;
kfree(b_entry_name);
kfree(buffer);
+ b_entry_name = NULL;
+ buffer = NULL;
brelse(is->iloc.bh);
kfree(is);
kfree(bs);
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 3fc4e3a..2168da1 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -12,6 +12,7 @@
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
+#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/gfs2_ondisk.h>
@@ -26,61 +27,6 @@
#include "trans.h"
#include "util.h"

-#define ACL_ACCESS 1
-#define ACL_DEFAULT 0
-
-int gfs2_acl_validate_set(struct gfs2_inode *ip, int access,
- struct gfs2_ea_request *er, int *remove, mode_t *mode)
-{
- struct posix_acl *acl;
- int error;
-
- error = gfs2_acl_validate_remove(ip, access);
- if (error)
- return error;
-
- if (!er->er_data)
- return -EINVAL;
-
- acl = posix_acl_from_xattr(er->er_data, er->er_data_len);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- if (!acl) {
- *remove = 1;
- return 0;
- }
-
- error = posix_acl_valid(acl);
- if (error)
- goto out;
-
- if (access) {
- error = posix_acl_equiv_mode(acl, mode);
- if (!error)
- *remove = 1;
- else if (error > 0)
- error = 0;
- }
-
-out:
- posix_acl_release(acl);
- return error;
-}
-
-int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access)
-{
- if (!GFS2_SB(&ip->i_inode)->sd_args.ar_posix_acl)
- return -EOPNOTSUPP;
- if (!is_owner_or_cap(&ip->i_inode))
- return -EPERM;
- if (S_ISLNK(ip->i_inode.i_mode))
- return -EOPNOTSUPP;
- if (!access && !S_ISDIR(ip->i_inode.i_mode))
- return -EACCES;
-
- return 0;
-}
-
static int acl_get(struct gfs2_inode *ip, const char *name,
struct posix_acl **acl, struct gfs2_ea_location *el,
char **datap, unsigned int *lenp)
@@ -277,3 +223,117 @@ out_brelse:
return error;
}

+static int gfs2_acl_type(const char *name)
+{
+ if (strcmp(name, GFS2_POSIX_ACL_ACCESS) == 0)
+ return ACL_TYPE_ACCESS;
+ if (strcmp(name, GFS2_POSIX_ACL_DEFAULT) == 0)
+ return ACL_TYPE_DEFAULT;
+ return -EINVAL;
+}
+
+static int gfs2_xattr_system_get(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ int type;
+
+ type = gfs2_acl_type(name);
+ if (type < 0)
+ return type;
+
+ return gfs2_xattr_get(inode, GFS2_EATYPE_SYS, name, buffer, size);
+}
+
+static int gfs2_set_mode(struct inode *inode, mode_t mode)
+{
+ int error = 0;
+
+ if (mode != inode->i_mode) {
+ struct iattr iattr;
+
+ iattr.ia_valid = ATTR_MODE;
+ iattr.ia_mode = mode;
+
+ error = gfs2_setattr_simple(GFS2_I(inode), &iattr);
+ }
+
+ return error;
+}
+
+static int gfs2_xattr_system_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ struct posix_acl *acl = NULL;
+ int error = 0, type;
+
+ if (!sdp->sd_args.ar_posix_acl)
+ return -EOPNOTSUPP;
+
+ type = gfs2_acl_type(name);
+ if (type < 0)
+ return type;
+ if (flags & XATTR_CREATE)
+ return -EINVAL;
+ if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
+ return value ? -EACCES : 0;
+ if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER))
+ return -EPERM;
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ if (!value)
+ goto set_acl;
+
+ acl = posix_acl_from_xattr(value, size);
+ if (!acl) {
+ /*
+ * acl_set_file(3) may request that we set default ACLs with
+ * zero length -- defend (gracefully) against that here.
+ */
+ goto out;
+ }
+ if (IS_ERR(acl)) {
+ error = PTR_ERR(acl);
+ goto out;
+ }
+
+ error = posix_acl_valid(acl);
+ if (error)
+ goto out_release;
+
+ error = -EINVAL;
+ if (acl->a_count > GFS2_ACL_MAX_ENTRIES)
+ goto out_release;
+
+ if (type == ACL_TYPE_ACCESS) {
+ mode_t mode = inode->i_mode;
+ error = posix_acl_equiv_mode(acl, &mode);
+
+ if (error <= 0) {
+ posix_acl_release(acl);
+ acl = NULL;
+
+ if (error < 0)
+ return error;
+ }
+
+ error = gfs2_set_mode(inode, mode);
+ if (error)
+ goto out_release;
+ }
+
+set_acl:
+ error = gfs2_xattr_set(inode, GFS2_EATYPE_SYS, name, value, size, 0);
+out_release:
+ posix_acl_release(acl);
+out:
+ return error;
+}
+
+struct xattr_handler gfs2_xattr_system_handler = {
+ .prefix = XATTR_SYSTEM_PREFIX,
+ .get = gfs2_xattr_system_get,
+ .set = gfs2_xattr_system_set,
+};
+
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
index 6751930..cc95439 100644
--- a/fs/gfs2/acl.h
+++ b/fs/gfs2/acl.h
@@ -13,26 +13,12 @@
#include "incore.h"

#define GFS2_POSIX_ACL_ACCESS "posix_acl_access"
-#define GFS2_POSIX_ACL_ACCESS_LEN 16
#define GFS2_POSIX_ACL_DEFAULT "posix_acl_default"
-#define GFS2_POSIX_ACL_DEFAULT_LEN 17
+#define GFS2_ACL_MAX_ENTRIES 25

-#define GFS2_ACL_IS_ACCESS(name, len) \
- ((len) == GFS2_POSIX_ACL_ACCESS_LEN && \
- !memcmp(GFS2_POSIX_ACL_ACCESS, (name), (len)))
-
-#define GFS2_ACL_IS_DEFAULT(name, len) \
- ((len) == GFS2_POSIX_ACL_DEFAULT_LEN && \
- !memcmp(GFS2_POSIX_ACL_DEFAULT, (name), (len)))
-
-struct gfs2_ea_request;
-
-int gfs2_acl_validate_set(struct gfs2_inode *ip, int access,
- struct gfs2_ea_request *er,
- int *remove, mode_t *mode);
-int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access);
-int gfs2_check_acl(struct inode *inode, int mask);
-int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip);
-int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr);
+extern int gfs2_check_acl(struct inode *inode, int mask);
+extern int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip);
+extern int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr);
+extern struct xattr_handler gfs2_xattr_system_handler;

#endif /* __ACL_DOT_H__ */
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 8a0f8ef..6b80354 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1507,18 +1507,6 @@ static int gfs2_xattr_user_set(struct inode *inode, const char *name,
return gfs2_xattr_set(inode, GFS2_EATYPE_USR, name, value, size, flags);
}

-static int gfs2_xattr_system_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- return gfs2_xattr_get(inode, GFS2_EATYPE_SYS, name, buffer, size);
-}
-
-static int gfs2_xattr_system_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- return gfs2_xattr_set(inode, GFS2_EATYPE_SYS, name, value, size, flags);
-}
-
static int gfs2_xattr_security_get(struct inode *inode, const char *name,
void *buffer, size_t size)
{
@@ -1543,12 +1531,6 @@ static struct xattr_handler gfs2_xattr_security_handler = {
.set = gfs2_xattr_security_set,
};

-static struct xattr_handler gfs2_xattr_system_handler = {
- .prefix = XATTR_SYSTEM_PREFIX,
- .get = gfs2_xattr_system_get,
- .set = gfs2_xattr_system_set,
-};
-
struct xattr_handler *gfs2_xattr_handlers[] = {
&gfs2_xattr_user_handler,
&gfs2_xattr_security_handler,
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index ca0f5eb..8868493 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -22,6 +22,7 @@
#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
+#include <linux/blkdev.h>
#include <trace/events/jbd2.h>

/*
@@ -515,6 +516,20 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
journal->j_tail_sequence = first_tid;
journal->j_tail = blocknr;
spin_unlock(&journal->j_state_lock);
+
+ /*
+ * If there is an external journal, we need to make sure that
+ * any data blocks that were recently written out --- perhaps
+ * by jbd2_log_do_checkpoint() --- are flushed out before we
+ * drop the transactions from the external journal. It's
+ * unlikely this will be necessary, especially with a
+ * appropriately sized journal, but we need this to guarantee
+ * correctness. Fortunately jbd2_cleanup_journal_tail()
+ * doesn't get called all that often.
+ */
+ if ((journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(journal->j_fs_dev, NULL);
if (!(journal->j_flags & JBD2_ABORT))
jbd2_journal_update_superblock(journal, 1);
return 0;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8896c1d..09ab6ac 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -259,6 +259,7 @@ static int journal_submit_data_buffers(journal_t *journal,
ret = err;
spin_lock(&journal->j_list_lock);
J_ASSERT(jinode->i_transaction == commit_transaction);
+ commit_transaction->t_flushed_data_blocks = 1;
jinode->i_flags &= ~JI_COMMIT_RUNNING;
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
@@ -708,8 +709,17 @@ start_journal_io:
}
}

- /* Done it all: now write the commit record asynchronously. */
+ /*
+ * If the journal is not located on the file system device,
+ * then we must flush the file system device before we issue
+ * the commit record
+ */
+ if (commit_transaction->t_flushed_data_blocks &&
+ (journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(journal->j_fs_dev, NULL);

+ /* Done it all: now write the commit record asynchronously. */
if (JBD2_HAS_INCOMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
err = journal_submit_commit_record(journal, commit_transaction,
@@ -720,13 +730,6 @@ start_journal_io:
blkdev_issue_flush(journal->j_dev, NULL);
}

- /*
- * This is the right place to wait for data buffers both for ASYNC
- * and !ASYNC commit. If commit is ASYNC, we need to wait only after
- * the commit block went to disk (which happens above). If commit is
- * SYNC, we need to wait for data buffers before we start writing
- * commit block, which happens below in such setting.
- */
err = journal_finish_inode_data_buffers(journal, commit_transaction);
if (err) {
printk(KERN_WARNING
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index a4cd1b7..5ec74cd 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -840,8 +840,8 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET;
*p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
*p++ = cpu_to_be32(0);
- *p++ = cpu_to_be32(iap->ia_mtime.tv_sec);
- *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec);
+ *p++ = cpu_to_be32(iap->ia_atime.tv_sec);
+ *p++ = cpu_to_be32(iap->ia_atime.tv_nsec);
}
else if (iap->ia_valid & ATTR_ATIME) {
bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 4bf23f6..a53b9e5 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -534,6 +534,22 @@ static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
}
}

+#ifdef CONFIG_NFS_V4
+static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
+ int showdefaults)
+{
+ struct nfs_client *clp = nfss->nfs_client;
+
+ seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
+ seq_printf(m, ",minorversion=%u", clp->cl_minorversion);
+}
+#else
+static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
+ int showdefaults)
+{
+}
+#endif
+
/*
* Describe the mount options in force on this server representation
*/
@@ -595,11 +611,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,

if (version != 4)
nfs_show_mountd_options(m, nfss, showdefaults);
+ else
+ nfs_show_nfsv4_options(m, nfss, showdefaults);

-#ifdef CONFIG_NFS_V4
- if (clp->rpc_ops->version == 4)
- seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
-#endif
if (nfss->options & NFS_OPTION_FSCACHE)
seq_printf(m, ",fsc");
}
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 740ac3a..e7bdaaf 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -48,7 +48,7 @@ struct acpi_power_register {
u8 space_id;
u8 bit_width;
u8 bit_offset;
- u8 reserved;
+ u8 access_size;
u64 address;
} __attribute__ ((packed));

@@ -74,6 +74,7 @@ struct acpi_processor_cx {
u32 power;
u32 usage;
u64 time;
+ u8 bm_sts_skip;
struct acpi_processor_cx_policy promotion;
struct acpi_processor_cx_policy demotion;
char desc[ACPI_CX_DESC_LEN];
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 07432a1..c010b94 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -251,7 +251,6 @@ int acpi_check_mem_region(resource_size_t start, resource_size_t n,
void __init acpi_no_s4_hw_signature(void);
void __init acpi_old_suspend_ordering(void);
void __init acpi_s4_no_nvs(void);
-void __init acpi_set_sci_en_on_resume(void);
#endif /* CONFIG_PM_SLEEP */

struct acpi_osc_context {
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 15e4eb7..7ffab7c 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -357,6 +357,8 @@ struct ethtool_rxnfc {
__u32 flow_type;
/* The rx flow hash value or the rule DB size */
__u64 data;
+ /* The following fields are not valid and must not be used for
+ * the ETHTOOL_{G,X}RXFH commands. */
struct ethtool_rx_flow_spec fs;
__u32 rule_cnt;
__u32 rule_locs[0];
diff --git a/include/linux/fb.h b/include/linux/fb.h
index de9c722..862e7d4 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -784,8 +784,6 @@ struct fb_tile_ops {
#define FBINFO_MISC_USEREVENT 0x10000 /* event request
from userspace */
#define FBINFO_MISC_TILEBLITTING 0x20000 /* use tile blitting */
-#define FBINFO_MISC_FIRMWARE 0x40000 /* a replaceable firmware
- inited framebuffer */

/* A driver may set this flag to indicate that it does want a set_par to be
* called every time when fbcon_switch is executed. The advantage is that with
@@ -799,6 +797,8 @@ struct fb_tile_ops {
*/
#define FBINFO_MISC_ALWAYS_SETPAR 0x40000

+/* where the fb is a firmware driver, and can be replaced with a proper one */
+#define FBINFO_MISC_FIRMWARE 0x80000
/*
* Host and GPU endianness differ.
*/
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index d315446..83d7510 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -11,6 +11,7 @@
struct firmware {
size_t size;
const u8 *data;
+ struct page **pages;
};

struct device;
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 52e15e0..e766072 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1098,6 +1098,8 @@ enum ieee80211_category {
WLAN_CATEGORY_SA_QUERY = 8,
WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9,
WLAN_CATEGORY_WMM = 17,
+ WLAN_CATEGORY_MESH_PLINK = 30, /* Pending ANA approval */
+ WLAN_CATEGORY_MESH_PATH_SEL = 32, /* Pending ANA approval */
WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126,
WLAN_CATEGORY_VENDOR_SPECIFIC = 127,
};
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index f1011f7..638ce45 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -653,6 +653,7 @@ struct transaction_s
* waiting for it to finish.
*/
unsigned int t_synchronous_commit:1;
+ unsigned int t_flushed_data_blocks:1;

/*
* For use by the filesystem to store fs-specific data
diff --git a/include/linux/mmc/sdio.h b/include/linux/mmc/sdio.h
index 47ba464..118f029 100644
--- a/include/linux/mmc/sdio.h
+++ b/include/linux/mmc/sdio.h
@@ -94,6 +94,8 @@

#define SDIO_BUS_WIDTH_1BIT 0x00
#define SDIO_BUS_WIDTH_4BIT 0x02
+#define SDIO_BUS_ECSI 0x20 /* Enable continuous SPI interrupt */
+#define SDIO_BUS_SCSI 0x40 /* Support continuous SPI interrupt */

#define SDIO_BUS_CD_DISABLE 0x80 /* disable pull-up on DAT3 (pin 1) */

diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h
index 3d0a9ff..a28c37d 100644
--- a/include/linux/ssb/ssb.h
+++ b/include/linux/ssb/ssb.h
@@ -302,6 +302,7 @@ struct ssb_bus {
u16 chip_id;
u16 chip_rev;
u16 sprom_size; /* number of words in sprom */
+ u16 sprom_offset;
u8 chip_package;

/* List of devices (cores) on the backplane. */
diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h
index 4e27acf..7600f38 100644
--- a/include/linux/ssb/ssb_driver_chipcommon.h
+++ b/include/linux/ssb/ssb_driver_chipcommon.h
@@ -46,6 +46,7 @@
#define SSB_PLLTYPE_7 0x00038000 /* 25Mhz, 4 dividers */
#define SSB_CHIPCO_CAP_PCTL 0x00040000 /* Power Control */
#define SSB_CHIPCO_CAP_OTPS 0x00380000 /* OTP size */
+#define SSB_CHIPCO_CAP_SPROM 0x40000000 /* SPROM present */
#define SSB_CHIPCO_CAP_OTPS_SHIFT 19
#define SSB_CHIPCO_CAP_OTPS_BASE 5
#define SSB_CHIPCO_CAP_JTAGM 0x00400000 /* JTAG master present */
@@ -564,6 +565,7 @@ struct ssb_chipcommon_pmu {
struct ssb_chipcommon {
struct ssb_device *dev;
u32 capabilities;
+ u32 status;
/* Fast Powerup Delay constant */
u16 fast_pwrup_delay;
struct ssb_chipcommon_pmu pmu;
diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h
index 9ae9082..b8be23c 100644
--- a/include/linux/ssb/ssb_regs.h
+++ b/include/linux/ssb/ssb_regs.h
@@ -170,7 +170,8 @@
#define SSB_SPROMSIZE_WORDS_R4 220
#define SSB_SPROMSIZE_BYTES_R123 (SSB_SPROMSIZE_WORDS_R123 * sizeof(u16))
#define SSB_SPROMSIZE_BYTES_R4 (SSB_SPROMSIZE_WORDS_R4 * sizeof(u16))
-#define SSB_SPROM_BASE 0x1000
+#define SSB_SPROM_BASE1 0x1000
+#define SSB_SPROM_BASE31 0x0800
#define SSB_SPROM_REVISION 0x107E
#define SSB_SPROM_REVISION_REV 0x00FF /* SPROM Revision number */
#define SSB_SPROM_REVISION_CRC 0xFF00 /* SPROM CRC8 value */
diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h
index f456534..3e2576d 100644
--- a/include/math-emu/op-common.h
+++ b/include/math-emu/op-common.h
@@ -799,7 +799,7 @@ do { \
X##_e -= (_FP_W_TYPE_SIZE - rsize); \
X##_e = rsize - X##_e - 1; \
\
- if (_FP_FRACBITS_##fs < rsize && _FP_WFRACBITS_##fs < X##_e) \
+ if (_FP_FRACBITS_##fs < rsize && _FP_WFRACBITS_##fs <= X##_e) \
__FP_FRAC_SRS_1(ur_, (X##_e - _FP_WFRACBITS_##fs + 1), rsize);\
_FP_FRAC_DISASSEMBLE_##wc(X, ur_, rsize); \
if ((_FP_WFRACBITS_##fs - X##_e - 1) > 0) \
diff --git a/kernel/futex.c b/kernel/futex.c
index 1ad4fa6..3071911 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -429,20 +429,11 @@ static void free_pi_state(struct futex_pi_state *pi_state)
static struct task_struct * futex_find_get_task(pid_t pid)
{
struct task_struct *p;
- const struct cred *cred = current_cred(), *pcred;

rcu_read_lock();
p = find_task_by_vpid(pid);
- if (!p) {
- p = ERR_PTR(-ESRCH);
- } else {
- pcred = __task_cred(p);
- if (cred->euid != pcred->euid &&
- cred->euid != pcred->uid)
- p = ERR_PTR(-ESRCH);
- else
- get_task_struct(p);
- }
+ if (p)
+ get_task_struct(p);

rcu_read_unlock();

@@ -564,8 +555,8 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
if (!pid)
return -ESRCH;
p = futex_find_get_task(pid);
- if (IS_ERR(p))
- return PTR_ERR(p);
+ if (!p)
+ return -ESRCH;

/*
* We need to look at the task state flags to figure out,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 986519e..fa4bdd4 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -436,6 +436,9 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
/* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
desc->status |= flags;
+
+ if (chip != desc->chip)
+ irq_chip_set_defaults(desc->chip);
}

return ret;
diff --git a/kernel/module.c b/kernel/module.c
index dfa33e8..4b270e6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -870,7 +870,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
mutex_lock(&module_mutex);
/* Store the name of the last unloaded module for diagnostic purposes */
strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
- ddebug_remove_module(mod->name);
free_module(mod);

out:
@@ -1533,6 +1532,9 @@ static void free_module(struct module *mod)
remove_sect_attrs(mod);
mod_kobject_remove(mod);

+ /* Remove dynamic debug info */
+ ddebug_remove_module(mod->name);
+
/* Arch-specific cleanup. */
module_arch_cleanup(mod);

diff --git a/kernel/sched.c b/kernel/sched.c
index 34d924e..a0157c7 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1261,6 +1261,12 @@ static void sched_avg_update(struct rq *rq)
s64 period = sched_avg_period();

while ((s64)(rq->clock - rq->age_stamp) > period) {
+ /*
+ * Inline assembly required to prevent the compiler
+ * optimising this loop into a divmod call.
+ * See __iter_div_u64_rem() for another example of this.
+ */
+ asm("" : "+rm" (rq->age_stamp));
rq->age_stamp += period;
rq->rt_avg /= 2;
}
@@ -1711,9 +1717,6 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)

static void update_h_load(long cpu)
{
- if (root_task_group_empty())
- return;
-
walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
}

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 4c12ddb..5aef51e 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -216,22 +216,34 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr)
return 0;
}

-static int ethtool_set_rxnfc(struct net_device *dev, void __user *useraddr)
+static int ethtool_set_rxnfc(struct net_device *dev,
+ u32 cmd, void __user *useraddr)
{
- struct ethtool_rxnfc cmd;
+ struct ethtool_rxnfc info;
+ size_t info_size = sizeof(info);

if (!dev->ethtool_ops->set_rxnfc)
return -EOPNOTSUPP;

- if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
+ /* struct ethtool_rxnfc was originally defined for
+ * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data
+ * members. User-space might still be using that
+ * definition. */
+ if (cmd == ETHTOOL_SRXFH)
+ info_size = (offsetof(struct ethtool_rxnfc, data) +
+ sizeof(info.data));
+
+ if (copy_from_user(&info, useraddr, info_size))
return -EFAULT;

- return dev->ethtool_ops->set_rxnfc(dev, &cmd);
+ return dev->ethtool_ops->set_rxnfc(dev, &info);
}

-static int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr)
+static int ethtool_get_rxnfc(struct net_device *dev,
+ u32 cmd, void __user *useraddr)
{
struct ethtool_rxnfc info;
+ size_t info_size = sizeof(info);
const struct ethtool_ops *ops = dev->ethtool_ops;
int ret;
void *rule_buf = NULL;
@@ -239,13 +251,22 @@ static int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr)
if (!ops->get_rxnfc)
return -EOPNOTSUPP;

- if (copy_from_user(&info, useraddr, sizeof(info)))
+ /* struct ethtool_rxnfc was originally defined for
+ * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data
+ * members. User-space might still be using that
+ * definition. */
+ if (cmd == ETHTOOL_GRXFH)
+ info_size = (offsetof(struct ethtool_rxnfc, data) +
+ sizeof(info.data));
+
+ if (copy_from_user(&info, useraddr, info_size))
return -EFAULT;

if (info.cmd == ETHTOOL_GRXCLSRLALL) {
if (info.rule_cnt > 0) {
- rule_buf = kmalloc(info.rule_cnt * sizeof(u32),
- GFP_USER);
+ if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32))
+ rule_buf = kmalloc(info.rule_cnt * sizeof(u32),
+ GFP_USER);
if (!rule_buf)
return -ENOMEM;
}
@@ -256,7 +277,7 @@ static int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr)
goto err_out;

ret = -EFAULT;
- if (copy_to_user(useraddr, &info, sizeof(info)))
+ if (copy_to_user(useraddr, &info, info_size))
goto err_out;

if (rule_buf) {
@@ -1111,12 +1132,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GRXCLSRLCNT:
case ETHTOOL_GRXCLSRULE:
case ETHTOOL_GRXCLSRLALL:
- rc = ethtool_get_rxnfc(dev, useraddr);
+ rc = ethtool_get_rxnfc(dev, ethcmd, useraddr);
break;
case ETHTOOL_SRXFH:
case ETHTOOL_SRXCLSRLDEL:
case ETHTOOL_SRXCLSRLINS:
- rc = ethtool_set_rxnfc(dev, useraddr);
+ rc = ethtool_set_rxnfc(dev, ethcmd, useraddr);
break;
case ETHTOOL_GGRO:
rc = ethtool_get_gro(dev, useraddr);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e587e68..e696250 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -945,7 +945,10 @@ static void neigh_update_hhs(struct neighbour *neigh)
{
struct hh_cache *hh;
void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *)
- = neigh->dev->header_ops->cache_update;
+ = NULL;
+
+ if (neigh->dev->header_ops)
+ update = neigh->dev->header_ops->cache_update;

if (update) {
for (hh = neigh->hh; hh; hh = hh->hh_next) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fcd278a..af83bdf 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2037,6 +2037,9 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
int mib_idx;
int fwd_rexmitting = 0;

+ if (!tp->packets_out)
+ return;
+
if (!tp->lost_out)
tp->retransmit_high = tp->snd_una;

diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 5a7f00c..1264ad0 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -95,9 +95,11 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
fl.fl_ip_dport = otcph.source;
security_skb_classify_flow(oldskb, &fl);
dst = ip6_route_output(net, NULL, &fl);
- if (dst == NULL)
+ if (dst == NULL || dst->error) {
+ dst_release(dst);
return;
- if (dst->error || xfrm_lookup(net, &dst, &fl, NULL, 0))
+ }
+ if (xfrm_lookup(net, &dst, &fl, NULL, 0))
return;

hh_len = (dst->dev->hard_header_len + 15)&~15;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4a15df1..5bea319 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -269,12 +269,6 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata,
if (wk->bss->wmm_used)
wmm = 1;

- /* get all rates supported by the device and the AP as
- * some APs don't like getting a superset of their rates
- * in the association request (e.g. D-Link DAP 1353 in
- * b-only mode) */
- rates_len = ieee80211_compatible_rates(wk->bss, sband, &rates);
-
if ((wk->bss->cbss.capability & WLAN_CAPABILITY_SPECTRUM_MGMT) &&
(local->hw.flags & IEEE80211_HW_SPECTRUM_MGMT))
capab |= WLAN_CAPABILITY_SPECTRUM_MGMT;
@@ -309,6 +303,17 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata,
*pos++ = wk->ssid_len;
memcpy(pos, wk->ssid, wk->ssid_len);

+ if (wk->bss->supp_rates_len) {
+ /* get all rates supported by the device and the AP as
+ * some APs don't like getting a superset of their rates
+ * in the association request (e.g. D-Link DAP 1353 in
+ * b-only mode) */
+ rates_len = ieee80211_compatible_rates(wk->bss, sband, &rates);
+ } else {
+ rates = ~0;
+ rates_len = sband->n_bitrates;
+ }
+
/* add all rates which were marked to be used above */
supp_rates_len = rates_len;
if (supp_rates_len > 8)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3ee3cb8..38499c4 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1818,6 +1818,11 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
return RX_CONTINUE;
}
break;
+ case WLAN_CATEGORY_MESH_PLINK:
+ case WLAN_CATEGORY_MESH_PATH_SEL:
+ if (ieee80211_vif_is_mesh(&sdata->vif))
+ return ieee80211_mesh_rx_mgmt(sdata, rx->skb);
+ break;
default:
/* do not process rejected action frames */
if (mgmt->u.action.category & 0x80)
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index fd6411d..169111a 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -62,7 +62,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
bool beacon)
{
struct ieee80211_bss *bss;
- int clen;
+ int clen, srlen;
s32 signal = 0;

if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM)
@@ -94,23 +94,24 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
if (bss->dtim_period == 0)
bss->dtim_period = 1;

- bss->supp_rates_len = 0;
+ /* replace old supported rates if we get new values */
+ srlen = 0;
if (elems->supp_rates) {
- clen = IEEE80211_MAX_SUPP_RATES - bss->supp_rates_len;
+ clen = IEEE80211_MAX_SUPP_RATES;
if (clen > elems->supp_rates_len)
clen = elems->supp_rates_len;
- memcpy(&bss->supp_rates[bss->supp_rates_len], elems->supp_rates,
- clen);
- bss->supp_rates_len += clen;
+ memcpy(bss->supp_rates, elems->supp_rates, clen);
+ srlen += clen;
}
if (elems->ext_supp_rates) {
- clen = IEEE80211_MAX_SUPP_RATES - bss->supp_rates_len;
+ clen = IEEE80211_MAX_SUPP_RATES - srlen;
if (clen > elems->ext_supp_rates_len)
clen = elems->ext_supp_rates_len;
- memcpy(&bss->supp_rates[bss->supp_rates_len],
- elems->ext_supp_rates, clen);
- bss->supp_rates_len += clen;
+ memcpy(bss->supp_rates + srlen, elems->ext_supp_rates, clen);
+ srlen += clen;
}
+ if (srlen)
+ bss->supp_rates_len = srlen;

bss->wmm_used = elems->wmm_param || elems->wmm_info;

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 27c30cf..95682e5 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -146,6 +146,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport);

ct_write_lock(hash);
+ spin_lock(&cp->lock);

if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
list_add(&cp->c_list, &ip_vs_conn_tab[hash]);
@@ -158,6 +159,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
ret = 0;
}

+ spin_unlock(&cp->lock);
ct_write_unlock(hash);

return ret;
@@ -177,6 +179,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport);

ct_write_lock(hash);
+ spin_lock(&cp->lock);

if (cp->flags & IP_VS_CONN_F_HASHED) {
list_del(&cp->c_list);
@@ -186,6 +189,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
} else
ret = 0;

+ spin_unlock(&cp->lock);
ct_write_unlock(hash);

return ret;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 5cdbf7c..b6fcf68 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -238,7 +238,8 @@ struct sock_xprt {
* State of TCP reply receive
*/
__be32 tcp_fraghdr,
- tcp_xid;
+ tcp_xid,
+ tcp_calldir;

u32 tcp_offset,
tcp_reclen;
@@ -961,7 +962,7 @@ static inline void xs_tcp_read_calldir(struct sock_xprt *transport,
{
size_t len, used;
u32 offset;
- __be32 calldir;
+ char *p;

/*
* We want transport->tcp_offset to be 8 at the end of this routine
@@ -970,26 +971,33 @@ static inline void xs_tcp_read_calldir(struct sock_xprt *transport,
* transport->tcp_offset is 4 (after having already read the xid).
*/
offset = transport->tcp_offset - sizeof(transport->tcp_xid);
- len = sizeof(calldir) - offset;
+ len = sizeof(transport->tcp_calldir) - offset;
dprintk("RPC: reading CALL/REPLY flag (%Zu bytes)\n", len);
- used = xdr_skb_read_bits(desc, &calldir, len);
+ p = ((char *) &transport->tcp_calldir) + offset;
+ used = xdr_skb_read_bits(desc, p, len);
transport->tcp_offset += used;
if (used != len)
return;
transport->tcp_flags &= ~TCP_RCV_READ_CALLDIR;
- transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
- transport->tcp_flags |= TCP_RCV_COPY_DATA;
/*
* We don't yet have the XDR buffer, so we will write the calldir
* out after we get the buffer from the 'struct rpc_rqst'
*/
- if (ntohl(calldir) == RPC_REPLY)
+ switch (ntohl(transport->tcp_calldir)) {
+ case RPC_REPLY:
+ transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
+ transport->tcp_flags |= TCP_RCV_COPY_DATA;
transport->tcp_flags |= TCP_RPC_REPLY;
- else
+ break;
+ case RPC_CALL:
+ transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
+ transport->tcp_flags |= TCP_RCV_COPY_DATA;
transport->tcp_flags &= ~TCP_RPC_REPLY;
- dprintk("RPC: reading %s CALL/REPLY flag %08x\n",
- (transport->tcp_flags & TCP_RPC_REPLY) ?
- "reply for" : "request with", calldir);
+ break;
+ default:
+ dprintk("RPC: invalid request message type\n");
+ xprt_force_disconnect(&transport->xprt);
+ }
xs_tcp_check_fraghdr(transport);
}

@@ -1009,12 +1017,10 @@ static inline void xs_tcp_read_common(struct rpc_xprt *xprt,
/*
* Save the RPC direction in the XDR buffer
*/
- __be32 calldir = transport->tcp_flags & TCP_RPC_REPLY ?
- htonl(RPC_REPLY) : 0;
-
memcpy(rcvbuf->head[0].iov_base + transport->tcp_copied,
- &calldir, sizeof(calldir));
- transport->tcp_copied += sizeof(calldir);
+ &transport->tcp_calldir,
+ sizeof(transport->tcp_calldir));
+ transport->tcp_copied += sizeof(transport->tcp_calldir);
transport->tcp_flags &= ~TCP_RCV_COPY_CALLDIR;
}

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 801a16a..03efeab 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1311,7 +1311,7 @@ static unsigned int *reloc_location(struct elf_info *elf,
int section = sechdr->sh_info;

return (void *)elf->hdr + sechdrs[section].sh_offset +
- (r->r_offset - sechdrs[section].sh_addr);
+ r->r_offset - sechdrs[section].sh_addr;
}

static int addend_386_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index 1305f7c..641d7f0 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -1821,7 +1821,9 @@ static irqreturn_t snd_echo_interrupt(int irq, void *dev_id)
/* The hardware doesn't tell us which substream caused the irq,
thus we have to check all running substreams. */
for (ss = 0; ss < DSP_MAXPIPES; ss++) {
- if ((substream = chip->substream[ss])) {
+ substream = chip->substream[ss];
+ if (substream && ((struct audiopipe *)substream->runtime->
+ private_data)->state == PIPE_STATE_STARTED) {
period = pcm_pointer(substream) /
substream->runtime->period_size;
if (period != chip->last_period[ss]) {
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 82a53d9..aa2ec23 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8942,6 +8942,7 @@ static struct snd_pci_quirk alc882_ssid_cfg_tbl[] = {
SND_PCI_QUIRK(0x106b, 0x3800, "MacbookPro 4,1", ALC885_MBP3),
SND_PCI_QUIRK(0x106b, 0x3e00, "iMac 24 Aluminum", ALC885_IMAC24),
SND_PCI_QUIRK(0x106b, 0x3f00, "Macbook 5,1", ALC885_MB5),
+ SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC885_MB5),
/* FIXME: HP jack sense seems not working for MBP 5,1 or 5,2,
* so apparently no perfect solution yet
*/
diff --git a/sound/soc/codecs/wm8776.c b/sound/soc/codecs/wm8776.c
index a9829aa..8286c62 100644
--- a/sound/soc/codecs/wm8776.c
+++ b/sound/soc/codecs/wm8776.c
@@ -93,7 +93,6 @@ SOC_DAPM_SINGLE("Bypass Switch", WM8776_OUTMUX, 2, 1, 0),

static const struct snd_soc_dapm_widget wm8776_dapm_widgets[] = {
SND_SOC_DAPM_INPUT("AUX"),
-SND_SOC_DAPM_INPUT("AUX"),

SND_SOC_DAPM_INPUT("AIN1"),
SND_SOC_DAPM_INPUT("AIN2"),
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 43cf3ea..a31a8cd 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -48,6 +48,9 @@ static inline void callchain_init(struct callchain_node *node)
INIT_LIST_HEAD(&node->brothers);
INIT_LIST_HEAD(&node->children);
INIT_LIST_HEAD(&node->val);
+
+ node->parent = NULL;
+ node->hit = 0;
}

static inline u64 cumul_hits(struct callchain_node *node)
--
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/

Next message: Greg KH: "Re: Linux 2.6.27.49"
Previous message: Greg KH: "Linux 2.6.32.17"
In reply to: Greg KH: "Linux 2.6.32.17"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]